CN112084648B

CN112084648B - Method and device for predicting residual service life of equipment and electronic equipment

Info

Publication number: CN112084648B
Application number: CN202010917255.XA
Authority: CN
Inventors: 孙泽懿; 祝彦森; 孙靖文; 徐凯波
Original assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Current assignee: Shanghai Minglue Artificial Intelligence Group Co Ltd
Priority date: 2020-09-03
Filing date: 2020-09-03
Publication date: 2024-05-24
Anticipated expiration: 2040-09-03
Also published as: CN112084648A

Abstract

The application provides a method and a device for predicting the residual service life of equipment and electronic equipment, and belongs to the technical field of equipment service life prediction. The method comprises the following steps: determining the equipment to be converted from a first operation stage to a second operation stage in a plurality of operation stages, wherein the operation stages are obtained by dividing the use state of the equipment according to the equipment abrasion degree; acquiring operation parameters of the equipment in the second operation stage; predicting a second remaining useful life of the device based on the operating parameters; and replacing the first residual service life corresponding to the first operation stage with the second residual service life to serve as a target residual service life of the equipment, wherein the target residual service life is used for maintaining the equipment. By adopting the technical scheme provided by the application, the problem of low prediction accuracy of the residual service life of the equipment can be solved.

Description

Method and device for predicting residual service life of equipment and electronic equipment

Technical Field

The present application relates to the field of equipment life prediction technologies, and in particular, to a method and an apparatus for predicting a remaining service life of an equipment, and an electronic device.

Background

The remaining service life of a device refers to the length of time that the device can operate before failing and failing to continue operation. The residual service life of the equipment is predicted, so that a maintenance strategy can be conveniently formulated according to a prediction result, and the normal operation of the equipment is ensured to the maximum extent, thereby avoiding the problems of economic loss, casualties, environmental damage and the like caused by equipment faults.

In the related art, when calculating the remaining service life of a certain device, the average service life of the device of the type can be determined by counting the service lives of devices belonging to the same type as the device. The difference between the average service life and the length of time the device has been operated can then be taken as the remaining service life of the device.

However, the running environment and the task to be executed of different devices are different, and the remaining service life is determined by adopting the mode of counting the average service life, so that the prediction accuracy of the remaining service life is low.

Disclosure of Invention

The embodiment of the application aims to provide a method and a device for predicting the residual service life of equipment, electronic equipment and a storage medium, so as to solve the problem of low accuracy of predicting the residual service life of the equipment. The specific technical scheme is as follows:

in a first aspect, there is provided a method of predicting remaining useful life of a device, the method comprising:

Determining the equipment to be converted from a first operation stage to a second operation stage in a plurality of operation stages, wherein the operation stages are obtained by dividing the use state of the equipment according to the equipment abrasion degree;

Acquiring operation parameters of the equipment in the second operation stage;

Predicting a second remaining useful life of the device based on the operating parameters;

And replacing the first residual service life corresponding to the first operation stage with the second residual service life to serve as a target residual service life of the equipment, wherein the target residual service life is used for maintaining the equipment.

Optionally, the determining device transitions from a first operation phase to a second operation phase of the plurality of operation phases, including:

And receiving an operation phase conversion instruction, wherein the operation phase conversion instruction is used for indicating the equipment to be converted from the first operation phase to the second operation phase.

acquiring current operation parameters of the equipment;

acquiring a parameter interval and an operation stage which correspond to the equipment and have a corresponding relation;

Determining a target parameter interval in which the operation parameter falls in the parameter interval;

And under the condition that the target operation phase corresponding to the target parameter interval is different from the first operation phase corresponding to the equipment, determining the target operation phase as the second operation phase, and determining that the equipment is converted from the first operation phase to the second operation phase.

collecting a plurality of operating parameters in a current operating phase;

Calculating a change curve of the operation parameters along with time change based on the operation parameters and the acquisition time of each operation parameter;

calculating the similarity between the change curve and the change curve corresponding to the first operation stage;

and under the condition that the similarity is smaller than a preset similarity threshold, determining that the equipment is switched from the first operation stage to the second operation stage.

acquiring operation parameters of the equipment, wherein the types of the operation parameters are at least two;

determining, for each operating parameter, whether the device transitions from the first operating phase to the second operating phase based on such operating parameter, resulting in a determination corresponding to such operating parameter;

according to the corresponding determination results of the at least two operation parameters, calculating the probability of the equipment switching from the first operation stage to the second operation stage;

and determining that the equipment is converted from the first operation stage to the second operation stage under the condition that the probability is larger than a preset probability threshold value.

Optionally, the predicting the second remaining service life of the device based on the operating parameter includes:

acquiring a first calculation model, wherein the first calculation model is used for predicting the residual service life;

Acquiring the running time of the equipment;

Updating function parameters of the first calculation model based on the running time to obtain a second calculation model, and replacing the first calculation model by using the second calculation model as a target calculation model of the equipment;

and predicting the second residual service life through the target calculation model and the operation parameters of the equipment.

In a second aspect, there is provided an apparatus for predicting the remaining useful life of a device, the apparatus comprising:

The device comprises a determining module, a judging module and a judging module, wherein the determining module is used for determining that the device is converted from a first operation stage to a second operation stage in a plurality of operation stages, and the operation stages are obtained by dividing the use state of the device according to the wear degree of the device;

the acquisition module is used for acquiring the operation parameters of the equipment in the second operation stage;

a prediction module for predicting a second remaining useful life of the device based on the operating parameter;

and the replacing module is used for replacing the first residual service life corresponding to the first operation stage by using the second residual service life as a target residual service life of the equipment, wherein the target residual service life is used for maintaining the equipment.

Optionally, the determining module is configured to receive an operation phase conversion instruction, where the operation phase conversion instruction is configured to instruct the device to convert from the first operation phase to the second operation phase.

Optionally, the determining module includes:

the first acquisition submodule is used for acquiring current operation parameters of the equipment;

the second acquisition sub-module is used for acquiring a parameter interval and an operation stage which correspond to the equipment and have a corresponding relation;

the first determining submodule is used for determining a target parameter interval in which the operation parameter falls in the parameter interval;

And the second determining submodule is used for determining the target operation stage as the second operation stage and determining that the equipment is converted from the first operation stage to the second operation stage when the target operation stage corresponding to the target parameter interval is different from the first operation stage corresponding to the equipment.

Optionally, the determining module includes:

an acquisition sub-module for acquiring a plurality of operating parameters in a current operating phase;

A first calculation sub-module, configured to calculate a change curve of an operation parameter according to time change based on the plurality of operation parameters and an acquisition time of each operation parameter;

the second calculation sub-module is used for calculating the similarity between the change curve and the change curve corresponding to the first operation stage;

And the third determining submodule is used for determining that the equipment is switched from the first operation stage to the second operation stage under the condition that the similarity is smaller than a preset similarity threshold value.

Optionally, the determining module includes:

A third obtaining sub-module, configured to obtain operation parameters of the device, where the types of the operation parameters are at least two;

A fourth determining sub-module for determining, for each operating parameter, whether the apparatus transitions from the first operating phase to the second operating phase based on such operating parameter, resulting in a determination result corresponding to such operating parameter;

A third calculation sub-module, configured to calculate, according to a determination result corresponding to the at least two operation parameters, a probability of the device transitioning from the first operation stage to the second operation stage;

and a fifth determining sub-module, configured to determine that the device transitions from the first operation phase to the second operation phase when the probability is greater than a preset probability threshold.

Optionally, the prediction module includes:

The fourth acquisition sub-module is used for acquiring a first calculation model, and the first calculation model is used for predicting the residual service life;

A fifth acquisition sub-module for acquiring the already running time of the device;

An updating sub-module, configured to update function parameters of the first computing model based on the executed time, obtain a second computing model, and replace the first computing model with the second computing model to serve as a target computing model of the device;

And the prediction sub-module is used for predicting the second residual service life through the target calculation model and the operation parameters of the equipment.

In a third aspect, an electronic device is provided, including a processor, a communication interface, a memory, and a communication bus, where the processor, the communication interface, and the memory complete communication with each other through the communication bus;

a memory for storing a computer program;

A processor for implementing the method steps of any of the first aspects when executing a program stored on a memory.

In a fourth aspect, a computer-readable storage medium is provided, in which a computer program is stored which, when being executed by a processor, carries out the method steps of any of the first aspects.

In a fifth aspect, there is provided a computer program product comprising instructions which, when run on a computer, cause the computer to perform any of the above described method of predicting remaining life of a device.

The embodiment of the application has the beneficial effects that:

The embodiment of the application provides a method and a device for predicting the residual life of equipment, electronic equipment and a storage medium. In the application, after the equipment is determined to be converted from a first operation stage to a second operation stage in a plurality of operation stages, the operation parameters of the equipment in the second operation stage are obtained, wherein the plurality of operation stages are obtained by dividing the use state of the equipment according to the equipment abrasion degree. And then, predicting the second residual service life of the equipment based on the operation parameters, and replacing the first residual service life corresponding to the first operation stage with the second residual service life to serve as the target residual service life of the equipment, wherein the target residual service life is used for maintaining the equipment.

Because the operation parameters of the equipment are used as influencing factors for predicting the residual service life, when the equipment enters the second operation stage, the residual service life is calculated based on the operation parameters in the second operation stage, so that the calculated residual service life is more in line with the actual operation condition of the equipment, and the prediction accuracy of the residual service life can be improved.

Of course, it is not necessary for any one product or method of practicing the application to achieve all of the advantages set forth above at the same time.

Drawings

In order to more clearly illustrate the embodiments of the application or the technical solutions of the prior art, the drawings which are used in the description of the embodiments or the prior art will be briefly described, and it will be obvious to a person skilled in the art that other drawings can be obtained from these drawings without inventive effort.

FIG. 1 is a schematic illustration of an operational phase provided by an embodiment of the present application;

FIG. 2 is a flowchart of a method for predicting a remaining service life of a device according to an embodiment of the present application;

FIG. 3 is a schematic diagram of a step of predicting remaining service life by using a calculation model according to an embodiment of the present application;

FIG. 4 is a schematic diagram of a multi-stage PHM model according to an embodiment of the present application;

FIG. 5 is a schematic structural diagram of a device for predicting the remaining service life of equipment according to an embodiment of the present application;

fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the present application.

Detailed Description

The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.

The embodiment of the application provides a method for predicting the residual service life of equipment, which can be applied to any equipment with a data processing function. For example, the device having the data processing function may specifically include a desktop computer, a portable computer, an internet television, a smart mobile terminal, a wearable smart terminal, and the like. Any device capable of implementing the embodiments of the present application belongs to the protection scope of the embodiments of the present application, and is not limited herein.

When predicting the residual service life of a certain mechanical device, if the mechanical device has a data processing function, the mechanical device can be used as the device for realizing the embodiment of the application; if the machine does not have data processing functionality, the operating parameters of the machine may be obtained by another device having data processing functionality and a prediction of the remaining useful life of the machine may be made.

Researchers have found that during actual production the wear process of the equipment is not static and that at the end of the life of the equipment there is an accelerated ageing phenomenon, i.e. the closer to the end of the life of the equipment the faster the wear rate of the equipment. Thus, the lifecycle of a device may be divided into a plurality of operational phases based on the device wear level of the device.

The wear of the device may be expressed by different indicators, for example, the wear of the device may be expressed by the size of the device, which may change as the device ages and wears; the wear degree of the equipment can be expressed by the operation parameters in the working process of the equipment, and the operation parameters of the equipment can be changed along with the aging and the wear of the equipment.

Taking the equipment as a drill bit for example, the thrust force exerted by the drill bit in the working process can be used for representing the abrasion degree of the equipment. Dividing the aging and abrasion process of the drill bit according to the thrust force of the drill bit in the working process to obtain a plurality of stages. Fig. 1 is a schematic diagram of an operation stage according to an embodiment of the present application, where a plurality of operation stages obtained by dividing the aging and wear degrees of a drill bit according to thrust forces applied to the drill bit during operation are shown.Representing the separate time points of run phase n and run phase n+1,/>Representing the covariates detected during run phase n, i.e., the thrust of the drill bit. The value of n can be 0, 1,2,3,4 … ….

Because the residual service life of the equipment is predicted based on a plurality of operation stages, the abrasion aging degree of the equipment in different operation stages can be captured, the calculated residual service life is more in line with the actual operation condition of the equipment, and the prediction accuracy of the residual service life can be improved. Further, the possibility of overestimating the remaining service life can be effectively reduced, and the phenomenon of continuing to use the device after exceeding the remaining service life is avoided, thereby reducing the occurrence of catastrophic failure.

For ease of understanding, the terms involved in the embodiments of the present application will be described first:

The proportional risk regression model (Proportional Hazards Model, PHM model) is a semi-parametric regression model proposed by United kingdom statistician. The model takes survival ending and survival time as strain quantity, can analyze the influence of a plurality of factors on survival time at the same time, can analyze data with the truncated survival time, and does not need to estimate the survival distribution type of the data. Because of the excellent properties, the model has been widely applied in medical follow-up study since the advent of the model, and is the most widely applied multi-factor analysis method in survival analysis so far.

Residual life prediction (REMAINING USEFUL LIFE PREDICTION): the residual service life prediction is an important task in the field of equipment maintenance, and is generally performed according to the reliability theory and collected data related to the operation and health degree of equipment.

The following will describe in detail a method for predicting the remaining service life of an apparatus according to an embodiment of the present application with reference to a specific embodiment, as shown in fig. 2, the specific steps are as follows:

Step 201, determining that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases.

In practice, the manner in which the device is determined to transition from a first operational stage to a second operational stage of the plurality of operational stages may be varied, and in one possible implementation, the device may be determined to transition from the first operational stage to the second operational stage based on the received instructions. The specific processing will be described in detail later.

In another possible implementation, there may be multiple ways of partitioning the operational phases, and the ways in which the device is determined to transition from the first operational phase to the second operational phase may be different for different partitioning ways.

The embodiment of the application provides two dividing modes of operation stages, which are respectively as follows: dividing the rated service life of equipment to obtain a plurality of operation stages; and determining a plurality of operation stages according to the change condition of the operation parameters.

In a first mode, the device may be determined to switch from the first operation stage to the second operation stage according to the operation time length of the device, and the specific processing procedure includes: the rated service life of the equipment is divided to obtain a plurality of time length thresholds, and each time length threshold corresponds to one operation stage.

When predicting the residual service life of a certain device, the running time length of the device can be compared with a plurality of time length thresholds, and the maximum time length threshold reached by the running time length is obtained. If the maximum duration threshold is different from the maximum duration threshold reached when the last prediction of remaining useful life was made, it is determined that the device transitions from the first operational phase to the second operational phase.

For example, the rated service life of the drill bit is 6 months, and the rated service life of the drill bit is divided to obtain three duration thresholds of 2 months, 3 months and 5 months, wherein the three duration thresholds correspond to three operation phases respectively. The current running duration of the drill bit is 3 months, and when the residual service life of the drill bit is predicted, the running duration of the drill bit can be compared with a plurality of duration thresholds to obtain a maximum duration threshold value reached by the running duration, namely 3 months. Since the maximum duration threshold is 2 months different from the maximum duration threshold reached when the last prediction of remaining useful life was made, it may be determined that the drill bit transitioned from the first operational phase to the second operational phase.

In the second mode, it may be determined that the apparatus is to be shifted from the first operation stage to the second operation stage according to the change condition of the operation parameter. The specific determination may be varied, for example, parameter thresholds for a plurality of operating parameters may be set, each parameter threshold corresponding to one operating phase. When the residual service life of a certain device is predicted, the current operation parameter of the device can be compared with a plurality of parameter thresholds, and the maximum parameter threshold reached by the current operation parameter is obtained. If the maximum parameter threshold is different from the maximum parameter threshold reached when the last prediction of remaining useful life was made, it is determined that the device transitions from the first operational phase to the second operational phase.

Taking the equipment as a drill bit and the operation parameters as thrust as an example, three thrust thresholds of 10N, 15N and 30N can be set, and the three thrust thresholds respectively correspond to three operation stages. The current operation parameter of the drill bit is 15N, and when the residual service life of the drill bit is predicted, the current operation parameter of the drill bit can be compared with a plurality of parameter thresholds to obtain the maximum parameter threshold value which is 15N and reached by the current operation parameter. Since the maximum parameter threshold is different from the maximum parameter threshold 10N reached when the last prediction of remaining useful life was made, it may be determined that the drill bit is transitioning from the first operational phase to the second operational phase.

Other implementations of the device transition from the first operating phase to the second operating phase are determined based on the change in the operating parameter, as will be described later.

Alternatively, other dividing modes may be used to divide the usage state of the device according to the wear level of the device to obtain multiple operation phases, and the specific dividing mode is not limited herein.

In the embodiment of the present application, the first operation stage may refer to an operation stage determined when the last prediction of the remaining service life is performed, the second operation stage is a different operation stage from the first operation stage, the first operation stage and the second operation stage are only used for distinguishing the operation stages, and specific names of the first operation stage and the second operation stage are not limited herein.

Step 202, acquiring operation parameters of the equipment in a second operation stage.

In practice, the operating parameters of the device in the second operating phase may be obtained in a plurality of ways, and in one possible implementation, the operating parameters of the device in the second operating phase may be obtained by means of real-time acquisition; in another possible implementation, the operating parameters of the device in the second operating phase may be pre-acquired and stored locally, in which case the operating parameters of the device in the second operating phase may be obtained by reading the locally stored operating parameters.

Step 203, predicting a second remaining useful life of the device based on the operating parameters.

In an implementation, for the second operation phase, the current remaining service life of the device may be predicted based on the acquired operation parameters, resulting in a second remaining service life.

In the embodiment of the present application, the remaining service life of the computing device may be calculated by using a computing model, and the computing model may be a proportional risk regression model, and any model having a function of predicting the remaining service life may be used as the computing model in the embodiment of the present application, which is not specifically limited herein. The specific processing of the remaining useful life of the computing device using the computational model will be described later.

Step 204, replacing the first remaining service life corresponding to the first operation stage with the second remaining service life to serve as the target remaining service life of the device.

Wherein the target remaining useful life is for maintenance of the device.

And replacing the first residual service life corresponding to the first operation stage by using the second residual service life as the target residual service life of the equipment, so that the target residual service life can be updated. Furthermore, by updating the target remaining service life, the user of the device can be prevented from continuing to use the device after exceeding the target remaining service life, so that accidents can be avoided.

Meanwhile, in the case that the experience values of the remaining service lives of the same type of equipment in different operation phases are obtained in advance, the target remaining service lives of the current equipment can be compared with the experience values of the remaining service lives in the same operation phase. Then, a maintenance mode of the current equipment can be formulated according to the comparison result.

In the embodiment of the application, the operation parameters of the equipment in the second operation stage can be acquired after the equipment is determined to be converted from the first operation stage to the second operation stage in the plurality of operation stages. Then, a second remaining service life of the device is predicted based on the operating parameters, and the second remaining service life is used to replace the first remaining service life corresponding to the first operating stage as a target remaining service life of the device.

Because the operation parameters of the equipment are used as influencing factors for predicting the residual service life, when the equipment enters the second operation stage, the residual service life is calculated based on the operation parameters in the second operation stage, so that the calculated residual service life is more in line with the actual operation condition of the equipment, and the prediction accuracy of the residual service life can be improved. Further, the possibility of overestimating the remaining service life can be effectively reduced, and the phenomenon of continuing to use the device after exceeding the remaining service life is avoided, thereby reducing the occurrence of catastrophic failure.

Optionally, an embodiment of the present application provides an implementation manner for determining, according to a received instruction, a transition of a device from a first operation stage to a second operation stage, including: and receiving an operation phase conversion instruction. The operation phase conversion instruction is used for indicating the equipment to be converted from the first operation phase to the second operation phase.

In practice, the user of the device may determine, based on actual operating experience, that the device is to be shifted from the first operating phase to the second operating phase, in which case the user may issue an operating phase shift instruction. Thus, it may be determined that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases based on the received instructions.

For example, the operating parameters of the device may be acquired by an acquisition device having an operating parameter acquisition function. The acquisition device can output the acquired operation parameters, and a user of the equipment can determine the operation stage of the equipment according to the change of the operation parameters.

The change in the operating parameter may refer to a deviation value between the operating parameter and a preset operating parameter, and when the user determines that the deviation value exceeds a preset deviation value threshold, it may be determined that the apparatus transitions from the first operating phase to the second operating phase. The change in the operating parameter may also refer to a speed of the change in the operating parameter over time, and when the user determines that the speed exceeds a preset speed threshold, it may be determined that the device transitions from the first operating phase to the second operating phase.

Optionally, the collecting device can automatically collect the operation parameters of the equipment according to a preset collecting period, and the collecting device can collect the operation parameters of the equipment after receiving the collecting instruction. Any device with an operation parameter collection function can be used as the collection device, and the embodiment of the application is not particularly limited.

In the embodiment of the application, on one hand, the device is determined to be converted from the first operation stage to the second operation stage by receiving the operation stage conversion instruction, so that the determination of operation stage conversion can be realized quickly and conveniently. On the other hand, since the operation phase transition instruction is issued by the user based on the actual operation experience, by receiving the operation phase transition instruction, the operation phase transition instruction determining apparatus transitions from the first operation phase to the second operation phase, it is possible to ensure the accuracy of determining that the operation phase transition has occurred.

Optionally, although the operation parameters of the device may change along with the aging and abrasion degree of the device, the change amplitude of the operation parameters in the same operation stage is small, so that the parameter range of the operation parameters can be divided according to actual operation experience to obtain a plurality of parameter intervals. Each parameter interval can correspond to one operation stage, so that the corresponding relation between the parameter interval and the operation stage can be obtained.

The embodiment of the application provides an implementation mode for determining equipment to be converted from a first operation stage to a second operation stage based on the corresponding relation between a parameter interval and the operation stage and the current operation parameters of the equipment, which comprises the following steps:

Step1, acquiring current operation parameters of equipment.

In practice, the current operating parameters of the device may be acquired by the acquisition means.

Optionally, the collecting device may collect the operation parameters of the device according to a preset collection period; the acquisition device can also acquire the operation parameters of the equipment after receiving the acquisition instruction.

And 2, acquiring a parameter interval and an operation stage which correspond to the equipment and have a corresponding relation.

In implementation, parameter intervals and operation phases corresponding to various devices and having corresponding relations can be stored. The parameter interval and the operation stage which correspond to the current equipment and have the corresponding relation can be searched in the parameter interval and the operation stage which correspond to the various equipment and have the corresponding relation. The current equipment is the equipment with the residual service life to be predicted.

The parameter section and the operation phase having the correspondence relationship may be stored locally, whereby the correspondence relationship may be read from the local. Or the parameter section and the operation phase having the correspondence relationship may be stored on another device, whereby the correspondence relationship may be acquired from the other device.

And step 3, determining a target parameter interval in which the operation parameter falls in the parameter interval.

In implementation, a parameter interval with a corresponding relationship and a plurality of parameter intervals included in an operation stage can be determined, and then, a parameter interval in which a current operation parameter of the device falls in the plurality of parameter intervals can be determined, so as to obtain a target parameter interval. Then, the operation phase corresponding to the target parameter interval can be used as the target operation phase.

And 4, determining the target operation stage as a second operation stage and determining that the equipment is converted from the first operation stage to the second operation stage under the condition that the target operation stage corresponding to the target parameter interval is different from the first operation stage corresponding to the equipment.

In implementations, a first operational phase of the target operational phase corresponding to the device may be compared, and in the event that the target operational phase is different from the first operational phase, the target operational phase may be determined to be a second operational phase, and a transition of the device from the first operational phase to the second operational phase may be determined. In the case where the target operation phase is the same as the first operation phase, no subsequent processing may be performed.

In the embodiment of the application, the operation phase corresponding to the current operation parameter of the equipment is determined according to the parameter interval and the operation phase corresponding to the equipment and having the corresponding relation, so that the current target operation phase of the equipment can be accurately determined. Further, based on the comparison of the determined target operation stage and the first operation stage corresponding to the device, whether the device is switched from the first operation stage to the second operation stage is determined, so that accuracy of determining that operation stage switching occurs can be ensured.

Optionally, the wear speeds of the devices in different operation phases are different, so that the operation period of the devices can be divided according to the time-dependent change of the operation parameters, so as to obtain a plurality of operation phases. Further, for each operation phase, a change curve indicating the time-dependent change of the operation parameter in that operation phase may be stored in advance.

When the change curve determined based on the operation parameters is significantly different from the change curve corresponding to the first operation phase, it may be confirmed that the apparatus is shifted from the first operation phase to the second operation phase. Thus, the process of determining the transition of the device from the first operating phase to the second operating phase based on the change in the operating parameter and the corresponding change profile for each operating phase comprises:

Step one, collecting a plurality of operation parameters in the current operation stage.

In practice, a plurality of operating parameters can be acquired at the current operating stage by the acquisition device, and the acquisition time for acquiring each operating parameter is recorded.

Alternatively, the manner of collecting the plurality of operating parameters at the current operating stage may be various, for example, the plurality of operating parameters may be collected at a preset collecting interval, or the plurality of operating parameters may be collected randomly.

And step two, calculating a change curve of the operation parameters along with time change based on the plurality of operation parameters and the acquisition time of each operation parameter.

And thirdly, calculating the similarity between the change curve and the change curve corresponding to the first operation stage.

In implementation, a first operation phase corresponding to the device may be determined, and a change curve corresponding to the first operation phase may be obtained. As shown in fig. 1, the curve indicated by AB in the diagram may represent a corresponding change curve for the first operating phase.

Then, a similarity between the determined change curve and the change curve corresponding to the first operation stage may be calculated. Then, the calculated similarity may be compared with a preset similarity threshold. And under the condition that the similarity is not smaller than a preset similarity threshold value, determining the current operation stage as the first operation stage.

And step four, determining that the equipment is switched from the first operation stage to the second operation stage under the condition that the similarity is smaller than a preset similarity threshold value.

In an implementation, in the event that the similarity is less than a preset similarity threshold, it may be determined that the current operational phase is not the first operational phase, and the device transitions from the first operational phase to the second operational phase.

In the embodiment of the application, the change curve of the operation parameters along with time is calculated based on the plurality of operation parameters acquired in the current operation stage and the acquisition time of each operation parameter, and the similarity between the change curve and the change curve corresponding to the first operation stage is calculated, so that the change condition of the operation parameters in the current operation stage can be compared with the change condition in the first operation stage. Further, under the condition that the similarity is smaller than a preset similarity threshold, the device is determined to be switched from the first operation stage to the second operation stage, and the accuracy of determining that the operation stage is switched can be ensured.

Alternatively, the types of operation parameters affecting the remaining service life of the device may be at least two, in which case at least two operation parameters may be obtained, and based on the at least two operation parameters, determining whether the device transitions from the first operation phase to the second operation phase, the specific process includes:

And (1) acquiring the operation parameters of the equipment.

In practice, a parameter value for each of at least two operating parameters of the device may be obtained for that operating parameter.

And (2) determining whether the equipment is switched from the first operation stage to the second operation stage according to each operation parameter based on the operation parameters, and obtaining a determination result corresponding to the operation parameters.

In implementation, for each operation parameter, the manner described in the above steps 1 to 4 may be adopted, or the manner described in the above steps one to four may be adopted to determine whether the device is switched from the first operation stage to the second operation stage, so as to obtain a determination result corresponding to the operation parameter.

And (3) calculating the probability of the equipment switching from the first operation stage to the second operation stage according to the corresponding determination results of at least two operation parameters.

In an implementation, weights may be set for each operating parameter, and a probability of the device transitioning from the first operating phase to the second operating phase may be calculated based on the weights corresponding to each operating parameter and the determination corresponding to each operating parameter.

After calculating the probability of the device transitioning from the first operational phase to the second operational phase, the calculated probability may be compared to a preset probability threshold. When the preset probability threshold is 1, the condition that the determination result of each operation parameter indicates that the equipment is converted from the first operation stage to the second operation stage is indicated, and the equipment is determined to be converted from the first operation stage to the second operation stage.

And (4) determining that the equipment is switched from the first operation stage to the second operation stage under the condition that the probability is larger than a preset probability threshold value.

And under the condition that the calculated probability is not greater than a preset probability threshold value, determining the current operation stage of the equipment as a first operation stage.

For example, two operating parameters of the device may be obtained, operating parameter a and operating parameter B, respectively. The weight of the operation parameter A is 0.6, the weight of the operation parameter B is 0.4, and the corresponding determination result of the operation parameter A is that the equipment is converted from a first operation stage to a second operation stage and is recorded as 1; the corresponding determination result of the operation parameter B is that the current operation stage is still the first operation stage, and is recorded as 0.

The probability of the device transitioning from the first operation phase to the second operation phase may be calculated according to the determination result and the weight corresponding to the two operation parameters, to obtain 0.6, and then the calculated probability may be compared with a preset probability threshold value of 0.5. Since the probability 0.6 is greater than the preset probability threshold value 0.5, it may be determined that the device transitions from the first operation phase to the second operation phase.

In the embodiment of the application, under the condition that at least two operation parameters influencing the residual service life of the equipment exist, determining results corresponding to each operation parameter are respectively determined, and then the probability of the equipment switching from the first operation stage to the second operation stage is calculated according to the determining results corresponding to each operation parameter. Therefore, the influence of at least two operation parameters on the residual service life of the equipment can be comprehensively considered, and the accuracy of determining the occurrence of operation stage conversion can be ensured.

Optionally, an embodiment of the present application further provides an implementation manner for predicting a remaining service life based on a calculation model and an operation parameter, as shown in fig. 3, including the following steps:

The acquired operating parameters may be used as covariates based on which fitting parameters are calculated. The specific calculation process is as follows: 1) Calculating the conditional failure probability; at a given point in time, the mortality of components in the device that have not failed is obtained, and then, the sum of the mortality of components that have not failed is calculated, and the mortality of each component is divided by the sum to obtain the conditional failure probability of the component. 2) And calculating a partial maximum likelihood function, and taking the product of the conditional failure probabilities of all the components as the partial maximum likelihood function. 3) And taking the logarithm of the partial maximum likelihood function and maximizing the logarithm to obtain fitting parameters.

After the fitting parameters are calculated, the equipment risk rate can be calculated. The specific calculation process is as follows: 1) The covariates are multiplied together with the fitting parameters to yield relative risk factors, which can be expressed in an exponential form as a linear combination of the different covariates detected during wear. 2) The basic risk rate is calculated, and since the service life of the device is subject to random distribution, the basic risk rate can be calculated based on random distribution, wherein the random distribution can be exponential distribution, weibull distribution (Weber distribution), and the like, and the embodiment of the application is not particularly limited. In addition, the base risk may also be calculated by means of a non-parametric estimation, which may be a partial maximum likelihood estimation. 3) And multiplying the relative risk coefficient by the basic risk rate to obtain the equipment risk rate.

Since the equipment risk is the first derivative of the failure function, the failure function can be obtained by integrating the equipment risk. The survival function can then be calculated by the formula survival function = 1-failure function. And then, the remaining service life of the survival function computing equipment in each operation stage is reused, and the remaining service life of the last operation stage is the second remaining service life.

For example, the service life of the device follows a random distribution, and F (t) may be used to represent a cumulative distribution function of the service life of the device, i.e., a failure function of the device. F (t) for a device may represent the probability that the lifetime of the device does not exceed t. The probability density function of the lifetime distribution, i.e. the equipment risk, is denoted by f (t). Since the equipment risk F (t) is the first derivative of the failure function F (t), the failure function F (t) can be calculated by integrating the equipment risk F (t).

The survival function, i.e. the probability that the lifetime of the device is greater than t, is denoted by S (t). S (t) =1-F (t). And then the RUL (REMAINING USEFUL LIFE, the residual service life) can be calculated according to the survival function S (t), namely, the second residual service life.

Alternatively, a PHM model may be employed as the calculation model. In the related art, considering that the equipment is worn in the use process, a single-stage PHM model is adopted to predict the residual service life of the equipment, namely, a set of fitting parameters is adopted to calculate the life cycle of the whole equipment operation. The single-phase PHM model assumes that the wear process of the device is a static process. However, in the practical application process, an accelerated aging phenomenon exists at the end of the use period of the equipment, and the residual service life of the equipment is overestimated by adopting a single-stage PHM model to predict the residual service life.

According to the method for predicting the residual service life, provided by the embodiment of the application, the life cycle of equipment can be divided into a plurality of different aging and abrasion stages, a multi-stage PHM model shown in figure 4 can be utilized, and the PHM model and the operation parameters in the operation stages are adopted for predicting the residual service life for each operation stage. Therefore, the wear aging conditions of the equipment in different operation stages can be accurately captured, and further the wear aging process of the equipment in a plurality of operation stages can be described. Meanwhile, the calculated residual service life is more in line with the actual running condition of the equipment, and the prediction accuracy of the residual service life can be improved.

Optionally, a calculation model used for predicting the remaining service life may be updated, and a second remaining service life may be predicted based on the updated calculation model, where the processing procedure includes:

Step1, acquiring a first calculation model.

In implementation, a calculation model adopted when predicting the residual service life for the first time can be used as a first calculation model; the calculation model used in predicting the remaining service life last time may be used as the first calculation model.

And 2, acquiring the running time of the equipment.

And 3, updating function parameters of the first calculation model based on the running time to obtain a second calculation model, and using the second calculation model to replace the first calculation model as a target calculation model of the equipment.

In an implementation, the first calculation model may contain a base risk rate that is derived from calculating a random distribution of service lives based on a service life data set, which may include service lives of a plurality of devices of the same type.

Thus, the already running time of the device may be added to the lifetime data set to update the lifetime data set. The random distribution of the service life is then recalculated based on the updated service life data set, thereby updating the function parameters in the base risk. Thereafter, the first calculation model containing the updated function parameters may be used as a second calculation model, and the second calculation model may be used as a target calculation model of the apparatus instead of the first calculation model.

Alternatively, the service life of the device belonging to the same type as the device for which the remaining service life is to be predicted may also be acquired, and the acquired service life and the already-running time length are added to the service life data set to update the service life data set.

And 4, predicting the second residual service life through the target calculation model and the operation parameters of the equipment.

In implementation, the process of predicting the second remaining service life through the target calculation model and the operation parameters of the device is similar to the process of predicting the second remaining service life through the calculation model and the operation parameters of the device, and will not be described herein.

In the embodiment of the application, the function parameters of the first calculation model are updated based on the running time, and the updated second calculation model is used as the target calculation model of the equipment, so that the accuracy of predicting the second residual service life based on the target calculation model and the running parameters can be improved.

Based on the same technical concept, the embodiment of the application also provides a device for predicting the residual service life of equipment, as shown in fig. 5, the device comprises:

A determining module 510, configured to determine that the device transitions from a first operation stage to a second operation stage of a plurality of operation stages, where the plurality of operation stages are obtained by dividing usage states of the device according to a wear degree of the device;

An obtaining module 520, configured to obtain an operation parameter of the device in the second operation stage;

A prediction module 530 for predicting a second remaining useful life of the device based on the operating parameters;

And a replacing module 540, configured to replace the first remaining service life corresponding to the first operation stage with the second remaining service life as a target remaining service life of the device, where the target remaining service life is used for maintaining the device.

Optionally, the determining module includes:

Optionally, the prediction module includes:

The embodiment of the application provides a device for predicting the residual life of equipment, which is used for acquiring the operation parameters of the equipment in a second operation stage after determining that the equipment is converted from the first operation stage to the second operation stage in a plurality of operation stages, wherein the operation stages are obtained by dividing the use state of the equipment according to the abrasion degree of the equipment. And then, predicting the second residual service life of the equipment based on the operation parameters, and replacing the first residual service life corresponding to the first operation stage with the second residual service life to serve as the target residual service life of the equipment, wherein the target residual service life is used for maintaining the equipment.

Based on the same technical concept, the embodiment of the present application further provides an electronic device, as shown in fig. 6, including a processor 601, a communication interface 602, a memory 603, and a communication bus 604, where the processor 601, the communication interface 602, and the memory 603 perform communication with each other through the communication bus 604,

A memory 603 for storing a computer program;

the processor 601 is configured to execute the program stored in the memory 603, and implement the following steps:

Acquiring operation parameters of the equipment in the second operation stage;

acquiring current operation parameters of the equipment;

collecting a plurality of operating parameters in a current operating phase;

Acquiring the running time of the equipment;

The communication bus mentioned above for the electronic device may be a peripheral component interconnect standard (PERIPHERAL COMPONENT INTERCONNECT, PCI) bus or an extended industry standard architecture (Extended Industry Standard Architecture, EISA) bus, etc. The communication bus may be classified as an address bus, a data bus, a control bus, or the like. For ease of illustration, the figures are shown with only one bold line, but not with only one bus or one type of bus.

The communication interface is used for communication between the electronic device and other devices.

The Memory may include random access Memory (Random Access Memory, RAM) or may include Non-Volatile Memory (NVM), such as at least one disk Memory. Optionally, the memory may also be at least one memory device located remotely from the aforementioned processor.

The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but may also be a digital signal processor (DIGITAL SIGNAL Processing, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components.

In yet another embodiment of the present application, there is also provided a computer readable storage medium having stored therein a computer program which, when executed by a processor, implements the steps of the method for predicting the remaining useful life of any of the devices described above.

In yet another embodiment of the present application, a computer program product containing instructions that, when run on a computer, cause the computer to perform the method of predicting the remaining useful life of any of the devices of the above embodiments is also provided.

In the above embodiments, it may be implemented in whole or in part by software, hardware, firmware, or any combination thereof. When implemented in software, may be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When loaded and executed on a computer, produces a flow or function in accordance with embodiments of the present application, in whole or in part. The computer may be a general purpose computer, a special purpose computer, a computer network, or other programmable apparatus. The computer instructions may be stored in or transmitted from one computer-readable storage medium to another, for example, by wired (e.g., coaxial cable, optical fiber, digital Subscriber Line (DSL)), or wireless (e.g., infrared, wireless, microwave, etc.). The computer readable storage medium may be any available medium that can be accessed by a computer or a data storage device such as a server, data center, etc. that contains an integration of one or more available media. The usable medium may be a magnetic medium (e.g., floppy disk, hard disk, tape), an optical medium (e.g., DVD), or a semiconductor medium (e.g., solid state disk Solid STATE DISK (SSD)), etc.

It should be noted that in this document, relational terms such as "first" and "second" and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.

The foregoing is only a specific embodiment of the application to enable those skilled in the art to understand or practice the application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A method of predicting the remaining useful life of a device, the method comprising:

Acquiring operation parameters of the equipment in the second operation stage;

Predicting a second remaining useful life of the device based on the operating parameters, comprising: taking the operation parameters as covariates, and calculating fitting parameters based on the covariates; calculating a device risk rate based on the fitting parameters; integrating and calculating the equipment risk rate to obtain a failure function; calculating a survival function based on the failure function, wherein the survival function = 1-failure function; calculating the residual service life of the equipment in each operation stage based on the survival function, and determining the residual service life of the last operation stage as the second residual service life;

2. The method of claim 1, wherein the determining that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases comprises:

3. The method of claim 1, wherein the determining that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases comprises:

acquiring current operation parameters of the equipment;

4. The method of claim 1, wherein the determining that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases comprises:

collecting a plurality of operating parameters in a current operating phase;

5. The method of claim 1, wherein the determining that the device transitions from a first operational phase to a second operational phase of the plurality of operational phases comprises:

6. The method of claim 1, wherein predicting a second remaining useful life of the device based on the operating parameter comprises:

Acquiring the running time of the equipment;

7. A device for predicting the remaining useful life of an apparatus, the device comprising:

A prediction module for predicting a second remaining useful life of the device based on the operating parameters, comprising: taking the operation parameters as covariates, and calculating fitting parameters based on the covariates; calculating a device risk rate based on the fitting parameters; integrating and calculating the equipment risk rate to obtain a failure function; calculating a survival function based on the failure function, wherein the survival function = 1-failure function; calculating the residual service life of the equipment in each operation stage based on the survival function, and determining the residual service life of the last operation stage as the second residual service life;

8. The apparatus of claim 7, wherein the determination module is to receive a run phase transition instruction to instruct the device to transition from the first run phase to the second run phase.

9. The electronic equipment is characterized by comprising a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory are communicated with each other through the communication bus;

a memory for storing a computer program;

a processor for carrying out the method steps of any one of claims 1-6 when executing a program stored on a memory.

10. A computer-readable storage medium, characterized in that the computer-readable storage medium has stored therein a computer program which, when executed by a processor, implements the method steps of any of claims 1-6.