CN118068820B - Intelligent fault diagnosis method for hydraulic support controller - Google Patents
Intelligent fault diagnosis method for hydraulic support controller Download PDFInfo
- Publication number
- CN118068820B CN118068820B CN202410473011.5A CN202410473011A CN118068820B CN 118068820 B CN118068820 B CN 118068820B CN 202410473011 A CN202410473011 A CN 202410473011A CN 118068820 B CN118068820 B CN 118068820B
- Authority
- CN
- China
- Prior art keywords
- data
- working face
- hydraulic
- hydraulic support
- working
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 143
- 238000003745 diagnosis Methods 0.000 title claims abstract description 32
- 239000000428 dust Substances 0.000 claims abstract description 42
- 239000002245 particle Substances 0.000 claims abstract description 42
- 230000004927 fusion Effects 0.000 claims abstract description 21
- 230000008569 process Effects 0.000 claims description 64
- 238000004364 calculation method Methods 0.000 claims description 40
- 230000006870 function Effects 0.000 claims description 32
- 230000003068 static effect Effects 0.000 claims description 24
- 238000012545 processing Methods 0.000 claims description 8
- 238000007689 inspection Methods 0.000 claims description 4
- 230000004913 activation Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 abstract description 2
- 239000003245 coal Substances 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 4
- 238000012549 training Methods 0.000 description 4
- 230000002159 abnormal effect Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000004519 manufacturing process Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 239000010720 hydraulic oil Substances 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001934 delay Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012806 monitoring device Methods 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
- G05B23/0205—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults
- G05B23/0218—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterised by the fault detection method dealing with either existing or incipient faults
- G05B23/0221—Preprocessing measurements, e.g. data collection rate adjustment; Standardization of measurements; Time series or signal analysis, e.g. frequency analysis or wavelets; Trustworthiness of measurements; Indexes therefor; Measurements using easily measured parameters to estimate parameters difficult to measure; Virtual sensor creation; De-noising; Sensor fusion; Unconventional preprocessing inherently present in specific fault detection methods like PCA-based methods
-
- E—FIXED CONSTRUCTIONS
- E21—EARTH OR ROCK DRILLING; MINING
- E21D—SHAFTS; TUNNELS; GALLERIES; LARGE UNDERGROUND CHAMBERS
- E21D23/00—Mine roof supports for step- by- step movement, e.g. in combination with provisions for shifting of conveyors, mining machines, or guides therefor
- E21D23/12—Control, e.g. using remote control
Landscapes
- Engineering & Computer Science (AREA)
- Mining & Mineral Resources (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Life Sciences & Earth Sciences (AREA)
- Geochemistry & Mineralogy (AREA)
- Geology (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses an intelligent fault diagnosis method for a hydraulic support controller, which relates to the technical field of intelligent control of hydraulic supports and comprises the following steps: s1, acquiring real-time parameter data of each working face hydraulic support to obtain a parameter data set of each working face hydraulic support; s2, determining fault states of hydraulic supports of all working surfaces; s3, adjusting the working state of each working face hydraulic support; s4, performing self-repairing on the hydraulic support of the working face; s5, after self-repairing, judging whether the fault state of each working face hydraulic support is changed, if so, completing fault diagnosis, and otherwise, sending out alarm notification. According to the invention, key operation parameters of the hydraulic support, such as pressure, dust, particle concentration, temperature and the like, can be monitored and analyzed in real time through the multi-mode fusion model, and the machine learning model is utilized to learn historical fault data, so that the accuracy and timeliness of fault diagnosis are improved.
Description
Technical Field
The invention relates to the technical field of intelligent control of hydraulic supports, in particular to an intelligent fault diagnosis method for a hydraulic support controller.
Background
In modern coal mine production, a hydraulic support is used as key equipment of a coal mine working face and bears important tasks of guaranteeing safety of miners and maintaining smooth production. Conventional hydraulic mount systems rely on manual detection and periodic maintenance to prevent and treat faults, which is not only time-consuming and labor-consuming, but also often difficult to achieve early detection and quick response to faults. With the development of technology, although some automatic monitoring and control technologies are introduced, the existing system still has obvious defects in fault diagnosis, self-repairing capability and remote updating.
First, the prior art relies mainly on simple logic decisions or preset rules in terms of fault diagnosis. Because of the complexity of the working environment of the coal mine, the hydraulic support system has various fault types, and the diagnosis based on the rule is difficult to cover all potential fault scenes, so that the phenomena of missing report and false report of fault diagnosis are common.
Second, existing hydraulic mount control systems are often limited in their ability to self-repair. When a system detects a fault, manual intervention is required for processing in most cases, which not only delays the fault processing time, but also increases the security risk. In the case of personnel not being able to reach the site immediately, the lack of an effective self-healing mechanism means that the system may be in an abnormal state for a long time, increasing the risk of accidents.
Furthermore, with respect to software updates and maintenance of the system, conventional methods typically require manual action by field operators, which is not only inefficient, but also does not allow for timely updates in certain emergency situations. Especially in the face of complex and changeable coal mine environments, the failure to update the fault diagnosis and self-repairing algorithm in real time means that the adaptability and reliability of the system cannot be guaranteed.
In summary, the existing hydraulic bracket control system has the following main drawbacks: 1. the fault diagnosis accuracy and timeliness are insufficient, and complex and changeable fault scenes are difficult to cover; 2. the lack of an effective self-repairing mechanism often depends on manual intervention, and has low efficiency and potential safety hazard; 3. the system software update and maintenance efficiency is low, and new failure modes and challenges cannot be responded to in time. Therefore, how to provide an intelligent fault diagnosis method for a hydraulic support controller is a problem that needs to be solved by those skilled in the art.
Disclosure of Invention
The invention provides an intelligent fault diagnosis method for a hydraulic support controller in order to solve the problems.
The technical scheme of the invention is as follows: the intelligent fault diagnosis method of the hydraulic support controller comprises the following steps:
S1, acquiring real-time parameter data of each working face hydraulic support, and grouping the real-time parameter data of each working face hydraulic support to obtain a parameter data set of each working face hydraulic support;
S2, constructing a multi-mode fusion model, and analyzing parameter data sets of the hydraulic supports of all working surfaces by using the multi-mode fusion model to determine fault states of the hydraulic supports of all working surfaces;
S3, adjusting the working state of each working face hydraulic support according to the fault state of each working face hydraulic support;
s4, performing self-repairing on the hydraulic supports of the working face based on the working states of the hydraulic supports of the working face;
S5, after self-repairing, judging whether the fault state of each working face hydraulic support is changed, if so, completing fault diagnosis, and otherwise, sending out alarm notification.
Further, S1 comprises the following sub-steps:
s11, collecting real-time parameter data of hydraulic supports of all working surfaces; the real-time parameter data of each working face hydraulic support comprises pressure data, dust and particle concentration data, temperature data, vibration data, three-dimensional position data and hydraulic pump working efficiency data;
s12, performing time stamp marking on the real-time parameter data of each working face hydraulic support to obtain time stamps of each working face hydraulic support;
and S13, constructing parameter data sets for the hydraulic supports of the working surfaces according to the time stamps and the data types of the hydraulic supports of the working surfaces.
Further, in S12, a time stamp of the ith working surface hydraulic mountThe expression of (2) is:
；
in the method, in the process of the invention, A specific point in time of the data acquisition is indicated,A function representing converting the data acquisition time into a time stamp;
s13, parameter data set of hydraulic support of ith working face The expression of (2) is:
；
in the method, in the process of the invention, Indicating the type of data collected by the ith face hydraulic mount,Representing a data value specific to the data type.
Further, S2 comprises the following sub-steps:
S21, grouping parameter data sets of hydraulic supports of all working surfaces, taking vibration data of the hydraulic supports of all working surfaces and working efficiency data of a hydraulic pump as time series data, and taking pressure data, dust and particle concentration data, temperature data and three-dimensional position data as static data;
S22, respectively preprocessing time series data and static data of each working face hydraulic support to obtain standardized time series data and standardized static data; the standardized time series data comprise standard vibration data and standard hydraulic pump working efficiency data, and the standardized static data comprise standard pressure data, standard dust and particle concentration data, standard temperature data and standard three-dimensional position data;
S23, constructing a multi-mode fusion model, and analyzing the standardized time sequence data and the standardized static data of the hydraulic supports of all working faces by using the multi-mode fusion model to obtain time sequence data characteristics and static data characteristics; the time series data features comprise vibration data features and hydraulic pump working efficiency data features, and the static data features comprise pressure data features, dust and particle concentration data features, temperature data features and three-dimensional position data features;
S24, fusing the time series data characteristics and the static data characteristics of the hydraulic supports of the working faces to generate characteristic representations;
S25, processing characteristic representations of the hydraulic supports of all working faces to obtain hidden characteristics;
s26, determining probability distribution of each working face hydraulic support to each fault type according to hidden characteristics of each working face hydraulic support;
S27, determining the fault state of each working face hydraulic support according to probability distribution of each working face hydraulic support to each fault type.
Further, in S22, standard vibration data of the ith working face hydraulic mountThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Vibration data representing the i-th face hydraulic mount,The mean value of vibration data of all working face hydraulic supports is represented,The standard deviation of vibration data of all working face hydraulic supports is represented,Vibration data representing all working face hydraulic supports;
in S22, standard hydraulic pump working efficiency data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Hydraulic pump work efficiency data representing the ith work surface hydraulic mount,The hydraulic pump working efficiency data average value of all working face hydraulic supports is represented,The standard deviation of the hydraulic pump work efficiency data of all working face hydraulic supports is represented,Hydraulic pump work efficiency data representing all work face hydraulic supports;
s22, standard pressure data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Pressure data representing an ith face hydraulic mount,The pressure data mean value of all working face hydraulic supports is represented,The standard deviation of the pressure data representing all the working face hydraulic supports,Pressure data representing all working face hydraulic supports;
S22, standard dust and particle concentration data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Dust and particle concentration data representing the ith face hydraulic mount,The data mean value of dust and particle concentration of all working face hydraulic supports is represented,The standard deviation of dust and particle concentration data of all working face hydraulic supports is represented,Dust and particle concentration data representing all working face hydraulic supports;
s22, standard temperature data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Temperature data representing the hydraulic mount of the ith working face,The temperature data mean value of all working face hydraulic supports is represented,The standard deviation of the temperature data of all working face hydraulic supports is shown,Temperature data representing all working face hydraulic supports;
S22, standard three-dimensional position data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Three-dimensional position data representing the hydraulic mount of the ith working face,Representing the three-dimensional position data average value of all the working surface hydraulic supports,Representing the standard deviation of the three-dimensional position data of all working face hydraulic supports,Three-dimensional position data representing all working face hydraulic supports.
Further, in S23, the vibration data characteristic of the ith working face hydraulic mountThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard vibration data representing an ith face hydraulic mount,Representing a long-short-term memory neural network function;
In S23, hydraulic pump working efficiency data characteristics of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard hydraulic pump work efficiency data representing an ith work face hydraulic mount;
In S23, the pressure data characteristic of the ith working face hydraulic bracket The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard pressure data representing the ith face hydraulic mount,Representing a convolutional neural network function;
in S23, the dust and particle concentration data characteristics of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard dust and particle concentration data representing an ith working face hydraulic mount;
S23, temperature data characteristics of hydraulic support of ith working face The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard temperature data representing an ith working face hydraulic mount;
in S23, three-dimensional position data feature of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, And the standard three-dimensional position data of the hydraulic support of the ith working surface are shown.
Further, in S24, the characteristic of the ith working face hydraulic mount indicatesThe expression of (2) is:
；
in the method, in the process of the invention, Representing the pressure data characteristic of the ith face hydraulic mount,Indicating the dust and particle concentration data characteristics of the ith working face hydraulic support,Representing the temperature data characteristic of the ith face hydraulic mount,Representing three-dimensional position data characteristics of the hydraulic support of the ith working surface,Representing the vibration data characteristic of the i-th face hydraulic mount,The hydraulic pump work efficiency data characteristic of the i-th working face hydraulic support is represented,Representing a characteristic tandem operation;
in S25, hidden features of the ith working face hydraulic mount The expression of (2) is:
；
in the method, in the process of the invention, Representing the weights of the first fully connected layer,Representing the bias of the first fully connected layer,Representing a ReLU activation function;
in S26, probability distribution of the ith working face hydraulic mount to the jth fault type The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, The index is represented by an index number,Representing the weight of the second fully connected layer for j fault types,Representing the bias of the second fully connected layer for j fault types,The weights of the second fully connected layer for k fault types are indicated,The bias of the second fully connected layer for k fault types is shown.
Further, S4 comprises the sub-steps of:
s41, based on the working state of the working face hydraulic support, inquiring and updating a controller of the working face hydraulic support by using an inspection operation function;
s42, after the controller inquires and updates, the controller of the working face hydraulic support is downloaded and updated by using a downloading function;
S43, initializing the downloaded and updated controller by using an initializing function to finish self-repairing.
Further, in S41, the operation function is checkedThe expression of (2) is:
；
in the method, in the process of the invention, Which means that the remote server is in the form of a server,Indicating the current software version of the face hydraulic mount controller,Representing a query operation;
in S42, the function is downloaded The expression of (2) is:
；
in the method, in the process of the invention, A download operation is indicated and the download operation is indicated,Representing querying the updated controller;
In S43, the function is initialized The expression of (2) is:
in the method, in the process of the invention, Representing an initialization operation.
The beneficial effects of the invention are as follows:
(1) According to the invention, key operation parameters of the hydraulic support, such as pressure, dust, particle concentration, temperature and the like, can be monitored and analyzed in real time through the multi-mode fusion model, and the machine learning model is utilized to learn historical fault data, so that the accuracy and timeliness of fault diagnosis are improved;
(2) According to the invention, through automatically executing preset self-repairing measures, such as adjusting working parameters, starting a standby system or switching to a safety mode, the autonomy and continuous operation capability of the hydraulic support system when faults are detected are obviously enhanced, and the dependence on manual intervention is reduced.
Drawings
Fig. 1 is a flow chart of a hydraulic bracket controller intelligent fault diagnosis method.
Detailed Description
Embodiments of the present invention are further described below with reference to the accompanying drawings.
As shown in fig. 1, the invention provides an intelligent fault diagnosis method for a hydraulic support controller, which comprises the following steps:
S1, acquiring real-time parameter data of each working face hydraulic support, and grouping the real-time parameter data of each working face hydraulic support to obtain a parameter data set of each working face hydraulic support;
S2, constructing a multi-mode fusion model, and analyzing parameter data sets of the hydraulic supports of all working surfaces by using the multi-mode fusion model to determine fault states of the hydraulic supports of all working surfaces;
S3, adjusting the working state of each working face hydraulic support according to the fault state of each working face hydraulic support;
s4, performing self-repairing on the hydraulic supports of the working face based on the working states of the hydraulic supports of the working face;
S5, after self-repairing, judging whether the fault state of each working face hydraulic support is changed, if so, completing fault diagnosis, and otherwise, sending out alarm notification.
In an embodiment of the present invention, S1 comprises the following sub-steps:
s11, collecting real-time parameter data of hydraulic supports of all working surfaces; the real-time parameter data of each working face hydraulic support comprises pressure data, dust and particle concentration data, temperature data, vibration data, three-dimensional position data and hydraulic pump working efficiency data;
s12, performing time stamp marking on the real-time parameter data of each working face hydraulic support to obtain time stamps of each working face hydraulic support;
and S13, constructing parameter data sets for the hydraulic supports of the working surfaces according to the time stamps and the data types of the hydraulic supports of the working surfaces.
In the embodiment of the present invention, in S12, the timestamp of the ith working surface hydraulic bracketThe expression of (2) is:
；
in the method, in the process of the invention, A specific point in time of the data acquisition is indicated,A function representing converting the data acquisition time into a time stamp;
s13, parameter data set of hydraulic support of ith working face The expression of (2) is:
；
in the method, in the process of the invention, Indicating the type of data collected by the ith face hydraulic mount,Representing a data value specific to the data type.
In the embodiment of the invention, in S1, a pressure sensor, a dust and particle concentration sensor, a temperature sensor, a vibration sensor, a position sensor and a hydraulic pump efficiency sensor are uniformly distributed and installed on each working face hydraulic support of a coal mine; the pressure sensor monitors working pressure in a hydraulic system of the hydraulic support of the working face in real time and collects pressure data; dust and particle concentration sensors monitor dust and particle concentration in hydraulic oil of a hydraulic support of a working face and collect dust and particle concentration data; the temperature sensor is used for measuring the working temperature of a hydraulic system of the hydraulic support of the working face and collecting temperature data; the vibration sensor captures the vibration characteristics of the hydraulic support of the working face and collects the vibration data of the hydraulic support; the position sensor is used for positioning the three-dimensional position coordinates of the hydraulic support of the working face in the coal mine and collecting the three-dimensional position data of the hydraulic support; the hydraulic pump efficiency sensor evaluates the working efficiency of the hydraulic support hydraulic pump of the working face and collects the working efficiency data of the hydraulic pump. The present invention may also assign a unique data set identifier to each data setThe expression is:
；
in the method, in the process of the invention, A sequence number representing the data set is displayed,The number of the hydraulic support of the working face is shown,Indicating the type of data collected by the ith face hydraulic mount,Representing the identification function.
In an embodiment of the present invention, S2 comprises the following sub-steps:
S21, grouping parameter data sets of hydraulic supports of all working surfaces, taking vibration data of the hydraulic supports of all working surfaces and working efficiency data of a hydraulic pump as time series data, and taking pressure data, dust and particle concentration data, temperature data and three-dimensional position data as static data;
S22, respectively preprocessing time series data and static data of each working face hydraulic support to obtain standardized time series data and standardized static data; the standardized time series data comprise standard vibration data and standard hydraulic pump working efficiency data, and the standardized static data comprise standard pressure data, standard dust and particle concentration data, standard temperature data and standard three-dimensional position data;
S23, constructing a multi-mode fusion model, and analyzing the standardized time sequence data and the standardized static data of the hydraulic supports of all working faces by using the multi-mode fusion model to obtain time sequence data characteristics and static data characteristics; the time series data features comprise vibration data features and hydraulic pump working efficiency data features, and the static data features comprise pressure data features, dust and particle concentration data features, temperature data features and three-dimensional position data features;
S24, fusing the time series data characteristics and the static data characteristics of the hydraulic supports of the working faces to generate characteristic representations;
S25, processing characteristic representations of the hydraulic supports of all working faces to obtain hidden characteristics;
s26, determining probability distribution of each working face hydraulic support to each fault type according to hidden characteristics of each working face hydraulic support;
S27, determining the fault state of each working face hydraulic support according to probability distribution of each working face hydraulic support to each fault type.
In the embodiment of the present invention, in S22, standard vibration data of the i-th working surface hydraulic support is obtainedThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Vibration data representing the i-th face hydraulic mount,The mean value of vibration data of all working face hydraulic supports is represented,The standard deviation of vibration data of all working face hydraulic supports is represented,Vibration data representing all working face hydraulic supports;
in S22, standard hydraulic pump working efficiency data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Hydraulic pump work efficiency data representing the ith work surface hydraulic mount,The hydraulic pump working efficiency data average value of all working face hydraulic supports is represented,The standard deviation of the hydraulic pump work efficiency data of all working face hydraulic supports is represented,Hydraulic pump work efficiency data representing all work face hydraulic supports;
s22, standard pressure data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Pressure data representing an ith face hydraulic mount,The pressure data mean value of all working face hydraulic supports is represented,The standard deviation of the pressure data representing all the working face hydraulic supports,Pressure data representing all working face hydraulic supports;
S22, standard dust and particle concentration data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Dust and particle concentration data representing the ith face hydraulic mount,The data mean value of dust and particle concentration of all working face hydraulic supports is represented,The standard deviation of dust and particle concentration data of all working face hydraulic supports is represented,Dust and particle concentration data representing all working face hydraulic supports;
s22, standard temperature data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Temperature data representing the hydraulic mount of the ith working face,The temperature data mean value of all working face hydraulic supports is represented,The standard deviation of the temperature data of all working face hydraulic supports is shown,Temperature data representing all working face hydraulic supports;
S22, standard three-dimensional position data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Three-dimensional position data representing the hydraulic mount of the ith working face,Representing the three-dimensional position data average value of all the working surface hydraulic supports,Representing the standard deviation of the three-dimensional position data of all working face hydraulic supports,Three-dimensional position data representing all working face hydraulic supports.
In the embodiment of the present invention, in S23, the vibration data characteristic of the i-th working surface hydraulic supportThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard vibration data representing an ith face hydraulic mount,Representing a long-short-term memory neural network function; in the calculation formula of the vibration data characteristics, the vibration data characteristics can be expanded into (the same principle as other characteristics): ; in the method, in the process of the invention, The 1 st standard vibration data representing the i-th face hydraulic mount,Standard vibration data representing the 2 nd of the i-th face hydraulic mount,The last standard vibration data for the ith face hydraulic mount is shown.
In S23, hydraulic pump working efficiency data characteristics of the ith working face hydraulic supportThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard hydraulic pump work efficiency data representing an ith work face hydraulic mount;
In S23, the pressure data characteristic of the ith working face hydraulic bracket The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard pressure data representing the ith face hydraulic mount,Representing a convolutional neural network function;
in S23, the dust and particle concentration data characteristics of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard dust and particle concentration data representing an ith working face hydraulic mount;
S23, temperature data characteristics of hydraulic support of ith working face The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard temperature data representing an ith working face hydraulic mount;
in S23, three-dimensional position data feature of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, And the standard three-dimensional position data of the hydraulic support of the ith working surface are shown.
In the embodiment of the present invention, in S24, the characteristic of the i-th working surface hydraulic support representsThe expression of (2) is:
；
in the method, in the process of the invention, Representing the pressure data characteristic of the ith face hydraulic mount,Indicating the dust and particle concentration data characteristics of the ith working face hydraulic support,Representing the temperature data characteristic of the ith face hydraulic mount,Representing three-dimensional position data characteristics of the hydraulic support of the ith working surface,Representing the vibration data characteristic of the i-th face hydraulic mount,The hydraulic pump work efficiency data characteristic of the i-th working face hydraulic support is represented,Representing a characteristic tandem operation;
in S25, hidden features of the ith working face hydraulic mount The expression of (2) is:
；
in the method, in the process of the invention, Representing the weights of the first fully connected layer,Representing the bias of the first fully connected layer,Representing a ReLU activation function;
in S26, probability distribution of the ith working face hydraulic mount to the jth fault type The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, The index is represented by an index number,Representing the weight of the second fully connected layer for j fault types,Representing the bias of the second fully connected layer for j fault types,The weights of the second fully connected layer for k fault types are indicated,The bias of the second fully connected layer for k fault types is shown.
In the embodiment of the present invention, in S3, the fault states of the working surface hydraulic support include a first fault state, a second fault state, a third fault state, and a fourth fault state;
The first fault state is that the pressure reading of the working face hydraulic support does not belong to a preset pressure working range; due to hydraulic pump failure, hydraulic oil leakage, or pressure sensor failure, it is necessary to cope with by increasing the output pressure of the pump or adjusting the pressure release valve;
The second fault state is specifically a sensor failure of the working face hydraulic support; when the bracket position sensor fails, the position information of the bracket cannot be accurately acquired, in which case, the selection of starting the standby system means starting the standby position monitoring device or adopting a manual measurement mode to maintain production operation;
The third fault state is specifically a software fault of the hydraulic support of the working face, and the fault relates to a software problem of the support control system, which is caused by a software programming error, abnormal data processing or compatibility problem after the system is updated. When software-induced operational anomalies are found, system software upgrades or fixes are an effective means of addressing such failures.
The fourth fault condition is in particular an electrical system fault, which may involve a power problem, a short circuit or a damaged electrical component. Switching to the safety mode means stopping all electrical operations when the electrical system fails.
For the measure of adjusting the operating parameters, the specific parameter adjustment is determined by the following formula:
；
Wherein, Based on the parameter adjustment amount specified by the fault type,The parameters after the adjustment are indicated,Indicating the parameters before adjustment.
In an embodiment of the present invention, S4 comprises the following sub-steps:
s41, based on the working state of the working face hydraulic support, inquiring and updating a controller of the working face hydraulic support by using an inspection operation function;
s42, after the controller inquires and updates, the controller of the working face hydraulic support is downloaded and updated by using a downloading function;
S43, initializing the downloaded and updated controller by using an initializing function to finish self-repairing.
In the embodiment of the present invention, in S41, the operation function is checkedThe expression of (2) is:
；
in the method, in the process of the invention, Which means that the remote server is in the form of a server,Indicating the current software version of the face hydraulic mount controller,Representing a query operation;
in S42, the function is downloaded The expression of (2) is:
；
in the method, in the process of the invention, A download operation is indicated and the download operation is indicated,Representing querying the updated controller;
In S43, the function is initialized The expression of (2) is:
；
in the method, in the process of the invention, Representing an initialization operation.
In the embodiment of the invention, after the self-repairing measure is executed, the controller utilizes the installed sensor to acquire key operation parameters again and evaluates the current operation state of the hydraulic support; and transmitting the re-collected operation parameter data to a processing unit of the controller, and analyzing by using the updated fault diagnosis algorithm to judge the effect of the self-repairing measure. If the analysis results show that the fault has been effectively handled, i.e. all monitored parameters are within normal operating range, the controller will update the system state to "normal" and record a log of the success of the self-repairing operation. If the analysis result indicates that the fault is not completely solved or a new abnormal index exists, the controller starts an alarm program, generates alarm information containing fault type, current state and recommended inspection measures, and sends the alarm information to maintenance personnel through a preset communication interface to ensure timely manual intervention. The controller will record detailed fault analysis results and information about the alarm issue.
In each fault diagnosis and self-repairing measure execution process, the controller automatically collects and records the time of fault occurrence, fault type, fault prediction accuracy, selected self-repairing measure, self-repairing executing result and re-monitoring result; the controller stores the information in an internal database in a structured manner, and each record is associated with a corresponding hydraulic support identifier, a timestamp and a fault processing result; the controller periodically transmits the collected data set to the model training server; after receiving the data, the model training server is used for training and optimizing the multi-modal fusion model, and in the training process, the performance of the multi-modal fusion model is evaluated by adopting a cross verification technology; the multi-mode fusion model is trained and verified to show that the performance is improved, and a new multi-mode fusion model version is deployed back to the controller to replace or update the existing fault diagnosis and self-repair algorithm; after receiving the new multi-mode fusion model, the controller automatically performs system testing to verify whether the integration of the new multi-mode fusion model affects the existing system functions, and after the testing is passed, the new multi-mode fusion model is put into use.
Those of ordinary skill in the art will recognize that the embodiments described herein are for the purpose of aiding the reader in understanding the principles of the present invention and should be understood that the scope of the invention is not limited to such specific statements and embodiments. Those of ordinary skill in the art can make various other specific modifications and combinations from the teachings of the present disclosure without departing from the spirit thereof, and such modifications and combinations remain within the scope of the present disclosure.
Claims (8)
1. The intelligent fault diagnosis method for the hydraulic support controller is characterized by comprising the following steps of:
S1, acquiring real-time parameter data of each working face hydraulic support, and grouping the real-time parameter data of each working face hydraulic support to obtain a parameter data set of each working face hydraulic support;
S2, constructing a multi-mode fusion model, and analyzing parameter data sets of the hydraulic supports of all working surfaces by using the multi-mode fusion model to determine fault states of the hydraulic supports of all working surfaces;
S3, adjusting the working state of each working face hydraulic support according to the fault state of each working face hydraulic support;
s4, performing self-repairing on the hydraulic supports of the working face based on the working states of the hydraulic supports of the working face;
s5, after self-repairing, judging whether the fault state of each working face hydraulic support is changed, if so, completing fault diagnosis, otherwise, sending out alarm notification;
The step S2 comprises the following substeps:
S21, grouping parameter data sets of hydraulic supports of all working surfaces, taking vibration data of the hydraulic supports of all working surfaces and working efficiency data of a hydraulic pump as time series data, and taking pressure data, dust and particle concentration data, temperature data and three-dimensional position data as static data;
S22, respectively preprocessing time series data and static data of each working face hydraulic support to obtain standardized time series data and standardized static data; the standardized time series data comprise standard vibration data and standard hydraulic pump working efficiency data, and the standardized static data comprise standard pressure data, standard dust and particle concentration data, standard temperature data and standard three-dimensional position data;
S23, constructing a multi-mode fusion model, and analyzing the standardized time sequence data and the standardized static data of the hydraulic supports of all working faces by using the multi-mode fusion model to obtain time sequence data characteristics and static data characteristics; the time series data features comprise vibration data features and hydraulic pump working efficiency data features, and the static data features comprise pressure data features, dust and particle concentration data features, temperature data features and three-dimensional position data features;
S24, fusing the time series data characteristics and the static data characteristics of the hydraulic supports of the working faces to generate characteristic representations;
S25, processing characteristic representations of the hydraulic supports of all working faces to obtain hidden characteristics;
s26, determining probability distribution of each working face hydraulic support to each fault type according to hidden characteristics of each working face hydraulic support;
S27, determining the fault state of each working face hydraulic support according to probability distribution of each working face hydraulic support to each fault type.
2. The intelligent fault diagnosis method for a hydraulic support controller according to claim 1, wherein S1 comprises the following sub-steps:
s11, collecting real-time parameter data of hydraulic supports of all working surfaces; the real-time parameter data of each working face hydraulic support comprises pressure data, dust and particle concentration data, temperature data, vibration data, three-dimensional position data and hydraulic pump working efficiency data;
s12, performing time stamp marking on the real-time parameter data of each working face hydraulic support to obtain time stamps of each working face hydraulic support;
and S13, constructing parameter data sets for the hydraulic supports of the working surfaces according to the time stamps and the data types of the hydraulic supports of the working surfaces.
3. The intelligent fault diagnosis method for hydraulic support controller according to claim 2, wherein in S12, the timestamp of the ith working face hydraulic support is recordedThe expression of (2) is:
；
in the method, in the process of the invention, A specific point in time of the data acquisition is indicated,A function representing converting the data acquisition time into a time stamp;
in the S13, parameter data set of the ith working face hydraulic support The expression of (2) is:
；
in the method, in the process of the invention, Indicating the type of data collected by the ith face hydraulic mount,Representing a data value specific to the data type.
4. The intelligent fault diagnosis method for hydraulic support controller according to claim 1, wherein in S22, standard vibration data of the i-th working face hydraulic support is obtainedThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Vibration data representing the i-th face hydraulic mount,The mean value of vibration data of all working face hydraulic supports is represented,The standard deviation of vibration data of all working face hydraulic supports is represented,Vibration data representing all working face hydraulic supports;
in the step S22, the standard hydraulic pump working efficiency data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Hydraulic pump work efficiency data representing the ith work surface hydraulic mount,The hydraulic pump working efficiency data average value of all working face hydraulic supports is represented,The standard deviation of the hydraulic pump work efficiency data of all working face hydraulic supports is represented,Hydraulic pump work efficiency data representing all work face hydraulic supports;
In the step S22, standard pressure data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Pressure data representing an ith face hydraulic mount,The pressure data mean value of all working face hydraulic supports is represented,The standard deviation of the pressure data representing all the working face hydraulic supports,Pressure data representing all working face hydraulic supports;
in S22, standard dust and particle concentration data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Dust and particle concentration data representing the ith face hydraulic mount,The data mean value of dust and particle concentration of all working face hydraulic supports is represented,The standard deviation of dust and particle concentration data of all working face hydraulic supports is represented,Dust and particle concentration data representing all working face hydraulic supports;
In the step S22, standard temperature data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Temperature data representing the hydraulic mount of the ith working face,The temperature data mean value of all working face hydraulic supports is represented,The standard deviation of the temperature data of all working face hydraulic supports is shown,Temperature data representing all working face hydraulic supports;
In the S22, standard three-dimensional position data of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Three-dimensional position data representing the hydraulic mount of the ith working face,Representing the three-dimensional position data average value of all the working surface hydraulic supports,Representing the standard deviation of the three-dimensional position data of all working face hydraulic supports,Three-dimensional position data representing all working face hydraulic supports.
5. The intelligent fault diagnosis method for hydraulic support controller according to claim 1, wherein in S23, the vibration data characteristic of the i-th working surface hydraulic support is determinedThe calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard vibration data representing an ith face hydraulic mount,Representing a long-short-term memory neural network function;
in S23, hydraulic pump working efficiency data characteristics of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard hydraulic pump work efficiency data representing an ith work face hydraulic mount;
in S23, the pressure data characteristic of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard pressure data representing the ith face hydraulic mount,Representing a convolutional neural network function;
In S23, the dust and particle concentration data characteristics of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard dust and particle concentration data representing an ith working face hydraulic mount;
In S23, the temperature data characteristic of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, Standard temperature data representing an ith working face hydraulic mount;
in S23, three-dimensional position data feature of the ith working face hydraulic support The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, And the standard three-dimensional position data of the hydraulic support of the ith working surface are shown.
6. The intelligent fault diagnosis method for hydraulic support controller according to claim 1, wherein in S24, the characteristic of the ith working face hydraulic support representsThe expression of (2) is:
；
in the method, in the process of the invention, Representing the pressure data characteristic of the ith face hydraulic mount,Indicating the dust and particle concentration data characteristics of the ith working face hydraulic support,Representing the temperature data characteristic of the ith face hydraulic mount,Representing three-dimensional position data characteristics of the hydraulic support of the ith working surface,Representing the vibration data characteristic of the i-th face hydraulic mount,The hydraulic pump work efficiency data characteristic of the i-th working face hydraulic support is represented,Representing a characteristic tandem operation;
In S25, the hidden feature of the ith working face hydraulic support The expression of (2) is:
；
in the method, in the process of the invention, Representing the weights of the first fully connected layer,Representing the bias of the first fully connected layer,Representing a ReLU activation function;
in S26, probability distribution of the ith working face hydraulic support to the jth fault type The calculation formula of (2) is as follows:
；
in the method, in the process of the invention, The index is represented by an index number,Representing the weight of the second fully connected layer for j fault types,Representing the bias of the second fully connected layer for j fault types,The weights of the second fully connected layer for k fault types are indicated,The bias of the second fully connected layer for k fault types is shown.
7. The intelligent fault diagnosis method for a hydraulic support controller according to claim 1, wherein S4 comprises the sub-steps of:
s41, based on the working state of the working face hydraulic support, inquiring and updating a controller of the working face hydraulic support by using an inspection operation function;
s42, after the controller inquires and updates, the controller of the working face hydraulic support is downloaded and updated by using a downloading function;
S43, initializing the downloaded and updated controller by using an initializing function to finish self-repairing.
8. The intelligent fault diagnosis method for a hydraulic support controller according to claim 7, wherein in S41, an operation function is checkedThe expression of (2) is:
；
in the method, in the process of the invention, Which means that the remote server is in the form of a server,Indicating the current software version of the face hydraulic mount controller,Representing a query operation;
In S42, the function is downloaded The expression of (2) is:
；
in the method, in the process of the invention, A download operation is indicated and the download operation is indicated,Representing querying the updated controller;
in S43, the function is initialized The expression of (2) is:
；
in the method, in the process of the invention, Representing an initialization operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410473011.5A CN118068820B (en) | 2024-04-19 | 2024-04-19 | Intelligent fault diagnosis method for hydraulic support controller |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410473011.5A CN118068820B (en) | 2024-04-19 | 2024-04-19 | Intelligent fault diagnosis method for hydraulic support controller |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118068820A CN118068820A (en) | 2024-05-24 |
| CN118068820B true CN118068820B (en) | 2024-07-16 |
Family
ID=91102506
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410473011.5A Active CN118068820B (en) | 2024-04-19 | 2024-04-19 | Intelligent fault diagnosis method for hydraulic support controller |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118068820B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN119573984B (en) * | 2024-11-28 | 2025-07-01 | 河南能源集团重型装备有限公司 | Leakage diagnosis system and method for hydraulic support |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113266403A (en) * | 2021-06-08 | 2021-08-17 | 中国矿业大学 | Method for monitoring state of hydraulic support system of coal mine unattended working face |
| CN114320420A (en) * | 2021-12-17 | 2022-04-12 | 北京天玛智控科技股份有限公司 | Control method and system for hydraulic support of fully mechanized coal mining face |
| CN115204272A (en) * | 2022-06-24 | 2022-10-18 | 中南大学 | Industrial system fault diagnosis method and equipment based on multi-sampling rate data |
Family Cites Families (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103670457B (en) * | 2013-12-05 | 2015-12-09 | 四川航天电液控制有限公司 | Coal mine fully-mechanized mining working hydraulic support real-time monitoring system |
| EP3977360A1 (en) * | 2019-05-29 | 2022-04-06 | F. Hoffmann-La Roche AG | Integrated neural networks for determining protocol configurations |
| CN111178586B (en) * | 2019-12-06 | 2022-09-23 | 浙江工业大学 | Online patriotic public opinion events tracking, forecasting and grooming methods |
| CN112101094B (en) * | 2020-08-02 | 2023-08-22 | 华南理工大学 | Suicide risk assessment method based on limb language |
| US12087446B2 (en) * | 2021-06-02 | 2024-09-10 | Neumora Therapeutics, Inc. | Multimodal dynamic attention fusion |
| CN114462459A (en) * | 2022-04-12 | 2022-05-10 | 合肥合锻智能制造股份有限公司 | Hydraulic machine fault diagnosis method based on 1DCNN-LSTM network model |
| CN116974864A (en) * | 2022-09-07 | 2023-10-31 | 中移（杭州）信息技术有限公司 | Data detection method and device, electronic equipment and storage medium |
| CN116186946B (en) * | 2023-05-04 | 2023-08-18 | 平顶山天安煤业股份有限公司 | Hydraulic system fault diagnosis method and system based on diagnosis model |
| CN117309038A (en) * | 2023-08-29 | 2023-12-29 | 中煤科工集团重庆研究院有限公司 | Mining electromechanical equipment fault diagnosis system and method based on multi-mode sensing |
| CN117216640A (en) * | 2023-09-15 | 2023-12-12 | 马鞍山师范高等专科学校 | Power time sequence data anomaly detection method |
| CN117670109A (en) * | 2023-11-16 | 2024-03-08 | 苏州新建元数字科技有限公司 | Enterprise credibility assessment method, device, system and storage medium |
-
2024
- 2024-04-19 CN CN202410473011.5A patent/CN118068820B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113266403A (en) * | 2021-06-08 | 2021-08-17 | 中国矿业大学 | Method for monitoring state of hydraulic support system of coal mine unattended working face |
| CN114320420A (en) * | 2021-12-17 | 2022-04-12 | 北京天玛智控科技股份有限公司 | Control method and system for hydraulic support of fully mechanized coal mining face |
| CN115204272A (en) * | 2022-06-24 | 2022-10-18 | 中南大学 | Industrial system fault diagnosis method and equipment based on multi-sampling rate data |
Non-Patent Citations (1)
| Title |
|---|
| 深度学习网络旋转部件故障诊断与寿命预测改进方法研究;王晨阳;中国博士学位论文全文数据库 工程科技Ⅱ辑;20240415(第04期);C029-22 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118068820A (en) | 2024-05-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111160804B (en) | Mining equipment management method, device and system based on Internet of things | |
| CN115393142A (en) | Intelligent park management method and management platform | |
| CN112926257A (en) | Reciprocating natural gas compressor fault diagnosis system and diagnosis method | |
| US8019570B2 (en) | System and method for continuous online safety and reliability monitoring | |
| US8099672B2 (en) | System and method for continuous online safety and reliability monitoring | |
| CN116664113A (en) | Intelligent safety supervision system for electric power metering standardized operation | |
| CN117649752B (en) | Monitoring, early warning and disposing method, device, equipment and medium for water supply network | |
| KR20190021560A (en) | Failure prediction system using big data and failure prediction method | |
| CN101255950A (en) | Intelligent warning system for computation and pipe monitoring of oil transportation collection and transmission system | |
| CN118068820B (en) | Intelligent fault diagnosis method for hydraulic support controller | |
| CN114781476B (en) | System and method for analyzing faults of measuring equipment | |
| CN104764595A (en) | Remote diagnostic system | |
| CN114353869A (en) | Online monitoring method and system for mobile equipment and readable storage medium | |
| CN119378787A (en) | A smart monitoring system for township rainwater and sewage pipe networks | |
| CN111627199A (en) | Hydropower station dam safety monitoring system and monitoring method | |
| CN117540310A (en) | Abnormality detection method and system for water affair culvert box based on machine learning | |
| CN119652942A (en) | A water conservancy safety detection method based on AI edge computing | |
| CN119444185A (en) | A self-service water filling machine intelligent operation and maintenance management method and platform | |
| CN118068790A (en) | Industrial production data management method and system | |
| CN110351367A (en) | For the long-distance maintenance method and system of fire-fighting equipment | |
| Tang et al. | Development of predictive maintenance system for nuclear power turbine unit | |
| CN115755847A (en) | Industrial control system grade protection evaluation method and system | |
| CN115307684A (en) | Predictive maintenance system for equipment failure based on BIM | |
| CN114372500A (en) | Intelligent factory control system based on big data | |
| CN119063934B (en) | Ball valve leakage detection method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |