CN118163573A - Fault prediction method and system and vehicle - Google Patents
Fault prediction method and system and vehicle Download PDFInfo
- Publication number
- CN118163573A CN118163573A CN202410251385.2A CN202410251385A CN118163573A CN 118163573 A CN118163573 A CN 118163573A CN 202410251385 A CN202410251385 A CN 202410251385A CN 118163573 A CN118163573 A CN 118163573A
- Authority
- CN
- China
- Prior art keywords
- compressor
- current
- air conditioning
- passenger cabin
- conditioning system
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 37
- 238000004378 air conditioning Methods 0.000 claims abstract description 81
- 238000003062 neural network model Methods 0.000 claims abstract description 31
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000010606 normalization Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 8
- 238000004364 calculation method Methods 0.000 description 7
- 238000007781 pre-processing Methods 0.000 description 6
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 3
- 238000012545 processing Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000001276 controlling effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000002245 particle Substances 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 230000036760 body temperature Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 238000007667 floating Methods 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000002035 prolonged effect Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/00978—Control systems or circuits characterised by failure of detection or safety means; Diagnostic methods
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60H—ARRANGEMENTS OF HEATING, COOLING, VENTILATING OR OTHER AIR-TREATING DEVICES SPECIALLY ADAPTED FOR PASSENGER OR GOODS SPACES OF VEHICLES
- B60H1/00—Heating, cooling or ventilating [HVAC] devices
- B60H1/00642—Control systems or circuits; Control members or indication devices for heating, cooling or ventilating devices
- B60H1/0073—Control systems or circuits characterised by particular algorithms or computational models, e.g. fuzzy logic or dynamic models
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Thermal Sciences (AREA)
- Mechanical Engineering (AREA)
- Fuzzy Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Theoretical Computer Science (AREA)
- Air-Conditioning For Vehicles (AREA)
Abstract
The embodiment of the application provides a fault prediction method, a fault prediction system and a vehicle, wherein the method comprises the following steps: determining a target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature; starting a fault prediction mode based on matching of the current compressor speed and the target compressor speed; generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode; based on at least one failure prediction result, whether the air conditioning system fails or not is judged, and a user is prompted, so that the failure of the air conditioning system can be predicted, and the prompt can be detected and sent out before the failure occurs, and the comfort and riding experience of personnel in a vehicle are ensured.
Description
Technical Field
The application relates to the technical field of air conditioners, in particular to a fault prediction method, a fault prediction system and a vehicle.
Background
Air conditioning systems for automobiles are very important for the driving experience of the driver and the riding experience of the passengers, and when the air conditioning system fails, the temperature in the automobile may be too high or too low, which may cause discomfort and fatigue of the personnel in the automobile.
Disclosure of Invention
In view of the above, the application provides a fault prediction method, a fault prediction system and a vehicle, which can be used for carrying out fault prediction, detecting and prompting before the fault occurs, and ensuring the comfort and riding experience of personnel in the vehicle.
In a first aspect, an embodiment of the present application provides a fault prediction method, including:
determining a target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature;
starting a fault prediction mode based on matching of a current compressor speed with the target compressor speed;
Generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode;
And judging whether the air conditioning system is in fault or not based on the at least one fault prediction result, and prompting a user.
The embodiment of the invention provides a fault prediction method, which predicts whether an air conditioning system is in fault or not when the temperature of a current passenger cabin is matched with a set temperature and the rotating speed of a current compressor is matched with the target rotating speed of the compressor, and can detect and give a prompt before the fault is generated, thereby ensuring the comfort and riding experience of personnel in a vehicle.
In a second aspect, an embodiment of the present application provides a fault prediction system, including:
The determining module is used for determining the target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature;
The starting module is used for starting a fault prediction mode based on the fact that the current rotation speed of the compressor is matched with the target rotation speed of the compressor;
The first generation module is used for generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode;
and the judging module is used for judging whether the air conditioning system is in fault or not based on the at least one fault prediction result and prompting a user.
The embodiment of the invention provides a fault prediction system which comprises a determining module, an opening module, a first generating module and a judging module, wherein the fault prediction system predicts whether an air conditioning system can generate faults, and can detect and give out prompts before the faults are generated, so that comfort and riding experience of personnel in a vehicle are ensured.
In a third aspect, an embodiment of the present application provides a vehicle comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, trigger the vehicle to perform the method of any one of the first aspects.
The embodiment of the invention provides a vehicle, wherein a fault prediction method can be realized based on the vehicle, the vehicle comprises an air conditioning system, and when the temperature of a current passenger cabin is matched with a set temperature and the rotating speed of a current compressor is matched with the target rotating speed of the compressor, whether the air conditioning system has a fault or not is predicted, and a prompt can be detected and sent out before the fault occurs, so that the comfort and riding experience of personnel in the vehicle are ensured.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed in the embodiments will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart of a fault prediction method according to an embodiment of the present application;
FIG. 2 is a flowchart for establishing a database and training a neural network model according to an embodiment of the present invention;
FIG. 3 is a flow chart of a fault prediction according to an embodiment of the present invention;
fig. 4 is a schematic structural diagram of a fault prediction system according to an embodiment of the present invention;
fig. 5 is a schematic structural diagram of a vehicle according to an embodiment of the present invention.
Detailed Description
For a better understanding of the technical solution of the present application, the following detailed description of the embodiments of the present application refers to the accompanying drawings.
It should be understood that the described embodiments are merely some, but not all, embodiments of the application. 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 terminology used in the embodiments of the application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this application and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.
It should be understood that the term "and/or" as used herein is merely one way of describing an association of associated objects, meaning that there may be three relationships, e.g., a and/or b, which may represent: the first and second cases exist separately, and the first and second cases exist separately. In this context, the character "/" indicates that the front and rear associated objects are an "or" relationship.
The system monitors the running state of a joint inside the automobile air conditioner in real time by using a signal acquisition unit consisting of a vibration sensor and an air quantity sensor to send out an alarm signal, and timely reminds a driver to check and repair the air conditioner to avoid further damage of the air conditioner. Meanwhile, the particle swarm optimization support vector machine network model is used for analyzing and processing the data to be tested, and the data is compared and analyzed by using the model to process the data. However, the signal acquisition unit formed by additionally installing the vibration sensor and the air quantity sensor is required to be matched with the original vehicle compressor, and the signal acquisition unit occupies large space, is not easy to install, and is time-consuming and labor-consuming. The particle swarm optimization support vector network model has higher requirements on an example, so that the requirements on a controller are higher, the common controller cannot be realized, a special processor is required to be additionally arranged, and the cost is increased. The traditional machine learning method is based on the training of a large amount of data, the actual operation working condition of an air conditioning system is complex, when the machine learning is applied to the air conditioning system, the machine learning model is required to be trained by covering the data under various working conditions, the recognition capability of a network model is further improved, a large amount of manpower and time are required, meanwhile, the air conditioning system of a vehicle is generally in a dynamic state, and the rotating speed of a compressor can be greatly fluctuated due to the external influence, so that the stability of the working condition cannot be ensured.
Fig. 1 is a flowchart of a fault prediction method according to an embodiment of the present invention, as shown in fig. 1, where the method includes:
And 101, determining the target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature.
In some embodiments, the vehicle may acquire a current passenger compartment temperature or current passenger compartment load, and may also receive a current passenger compartment temperature or current passenger compartment load actively entered by a user or other device. The set temperature includes a set temperature of the air conditioning system, and the current passenger compartment load is related to the in-vehicle parameters, the out-of-vehicle parameters, the number of passengers, the body temperature, and the like.
Matching the current passenger cabin temperature to the set temperature includes: in the first time period, the temperature difference between the current passenger cabin temperature and the set temperature is less than or equal to the temperature preset difference. The current passenger compartment temperature is allowed to float around the set temperature for a period of time to stabilize the temperature within the vehicle, e.g., during a first period of time, the current passenger compartment temperature reaches the set air conditioning system temperature and the difference between the current passenger compartment temperature and the set air conditioning system temperature does not float more than a preset temperature float difference. The set temperature includes a temperature preset in the program instead of a temperature regulated in real time, and the first period of time may also include a period of time preset in the program, but in the embodiment of the present invention, the set temperature or the first period of time is not limited, and the current passenger cabin temperature or the current source of the passenger cabin load is not limited.
And 102, starting a fault prediction mode based on the matching of the current compressor rotating speed and the target compressor rotating speed.
In some embodiments, matching the compressor target speed based on the current compressor speed includes: and controlling the compressor to run at the target rotating speed of the compressor, wherein in the second time period, the rotating speed difference between the current rotating speed of the compressor and the target rotating speed of the compressor is smaller than or equal to the preset rotating speed difference, but the second time period is not limited in the embodiment of the invention.
The vehicle has a failure prediction mode, and the vehicle enters the failure prediction mode when the rotation speed of the compressor is stably operated in a surrounding range of the target rotation speed of the compressor. When the vehicle is in the fault prediction mode, the rotation speed of the compressor is controlled in a strong way in a rated time period, so that the current rotation speed of the compressor in the rated time period is matched with the target rotation speed of the compressor.
And 103, generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode.
In some embodiments, the neural network model comprises a multi-layer feedforward neural network (Back Propagation Neural Network) model trained according to an error back propagation algorithm, BP (Back Propagation) is a network proposed by the group of scientists, beginning with Rumelhart and MCCELLAND, in 1986, the BP neural network model is one of the most widely used neural network models at present, and the topology of the BP neural network model comprises an input layer (input), an hidden layer (HIDE LAYER) and an output layer (output layer). The BP neural network model can learn and store a large number of mapping relations of input-output modes without revealing mathematical equations describing the mapping relations in advance, the learning rule adopted is a gradient descent method, and the weight and the threshold value of the BP neural network are continuously adjusted through back propagation, so that the square sum of errors of the network is minimum. However, the neural network model may also include other models, for example, the neural network model may also include a feedforward neural network, a convolution nerve channel, a feedback neural network, and the neural network model is not limited in the embodiment of the present invention.
And the vehicle performs strong control on the rotating speed of the compressor in a rated time period, continuously predicts whether the air conditioning system fails according to the current air conditioning system data based on the neural network model, and generates at least one failure prediction result. Since the error of the determination result of determining whether the air conditioning system is likely to fail based on the failure prediction result is large when the rated time is set within 2 minutes in the actual test case, the rated time period is generally greater than or equal to 2 minutes, for example, the rated time period is 5 minutes, and the vehicle generates a plurality of failure prediction results. The failure prediction result may be represented by a number, for example, the failure prediction result is 0, which represents that the air conditioning system is predicted to be free of failure; the failure prediction result is 1, which represents that the air conditioning system is predicted to have failure; the failure prediction result is-1, which represents that the failure prediction is not entered. However, the fault prediction result can be set by the user according to actual needs, and the embodiment of the invention does not limit the expression form of the fault prediction result.
Because the rotation speed of the compressor is controlled strongly in the rated time period, the rotation speed of the compressor does not have larger fluctuation in the rated time period, and the working condition is ensured to be stable, so that the data training amount in the process of generating the neural network model is reduced, and the influence on the fault prediction result caused by the complex rotation speed of the compressor in the actual operation is also reduced.
And 104, judging whether the air conditioning system is in fault or not based on at least one fault prediction result, and prompting a user.
In some embodiments, when the number of failure prediction results is one, the vehicle makes a judgment based on the meaning indicated by the failure prediction result. When the number of the fault prediction results is a plurality of, the vehicle counts the proportion of the fault prediction results which are predicted to be faults in the plurality of fault prediction results, and generates a predicted fault proportion; judging whether the fault prediction proportion is larger than the fault preset proportion or not; if the failure prediction proportion is larger than the failure preset proportion, determining that the air conditioning system fails; if the failure prediction proportion is less than or equal to the failure preset proportion, determining that the air conditioning system cannot fail.
In some embodiments, if the vehicle determines that the air conditioning system will fail, prompting the user that the air conditioning system will fail; if the air conditioning system is judged not to be faulty, the user is not prompted. Or if the vehicle judges that the air conditioning system fails, the vehicle does not prompt the user; and if the air conditioning system is judged not to be faulty, prompting the user that the air conditioning system is normal in operation. Or if the vehicle judges that the air conditioning system can fail, prompting the user that the air conditioning system can fail; and if the air conditioning system is judged not to be faulty, prompting the user that the air conditioning system is normal in operation. The vehicle may prompt the user, through at least one of display, sound, or vibration, that the air conditioning system is predicted to fail or that the air conditioning system is functioning properly, e.g., a display screen displays a text image prompt, a speaker plays a sound prompt, a vibration module emits a vibration prompt, etc. Therefore, the user can know whether the air conditioning system is in fault or not, and the user can find out before the air conditioning system is in fault.
The embodiment of the invention provides a fault prediction method, which predicts whether an air conditioning system will fail or not when the temperature of a current passenger cabin is matched with a set temperature and the rotating speed of a current compressor is matched with the target rotating speed of the compressor; the current passenger cabin temperature is stable and the current compressor rotation speed is stable in the prediction process, the fault prediction mode provides a stable prediction environment, so that the compressor rotation speed does not have larger fluctuation, the influence on a fault prediction result caused by complex compressor rotation speed conditions in actual operation is reduced, the requirement on a processor of a vehicle is reduced, the general power-calculating processor of the vehicle can execute the method, and of course, advanced or other additionally installed processors can execute the method. Meanwhile, the system can remind the user, so that discomfort and fatigue of personnel in the vehicle caused by overhigh or overlow temperature in the vehicle due to the failure of the air conditioning system are improved, and comfort and riding experience of the personnel in the vehicle are ensured.
In one possible implementation, after step 104, the method further includes: step 105, exiting the failure prediction mode.
In some embodiments, exiting the failure prediction mode includes: the vehicle stops to strongly control the rotational speed of the compressor. For example, after 5 minutes of operation in the failure prediction mode, the vehicle exits the failure prediction mode and stops the forced control of the current compressor speed based on the compressor target speed.
In one possible implementation, step 101 specifically includes: and taking the compressor rotating speed corresponding to the current passenger cabin load determined from the database as the target rotating speed of the compressor.
In some embodiments, the database is a Q-S database; the database is used for storing the corresponding relation between the passenger cabin load (Q) and the rotating speed (S) of the compressor. For example, the database includes a table of passenger compartment load versus compressor speed; or the database comprises a calculation formula of the load of the passenger cabin and the rotating speed of the compressor, etc.
Step 101 is also preceded by: and 100, generating a database based on the rotation speed of the compressor corresponding to the passenger cabin load and the passenger cabin load under the experimental working condition mode.
The experimental working condition modes comprise experimental working conditions and/or air conditioning modes, and the experimental working conditions comprise at least one single working condition; the experimental working conditions comprise one or more of all known working conditions such as a normal working condition and a limiting working condition, and the air conditioning mode comprises a refrigerating mode or a heating mode, so that the corresponding relation between the load of the passenger cabin and the rotating speed of the compressor under different working conditions of different modes is established.
The step 100 specifically includes:
Step 1001, under a single working condition, obtaining a passenger cabin load and a compressor rotation speed corresponding to the passenger cabin load based on matching of the passenger cabin temperature and the set temperature, and determining a set of corresponding relations.
In some embodiments, the single condition is any one of all known conditions such as a normal condition, a limit condition, etc., for example, the single condition is simulated according to a common usage scenario of an air conditioning system of an automobile. And the vehicle is based on the fact that the floating of the difference value between the passenger cabin temperature and the set temperature in a period of time does not exceed the preset temperature difference, the passenger cabin load and the corresponding compressor rotating speed at the moment are obtained, and a group of corresponding relations are established. The rotating speed of the compressor is controlled based on a database mode, so that on one hand, the subsequent experimental quantity can be reduced, and only the relation between the load condition of the passenger cabin and the rotating speed of the compressor is needed to be found; on the other hand, the influence on the fault prediction result caused by the instability of the actual situation can be reduced.
When there are two single working conditions, the vehicle obtains the load of the passenger cabin and the rotation speed of the compressor corresponding to the load of the passenger cabin based on the matching of the temperature of the passenger cabin and the set temperature under the other single working condition, the second set of corresponding relations are determined, and similarly, when there are a plurality of single working conditions, the vehicle circularly executes step 1001, and the vehicle can obtain the load of the passenger cabin and the rotation speed of the compressor corresponding to the load of the passenger cabin under each single working condition, and the corresponding relation between the load of the passenger cabin and the rotation speed of the compressor is determined.
Step 1002, generating a database based on at least one single working condition.
In some embodiments, the vehicle generates a database based on at least one single operating condition resulting in a correspondence between passenger cabin load and compressor speed. The vehicle may store the passenger compartment load and the compressor speed corresponding to the passenger compartment load in the form of a lookup table, or the vehicle may store the passenger compartment load and the compressor speed corresponding to the passenger compartment load in the form of a calculation formula.
In one possible implementation, step 103 further includes, before: and training the neural network according to the air conditioning system under the experimental working condition mode to generate a neural network model.
In some embodiments, after step 1001, the vehicle may also acquire air conditioning system data at the determined compressor speed, train the neural network, and generate a neural network model. Thereby reducing the amount of training, reducing the cost of labor and reducing the time spent training.
FIG. 2 is a flowchart for establishing a database and training a neural network model according to an embodiment of the present invention, where, as shown in FIG. 2, after a vehicle reaches a target vehicle temperature based on a current passenger cabin temperature and is stable, data is collected, and a stable compressor rotation speed can be collected, so as to obtain a passenger cabin load and a compressor rotation speed corresponding to the passenger cabin load, and further generate a Q-S database, where the target vehicle temperature refers to a set temperature; and acquiring air conditioning system data so as to train the BP neural network and obtain a BP neural network structure, so that the determination of the rotating speed of the compressor corresponding to the load of the passenger cabin and the generation of the neural network model can be simultaneously performed.
The vehicle comprises a sensor, the sensor can acquire passenger cabin temperature, passenger cabin load, compressor rotating speed, air conditioning system data and the like, and when the vehicle carries out fault prediction, the vehicle can acquire the passenger cabin temperature, the passenger cabin load, the compressor rotating speed, the air conditioning system data and the like from the sensor, so that the sensor of the existing vehicle can be used, and the installation of a special sensor is reduced or eliminated.
When testing under a single working condition, the test and training can be simultaneously carried out under the condition that the condition allows; or the neural network model applied in the step 103 can be trained and then applied to the vehicle, so that the calculation amount of the vehicle is reduced, and the volume of the vehicle-mounted controller is also reduced. And under the condition that the condition allows, a plurality of single-working-condition tests are simultaneously carried out, so that the establishment time of a database and the training time of a neural network model are shortened.
In one possible implementation, step 103 specifically includes:
and 1031, carrying out normalization preprocessing on the current air conditioning system data to generate standard air conditioning system data.
And 1032, inputting the standard air conditioning system data into the neural network model to generate a fault prediction result.
In some embodiments, the vehicle repeatedly performs steps 1031 through 1032 over a nominal time period.
In some embodiments, fig. 3 is a flowchart of a fault prediction method according to an embodiment of the present invention, and as shown in fig. 3, the vehicle includes a mode detection module. The mode detection module can be used as a vehicle temperature detection module and is used for acquiring the current passenger cabin temperature; or may be used as a failure prediction determination module for determining whether a failure prediction mode may be enabled, as in some situations it may be desirable for the vehicle not to enable failure prediction in order to do other operations. The mode detection module in this flowchart may be used as a vehicle temperature detection module for collecting the current passenger compartment temperature. The current passenger cabin temperature may be stored in memory and the vehicle may retrieve the current passenger cabin temperature directly from memory so the mode detection module may be deleted from the present flowchart.
Judging whether the vehicle temperature reaches a target, wherein the vehicle temperature refers to the current passenger cabin temperature, and the target refers to the set temperature; if the current passenger cabin temperature reaches the target, judging whether the vehicle condition is stable or not based on whether the temperature difference between the current passenger cabin temperature and the set temperature is stable or not in the first time period; judging that the vehicle condition is stable based on the temperature difference between the current passenger cabin temperature and the set temperature in the first time period; after judging that the vehicle condition is stable, obtaining a target rotating speed of the compressor through a Q-S database, and strongly controlling the rotating speed of the compressor to be the target rotating speed of the compressor; characteristic data acquisition is carried out to acquire current air conditioning system data; carrying out data preprocessing on the current air conditioning system data; inputting the preprocessed air conditioning system data into a BP neural network model for fault prediction, and outputting a predicted result; ending the flow.
And if the current passenger cabin temperature does not reach the target, triggering the mode detection module to execute the step of collecting the current passenger cabin temperature. If the vehicle condition is judged to be unstable, the step of judging whether the current passenger cabin temperature reaches the target is continuously carried out.
Therefore, whether the air conditioning system fails or not can be predicted, and a user can find out before the air conditioning system fails when the air conditioning system fails; when the fault needs to be repaired, the repair can be performed, the further deterioration of the fault and the more serious damage caused by the fault can be avoided, and the fault can not further influence other key components so as to cause larger damage and expensive maintenance cost; through fault prediction and later maintenance, the service life of an air conditioning system can be prolonged, the reliability of the whole vehicle can be maintained, and economic benefits can be ensured.
Fig. 4 is a schematic structural diagram of a fault prediction system according to an embodiment of the present invention, as shown in fig. 4, where the system includes: the device comprises a determining module 11, an opening module 12, a first generating module 13, a judging module 14 and a prompting module 15. The determining module 11 is electrically connected with the opening module 12, the opening module 12 is electrically connected with the first generating module 13, the first generating module 13 is electrically connected with the judging module 14, and the judging module 14 is electrically connected with the prompting module 15.
The determining module 11 is configured to determine a target rotational speed of the compressor according to the current passenger compartment load based on the current passenger compartment temperature matching the set temperature. The turn-on module 12 is configured to turn on the failure prediction mode based on the current compressor speed matching the compressor target speed. The first generation module 13 is configured to generate at least one failure prediction result according to the current air conditioning system data and the neural network model in a rated period of time based on the failure prediction mode. The judging module 14 is configured to judge whether the air conditioning system will fail based on at least one failure prediction result, and prompt a user.
In a possible implementation, the apparatus further comprises a control module 15. The control module 15 is electrically connected to the opening module 12.
The control module 15 is specifically configured to control the current compressor speed to match the target compressor speed during the nominal time period when in the failure prediction mode.
In one possible implementation, the current passenger compartment temperature matches a set temperature, including: and in a first time period, the temperature difference between the current passenger cabin temperature and the set temperature is less than or equal to a preset temperature difference.
In one possible implementation, the current compressor speed matches the compressor target speed, including: and in a second time period, the rotation speed difference between the current rotation speed of the compressor and the target rotation speed of the compressor is smaller than or equal to a preset rotation speed difference.
In one possible implementation, the system further includes a second generation module 16; the second generation module 16 is electrically connected to the first generation module 13.
The second generation module 16 is configured to train the neural network according to the air conditioning system data in the experimental working condition mode, and generate a neural network model.
In one possible implementation, the determining module 11 is specifically configured to use the compressor speed corresponding to the current passenger cabin load determined from the database as the compressor target speed.
In one possible implementation, the system further includes: a database construction module 17; the database construction module 17 is electrically connected with the determination module 11.
The database building module 17 is configured to generate a database based on the passenger compartment load and the compressor rotation speed corresponding to the passenger compartment load in the experimental condition mode.
In one possible implementation, database build module 17 includes a determination submodule 171 and a generation submodule 172. The determination submodule 171 is electrically connected with the generation submodule 172.
The experimental condition mode includes at least one single condition; the determining submodule 171 is used for obtaining the passenger cabin load and the compressor rotating speed corresponding to the passenger cabin load based on the matching of the passenger cabin temperature and the set temperature under a single working condition, and determining a group of corresponding relations; the generating sub-module 172 is configured to generate the database based on the at least one single operating condition.
In one possible implementation, the first generation module 13 includes a data preprocessing sub-module 131 and a fault prediction sub-module 132. The data preprocessing sub-module 131 is electrically connected with the failure prediction sub-module 132.
The data preprocessing sub-module 131 is used for performing normalization preprocessing on the current air conditioning system data to generate standard air conditioning system data; the fault prediction sub-module 132 is configured to input standard air conditioning system data into the neural network model to generate a fault prediction result.
In one possible implementation, the system further includes a signal acquisition module 18, the signal acquisition module 18 being electrically connected to the second generation module 16.
In some embodiments, the signal acquisition module is a virtual module, rather than a sensor, belonging to a certain command section of the computer program, so as to acquire the detection parameter data of the air conditioning system, so that the system does not need to add a special sensor and a calculation processor.
The embodiment of the invention provides a fault prediction system, which predicts whether an air conditioning system will fail or not when the temperature of a current passenger cabin is matched with a set temperature and the rotating speed of a current compressor is matched with the target rotating speed of the compressor; the current passenger cabin temperature is stable and the current compressor rotation speed is stable in the prediction process, the fault prediction mode provides a stable prediction environment, so that the compressor rotation speed does not have larger fluctuation, the influence on a fault prediction result caused by complex compressor rotation speed conditions in actual operation is reduced, the requirement on calculation force is low, the requirement on a processor of a vehicle is reduced, the vehicle can be designed based on a controller of the vehicle, the common calculation force processor of the vehicle can execute the method without adding other calculation processors, and the advanced or added processor can execute the method; meanwhile, the system can remind a user whether the air conditioning system can fail, so that discomfort and fatigue of personnel in the vehicle caused by overhigh or overlow temperature in the vehicle due to the failure of the air conditioning system are avoided, and comfort and riding experience of the personnel in the vehicle are ensured.
Corresponding to the embodiment, the application also provides a vehicle. Fig. 5 is a schematic structural diagram of a vehicle according to an embodiment of the present application, as shown in fig. 5, a vehicle 800 may include: a processor 801, a memory 802, and a communication unit 803. The components may communicate via one or more buses, and it will be appreciated by those skilled in the art that the configuration of the vehicle as shown in the drawings is not limiting of the embodiments of the application, as it may be a bus-like structure, a star-like structure, or include more or fewer components than shown, or may be a combination of certain components or a different arrangement of components.
Wherein the communication unit 803 is configured to establish a communication channel, so that the vehicle can communicate with other devices. Receiving user data sent by other devices or sending user data to other devices.
The processor 801, which is a control center of the vehicle, connects various parts of the entire vehicle using various interfaces and lines, performs various functions of the vehicle and/or processes data by running or executing software programs, instructions, and/or modules stored in the memory 802, and invoking data stored in the memory. The processor may be comprised of integrated circuits (INTEGRATED CIRCUIT, ICs), such as a single packaged IC, or may be comprised of packaged ICs that connect multiple identical or different functions. For example, the processor 801 may include only a central processing unit (central processing unit, CPU). In the embodiment of the invention, the CPU can be a single operation core or can comprise multiple operation cores.
Memory 802 for storing instructions for execution by processor 801, memory 802 may be implemented with any type of volatile or nonvolatile memory device or combination thereof, such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk, or optical disk.
The execution of the instructions in memory 802, when executed by processor 801, enables vehicle 800 to perform some or all of the steps of the embodiment shown in fig. 1.
The same or similar parts between the various embodiments in this specification are referred to each other. In particular, for system embodiments and vehicle embodiments, the description is relatively simple, as it is substantially similar to the method embodiments, with reference to the description of the method embodiments.
Claims (11)
1. A method of fault prediction, comprising:
determining a target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature;
starting a fault prediction mode based on matching of a current compressor speed with the target compressor speed;
Generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode;
And judging whether the air conditioning system is in fault or not based on the at least one fault prediction result, and prompting a user.
2. The method of claim 1, wherein the current compressor speed is controlled to match the compressor target speed for a nominal period of time when in a failure prediction mode.
3. The method of claim 1, wherein the current passenger compartment temperature matches a set temperature, comprising:
And in a first time period, the temperature difference between the current passenger cabin temperature and the set temperature is less than or equal to a preset temperature difference.
4. The method of claim 1, wherein the current compressor speed matches the compressor target speed, comprising:
And in a second time period, the rotation speed difference between the current rotation speed of the compressor and the target rotation speed of the compressor is smaller than or equal to a preset rotation speed difference.
5. The method of claim 1, wherein prior to generating the at least one failure prediction result, further comprising:
Training the neural network according to the air conditioning system data under the experimental working condition mode to generate the neural network model.
6. The method of claim 1, wherein determining the compressor target speed based on the current passenger compartment load comprises:
and taking the compressor rotating speed corresponding to the current passenger cabin load determined from the database as the target rotating speed of the compressor.
7. The method of claim 6, wherein said determining the compressor speed corresponding to the current passenger compartment load as the compressor target speed from a database is preceded by:
And generating the database based on the rotation speed of the compressor corresponding to the passenger cabin load and the passenger cabin load under the experimental working condition mode.
8. The method of claim 7, wherein the experimental operating mode comprises at least one single operating mode; the generating the database based on the compressor rotation speed of the passenger cabin load and the passenger cabin load under the experimental working condition mode comprises the following steps:
Under the single working condition, based on the matching of the passenger cabin temperature and the set temperature, obtaining the passenger cabin load and the rotating speed of the compressor corresponding to the passenger cabin load, and determining a group of corresponding relations;
The database is generated based on the at least one single operating condition.
9. The method of claim 1, wherein generating at least one failure prediction result based on current air conditioning system data and a neural network model comprises:
carrying out normalization pretreatment on the current air conditioning system data to generate standard air conditioning system data;
and inputting the standard air conditioning system data into the neural network model to generate the fault prediction result.
10. A fault prediction system, comprising:
The determining module is used for determining the target rotating speed of the compressor according to the current passenger cabin load based on the matching of the current passenger cabin temperature and the set temperature;
The starting module is used for starting a fault prediction mode based on the fact that the current rotation speed of the compressor is matched with the target rotation speed of the compressor;
The first generation module is used for generating at least one fault prediction result according to the current air conditioning system data and the neural network model in a rated time period based on the fault prediction mode;
and the judging module is used for judging whether the air conditioning system is in fault or not based on the at least one fault prediction result and prompting a user.
11. A vehicle comprising a memory for storing computer program instructions and a processor for executing the program instructions, wherein the computer program instructions, when executed by the processor, cause the vehicle to perform the method of any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251385.2A CN118163573A (en) | 2024-03-05 | 2024-03-05 | Fault prediction method and system and vehicle |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410251385.2A CN118163573A (en) | 2024-03-05 | 2024-03-05 | Fault prediction method and system and vehicle |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118163573A true CN118163573A (en) | 2024-06-11 |
Family
ID=91359678
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410251385.2A Pending CN118163573A (en) | 2024-03-05 | 2024-03-05 | Fault prediction method and system and vehicle |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118163573A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118700794A (en) * | 2024-08-28 | 2024-09-27 | 深圳丰汇汽车电子有限公司 | A Fault Diagnosis System for Automobile Air Conditioning System |
| CN118991337A (en) * | 2024-07-24 | 2024-11-22 | 广州汽车集团股份有限公司 | Fault diagnosis method of thermal management system, vehicle and cloud equipment |
-
2024
- 2024-03-05 CN CN202410251385.2A patent/CN118163573A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN118991337A (en) * | 2024-07-24 | 2024-11-22 | 广州汽车集团股份有限公司 | Fault diagnosis method of thermal management system, vehicle and cloud equipment |
| CN118700794A (en) * | 2024-08-28 | 2024-09-27 | 深圳丰汇汽车电子有限公司 | A Fault Diagnosis System for Automobile Air Conditioning System |
| CN118700794B (en) * | 2024-08-28 | 2024-11-12 | 深圳丰汇汽车电子有限公司 | A Fault Diagnosis System for Automobile Air Conditioning System |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN118163573A (en) | Fault prediction method and system and vehicle | |
| CN106843190B (en) | Distributed vehicle health management system | |
| US9068759B2 (en) | Motor current based air circuit obstruction detection | |
| CN109507981B (en) | Vehicle testing method and device and machine-readable storage medium | |
| US7612464B2 (en) | Electronic control system with malfunction monitor | |
| US20190311552A1 (en) | Fault diagnosis using distributed pca architecture | |
| US20060142976A1 (en) | Method and apparatus for in-situ detection and isolation of aircraft engine faults | |
| US7275184B2 (en) | Software verification method for control units and verification system | |
| CN110347130B (en) | Subsystem linkage control scheme processing method, device, system, equipment and medium | |
| US7921337B2 (en) | Systems and methods for diagnosing faults in electronic systems | |
| CN105584317B (en) | The method and cooling fan controller of cooling fan are controlled in cooling fan controller | |
| US9342441B2 (en) | Methodology and tool support for test organization and migration for embedded software | |
| CN104865948A (en) | Automatic vehicle controller diagnosing device and method | |
| CN104714463B (en) | A kind of safety monitoring system and method | |
| CN116872685B (en) | Remote diagnosis method, system, platform and storage medium for vehicle air conditioning system | |
| CN113340460B (en) | Temperature testing system and method | |
| US11551488B2 (en) | Adaptive fault diagnostic system for motor vehicles | |
| CN113310708B (en) | Method, apparatus, computer program product and storage medium for testing durability of actuator | |
| US20240169772A1 (en) | Vehicle abnormality detection device and vehicle abnormality detection method | |
| CN106383511A (en) | Simulation test method, device and system for vehicle control unit | |
| CN108153285B (en) | Automobile safety monitoring method, device, storage medium and system | |
| CN114117395A (en) | Validating instruction sequences | |
| CN111552584A (en) | Test system, method and device for satellite level fault diagnosis isolation and recovery function | |
| EP4354276A1 (en) | Cockpit domain control device and method for detecting display error by using cockpit domain control device | |
| CN102890494A (en) | Functional verification method of automobile diagnosis instrument |
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 |