CN116466689A - Fault diagnosis method and device - Google Patents
Fault diagnosis method and device Download PDFInfo
- Publication number
- CN116466689A CN116466689A CN202310723838.2A CN202310723838A CN116466689A CN 116466689 A CN116466689 A CN 116466689A CN 202310723838 A CN202310723838 A CN 202310723838A CN 116466689 A CN116466689 A CN 116466689A
- Authority
- CN
- China
- Prior art keywords
- state data
- fault
- fault diagnosis
- electric drive
- data
- 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.)
- Granted
Links
- 238000003745 diagnosis Methods 0.000 title claims abstract description 123
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000001514 detection method Methods 0.000 claims abstract description 111
- 238000004590 computer program Methods 0.000 claims description 11
- 230000015572 biosynthetic process Effects 0.000 claims description 6
- 238000012545 processing Methods 0.000 abstract description 2
- 239000010705 motor oil Substances 0.000 description 9
- 238000012549 training Methods 0.000 description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 8
- 238000004891 communication Methods 0.000 description 7
- 239000003921 oil Substances 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000016507 interphase Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 2
- 230000009467 reduction Effects 0.000 description 2
- 230000005856 abnormality Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012360 testing method 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
- G05B23/0259—Electric testing or monitoring by means of a monitoring system capable of detecting and responding to faults characterized by the response to fault detection
- G05B23/0262—Confirmation of fault detection, e.g. extra checks to confirm that a failure has indeed occurred
-
- 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
- G05B2219/00—Program-control systems
- G05B2219/20—Pc systems
- G05B2219/24—Pc safety
- G05B2219/24065—Real time diagnostics
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The application relates to the technical field of data processing, and provides a fault diagnosis method and device. The method comprises the following steps: determining a fault label of the electric drive assembly according to the fault data of the electric drive assembly; extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label; detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data; and obtaining a fault diagnosis result of the electric drive assembly according to each detection result. The fault diagnosis method provided by the embodiment of the application can improve the accuracy of fault diagnosis of the electric drive assembly.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a fault diagnosis method and device.
Background
In a new energy automobile, an electric drive component, such as a motor and/or a motor controller, for driving the vehicle is an important component affecting the performance and safety of the new energy automobile, so that when the electric drive component fails, it is necessary to diagnose the failure in time.
Conventionally, in a fault diagnosis method, fault data about an electric drive unit in whole vehicle data is checked, and then the fault data is searched for a diagnosis result corresponding to the fault data from a data table in which a mapping relation between each fault data and each diagnosis result is recorded, as a fault diagnosis result. However, since the fault may be caused by various situations, matching the diagnosis result only by the fault data may cause the obtained fault diagnosis result to be not matched with the actual situation causing the fault, affecting the accuracy of the obtained fault diagnosis result.
Disclosure of Invention
The present application aims to solve at least one of the technical problems existing in the related art. Therefore, the fault diagnosis method can improve the accuracy of fault diagnosis of the electric drive assembly.
The application also provides a fault diagnosis device.
The application also provides electronic equipment.
The present application also proposes a computer-readable storage medium.
The application also proposes a vehicle.
The fault diagnosis method according to the embodiment of the first aspect of the application comprises the following steps:
determining a fault label of the electric drive assembly according to fault data of the electric drive assembly;
extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and obtaining a fault diagnosis result of the electric drive assembly according to each detection result.
After the fault label of the electric drive assembly is determined through the fault data of the electric drive assembly, each associated state data corresponding to the fault label is extracted, at least one target state data in each associated state data is detected according to each preset condition corresponding to the associated state data one by one, and a fault diagnosis result of the electric drive assembly is obtained according to the detection result of each target state data, so that the state data associated with the fault of the electric drive assembly can be utilized to determine what condition is caused by the fault, the matching degree of the fault diagnosis result and the actual condition causing the fault is improved, and the accuracy of fault diagnosis of the electric drive assembly is further improved.
According to one embodiment of the present application, according to the fault tag, extracting each associated state data corresponding to the fault tag from each state data of the electric drive assembly includes:
extracting each associated state data in a preset period from each state data of the electric drive assembly according to the fault label;
wherein the preset period includes a failure time at which the failure data is detected.
According to one embodiment of the present application, the preset time period includes a first target time period before the fault time.
According to one embodiment of the present application, the preset time period includes a second target time period after the fault time.
According to an embodiment of the present application, detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data, to obtain a detection result of each target state data, includes:
and according to the dependency relationship of each preset condition, sequentially acquiring corresponding associated state data for detection, marking the currently detected associated state data as target state data for each detection, detecting the target state data according to the preset condition corresponding to the target state data, acquiring the next preset condition associated with the detection result after the detection result of the target state data is obtained, marking the next associated state data corresponding to the next preset condition as the target state data for detection until the next preset condition associated with the detection result cannot be acquired, and ending the detection of the target state data to obtain the detection result of each target state data.
According to one embodiment of the present application, the dependency of each preset condition is determined according to each historical detection result corresponding to the historical fault diagnosis result.
According to one embodiment of the present application, obtaining a fault diagnosis result of the electric drive assembly according to each detection result includes:
obtaining diagnostic data representing the cause of the formation of the fault data according to each detection result;
and inputting the diagnosis data into a trained fault diagnosis model to obtain the fault diagnosis result.
The fault diagnosis apparatus according to the embodiment of the second aspect of the present application includes:
the fault label determining module is used for determining a fault label of the electric driving assembly according to the fault data of the electric driving assembly;
the state data acquisition module is used for extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
the detection result acquisition module is used for detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and the diagnosis result acquisition module is used for acquiring a fault diagnosis result of the electric drive assembly according to each detection result.
An electronic device according to an embodiment of a third aspect of the present application includes a processor and a memory storing a computer program, where the processor implements the fault diagnosis method according to any of the above embodiments when executing the computer program.
A computer-readable storage medium according to an embodiment of a fourth aspect of the present application has stored thereon a computer program which, when executed by a processor, implements the fault diagnosis method described in any of the above embodiments.
The above technical solutions in the embodiments of the present application have at least one of the following technical effects:
after the fault label of the electric drive assembly is determined through the fault data of the electric drive assembly, each associated state data corresponding to the fault label is extracted, at least one target state data in each associated state data is detected according to each preset condition corresponding to the associated state data one by one, and a fault diagnosis result of the electric drive assembly is obtained according to the detection result of each target state data, so that the state data associated with the fault of the electric drive assembly can be utilized to determine what condition is caused by the fault, the matching degree of the fault diagnosis result and the actual condition causing the fault is improved, and the accuracy of fault diagnosis of the electric drive assembly is further improved.
Drawings
For a clearer description of the present application or of the prior art, the drawings that are used in the description of the embodiments or of the prior art will be briefly described, it being apparent that the drawings in the description below are some embodiments of the present application, and that other drawings may be obtained from these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a fault diagnosis method according to an embodiment of the present disclosure;
FIG. 2 is a schematic structural diagram of a fault diagnosis tree according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of a fault diagnosis apparatus provided in an embodiment of the present application;
fig. 4 is a schematic structural diagram of an electronic device according to an embodiment of the present application.
Detailed Description
For the purposes of making the objects, technical solutions and advantages of the present application more apparent, the technical solutions in the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application, and it is apparent that the described embodiments are some, but not all, embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
The fault diagnosis method and device provided in the embodiments of the present application will be described and illustrated in detail below by means of several specific embodiments.
In one embodiment, a fault diagnosis method is provided, which is applied to a terminal device and is used for performing fault diagnosis of an electric drive assembly. The terminal device can be a desktop terminal, a portable terminal or a server, the server can be an independent server or a server cluster formed by a plurality of servers, and the server can also be a cloud server for providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDNs, big data and artificial intelligent sampling point devices and the like.
As shown in fig. 1, the fault diagnosis method provided in this embodiment includes:
step 101, determining a fault label of an electric drive assembly according to fault data of the electric drive assembly;
102, extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
step 103, detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively, and obtaining a detection result of each target state data;
and 104, obtaining a fault diagnosis result of the electric drive assembly according to each detection result.
In some embodiments, the electric drive assembly may include a motor and/or a motor controller. The fault data of the electric drive assembly can be collected through bus collection equipment hung on a vehicle carrying the electric drive assembly. The fault data acquired by the default bus acquisition device are in a data format containing specific signal names, such as mdf, mf4 and the like. And when the terminal equipment performs fault diagnosis, acquiring fault data of the electric drive assembly through the bus acquisition equipment.
The terminal device can record fault labels corresponding to the fault data one by one in advance, so that after the fault data are obtained, the fault label of the electric drive assembly can be determined according to the fault label mapped by the fault data. For example, assuming that the fault data collected by the bus collection device hung on the vehicle is the data of the electric drive power reduction, the terminal device can extract the fault label mapped to the motor over-temperature fault as the fault label of the electric drive component according to the data of the electric drive power reduction.
After the fault label of the electric drive assembly is obtained, each associated state data corresponding to the fault label can be extracted from each state data of the electric drive assembly according to the association relation between the preset fault label and the state data. If the electric drive component is a motor and the fault label is an over-temperature fault of the motor, all state data corresponding to the over-temperature fault of the motor can be obtained from all state data of the motor as all associated state data according to the association relation between the fault label and the state data preset by the terminal equipment. For example, each associated status data corresponding to a motor over-temperature fault may include motor temperature, oil and water pump speeds and status, oil and water pump fault flags, controller current, motor speed, and the like.
After each associated state data is obtained, at least one associated state data may be taken as target state data. Then, for any target state data, a preset condition corresponding to the target state data can be obtained to judge whether the target state data meets the corresponding preset condition, so that a detection result of the target state data is obtained.
For example, assuming that the target state data is a motor temperature, a corresponding preset condition may be obtained as "whether the motor temperature reaches a threshold value". In this way, the detection result that the motor temperature reaches or does not reach the threshold value can be obtained by detecting whether the motor temperature reaches the threshold value.
After the detection results of the target state data are obtained, the detection results of the target state data are combined to form diagnosis data representing the cause of formation of the fault data, and the fault diagnosis result corresponding to the diagnosis data is matched as the fault diagnosis result of the electric drive assembly.
After the fault label of the electric drive assembly is determined through the fault data of the electric drive assembly, each associated state data corresponding to the fault label is extracted, at least one target state data in each associated state data is detected according to each preset condition corresponding to the associated state data one by one, and a fault diagnosis result of the electric drive assembly is obtained according to the detection result of each target state data, so that the state data associated with the fault of the electric drive assembly can be utilized to determine what condition is caused by the fault, the matching degree of the fault diagnosis result and the actual condition causing the fault is improved, and the accuracy of fault diagnosis of the electric drive assembly is further improved.
To further improve the accuracy of fault diagnosis, in some embodiments, extracting, from each state data of the power driving assembly, each associated state data corresponding to the fault label according to the fault label includes:
extracting each associated state data in a preset period from each state data of the electric drive assembly according to the fault label;
wherein the preset period includes a failure time at which the failure data is detected.
By taking a fault tag as an example of motor over-temperature fault, if the fault time when fault data is detected is T0, that is, the time when the fault occurs is T0, a preset time period T0 including the fault time T0 can be generated, for example, the preset time period T0 is determined according to the fault time T0, and then according to the fault tag of the motor over-temperature fault, relevant state data such as motor temperature, oil pump and water pump rotating speeds and states, oil pump and water pump fault tags, controller current, motor rotating speeds and the like in the time period T0 can be extracted from all state data of the electric drive assembly. Therefore, any extracted associated state data can be ensured to comprise the instantaneous data when the motor fails, so that the detection result obtained by using each associated state data can reflect the cause of the failure, and the accuracy of failure diagnosis is further improved.
To further improve the accuracy of the fault diagnosis, in some embodiments, the preset time period includes a first target time period before the fault time.
Taking a fault tag as an example of motor over-temperature fault, if the reason of motor over-temperature is that the accumulated temperature rise is up to a fault threshold value due to intermittent stalling of the water pump, if only instantaneous data of a fault moment are acquired, an un-stalled working point of the intermittent stalling of the water pump can be just acquired, the water pump is found to be at a normal working point but the motor is over-temperature according to the instantaneous data, and further the real reason that the motor over-temperature fault is caused by the intermittent stalling of the water pump cannot be deduced. Therefore, the preset period may be set to include the first target period before the fault time, for example, 60S, so as to cover most of the fault detection conditions, especially the relatively slow temperature rise overtemperature condition, where the temperature abnormality is accumulated, and a certain data support diagnosis before the fault is required. Therefore, any extracted associated state data can comprise the instantaneous data of the motor when the motor fails and the data before the motor fails, so that the detection result obtained by using each associated state data can reflect the cause of the failure, and the accuracy of fault diagnosis is further improved.
To further improve the accuracy of the fault diagnosis, in some embodiments, the preset time period includes a second target time period after the fault time.
Considering that when a plurality of faults are reported simultaneously or sequentially, the real cause of the faults is difficult to distinguish according to the instantaneous data at the moment of the faults, but the data when the faults enter the protection action after the faults occur can provide clues for fault diagnosis. Taking a fault tag as an interphase short circuit fault as an example, if the interphase of the motor is short-circuited accidentally, single-phase current flowing, multi-phase current flowing, a driving chip fault and the like are reported, and the motor controller enters an active short circuit after the fault. Firstly, judging whether a driving chip of a lower tube or an upper tube is normal according to a phase current waveform of a fault backward active short circuit, and if the driving chip is sinusoidal, judging that the driving chip of the backward active short circuit is normal; then judging whether the PWM control software has problems or not according to the PWM control instructions before and after the fault and the active short-circuit control instruction; and finally judging that the phase-to-phase short circuit is caused by the phase-to-phase short circuit according to the single-phase current flowing and the multiphase current flowing and the sine wave divergence mode of the single-phase current after the active short circuit, and the sine wave divergence of the single-phase current is caused by the active short circuit and the superimposed phase-to-phase short circuit. The diverging sine wave may in fact further cause the motor to overheat. If there is no data after failure, the motor can only be found out to be over-temperature through the data, and the true cause caused by the interphase short circuit cannot be deduced. Therefore, the preset period may be set to include the second target period after the fault time, for example, 60S, so as to cover most of fault detection conditions, especially the situation that the real cause of the fault may cause temperature rise and thus report an over-temperature fault. Therefore, any extracted associated state data can comprise the instantaneous data when the motor fails and the data after the motor fails, so that the detection result obtained by using each associated state data subsequently comprises the state representation after the failure of the electric drive assembly, the failure occurrence cause can be reflected by the state representation after the failure of the electric drive assembly, and the accuracy of failure diagnosis is further improved.
It is understood that the preset time period may include both the first target time period and the second target time period. When the preset time period comprises a first target time period and a second target time period at the same time, the associated state data comprise associated state data in the first target time period, associated state data at the fault moment and associated state data in the second target time period. Taking the associated state data as the motor temperature as an example, assuming that the fault time is t0, and the first target period and the second target period are both 60s apart from t0, the motor temperature acquired at this time comprises the motor temperature 60s before the t0 time, the motor temperature at the t0 time and the motor temperature 60s after the t0 time.
After each associated state data is obtained, any associated state data can be used as target state data, and then the target state data is detected by utilizing preset conditions corresponding to the target state data. If the target state data includes the target state data of the first target period, the fault time and the second target period, the target state data of the first target period, the fault time and the second target period can be detected respectively by using the preset condition. If the target state data is assumed to be the motor temperature, and the corresponding preset condition is that whether the motor temperature reaches the threshold value, whether the motor temperature in the first target period reaches the threshold value, whether the motor temperature in the fault moment reaches the threshold value, and whether the target state data in the second target period reaches the threshold value can be detected according to the preset condition, so as to obtain a corresponding detection result.
In order to improve the accuracy of the fault diagnosis result obtained later, each associated state data can be used as target state data for detection. However, this detection method requires a large data amount of the detected target state data. Meanwhile, because the association relationship exists between preset conditions, for example, between preset condition 1 of whether the temperature of the motor reaches a threshold value and preset condition 2 of whether the average value of the oil temperature of the motor is greater than the threshold value, if the preset condition 1 is not met, the preset condition 2 is not required to be checked. Therefore, if each associated state data is directly detected as the target state data, invalid detection may occur, and the detection efficiency may be affected.
For this purpose, in some embodiments, detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data, to obtain a detection result of each target state data includes:
and according to the dependency relationship of each preset condition, sequentially acquiring corresponding associated state data for detection, marking the currently detected associated state data as target state data for each detection, detecting the target state data according to the preset condition corresponding to the target state data, acquiring the next preset condition associated with the detection result after the detection result of the target state data is obtained, marking the next associated state data corresponding to the next preset condition as the target state data for detection until the next preset condition associated with the detection result cannot be acquired, and ending the detection of the target state data to obtain the detection result of each target state data.
In some embodiments, the terminal device may store in advance a fault diagnosis tree formed according to the association relationship of each preset condition. As shown in fig. 2, the fault diagnosis tree includes a plurality of nodes, each node represents a preset condition, if a connection path exists between the nodes, it represents that an association relationship exists between the two nodes, the connection path includes a connection attribute and a direction, where the connection attribute of the connection path represents a detection result of a start node of the connection path, and the direction of the connection path represents a judgment order between the two nodes. For example, the node a indicates whether the preset condition "the motor temperature reaches the threshold value 1", the node B indicates whether the preset condition "the average value of the motor oil temperature is greater than the threshold value 2", the node C indicates whether the preset condition "the average actual rotation speed of the motor oil pump and the average requested rotation speed deviation is greater than the threshold value 3", etc., a connection path from the node a to the node B exists between the node a and the node B, and the connection attribute of the connection path is yes, that is, the judgment of entering the node B is indicated when the detection result of the node a is yes. There is a connection path from node B to node C between node B and node C, and the connection attribute of the connection path is yes, that is, it means that when the detection result of node B is yes, the judgment of node C is entered. At this time, the dependency relationship of each preset condition can be determined according to the fault diagnosis tree.
In order to make the dependency of the preset conditions more accurate, in some embodiments, the dependency of each preset condition may be determined according to each historical detection result corresponding to the historical fault diagnosis result.
For example, assuming that the historical detection results are motor overtemperatures, and the corresponding historical detection results are that the motor temperature is greater than a threshold 1, the average value of the motor oil temperature is greater than a threshold 2, and the deviation of the average actual rotation speed and the average requested rotation speed of the motor oil pump is greater than a threshold 3, the sequence of the historical detection results can be determined to be that the motor temperature is greater than the threshold 1, the average value of the motor oil temperature is greater than the threshold 2, and the deviation of the average actual rotation speed and the average requested rotation speed of the motor oil pump is greater than the threshold 3 according to the fineness degree of the historical detection results, and after the sequence of the historical detection results is determined, the dependency relationship of the preset conditions corresponding to the historical detection results can be updated according to the sequence of the historical detection results. Thus, after the dependency relationship of each preset condition is updated for a plurality of times, each preset condition of which the dependency relationship is more in line with the actual situation can be obtained, and the accuracy of the detection result determined by the dependency relationship of each preset condition is improved.
After the dependency relationship of each preset condition is determined, the target state data can be sequentially obtained from each associated state data according to the dependency relationship for detection. For example, assuming that the dependency relationship of each preset condition is shown in fig. 2, where node a indicates that the preset condition "whether the motor temperature reaches the threshold 1", node B indicates that the preset condition "whether the average value of the motor oil temperature is greater than the threshold 2", and node C indicates that the preset condition "whether the average actual rotation speed of the motor oil pump and the average requested rotation speed deviation are greater than the threshold 3", the motor temperature may be first used as the target state data, and then input into node a, to determine whether the motor temperature reaches the threshold 1. If the detection result of the node a is yes, it indicates that the preset condition of the node B needs to be adopted for judgment, and at this time, the associated state data corresponding to the preset condition of the node B, that is, the motor oil temperature, can be used as the target state data, and the detection is performed through the preset condition of the node B. And analogically, ending the detection of the target state data until the next preset condition associated with the detection result cannot be obtained.
Taking the dependency relationship of each preset condition as shown in fig. 2 as an example, assume that the detection result of the node a is "no", that is, the motor temperature does not reach the threshold value 1, and at this time, since there is no connection path corresponding to the test result, the detection is ended, and the obtained detection result of each target state data is that the motor temperature does not reach the threshold value 1. Therefore, the association relation of each preset condition can be utilized to select the target state data for detection, the occurrence of invalid detection is reduced, and the detection efficiency is improved.
After the detection result of each target state data is obtained, the fault diagnosis result corresponding to the diagnosis data can be matched as the fault diagnosis result of the electric drive assembly according to the detection result of each target state data.
To make the matched fault diagnosis result more accurate, in some embodiments, obtaining the fault diagnosis result of the electric drive assembly according to each detection result includes:
obtaining diagnostic data representing the cause of the formation of the fault data according to each detection result;
and inputting the diagnosis data into a trained fault diagnosis model to obtain the fault diagnosis result.
In some embodiments, the fault diagnosis model may be a convolutional neural network model or the like. For the training of the fault diagnosis model, a plurality of diagnosis data representing the formation reasons of different fault data can be used as training samples, each training sample is sequentially input into the fault diagnosis model, after the fault diagnosis result output by the fault diagnosis model is obtained in each input, the fault diagnosis result is matched with a preset fault diagnosis result corresponding to the training sample input at this time. And under the condition that the two are not matched, adopting a gradient descent method, adjusting network parameters of the fault diagnosis model through error back propagation, and then performing next training until the fault diagnosis result obtained by each input training sample is matched with the preset fault diagnosis result corresponding to the current input training sample, and finishing the training of the fault diagnosis model to obtain a trained fault diagnosis model.
After the trained fault diagnosis model is obtained, the diagnosis data composed of all detection results can be input into the trained fault diagnosis model, so that the fault diagnosis result of the electric drive assembly is obtained.
The fault diagnosis apparatus provided in the present application will be described below, and the fault diagnosis apparatus described below and the fault diagnosis method described above may be referred to correspondingly to each other.
In one embodiment, as shown in fig. 3, there is provided a fault diagnosis apparatus including:
a fault tag determining module 210, configured to determine a fault tag of an electric driving component according to fault data of the electric driving component;
a state data obtaining module 220, configured to extract, according to the fault tag, each associated state data corresponding to the fault tag from each state data of the electric drive assembly;
the detection result obtaining module 230 is configured to detect at least one target state data in each associated state data according to preset conditions corresponding to each associated state data, so as to obtain a detection result of each target state data;
the diagnosis result obtaining module 240 is configured to obtain a fault diagnosis result of the electric drive assembly according to each detection result.
After the fault label of the electric drive assembly is determined through the fault data of the electric drive assembly, each associated state data corresponding to the fault label is extracted, at least one target state data in each associated state data is detected according to each preset condition corresponding to the associated state data one by one, and a fault diagnosis result of the electric drive assembly is obtained according to the detection result of each target state data, so that the state data associated with the fault of the electric drive assembly can be utilized to determine what condition is caused by the fault, the matching degree of the fault diagnosis result and the actual condition causing the fault is improved, and the accuracy of fault diagnosis of the electric drive assembly is further improved.
In one embodiment, the status data acquisition module 220 is specifically configured to:
extracting each associated state data in a preset period from each state data of the electric drive assembly according to the fault label;
wherein the preset period includes a failure time at which the failure data is detected.
In an embodiment, the preset period includes a first target period before the fault time.
In an embodiment, the preset time period includes a second target time period after the fault time.
In one embodiment, the detection result obtaining module 230 is specifically configured to:
and according to the dependency relationship of each preset condition, sequentially acquiring corresponding associated state data for detection, marking the currently detected associated state data as target state data for each detection, detecting the target state data according to the preset condition corresponding to the target state data, acquiring the next preset condition associated with the detection result after the detection result of the target state data is obtained, marking the next associated state data corresponding to the next preset condition as the target state data for detection until the next preset condition associated with the detection result cannot be acquired, and ending the detection of the target state data to obtain the detection result of each target state data.
In an embodiment, the dependency relationship of each preset condition is determined according to each historical detection result corresponding to the historical fault diagnosis result.
In one embodiment, the diagnostic result acquisition module 240 is specifically configured to:
obtaining diagnostic data representing the cause of the formation of the fault data according to each detection result;
and inputting the diagnosis data into a trained fault diagnosis model to obtain the fault diagnosis result.
Fig. 4 illustrates a physical schematic diagram of an electronic device, as shown in fig. 4, which may include: processor 810, communication interface (Communication Interface) 820, memory 830, and communication bus 840, wherein processor 810, communication interface 820, memory 830 accomplish communication with each other through communication bus 840. The processor 810 may call a computer program in the memory 830 to perform a fault diagnosis method, for example, including:
determining a fault label of the electric drive assembly according to fault data of the electric drive assembly;
extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and obtaining a fault diagnosis result of the electric drive assembly according to each detection result.
Further, the logic instructions in the memory 830 described above may be implemented in the form of software functional units and may be stored in a computer-readable storage medium when sold or used as a stand-alone product. Based on such understanding, the technical solution of the present application may be embodied essentially or in a part contributing to the prior art or in a part of the technical solution, in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods of the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In another aspect, embodiments of the present application further provide a storage medium, where the storage medium includes a computer program, where the computer program may be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer is capable of executing the fault diagnosis method provided in the foregoing embodiments, for example, including:
determining a fault label of the electric drive assembly according to fault data of the electric drive assembly;
extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and obtaining a fault diagnosis result of the electric drive assembly according to each detection result.
The apparatus embodiments described above are merely illustrative, wherein elements illustrated as separate elements may or may not be physically separate, and elements shown as elements may or may not be physical elements, may be located in one place, or may be distributed over a plurality of network elements. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of this embodiment. Those of ordinary skill in the art will understand and implement the present invention without undue burden.
From the above description of the embodiments, it will be apparent to those skilled in the art that the embodiments may be implemented by means of software plus necessary general hardware platforms, or of course may be implemented by means of hardware. Based on this understanding, the foregoing technical solution may be embodied essentially or in a part contributing to the prior art in the form of a software product, which may be stored in a computer readable storage medium, such as ROM/RAM, a magnetic disk, an optical disk, etc., including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only for illustrating the technical solution of the present application, and are not limiting thereof; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. A fault diagnosis method, characterized by comprising:
determining a fault label of the electric drive assembly according to fault data of the electric drive assembly;
extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and obtaining a fault diagnosis result of the electric drive assembly according to each detection result.
2. The fault diagnosis method according to claim 1, wherein extracting, from each state data of the electric drive component, each associated state data corresponding to the fault tag, based on the fault tag, comprises:
extracting each associated state data in a preset period from each state data of the electric drive assembly according to the fault label;
wherein the preset period includes a failure time at which the failure data is detected.
3. The fault diagnosis method according to claim 2, wherein the preset period includes a first target period before the fault time.
4. A fault diagnosis method according to claim 2 or 3, wherein the preset period includes a second target period after the fault time.
5. The fault diagnosis method according to claim 1 or 2, wherein detecting at least one target state data in each associated state data according to preset conditions respectively corresponding to each associated state data, to obtain a detection result of each target state data, comprises:
and according to the dependency relationship of each preset condition, sequentially acquiring corresponding associated state data for detection, marking the currently detected associated state data as target state data for each detection, detecting the target state data according to the preset condition corresponding to the target state data, acquiring the next preset condition associated with the detection result after the detection result of the target state data is obtained, marking the next associated state data corresponding to the next preset condition as the target state data for detection until the next preset condition associated with the detection result cannot be acquired, and ending the detection of the target state data to obtain the detection result of each target state data.
6. The method according to claim 5, wherein the dependency of each preset condition is determined based on each history detection result corresponding to the history fault diagnosis result.
7. The fault diagnosis method according to claim 1 or 2, wherein obtaining a fault diagnosis result of the electric drive assembly based on each of the detection results, comprises:
obtaining diagnostic data representing the cause of the formation of the fault data according to each detection result;
and inputting the diagnosis data into a trained fault diagnosis model to obtain the fault diagnosis result.
8. A fault diagnosis apparatus characterized by comprising:
the fault label determining module is used for determining a fault label of the electric driving assembly according to the fault data of the electric driving assembly;
the state data acquisition module is used for extracting each associated state data corresponding to the fault label from each state data of the electric drive assembly according to the fault label;
the detection result acquisition module is used for detecting at least one target state data in each associated state data according to preset conditions corresponding to each associated state data respectively to obtain a detection result of each target state data;
and the diagnosis result acquisition module is used for acquiring a fault diagnosis result of the electric drive assembly according to each detection result.
9. An electronic device comprising a processor and a memory storing a computer program, characterized in that the processor implements the fault diagnosis method of any one of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the fault diagnosis method of any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310723838.2A CN116466689B (en) | 2023-06-19 | 2023-06-19 | Fault diagnosis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310723838.2A CN116466689B (en) | 2023-06-19 | 2023-06-19 | Fault diagnosis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116466689A true CN116466689A (en) | 2023-07-21 |
| CN116466689B CN116466689B (en) | 2023-09-05 |
Family
ID=87179262
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310723838.2A Active CN116466689B (en) | 2023-06-19 | 2023-06-19 | Fault diagnosis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116466689B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117723965A (en) * | 2023-12-13 | 2024-03-19 | 上海正泰自动化软件***有限公司 | Motor fault detection method and device, storage medium and electronic equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187672A (en) * | 2018-02-22 | 2019-08-30 | 发那科株式会社 | Trouble-shooter and machine learning device |
| CN110943857A (en) * | 2019-11-20 | 2020-03-31 | 国网湖北省电力有限公司信息通信公司 | Power communication network fault analysis and positioning method based on convolutional neural network |
| CN112150596A (en) * | 2020-09-30 | 2020-12-29 | 国网智能科技股份有限公司 | Holographic reconstruction method and system for substation equipment fault |
| CN112183590A (en) * | 2020-09-14 | 2021-01-05 | 浙江大学 | Transformer fault diagnosis method based on Oneclass SVM algorithm |
| CN115398439A (en) * | 2021-04-16 | 2022-11-25 | 华为数字能源技术有限公司 | Fault early warning method and device for motor driver |
| CN115798078A (en) * | 2022-11-29 | 2023-03-14 | 永安行科技股份有限公司 | Vehicle accurate fault diagnosis method and device |
| CN115952096A (en) * | 2022-12-30 | 2023-04-11 | 华润数字科技有限公司 | Fault detection method, device, equipment and medium of data center software system |
-
2023
- 2023-06-19 CN CN202310723838.2A patent/CN116466689B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110187672A (en) * | 2018-02-22 | 2019-08-30 | 发那科株式会社 | Trouble-shooter and machine learning device |
| CN110943857A (en) * | 2019-11-20 | 2020-03-31 | 国网湖北省电力有限公司信息通信公司 | Power communication network fault analysis and positioning method based on convolutional neural network |
| CN112183590A (en) * | 2020-09-14 | 2021-01-05 | 浙江大学 | Transformer fault diagnosis method based on Oneclass SVM algorithm |
| CN112150596A (en) * | 2020-09-30 | 2020-12-29 | 国网智能科技股份有限公司 | Holographic reconstruction method and system for substation equipment fault |
| CN115398439A (en) * | 2021-04-16 | 2022-11-25 | 华为数字能源技术有限公司 | Fault early warning method and device for motor driver |
| CN115798078A (en) * | 2022-11-29 | 2023-03-14 | 永安行科技股份有限公司 | Vehicle accurate fault diagnosis method and device |
| CN115952096A (en) * | 2022-12-30 | 2023-04-11 | 华润数字科技有限公司 | Fault detection method, device, equipment and medium of data center software system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117723965A (en) * | 2023-12-13 | 2024-03-19 | 上海正泰自动化软件***有限公司 | Motor fault detection method and device, storage medium and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116466689B (en) | 2023-09-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116466689B (en) | Fault diagnosis method and device | |
| CN1254004C (en) | Method and devie for testing fault on stator winding of an AC motor | |
| CN108196154B (en) | Fault detection and fault positioning method for rotary rectifier of aviation three-stage synchronous motor | |
| CN104808642A (en) | Pump group automatic diagnosis method based on internet of things | |
| CN109725220B (en) | Detection method, system and device for transformer oil cooling loop | |
| CN109696627A (en) | A kind of motor in electric automobile three-phase power line Phase Faults method and device | |
| US20160195583A1 (en) | Fault diagnosing method based on standard deviation of detail coefficients for power converter of switched reluctance motor | |
| CN111830409A (en) | Motor thermal fault diagnosis method and device based on deep neural network | |
| CN106526479A (en) | Grid-harmonic-characteristic-based fault diagnosis method for electric system of electric shovel | |
| HS et al. | Electrical fault detection using machine learning algorithm for centrifugal water pumps | |
| CN111582463B (en) | Servo motor fault recognition and model training method, device, medium and terminal | |
| CN113503289A (en) | Hydraulic motor fault detection method, device and system and excavator | |
| CN113642123B (en) | Health assessment method and device for heat dissipation system of working machine and working machine | |
| CN116859240A (en) | Direct-current brushless motor fault identification method based on multiple sensors and edge calculation | |
| Shu et al. | DBF-CNN: A double-branch fusion residual CNN for diagnosis of induction motor broken rotor bar | |
| WO2022217597A1 (en) | Fault early-warning method and apparatus for motor driver | |
| KR102247179B1 (en) | Xai-based normal learning data generation method and device for unsupervised learning of abnormal behavior detection model | |
| CN108266364A (en) | Electric pump load too low method for diagnosing faults and device | |
| CN112034338B (en) | Phase current open circuit diagnosis method and device for electric power steering motor | |
| CN114384413A (en) | Motor state perception chip | |
| Matić et al. | Artificial neural networks eccentricity fault detection of induction motor | |
| Tsai et al. | On-line condition monitoring of servo motor drive systems by HHT in Industry 4.0 | |
| CN116559655A (en) | Wind driven generator stator fault detection method, device and fault early warning system | |
| CN116559725A (en) | Inter-turn short circuit diagnosis method, device and equipment for double three-phase permanent magnet synchronous motor | |
| CN116626486A (en) | Rotor broken bar fault diagnosis method, device and equipment of cage type asynchronous motor |
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 |