CN-122020583-A - Fault positioning method, device, equipment and program product based on association rule

CN122020583ACN 122020583 ACN122020583 ACN 122020583ACN-122020583-A

Abstract

The embodiment of the application provides a fault locating method, device, equipment and program product based on association rules. Relates to the field of fault diagnosis of energy storage systems. The method comprises the steps of obtaining a state code, a fault code and operation parameters of energy storage thermal management equipment, generating a fault rule base by adopting an association rule mining algorithm based on the state code, the fault code and the operation parameters, screening abnormal data deviating from a standard by performing unsupervised cluster analysis on the operation parameters, fusing the abnormal data with the fault rule base to generate a fault map, and outputting a fault positioning report of the energy storage thermal management equipment based on the fault map, wherein the fault positioning report at least comprises a fault propagation path and an overhaul scheme, and the fault propagation path is a path of a causal relation between the fault code and the abnormal mode. The method is used for achieving the effect of improving the fault positioning efficiency and accuracy.

Inventors

QU JINGJING
HUANG QIANWEN
LIU LU
JI XUEYUAN
WU QIANQIAN
QU SHUAI

Assignees

北京海博思创科技股份有限公司

Dates

Publication Date: 20260512
Application Date: 20251230

Claims (11)

1. The fault positioning method based on the association rule is characterized by comprising the following steps of: The method comprises the steps of acquiring a state code, a fault code and an operation parameter of energy storage thermal management equipment, wherein the state code indicates an identifier of the current operation state of the equipment, the fault code indicates an identifier of the fault of the energy storage thermal management equipment, and the operation parameter indicates a continuity parameter acquired in the operation process of the energy storage thermal management equipment; Generating a fault rule base by adopting an association rule mining algorithm based on the state code, the fault code and the operation parameter, wherein the fault rule base comprises association rules among the state code, the fault code and the operation parameter, and the association rule mining algorithm is used for finding implicit association among data item sets; Screening abnormal data deviating from the standard by performing unsupervised cluster analysis on the operation parameters; Fusing the abnormal data with the fault rule base to generate a fault map; based on the fault map, outputting a fault positioning report of the energy storage thermal management device, wherein the fault positioning report at least comprises a fault propagation path and an overhaul scheme, and the fault propagation path is a path of causal relation between the fault code and an abnormal mode.
2. The method of claim 1, wherein the generating a fault rule base using an association rule mining algorithm based on the status code, the fault code, and the operating parameter comprises: Screening association rules between the state code and the operation parameters based on a support degree, a confidence degree and a lifting degree, wherein the support degree represents the frequency of the simultaneous occurrence of the state code and the operation parameters, the confidence degree represents the probability of the simultaneous occurrence of the operation parameters when the state code occurs, and the lifting degree is used for measuring the independence between the state code and the operation parameters; generating a fault rule base based on the association rule and the association rule mining algorithm; the device aging index is used for reflecting the comprehensive index of the running state of the energy storage heat management device; and updating the fault rule base based on the adjusted confidence threshold.
3. The method of claim 2, wherein after the screening the association rules between the status code and the operating parameters based on the support, the confidence and the promotion, further comprising: adjusting a confidence threshold based on an operating environment change of the energy storage thermal management device, wherein the operating environment change comprises an ambient temperature or load fluctuation; the weight of the association rule is dynamically adjusted according to the historical accuracy rate, wherein the historical accuracy rate represents the historical data of the fault positioning accuracy rate of the association rule in the fault rule base; And updating the fault rule base based on the confidence threshold and the weight of the association rule.
4. The method of claim 1, wherein screening out abnormal data deviating from a standard by performing an unsupervised clustering analysis on the operating parameters comprises: Extracting multi-dimensional characteristics of the operation parameters, wherein the multi-dimensional characteristics comprise time sequence characteristics, spatial distribution characteristics and equipment aging indexes, the time sequence characteristics are characteristics reflecting the change of the operation parameters along with time, and the spatial distribution characteristics represent the layout relation between equipment and a battery cluster; And performing unsupervised clustering analysis based on the multidimensional features, and screening out abnormal data deviating from the standard.
5. The method of claim 1, wherein the fusing the anomaly data with the fault rule base to generate a fault map comprises: Determining an abnormal mode of the operation parameter through unsupervised cluster analysis; And constructing a fault map based on the association rules in the fault rule base and the abnormal mode, wherein the fault map comprises a device state code layer, an operation parameter layer and an abnormal mode layer.
6. The method of claim 5, further comprising, after generating the fault map: And screening fault propagation paths in the fault map based on a causal reasoning algorithm, and eliminating false association paths caused by environmental factors.
7. The method according to any one of claims 1 to 6, further comprising: And adjusting the fault rule base based on a feedback reinforcement learning algorithm, wherein the feedback reinforcement learning algorithm adjusts the weight of the association rule according to the verification result.
8. A fault locating device based on association rules, comprising: The system comprises an acquisition module, a state code acquisition module and a control module, wherein the acquisition module is used for acquiring a state code, a fault code and an operation parameter of the energy storage thermal management equipment, the state code indicates an identifier of the current operation state of the equipment, the fault code indicates an identifier of the fault of the energy storage thermal management equipment, and the operation parameter indicates a continuity parameter acquired in the operation process of the energy storage thermal management equipment; the first generation module is used for generating a fault rule base by adopting an association rule mining algorithm based on the state code, the fault code and the operation parameter, wherein the fault rule base comprises association rules among the state code, the fault code and the operation parameter, and the association rule mining algorithm is used for finding implicit association among data item sets; the screening module is used for screening abnormal data deviating from the standard by performing unsupervised cluster analysis on the operation parameters; the second generation module is used for fusing the abnormal data with the fault rule base to generate a fault map; The output module is used for outputting a fault positioning report of the energy storage heat management equipment based on the fault map, wherein the fault positioning report at least comprises a fault propagation path and an overhaul scheme, and the fault propagation path is a path of causal relation between the fault code and the abnormal mode.
9. An electronic device is characterized by comprising a memory and a processor; The memory stores computer-executable instructions; The processor executing computer-executable instructions stored in the memory, causing the processor to perform the method of any one of claims 1-7.
10. A computer readable storage medium having stored therein computer executable instructions which when executed by a processor are adapted to carry out the method of any one of claims 1-7.
11. A computer program product comprising a computer program which, when executed by a processor, implements the method of any of claims 1-7.

Description

Fault positioning method, device, equipment and program product based on association rule Technical Field The present application relates to the field of fault diagnosis of energy storage systems, and in particular, to a fault positioning method, apparatus, device and program product based on association rules. Background In the energy storage system, a large amount of heat can be generated in the charging and discharging process of the internal battery cluster, and the temperature needs to be regulated in real time through energy storage heat management equipment, so that the out-of-control heating or equipment damage caused by over-temperature is prevented. When the energy storage heat management equipment breaks down, the safe and stable operation of the battery cluster is affected, and therefore, the fault location of the energy storage heat management equipment is crucial. At present, the existing fault locating method mainly carries out fault locating based on abnormal detection of a threshold value. The method mainly comprises the step of judging whether the equipment is abnormal or not through presetting threshold ranges of parameters such as temperature, pressure, current and the like. However, the method relies on experience, so that the existing fault positioning method has low fault positioning efficiency and poor accuracy. Disclosure of Invention The application provides a fault positioning method, device, equipment and program product based on association rules, which are used for achieving the effect of improving the efficiency and accuracy of fault positioning. In a first aspect, the present application provides a fault locating method based on association rules, the method comprising: The method comprises the steps of acquiring a state code, a fault code and an operation parameter of energy storage thermal management equipment, wherein the state code indicates an identifier of the current operation state of the equipment, the fault code indicates an identifier of the fault of the energy storage thermal management equipment, and the operation parameter indicates a continuity parameter acquired in the operation process of the energy storage thermal management equipment; Generating a fault rule base by adopting an association rule mining algorithm based on the state code, the fault code and the operation parameter, wherein the fault rule base comprises association rules among the state code, the fault code and the operation parameter, and the association rule mining algorithm is used for finding implicit association among data item sets; Screening abnormal data deviating from the standard by performing unsupervised cluster analysis on the operation parameters; Fusing the abnormal data with the fault rule base to generate a fault map; based on the fault map, outputting a fault positioning report of the energy storage thermal management device, wherein the fault positioning report at least comprises a fault propagation path and an overhaul scheme, and the fault propagation path is a path of causal relation between the fault code and an abnormal mode. In one possible implementation manner, the generating a fault rule base by using an association rule mining algorithm based on the status code, the fault code and the operation parameter includes: Screening association rules between the state code and the operation parameters based on a support degree, a confidence degree and a lifting degree, wherein the support degree represents the frequency of the simultaneous occurrence of the state code and the operation parameters, the confidence degree represents the probability of the simultaneous occurrence of the operation parameters when the state code occurs, and the lifting degree is used for measuring the independence between the state code and the operation parameters; generating a fault rule base based on the association rule and the association rule mining algorithm; the device aging index is used for reflecting the comprehensive index of the running state of the energy storage heat management device; and updating the fault rule base based on the adjusted confidence threshold. In a possible implementation manner, after the screening of the association rule between the status code and the operation parameter based on the support degree, the confidence degree and the promotion degree, the method further includes: adjusting a confidence threshold based on an operating environment change of the energy storage thermal management device, wherein the operating environment change comprises an ambient temperature or load fluctuation; the weight of the association rule is dynamically adjusted according to the historical accuracy rate, wherein the historical accuracy rate represents the historical data of the fault positioning accuracy rate of the association rule in the fault rule base; And updating the fault rule base based on the confidence threshold and the weight of the association rule. In one possible