CN-121995788-A - Equipment fault prediction method and device and electronic equipment

CN121995788ACN 121995788 ACN121995788 ACN 121995788ACN-121995788-A

Abstract

The invention provides a device fault prediction method, a device and electronic equipment, equipment operation data of equipment to be detected are obtained, the equipment operation data are input into a pre-trained prediction model, so that the prediction model predicts faults of the equipment to be detected based on the equipment operation data to obtain a prediction result, the prediction result is used for indicating the probability and the type of the faults of the equipment to be detected in a future preset time period, if the probability of the faults indicated by the prediction result is greater than or equal to a preset probability threshold value, a parameter adjustment strategy is determined according to the type of the faults indicated by the prediction result, a parameter adjustment instruction is generated based on the parameter adjustment strategy, and the parameter adjustment instruction is sent to the equipment to be detected, so that the equipment to be detected automatically adjusts equipment parameters based on the parameter adjustment instruction. According to the method, the equipment operation data are collected, the prediction model is utilized to predict faults, the equipment parameters can be adjusted in advance to avoid faults, and the stability and maintenance efficiency of equipment operation are improved.

Inventors

MU KAITONG
XIE BIN
LEI PENGFEI
ZONG YI
XIE ZHUORUI
CHEN SHIXIAO

Assignees

广东芬尼克兹节能设备有限公司

Dates

Publication Date: 20260508
Application Date: 20251224

Claims (10)

1. A method of predicting equipment failure, the method comprising: Acquiring equipment operation data of equipment to be detected; Inputting the equipment operation data into a pre-trained prediction model so that the prediction model predicts the faults of the equipment to be detected based on the equipment operation data to obtain a prediction result, wherein the prediction result is used for indicating the occurrence probability and the occurrence type of the faults of the equipment to be detected in a preset time period in the future; If the fault occurrence probability indicated by the prediction result is greater than or equal to a preset probability threshold, determining a parameter adjustment strategy according to the fault occurrence type indicated by the prediction result, generating a parameter adjustment instruction based on the parameter adjustment strategy, and sending the parameter adjustment instruction to the equipment to be detected so that the equipment to be detected automatically adjusts equipment parameters based on the parameter adjustment instruction.
2. The method of claim 1, wherein the step of obtaining device operational data of the device to be tested comprises: and acquiring equipment operation data of the equipment to be detected in real time through an equipment sensor in the equipment to be detected, wherein the equipment operation data comprises equipment component working parameters and/or equipment operation environment parameters.
3. The method of claim 1 or 2, wherein prior to the step of inputting the plant operational data into a pre-trained predictive model, the method further comprises: Preprocessing the equipment operation data to obtain preprocessed equipment operation data, wherein the preprocessing comprises at least one processing mode of outlier rejection, complement missing values and standardized processing.
4. A method according to claim 3, wherein the step of inputting the plant operational data into a pre-trained predictive model comprises: Storing the preprocessed equipment operation data to a cloud platform database; and inputting the preprocessed equipment operation data stored in the cloud platform database into a pre-trained prediction model through a cloud platform.
5. The method of claim 4, wherein the step of generating parameter adjustment instructions based on the parameter adjustment policy and transmitting the parameter adjustment instructions to the device to be detected comprises: and generating a parameter adjustment instruction based on the parameter adjustment strategy, and sending the parameter adjustment instruction to the equipment to be detected through the cloud platform.
6. The method according to claim 1, wherein the predictive model is trained by: Constructing an initial test model according to the equipment type and the equipment operation scene of the equipment to be detected; And training the initial test model based on a preset training data set to obtain a test model after training, wherein the preset training data set comprises historical fault data and/or equipment operation data stored in a cloud platform database and a prediction result corresponding to the equipment operation data.
7. The method of claim 1, wherein the step of determining a parameter adjustment strategy based on the type of fault occurrence indicated by the prediction result comprises: And acquiring a parameter adjustment strategy matched with the fault occurrence type indicated by the prediction result from a preset fault and adjustment strategy relation library, wherein the fault and adjustment strategy relation library comprises a plurality of fault occurrence types and parameter adjustment strategies corresponding to each fault occurrence type.
8. An apparatus for predicting equipment failure, the apparatus comprising: The data acquisition module is used for acquiring equipment operation data of equipment to be detected; The fault prediction module is used for inputting the equipment operation data into a pre-trained prediction model so that the prediction model predicts the faults of the equipment to be detected based on the equipment operation data to obtain a prediction result, wherein the prediction result is used for indicating the occurrence probability and the occurrence type of the faults of the equipment to be detected in a preset time period in the future; And the parameter adjustment module is used for determining a parameter adjustment strategy according to the fault occurrence type indicated by the prediction result if the fault occurrence probability indicated by the prediction result is greater than or equal to a preset probability threshold, generating a parameter adjustment instruction based on the parameter adjustment strategy, and sending the parameter adjustment instruction to the equipment to be detected so that the equipment to be detected automatically adjusts equipment parameters based on the parameter adjustment instruction.
9. An electronic device comprising a processor and a memory, the memory stores computer executable instructions executable by the processor, the processor executing the computer-executable instructions to implement the device failure prediction method of any of claims 1-7.
10. A computer readable storage medium storing computer executable instructions which, when invoked and executed by a processor, cause the processor to implement the device fault prediction method of any one of claims 1-7.

Description

Equipment fault prediction method and device and electronic equipment Technical Field The present invention relates to the field of equipment fault processing technologies, and in particular, to a method and an apparatus for predicting equipment faults, and an electronic device. Background The traditional equipment fault treatment scheme mostly adopts a post-maintenance or regular preventive maintenance mode, and faults are judged only by means of manual inspection or a simple alarm function of the equipment, so that the potential value of equipment operation data and precursor characteristics before faults occur are completely ignored, and the problems of untimely fault early warning, low maintenance efficiency, poor operation stability, high comprehensive cost and the like exist in the traditional equipment fault treatment scheme. Disclosure of Invention In view of the above, the invention aims to provide a device fault prediction method, a device and an electronic device, so as to predict the device fault in advance and actively intervene, and ensure the continuous and stable operation of the device. The embodiment of the invention provides a device fault prediction method, which comprises the steps of obtaining device operation data of a device to be detected, inputting the device operation data into a pre-trained prediction model to enable the prediction model to conduct fault prediction on the device to be detected based on the device operation data to obtain a prediction result, wherein the prediction result is used for indicating the fault occurrence probability and the fault occurrence type of the device to be detected in a preset time period in the future, if the fault occurrence probability indicated by the prediction result is greater than or equal to a preset probability threshold value, determining a parameter adjustment strategy according to the fault occurrence type indicated by the prediction result, generating a parameter adjustment instruction based on the parameter adjustment strategy, and sending the parameter adjustment instruction to the device to be detected, so that the device to be detected automatically adjusts device parameters based on the parameter adjustment instruction. In an alternative embodiment, the step of acquiring the device operation data of the device to be detected includes collecting the device operation data of the device to be detected in real time through a device sensor in the device to be detected, wherein the device operation data includes a device component operation parameter and/or a device operation environment parameter. In an alternative embodiment, before the step of inputting the device operation data into the pre-trained prediction model, the method further comprises the step of preprocessing the device operation data to obtain preprocessed device operation data, wherein the preprocessing comprises at least one processing mode of outlier rejection, complement of missing values and standardization processing. In an alternative embodiment, the step of inputting the device operation data into the pre-trained prediction model includes storing the preprocessed device operation data into a cloud platform database, and inputting the preprocessed device operation data stored in the cloud platform database into the pre-trained prediction model through the cloud platform. In an alternative embodiment, the step of generating the parameter adjustment instruction based on the parameter adjustment policy and sending the parameter adjustment instruction to the device to be detected includes generating the parameter adjustment instruction based on the parameter adjustment policy and sending the parameter adjustment instruction to the device to be detected through the cloud platform. In an alternative embodiment, the prediction model is obtained through training by constructing an initial test model according to the equipment type and the equipment operation scene of equipment to be detected, and training the initial test model based on a preset training data set to obtain a test model after training, wherein the preset training data set comprises historical fault data and/or equipment operation data stored in a cloud platform database and prediction results corresponding to the equipment operation data. In an alternative embodiment, the step of determining the parameter adjustment policy according to the fault occurrence type indicated by the prediction result includes obtaining a parameter adjustment policy matched with the fault occurrence type indicated by the prediction result from a preset fault and adjustment policy relation library, where the fault and adjustment policy relation library includes multiple fault occurrence types and parameter adjustment policies corresponding to each fault occurrence type. The device comprises a data acquisition module, a fault prediction module and a parameter adjustment module, wherein the data acquisition module is used for