Fault prediction method and device, equipment and storage medium

Abstract

The invention discloses a fault prediction method and device, equipment and a storage medium, and relates to the technical field of power electronics, and the method comprises the steps: obtaining the current performance data of power equipment, adjusting a pre-trained fault prediction model according to the current performance data, and obtaining a target fault prediction model, the fault prediction model is used for determining fault attributes according to the performance data, and the fault attributes at least comprise fault time, fault position, fault type and fault degree; inputting the current performance data into a performance prediction model, so that the performance prediction model determines predicted performance data according to the current performance data; and when it is determined that the data trend of the predicted performance data is data deviation, inputting the current performance data into the target fault prediction model, so that the target fault prediction model determines a fault attribute according to the current performance data. According to the technical scheme, when the predicted performance data corresponding to the current performance data deviates, the fault attribute is determined according to the current performance data, and accurate and timely fault prediction is achieved.

Description

Technical Field

[0001] Embodiments of the present invention relate to the field of power electronics technology, and in particular to a fault prediction method, device, equipment and storage medium. Background Art

[0002] In the field of equipment maintenance, traditional maintenance strategies mainly include regular inspections and emergency repairs after a fault occurs. These maintenance strategies are often discovered only after the fault has occurred and caused damage, resulting in high maintenance costs and extended equipment downtime, which in turn affects service continuity and user satisfaction.

[0003] In the existing technology, artificial intelligence-based fault prediction technology has begun to be applied to equipment maintenance. It can predict potential faults by analyzing the historical data and real-time data of the equipment, thereby achieving more timely maintenance.

[0004] However, the accuracy of fault prediction by predictive models directly based on equipment data is not high. Summary of the invention

[0005] The present invention provides a fault prediction method, device, equipment and storage medium to improve the accuracy of fault prediction.

[0006] In a first aspect, an embodiment of the present invention provides a fault prediction method, comprising:

[0007] Obtain current performance data of power equipment;

[0008] Adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree;

[0009] Inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data;

[0010] When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

[0011] The technical solution of an embodiment of the present invention provides a fault prediction method, including: obtaining current performance data of power equipment; adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree; inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data according to the current performance data; when it is determined that the data trend of the predicted performance data is a data deviation, inputting the current performance data into the target fault prediction model so that the target fault prediction model determines the fault attributes according to the current performance data. The above technical scheme can first obtain the current performance data of each power equipment in the power system through sensors, and secondly, fine-tune the fault prediction model according to the current performance data obtained in real time to obtain a target fault prediction model that better matches the current performance data. Then, the current performance data can be input into the performance prediction model, and the predicted performance data corresponding to the current performance data can be determined through the performance prediction model to achieve prediction of the performance data, and then the data trend of the predicted performance data can be determined. When it is determined that the data trend of the predicted performance data is a data deviation, it is determined that there is a power equipment that may fail, and the current performance data is input into the target fault prediction model, and fault prediction is performed through the target fault prediction model to improve the accuracy and timeliness of fault prediction.

[0012] Furthermore, the current performance data of the power equipment is obtained, including:

[0013] The temperature change, vibration state, operating noise, current load, pressure change and operating frequency of the electric equipment are obtained based on the temperature sensor, vibration sensor, sound sensor, current sensor, pressure sensor and frequency sensor integrated in the electric equipment.

[0014] Further, adjusting the pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model includes:

[0015] updating the fault prediction model in real time according to the current performance data gradually received to obtain the target fault prediction model;

[0016] Alternatively, the fault prediction model is incrementally updated according to the current performance data to obtain the target fault prediction model.

[0017] Furthermore, after determining the predicted performance data, it also includes:

[0018] Determine a first change rate of each of the predicted performance data relative to its corresponding current performance data, and a second change rate of each of the predicted performance data relative to its corresponding baseline performance data;

[0019] The data trend of the predicted performance data is determined based on a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data.

[0020] Further, determining the data trend of the predicted performance data according to a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data, includes:

[0021] In the case where it is determined that the first change rate of any of the predicted performance data is greater than the first preset change rate, and / or the second change rate of any of the predicted performance data is greater than the second preset change rate, determining that the data trend of the predicted performance data is a data deviation;

[0022] Otherwise, it is determined that the data trend of the predicted performance data is normal.

[0023] Furthermore, after determining the fault attribute, the method further includes:

[0024] When it is determined that the fault degree is of low risk, self-healing control is performed on the fault location before the fault time according to the fault type.

[0025] Furthermore, after determining the fault attribute, the method further includes:

[0026] A fault maintenance plan is generated according to the fault attributes and current maintenance resources, and fault maintenance is performed on the fault location based on the fault maintenance plan.

[0027] In a second aspect, an embodiment of the present invention further provides a fault prediction device, comprising:

[0028] An acquisition module, used to acquire current performance data of the power equipment;

[0029] an adjustment module, configured to adjust a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree;

[0030] a determination module, configured to input the current performance data into a performance prediction model, so that the performance prediction model determines predicted performance data based on the current performance data;

[0031] The execution module is used to input the current performance data into the target fault prediction model when determining that the data trend of the predicted performance data is data deviation, so that the target fault prediction model determines the fault attribute according to the current performance data.

[0032] In a third aspect, an embodiment of the present invention further provides an electronic device, the electronic device comprising:

[0033] at least one processor; and a memory communicatively coupled to the at least one processor;

[0034] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault prediction method as described in any one of the first aspects.

[0035] In a fourth aspect, an embodiment of the present invention further provides a storage medium comprising computer executable instructions, wherein the computer executable instructions, when executed by a computer processor, are used to execute the fault prediction method as described in any one of the first aspects.

[0036] In a fifth aspect, the present application provides a computer program product, which includes computer instructions. When the computer instructions are executed on a computer, the computer executes the fault prediction method provided in the first aspect.

[0037] It should be noted that the above computer instructions may be stored in whole or in part on a computer-readable storage medium, wherein the computer-readable storage medium may be packaged together with the processor of the fault prediction device, or may be packaged separately from the processor of the fault prediction device, which is not limited in this application.

[0038] The description of the second, third, fourth and fifth aspects in this application can refer to the detailed description of the first aspect; and the beneficial effects of the description of the second, third, fourth and fifth aspects can refer to the beneficial effect analysis of the first aspect, which will not be repeated here.

[0039] In this application, the name of the above-mentioned fault prediction device does not limit the device or functional module itself. In actual implementation, these devices or functional modules may appear with other names. As long as the functions of each device or functional module are similar to those of this application, they fall within the scope of the claims of this application and their equivalent technologies.

[0040] These and other aspects of the present application will become more apparent from the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0042] Figure 1 A flowchart of a fault prediction method provided by an embodiment of the present invention;

[0043] Figure 2 A flowchart of another fault prediction method provided by an embodiment of the present invention;

[0044] Figure 3 A schematic diagram of the structure of a fault prediction device provided by an embodiment of the present invention;

[0045] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The present invention will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the present invention, rather than to limit the present invention. It should also be noted that, for ease of description, only parts related to the present invention, rather than all structures, are shown in the accompanying drawings.

[0047] The term "and / or" in this article is merely a description of the association relationship of associated objects, indicating that three relationships may exist. For example, A and / or B can mean: A exists alone, A and B exist at the same time, and B exists alone.

[0048] The terms "first" and "second" and the like in the specification and drawings of this application are used to distinguish different objects, or to distinguish different processing of the same object, rather than to describe a specific order of objects.

[0049] In addition, the terms "including" and "having" and any variations thereof mentioned in the description of the present application are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include other steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.

[0050] It should be mentioned before discussing exemplary embodiments in more detail that some exemplary embodiments are described as processes or methods depicted as flow charts. Although the flow charts describe various operations (or steps) as sequential processes, many operations therein can be implemented in parallel, concurrently or simultaneously. In addition, the order of various operations can be rearranged. The process can be terminated when its operation is completed, but can also have additional steps not included in the accompanying drawings. The process can correspond to methods, functions, procedures, subroutines, subprograms, etc. In addition, the embodiments in the present invention and the features in the embodiments can be combined with each other without conflict.

[0051] It should be noted that, in the embodiments of the present application, words such as "exemplary" or "for example" are used to indicate examples, illustrations or descriptions. Any embodiment or design described as "exemplary" or "for example" in the embodiments of the present application should not be interpreted as being more preferred or more advantageous than other embodiments or designs. Specifically, the use of words such as "exemplary" or "for example" is intended to present related concepts in a specific way.

[0052] In the description of the present application, unless otherwise specified, “plurality” means two or more.

[0053] Figure 1 A flowchart of a fault prediction method provided by an embodiment of the present invention is provided. This embodiment is applicable to situations where accurate prediction of equipment faults is required. The method can be executed by a fault prediction device, such as Figure 1 As shown, the specific steps include:

[0054] Step 110: Obtain current performance data of the power equipment.

[0055] The power equipment of the power system may include power generation equipment and power supply equipment, etc. The performance data of the power equipment may include temperature change, vibration state, operating noise, current load, pressure change and operating frequency, etc.

[0056] Specifically, the current performance data of each power device can be obtained when the power system is running. Specifically, the temperature change, vibration state, operating noise, current load, pressure change and operating frequency of each power device can be obtained through sensors.

[0057] In the embodiment of the present invention, the current performance data of each power device in the power system is acquired through sensors.

[0058] Step 120: Adjust the pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model.

[0059] The fault prediction model is used to determine fault attributes according to performance data, and the fault attributes at least include fault time, fault location, fault type and fault degree.

[0060] Specifically, the fault prediction model is deployed in an adaptive learning engine, which is integrated with an online learning mechanism. The online learning mechanism can fine-tune the fault prediction model according to the current performance data obtained to obtain a target fault prediction model that is more compatible with the current performance data. The target fault prediction model can make more accurate fault predictions for power equipment based on the current performance data.

[0061] The online learning mechanism allows the fault prediction model to be updated instantly based on the current performance data without retraining the entire model. The fault prediction model can be adjusted in time according to the performance changes of the power equipment, thereby achieving rapid response to the performance changes of the power equipment and continuous optimization of the fault prediction model.

[0062] In the embodiment of the present invention, fine-tuning of the fault prediction model is achieved according to the current performance data acquired in real time, so as to obtain a target fault prediction model that better matches the current performance data.

[0063] Step 130: Input the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data.

[0064] Among them, the performance prediction model is obtained by training an autoregressive integrated moving average model by obtaining historical performance data in a first historical time period and target performance data in a second historical time period after the first historical time period. The performance prediction model can learn the changing trend of performance data over time and predict the future value of performance data.

[0065] Specifically, the current performance data may be input into a performance prediction model, and the performance prediction model may predict predicted performance data corresponding to the current performance data based on the learned trend of performance data changes over time, thereby realizing the prediction of performance data.

[0066] In the embodiment of the present invention, the predicted performance data corresponding to the current performance data is determined by a performance prediction model to achieve prediction of the performance data.

[0067] In actual applications, step 120 and step 130 may be executed after step 110, and the specific execution order of step 120 and step 130 is not specifically limited. For example, step 120 may be executed first and then step 130, or step 130 may be executed first and then step 120, or step 120 and step 130 may be executed simultaneously.

[0068] Step 140: When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

[0069] Specifically, after determining the predicted performance data corresponding to the current performance data, the data trend of the predicted performance data can be determined based on the current performance data and the predicted performance data or the benchmark performance data corresponding to the current performance data. Specifically, if any predicted performance data deviates from the current performance data or the benchmark performance data corresponding to the predicted performance data, the data trend of the predicted performance data is determined to be data deviation. At this time, it can be determined that the performance of the power equipment corresponding to the predicted performance data has a tendency to deteriorate, and further it can be determined that the power equipment corresponding to the predicted performance data may fail in the future.

[0070] When it is determined that the data trend of the predicted performance data is data deviation, the current performance data can be input into the target fault prediction model so that the target fault prediction model determines the fault attributes based on the current performance data, that is, at least determines the fault time, fault location, fault type and fault degree.

[0071] In an embodiment of the present invention, by determining the data trend of the predicted performance data of the power equipment, it is possible to determine whether there is power equipment that may fail. When it is determined that there is power equipment that may fail, the fault attribute is determined through the target fault prediction model, thereby improving the accuracy and timeliness of the fault prediction.

[0072] The fault prediction method provided by an embodiment of the present invention includes: obtaining current performance data of power equipment; adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree; inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data according to the current performance data; and when it is determined that the data trend of the predicted performance data is a data deviation, inputting the current performance data into the target fault prediction model so that the target fault prediction model determines the fault attributes according to the current performance data. The above technical scheme can first obtain the current performance data of each power equipment in the power system through sensors, and secondly, fine-tune the fault prediction model according to the current performance data obtained in real time to obtain a target fault prediction model that better matches the current performance data. Then, the current performance data can be input into the performance prediction model, and the predicted performance data corresponding to the current performance data can be determined through the performance prediction model to achieve prediction of the performance data, and then the data trend of the predicted performance data can be determined. When it is determined that the data trend of the predicted performance data is a data deviation, it is determined that there is a power equipment that may fail, and the current performance data is input into the target fault prediction model, and fault prediction is performed through the target fault prediction model to improve the accuracy and timeliness of fault prediction.

[0073] Figure 2 This is a flowchart of another fault prediction method provided by an embodiment of the present invention. This embodiment is specific based on the above embodiment. Figure 2 As shown, in this embodiment, the method may further include:

[0074] Step 210: Obtain current performance data of the power equipment.

[0075] In one implementation, step 210 may specifically include:

[0076] The temperature change, vibration state, operating noise, current load, pressure change and operating frequency of the electric equipment are obtained based on the temperature sensor, vibration sensor, sound sensor, current sensor, pressure sensor and frequency sensor integrated in the electric equipment.

[0077] Specifically, the current performance data of each power equipment can be obtained when the power system is running. Specifically, the temperature data, vibration data, sound data, power data, pressure data and frequency data of each power equipment can be obtained through the temperature sensors, vibration sensors, sound sensors, current sensors, pressure sensors and frequency sensors integrated in each power equipment, and then the temperature change, vibration state, operating noise, current load, pressure change and operating frequency of each power equipment can be determined.

[0078] In practical applications, after obtaining the current performance data of each power device, the current performance data can be processed, for example, filtering, denoising and normalizing the current performance data to reduce noise and interference in the current performance data and improve the accuracy of subsequent analysis.

[0079] In the embodiment of the present invention, the current performance data of each power device in the power system is acquired through sensors.

[0080] Step 220: Adjust the pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model.

[0081] The fault prediction model is used to determine fault attributes according to performance data, and the fault attributes at least include fault time, fault location, fault type and fault degree.

[0082] In one implementation, step 220 may specifically include:

[0083] The fault prediction model is updated in real time according to the current performance data gradually received to obtain the target fault prediction model; or, the fault prediction model is incrementally updated according to the current performance data to obtain the target fault prediction model.

[0084] Specifically, on the one hand, the fault prediction model can be updated in real time by using an online learning mechanism based on the current performance data that is gradually received to obtain a target fault prediction model. On the other hand, the fault prediction model can be incrementally updated based on the current performance data to obtain a target fault prediction model. Moreover, during the model updating process, the performance of the fault prediction model is continuously monitored to ensure that the prediction accuracy of the fault prediction model is not reduced.

[0085] It should be noted that when updating the fault prediction model in real time, data stream processing technology can be used to process the current performance data, and an automated model update strategy can be used to update the fault prediction model to ensure that the model can efficiently process continuous data streams and automatically adjust when necessary.

[0086] In the embodiment of the present invention, fine-tuning of the fault prediction model is achieved according to the current performance data acquired in real time, so as to obtain a target fault prediction model that better matches the current performance data.

[0087] Step 230: Input the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data.

[0088] Similarly, step 220 and step 230 may be executed after step 210, and the specific execution order of step 220 and step 230 is not specifically limited. For example, step 220 may be executed first and then step 230, or step 230 may be executed first and then step 220, or step 220 and step 230 may be executed simultaneously.

[0089] Step 240: Determine a first change rate of each of the predicted performance data relative to its corresponding current performance data, and a second change rate of each of the predicted performance data relative to its corresponding baseline performance data.

[0090] Among them, the benchmark performance data can be understood as the mean of historical performance data. By conducting in-depth analysis of the historical performance data of power equipment under normal operating conditions, the benchmark performance data of each performance data of the power equipment can be calculated. The benchmark performance data is the reference standard for the health status of the power equipment.

[0091] Specifically, for each predicted performance data, the difference between the predicted performance data and its corresponding current performance data can be determined, and then the first change rate of the predicted performance data relative to its corresponding current performance data can be determined based on the ratio of this difference to the predicted performance data. The difference between the predicted performance data and its corresponding baseline performance data can also be determined, and then the second change rate of the predicted performance data relative to its corresponding baseline performance data can be determined based on the ratio of this difference to the predicted performance data.

[0092] In the embodiment of the present invention, a first change rate of each predicted performance data relative to its corresponding current performance data and a second change rate of each predicted performance data relative to its corresponding baseline performance data are determined.

[0093] Step 250: Determine the data trend of the predicted performance data based on a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data.

[0094] In one implementation, step 250 may specifically include:

[0095] When it is determined that the first change rate of any of the predicted performance data is greater than the first preset change rate, and / or when the second change rate of any of the predicted performance data is greater than the second preset change rate, the data trend of the predicted performance data is determined to be data deviation; otherwise, the data trend of the predicted performance data is determined to be data normal.

[0096] Among them, the first preset change rate is the maximum change rate of the predicted performance data relative to the current performance data. If the change rate of the predicted performance data relative to the current performance data is greater than the first preset change rate, it means that the data trend of the predicted performance data may deviate. The second preset change rate is the maximum change rate of the predicted performance data relative to the baseline performance data. If the change rate of the predicted performance data relative to the baseline performance data is greater than the second preset change rate, it means that the data trend of the predicted performance data may deviate.

[0097] Specifically, for each predicted performance data, the first change rate of the predicted performance data and the first preset change rate can be compared, and the second change rate of the predicted performance data can be compared to be greater than the second preset change rate. When it is determined that the first change rate of any predicted performance data is greater than the first preset change rate, the data trend of the predicted performance data is determined to be data deviation; when it is determined that the second change rate of any predicted performance data is greater than the second preset change rate, the data trend of the predicted performance data is determined to be data deviation; when it is determined that the first change rate of any predicted performance data is greater than the first preset change rate and the second change rate is greater than the second preset change rate, the data trend of the predicted performance data is determined to be data deviation; otherwise, the data trend of the predicted performance data is determined to be normal.

[0098] In practical applications, in order to improve accuracy, after determining that the data trends of the predicted performance data are all data deviations for five consecutive times, the data trend of the predicted performance data may be determined to be data deviation.

[0099] Of course, the data trend of the predicted performance data can also be determined based on anomaly detection algorithms such as isolation forests or single-class support vector machines. Specifically, it can be determined whether the predicted performance data deviates from its corresponding benchmark performance data, and when it is continuously determined that the predicted performance data for a preset time period deviates from its corresponding benchmark performance data, the data trend of the predicted performance data is determined to be data deviation. By quickly identifying possible performance anomalies, the data trend of the predicted performance data can be quickly determined.

[0100] In the embodiment of the present invention, the data trend of the predicted performance data is evaluated based on the long-term trend of the performance data predicted by the performance prediction model, the real-time data and the benchmark data.

[0101] Step 260: When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

[0102] Among them, the target fault prediction model is obtained by adjusting the fault prediction model through the current performance data. The fault prediction model is obtained by training a network model composed of a convolutional neural network and a recurrent neural network with sample performance data and the actual fault attributes corresponding to the sample performance data. It is used to determine the fault time, fault location, fault type and fault degree according to the current performance data. The fault type may include bearing failure, motor failure, pump failure, sensor failure, controller or actuator failure, and the fault degree may include low risk, medium risk and high risk.

[0103] When training the network model, the loss function can be minimized. Optimize the model weights, where y i represents the actual fault attributes corresponding to the sample performance data, It represents the fault attribute corresponding to the sample performance data determined by the network model, and N represents the data volume of the sample performance data. The network model parameters are automatically adjusted based on the back propagation algorithm and gradient descent method to adapt to changes in equipment performance.

[0104] The fault prediction model can predict potential faults and achieve rapid prediction and location of faults by performing time series analysis and feature extraction on the current performance data of each power device in the power system, identifying the abnormal state of the performance data, and thus predicting potential faults. In particular, it can predict the fault time, fault location, and fault type, and then determine the fault extent based on the fault type. In addition, the network model can also include long-term and short-term memory network units to enhance the model's understanding of time dependence and improve the accuracy of fault prediction. It is also possible to determine the impact of various faults on the performance, safety, cost, and operation of the power system by statistically analyzing historical fault data, and then determine the probability of the occurrence of the fault. It is also possible to analyze the specific impact of the fault on the performance of the power system, such as downtime, degree of performance degradation, etc. After determining the fault time, fault location, and fault type, the position of the fault in the risk matrix can be determined based on the importance of the fault location to the power system and the probability of the fault occurring, so as to determine the fault extent based on the risk matrix. The risk matrix is ​​a two-dimensional table, with the horizontal axis representing the probability of a fault and the vertical axis representing the importance of the fault location to the power system. Therefore, low-risk areas, medium-risk areas, and high-risk areas can be delineated in the risk matrix, that is, areas where the probability of a fault is less than a preset probability and the importance of the fault location to the power system is less than a preset degree can be delineated as low-risk areas, areas where the probability of a fault is greater than a preset probability and the importance of the fault location to the power system is greater than a preset degree can be delineated as high-risk areas, and other areas can be delineated as medium-risk areas. By locating the fault in the corresponding area of ​​the risk matrix, the degree of the fault can be determined, and high-risk faults that need to be handled first can be quickly identified.

[0105] Specifically, when it is determined that the data trend of the predicted performance data is a data deviation, the current performance data can be input into the target fault prediction model, and the target fault prediction model can determine the fault time, fault location, fault type and fault degree according to the current performance data.

[0106] In an embodiment of the present invention, when it is determined that the data trend of the predicted performance data of the power equipment is a data deviation, it can be determined that there is a power equipment that may fail, and then the fault attribute can be determined through the target fault prediction model, thereby improving the accuracy and timeliness of fault prediction.

[0107] Step 270: When it is determined that the fault level is low risk, self-healing control is performed on the fault location before the fault time according to the fault type.

[0108] Low-risk faults can be understood as early or minor faults that will not immediately cause the power equipment to stop operating completely, but may affect the performance of the power equipment or indicate more serious problems, such as slight performance degradation, slight temperature increase, slight delay in response time, slight vibration or noise increase, software warnings, minor network communication problems, and minor glitches in the user interface. Such faults can be automatically detected and repaired through self-healing control. The recovery strategy library includes self-healing control strategies for different fault types.

[0109] Specifically, low-risk faults can generally be maintained through the self-healing control function of the power system. Therefore, when the fault level is determined to be low risk, self-healing control can be performed on the fault location before the fault time according to the fault type. Specifically, a self-healing control strategy predefined for the fault type can be executed at the fault location according to the fault type, such as increasing the flow of the cooling equipment, adjusting the speed of the fan, restarting the network interface, or restarting the device to restore the normal function of the fault location without human intervention, thereby improving the reliability of the power equipment and reducing maintenance costs.

[0110] In addition, the self-healing control function with a real-time feedback mechanism can self-learn and optimize according to the results of fault handling. If the maintenance operation of the self-healing control for the fault type fails to restore the normal function of the fault location, the system will record the cause of the failure and adjust the self-healing control strategy.

[0111] In the embodiment of the present invention, when it is determined that the fault degree is low risk, a self-healing control strategy corresponding to the fault type is implemented to perform self-healing control on the predicted fault before the fault time, thereby avoiding further aggravation of the fault.

[0112] Step 280: Generate a fault maintenance plan according to the fault attributes and current maintenance resources, and perform fault maintenance on the fault location based on the fault maintenance plan.

[0113] Specifically, the current maintenance resources and the fault attributes of each predicted fault can be evaluated based on the resource optimization algorithm, and maintenance resources can be allocated to each predicted fault according to the fault attributes of each predicted fault and the current maintenance resources. The fault maintenance plan for each predicted fault is determined with maximizing resource utilization and minimizing maintenance costs as constraints, and fault maintenance is performed on the fault location based on the fault maintenance plan.

[0114] In actual applications, the fault maintenance plan can be automatically adjusted based on information such as the execution status of maintenance tasks, fault resolution, resource consumption, actual costs, equipment status updates, unexpected discoveries, user satisfaction, technician feedback, environmental factors, safety reports, time tracking, and quality control results fed back from on-site feedback, so as to reallocate resources to faults and ensure the continuity and effectiveness of fault maintenance work.

[0115] In an embodiment of the present invention, a fault maintenance plan is generated according to fault attributes and current maintenance resources, and fault maintenance is performed on the fault location based on the fault maintenance plan, thereby achieving timely and effective maintenance of the predicted fault based on the maintenance resources allocated for the predicted fault, effectively avoiding the occurrence of the fault.

[0116] The fault prediction method provided by the embodiment of the present invention includes: obtaining current performance data of the power equipment; adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model; inputting the current performance data into the performance prediction model so that the performance prediction model determines the predicted performance data according to the current performance data; determining a first change rate of each predicted performance data relative to its corresponding current performance data, and a second change rate of each predicted performance data relative to its corresponding benchmark performance data; determining the data trend of the predicted performance data according to a first preset change rate and a first change rate corresponding to each predicted performance data, and a second preset change rate and a second change rate corresponding to each predicted performance data; when it is determined that the data trend of the predicted performance data is a data deviation, inputting the current performance data into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data; when it is determined that the fault degree is a low risk, performing self-healing control on the fault location before the fault time according to the fault type; generating a fault maintenance plan according to the fault attribute and current maintenance resources, and performing fault maintenance on the fault location based on the fault maintenance plan. The above technical solution can firstly obtain the current performance data of each power equipment in the power system through sensors, and secondly, fine-tune the fault prediction model according to the current performance data obtained in real time to obtain a target fault prediction model that better matches the current performance data, and then input the current performance data into the performance prediction model, and determine the predicted performance data corresponding to the current performance data through the performance prediction model to achieve the prediction of the performance data, and then determine the first change rate of each predicted performance data relative to its corresponding current performance data, and the second change rate of each predicted performance data relative to its corresponding benchmark performance data, according to the first preset change rate corresponding to each predicted performance data. The first change rate, as well as the second change rate corresponding to the second preset change rate and each predicted performance data, determine the data trend of the predicted performance data, and evaluate the data trend of the predicted performance data based on the long-term trend of the performance data predicted by the performance prediction model, real-time data and benchmark data. Through this multi-dimensional analysis, a more comprehensive understanding of the predicted performance of the equipment is achieved, which facilitates timely discovery and response to potential failures of the equipment. When it is determined that the data trend of the predicted performance data is a data deviation, it is determined that there is a possible faulty power equipment, and the current performance data is input into the target fault prediction model. Fault prediction is performed through the target fault prediction model to improve the accuracy and timeliness of fault prediction.

[0117] Furthermore, when the fault level is determined to be low risk, the self-healing control strategy corresponding to the fault type is used to perform self-healing control on the predicted fault before the fault time, thus avoiding further aggravation of the fault. A fault maintenance plan is generated based on the fault attributes and current maintenance resources, and fault maintenance is performed on the fault location based on the fault maintenance plan. Timely and effective maintenance of the predicted fault based on the maintenance resources allocated for the predicted fault effectively avoids the occurrence of the fault, ultimately achieving rapid fault location and maintenance, and significantly improving the maintenance efficiency of the fault.

[0118] Figure 3 This is a schematic diagram of the structure of a fault prediction device provided by an embodiment of the present invention, which can be applied to situations where accurate prediction of equipment faults is required to improve the accuracy of fault prediction. The device can be implemented by software and / or hardware and is generally integrated in electronic equipment, such as computer equipment.

[0119] like Figure 3 As shown, the device comprises:

[0120] An acquisition module 310 is used to acquire current performance data of the power equipment;

[0121] An adjustment module 320, configured to adjust a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree;

[0122] A determination module 330, configured to input the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data;

[0123] The execution module 340 is used to input the current performance data into the target fault prediction model when determining that the data trend of the predicted performance data is data deviation, so that the target fault prediction model determines the fault attribute according to the current performance data.

[0124] The fault prediction device provided in this embodiment obtains current performance data of the power equipment; adjusts a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree; inputs the current performance data into the performance prediction model so that the performance prediction model determines predicted performance data according to the current performance data; and when it is determined that the data trend of the predicted performance data is a data deviation, inputs the current performance data into the target fault prediction model so that the target fault prediction model determines the fault attributes according to the current performance data. The above technical scheme can first obtain the current performance data of each power equipment in the power system through sensors, and secondly, fine-tune the fault prediction model according to the current performance data obtained in real time to obtain a target fault prediction model that better matches the current performance data. Then, the current performance data can be input into the performance prediction model, and the predicted performance data corresponding to the current performance data can be determined through the performance prediction model to achieve prediction of the performance data, and then the data trend of the predicted performance data can be determined. When it is determined that the data trend of the predicted performance data is a data deviation, it is determined that there is a power equipment that may fail, and the current performance data is input into the target fault prediction model, and fault prediction is performed through the target fault prediction model to improve the accuracy and timeliness of fault prediction.

[0125] Based on the above embodiment, the acquisition module 310 is specifically used for:

[0126] The temperature change, vibration state, operating noise, current load, pressure change and operating frequency of the electric equipment are obtained based on the temperature sensor, vibration sensor, sound sensor, current sensor, pressure sensor and frequency sensor integrated in the electric equipment.

[0127] Based on the above embodiment, the adjustment module 320 is specifically used for:

[0128] The fault prediction model is updated in real time according to the current performance data gradually received to obtain the target fault prediction model; or, the fault prediction model is incrementally updated according to the current performance data to obtain the target fault prediction model.

[0129] Based on the above embodiment, the device further includes:

[0130] A trend determination module is used to determine, after determining the predicted performance data, a first change rate of each predicted performance data relative to its corresponding current performance data, and a second change rate of each predicted performance data relative to its corresponding baseline performance data; and determine the data trend of the predicted performance data based on a first preset change rate and the first change rate corresponding to each predicted performance data, and a second preset change rate and the second change rate corresponding to each predicted performance data.

[0131] In one embodiment, determining the data trend of the predicted performance data according to a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data, includes:

[0132] When it is determined that the first change rate of any of the predicted performance data is greater than the first preset change rate, and / or when the second change rate of any of the predicted performance data is greater than the second preset change rate, the data trend of the predicted performance data is determined to be data deviation; otherwise, the data trend of the predicted performance data is determined to be data normal.

[0133] Based on the above embodiment, the device further includes:

[0134] The control module is used to, after determining the fault attribute, perform self-healing control on the fault location before the fault time according to the fault type when determining that the fault degree is low risk.

[0135] Based on the above embodiment, the device further includes:

[0136] The maintenance module is used to generate a fault maintenance plan according to the fault attributes and current maintenance resources after determining the fault attributes, and perform fault maintenance on the fault location based on the fault maintenance plan.

[0137] The fault prediction device provided in the embodiment of the present invention can execute the fault prediction method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of executing the fault prediction method.

[0138] It is worth noting that in the embodiment of the above-mentioned fault prediction device, the various units and modules included are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the scope of protection of the present invention.

[0139] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. Figure 4A block diagram of an exemplary electronic device 4 suitable for implementing embodiments of the present invention is shown. Figure 4 The electronic device 4 shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0140] like Figure 4 As shown, the electronic device 4 is in the form of a general purpose computing electronic device. The components of the electronic device 4 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 connecting different system components (including the system memory 28 and the processing unit 16).

[0141] Bus 18 represents one or more of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, a processor or a local bus using any of a variety of bus architectures. By way of example, these architectures include, but are not limited to, an Industry Standard Architecture (ISA) bus, a Micro Channel Architecture (MAC) bus, an Enhanced ISA bus, a Video Electronics Standards Association (VESA) local bus, and a Peripheral Component Interconnect (PCI) bus.

[0142] The electronic device 4 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by the electronic device 4, including volatile and non-volatile media, removable and non-removable media.

[0143] The system memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. The electronic device 4 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, the storage system 34 may be used to read and write non-removable, non-volatile magnetic media ( Figure 4 not shown, usually called a "hard drive"). Although Figure 4 Not shown in the figure, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk"), and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, a DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to the bus 18 via one or more data medium interfaces. The system memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to perform the functions of the various embodiments of the present invention.

[0144] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in system memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which or some combination may include an implementation of a network environment. Program modules 42 generally perform the functions and / or methods of the embodiments described herein.

[0145] The electronic device 4 may also communicate with one or more external devices 14 (e.g., keyboards, pointing devices, displays 24, etc.), one or more devices that enable a user to interact with the electronic device 4, and / or any device that enables the electronic device 4 to communicate with one or more other computing devices (e.g., network cards, modems, etc.). Such communication may be performed via an input / output (I / O) interface 22. Furthermore, the electronic device 4 may also communicate with one or more networks (e.g., a local area network (LAN), a wide area network (WAN), and / or a public network, such as the Internet) via a network adapter 20. Figure 4 As shown, the network adapter 20 communicates with other modules of the electronic device 4 via the bus 18. It should be understood that although Figure 4 Not shown, other hardware and / or software modules may be used in conjunction with the electronic device 4, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0146] The processing unit 16 executes various functional applications and page displays by running the program stored in the system memory 28, for example, implementing the fault prediction method provided by the embodiment of the present invention, the method comprising:

[0147] Obtain current performance data of power equipment;

[0148] Adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree;

[0149] Inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data;

[0150] When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

[0151] Of course, those skilled in the art can understand that the processor can also implement the technical solution of the fault prediction method provided by any embodiment of the present invention.

[0152] An embodiment of the present invention provides a computer-readable storage medium on which a computer program is stored. When the program is executed by a processor, for example, a fault prediction method provided by an embodiment of the present invention is implemented. The method includes:

[0153] Obtain current performance data of power equipment;

[0154] Adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree;

[0155] Inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data;

[0156] When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

[0157] The computer storage medium of the embodiment of the present invention can adopt any combination of one or more computer-readable media. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable storage medium can be, for example, but not limited to: an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive list) of computer-readable storage media include: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium can be any tangible medium containing or storing a program, which can be used by an instruction execution system, device or device or used in combination with it.

[0158] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.

[0159] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.

[0160] Computer program code for performing the operations of the present invention may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0161] It should be understood by those skilled in the art that the modules or steps of the present invention described above can be implemented by a general-purpose computing device, they can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, optionally, they can be implemented by a program code executable by a computer device, so that they can be stored in a storage device and executed by the computing device, or they can be made into individual integrated circuit modules, or multiple modules or steps therein can be made into a single integrated circuit module for implementation. Thus, the present invention is not limited to any specific combination of hardware and software.

[0162] In addition, the acquisition, storage, use, and processing of data in the technical solution of the present invention are in compliance with the relevant provisions of national laws and regulations.

[0163] Note that the above are only preferred embodiments of the present invention and the technical principles used. Those skilled in the art will understand that the present invention is not limited to the specific embodiments herein, and that various obvious changes, readjustments and substitutions can be made by those skilled in the art without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in more detail through the above embodiments, the present invention is not limited to the above embodiments, and may include more other equivalent embodiments without departing from the concept of the present invention, and the scope of the present invention is determined by the scope of the appended claims.

Claims

1. A fault prediction method, characterized in that: include: Obtain current performance data of power equipment; Adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree; Inputting the current performance data into a performance prediction model so that the performance prediction model determines predicted performance data based on the current performance data; When it is determined that the data trend of the predicted performance data is a data deviation, the current performance data is input into the target fault prediction model so that the target fault prediction model determines the fault attribute according to the current performance data.

2. The fault prediction method according to claim 1, characterized in that: Get current performance data of power equipment, including: The temperature change, vibration state, operating noise, current load, pressure change and operating frequency of the electric equipment are obtained based on the temperature sensor, vibration sensor, sound sensor, current sensor, pressure sensor and frequency sensor integrated in the electric equipment.

3. The fault prediction method according to claim 1, characterized in that: Adjusting a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model includes: updating the fault prediction model in real time according to the current performance data gradually received to obtain the target fault prediction model; Alternatively, the fault prediction model is incrementally updated according to the current performance data to obtain the target fault prediction model.

4. The fault prediction method according to claim 1, characterized in that: After determining the predicted performance data, also include: Determine a first change rate of each of the predicted performance data relative to its corresponding current performance data, and a second change rate of each of the predicted performance data relative to its corresponding baseline performance data; The data trend of the predicted performance data is determined based on a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data.

5. The fault prediction method according to claim 4, characterized in that: Determining the data trend of the predicted performance data according to a first preset change rate and a first change rate corresponding to each of the predicted performance data, and a second preset change rate and a second change rate corresponding to each of the predicted performance data, includes: In the case where it is determined that the first change rate of any of the predicted performance data is greater than the first preset change rate, and / or the second change rate of any of the predicted performance data is greater than the second preset change rate, determining that the data trend of the predicted performance data is a data deviation; Otherwise, it is determined that the data trend of the predicted performance data is normal.

6. The fault prediction method according to claim 1, characterized in that: After determining the fault attributes, it also includes: When it is determined that the fault degree is of low risk, self-healing control is performed on the fault location before the fault time according to the fault type.

7. The fault prediction method according to claim 1, characterized in that: After determining the fault attributes, it also includes: A fault maintenance plan is generated according to the fault attributes and current maintenance resources, and fault maintenance is performed on the fault location based on the fault maintenance plan.

8. A fault prediction device, characterized in that: include: An acquisition module, used to acquire current performance data of the power equipment; an adjustment module, configured to adjust a pre-trained fault prediction model according to the current performance data to obtain a target fault prediction model, wherein the fault prediction model is used to determine fault attributes according to the performance data, and the fault attributes include at least fault time, fault location, fault type and fault degree; a determination module, configured to input the current performance data into a performance prediction model, so that the performance prediction model determines predicted performance data based on the current performance data; The execution module is used to input the current performance data into the target fault prediction model when determining that the data trend of the predicted performance data is data deviation, so that the target fault prediction model determines the fault attribute according to the current performance data.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively coupled to the at least one processor; The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the fault prediction method as described in any one of claims 1-7.

10. A storage medium containing computer executable instructions, characterized in that: The computer executable instructions are used to perform the fault prediction method according to any one of claims 1 to 7 when executed by a computer processor.

Images