Power equipment fault diagnosis system and method based on artificial intelligence

Abstract

The invention discloses a power equipment fault diagnosis system and method based on artificial intelligence, and relates to the technical field of fault diagnosis, and the method comprises the following steps: collecting the operation data of power equipment, and obtaining the operation data; performing feature extraction according to the operation data to obtain feature data; performing fault type classification according to the feature data to obtain a fault classification result; performing fault positioning according to the fault classification result to obtain a fault positioning result; performing equipment health state evaluation according to the fault positioning result to obtain an evaluation result; performing fault prediction according to the evaluation result to obtain a fault prediction result; and performing maintenance decision support according to a fault prediction result. According to the method, the accuracy and adaptability of fault positioning are improved, the capability of processing multiple faults is improved, the response speed and precision of fault prediction are improved, the risks of equipment shutdown and damage are reduced, and the reliability and stability of a power system are improved.

Description

Technical Field

[0001] This invention relates to the field of fault diagnosis technology, specifically to a power equipment fault diagnosis system and method based on artificial intelligence. Background Technology

[0002] With the rapid development of smart grids, equipment in power systems is becoming increasingly complex, and traditional manual maintenance methods can no longer meet the growing demand for equipment fault detection and repair. Research on power equipment fault diagnosis methods has become an important direction for improving the stability and reliability of power systems.

[0003] Existing technologies have shortcomings in fault location: most existing fault location methods are based on static analysis methods and simple models, which cannot take into account the fault propagation path and the interrelationship of power equipment, comprehensively analyze the fault propagation path, and are difficult to handle multiple faults. The accuracy and adaptability of fault location are insufficient.

[0004] Existing technologies for fault prediction have shortcomings: existing fault prediction technologies mainly rely on statistical models, rule-based methods, or simple machine learning models, which are not sensitive enough to the changing trends of equipment health status, resulting in poor performance in complex equipment or rapidly changing environments, and are prone to misjudgment or omission. Summary of the Invention

[0005] To address the shortcomings of existing technologies, this invention provides an artificial intelligence-based power equipment fault diagnosis system and method to solve the problems mentioned in the background section.

[0006] To achieve the above objectives, the present invention provides the following technical solution:

[0007] In a first aspect, embodiments of the present invention provide a power equipment fault diagnosis system and method based on artificial intelligence, comprising the following steps:

[0008] S1. Power equipment operation data acquisition, obtaining operation data;

[0009] S2. Extract features from the running data to obtain feature data;

[0010] S3. Classify the fault types based on the feature data to obtain the fault classification results;

[0011] S4. Based on the fault classification results, locate the fault and obtain the fault location results;

[0012] S5. Based on the fault location results, conduct an equipment health status assessment to obtain the assessment results;

[0013] S6. Based on the evaluation results, perform fault prediction to obtain the fault prediction results;

[0014] S7. Provide maintenance decision support based on fault prediction results.

[0015] To further optimize this technical solution, the feature extraction in S2 includes:

[0016] The obtained operational data is standardized, and a feature analysis extraction model is used to extract features from the processed data to extract the changing features during equipment operation.

[0017] To further optimize this technical solution, the feature analysis and extraction model includes:

[0018] ;

[0019] in:

[0020] : The time-frequency energy distribution at frequency f and time t;

[0021] Adaptive weighting coefficients;

[0022] : The k-th wavelet basis function;

[0023] Sensor data; * indicates a convolution operation.

[0024] The number of wavelet basis functions.

[0025] To further optimize this technical solution, the fault location in S4 includes:

[0026] Based on the fault classification results, a fault location model is used to analyze the propagation path of the fault in the power equipment and locate the fault.

[0027] To further optimize this technical solution, the fault location model includes:

[0028] ;

[0029] in:

[0030] The probability that node i will fail;

[0031] : Propagation intensity coefficient;

[0032] : Confidence level of fault type classification;

[0033] : The electrical distance between node j and node i;

[0034] Total number of nodes.

[0035] To further optimize this technical solution, the propagation intensity coefficient includes:

[0036] ;

[0037] in:

[0038] Electrical impedance between node i and node j;

[0039] : The maximum value of electrical impedance;

[0040] : Electrical inductance between point i and node j;

[0041] : The maximum value of electrical inductance.

[0042] To further optimize this technical solution, the equipment health status assessment in S5 includes:

[0043] Based on the fault location results and combined with the equipment's historical operating data, a Bayesian network-based inference method is used to assess the equipment's health status.

[0044] To further optimize this technical solution, the fault prediction in S6 includes:

[0045] Based on the assessment results, a fault prediction model is used to analyze the equipment's historical operating data and health assessment information to predict the probability of equipment failure.

[0046] To further optimize this technical solution, the fault prediction model includes:

[0047] ;

[0048] in:

[0049] : The predicted probability of equipment failure at time t+T;

[0050] : Health status assessment result of device i at time t;

[0051] Weighting coefficients;

[0052] : Dynamic adjustment coefficient;

[0053] The rate of change of health status over time;

[0054] Attenuation coefficient;

[0055] Total number of devices.

[0056] This technical solution has been further optimized, including the following functional modules:

[0057] The system includes a data acquisition and processing module, a feature extraction module, a fault classification module, a fault location module, an equipment evaluation module, a fault prediction module, and a decision support module.

[0058] In a second aspect, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, wherein: when the computer program instructions are executed by the processor, they implement the steps of the artificial intelligence-based power equipment fault diagnosis system and method described in the first aspect of the present invention.

[0059] Thirdly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program instructions are executed by a processor, they implement the steps of the artificial intelligence-based power equipment fault diagnosis system and method described in the first aspect of the present invention.

[0060] Compared with existing technologies, the present invention provides an artificial intelligence-based power equipment fault diagnosis system and method, which has the following beneficial effects:

[0061] This AI-based power equipment fault diagnosis system and method, through a fault location model, can efficiently and accurately locate fault sources and their propagation paths in complex power equipment networks, improving the accuracy and adaptability of fault location and enhancing the ability to handle multiple faults.

[0062] By combining fault prediction models with equipment health status assessment results and historical data, the changing trends of equipment health status can be reflected in real time, improving the response speed and accuracy of fault prediction, reducing the risk of equipment downtime and damage, and improving the reliability and stability of the power system. Attached Figure Description

[0063] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0064] Figure 1 This is a flowchart illustrating an artificial intelligence-based fault diagnosis method for power equipment proposed in this invention.

[0065] Figure 2 This is a flowchart illustrating the fault location model of an artificial intelligence-based power equipment fault diagnosis method proposed in this invention.

[0066] Figure 3 This is a flowchart illustrating the fault prediction model of an artificial intelligence-based power equipment fault diagnosis method proposed in this invention.

[0067] Figure 4 This is a schematic diagram of a power equipment fault diagnosis system based on artificial intelligence proposed in this invention. Detailed Implementation

[0068] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0069] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0070] Secondly, the term "an embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places throughout this specification does not necessarily refer to the same embodiment, nor is it a single embodiment or an embodiment selectively excluded from other embodiments.

[0071] Example 1:

[0072] Reference Figures 1-3 This is the first embodiment of the present invention, which provides a power equipment fault diagnosis method based on artificial intelligence, including the following steps:

[0073] S1. Power equipment operation data acquisition, to obtain operation data.

[0074] In this embodiment, the data acquisition process includes:

[0075] By installing sensors, including temperature sensors, current sensors, voltage sensors, vibration sensors, and pressure sensors, in different parts of key equipment, real-time operating data of the power equipment is collected, including various data such as temperature, current, voltage, vibration, and pressure, providing a data foundation for subsequent diagnostic analysis.

[0076] S2. Extract features from the running data to obtain feature data.

[0077] In this embodiment, feature extraction includes:

[0078] The obtained operational data is standardized, and a feature extraction model is used to extract features from the processed data, revealing the changing characteristics during equipment operation. The data after feature extraction reflects different operating states of the equipment, providing crucial information for subsequent classification and diagnosis.

[0079] Furthermore, the feature analysis and extraction model includes:

[0080] ;

[0081] in:

[0082] : The time-frequency energy distribution at frequency f and time t;

[0083] Adaptive weighting coefficients adjust the role of each wavelet basis function in the time-frequency space, and optimize the adjustment based on the historical operating status and fault modes of the equipment;

[0084] : The k-th wavelet basis function;

[0085] Sensor data; * indicates a convolution operation.

[0086] The number of wavelet basis functions.

[0087] This model extracts features through wavelet transform and time-frequency analysis.

[0088] Compared with traditional wavelet transform or time-frequency analysis methods, this model combines wavelet transform and time-frequency analysis, and adopts a weighting mechanism and adaptive adjustment, so that information from different frequency bands can be extracted preferentially according to the characteristics of the fault, thereby enhancing the diagnostic accuracy.

[0089] The use of the above model includes:

[0090] Data preparation: Data from multiple sensors is acquired in step S1. This includes various data such as temperature, current, voltage, vibration, and pressure.

[0091] Time-frequency analysis: Adaptive weighting coefficients are set based on the equipment's historical operating status and known fault modes. Through convolution operations * The signal response is calculated at each frequency band and time point to obtain the energy distribution at each time frequency point. This transforms the time-domain signal into time-frequency domain features;

[0092] Feature extraction: in time-frequency energy distribution In this process, key frequency bands and time windows are selected to extract features that describe the health status of the equipment. For example, when the equipment is overloaded or short-circuited, energy fluctuations in certain frequency bands become obvious, and these changes are extracted as key diagnostic criteria.

[0093] S3. Classify the fault types based on the feature data to obtain the fault classification results.

[0094] In this embodiment, the fault type classification includes:

[0095] Based on feature data, Support Vector Machine (SVM) (existing technology) is used to distinguish different categories of data, classify fault types, and determine whether the equipment has failed and the type of fault. SVM can effectively handle high-dimensional data and has good generalization ability in feature space.

[0096] S4. Based on the fault classification results, locate the fault and obtain the fault location results.

[0097] In this embodiment, fault location includes:

[0098] Based on the fault classification results, a fault location model is used to analyze the propagation path of the fault in the power equipment, infer the specific location of the fault, and perform fault location.

[0099] Furthermore, the fault location model includes:

[0100] ;

[0101] in:

[0102] : The probability of node i failing; each node represents a device or component.

[0103] : Propagation intensity coefficient, representing the fault propagation intensity from node j to node i;

[0104] The classification confidence of the fault type is obtained through step S4;

[0105] The electrical distance between node j and node i; the closer the electrical distance, the greater the impact of fault propagation.

[0106] Total number of nodes.

[0107] Furthermore, the propagation intensity coefficient includes:

[0108] ;

[0109] in:

[0110] The electrical impedance between node i and node j; the smaller the impedance, the easier it is for current to propagate, and the stronger the fault propagation intensity.

[0111] The maximum electrical impedance is used as a standardization factor to make a uniform comparison of the propagation intensity between devices with different electrical characteristics.

[0112] The electrical inductance between point i and node j; the larger the inductance, the slower the response to a fault and the weaker the propagation strength.

[0113] The maximum value of electrical inductance is used as a standardization factor to adjust for the influence of inductance.

[0114] This model combines fault tree analysis and fault propagation networks to deduce fault sources and their propagation paths based on classification results in the context of complex power equipment topologies.

[0115] Unlike traditional fault location methods, this method not only infers fault location based on fault tree analysis, but also considers the fault propagation path and the interrelationship of power equipment. It identifies multiple fault modes in complex power systems, accurately locates the source of different types of faults, and can be adjusted according to the actual topology of the power network, thus improving the accuracy and adaptability of fault location.

[0116] The steps for using this model include:

[0117] Data input: Obtain the confidence level for each fault type in step S4. This reflects the possible types of equipment failures and their accuracy, providing an important basis for fault location;

[0118] Fault propagation path analysis: by calculating the propagation strength coefficient Electrical distance between and equipment Analyze the fault propagation path and identify how the fault spreads to other devices;

[0119] Fault location: based on the calculated probability of node failure. By comparing the failure probabilities of each node in the system, the most likely source of failure is determined. If multiple failures exist, the failure propagation path is combined to determine which devices or components may be the source of secondary failures.

[0120] S5. Based on the fault location results, conduct an equipment health status assessment to obtain the assessment results.

[0121] In this embodiment, the equipment health status assessment includes:

[0122] Based on the fault location results and combined with the equipment's historical operating data, a Bayesian network-based inference method (existing technology) is used to comprehensively analyze the equipment's fault modes, operating environment, and life cycle to conduct an equipment health status assessment. This method helps to assess the equipment's remaining service life and provides data support for subsequent maintenance decisions.

[0123] S6. Based on the evaluation results, perform fault prediction to obtain the fault prediction results.

[0124] In this embodiment, fault prediction includes:

[0125] Based on the assessment results, a fault prediction model is used to analyze the equipment's historical operating data and health assessment information to predict the probability of equipment failure.

[0126] Furthermore, the fault prediction model includes:

[0127] ;

[0128] in:

[0129] : The predicted probability of equipment failure at time t+T;

[0130] : The health status assessment result of device i at time t. The higher the value, the healthier the device; the lower the value, the greater the possibility of device failure.

[0131] Weighting coefficients reflect the impact of different equipment health states on overall fault prediction;

[0132] : Dynamic adjustment coefficient, reflecting the impact of the rate of change in health status on overall fault prediction;

[0133] The rate of change of health status over time;

[0134] Attenuation coefficient: describes the attenuation trend of the equipment's failure probability over a future period of time, and is adjusted according to the equipment's service life and working environment;

[0135] Total number of devices.

[0136] This model combines equipment health status, historical fault data, and time-series characteristics to achieve more accurate fault prediction.

[0137] Compared with traditional prediction methods based on fixed models or relying solely on historical data, this model introduces a dynamic adjustment mechanism, enabling fault prediction to be optimized based on the real-time status and historical trends of the equipment, thereby improving the accuracy and response speed of fault prediction.

[0138] The steps for using the model include:

[0139] Data Acquisition: Obtain the health status assessment results in step S6. And calculate the rate of change of health status over time. Capture device health trends;

[0140] Parameter adjustment: Adjust the weighting coefficients of the device health status based on the acquired data. Coefficient of the rate of change in health status This improves the model's prediction accuracy and reduces errors in equipment failure prediction.

[0141] Fault prediction: Based on the obtained data and parameters, fault prediction is performed to obtain the predicted equipment failure probability at time t+T. This probability value reflects the likelihood of equipment failure. Based on the prediction results, maintenance personnel can take corresponding preventive measures before the failure occurs, such as performing maintenance, replacing equipment, or adjusting operating strategies in advance.

[0142] S7. Provide maintenance decision support based on fault prediction results.

[0143] In this embodiment, maintenance decision support includes:

[0144] Based on the fault prediction results, combined with the importance and scope of the equipment, the decision tree analysis method (existing technology) is used to analyze the maintenance effectiveness, cost and risk under different fault prediction scenarios, formulate a reasonable maintenance plan, and determine the best maintenance action.

[0145] Example 2:

[0146] Reference Figure 4 This is the second embodiment of the present invention, which provides an artificial intelligence-based power equipment fault diagnosis system, including the following functional modules:

[0147] Data acquisition and processing module: Collects and processes real-time operating data of power equipment through sensors;

[0148] Feature extraction module: Extracts features from the obtained data to obtain feature values ​​related to the fault;

[0149] Fault classification module: Based on feature values, determine whether a fault exists, identify the fault type, and classify the fault.

[0150] Fault location module: Through the fault location model, it locates the fault source and its propagation path to achieve fault location;

[0151] Equipment assessment module: Based on the fault location results and combined with the equipment's historical operating data, a comprehensive analysis of the equipment's fault modes, operating environment, and life cycle is conducted to assess the equipment's health status.

[0152] Fault prediction module: It uses a fault prediction model to predict faults by combining the equipment's health status, historical fault data, and time-series changes.

[0153] Decision support module: Based on the fault prediction results, combined with the importance and scope of the equipment, analyze the maintenance effectiveness, cost and risk under different fault prediction scenarios, and formulate reasonable maintenance plans.

[0154] Example 3:

[0155] This embodiment also provides a computer device applicable to an artificial intelligence-based power equipment fault diagnosis system and method, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to realize the artificial intelligence-based power equipment fault diagnosis system and method proposed in the above embodiment.

[0156] This embodiment also provides a storage medium storing a computer program, which, when executed by a processor, implements an artificial intelligence-based power equipment fault diagnosis system and method as proposed in the above embodiments.

[0157] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0158] If a function is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0159] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as a sequenced list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by, or in conjunction with, an instruction execution system, apparatus, or device (such as a computer-based system, a processor-including system, or other system that can fetch and execute instructions from, an instruction execution system, apparatus, or device). For the purposes of this specification, "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transmit programs for use by, or in conjunction with, an instruction execution system, apparatus, or device.

[0160] More specific examples (a non-exhaustive list) of computer-readable media include: electrical connections (electronic devices) having one or more wires, portable computer disk drives (magnetic devices), random access memory (RAM), read-only memory (ROM), erasable and editable read-only memory (EPROM or flash memory), fiber optic devices, and portable optical disc read-only memory (CDROM). Furthermore, computer-readable media can even be paper or other suitable media on which programs can be printed, because programs can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpreting, or otherwise processing as necessary, and then stored in computer memory.

[0161] It should be understood that various parts of the present invention can be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented using any one or a combination of the following techniques known in the art: discrete logic circuits having logic gates for implementing logical functions on data signals, application-specific integrated circuits (ASICs) having suitable combinational logic gates, programmable gate arrays (PGAs), field-programmable gate arrays (FPGAs), etc.

[0162] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for fault diagnosis of power equipment based on artificial intelligence, characterized in that, Includes the following steps: S1. Power equipment operation data acquisition, obtaining operation data; S2. Extract features from the running data to obtain feature data; S3. Classify the fault types based on the feature data to obtain the fault classification results; S4. Based on the fault classification results, locate the fault and obtain the fault location results; S5. Based on the fault location results, conduct an equipment health status assessment to obtain the assessment results; S6. Based on the evaluation results, perform fault prediction to obtain the fault prediction results; S7. Provide maintenance decision support based on fault prediction results.

2. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 1, characterized in that, The feature extraction in S2 includes: The obtained operational data is standardized, and a feature analysis extraction model is used to extract features from the processed data to extract the changing features during equipment operation.

3. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 2, characterized in that, The feature analysis and extraction model includes: ； in: : The time-frequency energy distribution at frequency f and time t; Adaptive weighting coefficients; : The k-th wavelet basis function; Sensor data; * indicates a convolution operation. The number of wavelet basis functions.

4. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 1, characterized in that, The fault location in S4 includes: Based on the fault classification results, a fault location model is used to analyze the propagation path of the fault in the power equipment and locate the fault.

5. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 4, characterized in that, The fault location model includes: ； in: The probability that node i will fail; : Propagation intensity coefficient; : Confidence level of fault type classification; : The electrical distance between node j and node i; Total number of nodes.

6. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 5, characterized in that, The propagation intensity coefficient includes: ； in: Electrical impedance between node i and node j; : The maximum value of electrical impedance; : Electrical inductance between point i and node j; : The maximum value of electrical inductance.

7. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 1, characterized in that, The equipment health status assessment in S5 includes: Based on the fault location results and combined with the equipment's historical operating data, a Bayesian network-based inference method is used to assess the equipment's health status.

8. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 1, characterized in that, The fault prediction in S6 includes: Based on the assessment results, a fault prediction model is used to analyze the equipment's historical operating data and health assessment information to predict the probability of equipment failure.

9. The method for fault diagnosis of power equipment based on artificial intelligence according to claim 8, characterized in that, The fault prediction model includes: ； in: : The predicted probability of equipment failure at time t+T; : Health status assessment result of device i at time t; Weighting coefficients; : Dynamic adjustment coefficient; The rate of change of health status over time; Attenuation coefficient; Total number of devices.

10. An artificial intelligence-based power equipment fault diagnosis system, constructed based on the artificial intelligence-based power equipment fault diagnosis method according to any one of claims 1-9, characterized in that, Includes the following functional modules: The system includes a data acquisition and processing module, a feature extraction module, a fault classification module, a fault location module, an equipment evaluation module, a fault prediction module, and a decision support module.

Images