Power equipment detection system and power equipment monitoring system

Abstract

This invention provides a power equipment testing system and a power equipment monitoring system, belonging to the field of power equipment testing technology. The power equipment testing system includes: a data acquisition module, comprising various sensors and video monitoring equipment configured on the power equipment, used to collect operating status data of the power equipment and surrounding environmental data; a fault classification module, used to determine the fault category based on the data collected by the data acquisition module; a fault determination module, used to determine the fault subtype based on the determined fault category and using a preset fault analysis strategy; and a fault prediction module, used to predict faults in the power equipment using a global fault prediction model constructed through federated learning. This invention, by combining multiple technologies, provides a more efficient and accurate solution for power equipment testing.

Description

Technical Field

[0001] This invention relates to the field of power equipment testing technology, and more specifically to a power equipment testing system and a power equipment monitoring system. Background Technology

[0002] Railway power equipment plays a vital role in power supply. As a core component of the power system, its reliable operation directly affects the stability and power quality of the entire system. With the continuous growth of societal demand for electricity and the ongoing expansion of the power system, the operating environment of power equipment is becoming increasingly complex, leading to a corresponding increase in the probability of failures. Once power equipment malfunctions, it can not only cause localized or even widespread power outages, greatly disrupting production and daily life, but also potentially trigger serious safety accidents, resulting in enormous economic losses.

[0003] Traditional power equipment inspection mainly relies on manual inspections and periodic preventative tests. Manual inspections suffer from high subjectivity, low efficiency, and long inspection cycles, making it difficult to monitor the equipment's operating status in real time and comprehensively. In fault diagnosis, existing systems are mostly based on single types of data or simple threshold judgments, making it difficult to accurately and comprehensively diagnose complex power equipment faults. Furthermore, the accuracy and reliability of fault prediction are low, failing to fully consider the interrelationships between power equipment and the influence of external environmental factors, resulting in insufficient lead time for fault prediction and inability to provide adequate early warning time for equipment maintenance. Summary of the Invention

[0004] This invention provides a power equipment testing system to solve the problems of low efficiency and poor accuracy in existing power equipment testing systems.

[0005] To achieve the above objectives, one embodiment of the present invention provides a power equipment detection system, comprising: a data acquisition module, including various sensors and video monitoring equipment configured on the power equipment, for acquiring operating status data of the power equipment and surrounding environmental data; a fault classification module, for determining fault categories based on the data acquired by the data acquisition module; a fault determination module, for determining fault subtypes based on the determined fault categories and using a preset fault analysis strategy; and a fault prediction module, for predicting faults in the power equipment using a global fault prediction model constructed through federated learning.

[0006] The fault categories include one or more of the following: poor operating condition faults, circuit abnormality faults, equipment defect faults, and environment-related faults. Determining the fault category based on the data collected by the data acquisition module includes: analyzing abrupt changes and harmonic content in the collected current and voltage data; if an abnormal increase in current and / or abnormal fluctuation in voltage occurs, the fault category is determined to be a poor operating condition fault or a circuit abnormality fault; analyzing the equipment's temperature, sound, and partial discharge parameters; if the equipment temperature is too high, the sound is abnormal, and / or the partial discharge exceeds the standard, the fault category is determined to be an equipment defect fault; analyzing the collected water level and gas content parameters; if the water level exceeds the safe water level and / or the gas content exceeds the standard value, the fault category is determined to be an environment-related fault.

[0007] The process of determining fault subtypes based on the identified fault category and using a preset fault analysis strategy includes: if the fault category is an adverse operating condition fault or a circuit abnormality fault, determining the corresponding fault subtype by analyzing parameter characteristics related to current and voltage; if the fault category is an equipment defect, determining the corresponding fault subtype by analyzing the temperature change curve of the cable, the characteristics of partial discharge pulses, and the sound spectrum, temperature, and partial discharge data of the distribution transformer; if the fault category is an environmentally related fault, determining the corresponding fault subtype by analyzing water level and gas content data.

[0008] The fault prediction module is also used to: preprocess the collected operating status data and extract key features related to power equipment faults; and train a local fault prediction model based on the preprocessed data and the extracted key features using a preset machine learning algorithm.

[0009] Differential privacy technology is used to encrypt the parameters of the trained local fault prediction model to obtain encrypted model parameters, which are then uploaded to the cloud blockchain. The blockchain then uses smart contracts configured within it to aggregate the model parameters uploaded by each power station using a federated averaging algorithm, generating a global fault prediction model that integrates data from multiple power stations.

[0010] The preprocessing of the collected operational status data includes: using a sliding window algorithm to smooth the data, removing noise interference, and using principal component analysis to reduce the dimensionality of the extracted key features, thereby improving the efficiency of subsequent model training and analysis.

[0011] The fault prediction module is also used to formulate maintenance plans for power equipment based on the prediction results of the global fault prediction model.

[0012] On the other hand, a power equipment monitoring system is also provided, which includes a cloud platform and the aforementioned power equipment detection system.

[0013] The power equipment detection system also includes: an application service module, equipped with a display unit, for displaying the equipment operating status, fault information, and fault warning information predicted by the global fault prediction model at each power station; and a secure communication module, which uses MQTT and OPC UA protocols and implements data transmission between modules through a TLS encrypted tunnel.

[0014] The cloud includes a blockchain, which is used to: aggregate model parameters uploaded by the power equipment detection systems of each power station using a federated averaging algorithm through smart contracts configured in the blockchain, to generate a global fault prediction model that integrates data information from multiple power stations; and distribute the generated global fault prediction model to the power equipment detection systems of each power station through the secure communication module.

[0015] The power equipment detection system is also used to: send corresponding early warning information to the application service module through the security communication module according to the determined fault subtype, and provide maintenance suggestions in combination with historical fault data and expert experience database.

[0016] This invention provides a power equipment detection system and a power equipment monitoring system. Through multiple types of sensors and video monitoring equipment, it achieves comprehensive real-time acquisition of operating status and surrounding environmental data, overcoming the drawbacks of manual inspections and periodic tests. Its fault classification and determination module, relying on advanced algorithms, can accurately determine fault categories and subtypes based on multi-source data, breaking through the limitations of traditional single-data or simple threshold diagnosis. The fault early warning module utilizes a global fault prediction model constructed with a generative adversarial network incorporating a spatiotemporal attention mechanism, employing federated learning to ensure data security, significantly improving the accuracy and reliability of predictions, and compensating for the shortcomings of traditional prediction techniques. Simultaneously, the system possesses functions such as secure communication assurance, model iterative optimization, and maintenance plan formulation, comprehensively meeting the needs of intelligent operation and maintenance of power systems for efficiency, accuracy, security, and scalability. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in this invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. In the drawings:

[0018] Figure 1 This is a schematic diagram of the power equipment testing system provided in an embodiment of the present invention;

[0019] Figure 2This is a flowchart of the global fault prediction model construction provided in this embodiment of the invention;

[0020] Figure 3 This is a flowchart of the fault determination process provided in an embodiment of the present invention;

[0021] Figure 4 This is a framework diagram of a power equipment monitoring system provided in an embodiment of the present invention. Detailed Implementation

[0022] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are for illustration and explanation only and are not intended to limit the scope of the present invention.

[0023] It should be noted that the acquisition, transmission, storage, use, and processing of data in the technical solution of this application all comply with the relevant provisions of national laws and regulations. In the embodiments of this application, certain existing industry solutions such as software, components, and models may be mentioned. These should be considered exemplary, intended only to illustrate the feasibility of implementing the technical solution of this application, and do not imply that the applicant has already used or necessarily used such solutions.

[0024] As a core component of the power system, ensuring the reliable operation of power equipment is crucial for maintaining the stability and security of power supply. With the increasing scale and complexity of power systems, the operating environments of power equipment are becoming more diverse and demanding, significantly increasing the risk of equipment failure. Traditional power equipment inspection methods primarily rely on manual inspections and periodic preventative tests. Manual inspections are limited by the professional skills, experience, and subjective judgment of inspectors, easily overlooking potential equipment faults. Furthermore, they cannot achieve real-time monitoring of equipment operating status and fail to promptly detect dynamic changes in equipment operating parameters. Therefore, developing a more efficient and accurate power equipment inspection system is of paramount importance.

[0025] This invention aims to solve many problems of traditional power equipment detection systems. It utilizes various sensors and video monitoring equipment to achieve real-time and comprehensive data collection on equipment operating status and the surrounding environment. The fault classification and determination module, leveraging advanced algorithms and integrating diverse data, accurately determines fault categories and subtypes, overcoming the limitations of traditional single-data or simple threshold diagnosis in handling complex faults. The fault early warning module employs a global fault prediction model built using a generative adversarial network incorporating a spatiotemporal attention mechanism. Through federated learning, it ensures data security, significantly improving the accuracy and reliability of predictions and overcoming the shortcomings of traditional prediction techniques. This comprehensively meets the urgent needs of intelligent operation and maintenance of power systems for efficiency and accuracy, effectively ensuring the stable operation of power systems and improving the quality of power services.

[0026] The following is combined with Figures 1-4 This invention is described in detail.

[0027] like Figure 1 and Figure 4 As shown in the figure, this embodiment of the invention provides a power equipment detection system, which includes: a data acquisition module, including various sensors and video monitoring equipment configured on the power equipment, for collecting operating status data of the power equipment and surrounding environmental data; a fault classification module, for determining fault categories based on the data collected by the data acquisition module; a fault determination module, for determining fault subtypes based on the determined fault categories and using a preset fault analysis strategy; and a fault prediction module, for predicting faults in the power equipment using a global fault prediction model constructed through federated learning.

[0028] Preferably, the power equipment detection system further includes: an application service module, configured with a display unit, for displaying the equipment operating status, fault information, and fault warning information predicted by the global fault prediction model at each power station; and a secure communication module, which uses MQTT and OPC UA protocols and implements data transmission between modules through a TLS encrypted tunnel.

[0029] In the power equipment detection system provided by this invention, the data acquisition module collects equipment operating status data and surrounding environmental data comprehensively and in real time through various sensors and video monitoring equipment deployed on the power equipment. This overcomes the limitations of traditional manual inspections in data acquisition and provides a rich data foundation for subsequent accurate analysis. The fault classification module accurately determines the fault category based on the collected data, while the fault determination module further clarifies the fault subtype using a preset fault analysis strategy. These two modules work together to effectively solve the problem that traditional fault diagnosis technologies rely on single data or simple threshold judgments, making it difficult to handle complex fault situations and resulting in poor diagnostic accuracy and comprehensiveness. The fault early warning module uses a global fault prediction model built based on federated learning to predict faults in power equipment. Federated learning technology ensures data security during the multi-site data fusion process, significantly improving the accuracy and reliability of fault prediction and overcoming the shortcomings of traditional experience models and simple time series analysis, which are unable to adapt to complex and changing equipment operating environments and have insufficient prediction lead time. Simultaneously, an application service module is introduced, equipped with a display unit, responsible for intuitively displaying the equipment operating status, fault information, and fault early warning information generated by the global fault prediction model at each power station. This greatly facilitates maintenance personnel in timely and comprehensive understanding of equipment status. A secure communication module was also set up. This module adopts the MQTT and OPC UA protocols and uses a TLS encrypted tunnel to achieve secure and stable data transmission between modules. It successfully solves the data security and privacy protection problem when merging data from multiple sites and provides a solid security guarantee for the data interaction of the entire power equipment testing system.

[0030] like Figure 3 As shown, preferably, the fault category includes one or more of the following: poor operating condition fault, circuit abnormality fault, equipment defect fault, and environment-related fault. Determining the fault category based on the data collected by the data acquisition module includes: analyzing abrupt changes and harmonic content in the collected current and voltage data; if an abnormal increase in current and / or abnormal fluctuation in voltage occurs, the fault category is determined to be a poor operating condition fault or a circuit abnormality fault; analyzing the equipment's temperature, sound, and partial discharge parameters; if the equipment temperature is too high, the sound is abnormal, and / or the partial discharge exceeds the standard, the fault category is determined to be an equipment defect fault; analyzing the collected water level and gas content parameters; if the water level exceeds the safe water level and / or the gas content exceeds the standard value, the fault category is determined to be an environment-related fault.

[0031] In a preferred embodiment of the present invention, the classification of fault categories and the specific methods for determining fault categories based on data acquisition are described in detail. Fault categories are clearly defined as four types: adverse operating condition faults, circuit abnormality faults, equipment defect faults, and environment-related faults. The basis for determining the fault category comes from the data collected by the data acquisition module. For adverse operating condition faults and circuit abnormality faults, the sudden changes in current and voltage data and harmonic content are analyzed, and the fault is determined when there is an abnormal increase in current and / or abnormal fluctuation in voltage. Equipment defect faults are determined based on the equipment's temperature, sound, and partial discharge parameters, and are determined when the equipment temperature is too high, the sound is abnormal, and / or the partial discharge exceeds the standard. Environment-related faults are determined by analyzing water level and gas content parameters, and are determined when the water level exceeds the safe level and / or the gas content exceeds the standard value. This classification and determination method has strong logic and practicality, comprehensively covering different fault situations that may occur in the operation of power equipment. It can accurately determine the fault type based on the actual collected data, providing a key foundation for subsequent fault diagnosis and handling, and effectively improving the accuracy and reliability of the power equipment detection system.

[0032] For example, at a power substation, after a thunderstorm, the system detected a sudden and rapid increase in the current of a transmission line from the normal 500A to 800A within a short period. Simultaneously, the voltage exhibited abnormal fluctuations of ±10%, and the harmonic content exceeded the normal range. Based on the fault category determination rules, the system immediately classified this fault as an adverse operating condition fault. On-site inspection by maintenance personnel revealed that a lightning strike had damaged the surge arrester on the line, causing the abnormal current and voltage. The current and voltage data collected by the data acquisition module showed significant abnormal fluctuations. The previously stable three-phase voltage data showed a sudden decrease in the amplitude of one phase, and the phase relationship with the other two phases also changed. Further analysis revealed a significant increase in the negative sequence voltage component, exceeding the normal operating range. This was due to poor wiring of the instrument transformer, causing a mis-sequence phenomenon during current transmission. Some current failed to flow along the normal path, resulting in abnormal negative sequence current and voltage. The system immediately classified this fault as a circuit anomaly fault. Within the same substation, during the operation of a critical transformer, the data acquisition module detected a rapid increase in oil temperature from the normal 50°C to 80°C. Furthermore, the sound sensor detected a sharp, abnormal sound emanating from the transformer, and partial discharge parameters exceeded standard values. Based on pre-defined rules, the system determined this to be an equipment defect. Maintenance personnel discovered a minor short circuit in the transformer's internal windings, causing these abnormalities. Additionally, the substation is located near a river. After a heavy rain, the data acquisition module reported that the water level had exceeded the safe warning line, and the gas concentration sensor detected SF6 gas levels exceeding the standard. The system quickly identified this as an environmentally related fault. Further investigation revealed that the heavy rain caused a blockage in the drainage system, leading to backflow of water, and that some electrical equipment, due to moisture, experienced minor discharges, causing SF6 gas decomposition and increased concentrations.

[0033] Preferably, the step of determining the fault subtype based on the determined fault category and using a preset fault analysis strategy includes: if the fault category is an adverse operating condition fault or a circuit abnormality fault, determining the corresponding fault subtype by analyzing the parameter characteristics related to current and voltage; if the fault category is an equipment defect, determining the corresponding fault subtype by analyzing the temperature change curve of the cable, the characteristics of partial discharge pulses, and the sound spectrum, temperature, and partial discharge data of the distribution transformer; if the fault category is an environmentally related fault, determining the corresponding fault subtype by analyzing water level and gas content data.

[0034] The preferred embodiment of the present invention clearly illustrates its working mechanism of further clarifying fault subtypes based on a determined fault category and with the aid of a preset fault analysis strategy. The fault analysis strategy includes:

[0035] (1) When the fault category is determined to be an adverse operating condition fault, the system will focus on analyzing the parameter characteristics related to current and voltage to determine the specific subtype. For example, if a load impact phenomenon is detected during system commissioning or operation, it can be judged by analyzing the instantaneous large change in current and the fluctuation amplitude of voltage. When single-phase grounding, two-phase short-circuit grounding, or three-phase short-circuit grounding faults occur, they can be identified based on the relationship between current and voltage changes between different phases, such as a sudden increase in current or a decrease in voltage in a certain phase. For power frequency overvoltage faults, it can be determined by monitoring whether the frequency and amplitude of the voltage exceed the normal power frequency range. When detecting interharmonic and harmonic overvoltage faults, it is necessary to analyze the spectral characteristics of current and voltage to check whether there are interharmonics or harmonic components of a specific frequency and whether their amplitude exceeds the standard value. When the excitation inrush current state caused by different reasons is detected during system commissioning or operation, it can be judged based on the transient change characteristics of the current, such as the initial amplitude of the current and the decay time. For ground loop current over-limit alarms and cable multi-point grounding faults, it can be determined by monitoring the magnitude and distribution of the grounding current.

[0036] (2) If the fault category is a circuit abnormality fault, the parameter characteristics related to current and voltage will also be analyzed. For example, when abnormal phenomena such as negative sequence, wrong sequence, and reverse polarity occur due to poor wiring of the current transformer, they can be judged by detecting the symmetry and phase relationship of the three-phase current and voltage. Negative sequence phenomenon will cause the three-phase current or voltage to be unbalanced, and the degree of abnormality can be determined by calculating the magnitude of the negative sequence component; when the sequence is wrong, the phase sequence relationship of the three phases will change, which can be identified by using a phase sequence detection device or analyzing the phase difference of voltage and current; reverse polarity can be judged by comparing the voltage and current output of the secondary side of the current transformer with the waveform and phase relationship under normal polarity.

[0037] (3) When the fault category is equipment defect fault, the system will determine the specific subtype by analyzing the cable temperature change curve, partial discharge pulse characteristics, and the sound spectrum, temperature, and partial discharge data of the distribution transformer. Real-time monitoring of cable temperature, if the temperature continues to rise and exceeds the normal range, may mean that the cable has problems such as insulation aging or overload. Analyzing the characteristics of partial discharge pulses, such as the frequency, amplitude, and number of discharges, can determine whether there are insulation defects or damage inside the cable. For distribution transformers, analyzing their sound spectrum can determine whether there are mechanical faults, such as loose iron core or short circuit in windings. Abnormal sounds will show specific frequency components in the spectrum. At the same time, monitoring the temperature and partial discharge data of the transformer, if the temperature is too high or the partial discharge exceeds the standard, can further determine whether there are faults such as insulation damage or winding overheating inside the transformer.

[0038] (4) If the fault category is an environmentally related fault, the system will determine the specific subtype by analyzing water level and gas content data. When the water level exceeds the safe level, it may cause immersion damage to electrical equipment. The severity of the fault can be judged based on the speed and height of the water level rise. For example, a slow rise may be due to a poor drainage system, while a rapid rise may be caused by external flooding. For gas content exceeding the standard warning, the specific fault can be determined based on the composition and content of different gases. For example, if the SF6 gas content exceeds the standard value, it may mean that there is a leakage problem in the electrical equipment; if the content of harmful gases such as carbon monoxide exceeds the standard, it may be a fault such as overheating or combustion inside the equipment.

[0039] Preferably, the fault determination module is further configured to: send corresponding early warning information to the application service module through the security communication module according to the determined fault subtype, and provide maintenance suggestions in combination with historical fault data and expert experience database.

[0040] In a preferred embodiment of the present invention, after determining the fault subtype, the fault determination module promptly transmits early warning information to the application service module through the secure communication module. At the same time, relying on historical fault data and expert experience database, it provides targeted maintenance suggestions. This solution improves system functions, ensures secure information transmission, enhances the efficiency and quality of power equipment maintenance, and promotes intelligent operation and maintenance of the power system.

[0041] like Figure 2 As shown, preferably, the fault prediction module is further configured to: preprocess the collected operating status data and extract key features related to power equipment faults; train a local fault prediction model using a preset machine learning algorithm based on the preprocessed data and the extracted key features; encrypt the parameters of the trained local fault prediction model using differential privacy technology to obtain encrypted model parameters, and upload them to the blockchain in the cloud, so that the blockchain can aggregate the model parameters uploaded by each power station using a federated averaging algorithm through smart contracts configured in the blockchain, and generate a global fault prediction model that integrates data information from multiple power stations.

[0042] In a preferred embodiment of the present invention, when constructing a global fault prediction model, firstly, the power equipment operating status data collected from various sensors and video monitoring equipment is preprocessed using specific algorithms. For example, a sliding window algorithm is used to remove noise interference from the data, ensuring the accuracy and stability of the data; principal component analysis is used to reduce the dimensionality of the data, improving the efficiency of subsequent analysis. Simultaneously, key features closely related to power equipment faults are deeply explored, such as the fluctuation characteristics of current and voltage, equipment temperature change curves, and partial discharge pulse characteristics, providing core data support for subsequent model training. Subsequently, the power equipment operating status data collected from various sensors and video monitoring equipment is preprocessed using specific algorithms. For example, a sliding window algorithm is used to remove noise interference from the data, ensuring the accuracy and stability of the data; principal component analysis is used to reduce the dimensionality of the data, improving the efficiency of subsequent analysis. Simultaneously, key features closely related to power equipment faults are deeply explored, such as the fluctuation characteristics of current and voltage, equipment temperature change curves, and partial discharge pulse characteristics, providing core data support for subsequent model training. Subsequently, to ensure data security and privacy, differential privacy technology was used to encrypt the parameters of the trained local fault prediction model. By adding specific noise to the model parameters, data leakage was effectively prevented without affecting the model's accuracy. After encryption, the encrypted model parameters were uploaded to the blockchain. The decentralized and immutable characteristics of the blockchain ensured the security and reliability of the parameters during transmission and storage. Then, the smart contract configured within the blockchain was activated, aggregating the model parameters uploaded from each power station using a federated averaging algorithm. This algorithm comprehensively considers the model parameters from each station to generate a global fault prediction model that integrates data from multiple power stations. This model integrates the commonalities and characteristics of equipment operation at different stations, offering wider applicability and higher accuracy compared to single-site models. Finally, the generated global fault prediction model was distributed to each power station via a secure communication module, enabling fault prediction to begin.

[0043] Preferably, the fault prediction module is further configured to formulate a maintenance plan for the power equipment based on the prediction results of the global fault prediction model.

[0044] In a preferred embodiment of the present invention, the present invention intelligently generates a maintenance plan based on the prediction results of a global fault prediction model. This method is highly practical, accurately identifies maintenance needs, optimizes resource allocation, and reduces operation and maintenance costs.

[0045] like Figure 4 As shown, this embodiment of the invention also provides a power equipment monitoring system, which includes a cloud platform and the aforementioned power equipment detection system.

[0046] Preferably, the cloud includes a blockchain, which is used to: aggregate model parameters uploaded by the power equipment detection systems of each power station using a federated averaging algorithm through smart contracts configured in the blockchain, to generate a global fault prediction model that integrates data information from multiple power stations; and distribute the generated global fault prediction model to the power equipment detection systems of each power station through the secure communication module.

[0047] More preferably, the fault prediction module is also used to: continuously train and update the local global fault prediction model using new local data from each power station; upload the updated model parameters of each power station to the blockchain and aggregate them to continuously iterate and optimize the global fault prediction model, so as to improve the accuracy and generalization ability of fault prediction.

[0048] In a preferred embodiment of the invention, after receiving the global fault prediction model, each site continuously trains and updates its local global fault prediction model using newly generated local data, enabling the model to adapt to changes in equipment operating conditions. Subsequently, the updated model parameters are uploaded to the blockchain again, and the smart contract uses a federated averaging algorithm to aggregate the data again, continuously iterating and optimizing the global fault prediction model to improve its accuracy and generalization ability in fault prediction, thus addressing the complex and ever-changing operating environment of power equipment. This technical solution effectively protects data security and privacy, preventing data theft or tampering, and meets the stringent data security requirements of the power industry. Each site independently trains its local model, fully considering the characteristics of its local equipment, and then aggregates the data using a federated averaging algorithm to generate a global model. This combines the local advantages of each site with the fusion of global data, improving the model's accuracy and generalization ability, and better adapting to the fault prediction needs of different power equipment.

[0049] In summary, the power equipment detection and monitoring system provided by this invention utilizes multiple sensors and monitoring equipment in its data acquisition module to overcome the limitations of traditional manual inspections and achieve comprehensive real-time data collection. The fault classification and fault determination modules, through the integration of multi-source data and advanced algorithms, accurately determine fault categories and subtypes, solving the accuracy and comprehensiveness problems caused by single data or simple threshold judgments in traditional diagnostic techniques. The fault prediction module constructs a global fault prediction model, combining federated learning to ensure data security, significantly improving the accuracy and reliability of predictions and overcoming the shortcomings of traditional prediction techniques. Furthermore, this system can intelligently formulate maintenance plans based on prediction results. After determining the fault subtype, the fault determination module can send early warnings and provide maintenance suggestions. The system also possesses secure communication guarantees and continuous model iteration and optimization capabilities, comprehensively meeting the needs of intelligent operation and maintenance of power systems for efficiency, accuracy, security, and scalability, effectively ensuring the stable operation of power systems and significantly improving the quality of power services.

[0050] It should be understood that, in various embodiments of the present invention, the order of the above-mentioned process numbers does not imply the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0051] Furthermore, the terms "system" and "network" are often used interchangeably in this paper. The term "and / or" in this paper merely describes the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A alone, A and B simultaneously, or B alone. Additionally, the character " / " in this paper generally indicates that the preceding and following related objects have an "or" relationship.

[0052] It should be understood that, in the embodiments of the present invention, "B corresponding to A" means that B is associated with A, and B can be determined based on A. However, it should also be understood that determining B based on A does not mean that B is determined solely based on A; B can also be determined based on A and / or other information.

[0053] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, computer software, or a combination of both. To clearly illustrate the interchangeability of hardware and software, the components and steps of the various examples have been generally described in terms of functionality in the foregoing description. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0054] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0055] In the embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through some interfaces, apparatuses, or units, or they may be electrical, mechanical, or other forms of connection.

[0056] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of the embodiments of the present invention, depending on actual needs.

[0057] Furthermore, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0058] From the above description of the embodiments, those skilled in the art will clearly understand that the present invention can be implemented in hardware, firmware, or a combination thereof. When implemented in software, the above-described functions can be stored in a computer-readable medium or transmitted as one or more instructions or code on a computer-readable medium. Computer-readable media include computer storage media and communication media, wherein communication media include any medium that facilitates the transmission of a computer program from one place to another. Storage media can be any available medium accessible to a computer. For example, but not limited to, computer-readable media can include RAM, ROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage media or other magnetic storage devices, or any other medium capable of carrying or storing desired program code in the form of instructions or data structures and accessible to a computer. Furthermore, any connection can suitably be a computer-readable medium. For example, if the software is transmitted from a website, server, or other remote source using coaxial cable, fiber optic cable, twisted pair, digital subscriber line (DSL), or wireless technologies such as infrared, radio, and microwave, then coaxial cable, fiber optic cable, twisted pair, DSL, or wireless technologies such as infrared, radio, and microwave are included in the scope of the medium. As used in this invention, disk and disc include compressed optical discs (CDs), laser discs, optical discs, digital versatile discs (DVDs), floppy disks, and Blu-ray discs, wherein disks typically magnetically copy data, while discs optically copy data using lasers. The combinations described above should also be included within the scope of protection for computer-readable media.

[0059] In summary, the above description is merely a preferred embodiment of the technical solution of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A power equipment testing system, characterized in that, The power equipment testing system includes: The data acquisition module includes various sensors and video monitoring equipment configured on the power equipment, used to collect operating status data of the power equipment and surrounding environmental data; The fault classification module is used to determine the fault category based on the data collected by the data acquisition module; The fault determination module is used to determine the fault subtype based on the determined fault category and using a preset fault analysis strategy; The fault prediction module is used to predict faults in power equipment using a global fault prediction model built through federated learning. The fault prediction module is also used to formulate maintenance plans for power equipment based on the prediction results of the global fault prediction model. The fault prediction module is also used to preprocess the collected operating status data and extract key features related to power equipment faults. Based on the preprocessed data and the extracted key features, a local fault prediction model is trained using a pre-set machine learning algorithm. Differential privacy technology is used to encrypt the parameters of the trained local fault prediction model to obtain encrypted model parameters, which are then uploaded to the cloud blockchain. The blockchain then uses smart contracts configured within it to aggregate the model parameters uploaded by each power station using a federated averaging algorithm, generating a global fault prediction model that integrates data from multiple power stations.

2. The power equipment testing system according to claim 1, characterized in that, The fault categories include one or more of the following: poor operating condition faults, circuit abnormality faults, equipment defect faults, and environment-related faults. Determining the fault category based on the data collected by the data acquisition module includes: Analyze the sudden changes and harmonic content of the collected current and voltage data. If there is an abnormal increase in current and / or abnormal fluctuation in voltage, the fault category is determined to be an adverse operating condition fault or a circuit abnormality fault. Analyze the equipment's temperature, sound, and partial discharge parameters. When the equipment temperature is too high, the sound is abnormal, and / or the partial discharge exceeds the standard, the fault category is determined to be an equipment defect fault. Analyze the collected water level and gas content parameters. If the water level exceeds the safe water level and / or the gas content exceeds the standard value, the fault category is determined to be an environmentally related fault.

3. The power equipment testing system according to claim 2, characterized in that, The step of determining the fault subtype based on the determined fault category and using a preset fault analysis strategy includes: If the fault category is an adverse operating condition fault or a circuit abnormality fault, the corresponding fault subtype is determined by analyzing the parameter characteristics related to current and voltage. If the fault category is equipment defect, the corresponding fault subtype can be determined by analyzing the temperature change curve of the cable, the characteristics of partial discharge pulses, and the sound spectrum, temperature, and partial discharge data of the distribution transformer. If the fault category is an environmentally related fault, the corresponding fault subtype can be determined by analyzing water level and gas content data.

4. The power equipment testing system according to claim 1, characterized in that, The preprocessing of the collected operational status data includes: The sliding window algorithm is used to smooth the data and remove noise interference. Principal component analysis is used to reduce the dimensionality of the extracted key features, thereby improving the efficiency of subsequent model training and analysis.

5. A power equipment monitoring system, characterized in that, The power equipment monitoring system includes a cloud platform and the power equipment detection system as described in any one of claims 1-4.

6. The power equipment monitoring system according to claim 5, characterized in that, The power equipment testing system also includes: The application service module is equipped with a display unit to display the equipment operating status, fault information, and fault warning information predicted by the global fault prediction model at each power station. The secure communication module uses MQTT and OPC UA protocols and implements data transmission between modules through a TLS encrypted tunnel.

7. The power equipment monitoring system according to claim 6, characterized in that, The cloud includes a blockchain, which is used for: By configuring smart contracts within the blockchain and using a federated averaging algorithm, the model parameters uploaded by the power equipment detection systems of each power station are aggregated to generate a global fault prediction model that integrates data from multiple power stations. The generated global fault prediction model is distributed to the power equipment detection system of each power station through the secure communication module.

8. The power equipment monitoring system according to claim 6, characterized in that, The power equipment testing system is also used for: Based on the determined fault subtype, the corresponding early warning information is sent to the application service module through the security communication module, and maintenance suggestions are given in combination with historical fault data and expert experience database.

Images