Real-time monitoring device and monitoring method for partial discharge ultrasonic signal of power equipment

Abstract

The invention provides a real-time monitoring device and monitoring method for partial discharge ultrasonic signals of power equipment, and relates to the technical field of power equipment monitoring. The real-time monitoring device for the partial discharge ultrasonic signal of the power equipment comprises a distributed monitoring system based on a block chain, intelligent monitoring based on edge computing, a positioning module based on an acoustic phased array, an environment monitoring module, a safety and protection module and a power management module. The integrity and security of partial discharge ultrasonic signal data are ensured and the data are prevented from being tampered or lost by using the decentralization and tampering-free characteristics of the block chain, the monitoring data are stored on a plurality of nodes in a distributed manner, the single-point fault is avoided, the reliability and fault tolerance of the data are improved, all data operations are recorded on the block chain, and the data operation efficiency is improved. The transparency and traceability of data are ensured, auditing and fault traceability are facilitated, real-time data processing and analysis are performed near a data source based on intelligent monitoring of edge calculation, and data transmission delay is reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of power equipment monitoring, and in particular to a real-time monitoring device and a monitoring method for partial discharge ultrasonic signals of power equipment. Background Art

[0002] Power equipment refers to various equipment required for power generation, transmission, transformation, distribution and consumption. These equipment play a vital role in the power system to ensure the safe, efficient and reliable transmission of electricity. Power equipment is exposed to high voltage, heat and other factors for a long time, and the gradual development of insulation aging and damage will lead to a significant decline in insulation performance, which becomes a hidden danger to the reliable operation of substation equipment and an important source of endangerment to the safety of power grid operation. The culprit of insulation accidents is mostly partial discharge, which is an initial manifestation of the decline in insulation performance of large-scale power equipment. Its continued development will lead to the breakdown of insulators and cause power accidents. Therefore, online monitoring of partial discharge of large-scale power equipment is particularly important.

[0003] There are still some problems in the use of existing real-time monitoring devices for partial discharge ultrasonic signals of power equipment. Traditional centralized data storage is vulnerable to attacks and data tampering, and traditional centralized data processing methods have data transmission delays. Therefore, technical personnel in this field provide a real-time monitoring device and monitoring method for partial discharge ultrasonic signals of power equipment to solve the problems raised in the above background technology. Summary of the invention

[0004] 1. Technical issues to be resolved

[0005] In view of the shortcomings of the prior art, the present invention provides a real-time monitoring device and method for partial discharge ultrasonic signals of power equipment, which solves the problems that traditional centralized data storage is vulnerable to attacks and data tampering, and traditional centralized data processing methods have data transmission delays.

[0006] (II) Technical solution

[0007] To achieve the above objectives, the present invention is implemented through the following technical solutions: a real-time monitoring device for partial discharge ultrasonic signals of power equipment, including a distributed monitoring system based on blockchain, intelligent monitoring based on edge computing, a positioning module based on acoustic phased array, an environmental monitoring module, a safety and protection module and a power management module;

[0008] The distributed monitoring system based on blockchain utilizes the decentralized and tamper-proof characteristics of blockchain to ensure the integrity and security of partial discharge ultrasonic signal data, and stores the monitoring data in a distributed manner on multiple nodes to avoid single point failures and improve data reliability and fault tolerance.

[0009] The edge computing-based intelligent monitoring performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time nature and response speed of monitoring, compresses and optimizes the collected data, reduces data transmission volume, and reduces network bandwidth and storage costs;

[0010] The acoustic phased array-based positioning module uses acoustic phased array technology to perform beamforming and signal enhancement on partial discharge ultrasonic signals, thereby improving signal strength and signal-to-noise ratio, and accurately positioning partial discharge signals by calculating signal arrival time difference or phase difference, thereby helping to quickly locate fault points.

[0011] Preferably, the power management module provides a stable power supply, manages battery charging and discharging, and extends battery life.

[0012] Preferably, a real-time monitoring method for partial discharge ultrasonic signals of power equipment comprises the following steps:

[0013] S1. System architecture and module integration,The system architecture includes a sensor network, which consists of multiple ultrasonic sensors,,which are used to collect partial discharge signals;

[0014] Edge computing nodes, responsible for preliminary processing and analysis of data;

[0015] Blockchain network for secure storage of data and execution of smart contracts;

[0016] IoT gateway, connecting sensor networks with the Internet to enable remote data transmission;

[0017] Cloud platform for centralized data analysis and visualization;

[0018] Environmental monitoring module, monitoring environmental parameters;

[0019] Safety and protection module to ensure safe and reliable operation of the system;

[0020] Power management module, providing stable power supply for the system;

[0021] S2. Data acquisition and preprocessing: The ultrasonic sensor collects the partial discharge signal, the signal preprocessing circuit amplifies and filters the signal, collects environmental parameters to assist data analysis, preprocesses the signal, removes the DC component, performs bandpass filtering, retains the partial discharge signal frequency band, amplifies the signal, and improves the signal-to-noise ratio;

[0022] S3. Intelligent monitoring, data processing and analysis based on edge computing, real-time data processing at edge computing nodes, extraction of signal characteristic peaks, frequency components and pulse widths, and application of machine learning models for fault diagnosis;

[0023] S3.1. Feature extraction, through the corresponding algorithm to scan the entire pre-processed signal, find the maximum value of the signal amplitude within a certain time range, this maximum value is the peak value of the signal, the calculation process involves traversing the signal data points, comparing the amplitude of each point, recording the time and amplitude value corresponding to the maximum amplitude, and use this as the peak information:

[0024] Features=[Peak(S filtered ), Frequency(S filtered ), PulseWidth(S filtered )]

[0025] Machine Learning Models:

[0026] Diagnosis = MLModel(Features)

[0027] Use models such as support vector machines and neural networks for classification;

[0028] S3.2. Use signal processing algorithms such as fast Fourier transform (FFT) to convert the time domain signal into the frequency domain to obtain the spectrum distribution of the signal. In the spectrum, we can clearly see the different frequency components contained in the signal and the energy corresponding to each frequency component. For a complex partial discharge ultrasonic signal, after FFT transformation, we can determine which frequency bands the main frequency components are concentrated in, whether the low frequency band or the high frequency band is dominant, etc. This helps to distinguish partial discharge caused by different reasons;

[0029] S3.3. During actual monitoring, the real-time extraction is input into the trained model, and the model performs complex calculations and judgments based on the learned patterns and rules, and finally outputs a corresponding fault diagnosis result, thereby realizing intelligent diagnosis of the current operating status of the power equipment;

[0030] S3.4. Real-time decision-making and response. According to the fault diagnosis results output by the machine learning model, the edge computing node must immediately make a corresponding decision-making action plan. According to the diagnosis results, when the decision is abnormal, the safety and protection module receives the corresponding instructions and activates the pre-set alarm device, triggering the sound and light alarm to sound an alarm and flashing lights. At the same time, it sends alarm text messages and pushes alarm messages to the relevant operation and maintenance personnel to inform them that the power equipment has abnormal conditions and needs to come to investigate and handle the faults as soon as possible. Make a decision to alarm or shut down in real time, and perform corresponding operations through the safety and protection module to maintain the normal operation of the system. Each module continues to operate according to the established process to ensure uninterrupted power equipment monitoring. The formula is:

[0031]

[0032] The decentralized and tamper-proof characteristics of blockchain are used to ensure the integrity and security of partial discharge ultrasonic signal data, prevent data from being tampered with or lost, and store monitoring data in a distributed manner on multiple nodes to avoid single point failures, improve data reliability and fault tolerance, and record all data operations on the blockchain to ensure data transparency and traceability, facilitating auditing and fault tracing.

[0033] S4. Distributed monitoring based on blockchain, encrypting the pre-processed signal data and diagnostic results, and uploading the encrypted data to the blockchain network;

[0034] S4.1. Blockchain network: Build a decentralized blockchain network to store and manage ultrasound signal data. Each monitoring point acts as a blockchain node, responsible for data collection, encryption, storage and transmission, and automatically executes predefined rules and logic.

[0035] S4.2. Data encryption: Use asymmetric encryption algorithms to encrypt data to ensure the security of data transmission and storage, and package the encrypted data into transactions, including data content, data source, timestamp, etc.;

[0036] S4.3. Signature verification: the data source digitally signs the transaction to ensure the authenticity and non-repudiation of the transaction, and broadcasts the transaction to all nodes in the blockchain network;

[0037] S4.4. Write smart contracts, define the logic of the contract, including trigger conditions and execution actions, deploy the smart contract code to the blockchain, and when the trigger conditions are met, the smart contract will be automatically executed, and the execution status and results of the contract will be continuously monitored. Based on edge computing, intelligent monitoring performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time nature and response speed of monitoring, compresses and optimizes the collected data, reduces data transmission volume, reduces network bandwidth and storage costs, integrates data processing and analysis functions into the monitoring device, realizes localized processing, and reduces dependence on cloud platforms;

[0038] S5. Positioning module based on acoustic phased array. The positioning technology based on acoustic phased array uses the beamforming and signal enhancement characteristics of the acoustic phased array to achieve accurate positioning of the partial discharge ultrasonic signal of the power equipment;

[0039] S5.1. Acoustic phased array sensor array, collects local discharge ultrasonic signals, and performs beam forming and signal enhancement to form a sensor array for receiving acoustic wave signals, and the sensor signals are pre-processed by amplification, filtering, etc.;

[0040] S5.2. Signal processing unit, which processes and calculates the collected signals, performs beam forming and signal enhancement, implements the phased array-based positioning algorithm, and calculates the signal arrival time difference or phase difference;

[0041] S5.3. Data processing and analysis module, which further processes and analyzes the positioning results, performs data analysis and fault diagnosis, and displays the positioning results to help users intuitively understand the fault location;

[0042] S5.4. Monitor environmental parameters to provide reference for positioning algorithms;

[0043] S5.5. Visualization display: Develop a visualization interface to display the positioning results and fault diagnosis information in real time. Use graphical tools to display the location and strength of the signal source. Use acoustic phased array technology to form beams and enhance the signal of partial discharge ultrasonic signals to improve the signal strength and signal-to-noise ratio. By calculating the signal arrival time difference or phase difference, the partial discharge signal can be accurately located to help quickly locate the fault point. It can detect and locate multiple partial discharge sources at the same time, improving the comprehensiveness and accuracy of monitoring. Phased array technology has strong environmental adaptability and can work stably in complex electromagnetic environments.

[0044] S6. Environmental monitoring and safety protection. The environmental monitoring module collects environmental parameters, combines the environmental parameters with partial discharge signal data, and conducts comprehensive analysis. The safety and protection module monitors the system status to ensure safe operation and prevent overvoltage, overcurrent, short circuit and other faults.

[0045] Preferably, in the above step S1, the modules are integrated, the sensor network is connected to the edge computing node via wired or wireless means, the edge computing node is connected to the Internet of Things gateway via a local area network or a wireless network, the Internet of Things gateway is connected to the cloud platform via the Internet, and the environmental monitoring module, the safety and protection module and the power management module are integrated in each monitoring point.

[0046] (III) Beneficial effects

[0047] The invention provides a real-time monitoring device and a monitoring method for partial discharge ultrasonic signals of electric power equipment.

[0048] It has the following beneficial effects:

[0049] 1. In the present invention, the decentralized and tamper-proof characteristics of blockchain are utilized to ensure the integrity and security of partial discharge ultrasonic signal data, prevent data from being tampered with or lost, and store monitoring data in a distributed manner on multiple nodes to avoid single point failures, improve data reliability and fault tolerance, and record all data operations on the blockchain to ensure data transparency and traceability, which is convenient for auditing and fault tracing.

[0050] 2. In the present invention, intelligent monitoring based on edge computing performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time and response speed of monitoring, compresses and optimizes the collected data, reduces the amount of data transmission, reduces network bandwidth and storage costs, integrates data processing and analysis functions into the monitoring device, realizes localized processing, and reduces dependence on the cloud platform.

[0051] 3. In the present invention, the acoustic phased array technology is used to perform beamforming and signal enhancement on the partial discharge ultrasonic signal, thereby improving the signal strength and signal-to-noise ratio. By calculating the signal arrival time difference or phase difference, the partial discharge signal can be accurately positioned to help quickly locate the fault point. It can simultaneously detect and locate multiple partial discharge sources, thereby improving the comprehensiveness and accuracy of monitoring. The phased array technology has strong environmental adaptability and can work stably in complex electromagnetic environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] Figure 1 It is a schematic diagram of the process of intelligent monitoring based on edge computing of the present invention;

[0053] Figure 2 This is a schematic diagram of the process of distributed monitoring based on blockchain of the present invention;

[0054] Figure 3 It is a schematic diagram of the flow of the positioning module based on the acoustic phased array of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Embodiment 1:

[0057] like Figure 1-3 As shown, an embodiment of the present invention provides a real-time monitoring device for partial discharge ultrasonic signals of power equipment, including a distributed monitoring system based on blockchain, intelligent monitoring based on edge computing, a positioning module based on an acoustic phased array, an environmental monitoring module, a safety and protection module, and a power management module;

[0058] The distributed monitoring system based on blockchain uses the decentralized and tamper-proof characteristics of blockchain to ensure the integrity and security of partial discharge ultrasonic signal data, and stores the monitoring data in a distributed manner on multiple nodes to avoid single point failures and improve data reliability and fault tolerance.

[0059] Intelligent monitoring based on edge computing performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time nature and response speed of monitoring, compresses and optimizes the collected data, reduces data transmission volume, and reduces network bandwidth and storage costs;

[0060] The positioning module based on acoustic phased array uses acoustic phased array technology to perform beamforming and signal enhancement on partial discharge ultrasonic signals, thereby improving signal strength and signal-to-noise ratio. By calculating the signal arrival time difference or phase difference, it can accurately locate the partial discharge signal and help quickly locate the fault point.

[0061] The power management module provides a stable power supply, manages battery charging and discharging, and extends battery life.

[0062] Preferably, a real-time monitoring method for partial discharge ultrasonic signals of power equipment comprises the following steps:

[0063] S1. System architecture and module integration,The system architecture includes a sensor network, which consists of multiple ultrasonic sensors,,which are used to collect partial discharge signals;

[0064] Edge computing nodes, responsible for preliminary processing and analysis of data;

[0065] Blockchain network for secure storage of data and execution of smart contracts;

[0066] IoT gateway, connecting sensor networks with the Internet to enable remote data transmission;

[0067] Cloud platform for centralized data analysis and visualization;

[0068] Environmental monitoring module, monitoring environmental parameters;

[0069] Safety and protection module to ensure safe and reliable operation of the system;

[0070] Power management module, providing stable power supply for the system;

[0071] S2. Data acquisition and preprocessing: The ultrasonic sensor collects the partial discharge signal, the signal preprocessing circuit amplifies and filters the signal, collects environmental parameters to assist data analysis, preprocesses the signal, removes the DC component, performs bandpass filtering, retains the partial discharge signal frequency band, amplifies the signal, and improves the signal-to-noise ratio;

[0072] S3. Intelligent monitoring, data processing and analysis based on edge computing, real-time data processing at edge computing nodes, extraction of signal characteristic peaks, frequency components and pulse widths, and application of machine learning models for fault diagnosis;

[0073] S3.1. Feature extraction, through the corresponding algorithm to scan the entire pre-processed signal, find the maximum value of the signal amplitude within a certain time range, this maximum value is the peak value of the signal, the calculation process involves traversing the signal data points, comparing the amplitude of each point, recording the time and amplitude value corresponding to the maximum amplitude, and use this as the peak information:

[0074] Features=[Peak(S filtered ), Frequency(S filtered ), PulseWidth(S filtered )]

[0075] Machine Learning Models:

[0076] Diagnosis = MLModel(Features)

[0077] Use models such as support vector machines and neural networks for classification;

[0078] S3.2. Use signal processing algorithms such as fast Fourier transform (FFT) to convert the time domain signal into the frequency domain to obtain the spectrum distribution of the signal. In the spectrum, we can clearly see the different frequency components contained in the signal and the energy corresponding to each frequency component. For a complex partial discharge ultrasonic signal, after FFT transformation, we can determine which frequency bands the main frequency components are concentrated in, whether the low frequency band or the high frequency band is dominant, etc. This helps to distinguish partial discharge caused by different reasons;

[0079] S3.3. During actual monitoring, the real-time extraction is input into the trained model, and the model performs complex calculations and judgments based on the learned patterns and rules, and finally outputs a corresponding fault diagnosis result, thereby realizing intelligent diagnosis of the current operating status of the power equipment;

[0080] S3.4. Real-time decision-making and response. According to the fault diagnosis results output by the machine learning model, the edge computing node must immediately make a corresponding decision-making action plan. According to the diagnosis results, when the decision is abnormal, the safety and protection module receives the corresponding instructions and activates the pre-set alarm device, triggering the sound and light alarm to sound an alarm and flashing lights. At the same time, it sends alarm text messages and pushes alarm messages to the relevant operation and maintenance personnel to inform them that the power equipment has abnormal conditions and needs to come to investigate and handle the faults as soon as possible. Make a decision to alarm or shut down in real time, and perform corresponding operations through the safety and protection module to maintain the normal operation of the system. Each module continues to operate according to the established process to ensure uninterrupted power equipment monitoring. The formula is:

[0081]

[0082] The decentralized and tamper-proof characteristics of blockchain are used to ensure the integrity and security of partial discharge ultrasonic signal data, prevent data from being tampered with or lost, and store monitoring data in a distributed manner on multiple nodes to avoid single point failures, improve data reliability and fault tolerance, and record all data operations on the blockchain to ensure data transparency and traceability, facilitating auditing and fault tracing.

[0083] S4. Distributed monitoring based on blockchain, encrypting the pre-processed signal data and diagnostic results, and uploading the encrypted data to the blockchain network;

[0084] S4.1. Blockchain network: Build a decentralized blockchain network to store and manage ultrasound signal data. Each monitoring point acts as a blockchain node, responsible for data collection, encryption, storage and transmission, and automatically executes predefined rules and logic.

[0085] S4.2. Data encryption: Use asymmetric encryption algorithms to encrypt data to ensure the security of data transmission and storage, and package the encrypted data into transactions, including data content, data source, timestamp, etc.;

[0086] S4.3. Signature verification: the data source digitally signs the transaction to ensure the authenticity and non-repudiation of the transaction, and broadcasts the transaction to all nodes in the blockchain network;

[0087] S4.4. Write smart contracts, define the logic of the contract, including trigger conditions and execution actions, deploy the smart contract code to the blockchain, and when the trigger conditions are met, the smart contract will be automatically executed, and the execution status and results of the contract will be continuously monitored. Based on edge computing, intelligent monitoring performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time nature and response speed of monitoring, compresses and optimizes the collected data, reduces data transmission volume, reduces network bandwidth and storage costs, integrates data processing and analysis functions into the monitoring device, realizes localized processing, and reduces dependence on cloud platforms;

[0088] S5. Positioning module based on acoustic phased array. The positioning technology based on acoustic phased array uses the beamforming and signal enhancement characteristics of the acoustic phased array to achieve accurate positioning of the partial discharge ultrasonic signal of the power equipment;

[0089] S5.1. Acoustic phased array sensor array, collects local discharge ultrasonic signals, and performs beam forming and signal enhancement to form a sensor array for receiving acoustic wave signals, and the sensor signals are pre-processed by amplification, filtering, etc.;

[0090] S5.2. Signal processing unit, which processes and calculates the collected signals, performs beam forming and signal enhancement, implements the phased array-based positioning algorithm, and calculates the signal arrival time difference or phase difference;

[0091] S5.3. Data processing and analysis module, which further processes and analyzes the positioning results, performs data analysis and fault diagnosis, and displays the positioning results to help users intuitively understand the fault location;

[0092] S5.4. Monitor environmental parameters to provide reference for positioning algorithms;

[0093] S5.5. Visualization display: Develop a visualization interface to display the positioning results and fault diagnosis information in real time. Use graphical tools to display the location and strength of the signal source. Use acoustic phased array technology to form beams and enhance the signal of partial discharge ultrasonic signals to improve the signal strength and signal-to-noise ratio. By calculating the signal arrival time difference or phase difference, the partial discharge signal can be accurately located to help quickly locate the fault point. It can detect and locate multiple partial discharge sources at the same time, improving the comprehensiveness and accuracy of monitoring. Phased array technology has strong environmental adaptability and can work stably in complex electromagnetic environments.

[0094] S6. Environmental monitoring and safety protection. The environmental monitoring module collects environmental parameters, combines the environmental parameters with partial discharge signal data, and conducts comprehensive analysis. The safety and protection module monitors the system status to ensure safe operation and prevent overvoltage, overcurrent, short circuit and other faults.

[0095] In the above step S1, the modules are integrated, the sensor network is connected to the edge computing node via wired or wireless means, the edge computing node is connected to the IoT gateway via a local area network or a wireless network, the IoT gateway is connected to the cloud platform via the Internet, and the environmental monitoring module, the safety and protection module and the power management module are integrated in each monitoring point.

[0096] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A real-time monitoring device for partial discharge ultrasonic signals of power equipment, characterized in that: Including distributed monitoring system based on blockchain, intelligent monitoring based on edge computing, positioning module based on acoustic phased array, environmental monitoring module, safety and protection module and power management module; The distributed monitoring system based on blockchain utilizes the decentralized and tamper-proof characteristics of blockchain to ensure the integrity and security of partial discharge ultrasonic signal data, and stores the monitoring data in a distributed manner on multiple nodes to avoid single point failures and improve data reliability and fault tolerance. The edge computing-based intelligent monitoring performs real-time data processing and analysis near the data source, reduces data transmission delays, improves the real-time nature and response speed of monitoring, compresses and optimizes the collected data, reduces data transmission volume, and reduces network bandwidth and storage costs; The acoustic phased array-based positioning module uses acoustic phased array technology to perform beamforming and signal enhancement on partial discharge ultrasonic signals, thereby improving signal strength and signal-to-noise ratio, and accurately positioning partial discharge signals by calculating signal arrival time difference or phase difference, thereby helping to quickly locate fault points.

2. A real-time monitoring device for partial discharge ultrasonic signals of power equipment according to claim 1, characterized in that: The power management module provides a stable power supply, manages battery charging and discharging, and prolongs battery life.

3. A method for real-time monitoring of partial discharge ultrasonic signals of power equipment, using a real-time monitoring device for partial discharge ultrasonic signals of power equipment according to any one of claims 1 to 2, characterized in that: The following steps are involved: S1. System architecture and module integration. The system architecture includes sensor network, edge computing node, blockchain network, IoT gateway, cloud platform, environmental monitoring module, power management module, and security and protection module. S2. Data acquisition and preprocessing: The ultrasonic sensor collects the partial discharge signal, the signal preprocessing circuit amplifies and filters the signal, collects environmental parameters to assist data analysis, preprocesses the signal, removes the DC component, performs bandpass filtering, retains the partial discharge signal frequency band, amplifies the signal, and improves the signal-to-noise ratio; S3. Intelligent monitoring, data processing and analysis based on edge computing, real-time data processing at edge computing nodes, extraction of signal characteristic peaks, frequency components and pulse widths, and application of machine learning models for fault diagnosis; S3.

1. Feature extraction, through the corresponding algorithm to scan the entire pre-processed signal, find the maximum value of the signal amplitude within a certain time range, this maximum value is the peak value of the signal, the calculation process involves traversing the signal data points, comparing the amplitude of each point, recording the time and amplitude value corresponding to the maximum amplitude, and use this as the peak information: Features=[Peak(S filtered ),Frequency(S filtered ),PulseWidth(S filtered )] Machine Learning Models: Diagnosis = MLModel(Features) Use models such as support vector machines and neural networks for classification; S3.

2. Use signal processing algorithms such as fast Fourier transform (FFT) to convert the time domain signal into the frequency domain to obtain the spectrum distribution of the signal. In the spectrum, we can clearly see the different frequency components contained in the signal and the energy corresponding to each frequency component. For a complex partial discharge ultrasonic signal, after FFT transformation, we can determine which frequency bands the main frequency components are concentrated in, whether the low frequency band or the high frequency band is dominant, etc. This helps to distinguish partial discharge caused by different reasons; S3.

3. During actual monitoring, the real-time extraction is input into the trained model, and the model performs complex calculations and judgments based on the learned patterns and rules, and finally outputs a corresponding fault diagnosis result, thereby realizing intelligent diagnosis of the current operating status of the power equipment; S3.

4. Real-time decision-making and response. According to the fault diagnosis results output by the machine learning model, the edge computing node must immediately make a corresponding decision-making action plan. According to the diagnosis results, when the decision is abnormal, the safety and protection module receives the corresponding instructions and activates the pre-set alarm device, triggering the sound and light alarm to sound an alarm and flashing lights. At the same time, it sends alarm text messages and pushes alarm messages to the relevant operation and maintenance personnel to inform them that the power equipment has abnormal conditions and needs to come to investigate and handle the faults as soon as possible. Make a decision to alarm or shut down in real time, and perform corresponding operations through the safety and protection module to maintain the normal operation of the system. Each module continues to operate according to the established process to ensure uninterrupted power equipment monitoring. The formula is: S4. Distributed monitoring based on blockchain, encrypting the pre-processed signal data and diagnostic results, and uploading the encrypted data to the blockchain network; S4.

1. Blockchain network: Build a decentralized blockchain network to store and manage ultrasound signal data. Each monitoring point acts as a blockchain node, responsible for data collection, encryption, storage and transmission, and automatically executes predefined rules and logic. S4.

2. Data encryption: Use asymmetric encryption algorithms to encrypt data to ensure the security of data transmission and storage, and package the encrypted data into transactions, including data content, data source, timestamp, etc.; S4.

3. Signature verification: the data source digitally signs the transaction to ensure the authenticity and non-repudiation of the transaction, and broadcasts the transaction to all nodes in the blockchain network; S4.

4. Write smart contracts, define the logic of the contract, including trigger conditions and execution actions, deploy the smart contract code to the blockchain, and when the trigger conditions are met, the smart contract will automatically execute, and continuously monitor the execution status and results of the contract; S5. Positioning module based on acoustic phased array. The positioning technology based on acoustic phased array uses the beamforming and signal enhancement characteristics of the acoustic phased array to achieve accurate positioning of the partial discharge ultrasonic signal of the power equipment; S5.

1. Acoustic phased array sensor array, collects local discharge ultrasonic signals, and performs beam forming and signal enhancement to form a sensor array for receiving acoustic wave signals, and the sensor signals are pre-processed by amplification, filtering, etc.; S5.

2. Signal processing unit, which processes and calculates the collected signals, performs beam forming and signal enhancement, implements the phased array-based positioning algorithm, and calculates the signal arrival time difference or phase difference; S5.

3. Data processing and analysis module, which further processes and analyzes the positioning results, performs data analysis and fault diagnosis, and displays the positioning results to help users intuitively understand the fault location; S5.

4. Monitor environmental parameters to provide reference for positioning algorithms; S5.

5. Visualization display: Develop a visualization interface to display positioning results and fault diagnosis information in real time, and use graphical tools to display the location and strength of the signal source; S6. Environmental monitoring and safety protection. The environmental monitoring module collects environmental parameters, combines the environmental parameters with partial discharge signal data, and conducts comprehensive analysis. The safety and protection module monitors the system status to ensure safe operation and prevent overvoltage, overcurrent, short circuit and other faults.

4. A real-time monitoring method for partial discharge ultrasonic signals of power equipment according to claim 3, characterized in that: In the module integration described in the above step S1, the sensor network is connected to the edge computing node via wired or wireless means, the edge computing node is connected to the Internet of Things gateway via a local area network or a wireless network, the Internet of Things gateway is connected to the cloud platform via the Internet, and the environmental monitoring module, the safety and protection module and the power management module are integrated in each monitoring point.

Images