Breaker partial discharge monitoring system

Abstract

The invention belongs to the technical field of circuit breaker discharge monitoring, and particularly relates to a circuit breaker partial discharge monitoring system which comprises a sensing acquisition module, a data acquisition and preprocessing module, a signal identification and diagnosis module, an alarm and decision module, a communication and visualization module and a system management and storage module. According to the circuit breaker partial discharge monitoring system provided by the invention, the high-frequency current sensor, the ultrasonic sensor, the ultrahigh-frequency electromagnetic wave sensor and the environmental parameter sensor are integrated, so that multi-dimensional detection of electric, magnetic and acoustic signals generated in a partial discharge process and an interference environment is realized, and the signal credibility and the recognition precision are effectively improved; and the problems of false alarm and missing alarm of a single sensor are avoided.

Description

Technical Field

[0001] This invention belongs to the field of circuit breaker discharge monitoring technology, specifically referring to a circuit breaker partial discharge monitoring system. Background Technology

[0002] Circuit breakers, as crucial switching devices in power systems, can close, carry, and interrupt current under normal circuit conditions, and carry and interrupt current under abnormal circuit conditions within a specified time. They automatically disconnect the circuit in case of faults such as overload, short circuit, and undervoltage, thus protecting power lines and equipment such as motors. Widely used in power distribution, they are key equipment for ensuring the stable operation of power systems.

[0003] However, partial discharge occurs frequently during circuit breaker operation, often an early sign of insulation degradation. If not addressed promptly, it can lead to serious electrical accidents. Current partial discharge detection technologies for circuit breakers have several shortcomings: low accuracy, difficulty in precisely capturing weak partial discharge signals, and a tendency to miss or misjudge detections; poor real-time performance, failing to reflect the real-time operating status of the circuit breaker and providing timely and effective data support for condition-based maintenance; weak anti-interference capability, easily affected by external interference signals in complex electromagnetic environments, leading to distorted detection results; and low automation, with most detection systems still requiring manual intervention, lacking intelligent data processing and analysis functions, and unable to achieve automatic early warning and fault diagnosis, increasing maintenance costs and workload. Summary of the Invention

[0004] To address the aforementioned issues and overcome the shortcomings of existing technologies, this invention provides a circuit breaker partial discharge monitoring system. To resolve the need for improvement in the processing and feature extraction capabilities of existing systems for product images, particularly when handling complex scenes and diverse product images, this invention proposes a circuit breaker partial discharge monitoring system that employs a multilayer perceptron as the feature representation unit. This enables the system to capture more complex nonlinear relationships within images. This helps to better represent abstract features in images and improves the system's ability to recognize complex patterns.

[0005] The technical solution adopted by this invention is as follows: This invention provides a circuit breaker partial discharge monitoring system, comprising: Sensor acquisition module: used to acquire partial discharge signals inside the circuit breaker in real time; Data acquisition and preprocessing module: Connected to the sensor acquisition module, it is used to convert the acquired analog signals into digital signals and perform preliminary data filtering, amplification and synchronization processing; Signal recognition and diagnosis module: used to perform in-depth analysis of preprocessed data to identify the type, severity and possible location of partial discharge; Alarm and Decision Module: Linked with the signal recognition module, it generates corresponding alarm signals based on the recognition results and triggers a multi-level response mechanism. Communication and visualization module: used to realize data transmission and graphical interaction between this system and external user terminals; System Management and Storage Module: Used to provide power supply, data management and operation and maintenance support for the entire system.

[0006] Furthermore, the sensor acquisition module includes: A high-frequency current sensor is used to detect transient pulse current signals generated by partial discharge; Ultrasonic sensors are used to capture sound wave signals generated during partial discharge. Ultra-high frequency electromagnetic wave sensor to detect electromagnetic radiation waves generated during partial discharge activity; Environmental parameter sensors will monitor in real time the temperature, humidity, air pressure, and electromagnetic interference intensity of the environment in which the circuit breaker is located.

[0007] Furthermore, the data acquisition and preprocessing module includes: The signal conditioning unit preprocesses the raw analog signal from the sensor to meet the ADC input requirements; The analog-to-digital converter accurately converts analog signals into digital signals for subsequent FPGA processing. The sampling synchronization and clock control unit ensures synchronous sampling among multiple ADC channels and provides a unified time reference. The data buffer and cache unit temporarily stores high-frequency sampled data to prevent data loss; The primary feature extraction and filtering unit uses FPGA to perform primary calculations on the raw data, reducing the workload on the main control unit.

[0008] Furthermore, the signal recognition and diagnosis module includes: The feature extraction unit analyzes the preprocessed digital signal and extracts key feature parameters of partial discharge. The pattern recognition unit classifies the discharge signals based on the extracted features and identifies different types of partial discharges. Interference identification and rejection unit distinguishes between partial discharge signals and non-discharge interference; The trend analysis unit analyzes the changing trends of partial discharge based on historical records and predicts potential risks. The risk assessment and health diagnosis unit evaluates the insulation status of the circuit breaker and generates a health rating based on the identification results, trend changes, and operating environment.

[0009] Furthermore, the alarm and decision-making module includes: The threshold determination unit compares the partial discharge characteristics input from the identification module with the set alarm threshold. Multi-level alarm units trigger different levels of alarm response mechanisms based on the judgment results; The response control unit executes the automatic response strategy. The information push and notification unit sends alarm information to the relevant platform; The alarm recording and tracing unit records each alarm event and related parameters for subsequent tracing and analysis.

[0010] Furthermore, the primary feature extraction and filtering unit employs an envelope extraction algorithm, the formula of which is as follows: The original signal is The Hilbert transform is denoted as signal envelope for: ; The Hilbert transform is defined as follows: .

[0011] Furthermore, the feature extraction unit uses partial discharge pulse amplitude extraction, and its algorithm formula is as follows: ; in, Discrete PD signal after bandpass filtering; : Detection window for each pulse.

[0012] Furthermore, the pattern recognition unit employs the support vector machine algorithm, the formula of which is as follows: For the input feature vector The training objective of SVM is to find the optimal hyperplane. ; in, Weight vector, representing the classification direction; : Bias term; the classification criterion is As one category, It belongs to another category.

[0013] Furthermore, the interference identification and removal unit employs a time-frequency domain energy distribution difference identification algorithm, the formula of which is as follows: After performing wavelet packet decomposition on the signal, the statistics of each sub-band are obtained. Energy: ; Then calculate the energy ratio: ; Construct template vectors and Using Euclidean distance: ; like It was judged as interference and removed.

[0014] This solution also discloses an operation method for a circuit breaker partial discharge monitoring system, which mainly includes the following steps: Step A1: After the system starts, the system management and storage module performs a status self-check on each sub-module; Step A2: The controller starts the high-frequency current sensor, ultrasonic sensor, ultra-high frequency electromagnetic wave sensor, and environmental parameter sensor in the sensing and acquisition module, and sets the sampling frequency, gain parameter, and synchronization clock source. Step A3: The data acquisition and preprocessing module starts the high-speed ADC and synchronous controller to synchronously sample the analog signals from multiple sensor channels; Step A4: Filter, amplify, and limit the acquired raw signal, and perform analog-to-digital conversion to form a processable digital signal stream; Step A5: Perform preliminary feature extraction on the digital signal using the FPGA and temporarily cache it in the high-speed cache area; Step A6: The signal recognition and diagnosis module identifies the type of partial discharge and eliminates non-partial discharge interference; Step A7: Based on the feature vector input, classify the discharge type and determine its severity and possible spatial location; Step A8: The alarm and decision module determines whether to trigger an early warning response based on the identification results and the set threshold, and records the current event level and discharge parameters; Step A9: Transmit the identification results and alarm information to the user terminal through the communication and visualization module; Step A10: The system management and storage module stores partial discharge data, phase spectrum, alarm records and trend charts in the local database and uploads them to the remote backup terminal.

[0015] The beneficial effects achieved by the present invention using the above structure are as follows: The present invention provides a circuit breaker partial discharge monitoring system, which achieves the following beneficial effects: (1) By integrating high-frequency current sensor, ultrasonic sensor, ultra-high frequency electromagnetic wave sensor and environmental parameter sensor, multi-dimensional detection of electrical, magnetic and acoustic signals generated during partial discharge and interference environment can be achieved, effectively improving signal reliability and recognition accuracy, and avoiding false alarms and missed alarms of a single sensor.

[0016] (2) Real-time data acquisition and preprocessing to ensure the continuity and stability of monitoring.

[0017] (3) Through various interference removal techniques such as wavelet packet energy distribution algorithm and phase distribution consistency discrimination, it can effectively identify and filter out non-partial discharge signals such as power frequency interference, wireless noise, and lightning strike induction, significantly improving the robustness and engineering adaptability of the system.

[0018] (4) The signal recognition and diagnosis module introduces the support vector machine learning algorithm to realize the automatic identification and risk level judgment of different types of partial discharges such as corona, internal discharge and surface discharge, and assist maintenance personnel in making accurate diagnoses and scientific decisions.

[0019] (5) The system management module supports online operation status monitoring, fault self-diagnosis and remote software upgrade, which can effectively reduce the frequency of manual inspection and maintenance costs, and improve the stability and intelligence level of the system throughout its entire life cycle. Attached Figure Description

[0020] Figure 1 This is a flowchart of a circuit breaker partial discharge monitoring system proposed in this invention.

[0021] The accompanying drawings are provided to further illustrate the invention and form part of the specification. They are used together with the embodiments of the invention to explain the invention and do not constitute a limitation thereof. Detailed Implementation

[0022] The technical solutions of the present invention will be clearly and completely described below with reference to the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative effort are within the scope of protection of the present invention.

[0023] Example 1: Please see Figure 1 As shown, this embodiment is a circuit breaker partial discharge monitoring system, including a sensor acquisition module, a data acquisition and preprocessing module, a signal recognition and diagnosis module, an alarm and decision module, a communication and visualization module, and a system management and storage module; Among them, the sensor acquisition module is used to acquire the partial discharge signal inside the circuit breaker in real time; Among them, the signal recognition and diagnosis module is used to perform in-depth analysis on the preprocessed data to identify the type, severity and possible location of partial discharge; Among them, the alarm and decision module is linked with the signal recognition module to generate corresponding alarm signals based on the recognition results and trigger a multi-level response mechanism. The system management and storage module is used to provide power supply, data management, and operation and maintenance support for the entire system. Example 2: Please see Figure 1 As shown, this embodiment illustrates a method for using a circuit breaker partial discharge monitoring system, including the following steps: Step A1: After the system starts, the system management and storage module performs a status self-check on each sub-module; Step A2: The controller starts the high-frequency current sensor, ultrasonic sensor, ultra-high frequency electromagnetic wave sensor, and environmental parameter sensor in the sensing and acquisition module, and sets the sampling frequency, gain parameter, and synchronization clock source. Step A3: The data acquisition and preprocessing module starts the high-speed ADC and synchronous controller to synchronously sample the analog signals from multiple sensor channels; Step A4: Filter, amplify, and limit the acquired raw signal, and perform analog-to-digital conversion to form a processable digital signal stream; Step A5: Perform preliminary feature extraction on the digital signal using the FPGA and temporarily cache it in the high-speed cache area; Step A6: The signal recognition and diagnosis module identifies the type of partial discharge and eliminates non-partial discharge interference; Step A7: Based on the feature vector input, classify the discharge type and determine its severity and possible spatial location; Step A8: The alarm and decision module determines whether to trigger an early warning response based on the identification results and the set threshold, and records the current event level and discharge parameters; Step A9: Transmit the identification results and alarm information to the user terminal through the communication and visualization module; Step A10: The system management and storage module stores partial discharge data, phase spectrum, alarm records and trend charts in the local database and uploads them to the remote backup terminal.

[0024] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

[0025] The present invention and its embodiments have been described above. This description is not restrictive, and the accompanying drawings are only one embodiment of the present invention; the actual structure is not limited thereto. In conclusion, if those skilled in the art are inspired by this description and design similar structures and embodiments without departing from the spirit of the invention, such designs should fall within the protection scope of the present invention.

Claims

1. A circuit breaker partial discharge monitoring system, characterized in that, include: Sensor acquisition module: used to acquire partial discharge signals inside the circuit breaker in real time; Data acquisition and preprocessing module: Connected to the sensor acquisition module, it is used to convert the acquired analog signals into digital signals and perform preliminary data filtering, amplification and synchronization processing; Signal recognition and diagnosis module: used to perform in-depth analysis of preprocessed data to identify the type, severity and possible location of partial discharge; Alarm and Decision Module: Linked with the signal recognition module, it generates corresponding alarm signals based on the recognition results and triggers a multi-level response mechanism. Communication and visualization module: used to realize data transmission and graphical interaction between this system and external user terminals; System Management and Storage Module: Used to provide power supply, data management and operation and maintenance support for the entire system.

2. The circuit breaker partial discharge monitoring system according to claim 1, characterized in that: The sensor acquisition module includes: A high-frequency current sensor is used to detect transient pulse current signals generated by partial discharge; Ultrasonic sensors are used to capture sound wave signals generated during partial discharge. Ultra-high frequency electromagnetic wave sensor to detect electromagnetic radiation waves generated during partial discharge activity; Environmental parameter sensors will monitor in real time the temperature, humidity, air pressure, and electromagnetic interference intensity of the environment in which the circuit breaker is located.

3. The circuit breaker partial discharge monitoring system according to claim 2, characterized in that: The data acquisition and preprocessing module includes: The signal conditioning unit preprocesses the raw analog signal from the sensor to meet the ADC input requirements; The analog-to-digital converter accurately converts analog signals into digital signals for subsequent FPGA processing. The sampling synchronization and clock control unit ensures synchronous sampling among multiple ADC channels and provides a unified time reference. The data buffer and cache unit temporarily stores high-frequency sampled data to prevent data loss; The primary feature extraction and filtering unit uses FPGA to perform primary calculations on the raw data, reducing the workload on the main control unit.

4. The circuit breaker partial discharge monitoring system according to claim 3, characterized in that: The signal recognition and diagnosis module includes: The feature extraction unit analyzes the preprocessed digital signal and extracts key feature parameters of partial discharge. The pattern recognition unit classifies the discharge signals based on the extracted features and identifies different types of partial discharges. Interference identification and rejection unit distinguishes between partial discharge signals and non-discharge interference; The trend analysis unit analyzes the changing trends of partial discharge based on historical records and predicts potential risks. The risk assessment and health diagnosis unit evaluates the insulation status of the circuit breaker and generates a health rating based on the identification results, trend changes, and operating environment.

5. A circuit breaker partial discharge monitoring system according to claim 4, characterized in that: The alarm and decision-making module includes: The threshold determination unit compares the partial discharge characteristics input from the identification module with the set alarm threshold. Multi-level alarm units trigger different levels of alarm response mechanisms based on the judgment results; The response control unit executes the automatic response strategy. The information push and notification unit sends alarm information to the relevant platform; The alarm recording and tracing unit records each alarm event and related parameters for subsequent tracing and analysis.

6. The circuit breaker partial discharge monitoring system according to claim 5, characterized in that: The primary feature extraction and filtering unit employs an envelope extraction algorithm, the formula of which is as follows: The original signal is The Hilbert transform is denoted as signal envelope for: ； The Hilbert transform is defined as follows: .

7. A circuit breaker partial discharge monitoring system according to claim 6, characterized in that: The feature extraction unit uses partial discharge pulse amplitude extraction, and its algorithm formula is as follows: ； in, Discrete PD signal after bandpass filtering; : Detection window for each pulse.

8. A circuit breaker partial discharge monitoring system according to claim 7, characterized in that: The pattern recognition unit uses the support vector machine algorithm, and its formula is as follows: For the input feature vector The training objective of SVM is to find the optimal hyperplane. ； in, Weight vector, representing the classification direction; : Bias term; the classification criterion is As one category, It belongs to another category.

9. A circuit breaker partial discharge monitoring system according to claim 8, characterized in that: The interference identification and removal unit employs a time-frequency domain energy distribution difference identification algorithm, the formula of which is as follows: After performing wavelet packet decomposition on the signal, the statistics of each sub-band are obtained. Energy: ； Then calculate the energy ratio: ； Construct template vectors and Using Euclidean distance: ； like It was judged as interference and removed.

10. An operation method for a circuit breaker partial discharge monitoring system, characterized in that; Operating the circuit breaker partial discharge monitoring system according to claim 9 mainly includes the following steps: Step A1: After the system starts, the system management and storage module performs a status self-check on each sub-module; Step A2: The controller starts the high-frequency current sensor, ultrasonic sensor, ultra-high frequency electromagnetic wave sensor, and environmental parameter sensor in the sensing and acquisition module, and sets the sampling frequency, gain parameter, and synchronization clock source. Step A3: The data acquisition and preprocessing module starts the high-speed ADC and synchronous controller to synchronously sample the analog signals from multiple sensor channels; Step A4: Filter, amplify, and limit the acquired raw signal, and perform analog-to-digital conversion to form a processable digital signal stream; Step A5: Perform preliminary feature extraction on the digital signal using the FPGA and temporarily cache it in the high-speed cache area; Step A6: The signal recognition and diagnosis module identifies the type of partial discharge and eliminates non-partial discharge interference; Step A7: Based on the feature vector input, classify the discharge type and determine its severity and possible spatial location; Step A8: The alarm and decision module determines whether to trigger an early warning response based on the identification results and the set threshold, and records the current event level and discharge parameters; Step A9: Transmit the identification results and alarm information to the user terminal through the communication and visualization module; Step A10: The system management and storage module stores partial discharge data, phase spectrum, alarm records and trend charts in the local database and uploads them to the remote backup terminal.

Images