Intelligent Diagnostic System and Method for Partial Discharge Based on Multimodal Signal Fusion

Abstract

This invention discloses a partial discharge intelligent diagnostic system and method based on multimodal signal fusion, belonging to the field of intelligent partial discharge diagnostic technology. It includes a device-side multimodal partial discharge detection unit, a multimodal data acquisition module, and a chip-based device-side discharge autonomous handling module. By fusing ultrasonic, electromagnetic wave, and visual signals, the intelligent partial discharge diagnostic system can detect partial discharge from multiple dimensions, effectively improving the accuracy and reliability of detection. Comprehensive analysis of multimodal data reduces the possibility of misdiagnosis and missed diagnosis caused by a single signal. The device-side discharge autonomous handling module can detect partial discharge in real time and perform edge judgment based on preset thresholds, quickly identifying partial discharge events. Independent edge deployment is possible, and real-time monitoring helps to promptly detect anomalies. It also interacts with the controller of the target device to send power-off control signals, and the rapid response prevents the partial discharge phenomenon from escalating and causing greater damage to the internal electrical components of the device.

Description

Technical Field

[0001] This invention relates to the field of intelligent partial discharge diagnosis technology, and in particular to an intelligent partial discharge diagnosis system and method based on multimodal signal fusion. Background Technology

[0002] Partial discharge (PD) is a common phenomenon in the insulation systems of high-voltage power equipment, which can lead to performance degradation or even malfunction. Currently, partial discharge diagnostic techniques mainly include ultrasonic testing, high-frequency current detection, ultra-high frequency testing, optical detection, and chemical detection.

[0003] Currently, partial discharge generated inside equipment is typically detected using methods such as ultrasonic testing, high-frequency current testing, ultra-high-frequency current testing, and optical testing.

[0004] Using ultrasonic signals to identify partial discharges is a detection method that is susceptible to environmental noise interference, suffers severe signal attenuation during propagation, and has low positioning accuracy.

[0005] High-frequency current detection detects high-frequency current signals caused by partial discharge, but has a limited detection range and is not sensitive to long-distance discharge.

[0006] Ultra-high frequency (UHF) detection uses UHF signals to detect partial discharge. However, the signal attenuates rapidly in complex environments, and the detection equipment is expensive.

[0007] Optical detection utilizes the light signals generated by partial discharge for detection. It is greatly affected by ambient light and the installation of the detection equipment is complex.

[0008] Diagnosis is achieved by detecting the chemical gases produced by partial discharge. However, this method has a long response time and cannot be monitored in real time.

[0009] Therefore, developing a novel partial discharge detection method to solve the problems of missed detection and misdiagnosis in traditional single partial discharge detection is an urgent technical issue that needs to be addressed. Summary of the Invention

[0010] To address the technical problems in partial discharge detection and diagnosis of the aforementioned devices, this invention provides an intelligent partial discharge diagnostic system and method based on multi-modal signal fusion. The technical solution adopted is as follows:

[0011] A partial discharge intelligent diagnostic system based on multimodal signal fusion includes a device-side multimodal partial discharge detection unit, a multimodal data acquisition module, and a chip-based device-side discharge autonomous handling module. The device-side multimodal partial discharge detection unit includes an ultrasonic detection module, an electromagnetic wave signal detection module, and a visual detection module. The ultrasonic detection module detects changes in ultrasonic signals inside the target device, the electromagnetic wave signal detection module detects ultra-high frequency electromagnetic wave signals generated inside the target device, and the visual detection module captures a visual image of the target device's interior. The ultrasonic detection module, electromagnetic wave signal detection module, and visual detection module are all communicatively connected to the signal input terminal of the multimodal data acquisition module. The signal output terminal of the data acquisition module is communicatively connected to the device-side discharge autonomous handling module. The device-side discharge autonomous handling module determines whether partial discharge has occurred based on thresholds. It sets ultrasonic change thresholds and UHF electromagnetic wave signal thresholds. If it determines that the current detected value of ultrasonic waves exceeds the ultrasonic change threshold and / or the current detected value of UHF electromagnetic wave signals exceeds the UHF electromagnetic wave signal threshold, and at the same time, the feature analysis of the internal visual image of the device shows luminescence characteristics, then it outputs the diagnostic result of partial discharge. The device-side discharge autonomous handling module is communicatively connected to the controller of the target device. When the edge judgment of the device-side discharge autonomous handling module shows the diagnostic result of partial discharge, it exchanges a power-off control signal with the controller of the target device.

[0012] By employing the above technical solutions and integrating ultrasonic, electromagnetic wave, and visual signals, the intelligent diagnostic system for partial discharge can detect partial discharge from multiple dimensions, effectively improving the accuracy and reliability of detection. The comprehensive analysis of multimodal data reduces the possibility of misdiagnosis and missed diagnosis caused by a single signal.

[0013] The device-side discharge autonomous handling module determines whether partial discharge has occurred based on thresholds. It sets ultrasonic change thresholds and ultra-high frequency electromagnetic wave signal thresholds. If it determines that the current ultrasonic detection value exceeds the ultrasonic change threshold and / or the current ultra-high frequency electromagnetic wave signal detection value exceeds the ultra-high frequency electromagnetic wave signal threshold, and at the same time, the feature analysis of the internal visual image of the device shows luminous characteristics, then it outputs the diagnostic result of partial discharge.

[0014] Upon detecting luminescent characteristics, if the current detected ultrasonic value exceeds the ultrasonic variation threshold and the current detected UHF electromagnetic wave signal exceeds the UHF electromagnetic wave signal threshold, the probability of partial discharge within the target device is very high. The system can output a diagnostic result indicating partial discharge based on edge detection, along with a power-off signal. The device-side discharge autonomous handling module can detect and perform edge detection based on preset thresholds in real time, quickly identifying partial discharge events. Because only thresholds are used for judgment, the computational load is relatively small, allowing for independent edge deployment. Real-time monitoring helps to promptly detect anomalies and interacts with the target device's controller to exchange power-off control signals. This rapid response prevents the partial discharge from escalating and causing greater damage to the internal electrical components of the device.

[0015] Timely detection and handling of partial discharge can prevent equipment damage and safety accidents caused by discharge, thus improving the safety and reliability of the system.

[0016] Optionally, the ultrasonic detection module includes an ultrasonic sensor mounting base, an ultrasonic sensor, a filter, and an ultrasonic data buffer. One end of the ultrasonic sensor mounting base is installed at the top center of the inner wall of the target device's housing, and the other end of the ultrasonic sensor mounting base is provided with a sensor mounting internal thread. The ultrasonic sensor is screwed onto the sensor mounting internal thread and receives ultrasonic signals from the target device's housing through the ultrasonic sensor mounting base. The ultrasonic sensor is communicatively connected to the filter, the filter is communicatively connected to the ultrasonic data buffer, and the ultrasonic data buffer is communicatively connected to the data input terminal of the multimodal data acquisition module.

[0017] By employing the above technical solution, partial discharge generates ultrasonic signals. When partial discharge occurs inside the target device, electrons in the discharge area move at high speed and collide with the surrounding medium, causing the medium to heat up and expand instantaneously, thus generating mechanical stress waves, i.e., ultrasonic waves. These ultrasonic signals propagate inside the device in the form of waves. An ultrasonic sensor mounting base combined with an ultrasonic sensor is used to receive these signals, which are then filtered and transmitted to the modal data acquisition module.

[0018] Optionally, the electromagnetic wave signal detection module includes an ultra-high frequency partial discharge sensor and an ultra-high frequency data buffer. The ultra-high frequency partial discharge sensor is installed inside the target device, around the main cable. The ultra-high frequency partial discharge sensor is communicatively connected to the ultra-high frequency data buffer, and the ultra-high frequency data buffer is communicatively connected to the data input terminal of the multi-modal data acquisition module.

[0019] By employing the above technical solution, the high-frequency partial discharge sensor detects the presence of partial discharge by coupling the ultra-high frequency electromagnetic wave signal generated by partial discharge in the electrical system. The basic principle of the ultra-high frequency detection method is to use an ultra-high frequency partial discharge sensor to detect the ultra-high frequency electromagnetic wave signal (the frequency of the electromagnetic wave is approximately 300MHz to 3GHz) generated during partial discharge in power equipment.

[0020] Optionally, the visual inspection module includes a visual camera and a visual data buffer. The visual camera is mounted on the inner wall of the target device's housing via a bracket to capture visual images of the target device's interior. The visual camera is communicatively connected to the visual data buffer, which is communicatively connected to the data input terminal of the multimodal data acquisition module.

[0021] By adopting the above technical solution, the visual camera can recognize luminous features.

[0022] Optionally, the device-side multimodal partial discharge detection unit further includes a wireless communication attenuation detection module. The wireless communication attenuation detection module includes a first wireless communication module, a second wireless communication module, and a wireless communication data buffer. The first and second wireless communication modules are respectively mounted on the inner wall of the target device's housing via brackets. The first and second wireless communication modules are wirelessly connected and exchange standard data packets with each other at set intervals. The first and second wireless communication modules store the received standard data packets in the wireless communication data buffer. The wireless communication data buffer is communicatively connected to the data input terminal of the multimodal data acquisition module.

[0023] Optionally, both the first and second wireless communication modules are Zigbee modules.

[0024] By adopting the above technical solution, the Zigbee module has the advantages of low cost, low power consumption, and small size. It can even work stably for several years when powered by a battery. Due to its small size, it will not cause interference to the target device after deployment. The Zigbee module is greatly affected by electromagnetic interference caused by partial discharge. Therefore, partial discharge can be detected by receiving standard data packets from another Zigbee transmitter module. The analysis of signal strength changes is mainly based on the parsing results of the standard data packets. The standard data packets can be a small segment of digital data, such as an Arabic numeral set from 1 to 10. The standard data packets are parsed to obtain the RSSI value of the wireless network transmitter. The structure containing the RSSI is aflncomingMSGPacket_t. In this structure, there are two variables related to communication quality. These are: aflncomingMSGPacket_t->rssi and rssirssiafincominaMSGPacket_t->inkQuality, where rssi: received signal strength indicator represents the signal strength value. The signal strength value is obtained based on the RSSI value. If a standard data packet is sent and received every 0.2 seconds, the difference between the RSSI values ​​of the two standard data packets can be used to obtain the signal strength change value. The wireless communication signal attenuation value is set to 30%. For example, if the signal strength change value is greater than 30%, it can be determined that the signal strength change exceeds the standard.

[0025] Optionally, the device-side discharge autonomous handling module includes a data storage device, a data analysis chip, and a vision analysis chip. The data storage device is communicatively connected to the data output terminal of the multimodal data acquisition module, and the data analysis chip and the vision analysis chip are communicatively connected to the data storage device, respectively.

[0026] By adopting the above technical solution, the main visual feature of partial discharge is the phenomenon of light emission, and the visual analysis chip can realize the recognition of the visual feature of light emission.

[0027] Optionally, the device-side discharge autonomous handling module also includes an audible and visual alarm. When the data analysis chip outputs a diagnostic result indicating partial discharge at the edge, it sends an alarm signal to the audible and visual alarm.

[0028] By adopting the above technical solution, an audible and visual alarm can be triggered when a partial discharge is detected at the output edge, prompting staff to take appropriate action.

[0029] The intelligent diagnostic method for partial discharge based on multimodal signal fusion detects partial discharge phenomena in target devices using an intelligent diagnostic system for partial discharge based on multimodal signal fusion, and includes the following steps:

[0030] Step 1: The device-side discharge autonomous handling module parses the detection data packets from the ultrasonic detection module, electromagnetic signal detection module, visual detection module, and wireless communication attenuation detection module, respectively.

[0031] Step 2: The device-side discharge autonomous handling module sets the ultrasonic wave change threshold, the ultra-high frequency electromagnetic wave signal threshold, and the wireless communication signal attenuation threshold.

[0032] Step 3: Set three out-of-limit items: the current detection value of ultrasonic wave exceeds the ultrasonic wave change threshold, the current detection value of UHF electromagnetic wave signal exceeds the UHF electromagnetic wave signal threshold, and the attenuation value of wireless communication signal exceeds the wireless communication signal attenuation threshold. If the device-side discharge autonomous handling module determines that at least one of the three out-of-limit items is out of limit, and at the same time the device-side discharge autonomous handling module analyzes the feature analysis of the internal visual image of the device and finds luminous features, then outputs the diagnostic result of partial discharge at the edge judgment, and the device-side discharge autonomous handling module exchanges a power-off control signal with the controller of the target device.

[0033] If more than two of the three exceed the standard, but the feature analysis of the internal visual image of the equipment does not show any luminous features, the equipment-side discharge autonomous handling module outputs a diagnostic result indicating partial discharge at the edge and exchanges a power-off control signal with the controller of the target equipment.

[0034] Step 4: The controller of the target device executes a power-off control.

[0035] By adopting the above technical solution, assuming that the background noise level recorded by our ultrasonic detection module under normal conditions is 20dB, and any signal exceeding this level by 10dB is considered a potential partial discharge signal, then the ultrasonic change threshold can be set to 30dB.

[0036] This means that if the detected ultrasonic signal intensity exceeds 30dB, it is judged as an excessive ultrasonic signal intensity, and the system believes that partial discharge may have occurred.

[0037] For ultra-high frequency (UHF) electromagnetic wave signals, assuming that the detected signal strength is 1 μV / m under normal conditions, and any signal exceeding this strength by 50 times is considered an indication of partial discharge, then the UHF electromagnetic wave signal threshold can be set to 50 μV / m.

[0038] If the detected ultra-high frequency electromagnetic wave signal intensity exceeds 50μV / m, the system will determine that the ultra-high frequency electromagnetic wave signal exceeds the standard and consider that partial discharge may have occurred.

[0039] If the wireless communication signal attenuation value is 30%, and the signal strength change value is greater than 30%, it can be determined that the signal strength change exceeds the standard, and the system will consider that partial discharge may have occurred.

[0040] By combining the identification results of luminescence characteristics, more accurate partial discharge detection results of target devices can be achieved, and timely power-off measures can be taken to avoid serious damage to electrical components of target devices caused by partial discharge.

[0041] Optionally, in step 3, when the device-side discharge autonomous handling module outputs a diagnostic result indicating partial discharge at the edge, it sends an alarm signal to the audible and visual alarm, which then performs the audible and visual alarm action.

[0042] In summary, the present invention has at least one of the following beneficial technical effects:

[0043] This invention provides an intelligent diagnostic system and method for partial discharge based on multimodal signal fusion. By fusing ultrasonic, electromagnetic, and visual signals, the intelligent diagnostic system can detect partial discharge from multiple dimensions, effectively improving the accuracy and reliability of detection. The comprehensive analysis of multimodal data reduces the possibility of misdiagnosis and missed diagnosis caused by a single signal.

[0044] The device-side discharge autonomous handling module can detect partial discharge events in real time and perform edge judgment based on preset thresholds, quickly identifying such events. Using only thresholds for judgment results in minimal computation, allowing for independent deployment at the edge. Real-time monitoring helps to promptly detect anomalies and exchanges power-off control signals with the target device's controller. This rapid response prevents the partial discharge from escalating and causing further damage to internal electrical components. Timely detection and handling of partial discharges prevents equipment damage and safety accidents caused by discharges, improving system safety and reliability. Attached Figure Description

[0045] Figure 1 This is a schematic diagram of the electrical component connection principle of the partial discharge intelligent diagnostic system based on multimodal signal fusion of the present invention;

[0046] Figure 2 This is a flowchart illustrating the intelligent diagnostic method for partial discharge based on multimodal signal fusion according to the present invention.

[0047] Explanation of reference numerals in the attached figures: 11. Ultrasonic detection module; 111. Ultrasonic sensor mounting base; 112. Ultrasonic sensor; 113. Filter; 114. Ultrasonic data buffer; 12. Electromagnetic signal detection module; 121. UHF partial discharge sensor; 122. UHF data buffer; 13. Visual inspection module; 131. Visual camera; 132. Visual data buffer; 14. Wireless communication attenuation detection module; 141. First wireless communication module; 142. Second wireless communication module; 143. Wireless communication data buffer; 2. Multimodal data acquisition module; 3. Equipment-side discharge autonomous handling module; 31. Data storage device; 32. Data analysis chip; 33. Visual analysis chip; 34. Audible and visual alarm. Detailed Implementation

[0048] The present invention will be further described in detail below with reference to the accompanying drawings.

[0049] This invention discloses a partial discharge intelligent diagnostic system and method based on multimodal signal fusion.

[0050] Reference Figure 1 and Figure 2 Example 1: A partial discharge intelligent diagnostic system based on multimodal signal fusion includes a device-side multimodal partial discharge detection unit, a multimodal data acquisition module 2, and a chip-based device-side discharge autonomous handling module 3. The device-side multimodal partial discharge detection unit includes an ultrasonic detection module 11, an electromagnetic wave signal detection module 12, and a visual detection module 13. The ultrasonic detection module 11 is used to detect changes in ultrasonic signals inside the target device. The electromagnetic wave signal detection module 12 is used to detect ultra-high frequency electromagnetic wave signals generated inside the target device. The visual detection module 13 captures visual images of the inside of the target device. The ultrasonic detection module 11, the electromagnetic wave signal detection module 12, and the visual detection module 13 are respectively connected to the signal input terminal of the multimodal data acquisition module 2. The signal output terminal of the multimodal data acquisition module 2 is connected to the device-side discharge autonomous handling module 3. The device-side discharge autonomous handling module 3 performs edge judgment based on thresholds to determine whether partial discharge has occurred. It sets ultrasonic change thresholds and ultra-high frequency electromagnetic wave signal thresholds. If the current detection value of ultrasonic waves exceeds the ultrasonic change threshold and / or the current detection value of ultra-high frequency electromagnetic wave signals exceeds the ultra-high frequency electromagnetic wave signal threshold, and at the same time, the feature analysis of the internal visual image of the device shows luminous characteristics, then it outputs the diagnostic result of partial discharge in the edge judgment. The device-side discharge autonomous handling module 3 is connected to the controller of the target device. When the edge judgment of the device-side discharge autonomous handling module 3 shows the diagnostic result of partial discharge, it exchanges a power-off control signal with the controller of the target device.

[0051] By integrating ultrasonic, electromagnetic wave, and visual signals, the intelligent diagnostic system for partial discharge can detect partial discharge from multiple dimensions, effectively improving the accuracy and reliability of detection. The comprehensive analysis of multimodal data reduces the possibility of misdiagnosis and missed diagnosis caused by a single signal.

[0052] The device-side discharge autonomous handling module 3 determines whether partial discharge has occurred based on thresholds. It sets ultrasonic change thresholds and ultra-high frequency electromagnetic wave signal thresholds. If it determines that the current detection value of ultrasonic waves exceeds the ultrasonic change threshold and / or the current detection value of ultra-high frequency electromagnetic wave signals exceeds the ultra-high frequency electromagnetic wave signal threshold, and at the same time, the feature analysis of the internal visual image of the device shows luminous characteristics, then it outputs the diagnostic result of partial discharge.

[0053] Simultaneously with the detection of luminescent features, if the current detected value of the ultrasonic wave exceeds the ultrasonic wave change threshold and the current detected value of the ultra-high frequency electromagnetic wave signal exceeds the ultra-high frequency electromagnetic wave signal threshold, the probability of partial discharge within the target device is very high. The system can output a diagnostic result indicating partial discharge based on edge detection, and simultaneously output a power-off signal. The device-side discharge autonomous handling module 3 can detect in real time and perform edge detection based on preset thresholds, quickly identifying partial discharge events. Because only thresholds are used for judgment, the computational load is small, allowing for independent edge deployment. Real-time monitoring helps to promptly detect anomalies and interacts with the target device's controller to exchange power-off control signals. This rapid response prevents the partial discharge phenomenon from escalating and causing greater damage to the electrical components within the device.

[0054] Timely detection and handling of partial discharge can prevent equipment damage and safety accidents caused by discharge, thus improving the safety and reliability of the system.

[0055] Example 2: The ultrasonic detection module 11 includes an ultrasonic sensor mounting base 111, an ultrasonic sensor 112, a filter 113, and an ultrasonic data buffer 114. One end of the ultrasonic sensor mounting base 111 is installed at the top center of the inner wall of the target device's housing. The other end of the ultrasonic sensor mounting base 111 is provided with a sensor mounting internal thread. The ultrasonic sensor 112 is screwed into the sensor mounting internal thread and receives ultrasonic signals from the target device's housing through the ultrasonic sensor mounting base 111. The ultrasonic sensor 112 is communicatively connected to the filter 113, the filter 113 is communicatively connected to the ultrasonic data buffer 114, and the ultrasonic data buffer 114 is communicatively connected to the data input terminal of the multimodal data acquisition module 2.

[0056] Partial discharge generates ultrasonic signals. When partial discharge occurs inside the target device, electrons in the discharge area move at high speed and collide with the surrounding medium, causing the medium to heat up and expand instantaneously, thus generating mechanical stress waves, which are ultrasonic waves. These ultrasonic signals propagate inside the device in the form of waves. Ultrasonic sensor mounting base 111, combined with ultrasonic sensor 112, receives these signals, which are then filtered by filter 113 before being transmitted to modal data acquisition module 2.

[0057] Example 3: The electromagnetic wave signal detection module 12 includes an ultra-high frequency partial discharge sensor 121 and an ultra-high frequency data buffer 122. The ultra-high frequency partial discharge sensor 121 is installed inside the main cable of the target device. The ultra-high frequency partial discharge sensor 121 is communicatively connected to the ultra-high frequency data buffer 122. The ultra-high frequency data buffer 122 is communicatively connected to the data input terminal of the multi-modal data acquisition module 2.

[0058] The high-frequency partial discharge sensor 121 detects the presence of partial discharge by coupling the ultra-high frequency electromagnetic wave signal generated by partial discharge in the electrical system. The basic principle of the ultra-high frequency detection method is to use an ultra-high frequency partial discharge sensor to detect the ultra-high frequency electromagnetic wave signal (the frequency of the electromagnetic wave is approximately 300MHz to 3GHz) generated during partial discharge in power equipment.

[0059] Example 4: The visual inspection module 13 includes a visual camera 131 and a visual data buffer 132. The visual camera 131 is mounted on the inner wall of the target device's housing via a bracket to capture the visual image inside the target device. The visual camera 131 is communicatively connected to the visual data buffer 132, and the visual data buffer 132 is communicatively connected to the data input terminal of the multimodal data acquisition module 2.

[0060] The visual camera 131 can identify luminous features.

[0061] In Example 5, the device-side multimodal partial discharge detection unit further includes a wireless communication attenuation detection module 14. The wireless communication attenuation detection module 14 includes a first wireless communication module 141, a second wireless communication module 142, and a wireless communication data buffer 143. The first wireless communication module 141 and the second wireless communication module 142 are respectively mounted on the inner wall of the target device housing via brackets. The first wireless communication module 141 and the second wireless communication module 142 are wirelessly connected to each other and exchange standard data packets wirelessly at set intervals. The first wireless communication module 141 and the second wireless communication module 142 store the received standard data packets in the wireless communication data buffer 143. The wireless communication data buffer 143 is communicatively connected to the data input terminal of the multimodal data acquisition module 2.

[0062] In Example 6, both the first wireless communication module 141 and the second wireless communication module 142 are Zigbee modules.

[0063] Zigbee modules have the advantages of low cost, low power consumption, and small size. They can even work stably for several years when powered by batteries. Due to their small size, they will not cause interference to the target device after deployment. Zigbee modules are greatly affected by electromagnetic interference caused by partial discharge. Therefore, partial discharge can be detected by receiving standard data packets from another Zigbee transmitter module. The analysis of signal strength changes is mainly based on the parsing results of the standard data packets. The standard data packets can be a small segment of digital data, such as an Arabic numeral set from 1 to 10. Parsing the standard data packets yields the RSSI value of the wireless network transmitter. The structure containing the RSSI is aflncomingMSGPacket_t. In this structure, there are two variables related to communication quality. These are: aflncomingMSGPacket_t->rssi and rssirssiafincominaMSGPacket_t>inkQuality, where rssi: received signal strength indicator, representing the signal strength value. The signal strength value is obtained based on the RSSI value. If a standard data packet is sent and received every 0.2 seconds, the signal strength change value can be obtained by comparing the difference between the RSSI values ​​of the two standard data packets. The wireless communication signal attenuation value is set to 30%. For example, if the signal strength change value is greater than 30%, it can be determined that the signal strength change exceeds the standard.

[0064] Example 7: The device-side discharge autonomous handling module 3 includes a data storage 31, a data analysis chip 32, and a vision analysis chip 33. The data storage 31 is communicatively connected to the data output terminal of the multimodal data acquisition module 2, and the data analysis chip 32 and the vision analysis chip 33 are communicatively connected to the data storage 31, respectively.

[0065] The main visual feature of partial discharge is luminescence, and the visual analysis chip 33 can recognize the luminescence visual feature.

[0066] Example 8: The device-side discharge autonomous handling module 3 also includes an audible and visual alarm 34. When the data analysis chip 32 outputs a diagnostic result indicating partial discharge at the edge, it sends an alarm signal to the audible and visual alarm 34.

[0067] It can trigger an audible and visual alarm when a partial discharge is detected at the output edge, alerting staff to take appropriate action.

[0068] Example 9: A partial discharge intelligent diagnostic method based on multimodal signal fusion. This method uses a partial discharge intelligent diagnostic system based on multimodal signal fusion to detect partial discharge phenomena in a target device, including the following steps:

[0069] Step 1: The device-side discharge autonomous handling module 3 parses the detection data packets of the ultrasonic detection module 11, electromagnetic wave signal detection module 12, visual detection module 13, and wireless communication attenuation detection module 14 respectively.

[0070] Step 2: The device-side discharge autonomous handling module 3 sets the ultrasonic wave change threshold, the ultra-high frequency electromagnetic wave signal threshold, and the wireless communication signal attenuation threshold;

[0071] Step 3: Set three out-of-limit items: the current detection value of ultrasonic wave exceeds the ultrasonic wave change threshold, the current detection value of UHF electromagnetic wave signal exceeds the UHF electromagnetic wave signal threshold, and the attenuation value of wireless communication signal exceeds the wireless communication signal attenuation threshold. If the device-side discharge autonomous handling module 3 determines that at least one of the three out-of-limit items is out of limit, and at the same time, the device-side discharge autonomous handling module 3 analyzes the feature analysis of the internal visual image of the device and finds luminous features, then outputs the diagnostic result of partial discharge at the edge judgment, and the device-side discharge autonomous handling module 3 exchanges a power-off control signal with the controller of the target device.

[0072] If more than two of the three exceed the standard, but the feature analysis of the internal visual image of the equipment does not show any luminous features, the equipment-side discharge autonomous handling module 3 outputs the diagnostic result of partial discharge at the edge and exchanges a power-off control signal with the controller of the target equipment.

[0073] Step 4: The controller of the target device executes a power-off control.

[0074] Assuming the ultrasonic detection module we use records a background noise level of 20dB under normal conditions, and any signal exceeding this level by 10dB is considered a potential partial discharge signal, then the ultrasonic variation threshold can be set to 30dB.

[0075] This means that if the detected ultrasonic signal intensity exceeds 30dB, it is judged as an excessive ultrasonic signal intensity, and the system believes that partial discharge may have occurred.

[0076] For ultra-high frequency (UHF) electromagnetic wave signals, assuming that the detected signal strength is 1 μV / m under normal conditions, and any signal exceeding this strength by 50 times is considered an indication of partial discharge, then the UHF electromagnetic wave signal threshold can be set to 50 μV / m.

[0077] If the detected ultra-high frequency electromagnetic wave signal intensity exceeds 50μV / m, the system will determine that the ultra-high frequency electromagnetic wave signal exceeds the standard and consider that partial discharge may have occurred.

[0078] If the wireless communication signal attenuation value is 30%, and the signal strength change value is greater than 30%, it can be determined that the signal strength change exceeds the standard, and the system will consider that partial discharge may have occurred.

[0079] By combining the identification results of luminescence characteristics, more accurate partial discharge detection results of target devices can be achieved, and timely power-off measures can be taken to avoid serious damage to electrical components of target devices caused by partial discharge.

[0080] In Example 10, in step 3, when the device-side discharge autonomous handling module 3 outputs a diagnostic result indicating partial discharge at the edge, it sends an alarm signal to the audible and visual alarm 34, which then performs the audible and visual alarm action.

[0081] The following is a Python code example based on the intelligent diagnostic method for partial discharge.

[0082] #Hypothetical threshold setting

[0083] ultrasonic_threshold = 30# Ultrasonic change threshold, in dB

[0084] uhf_threshold = 50e-6# UHF electromagnetic wave signal threshold, unit V / m

[0085] wireless_attenuation_threshold = 30 # Wireless communication signal attenuation threshold, in %

[0086] # Hypothetical detection data packet parsing function

[0087] def parse_detection_data(ultrasonic_data,uhf_data,visual_dat a,wireless_data):

[0088] # Parse the data packet and return the detection value

[0089] ultrasonic_value=ultrasonic_data['value']

[0090] uhf_value = uhf_data['value']

[0091] visual_feature=visual_data['feature']

[0092] wireless_attenuation=wireless_data['attenuation']

[0093] return ultrasonic_value,uhf_value,visual_feature,wirele ss_attenuation

[0094] # Hypothetical visual feature analysis function

[0095] def analyze_visual_feature(visual_data):

[0096] #Analyze visual data to determine if luminescence features are present.

[0097] return 'glow' in visual_data

[0098] #Hypothetical control signal sending function

[0099] def send_control_signal(controller,command):

[0100] #Send control signals to the controller

[0101] print(f"Control signal sent to controller:{command}")

[0102] #Hypothetical interactive function for a sound and light alarm

[0103] def alert_alerter(alerter):

[0104] #Send alarm signal to the audible and visual alarm

[0105] print("Alert signal sent to sound and light alerter.")

[0106] #Logic of the device-side discharge autonomous handling module

[0107] def discharge_diagnosis(ultrasonic_data,uhf_data,visual_data,wireless_data):

[0108] # Parse and detect data packets

[0109] ultrasonic_value, uhf_value, visual_feature, wireless_attenuation = parse_detection_data(ultrasonic_data, uhf_data, visual_data, wireless_data)

[0110] # Determine if it exceeds the standard

[0111] ultrasonic_exceeds = ultrasonic_value > ultrasonic_threshold

[0112] uhf_exceeds = uhf_value > uhf_threshold

[0113] wireless_exceeds = wireless_attenuation > wireless_attenuation_threshold

[0114] # Comprehensive judgment

[0115] if (ultrasonic_exceeds or uhf_exceeds or wireless_exceeds) and analyze_visual_feature(visual_feature):

[0116] # Output the diagnostic result and execute the power-off control

[0117] print("Local discharge detected. Initiating power-off sequence.")

[0118] send_control_signal(controller='device_controller', command='POWER_OFF')

[0119] alert_alerter(alerter='sound_light_alerter')

[0120] elif sum([ultrasonic_exceeds, uhf_exceeds, wireless_exceeds]) > 1:

[0121] #If more than two items exceed the limit, power-off control will be executed even if there are no visual characteristics.

[0122] print("Local discharge likely.Initiating power-off sequence.")

[0123] send_control_signal(controller='device_controller',command='POWER_OFF')

[0124] alert_alerter(alerter='sound_light_alerter')

[0125] else:

[0126] #No partial discharge phenomenon

[0127] print("No local discharge detected.")

[0128] #Example of detecting data packets

[0129] ultrasonic_data = {'value':35} # Ultrasonic test value, in dB

[0130] uhf_data={'value':60e-6}# UHF electromagnetic wave signal detection value, unit V / mvisual_data={'feature':'glow detected'}# Visual feature data

[0131] wireless_data = {'attenuation':35} # Wireless communication signal attenuation value, in %;

[0132] #Perform discharge diagnosis

[0133] discharge_diagnosis(ultrasonic_data,uhf_data,visual_data,wireless_data).

[0134] The above are all preferred embodiments of the present invention and are not intended to limit the scope of protection of the present invention. Therefore, all equivalent changes made in accordance with the structure, shape and principle of the present invention should be covered within the scope of protection of the present invention.

Claims

1. A partial discharge intelligent diagnosis system based on multi-modal signal fusion, characterized in that: The device end multi-modal partial discharge detection unit, the multi-modal data acquisition module (2) and the device end discharge autonomous disposal module (3) based on the chip are included, the device end multi-modal partial discharge detection unit includes an ultrasonic detection module (11), an electromagnetic wave signal detection module (12) and a visual detection module (13), the ultrasonic detection module (11) is used to detect the ultrasonic signal change inside the target device, the electromagnetic wave signal detection module (12) is used to detect the ultra-high frequency electromagnetic wave signal generated inside the target device, the visual detection module (13) shoots the visual picture inside the target device, the ultrasonic detection module (11), electromagnetic wave signal detection module (12) and visual detection module (13) are respectively connected with the signal input end of multi-modal data acquisition module (2) in communication, the signal output end of multi-modal data acquisition module (2) is connected with device end discharge autonomous disposal module (3) in communication, device end discharge autonomous disposal module (3) carries out edge judgment whether partial discharge appears based on threshold, sets ultrasonic change threshold and ultra-high frequency electromagnetic wave signal threshold, if it is judged that the current detection value of ultrasonic exceeds ultrasonic change threshold and or the current detection value of ultra-high frequency electromagnetic wave signal exceeds ultra-high frequency electromagnetic wave signal threshold, and the characteristic analysis of the visual picture inside the device appears light-emitting feature, then the diagnostic result of edge judgment that partial discharge appears is output, the device end discharge autonomous disposal module (3) is connected with the controller of target device in communication, when the diagnostic result of edge judgment that partial discharge appears of device end discharge autonomous disposal module (3), the power-off control signal is interacted with the controller of target device; Three over-standard items of ultrasonic current detection value exceeding ultrasonic change threshold, ultra-high frequency electromagnetic wave signal current detection value exceeding ultra-high frequency electromagnetic wave signal threshold and wireless communication signal attenuation value exceeding wireless communication signal attenuation threshold are set, if device end discharge autonomous disposal module (3) judges that at least one over-standard item appears in three over-standard items, and the characteristic analysis of the visual picture inside the device appears light-emitting feature analyzed by device end discharge autonomous disposal module (3), then the diagnostic result of edge judgment that partial discharge appears is output, and device end discharge autonomous disposal module (3) interacts power-off control signal to the controller of target device; If it is judged that more than two over-standard items appear in three over-standard items, but the characteristic analysis of the visual picture inside the device does not appear light-emitting feature, device end discharge autonomous disposal module (3) outputs the diagnostic result of edge judgment that partial discharge appears, and interacts power-off control signal to the controller of target device.

2. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 1, characterized in that: The ultrasonic detection module (11) comprises an ultrasonic sensor mounting seat (111), an ultrasonic sensor (112), a filter (113) and an ultrasonic data buffer (114), one end of the ultrasonic sensor mounting seat (111) is mounted in the middle position of the top of the inner wall of the device shell of the target device, the other end of the ultrasonic sensor mounting seat (111) is provided with a sensor mounting internal thread, the ultrasonic sensor (112) is screwed at the sensor mounting internal thread, the ultrasonic sensor mounting seat (111) receives the ultrasonic signal of the device shell of the target device, the ultrasonic sensor (112) is in communication connection with the filter (113), the filter (113) is in communication connection with the ultrasonic data buffer (114), and the ultrasonic data buffer (114) is in communication connection with the data input end of the multi-modal data acquisition module (2).

3. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 2, characterized in that: The electromagnetic wave signal detection module (12) comprises a very high frequency partial discharge sensor (121) and a very high frequency data buffer (122), the very high frequency partial discharge sensor (121) is arranged on the periphery of the main cable in the device interior of the target device, the very high frequency partial discharge sensor (121) is in communication connection with the very high frequency data buffer (122), and the very high frequency data buffer (122) is in communication connection with the data input end of the multi-modal data acquisition module (2).

4. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 3, characterized in that: The visual detection module (13) comprises a visual camera (131) and a visual data buffer (132), the visual camera (131) is mounted on the inner wall of the shell of the target device through a support, and the visual camera (131) is in communication connection with the visual data buffer (132), and the visual data buffer (132) is in communication connection with the data input end of the multi-modal data acquisition module (2).

5. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 4, characterized in that: The device end multi-modal partial discharge detection unit further comprises a wireless communication attenuation detection module (14), the wireless communication attenuation detection module (14) comprises a first wireless communication module (141), a second wireless communication module (142) and a wireless communication data buffer (143), the first wireless communication module (141) and the second wireless communication module (142) are respectively mounted on the inner wall of the shell of the target device through supports, the first wireless communication module (141) and the second wireless communication module (142) are in wireless communication connection, standard data packets are wirelessly communicated and interacted with each other every set time, the first wireless communication module (141) and the second wireless communication module (142) store the received standard data packets in the wireless communication data buffer (143), and the wireless communication data buffer (143) is in communication connection with the data input end of the multi-modal data acquisition module (2).

6. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 5, characterized in that: The first wireless communication module (141) and the second wireless communication module (142) are Zigbee modules.

7. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 6, characterized in that: The device end discharge autonomous disposal module (3) comprises a data storage (31), a data analysis chip (32) and a visual analysis chip (33), the data storage (31) is in communication connection with the data output end of the multi-modal data acquisition module (2), and the data analysis chip (32) and the visual analysis chip (33) are respectively in communication connection with the data storage (31).

8. The partial discharge intelligent diagnosis system based on multi-modal signal fusion according to claim 7, characterized in that: The device end discharge autonomous disposal module (3) further comprises an audible and visual alarm (34), when the data analysis chip (32) outputs the diagnostic result that the edge judgment appears partial discharge, an alarm signal is interacted to the audible and visual alarm (34).

9. A partial discharge intelligent diagnosis method based on multi-modal signal fusion, characterized in that, The partial discharge intelligent diagnosis system based on multi-modal signal fusion in claim 8 is used to detect the partial discharge phenomenon of a target device, comprising the following steps: Step 1, the device end discharge autonomous disposal module (3) respectively analyzes the detection data packets of the ultrasonic wave detection module (11), the electromagnetic wave signal detection module (12), the visual detection module (13) and the wireless communication attenuation detection module (14); Step 2, the device end discharge autonomous disposal module (3) sets the ultrasonic wave change threshold value, the ultra-high frequency electromagnetic wave signal threshold value and the wireless communication signal attenuation threshold value; Step 3, according to the judgment result of the device end discharge autonomous disposal module (3), the controller of the target device executes corresponding power-off control.

10. The partial discharge intelligent diagnosis method based on multi-modal signal fusion according to claim 9, characterized in that, In step 3, when the device end discharge autonomous disposal module (3) outputs the diagnostic result that the edge judgment appears partial discharge, an alarm signal is interacted to the audible and visual alarm (34), and the audible and visual alarm (34) executes audible and visual alarm action.

Images