Non-intrusive distribution network main equipment monitoring device and method based on multi-dimensional data

Abstract

The present invention discloses a non-intrusive distribution network main equipment monitoring device and method based on multidimensional data, comprising a multidimensional information acquisition module for acquiring ambient temperature, as well as sound data, temperature, and visible light images of the distribution network main equipment; a first processing module for sampling the sound data and extracting characteristic frequencies, determining partial discharge signals based on the characteristic frequencies, and locating the sound source based on the sound arrival time when a partial discharge signal is present; correcting the temperature of the distribution network main equipment based on the ambient temperature, marking the sound source locations where partial discharge signals exist and the corrected distribution network main equipment temperatures on a visible light image to construct a fusion graph; and a second processing module transmitting the fusion graph to an external terminal via a communication module. Monitoring is performed from outside the distribution network main equipment without modifying the monitored object, and the operating status is identified based on multidimensional data, with the operating status of the main equipment and other information being transmitted to the external terminal for easy viewing by on-site personnel.

Description

Technical Field

[0001] The present invention relates to the technical field of online monitoring of main equipment in a distribution network, and in particular to a non-intrusive monitoring device and method for main equipment in a distribution network based on multi-dimensional data. Background Art

[0002] The statements in this section merely provide background information related to the present invention and do not necessarily constitute prior art.

[0003] The main equipment in a distribution network is the equipment that transmits electrical energy, including distribution transformers, switchgear, ring network boxes, and power cables. These equipment is primarily constructed from a variety of high-performance insulating materials. During normal operation, these equipment can be subjected to a combination of external physical and chemical factors, as well as overload and high current shocks, which can gradually degrade its insulation performance. This can eventually lead to insulation breakdown, resulting in equipment damage and widespread regional power outages.

[0004] Currently, the method for detecting the operating status of the main equipment in the distribution network includes manual inspection. Manual inspection refers to the regular inspection of equipment by inspection personnel carrying professional equipment, such as acoustic imagers, thermal imagers, partial discharge detectors, etc.; however, portable testers have a single function, and inspection personnel often carry multiple devices to monitor them separately. In addition, the operating environment is harsh and the safety risks are high. This method has a large workload, low detection efficiency, and is affected by the skill level of inspection personnel, and cannot detect equipment hazards in a timely manner.

[0005] Methods for monitoring the operating status of primary distribution network equipment also include contact temperature measurement, which involves placing sensors such as thermistors and thermocouples in contact with the object being measured, ensuring that both maintain the same temperature. This method monitors temperatures such as transformers and cable connectors. However, these sensors are difficult to retrofit into already operating equipment and require power outages, making them difficult to deploy.

[0006] Non-contact temperature measurement methods, based on the principle of blackbody radiation, do not involve contact between the sensor and the object being measured. These include visible light and infrared temperature sensors, fiber optic temperature measurement, and surface acoustic wave temperature measurement. Fiber optic temperature measurement offers excellent insulation and strong anti-interference capabilities, overcoming high levels of electromagnetic interference and providing more accurate measurement results. However, fiber optic temperature measurement systems are very expensive. Surface acoustic wave temperature measurement offers wireless and passive temperature measurement, making it more convenient to use, but also more expensive. Furthermore, relying solely on temperature for determination, it cannot identify defects at an early stage.

[0007] In ultrasonic partial discharge detection, local discharges cause vibrations and produce sounds, often in the form of ultrasonic waves inaudible to the human ear. Ultrasonic sensors can monitor these sounds and indirectly identify partial discharges. However, ultrasonic sensors have limited sensitivity, a narrow effective detection range, and low detection efficiency.

[0008] The ultra-high frequency partial discharge detection method is a new partial discharge detection technology with the advantages of good anti-interference ability, high sensitivity, discharge point positioning, and high detection efficiency. However, it has some shortcomings, such as difficulty in characterizing the degree of partial discharge, the sensitivity requires exposed insulators to ensure, and the inability to calibrate the discharge amount.

[0009] The ground wave partial discharge detection method is used in ring main box partial discharge detection. It has high sensitivity, strong anti-interference ability, and is suitable for live detection. However, this method has been applied for a short time and has little actual operating experience. It is still difficult to fully explore and utilize ground waves for status assessment and fault diagnosis.

[0010] Pulse current partial discharge detection is commonly used in type testing, factory testing, and other offline tests of electrical equipment. This testing is achieved through a controlled boost measurement system that eliminates partial discharge. However, due to various forms of electromagnetic interference, the actual operating equipment does not have the boost test conditions required for offline testing. Therefore, live or online partial discharge testing based on the pulse current method is rarely used. Summary of the Invention

[0011] In order to solve the above problems, the present invention proposes a non-intrusive distribution network main equipment monitoring device and method based on multi-dimensional data. The monitoring is performed from the outside of the distribution network main equipment without any modification of the monitored object. The operating status is identified based on multi-dimensional data of sound, temperature, and visible light images, and the operating status of the target main equipment and audio-visual images, thermal images, visible light images, and fusion images are sent to an external terminal in real time for on-site inspection personnel to view.

[0012] In order to achieve the above object, the present invention adopts the following technical solutions:

[0013] In a first aspect, the present invention provides a non-intrusive distribution network main equipment monitoring device based on multi-dimensional data, comprising: a multi-dimensional information acquisition module, a first processing module, a second processing module and a communication module;

[0014] The multi-dimensional information acquisition module is used to obtain the ambient temperature, as well as the sound data, temperature and visible light image of the main equipment of the distribution network, and transmit the multi-dimensional information to the first processing module;

[0015] The first processing module is used to sample the sound data, extract the characteristic frequency of the sampled data, determine the partial discharge signal based on the characteristic frequency, and locate the sound source according to the sound arrival time when the partial discharge signal is present; correct the temperature of the main equipment of the distribution network according to the ambient temperature, mark the sound source location where the partial discharge signal exists and the corrected temperature of the main equipment of the distribution network on the visible light image, and construct a fusion image of the acoustic image, thermal image and visible light image;

[0016] The second processing module receives the fusion image and transmits the fusion image to an external terminal through the communication module.

[0017] As an optional implementation, the multi-dimensional information acquisition module includes a microphone array, an infrared detector, a visible light camera device and a temperature sensor; the microphone array is used to collect sound data emitted by the main equipment of the distribution network, the infrared detector is used to collect the temperature of the main equipment of the distribution network, and the temperature sensor is used to collect the ambient temperature; the visible light camera device is used to collect visible light images.

[0018] As an optional implementation, the microphone array includes a plurality of microphones arranged in a spiral manner.

[0019] As an optional embodiment, the first processing module includes a signal conditioning circuit and a signal processor; the microphone array is connected to the signal conditioning circuit, and the signal conditioning circuit is connected to the signal processor; the infrared detector, visible light camera device and temperature sensor are all connected to the signal processor.

[0020] As an optional implementation, the signal conditioning circuit receives sound data, samples the sound data, extracts characteristic frequencies from the sampled data, and transmits the extracted characteristic frequencies and the sampled data to the signal processor.

[0021] As an optional implementation, the signal conditioning circuit includes an analog-to-digital converter and an FPGA, the analog-to-digital converter is used to sample the sound data, and the FPGA is used to perform Fourier transform on the sampled data to extract the characteristic frequency.

[0022] As an optional implementation, the signal processor is used to determine the partial discharge signal based on the characteristic frequency. When the partial discharge signal exists, a generalized cross-correlation delay estimation algorithm is used on the sampled data to estimate the time difference between the sound reaching each microphone, and the sound source position is obtained based on the time difference.

[0023] As an optional implementation, the sound source position includes the sound source direction and distance.

[0024] As an optional embodiment, the monitoring device also includes a human-machine interface and a storage module, and the second processing module is connected to the display module through the human-machine interface; the storage module is connected to the second processing module to store audio-visual images, thermal images, visible light images and fusion images.

[0025] In a second aspect, the present invention provides a non-intrusive distribution network main equipment monitoring method based on multi-dimensional data, comprising:

[0026] Acquire ambient temperature, as well as sound data, temperature, and visible light images of main equipment in the distribution network;

[0027] Sampling the sound data, extracting the characteristic frequency of the sampled data, determining the partial discharge signal based on the characteristic frequency, and locating the sound source based on the arrival time of the sound when a partial discharge signal is present;

[0028] Correct the temperature of the main equipment of the distribution network according to the ambient temperature;

[0029] The sound source locations of partial discharge signals and the corrected temperatures of the main equipment in the distribution network are marked on the visible light image to construct a fusion image of the acoustic image, thermal image, and visible light image, and the fusion image is transmitted to an external terminal.

[0030] Compared with the prior art, the present invention has the following beneficial effects:

[0031] This embodiment proposes a non-intrusive distribution network main equipment monitoring device based on multi-dimensional data. The device monitors the distribution network main equipment from the outside without any modification to the monitored object. The device identifies the operating status based on multi-dimensional data of sound (acoustic imaging technology), temperature (infrared imaging technology), and video (visible light image recognition). The operating status of the target main equipment and audio-visual images, thermal images, visible light images, and fusion images are sent to an external terminal in real time for on-site inspection personnel to view. The device has the functions of saving alarm events and storing images, and can review historical events and images.

[0032] Advantages of additional aspects of the present invention will be given in part in the following description and in part will be obvious from the following description, or will be learned through practice of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] The accompanying drawings, which constitute a part of the present invention, are used to provide a further understanding of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute improper limitations on the present invention.

[0034] Figure 1 Schematic diagram of a non-intrusive distribution network main equipment monitoring device based on multi-dimensional data provided in Example 1 of the present invention;

[0035] Figure 2 Schematic diagram of the microphone array provided in Example 1 of the present invention. DETAILED DESCRIPTION

[0036] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0037] It should be noted that the following detailed descriptions are exemplary and intended to provide further explanation of the present invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by those skilled in the art to which the present invention belongs.

[0038] It should be noted that the terms used herein are only for describing specific embodiments and are not intended to limit exemplary embodiments according to the present invention. As used herein, unless the context clearly indicates otherwise, the singular form is also intended to include the plural form. In addition, it should be understood that the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device comprising a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0039] In the absence of conflict, the embodiments of the present invention and the features thereof may be combined with each other.

[0040] Example 1

[0041] Among the causes of transformer equipment failures and outages, approximately 80% are due to cracking of inter-turn insulation, insulation cracking of bushing leads to ground, and degradation of the bushing's own insulation. In comparison, equipment outages due to non-insulation faults account for less than 20%. Partial discharge (PD) is the most common fault characteristic of electrical equipment in ring main boxes before complete breakdown. PD can be caused by a variety of factors, including: burrs due to process defects; vibration that loosens components or even causes poor contact, leading to electrode potential fluctuations; and aging due to time and environmental factors. Therefore, monitoring the insulation health of electrical equipment and promptly repairing and replacing components with significant insulation cracking can effectively ensure the safe operation of electrical equipment. Furthermore, the operating temperature of electrical equipment is also a crucial factor to monitor. When the resistance of conductors (especially joints) increases, the operating temperature rises, often leading to component burnout and insulation damage. Therefore, monitoring the operating status of primary distribution network equipment primarily focuses on temperature and PD detection.

[0042] like Figure 1 As shown, this embodiment provides a non-intrusive distribution network main equipment monitoring device based on multi-dimensional data, comprising: a multi-dimensional information acquisition module, a first processing module, a second processing module and a communication module connected in sequence;

[0043] The multi-dimensional information acquisition module is used to obtain the ambient temperature, as well as the sound data, temperature and visible light image of the main equipment of the distribution network, and transmit the multi-dimensional information to the first processing module;

[0044] The first processing module is used to sample the sound data, extract the characteristic frequency of the sampled data, determine the partial discharge signal based on the characteristic frequency, and locate the sound source according to the sound arrival time when the partial discharge signal is present; correct the temperature of the main equipment of the distribution network according to the ambient temperature, mark the sound source location where the partial discharge signal exists and the corrected temperature of the main equipment of the distribution network on the visible light image, and construct a fusion image of the acoustic image, thermal image and visible light image;

[0045] The second processing module receives the fusion image and transmits the fusion image to an external terminal through the communication module.

[0046] In this embodiment, the multi-dimensional information acquisition module includes a microphone array MEMS, an infrared detector, a visible light camera device and a temperature sensor;

[0047] Specifically, the microphone array MEMS is used to collect sound data emitted by the main equipment of the power distribution network, and includes a plurality of microphones arranged in a spiral manner.

[0048] As an optional implementation, the microphone array MEMS includes a plurality of microphones arranged in a spiral manner.

[0049] The infrared detector is used to obtain the temperature of the main equipment of the distribution network; the temperature sensor is used to obtain the ambient temperature; the visible light camera device is used to obtain visible light images such as light and smoke; and the ambient temperature, the temperature of the main equipment of the distribution network and the visible light image are all directly transmitted to the second processing module.

[0050] In this embodiment, the first processing module includes a signal conditioning circuit and a signal processor DSP connected;

[0051] Specifically, the microphone array MEMS is connected to the signal conditioning circuit, and the signal conditioning circuit is connected to the signal processor; the infrared detector, visible light camera device and temperature sensor are all directly connected to the signal processor DSP, and the extracted temperature, ambient temperature and visible light image of the main equipment of the distribution network are directly transmitted to the signal processor DSP.

[0052] In this embodiment, the microphone array MEMS transmits the collected sound data to the signal conditioning circuit. After receiving the sound data, the signal conditioning circuit is used to sample the sound data and extract the characteristic frequency of the sampled data. The signal conditioning circuit transmits the extracted characteristic frequency to the signal processor DSP.

[0053] In this embodiment, the signal processor DSP receives characteristic frequencies of sound sampling data, ambient temperature, temperature of main equipment of the power distribution network, and visible light images;

[0054] Specifically, the signal processor DSP is used to identify partial discharge signals based on characteristic frequencies. When a partial discharge signal is present, a generalized cross correlation (GCC) algorithm is used on the sampled data to estimate the time difference between the sound reaching each microphone, and the sound source position is calculated based on the time difference.

[0055] The signal processor DSP is used to correct the temperature of the main equipment of the distribution network according to the ambient temperature and generate a thermal image;

[0056] The signal processor DSP is used to use the visible light image as the base image, mark the location of the local discharge electricity on the visible light image according to the location of the sound source, and generate an acoustic image to make the sound visible; at the same time, the corrected temperature of the main equipment of the distribution network is also marked on the visible light image to achieve the superposition of the acoustic image, thermal image and visible light image to obtain a fused image. The three images can be viewed separately or fused together.

[0057] As an optional implementation, the signal processor DSP can also identify fire and smoke in the visible light image based on image recognition technology, and send the recognition result to the second processing module, which then sends an alarm message to an external terminal.

[0058] In this embodiment, the signal conditioning circuit includes an analog-to-digital converter and an FPGA. The analog-to-digital converter is used to sample sound data, and the FPGA is used to perform Fourier transform on the sampled data to extract characteristic frequencies and identify partial discharge signals.

[0059] As an optional embodiment, the analog-to-digital converter uses a 24-bit Delta-Sigma analog-to-digital converter (ADC), which can sample sounds up to 192kHz.

[0060] As an optional implementation manner, the sound source position includes the sound source direction and distance.

[0061] In this embodiment, the microphone array contains 116 MEMS microphones in total. The array is arranged in a circle with an outer circle radius of 50mm, with 40 points evenly distributed at a spacing of 7.86mm. In the middle is a square matrix of 9*9 with a point spacing of 8.84mm. The four vertices of the square matrix coincide with the four points on the circle, and the center point of the square matrix is ​​removed. Figure 2 shown.

[0062] The microphone array is divided into four groups of 29 microphones each. Each group uses eight 4-channel, 24-bit ADCs for sampling. Each group is triggered by an FPGA for synchronous sampling, ensuring that all eight ADCs sample synchronously and read the ADC conversion results in parallel. The FPGA has excellent timing stability, ensuring the synchronization of sampling and the stability of latency to the greatest extent possible.

[0063] Each FPGA is equipped with a dual-port RAM chip. The FPGA stores the read conversion results and processed feature data in the dual-port RAM chip. The synchronous sampling trigger signals of the four FPGAs are uniformly output by a master MCU chip to ensure four groups of synchronous sampling.

[0064] The DSP reads data from four dual-port RAMs via a parallel bus to identify the location of the sound.

[0065] As an optional implementation method, the infrared detector uses a vanadium oxide uncooled infrared focal plane detector to measure 256*192 temperature points with a resolution of 256*192, a measurement range of -20°C to 400°C, an accuracy of ±2°C, a lens focal length of 4mm, a field of view angle of 42.0°*32.1°, and when the distance from the object to be measured is 3 meters, the effective detection area is 2.3m*2.5m, which fully meets the temperature measurement requirements of the main equipment of the distribution network.

[0066] As an optional implementation, the ambient temperature acquired by the temperature sensor is used to correct the measurement error of the vanadium oxide uncooled infrared focal plane detector to accurately measure the target temperature.

[0067] As an optional implementation, after marking the temperature of the main equipment of the distribution network on the visible light image, it is drawn into an infrared thermal image by color.

[0068] As an optional implementation, the visible light imaging device uses a visible light camera with a resolution of 1920*1080, a lens focal length of 5.75mm, and a field of view angle of 69.0°.

[0069] In this embodiment, the second processing module uses a high-speed ARM chip to complete functions such as communication, human-computer interaction, and data storage, and is responsible for the scheduling of the entire device.

[0070] In this embodiment, the monitoring device further includes a human-machine interface, and the second processing module is connected to the display module via the human-machine interface. The display module uses an LCD touch screen to complete operations such as parameter setting, image viewing, and event viewing.

[0071] As an optional implementation, the display module uses a color LCD screen, which can display audio-visual images, thermal images, visible light images, fusion images, etc.

[0072] In this embodiment, the monitoring device further includes a storage module, which is connected to the second processing module. The storage module includes a flash memory FLASH for storing monitoring data, alarm information, device parameters, matters, etc., which will not be lost in the event of power failure.

[0073] In this embodiment, the communication interface includes RS485, RJ45 and other network ports, and the operating status of the main equipment of the distribution network and audio-visual images, thermal images, visible light images and fusion images are sent to the external terminal in real time through the communication interface.

[0074] In this embodiment, the monitoring device further includes a power supply module, which is used to provide power supply, specifically providing AC220V AC input and outputting multiple voltage groups such as 12VDC, 5VDC, 3.3VDC, and 1.2VDC.

[0075] As an optional implementation, the power module uses a supercapacitor, which can support the device to run for 5 minutes in the event of an AC power outage, ensuring data transmission.

[0076] In this embodiment, the audio-visual images, thermal images, visible light fusion images, etc. processed by the signal processor DSP are sent to the second processing module to reduce the pressure on the signal processor DSP, and are sent by the second processing module to the storage module for storage, or sent to the external terminal through the communication module, or sent to the display module through the human-computer interface, etc.

[0077] In further embodiments, the monitoring device can also be used as a portable monitoring device. Unlike the aforementioned device, the power module is powered by a lithium battery, outputting multiple voltages such as 5VDC, 3.3VDC, and 1.2VDC. The lithium battery has charging and protection circuitry, a USB port for external charging, and USB output. Furthermore, the portable monitoring device supports 5G or 4G communications, enabling real-time transmission of operating status data and images.

[0078] This embodiment proposes a non-intrusive distribution network main equipment monitoring device based on multi-dimensional data. It monitors from the outside of the distribution network main equipment without any modification to the monitored object. It identifies the operating status based on multi-dimensional data of sound (acoustic imaging technology), temperature (infrared imaging technology), and video (visible light image recognition), and sends the operating status and image of the target equipment to the background in real time, which is convenient for on-site inspection personnel to view. The device has alarm event preservation and image storage functions, and can review historical events and images.

[0079] Example 2

[0080] This embodiment provides a non-intrusive distribution network main equipment monitoring method based on multi-dimensional data, including:

[0081] Acquire ambient temperature, as well as sound data, temperature, and visible light images of main equipment in the distribution network;

[0082] Sampling the sound data, extracting the characteristic frequency of the sampled data, determining the partial discharge signal based on the characteristic frequency, and locating the sound source based on the arrival time of the sound when a partial discharge signal is present;

[0083] Correct the temperature of the main equipment of the distribution network according to the ambient temperature;

[0084] The sound source locations of partial discharge signals and the corrected temperatures of the main equipment in the distribution network are marked on the visible light image to construct a fusion image of the acoustic image, thermal image, and visible light image, and the fusion image is transmitted to an external terminal.

[0085] Although the above describes the specific embodiments of the present invention in conjunction with the accompanying drawings, it is not intended to limit the scope of protection of the present invention. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art on the basis of the technical solution of the present invention without any creative work are still within the scope of protection of the present invention.

Claims

1. A non-intrusive distribution network main equipment monitoring device based on multi-dimensional data, characterized in that: include: Multi-dimensional information acquisition module, first processing module, second processing module and communication module; The multi-dimensional information acquisition module is used to obtain the ambient temperature, as well as the sound data, temperature and visible light image of the main equipment of the distribution network, and transmit the multi-dimensional information to the first processing module; The first processing module is used to sample the sound data, extract the characteristic frequency of the sampled data, determine the partial discharge signal based on the characteristic frequency, and locate the sound source according to the sound arrival time when the partial discharge signal is present; correct the temperature of the main equipment of the distribution network according to the ambient temperature, mark the sound source location where the partial discharge signal exists and the corrected temperature of the main equipment of the distribution network on the visible light image, and construct a fusion image of the acoustic image, thermal image and visible light image; The second processing module receives the fusion image and transmits the fusion image to an external terminal through the communication module; The multi-dimensional information acquisition module includes a microphone array, an infrared detector, a visible light camera and a temperature sensor; the microphone array is used to collect sound data emitted by the main equipment of the distribution network, the infrared detector is used to collect the temperature of the main equipment of the distribution network, and the temperature sensor is used to collect the ambient temperature; the visible light camera is used to collect visible light images; The microphone array includes several microphones arranged in a spiral pattern. A total of 116 MEMS microphones are placed in the microphone array. The array is arranged in the form of an outer circle and an inner square. The outer circle has a radius of 50mm and is evenly distributed with 40 points at a spacing of 7.86mm. In the middle is a square matrix of 9*9 with a point spacing of 8.84mm. The four vertices of the square matrix coincide with the four points on the circle, and the center point of the square matrix is ​​removed. The first processing module includes a signal conditioning circuit and a signal processor; the microphone array is connected to the signal conditioning circuit, and the signal conditioning circuit is connected to the signal processor; the infrared detector, the visible light camera device and the temperature sensor are all connected to the signal processor.

2. The non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to claim 1, characterized in that: The signal conditioning circuit receives sound data, is used for sampling the sound data, extracting characteristic frequencies from the sampled data, and transmitting the extracted characteristic frequencies and the sampled data to the signal processor.

3. The non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to claim 2, characterized in that: The signal conditioning circuit includes an analog-to-digital converter and an FPGA. The analog-to-digital converter is used to sample sound data, and the FPGA is used to perform Fourier transform on the sampled data to extract characteristic frequencies.

4. The non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to claim 1, characterized in that: The signal processor is used to determine the partial discharge signal according to the characteristic frequency. When the partial discharge signal exists, the generalized cross-correlation delay estimation algorithm is used on the sampled data to estimate the time difference of the sound reaching each microphone, and the sound source position is obtained according to the time difference.

5. The non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to claim 4, characterized in that: The sound source position includes the sound source direction and distance.

6. The non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to claim 1, characterized in that: The monitoring device also includes a human-machine interface and a storage module. The second processing module is connected to the display module via the human-machine interface. The storage module is connected to the second processing module to store the acoustic image, thermal image, visible light image and fusion image.

7. A non-intrusive distribution network main equipment monitoring method based on multi-dimensional data, using the non-intrusive distribution network main equipment monitoring device based on multi-dimensional data according to any one of claims 1 to 6, characterized in that: include: Acquire ambient temperature, as well as sound data, temperature, and visible light images of main equipment in the distribution network; Sampling the sound data, extracting the characteristic frequency of the sampled data, determining the partial discharge signal based on the characteristic frequency, and locating the sound source based on the arrival time of the sound when a partial discharge signal is present; Correct the temperature of the main equipment of the distribution network according to the ambient temperature; The sound source locations of partial discharge signals and the corrected temperatures of the main equipment in the distribution network are marked on the visible light image to construct a fusion image of the acoustic image, thermal image, and visible light image, and the fusion image is transmitted to an external terminal.

8. The non-intrusive distribution network main equipment monitoring method based on multi-dimensional data according to claim 7, characterized in that: The signal conditioning circuit receives sound data, is used for sampling the sound data, extracting characteristic frequencies from the sampled data, and transmitting the extracted characteristic frequencies and the sampled data to the signal processor.

9. The non-intrusive distribution network main equipment monitoring method based on multi-dimensional data according to claim 7, characterized in that: The signal conditioning circuit includes an analog-to-digital converter and an FPGA. The analog-to-digital converter is used to sample sound data, and the FPGA is used to perform Fourier transform on the sampled data to extract characteristic frequencies.

10. The non-intrusive distribution network main equipment monitoring method based on multi-dimensional data according to claim 7, characterized in that: The signal processor is used to determine the partial discharge signal according to the characteristic frequency. When the partial discharge signal exists, the generalized cross-correlation delay estimation algorithm is used on the sampled data to estimate the time difference of the sound reaching each microphone, and the sound source position is obtained according to the time difference.

Images