Method, device and equipment for determining fault in switch cabinet of transformer substation and medium

Abstract

The invention discloses a method, a device and equipment for determining a fault in a transformer substation switch cabinet and a medium, relates to the technical field of transformer substation monitoring, and can improve the determination efficiency and accuracy of the fault in the transformer substation switch cabinet. The scheme comprises the following steps: acquiring first time when a first sensor receives a first electromagnetic wave signal and second time when the first sensor receives a first ultrasonic signal; third time when the second sensor receives the second electromagnetic wave signal and fourth time when the second sensor receives the second ultrasonic wave signal are obtained, the first sensor and the second sensor are acoustic-electric combined partial discharge sensors, and the acoustic-electric combined partial discharge sensors are both arranged in the switch cabinet; the acquisition module is used for acquiring electromagnetic wave signals and ultrasonic wave signals of faults in the switch cabinet; determining a fault position according to the first time, the second time, the third time, the fourth time, the first position of the first sensor and the second position of the second sensor; and determining the fault component according to the fault position and the layout information of the internal components of the switch cabinet.

Description

Technical Field

[0001] The present application relates to the technical field of substation monitoring, and in particular to a method, device, equipment and medium for determining faults in a substation switch cabinet. Background Art

[0002] Currently, during the operation and maintenance of substations, the failure rate of high-voltage switchgear remains high. According to statistics, high-voltage switchgear is one of the equipment in substations that is more prone to failure, and the failure rate of high-voltage switchgear accounts for 30%-50% of the overall failure rate of substation equipment.

[0003] Currently, substation equipment status management and status monitoring operations rely heavily on manual labor. With a severely insufficient manpower-to-station ratio, overdue work and missed inspections are inevitable. When monitoring high-voltage switchgear, abnormalities in monitoring data, such as partial discharge data, are detected, making it difficult to accurately identify the switchgear fault and assist maintenance personnel in performing repairs. Summary of the Invention

[0004] The present application provides a method, apparatus, equipment and medium for determining faults in a substation switch cabinet, which can improve the efficiency and accuracy of determining faults in a substation switch cabinet.

[0005] In order to achieve the above objectives, this application adopts the following technical solutions: In a first aspect of an embodiment of the present application, a method for determining a fault in a substation switch cabinet is provided, the method comprising: Acquire a first time when the first sensor receives the first electromagnetic wave signal and a second time when the first sensor receives the first ultrasonic wave signal; Obtaining a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after the second sensor receives the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, and the combined acoustic and electrical partial discharge sensors are both deployed in the switch cabinet and are used to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet; determining a fault location according to the first time, the second time, the third time, the fourth time, a first position of the first sensor, and a second position of the second sensor; The faulty component is determined according to the fault location and the layout information of the components in the switch cabinet.

[0006] As a possible implementation manner, after determining the faulty component, the method further includes: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

[0007] As a possible implementation manner, determining the fault location according to the first time, the second time, the third time, and the fourth time includes: Obtain a time difference between the first time and the second time to obtain a first time difference; Obtain a time difference between the third time and the fourth time to obtain a second time difference; determining a first distance between the fault and the first sensor according to the first time difference; determining a second distance between the fault and the second sensor according to the second time difference; The fault location is determined according to the first distance, the second distance, the first position, and the second position.

[0008] As a possible implementation manner, determining the fault location according to the first distance, the second distance, the first position, and the second position includes: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The fault location is determined according to the intersection of the first circular curve and the second circular curve.

[0009] As a possible implementation manner, determining the first distance between the fault and the first sensor according to the first time difference includes: The first distance is determined according to the first time difference, a preset first transmission speed of the electromagnetic wave signal, and a preset second transmission speed of the ultrasonic wave signal.

[0010] As a possible implementation manner, after obtaining the fault type of the faulty component, the method further includes: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

[0011] As a possible implementation manner, determining the fault level of the faulty component according to the faulty component, the fault type corresponding to the faulty component, and the partial discharge data corresponding to the faulty component includes: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

[0012] In a second aspect of an embodiment of the present application, a device for determining a fault in a substation switch cabinet is provided, the device comprising: A first acquisition module is used to acquire a first time when the first sensor receives the first electromagnetic wave signal and a second time when the first sensor receives the first ultrasonic signal; a second acquisition module, configured to acquire a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after the second sensor receives the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, both of which are deployed in the switch cabinet and are configured to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet; a first determining module, configured to determine a fault location according to the first time, the second time, the third time, the fourth time, a first position of the first sensor, and a second position of the second sensor; The second determining module is configured to determine the faulty component according to the fault location and the layout information of the components in the switch cabinet.

[0013] As a possible implementation manner, the apparatus further includes a processing module, wherein the processing module is configured to: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

[0014] As a possible implementation manner, the first determining module is specifically configured to: Obtain a time difference between the first time and the second time to obtain a first time difference; Obtain a time difference between the third time and the fourth time to obtain a second time difference; determining a first distance between the fault and the first sensor according to the first time difference; determining a second distance between the fault and the second sensor according to the second time difference; The fault location is determined according to the first distance, the second distance, the first position, and the second position.

[0015] As a possible implementation manner, the first determining module is specifically configured to: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The fault location is determined according to the intersection of the first circular curve and the second circular curve.

[0016] As a possible implementation manner, the first determining module is specifically configured to: The first distance is determined according to the first time difference, a preset first transmission speed of the electromagnetic wave signal, and a preset second transmission speed of the ultrasonic wave signal.

[0017] As a possible implementation manner, the processing module is further configured to: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

[0018] As a possible implementation manner, the processing module is specifically configured to: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

[0019] According to a third aspect of an embodiment of the present application, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for determining a fault in a substation switch cabinet according to the first aspect of the embodiment of the present application is implemented.

[0020] In a fourth aspect of an embodiment of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method for determining a fault in a substation switch cabinet described in the first aspect of the embodiment of the present application is implemented.

[0021] The beneficial effects of the technical solutions provided in the embodiments of the present application include at least: The embodiment of the present application provides a method for determining a fault in a substation switch cabinet, which obtains a first time when a first sensor receives a first electromagnetic wave signal and a second time when a first ultrasonic signal is received; obtains a third time when a second sensor receives a second electromagnetic wave signal and a fourth time after receiving a second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electric partial discharge sensors, and the combined acoustic and electric partial discharge sensors are both deployed in the switch cabinet, and are used to collect electromagnetic wave signals and ultrasonic signals for the fault in the switch cabinet; determines the fault location according to the first time, the second time, the third time, the fourth time, the first position of the first sensor and the second position of the second sensor; determines the fault component according to the fault location and the layout information of the components in the switch cabinet, so as to assist operation and maintenance personnel in quickly judging the specific fault of the switch cabinet, thereby improving the efficiency of fault investigation and reducing the troubleshooting pressure of operation and maintenance personnel on the switch cabinet. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 A schematic diagram of a substation monitoring system provided in an embodiment of the present application; Figure 2 The process of the method for determining the fault in the substation switch cabinet provided in the embodiment of the present application Figure 1 ; Figure 3 The process of the method for determining the fault in the substation switch cabinet provided in the embodiment of the present application Figure 2 ; Figure 4 A structural diagram of a device for determining faults in a substation switch cabinet provided in an embodiment of the present application; Figure 5 A schematic diagram of the internal structure of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0024] In the following, the terms "first" and "second" are used for descriptive purposes only and should not be understood to indicate or imply relative importance or implicitly specify the number of the technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present disclosure, unless otherwise specified, "plurality" means two or more.

[0025] Additionally, the use of “based on” or “according to” is intended to be open and inclusive, in that a process, step, calculation, or other action “based on” or “according to” one or more conditions or values may, in practice, be based on additional conditions or beyond values.

[0026] In order to monitor substations, this application sets up the cloud, edge, and end sides in a cloud-edge collaborative manner. Among them, the cloud-edge collaborative computing platform is an intelligent computing architecture developed to meet the new challenges brought about by the development of the Internet of Things (IoT). To manage digital cloud computing, the platform can sink computing power from the centralized cloud to the edge nodes close to the data source, and optimize data processing capabilities through a distributed computing model. The cloud-edge collaborative computing model not only extends the capabilities of cloud native, but also enables data processing, business applications, and artificial intelligence (AI) models to be executed at the edge close to the data source by deploying edge nodes, solving the problems encountered by the Internet of Things when it is implemented, such as real-time response, data privacy, and convenient maintenance.

[0027] The cloud-edge collaborative computing platform has significantly improved data processing efficiency and system response speed in practical applications across multiple industries, enabling diverse intelligent applications and facilitating digital transformation across various sectors. The cloud can be used for advanced analysis and global optimization.

[0028] The cloud, edge, and device together constitute a substation monitoring system. According to one embodiment of the present invention, Figure 1 FIG. 1 shows a schematic diagram of a substation monitoring system according to an exemplary embodiment of the present invention. Figure 1 As shown in the figure, the substation monitoring system adopts a three-layer architecture of cloud side, edge side, and device side.

[0029] The cloud side includes the distribution network cloud master station or cloud server, the edge side includes digital node equipment or electronic equipment, and the terminal side may include dual ultrasonic partial discharge sensors and combined acoustic and electrical partial discharge sensors for monitoring substations.

[0030] The side of the substation monitoring system includes digital node devices. The computing device in the present invention can be specifically implemented as a digital node device, and the method for locating partial discharge in the substation switch cabinet of the present invention can be specifically executed by the digital node device deployed in the substation room. The digital node device is connected to the distribution network cloud master station in the north and is connected to one or more end-side devices in the south, such as one or more dual ultrasonic partial discharge sensors. The digital node device can be deployed in a 10KV switch room. The present invention does not limit the specific deployment method and deployment location of the digital node device.

[0031] Digital node devices can be deployed in two ways: fixed and portable. Fixed digital node devices can be deployed in a cabinet in the switch room and powered by a fixed power supply. They are suitable for long-term substation monitoring. Portable digital node devices are removable and reusable. They are suitable for short-term substation monitoring and can be powered by a mobile power supply.

[0032] According to one embodiment of the present invention, the present invention can be divided into power-guarantee substations and non-power-guarantee substations according to the different operation and maintenance levels of the substations. The operation and maintenance level of the power-guarantee substation is higher than that of the non-power-guarantee substation. The present invention can set substations with high load importance, which need to be focused on, or substations that undertake some active guarantee tasks as power-guarantee substations, and the remaining substations as non-power-guarantee substations. The present invention can deploy fixed digital node equipment in power-guarantee substations and deploy portable digital node equipment in non-power-guarantee substations.

[0033] Digital node devices collect partial discharge sensor data using the Internet of Things (IoT) protocol for power transmission and transformation equipment and synchronize sensor time using the DRX scheduler. Partial discharge sensor data can also include data collected by dual ultrasonic partial discharge sensors, which collect partial discharge data both inside and outside the switchgear.

[0034] The present invention does not limit the number of dual ultrasonic partial discharge sensors that can be connected to the digital node device, for example, it can be no less than 36. The digital node device supports data acquisition from various types of wired and wireless sensors such as IEC61850, MQTT, Modbμs, wireless networking protocol for IoT node devices of power transmission and transformation equipment, and micro-power wireless network communication protocol for IoT of power transmission and transformation equipment; supports Ethernet port, RS-485 / RS-232, wireless 4G+APN, LoRa wireless hardware communication, and supports wireless access capabilities such as 4G and 5G, as well as wired access capabilities such as optical fiber and Ethernet. The digital node device can access the distribution network cloud master station through the IEC104 protocol. The present invention does not limit the specific connection method between the digital node device and the distribution network cloud master station and the dual ultrasonic partial discharge sensor.

[0035] Back to Figure 1 ,like Figure 1 As shown, the cloud side includes a distribution network cloud master station. The distribution network cloud master station can be implemented as one or more computing devices. The present invention does not limit the specific component configuration of the distribution network cloud master station. The distribution network cloud master station can be deployed within or outside the substation and communicate with digital node devices deployed in the substation building. The distribution network cloud master station can display data collected by dual ultrasonic partial discharge sensors and combined acoustic and electrical partial discharge sensors within the switchroom, as well as generate partial discharge alarms within the switchgear and external interference signal alarms.

[0036] Traditional switchgear faces challenges such as long partial discharge (PD) detection cycles, heavy workloads, and high rates of false alarms during equipment status detection. Currently, grassroots personnel lack effective tools to promptly and accurately detect equipment status anomalies. This invention deploys dual ultrasonic partial discharge (PD) sensors in substation switchgear and develops a technology for identifying the presence of partial discharges inside and outside the switchgear. This technology effectively addresses the false alarm issues associated with traditional switchgear PD monitoring, helping operations and maintenance personnel quickly and accurately identify PD faults within the switchgear, significantly improving the ability to accurately locate PDs. The invention also incorporates a combined acoustic-electrical partial discharge (AD) sensor to collect both PD data (AE) and ultra-high frequency (UHF) data. An algorithm for locating faults within the switchgear based on time difference of arrival (TDOA) has been developed. This data is fused and integrated, effectively combining information from both signals to improve the accuracy of locating the source of discharge within the switchgear.

[0037] The embodiment of the present application provides a method for determining a fault in a transformer substation switch cabinet, such as Figure 2 As shown, the method includes the following steps: Step 201: Obtain a first time when a first sensor receives a first electromagnetic wave signal and a second time when a first sensor receives a first ultrasonic wave signal.

[0038] Step 202: Obtain a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after receiving the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, and the combined acoustic and electrical partial discharge sensors are both deployed in the switch cabinet to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet.

[0039] A substation includes multiple switchgear cabinets, which can be high-voltage switchgear cabinets. This application does not limit the specific type of switchgear cabinet. The present application provides a method for determining faults within a substation switchgear cabinet. To determine a fault within a switchgear cabinet, at least two combined acoustic and electrical partial discharge sensors can be deployed within the switchgear cabinet to collect electromagnetic and ultrasonic signals from the switchgear cabinet.

[0040] Specifically, the combined acoustic-electric partial discharge sensor can detect partial discharge data and ultra-high frequency data within the switchgear. Before partial discharge, the electric field stress, dielectric stress, and particle force around the discharge point are in a state of relative equilibrium. Partial discharge is a rapid charge release or migration process, which causes the electric field stress, mechanical stress, and particle force around the discharge point to lose equilibrium and produce an oscillatory change process. The rapid oscillation of mechanical stress and particle force causes the dielectric around the discharge point to vibrate, thereby generating an acoustic wave signal. The acoustic-electric combined partial discharge sensor can collect the acoustic wave signal as partial discharge data to achieve measurement purposes. Ultrasonic signals use air as the propagation medium, so the propagation speed of ultrasonic signals can be preset to 340m / s during calculations.

[0041] The insulation of power equipment has high dielectric strength and a high breakdown field strength. When partial discharge occurs in the insulation of power equipment, the breakdown process is extremely rapid, generating a pulse current with a rise time of less than 1ns. This also generates ultra-high frequency (UHF) electromagnetic waves with frequencies reaching up to GHz. Using a combined acoustic and electrical partial discharge sensor, the UHF electromagnetic wave signals generated by partial discharge in power equipment can be captured and collected as UHF data. For calculation purposes, the propagation speed of the UHF electromagnetic wave signal can be treated as the speed of light.

[0042] The parameters of the combined acoustic and electrical partial discharge sensor include: ultrasonic monitoring range 20-60kHz, sensitivity 0dBμV; transient ground monitoring range 3-100MHz, ultra-high frequency monitoring range 500-1500MHz, sensitivity -60dBm; wireless communication RF transmission power 15-17dBm; receiving sensitivity -109dBm.

[0043] It is understandable that the present invention can also group and schedule sensors corresponding to different switch cabinets according to the different switch cabinets monitored by the sensors. For example, the first acoustic-electric combined partial discharge sensor and the second acoustic-electric combined partial discharge sensor monitor the first switch cabinet, and the third acoustic-electric combined partial discharge sensor and the fourth acoustic-electric combined partial discharge sensor monitor the second switch cabinet. The digital node device can then group and schedule these sensors. The digital node device uses the first acoustic-electric combined partial discharge sensor and the second acoustic-electric combined partial discharge sensor as the first group of sensors and sets the corresponding start time and frequency for data collection; and uses the third acoustic-electric combined partial discharge sensor and the fourth acoustic-electric combined partial discharge sensor as the second group of sensors and sets the corresponding start time and frequency for data collection.

[0044] It should be noted that the combined acoustic and electrical partial discharge sensor can determine whether there is an abnormality in the switch cabinet based on the collected data. If so, the combined acoustic and electrical partial discharge sensor can transmit the information of the received electromagnetic wave signal and ultrasonic signal to the electronic equipment.

[0045] Specifically, when determining whether a switchgear has abnormal PD based on PD data, a switchgear PD reading of 8dBμV or higher and 20dBμV or lower indicates a concern level; a switchgear PD reading of 20dBμV or higher and 30dBμV or lower indicates a critical level; and a switchgear PD reading of 30dBμV or higher indicates a maintenance-required level. When digital node equipment detects switchgear PD data reaching these ranges, it generates general, critical, and crisis alerts, respectively, to alert operations and maintenance personnel. Therefore, a switchgear PD reading of 8dBμV or higher indicates an abnormal PD level.

[0046] Step 203: Determine a fault location based on the first time, the second time, the third time, the fourth time, the first position of the first sensor, and the second position of the second sensor; Step 204: Determine the faulty component based on the fault location and the layout information of the components in the switch cabinet.

[0047] Furthermore, since the switchgear deployment environment includes not only the switchgear itself but also other electrical appliances, such as lights and cameras, abnormalities in these external components, such as light flickering, can also generate partial discharges (PDs). These PD signals are also detected by the PD sensors monitoring the switchgear. Therefore, if the switchgear PD data collected by the dual ultrasonic PD sensors show abnormalities, it could be due to either abnormal PD in the switchgear itself or PD signals from disturbances in the environment.

[0048] According to one embodiment of the present invention, multiple dual ultrasonic partial discharge sensors and combined acoustic-electric partial discharge sensors are deployed in the substation. Each sensor may have an independent start time and frequency for data collection. Therefore, the data collected by these sensors may not be collected simultaneously. For example, the partial discharge data of the first switch cabinet is collected at a first time, and the partial discharge data of the second switch cabinet is collected at a second time. If the partial discharge data of the second switch cabinet is abnormal at the second time, it is impossible to compare the data at different times to determine whether the partial discharge abnormality is caused by interference such as external background noise, nor is it possible to calculate and locate the location of the partial discharge within the switch cabinet based on the data at different times.

[0049] To this end, the present invention employs a computing device (i.e., a digital node device) to generate a time synchronization instruction. This time synchronization instruction is used to cause all probes of multiple dual ultrasonic partial discharge sensors and combined acoustic-electric partial discharge sensors to begin collecting data at the same acquisition time specified by the next synchronized acquisition time, and to collect data at the same acquisition frequency specified by the synchronized acquisition frequency. The time synchronization instruction may specifically include the next synchronized acquisition time and the synchronized acquisition frequency. The digital node device then generates a DRX configuration instruction based on the time synchronization instruction and sends the DRX configuration instruction to each sensor.

[0050] The DRX configuration instruction includes the DRX cycle duration, i.e., how long a DRX cycle lasts, and the synchronization frame sequence number, which specifies the DRX cycle in which synchronization data collection begins. The DRX cycle duration is determined by the synchronization acquisition frequency, and the synchronization frame sequence number is determined by the next synchronization acquisition time. According to one embodiment of the present invention, the synchronization acquisition frequency and the corresponding DRX cycle duration can be set to 20μs, so that the synchronization acquisition accuracy of the sensor meets the computational requirements for identifying partial discharges inside and outside the cabinet, locating interference sources outside the cabinet, and locating partial discharges inside the cabinet, ensuring data synchronization between the various sensors and achieving a synchronization acquisition accuracy of less than ±20μs for the collected high-precision partial discharge data.

[0051] In addition, the dual ultrasonic partial discharge sensor includes an inner ultrasonic partial discharge probe and an outer ultrasonic partial discharge probe. The inner ultrasonic partial discharge probe is suitable for collecting the in-cabinet partial discharge data on the inside of the switch cabinet, and the outer ultrasonic partial discharge probe is suitable for collecting the out-cabinet partial discharge data on the outside of the switch cabinet. The present invention provides a method for locating in-cabinet partial discharge based on the arranged out-cabinet partial discharge probe and the inner ultrasonic partial discharge probe: by comparing the in-cabinet partial discharge data with the out-cabinet partial discharge data, it can be determined whether the partial discharge anomaly is caused by external interference outside the cabinet or due to an abnormality inside the switch cabinet. For example, if the out-cabinet partial discharge data is small or absent, it may be that an abnormality has occurred inside the switch cabinet. If the waveforms of the out-cabinet partial discharge data and the in-cabinet partial discharge data are similar, it may be that the in-cabinet partial discharge data anomaly is caused by interference outside the cabinet. Moreover, when comparing the in-cabinet partial discharge data with the out-cabinet partial discharge data, the simultaneity of the partial discharge data is ensured by high-precision synchronous acquisition technology; thereby realizing environmental interference identification and in-cabinet partial discharge positioning based on the in-cabinet ultrasonic partial discharge probes.

[0052] According to one embodiment of the present invention, the present invention can identify partial discharges inside and outside the cabinet according to the following steps to determine whether the abnormal partial discharge data is caused by external interference or an abnormality inside the switch cabinet. In response to receiving the partial discharge data sent by the dual ultrasonic partial discharge sensor, if the partial discharge abnormality of the switch cabinet is determined based on the partial discharge data, the first partial discharge data similarity is determined based on the partial discharge data inside the target cabinet and the partial discharge data outside the target cabinet collected by the dual ultrasonic partial discharge sensor in the target switch cabinet with the abnormal partial discharge; the second partial discharge data similarity is determined based on the partial discharge data outside the target cabinet collected by the dual ultrasonic partial discharge sensor in the target switch cabinet with the abnormal partial discharge and the partial discharge data outside the cabinet collected from other switch cabinets; if the first partial discharge data similarity and / or the second partial discharge data similarity are greater than the similarity threshold, it is determined that the partial discharge abnormality of the switch cabinet is caused by external interference. If the first partial discharge data similarity and the second partial discharge data similarity are both less than the similarity threshold, it is determined that the partial discharge abnormality of the switch cabinet is caused by an abnormality inside the switch cabinet.

[0053] Determining the first partial discharge data similarity includes: determining an in-cabinet feature vector based on an in-cabinet partial discharge spectrum of the target in-cabinet partial discharge data; determining an out-cabinet feature vector based on an out-cabinet partial discharge spectrum of the target out-cabinet partial discharge data; and calculating the first partial discharge data similarity based on the in-cabinet feature vector and the out-cabinet feature vector. Determining the feature vector based on the partial discharge spectrum includes: generating a feature vector based on one or more of a peak frequency, a valley frequency, a periodicity, and a slope of the partial discharge spectrum; and inputting the in-cabinet partial discharge spectrum of the target in-cabinet partial discharge data and the out-cabinet partial discharge spectrum of the target out-cabinet partial discharge data into an image similarity calculation model, and determining the first partial discharge data similarity based on an output of the image similarity calculation model.

[0054] According to one embodiment of the present invention, partial discharge data includes unstructured data, such as partial discharge pulse signals, and a partial discharge spectrum of the switchgear partial discharge data can be drawn based on the partial discharge pulse signals. Partial discharge spectrums of the switchgear partial discharge data include partial discharge phase distribution (PRPD) and partial discharge pulse signal (PRPS). The present invention does not limit the specific type of partial discharge spectrum drawn from the switchgear partial discharge data. Partial discharge spectrums include external partial discharge spectrum and internal partial discharge spectrum.

[0055] If the switchgear PD data abnormality is determined to be caused by an internal abnormality, the switchgear internal PD location is performed. When an internal PD abnormality occurs in the switchgear, ultrasonic and electromagnetic waves are emitted at the location where the PD fault occurs.

[0056] like Figure 3 As shown, the process of determining the fault location according to the first time, the second time, the third time, and the fourth time in step 204 may include: Step 301: Obtain a time difference between the first time and the second time to obtain a first time difference; Step 302: Obtain a time difference between the third time and the fourth time to obtain a second time difference; Step 303: Determine a first distance between the fault and the first sensor according to the first time difference; Step 304: Determine a second distance between the fault and the second sensor according to the second time difference; Step 305: Determine the fault location according to the first distance, the second distance, the first position, and the second position.

[0057] For the discharge signal of the same component, electromagnetic waves travel faster, at the speed of light, while ultrasonic waves travel slower, calculated as 340 m / s, the speed of sound in air. Therefore, there is a time difference, t, between the electromagnetic and ultrasonic waves reaching the sensor.

[0058] The present invention deploys multiple combined acoustic and electrical partial discharge (PD) sensors inside the switchgear to collect ultrasonic and electromagnetic signals. When a PD occurs at the fault location, both ultrasonic and electromagnetic signals are generated and emitted simultaneously. Because ultrasonic and electromagnetic signals travel at different speeds in the medium, there is a time lag between the reception of the ultrasonic and electromagnetic signals by the combined acoustic and electrical PD sensors.

[0059] Each combined acoustic and electrical partial discharge sensor can determine the time difference between the two signals arriving at the sensor based on the difference in arrival time of the two signals. Electromagnetic wave signals are transmitted faster, so the sensor will receive the electromagnetic wave signal first and then the ultrasonic signal. Optionally, the process of determining the fault location according to the first distance, the second distance, the first position, and the second position in step 305 may include: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The position of the intersection of the first circular curve and the second circular curve is determined as the fault position.

[0060] When determining the first distance and the second distance, the first time arrival difference is first determined based on the first time when the first acoustic-electric combined partial discharge sensor receives the electromagnetic wave signal and the second time when it receives the ultrasonic signal, and the second time arrival difference is determined based on the third time when the second acoustic-electric combined partial discharge sensor receives the electromagnetic wave signal and the fourth time when it receives the ultrasonic signal.

[0061] The present invention does not limit the number and location of sensors that collect signals emitted by the fault location. A first time difference of arrival is determined based on a first time when the first acoustic-electric combined partial discharge sensor receives the electromagnetic wave signal and a second time when it receives the ultrasonic signal, such as by subtracting the second time from the first time to obtain the first time difference of arrival. A second time difference of arrival is determined based on a third time when the second acoustic-electric combined partial discharge sensor receives the electromagnetic wave signal and a fourth time when it receives the ultrasonic signal, such as by subtracting the fourth time from the third time to obtain the second time difference of arrival.

[0062] According to one embodiment of the present invention, the time y at which the fault location simultaneously emits an electromagnetic wave signal and an ultrasonic signal cannot be determined. The first time the combined acoustic-electric partial discharge sensor receives the electromagnetic wave signal is t1, and the second time it receives the ultrasonic signal is t2. The time difference between the first and second arrival times is t2 - t1 = Δt.

[0063] The transmission speed of electromagnetic wave signals is v1, and the transmission speed of ultrasonic signals is v2. If the distance between the fault location and the combined acoustic and electrical partial discharge sensor is x, then x / v1 = t1 and x / v2 = t2.

[0064] x / v2-x / v1=t2-t1=Δt A first distance between the fault location and the first combined acoustic-electric partial discharge sensor is determined based on the first time difference of arrival. A second distance between the fault location and the second combined acoustic-electric partial discharge sensor is determined based on the second time difference of arrival. The first distance is determined based on the first time difference of arrival, the transmission speed of the electromagnetic wave signal, and the transmission speed of the ultrasonic signal. The second distance is determined based on the second time difference of arrival, the transmission speed of the electromagnetic wave signal, and the transmission speed of the ultrasonic signal.

[0065] According to one embodiment of the present invention, the distance between the fault location and the acoustic-electric combined partial discharge sensor is .

[0066] According to one embodiment of the present invention, the transmission speed v1 of the electromagnetic wave signal can be taken as the speed of light, and the transmission speed v2 of the ultrasonic signal can be taken as the speed of sound in air, which is 340 m / s. Since the transmission speed of the electromagnetic wave signal is much greater than the transmission speed of the ultrasonic signal, it can be used in the specific calculation process. To simplify, x=Δt ≈x=Δt v2. Therefore, the first distance can be determined based on the product of the ultrasonic transmission speed and the first arrival time difference; the second distance can be determined based on the product of the ultrasonic transmission speed and the second arrival time difference. That is, the first time is used as the reference time, and the second time when the acoustic-electric combined partial discharge sensor receives the ultrasonic signal is used as the acoustic wave transmission time of the discharge source signal to determine the distance between the fault location and the acoustic-electric combined partial discharge sensor.

[0067] Subsequently, fault location information of the fault location is determined based on the first distance, the second distance, and the positions of the first and second acoustic-electric combined partial discharge sensors. This includes: generating a first circular curve with the position of the first acoustic-electric combined partial discharge sensor as the center and the first distance as the radius; generating a second circular curve with the position of the second acoustic-electric combined partial discharge sensor as the center and the second distance as the radius; and determining the fault location information of the fault location based on the intersection of the first circular curve and the second circular curve. The projection point of the fault location in the switch cabinet is determined based on the first distance, the second distance, the distance between the first acoustic-electric combined partial discharge sensor and the projection point, and the distance between the second acoustic-electric combined partial discharge sensor and the projection point.

[0068] For example, a switchgear cabinet includes a first and a second acoustic-electric combined partial discharge sensor. The switchgear cabinet also includes components such as a trolley compartment, a busbar compartment, a cable compartment, and an instrument compartment. The first acoustic-electric combined partial discharge sensor can be deployed in the instrument compartment, and the second acoustic-electric combined partial discharge sensor can be deployed in the cable compartment. The present invention does not limit the deployment locations of the first and second acoustic-electric combined partial discharge sensors. The cable compartment includes a current transformer, outgoing line contacts, a grounding switch, and a line lightning arrester.

[0069] The locations of the first and second combined acoustic-electric partial discharge sensors are known. The first and second distances S1 and S2 have already been calculated. A first circular curve and a second circular curve are drawn based on the first and second distances S1 and S2, respectively, to obtain two intersection points. According to one embodiment of the present invention, if one of the two intersection points is outside the switchgear or is located near no switchgear components, that intersection point is discarded; the components located at the other intersection point are then determined.

[0070] The fault location includes its coordinates on the switchgear floor plan, indicating its specific location within the switchgear. Subsequently, one or more faulty components are identified based on the fault location information and the switchgear layout information. According to one embodiment of the present invention, the switchgear layout information includes the location information of various components within the switchgear, such as current transformers, outgoing line contacts, grounding switches, and line lightning arresters. By comparing the fault location information with the location information of the various components, one or more components near the fault location can be identified as the faulty components.

[0071] Optionally, after determining the faulty component in step 204, the method further includes: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

[0072] For example, if the faulty component is a current transformer, the fault type may be: poor contact of the current transformer, blown fuse of the current transformer, etc.

[0073] Optionally, after obtaining the fault type of the faulty component, the method further includes: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

[0074] Specifically, the process of determining the fault level of the faulty component according to the faulty component, the fault type corresponding to the faulty component, and the partial discharge data corresponding to the faulty component may be: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

[0075] In an actual implementation process, after the faulty component is obtained, the partial discharge data collected from the faulty component may be input into a fault type classification model pre-trained for the faulty component.

[0076] According to one embodiment of the present invention, the present invention also pre-generates a fault type classification model for each component in the switch cabinet, including: obtaining historical partial discharge data of each component under different fault types generated at historical times; generating a training sample based on each piece of historical partial discharge data, the partial discharge type to which the historical partial discharge data belongs, and the fault type corresponding to the historical partial discharge data to obtain a training sample set; training a neural network model based on the training sample set to generate a fault type classification model for the component.

[0077] According to one embodiment of the present invention, since switchgear contains numerous components, each with distinct characteristics, and exhibits different performance data when faulted and normal, the present invention collects partial discharge data for each component and, based on this data, trains each component individually. After identifying one or more faulty partial discharge components, fault classification is performed based on a pre-trained fault classification model for each component. This improves the accuracy of fault classification for each partial discharge component and enhances the efficiency of switchgear inspection.

[0078] According to one embodiment of the present invention, historical partial discharge data is partial discharge data generated by components in the switchgear at historical times. The present invention can use historical partial discharge data from component anomalies as positive samples, and historical partial discharge data from non-anomalies as negative samples, to train a fault type classification model. Each component may have multiple faults; the partial discharge data generated by each component when it experiences different faults will also be different. Therefore, when training the fault type classification model for each component, the present invention can collect multiple partial discharge data for each fault of that component as training samples.

[0079] According to one embodiment of the present invention, each partial discharge data set includes characteristic values for one or more of the following: amplitude, amplitude dispersion, number of discharges, discharge time interval, 50Hz frequency component, 100Hz frequency component, comparison of 50Hz and 100Hz frequency components, positive and negative semi-axis symmetry, single-peak or double-peak characteristics, polarity effect, fractal diagram, ultrasonic detection probability, and PRPS characteristics. The characteristic values of these characteristics can be determined from a PDRS spectrum generated from the partial discharge data, and the present invention does not limit the specific method for determining the characteristic values of these characteristics.

[0080] According to one embodiment of the present invention, each historical partial discharge data set is labeled with the partial discharge type and fault type. Using the partial discharge type along with the partial discharge data as training samples increases the data richness of the training samples and improves the training effectiveness of the fault type classification model. When determining the partial discharge type based on the partial discharge data or historical partial discharge data, a PDRS map can be generated based on the partial discharge data or historical partial discharge data. The PDRS map is then input into a pre-trained partial discharge type classification model, and the partial discharge type corresponding to the partial discharge data is determined based on the partial discharge type classification model. The present invention does not limit the specific training method for the partial discharge type classification model.

[0081] According to one embodiment of the present invention, the training sample set of the fault type classification model for each component includes training samples generated when the component has multiple different faults. The neural network model used in training can be specifically implemented as any one of the COX proportional hazard model, the survival support vector machine model, the random survival forest model, the DeepSurv nonlinear model, and the gradient boosting survival model; or multiple different neural network models can be trained separately, the average cross-validation consistency index of each model is determined, and the neural network model with the largest average cross-validation consistency index is selected as the final model used in the fault type classification model. The present invention does not limit the specific neural network model used when training the fault type classification model.

[0082] According to one embodiment of the present invention, inputting partial discharge data collected from a faulty component into a fault type classification model pre-trained for the faulty component includes: determining the partial discharge type to which the partial discharge data belongs based on the partial discharge data collected from the faulty component; and inputting the partial discharge data and the partial discharge type into the fault type classification model.

[0083] Finally, the fault information of the switch cabinet is generated according to the output of the fault type classification model of the fault component; the output of the fault type classification model of the fault component includes the fault type predicted according to the fault type classification model, and the fault information of the switch cabinet is generated according to the output of the fault type classification model of the fault component, including: generating the fault information of the switch cabinet according to each located fault component and the fault type predicted by the fault type classification model of the fault component.

[0084] According to one embodiment of the present invention, after the fault information is generated, the fault information and partial discharge data are input into a partial discharge fault classification model to determine the fault level; and alarm information is generated according to the fault level to warn of the fault.

[0085] According to one embodiment of the present invention, a partial discharge fault classification model pre-sets multiple different fault levels for different fault types; the fault levels for different fault types in different areas or components of the switchgear are determined differently. For example, when the partial discharge data of a component in the switchgear cable compartment is above 8dBμV and below 20dBμV, the fault level reaches the concern level; when the partial discharge data is above 20dBμV and below 30dBμV, the fault level reaches the severe level; when the partial discharge data of the switchgear is above 30dBμV, the fault level reaches the maintenance-required level. When the partial discharge data of a component in the switchgear cable compartment is above 8dBμV and below 20dBμV, the fault level reaches the concern level; when the partial discharge data is above 20dBμV and below 30dBμV, the fault level reaches the severe level; when the partial discharge data of the switchgear is above 30dBμV, the fault level reaches the maintenance-required level. When the partial discharge data of a component in the switchgear busbar compartment is above 8dBμV, the fault level reaches the severe level.

[0086] According to one embodiment of the present invention, the present invention can be applied in the field of partial discharge monitoring of substation switch cabinets, and can be used by operation and maintenance personnel to provide operation and maintenance personnel with accurate identification of partial discharge anomalies inside and outside the cabinet when the switch cabinet partial discharge is abnormal, as well as the function of troubleshooting interference sources outside the cabinet; when it is determined that the switch cabinet partial discharge abnormality is caused by external interference, an external interference source alarm is issued; when it is determined that the switch cabinet partial discharge abnormality is caused by an internal abnormality in the switch cabinet, an internal partial discharge abnormality alarm is issued in the switch cabinet, and alarm information of the external interference source alarm or the internal partial discharge abnormality alarm is sent to the distribution network cloud master station to handle the partial discharge abnormality; and corresponding data can also be sent to the distribution network cloud master station to display the specific data source of the abnormality judgment at the distribution network cloud master station, including partial discharge maps, etc., to assist operation and maintenance personnel in further analysis.

[0087] The present invention deploys detection devices such as dual ultrasonic partial discharge sensors and acoustic-electric combined partial discharge sensors in the substation, and uses an acoustic-electric combined method to locate the source of discharge in the cabinet. Specifically, it can first be determined based on the dual ultrasonic partial discharge sensors whether the partial discharge abnormality of the switch cabinet is caused by external interference or the partial discharge abnormality of the switch cabinet is caused by an abnormality inside the switch cabinet. If the partial discharge abnormality of the switch cabinet is caused by an abnormality inside the switch cabinet, the partial discharge in the switch cabinet is accurately located based on the acoustic-electric combined partial discharge sensor, which helps operation and maintenance personnel to quickly and accurately find the fault point, reduce the equipment operation and maintenance workload of grassroots business personnel, improve operation and maintenance efficiency, and ensure the reliability of power supply services. The present invention also supports sensor group scheduling when connecting to various sensors, and supports calculations of up to 4 groups with a total of 40 sensors. It can separately schedule the sensors deployed in each switch cabinet and locate the location of the partial discharge source in the cabinet.

[0088] The present invention studies the partial discharge fault location system of substation switch cabinets based on dual ultrasonic partial discharge sensors and combined acoustic and electrical partial discharge sensors. By integrating wireless networking technology, high-precision positioning algorithms, etc., the position of the partial discharge fault source is accurately located. By real-time monitoring of the combined acoustic and electrical signals inside and outside the switch cabinet, possible fault points are quickly discovered and located, thereby realizing the rapid location and processing of partial discharge faults in substation switch cabinets.

[0089] The present invention also provides a substation switchgear partial discharge fault location system based on dual ultrasonic partial discharge sensors and combined acoustic-electrical partial discharge sensors. This system integrates wireless networking technology and high-precision positioning algorithms to accurately locate the source of partial discharge faults within the switchgear. By real-time monitoring of combined acoustic-electrical signals inside and outside the switchgear, it rapidly detects and locates potential fault points, enabling rapid location and resolution of partial discharge faults in substation switchgear.

[0090] The substation switchgear partial discharge fault location system product configuration includes: At a 220kV substation, it includes one digital node device, two aggregation node devices connected to the digital node devices, four acoustic-electric combined partial discharge (PD) sensors deployed in cabinets, 24 dual-ultrasonic partial discharge (PD) sensors, and one station-side fault location application deployed on the digital node devices; at a 110kV substation, it includes one digital node device, one aggregation node device connected to the digital node devices, two acoustic-electric combined partial discharge (PD) sensors deployed in cabinets, 16 dual-ultrasonic partial discharge (PD) sensors, and one station-side fault location application deployed on the digital node devices. The station-side fault location application executes the present invention's method for locating partial discharges within substation switchgear cabinets.

[0091] The present invention also carries out a pilot application of the partial discharge fault location system for substation switch cabinets: a substation that has experienced abnormal partial discharge signals during historical detection is selected as a typical pilot application scenario, and a partial discharge fault location system based on combined acoustics and electricity is deployed in the substation to monitor partial discharge signals in real time and locate faults to verify the accuracy and stability of the system.

[0092] According to one embodiment of the present invention, a certain location has approximately 450 220kV and 110kV substations, including 87 Class I and higher power-saving substations, 73 Class II and III power-saving substations, and the remainder being non-power-saving substations. The deployment principle includes deploying one partial discharge fault location system product at each of the 87 Class I and higher power-saving substations, one partial discharge fault location system product every two stations at the 73 Class II and III power-saving substations, and a 10% periodic rotation monitoring of the 290 non-power-saving substations, based on the "portability and reusability" of core components. Based on this deployment principle, the pilot program was calculated to include 63 220kV substations and 90 110kV substations requiring the deployment of partial discharge fault location products.

[0093] During the pilot process, by deploying partial discharge fault location products in the substation, the combined acoustic and electrical fault location can accurately locate the location of the partial discharge source in the cabinet, which can help operation and maintenance personnel quickly and accurately find the fault point, shorten the troubleshooting time, improve maintenance efficiency, and achieve the purpose of accurately identifying and quickly handling switch cabinet faults.

[0094] like Figure 4 As shown, the present application provides a device for determining a fault in a substation switch cabinet, the device comprising: The first acquisition module 11 is configured to acquire a first time when the first sensor receives the first electromagnetic wave signal and a second time when the first sensor receives the first ultrasonic signal; a second acquisition module 12, configured to acquire a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after the second sensor receives the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, both of which are deployed in the switch cabinet and are configured to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet; a first determining module 13, configured to determine a fault location according to the first time, the second time, the third time, the fourth time, a first position of the first sensor, and a second position of the second sensor; The second determining module 14 is configured to determine a faulty component according to the fault location and the layout information of the components in the switch cabinet.

[0095] In one embodiment, the apparatus further comprises a processing module 15, wherein the processing module 15 is configured to: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

[0096] In one embodiment, the first determining module 13 is specifically configured to: Obtain a time difference between the first time and the second time to obtain a first time difference; Obtain a time difference between the third time and the fourth time to obtain a second time difference; determining a first distance between the fault and the first sensor according to the first time difference; determining a second distance between the fault and the second sensor according to the second time difference; The fault location is determined according to the first distance, the second distance, the first position, and the second position.

[0097] In one embodiment, the first determining module 13 is specifically configured to: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The position of the intersection of the first circular curve and the second circular curve is determined as the fault position.

[0098] In one embodiment, the first determining module 13 is specifically configured to: The first distance is determined according to the first time difference, a preset first transmission speed of the electromagnetic wave signal, and a preset second transmission speed of the ultrasonic wave signal.

[0099] In one embodiment, the processing module 15 is further configured to: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

[0100] In one embodiment, the processing module 15 is specifically configured to: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

[0101] The device for determining faults within a substation switchgear provided in this embodiment can implement the aforementioned method for determining faults within a substation switchgear. Its implementation principles and technical effects are similar and will not be further elaborated upon here. Each module in the aforementioned device for determining faults within a substation switchgear can be implemented in whole or in part via software, hardware, or a combination thereof. Each of these modules can be embedded in or independent of a processor in an electronic device in hardware form, or stored in a memory within the electronic device in software form, so that the processor can call and execute the corresponding operations of each of these modules.

[0102] The execution subject of the method for determining faults in a substation switch cabinet provided in the embodiment of the present application may be an electronic device, which may be a computer device, a terminal device, a server or a server cluster, and the embodiment of the present application does not specifically limit this.

[0103] Figure 5 FIG. 5 is a schematic diagram of an electronic device 500 according to an exemplary embodiment of the present invention. Figure 5 As shown, the electronic device 500 may include: a central processing unit 510, a memory 520, an input / output interface 530, a communication interface 540, and a bus 550. The central processing unit 510, the memory 520, the input / output interface 530, and the communication interface 540 are connected to each other via the bus 550 within the electronic device.

[0104] The central processing unit 510 can be implemented using a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0105] The memory 520 can be implemented in the form of ROM (Read Only Memory), RAM (Random Access Memory), static storage devices, dynamic storage devices, etc. The memory 520 can store an operating system and other application programs. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 520 and is called and executed by the central processing unit 510.

[0106] The input / output interface 530 is used to connect to input / output modules to enable information input and output. The communication interface 540 is used to enable communication between the electronic device and other devices. The bus 550 includes a path for transmitting information between the various components of the electronic device (e.g., the CPU 510, the memory 520, the input / output interface 530, and the communication interface 540).

[0107] It should be noted that although the electronic device shown above only includes a central processing unit 510, a memory 520, an input / output interface 530, a communication interface 540, and a bus 550, in a specific implementation, the electronic device may also include other components necessary for normal operation. In addition, those skilled in the art will understand that the electronic device may only include the components necessary to implement the embodiments of this specification, and does not necessarily include all the components shown in the figures.

[0108] An embodiment of the present invention also provides a non-transitory readable storage medium storing instructions for causing the computing device to execute a method according to an embodiment of the present invention. The readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be a computer-readable instruction, a data structure, a program module, or other data. Examples of readable storage media include, but are not limited to: phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassettes, tape disk storage or other magnetic storage devices, or any other non-transitory readable storage medium.

[0109] In another embodiment of the present application, a computer program product is also provided, which includes computer instructions. When the computer instructions are run on a device for determining a fault in a substation switch cabinet, the device for determining a fault in a substation switch cabinet executes each step of the method for determining a fault in a substation switch cabinet in the method flow shown in the above method embodiment.

[0110] In the above embodiments, all or part of the embodiments can be implemented using software, hardware, firmware, or any combination thereof. When implemented using a software program, all or part of the embodiments can be implemented in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer-executable instructions are loaded and executed on a computer, all or part of the processes or functions according to the embodiments of the present application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, the computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium that can be accessed by a computer or a data storage device such as a server or data center that includes one or more servers that can be integrated with the medium. The available media may be magnetic media (eg, floppy disks, hard disks, magnetic tapes), optical media (eg, DVDs), or semiconductor media (eg, solid state disks (SSDs)).

[0111] The technical features of the above embodiments can be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0112] The above embodiments merely represent several implementation methods of the present application. While the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the present invention. It should be noted that a person skilled in the art could make various modifications and improvements without departing from the spirit of the present application, all of which fall within the scope of protection of the present application. Therefore, the scope of protection of the present patent application shall be determined by the appended claims.

Claims

1. A method for determining a fault in a substation switch cabinet, characterized in that: The method comprises: Acquire a first time when the first sensor receives the first electromagnetic wave signal and a second time when the first sensor receives the first ultrasonic wave signal; Obtaining a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after the second sensor receives the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, and the combined acoustic and electrical partial discharge sensors are both deployed in the switch cabinet and are used to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet; determining a fault location according to the first time, the second time, the third time, the fourth time, a first position of the first sensor, and a second position of the second sensor; The faulty component is determined according to the fault location and the layout information of the components in the switch cabinet.

2. The method according to claim 1, characterized in that After determining the faulty component, the method further includes: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

3. The method according to claim 1, characterized in that The determining the fault location according to the first time, the second time, the third time, and the fourth time includes: Obtain a time difference between the first time and the second time to obtain a first time difference; Obtain a time difference between the third time and the fourth time to obtain a second time difference; determining a first distance between the fault and the first sensor according to the first time difference; determining a second distance between the fault and the second sensor according to the second time difference; The fault location is determined according to the first distance, the second distance, the first position, and the second position.

4. The method according to claim 3, characterized in that The determining the fault location according to the first distance, the second distance, the first position, and the second position includes: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The fault location is determined according to the intersection of the first circular curve and the second circular curve.

5. The method according to claim 3, characterized in that Determining the first distance between the fault and the first sensor according to the first time difference includes: The first distance is determined according to the first time difference, a preset first transmission speed of the electromagnetic wave signal, and a preset second transmission speed of the ultrasonic wave signal.

6. The method according to claim 2, characterized in that After obtaining the fault type of the faulty component, the method further includes: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

7. The method according to claim 6, characterized in that The determining the fault level of the faulty component according to the faulty component, the fault type corresponding to the faulty component, and the partial discharge data corresponding to the faulty component includes: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

8. A device for determining faults in a transformer substation switch cabinet, characterized in that: The device comprises: A first acquisition module is used to acquire a first time when the first sensor receives the first electromagnetic wave signal and a second time when the first sensor receives the first ultrasonic signal; a second acquisition module, configured to acquire a third time after the second sensor receives the second electromagnetic wave signal and a fourth time after the second sensor receives the second ultrasonic signal, wherein the first sensor and the second sensor are combined acoustic and electrical partial discharge sensors, both of which are deployed in the switch cabinet and are configured to collect electromagnetic wave signals and ultrasonic signals for faults in the switch cabinet; a first determining module, configured to determine a fault location according to the first time, the second time, the third time, the fourth time, a first position of the first sensor, and a second position of the second sensor; The second determining module is configured to determine the faulty component according to the fault location and the layout information of the components in the switch cabinet.

9. The device according to claim 8, characterized in that The device further includes a processing module, wherein the processing module is configured to: Acquiring collected partial discharge data of the faulty component; Inputting the faulty component and the partial discharge data of the faulty component into a preset fault classification model to obtain the fault type of the faulty component; The fault classification model is obtained by training based on training samples, and the training samples include: historical partial discharge data of each component in the switch cabinet under different fault types generated at historical times.

10. The device according to claim 8, characterized in that The first determining module is specifically configured to: Obtain a time difference between the first time and the second time to obtain a first time difference; Obtain a time difference between the third time and the fourth time to obtain a second time difference; determining a first distance between the fault and the first sensor according to the first time difference; determining a second distance between the fault and the second sensor according to the second time difference; The fault location is determined according to the first distance, the second distance, the first position, and the second position.

11. The device according to claim 10, characterized in that The first determining module is specifically configured to: generating a first circular curve with the first position as the center and the first distance as the radius; generating a second circular curve with the second position as the center and the second distance as the radius; The fault location is determined according to the intersection of the first circular curve and the second circular curve.

12. The device according to claim 10, characterized in that The first determining module is specifically configured to: The first distance is determined according to the first time difference, a preset first transmission speed of the electromagnetic wave signal, and a preset second transmission speed of the ultrasonic wave signal.

13. The device according to claim 9, characterized in that The processing module is further configured to: determining a fault level of the faulty component according to the faulty component, a fault type corresponding to the faulty component, and partial discharge data corresponding to the faulty component; Generate corresponding alarm information according to the fault level.

14. The device according to claim 13, characterized in that The processing module is specifically used for: Inputting the fault component, the fault type corresponding to the fault component, and the partial discharge data corresponding to the fault component into a preset partial discharge fault classification model to obtain the fault level; The partial discharge fault classification model is obtained by training based on sample data, and the sample data includes: fault levels corresponding to multiple different fault components under different fault types and partial discharge data.

15. An electronic device, characterized in that: The invention comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the method for determining a fault in a substation switch cabinet according to any one of claims 1 to 7 is implemented.

16. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method for determining a fault in a substation switch cabinet according to any one of claims 1 to 7 is implemented.

Images