Partial discharge monitoring method, device, equipment and medium based on digital twin
Through digital twin technology, the integration of high-frequency, ultra-high frequency and ultrasonic sensor data is built to build a transformer digital twin model, solving the problem of difficulty in fusion and positioning of multi-source data in local discharge monitoring of transformers, and achieving efficient and accurate local discharge positioning.
Patent Information
- Application Number
- CN202411228544.3
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-09-03
- Publication Date
- 2024-11-15
- Estimated Expiration
- 2044-09-03
AI Technical Summary
The existing local discharge monitoring of transformers lacks diagnostic analysis methods for multi-source data fusion, resulting in difficulty in positioning and inefficient efficiency.
Using a digital twin method, through the fusion of multi-source data of high-frequency, ultra-high frequency and ultrasonic sensors, a transformer digital twin model and arrival time difference fingerprint library are built to realize joint synchronous monitoring of electricity-electric, acoustic-electric, acoustic-acoustic, acoustic-acoustic, and acoustic-acoustic. Automatically calculate the arrival time difference of the sensor received signal to locate the local discharge point.
It significantly improves the accuracy and efficiency of local discharge monitoring, reduces labor calculation costs and positioning errors, and optimizes the display friendliness of local discharge positioning results.
Smart Images

Figure CN118759328B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of partial discharge monitoring, and in particular to a partial discharge monitoring method, device, electronic device and storage medium based on digital twin. Background Art
[0002] Transformers are one of the most important electrical equipment in the power system. Their operating conditions are directly related to the safe operation of the power system. Once a failure occurs, it will inevitably cause a large-scale power outage. In recent years, the main transformer equipment of substations has frequently failed, exposing the problems of insufficient existing detection, early warning and protection means, insufficient intrinsic safety of equipment, and insufficient monitoring technology.
[0003] Transformer partial discharge (PD) is mainly the discharge of the internal insulation of the transformer under the action of high voltage. Partial discharge only exists in the local position of the insulation and will not immediately form a through-breakdown or flashover of the entire insulation. Partial discharge cannot be directly observed by the operating personnel and can only be detected by a dedicated partial discharge detection device. The detection of partial discharge signals mainly detects various physical and chemical phenomena such as electricity, sound, light, temperature and gas generated during the discharge process through corresponding sensors, and is described by physical quantities that can characterize these partial discharge phenomena. The detection methods can be roughly divided into electrical measurement methods and non-electrical measurement methods. The electrical measurement method uses the pulse of the electrical signal generated by the partial discharge for measurement, which can reliably detect problems in the early stage of defects, including pulse current method, ultra-high frequency method, etc. Non-electrical measurement methods include gas analysis in oil, optical measurement method, ultrasonic detection method, etc. At present, the most widely used partial discharge detection methods are high-frequency pulse current method, gas analysis in oil, ultrasonic detection method and ultra-high frequency method.
[0004] ① High-frequency pulse current method (HF): The principle of this method is that when partial discharge occurs inside the transformer, the high-frequency current signals of these parts are sensed and analyzed by high-frequency current transformers at the iron core, clamp grounding wire, bushing end screen, arrester counter lead and other locations of the transformer. Currently, Rogowski coils are mostly used for measurement. The advantages of this method are high sensitivity, direct detection of the discharge charge of partial discharge, easy installation, accurate reflection of the amplitude change of partial discharge inside the transformer, and wide practicality; the disadvantages are poor anti-interference ability, easy interference by various signals in the ground network, and inability to locate partial discharge. The test data of the high-frequency pulse current method in engineering applications is generally used as a reference for ultra-high frequency or ultrasonic data.
[0005] ② Ultrasonic detection method (AE): When partial discharge occurs inside the transformer, ultrasonic signals will also be generated. When the signal propagates to the periphery of the transformer shell, the ultrasonic sensor installed on the transformer shell senses the ultrasonic signal, and monitors and locates the partial discharge signal through the amplitude of the ultrasonic pulse and the time difference of reaching each sensor. The advantages of the ultrasonic detection method are that the sensor is easy to install, the defect test in the middle and lower part of the transformer box does not require power outage, and the signal around the transformer shell can be quickly located. The disadvantage is that it is not sensitive to air gap discharge in oil and insulating materials, and may not be sensitive to defects in the transformer windings. It requires more points to be arranged or needs to be moved continuously.
[0006] ③UHF method (UHF): UHF method is an effective means of transformer partial discharge detection. This method uses UHF sensors to sense the UHF electromagnetic waves radiated by partial discharge. By monitoring, analyzing and comparing the waveform pulses, partial discharge monitoring is achieved. The UHF signal is located by the time difference method with high positioning accuracy of up to 0.3 meters. The advantages of the UHF method are that it is less affected by external interference when propagating inside the transformer, has strong anti-interference ability, high monitoring sensitivity, and is suitable for online monitoring. The disadvantage is that the UHF sensor needs to be pre-installed during transformer production, or it can only be installed through power outages, oil drainage, cover replacement, and testing of technical transformation projects.
[0007] The existing transformer partial discharge monitoring lacks a diagnostic analysis method for multi-source data fusion and has the problem of difficulty in defect location. Summary of the invention
[0008] The present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a partial discharge monitoring method, device, electronic device and storage medium based on digital twin, which can accurately identify partial discharge phenomena and accurately locate the partial discharge position.
[0009] In a first aspect, a partial discharge monitoring method based on digital twin according to an embodiment of the present invention is applied to a transformer, wherein the transformer is provided with a plurality of sensors, wherein the plurality of sensors include three types: a high-frequency sensor, an ultra-high-frequency sensor, and an ultrasonic sensor. A plurality of the high-frequency sensors, a plurality of the ultra-high-frequency sensors, and a plurality of the ultrasonic sensors respectively form a high-frequency monitoring channel, an ultra-high-frequency monitoring channel, and an ultrasonic monitoring channel. The method comprises the following steps:
[0010] According to the internal and external structure of the transformer and the installation position of each sensor, a three-dimensional display model of the transformer is established;
[0011] The three-dimensional transformer display model is spatially digitized to form a three-dimensional transformer digital model;
[0012] When each monitoring point inside the transformer is used as a local discharge source, the time difference of the local discharge signal reaching each sensor is obtained, and according to the time difference, an arrival time difference fingerprint library corresponding to the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel is established respectively;
[0013] Establishing a transformer digital twin model according to the arrival time difference fingerprint library and the transformer three-dimensional digital model;
[0014] Performing time synchronization on the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel;
[0015] A multi-source fusion recognition model is established according to the high-frequency sensor, the ultra-high-frequency sensor and the ultrasonic sensor; the multi-source fusion recognition model is used to identify the corresponding partial discharge type according to the partial discharge spectrum;
[0016] Determining the positioning accuracy of the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel for different partial discharge types;
[0017] When the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel detect the presence of a partial discharge signal in the transformer, identifying a partial discharge spectrum corresponding to the partial discharge signal;
[0018] The multi-source fusion recognition model identifies the local discharge type corresponding to the local discharge signal according to the local discharge spectrum;
[0019] According to the partial discharge type and the positioning accuracy, determining one of the high-frequency monitoring channel, the ultra-high-frequency monitoring channel and the ultrasonic monitoring channel as a positioning channel;
[0020] According to the time difference between the partial discharge signal and each sensor in the positioning channel, the partial discharge position of the transformer is located through the arrival time difference fingerprint library of the transformer digital twin model.
[0021] According to some embodiments of the present invention, the step of spatially digitizing the three-dimensional display model of the transformer to form a three-dimensional digital model of the transformer includes:
[0022] The smallest circumscribed cuboid of the three-dimensional display model of the transformer is defined as a scene; the bottom surface of the scene coincides with the ground where the transformer is located, the outside of the transformer is the external space of the scene, and the inside of the transformer is the internal space of the scene;
[0023] Taking a vertex of the scene as an origin, dividing the scene into a plurality of cubes at a preset resolution on the XYZ coordinate axes;
[0024] According to the serial number of the cube where any point of the scene is located, the coordinates of each point are quantized into digital coordinates, thereby forming the three-dimensional digital model of the transformer.
[0025] According to some embodiments of the present invention, the step of obtaining the time difference of the partial discharge signal reaching each of the sensors when each monitoring point inside the transformer is used as a partial discharge source, and establishing an arrival time difference fingerprint library corresponding to the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel respectively according to the time difference includes:
[0026] A partial discharge signal simulator is used to generate a partial discharge monitoring signal at each monitoring point inside the transformer as a partial discharge source;
[0027] Calculating the shortest transmission path for transmitting the partial discharge monitoring signal to each of the sensors through a path planning algorithm;
[0028] Obtaining the propagation speed of the partial discharge monitoring signal, and calculating the arrival time vector of each of the monitoring points according to the shortest transmission path and the propagation speed;
[0029] The arrival time difference fingerprint library is established according to the arrival time vector.
[0030] According to some embodiments of the present invention, calculating the shortest transmission path for transmitting the partial discharge monitoring signal to each of the sensors by a path planning algorithm includes:
[0031] If the partial discharge monitoring signal is an ultrasonic signal, the shortest transmission path is a straight line transmission path between the partial discharge source and each of the ultrasonic sensors;
[0032] If the partial discharge signal is an electromagnetic wave and there is an obstacle between the partial discharge source and the sensor, the shortest transmission path is the transmission path of the shortest distance from the partial discharge signal from the partial discharge source to the obstacle and after being reflected or diffracted by the obstacle to each of the ultra-high frequency sensors.
[0033] According to some embodiments of the present invention, the step of time synchronizing the signal waveforms detected by the high frequency monitoring channel, the ultra-high frequency monitoring channel, and the ultrasonic monitoring channel includes:
[0034] Using synchronous sampling technology, a synchronous clock is assigned to the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel; the accuracy of the synchronous clock is not less than nanosecond level;
[0035] Through the synchronous clock, the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel are provided with synchronized timestamps.
[0036] According to some embodiments of the present invention, the step of establishing a multi-source fusion recognition model based on the high frequency sensor, the ultra-high frequency sensor and the ultrasonic sensor includes:
[0037] Identify partial discharge spectra of various partial discharge types by using the high frequency sensor, the ultra-high frequency sensor and the ultrasonic sensor to obtain data features corresponding to different partial discharge types;
[0038] According to the data features, a deep learning network is trained to form the multi-source fusion recognition model.
[0039] According to some embodiments of the present invention, the method further comprises the following steps:
[0040] Obtaining a partial discharge spectrum, a discharge amplitude, a discharge pulse number and a positioning result of the partial discharge signal;
[0041] The partial discharge spectrum, the discharge amplitude, the number of discharge pulses and the positioning result are displayed on the transformer digital twin model.
[0042] In the second aspect, a partial discharge monitoring device based on digital twin according to an embodiment of the present invention includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions executable by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the partial discharge monitoring method based on digital twin as described in the embodiment of the first aspect.
[0043] In a third aspect, the smart seat according to an embodiment of the present invention includes the partial discharge monitoring device based on digital twin as described in the embodiment of the second aspect.
[0044] In a fourth aspect, according to a storage medium of an embodiment of the present invention, the storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the partial discharge monitoring method based on digital twins described in the embodiment of the first aspect.
[0045] The partial discharge monitoring method, device, electronic device and storage medium based on digital twin according to the embodiment of the present invention have at least the following beneficial effects: the present invention proposes a transformer partial discharge monitoring and automatic positioning technology based on intelligent synchronous acquisition of multiple sensors, and constructs a transformer digital twin model by fusing sensor data such as ultra-high frequency, high frequency, and ultrasonic wave, and constructs a multi-sensor arrival time difference fingerprint library, which can realize electric-electric, acoustic-electric, and acoustic-acoustic joint synchronous monitoring, and optimize the partial discharge positioning result; it proposes to construct a transformer digital twin model based on the transformer digital twin model technology according to the specific structure of the transformer, and establish an arrival time difference fingerprint library according to the signals sent by the possible partial discharge points inside the transformer collected by sensors installed at different positions. When there is partial discharge inside the transformer, according to the partial discharge pulse signal detected by multiple sensors, the algorithm program automatically calculates the arrival time difference of the signal received by each sensor, searches the arrival time difference fingerprint library to obtain the location of the partial discharge point, which can reduce the cost of human calculation and positioning error, and significantly improve the efficiency and accuracy of partial discharge monitoring.
[0046] Additional aspects and advantages 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
[0047] The above and / or additional aspects and advantages of the present invention will become apparent and easily understood from the description of the embodiments in conjunction with the following drawings, in which:
[0048] Figure 1 This is a flowchart of the steps of the partial discharge monitoring method based on digital twins according to an embodiment of the present invention;
[0049] Figure 2 Schematic diagram of the structure of a partial discharge monitoring device based on digital twin according to an embodiment of the present invention;
[0050] Figure 3 A schematic diagram of a three-dimensional display model of a transformer according to an embodiment of the present invention;
[0051] Figure 4 A schematic diagram of a three-dimensional digital model of a transformer according to an embodiment of the present invention;
[0052] Figure 5 A schematic diagram of a transmission path from a local discharge source to each ultrasonic sensor according to an embodiment of the present invention;
[0053] Figure 6 A schematic diagram of the transmission path of the ultra-high frequency electromagnetic wave reaching the sensor after being reflected or diffracted according to an embodiment of the present invention;
[0054] Figure 7 Schematic diagram of a transformer digital twin model according to an embodiment of the present invention. DETAILED DESCRIPTION
[0055] Embodiments of the present invention are described in detail below, and examples of the embodiments are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are only used to explain the present application, and are not to be construed as limitations on the present application. For the step numbers in the following embodiments, they are only provided for the convenience of explanation, and the order between the steps is not limited in any way, and the execution order of each step in the embodiment can be adaptively adjusted according to the understanding of those skilled in the art.
[0056] In the description of the present invention, it should be understood that descriptions involving orientations, such as up, down, front, back, left, right, etc., and orientations or positional relationships indicated are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the present invention and simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.
[0057] The terms "first", "second", "third" and "fourth" etc. in the specification and claims of the present invention and the drawings are used to distinguish different objects, rather than to describe a specific order. In addition, 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 that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or devices.
[0058] Reference to "embodiments" in the present invention means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0059] In recent years, in order to improve the stability of power grid operation, many new methods and technologies have emerged for the status detection of the primary core equipment of substations. The partial discharge problem of transformers is an important part of transformer status detection, and it is also a key factor affecting the safe, efficient and stable operation of the power grid. According to statistics, insulation aging and damage are the main causes of accidents in power transformers. Statistical analysis of multiple accidents that occurred in power transformers of 110kV and above showed that about 81% of the accidents were caused by insulation, and turn-to-turn insulation accidents accounted for 50%. Partial discharge is the main cause of insulation corrosion and causes flashover or breakdown. Short-term discharge will not cause damage to the dielectric of the entire channel, but the electrolysis caused by discharge accelerates the oxidation of the insulation and corrodes the insulation, which greatly reduces the life of the test transformer.
[0060] Partial discharge is an important factor in the safe and stable operation of power equipment. Rapid and timely detection of partial discharge faults, identification of partial discharge types and estimation of discharge point locations can minimize the harm caused by partial discharge.
[0061] To this end, the embodiment of the present invention provides a partial discharge monitoring method, device, electronic device and storage medium based on digital twin. Aiming at the problem that the existing transformer partial discharge monitoring lacks a diagnostic analysis method of multi-source data fusion, the present invention proposes a transformer partial discharge monitoring and automatic positioning technology based on intelligent synchronous acquisition of multiple sensors. By fusing the data of ultra-high frequency, high frequency, ultrasonic and other sensors, a transformer digital twin model is constructed, and a multi-sensor arrival time difference fingerprint library is constructed, which can realize electric-electric, acoustic-electric, acoustic-acoustic joint synchronous monitoring and optimize the partial discharge positioning result. In order to solve the problem of the difficulty in locating the existing partial discharge defects, it is proposed to construct a transformer digital twin model based on the transformer digital twin model technology according to the specific structure of the transformer, and establish an arrival time difference fingerprint library according to the signals sent by the possible partial discharge points inside the transformer collected by the sensors installed at different positions. When there is partial discharge inside the transformer, according to the partial discharge pulse signal detected by the multiple sensors, the algorithm program automatically calculates the arrival time difference of the signal received by each sensor, searches the arrival time difference fingerprint library to obtain the location of the partial discharge point, which can reduce the cost of manual calculation and positioning error, and significantly improve the efficiency and accuracy of partial discharge monitoring. In order to solve the problem of unfriendly display of existing transformer local discharge source positioning results, a monitoring data display technology based on the transformer digital twin model is proposed. Multiple local discharge amplitudes, frequencies, and spectrum data obtained by synchronous monitoring of multiple sensors and the positioning results obtained based on the arrival time difference fingerprint library are displayed in the three-dimensional transformer digital twin model to realize the positioning analysis of transformer local discharge defects.
[0062] The following describes in detail the partial discharge monitoring method, device, electronic device and storage medium based on digital twin according to the embodiments of the present invention in conjunction with the accompanying drawings.
[0063] On the one hand, if Figure 1 and Figure 2 As shown, an embodiment of the present invention proposes a partial discharge monitoring method based on digital twins. The method is applied to a transformer. The transformer is provided with a plurality of sensors. The plurality of sensors include three types: high-frequency sensors, ultra-high-frequency sensors, and ultrasonic sensors. A plurality of high-frequency sensors, a plurality of ultra-high-frequency sensors, and a plurality of ultrasonic sensors respectively form a high-frequency monitoring channel (HF), an ultra-high-frequency monitoring channel (UHF), and an ultrasonic monitoring channel (AE). The method comprises the following steps:
[0064] Step S100: establishing a three-dimensional display model of the transformer according to the internal and external structures of the transformer and the installation positions of various sensors;
[0065] Specifically, according to the internal and external structure of the transformer and the installation position of each sensor in the transformer, a 3D modeling tool such as Solidworks is used to perform 3D modeling on the structure to obtain a 3D display model of the transformer, such as Figure 3 shown.
[0066] Step S200: spatially digitizing the three-dimensional display model of the transformer to form a three-dimensional digital model of the transformer;
[0067] By spatially digitizing the three-dimensional display model of the transformer, it is easy to obtain the coordinates of each point inside the transformer, thereby facilitating the analysis and monitoring of the transformer. In this example, in order to spatially digitize the three-dimensional display model of the transformer, the above step S200 specifically includes the following three sub-steps:
[0068] (1) Define the smallest circumscribed cuboid of the transformer 3D display model as the scene; the bottom surface of the scene coincides with the ground where the transformer is located, the outside of the transformer is the external space of the scene, and the inside of the transformer is the internal space of the scene;
[0069] (2) Taking a vertex of the scene as the origin, divide the scene into multiple cubes on the XYZ coordinate axes with a preset resolution;
[0070] (3) According to the serial number of the cube where any point in the scene is located, the coordinates of each point are quantized into digital coordinates, thereby forming a three-dimensional digital model of the transformer.
[0071] For example, the three-dimensional digital model of the transformer is as follows: Figure 4As shown, first define the smallest circumscribed cuboid of the entire transformer 3D model as the "scene", and the bottom of the cuboid coincides with the ground where the transformer is located. In the scene, define the interior of the transformer as the "internal space" and the exterior of the transformer as the "external space". Take a vertex of the scene as the origin, and convert the length coordinate quantity into digital coordinates with a resolution of 0.1 meters (or other values) on the three coordinates of X, Y, and Z. For example, if the maximum dimensions of the transformer model in three directions are 5 meters, 4 meters, and 3 meters respectively, the dimensions of the scene are (5 meters, 4 meters, and 3 meters). After quantization, the entire scene is divided into (5 / 0.1)*(4 / 0.1)*(3 / 0.1)=60,000 cubes with a side length of 0.1 meters. The position coordinates of any point in the scene are converted into the serial number of the cube where it is located, that is, the digital coordinates, based on its distance from the origin. The digital coordinate range of the X direction is 0, 1, ..., 49, the digital coordinate range of the Y direction is 0, 1, ..., 39, and the digital coordinate range of the Z direction is 0, 1, ..., 29. For example, if the original coordinates of the location point in the scene are (3.85 meters, 2.52 meters, 2.01 meters), the digital coordinates after quantization are (39, 25, 20).
[0072] Step S300: obtaining the time difference of the partial discharge signal reaching each sensor when each monitoring point inside the transformer is used as a partial discharge source, and establishing an arrival time difference fingerprint library corresponding to the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel respectively according to the time difference;
[0073] Specifically, based on the established three-dimensional digital model of the transformer, the arrival time difference fingerprint library is calculated, that is, each point in the internal space of the transformer is traversed, and the time difference of the partial discharge signal emitted by each point reaching each sensor when it is used as a partial discharge source is calculated. By establishing the time difference fingerprint library, when the partial discharge signal is detected later, the partial discharge position generating the partial discharge signal can be located by the time difference of the partial discharge signal reaching each sensor. It should be noted that, since the detection principles of the high-frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel are different, it is necessary to establish corresponding arrival time difference fingerprint libraries for different channels, that is, the arrival time difference fingerprint library of the corresponding high-frequency monitoring channel is established by the time difference of the partial discharge signal reaching each high-frequency sensor, the arrival time difference fingerprint library of the corresponding ultra-high frequency monitoring channel is established by the time difference of the partial discharge signal reaching each ultra-high frequency sensor, and the arrival time difference fingerprint library of the corresponding ultrasonic monitoring channel is established by the time difference of the partial discharge signal reaching each ultrasonic sensor.
[0074] In this example, the above step S300 specifically includes the following four steps:
[0075] (1) Use a partial discharge signal simulator to generate partial discharge monitoring signals at various monitoring points inside the transformer as partial discharge sources;
[0076] (2) Calculate the shortest transmission path for the PD monitoring signal to be transmitted to each sensor through a path planning algorithm;
[0077] (3) Obtain the propagation speed of the partial discharge monitoring signal and calculate the arrival time vector of each monitoring point based on the shortest transmission path and propagation speed;
[0078] (4) Based on the arrival time vector, establish an arrival time difference fingerprint library.
[0079] In order to establish the arrival time difference fingerprint library, a partial discharge signal simulator is first used to generate partial discharge monitoring signals at each monitoring point that needs to be monitored inside the transformer, and the shortest transmission path for the partial discharge monitoring signal to be transmitted to each sensor is calculated through a path planning algorithm. Since the three-dimensional digital model of the transformer can be regarded as a three-dimensional space dot matrix composed of many points, the minimum distance problem on the surface can be converted into the problem of finding the shortest path between the starting point and the end point in the dot matrix of three-dimensional space in the network graph model composed of many tangent vertices. By traversing each monitoring point inside the transformer, calculating its shortest path to each sensor, and dividing it by its propagation speed, the arrival time difference vector of each monitoring point can be obtained and recorded in the arrival time difference fingerprint library. Among them, the path planning algorithm can use Dijkstra and other algorithms.
[0080] It should be noted that the ultrasonic signal can propagate in a straight line from the local discharge source to the sensor, so the calculation of the arrival time difference fingerprint library corresponding to the ultrasonic monitoring channel is relatively simple, and the straight-line distance from the local discharge source to each ultrasonic sensor can be calculated. Figure 5 As shown in the figure, S1~S4 are ultrasonic sensors, PD Source is the coordinate of a monitoring point inside the transformer, Vk is the propagation speed of ultrasonic waves in the transformer (about 1800m / s), d vk-1 ~d vk-4 is the propagation time of the ultrasonic signal from this point to each sensor, [d vk-2 -d vk-1 , d vk-3 -d vk-1 , d vk-4 -d vk-1 ] is the arrival time difference vector of the point, which is recorded in the arrival time difference fingerprint library of the ultrasonic monitoring channel. When there is an obstacle on the straight transmission path between the local discharge source and the UHF sensor, the present invention defines the shortest transmission path as the shortest path distance for the UHF electromagnetic wave to reach the sensor after reflection or diffraction according to the Fermat principle. Figure 6 shown.
[0081] Step S400: establishing a transformer digital twin model according to the arrival time difference fingerprint library and the transformer three-dimensional digital model;
[0082] It should be noted that based on the three-dimensional digital model of the transformer and combined with the arrival time difference fingerprint library, a transformer digital twin model is formed. Figure 7 As shown. By building a digital twin model of the transformer, the actual operating status of the transformer can be simulated, remote monitoring or real-time monitoring of the transformer can be achieved, partial discharge phenomena in the transformer can be discovered in time, and the location of the partial discharge can be located, so that the partial discharge problem can be solved as soon as possible to protect the transformer. At the same time, the digital twin model of the transformer can be used to perform various data analyses on the transformer.
[0083] Step S500: Time synchronization of the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel;
[0084] It should be noted that since a variety of different types of sensors are set in the transformer, and different types of sensors have different sampling frequencies, the collected data have different physical meanings; therefore, it is necessary to achieve synchronous monitoring between high-frequency sensors, ultra-high-frequency sensors and ultrasonic sensors to make the diagnosis and positioning results more accurate. In this example, the above step S500 includes the following two steps:
[0085] (1) Using synchronous sampling technology, a synchronous clock is assigned to the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel; the accuracy of the synchronous clock is not less than nanosecond level;
[0086] (2) By synchronizing the clock, the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel are equipped with synchronized timestamps.
[0087] By providing synchronized timestamps to the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel, the ability to accurately compare the arrival times of the waveforms is achieved, thus satisfying the prerequisite for precise positioning.
[0088] Step S600: establishing a multi-source fusion recognition model based on the high-frequency sensor, the ultra-high-frequency sensor and the ultrasonic sensor; the multi-source fusion recognition model is used to identify the corresponding partial discharge type according to the partial discharge spectrum;
[0089] It should be noted that there are many locations where partial discharge may occur inside the transformer, including breakdown of the oil channel in the oil-paper barrier insulation in the middle of the winding, breakdown of the oil channel at the end of the winding, breakdown of the oil gap close to the insulated wire and electrical paper (lead insulation, lap insulation, phase insulation), breakdown of the longitudinal insulating oil channel between coils (between turns and between layers), resin discharge of insulating cardboard screens, surface discharge of solid insulation, discharge of other metal foreign matter infiltrated into the insulation, etc. For discharges of different types and locations, the sensitivity of high-frequency signals, ultra-high-frequency signals and ultrasonic signals is different, and the positioning accuracy is also different. In order to maximize the positioning accuracy, it is necessary to determine the type of partial discharge. To this end, in this example, a multi-source fusion recognition model is established for high-frequency sensors, ultra-high-frequency sensors and ultrasonic sensors to identify the type of partial discharge. The above-mentioned step S600 specifically includes the following two steps:
[0090] (1) Identify partial discharge spectra of various partial discharge types through high-frequency sensors, ultra-high-frequency sensors and ultrasonic sensors, and obtain data features corresponding to different partial discharge types;
[0091] (2) Based on the data characteristics, train the deep learning network to form a multi-source fusion recognition model.
[0092] High-frequency sensors, ultra-high-frequency sensors and ultrasonic sensors are used to simultaneously identify partial discharge spectra of multiple different partial discharge types, so as to obtain data features corresponding to different partial discharge types. These data features are then used to train a deep learning network to form a multi-source fusion recognition model, which enables the multi-source fusion recognition model to identify the partial discharge type according to the partial discharge spectrum.
[0093] Step S700: determining the positioning accuracy of the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel for different partial discharge types;
[0094] After constructing a multi-source fusion recognition model and enabling it to identify the type of partial discharge based on the partial discharge spectrum, it is necessary to determine the positioning accuracy of the high-frequency monitoring channel, the ultra-high frequency monitoring channel, and the ultrasonic monitoring channel for different types of partial discharge. To this end, a partial discharge signal simulator can be used to generate partial discharge signals corresponding to different types of partial discharge at each monitoring point inside the transformer, and the partial discharge position is located according to the partial discharge signal through the high-frequency monitoring channel, the ultra-high frequency monitoring channel, and the ultrasonic monitoring channel, respectively, and the positioning results of each monitoring channel are compared with the actual partial discharge position, so as to determine the positioning accuracy of the high-frequency monitoring channel, the ultra-high frequency monitoring channel, and the ultrasonic monitoring channel for different types of partial discharge.
[0095] Step S800: When the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel detect the presence of a partial discharge signal in the transformer, a partial discharge spectrum corresponding to the partial discharge signal is identified;
[0096] When partial discharge occurs during the operation of the transformer, a partial discharge signal will be generated at the location of the partial discharge. The high-frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel will detect the partial discharge signal and determine the corresponding partial discharge spectrum based on the partial discharge signal.
[0097] Step S900: the multi-source fusion recognition model identifies the local discharge type corresponding to the local discharge signal according to the local discharge spectrum;
[0098] Step S1000: determining one of the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel as the positioning channel according to the partial discharge type and the positioning accuracy;
[0099] Step S1100: According to the time difference of the partial discharge signal reaching each sensor in the positioning channel, the partial discharge position of the transformer is located through the arrival time difference fingerprint library of the transformer digital twin model.
[0100] After the high-frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel identify the partial discharge spectrum corresponding to the partial discharge signal, the multi-source fusion recognition model will identify the partial discharge type corresponding to the partial discharge signal according to the partial discharge spectrum. Since the high-frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel have different sensitivities and positioning accuracy to the partial discharge signals generated by discharges of different types and locations, in order to maximize the positioning accuracy, it is necessary to select the monitoring channel for the partial discharge type after determining the partial discharge type for positioning. For example, assuming that the high-frequency monitoring channel has the highest positioning accuracy for the partial discharge type, the high-frequency monitoring channel is used as the positioning channel, and the partial discharge position of the transformer is located. After the positioning channel is selected, the partial discharge position of the transformer is located through the arrival time difference fingerprint library of the transformer digital twin model according to the time difference of the partial discharge signal reaching each sensor in the positioning channel. Since the arrival time difference fingerprint library records the partial discharge signals generated by different partial discharge positions, the time difference to different monitoring channels and the transmission path, after selecting the positioning channel, the time difference of the partial discharge signal reaching each sensor in the positioning channel is used to search the arrival time difference fingerprint library for the partial discharge position corresponding to the time difference.
[0101] Furthermore, the partial discharge monitoring method based on digital twin according to the embodiment of the present invention further includes the following steps:
[0102] Obtain the partial discharge spectrum, discharge amplitude, discharge pulse number and positioning results of the partial discharge signal;
[0103] The partial discharge spectrum, discharge amplitude, discharge pulse number and positioning results are displayed on the transformer digital twin model.
[0104] By intuitively displaying the partial discharge spectrum, discharge amplitude, number of discharge pulses and positioning results on the transformer digital twin model, operation and maintenance personnel can quickly understand the nature of the defects, the strength of the discharge and the corresponding components, and efficiently assess the defect risks.
[0105] The partial discharge monitoring method based on digital twin according to the embodiment of the present invention has the following characteristics:
[0106] (1) In view of the problem that the existing transformer partial discharge monitoring lacks a diagnostic analysis method for multi-source data fusion, the present invention proposes a transformer partial discharge monitoring and automatic positioning technology based on intelligent synchronous data collection of multiple sensors. By fusing the data of ultra-high frequency, high frequency, ultrasonic and other sensors, constructing a transformer digital twin model, and building a multi-sensor arrival time difference fingerprint library, it can realize electric-electric, acoustic-electric, and acoustic-acoustic joint synchronous monitoring and optimize the partial discharge positioning results.
[0107] 2) In order to solve the problem of the existing difficulty in locating partial discharge defects, a transformer digital twin model technology is proposed. According to the specific structure of the transformer, a transformer digital twin model is constructed, and an arrival time difference fingerprint library is established according to the signals emitted by possible partial discharge points inside the transformer collected by sensors installed at different positions. When there is partial discharge inside the transformer, the algorithm automatically calculates the arrival time difference of the signal received by each sensor based on the partial discharge pulse signal detected by multiple sensors, and searches the arrival time difference fingerprint library to obtain the location of the partial discharge point, which can reduce the cost of manual calculation and positioning error, and significantly improve the efficiency and accuracy of partial discharge monitoring.
[0108] 3) In order to solve the problem of unfriendly display of local discharge source positioning results of existing transformers, a monitoring data display technology based on the digital twin model of the transformer is proposed. Multiple local discharge amplitudes, frequencies, and spectrum data obtained by synchronous monitoring of multiple sensors and the positioning results obtained based on the arrival time difference fingerprint library are displayed in the three-dimensional digital twin model of the transformer to realize the positioning analysis of local discharge defects of the transformer.
[0109] On the other hand, an embodiment of the present invention further proposes a partial discharge monitoring device based on digital twin, the device comprising:
[0110] The processor may be implemented by a general-purpose central processing unit (CPU), 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 the present application;
[0111] The memory can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory can store an operating system and other applications. When the technical solution provided in the embodiments of this specification is implemented by software or firmware, the relevant program code is stored in the memory, and the processor is called to execute the partial discharge monitoring method based on digital twins in the embodiments of this application;
[0112] Input / output interface, used to realize information input and output;
[0113] Communication interface, used to realize communication interaction between this device and other devices. Communication can be realized through wired methods (such as USB, network cable, etc.) or wireless methods (such as mobile network, WIFI, Bluetooth, etc.);
[0114] The bus, which transfers information between the various components of the device (such as the processor, memory, input / output interfaces, and communication interfaces);
[0115] The processor, memory, input / output interface and communication interface are connected to each other through a bus inside the device.
[0116] On the other hand, an embodiment of the present invention further provides an electronic device, comprising the partial discharge monitoring device based on digital twin as described above.
[0117] On the other hand, an embodiment of the present invention further provides a storage medium, which is a computer-readable storage medium and stores a computer program. When the computer program is executed by a processor, the above-mentioned digital twin-based partial discharge monitoring method is implemented.
[0118] As a non-transient computer-readable storage medium, the memory can be used to store non-transient software programs and non-transient computer executable programs. In addition, the memory may include a high-speed random access memory, and may also include a non-transient memory, such as at least one disk storage device, a flash memory device, or other non-transient solid-state storage devices. In some embodiments, the memory may optionally include a memory remotely arranged relative to the processor, and these remote memories may be connected to the processor via a network. Examples of the above-mentioned networks include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof. The device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and are implemented to be located in one place, or may also be distributed to multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the present embodiment.
[0119] Although specific embodiments are described herein, those of ordinary skill in the art will recognize that many other modifications or alternative embodiments are also within the scope of the present disclosure. For example, any of the functions and / or processing capabilities described in conjunction with a particular device or component may be performed by any other device or component. In addition, although various exemplary implementations and architectures have been described according to embodiments of the present disclosure, those of ordinary skill in the art will recognize that many other modifications to the exemplary implementations and architectures described herein are also within the scope of the present disclosure.
[0120] Some aspects of the present disclosure are described above with reference to the block diagram and flow chart of the system, method, system and / or computer program product according to the exemplary embodiments.It should be understood that the combination of one or more blocks in the block diagram and the flow chart and the blocks in the block diagram and the flow chart can be realized by executing computer executable program instructions respectively.Equally, according to some embodiments, some blocks in the block diagram and the flow chart may not need to be executed in the order shown, or may not need to be executed in full.In addition, additional components and / or operations beyond those components and / or operations shown in the blocks in the block diagram and the flow chart may be present in certain embodiments.
[0121] Therefore, the blocks in the block diagrams and flow charts support the combination of devices for performing the specified functions, the combination of elements or steps for performing the specified functions, and the program instruction devices for performing the specified functions. It should also be understood that each block in the block diagrams and flow charts and the combination of blocks in the block diagrams and flow charts can be implemented by a special-purpose hardware computer system or a combination of special-purpose hardware and computer instructions that performs a specific function, element or step.
[0122] The program modules, applications, etc. described herein may include one or more software components, including, for example, software objects, methods, data structures, etc. Each such software component may include computer-executable instructions that, in response to execution, cause at least a portion of the functionality described herein (e.g., one or more operations of the illustrative methods described herein) to be performed.
[0123] Software components can be encoded with any of various programming languages. An exemplary programming language can be a low-level programming language, such as an assembly language associated with a specific hardware architecture and / or an operating system platform. The software component comprising assembly language instructions may need to be converted to executable machine code by an assembler before being executed by hardware architecture and / or platform. Another exemplary programming language can be a higher-level programming language, which can be transplanted across multiple architectures. The software component comprising a higher-level programming language may need to be converted to an intermediate representation by an interpreter or a compiler before execution. Other examples of programming languages include but are not limited to macro languages, shells or command languages, job control languages, scripting languages, database queries or search languages or report writing languages. In one or more exemplary embodiments, the software component comprising the instruction of one of the above-mentioned programming language examples can be directly executed by an operating system or other software components, without first being converted into another form.
[0124] Software components may be stored as files or other data storage structures. Software components of similar type or related functions may be stored together, such as in a specific directory, folder, or library. Software components may be static (e.g., preset or fixed) or dynamic (e.g., created or modified at execution time).
[0125] The embodiments of the present invention are described in detail above with reference to the accompanying drawings, but the present invention is not limited to the above embodiments, and various changes can be made within the knowledge scope of ordinary technicians in the relevant technical field without departing from the purpose of the present invention.
Claims
1. A partial discharge monitoring method based on digital twins, It is characterized in that Applied to a transformer, the transformer is provided with a plurality of sensors, the plurality of sensors include three types of high-frequency sensors, ultra-high-frequency sensors and ultrasonic sensors, a plurality of the high-frequency sensors, a plurality of the ultra-high-frequency sensors and a plurality of the ultrasonic sensors respectively form a high-frequency monitoring channel, an ultra-high-frequency monitoring channel and an ultrasonic monitoring channel, the method comprises the following steps: According to the internal and external structure of the transformer and the installation position of each sensor, a three-dimensional display model of the transformer is established; The three-dimensional transformer display model is spatially digitized to form a three-dimensional transformer digital model; When each monitoring point inside the transformer is used as a local discharge source, the time difference of the local discharge signal reaching each sensor is obtained, and according to the time difference, an arrival time difference fingerprint library corresponding to the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel is established respectively; Establishing a transformer digital twin model according to the arrival time difference fingerprint library and the transformer three-dimensional digital model; Performing time synchronization on the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel; A multi-source fusion recognition model is established according to the high-frequency sensor, the ultra-high-frequency sensor and the ultrasonic sensor; the multi-source fusion recognition model is used to identify the corresponding partial discharge type according to the partial discharge spectrum; Determining the positioning accuracy of the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel for different partial discharge types; When the high frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel detect the presence of a partial discharge signal in the transformer, identifying a partial discharge spectrum corresponding to the partial discharge signal; The multi-source fusion recognition model identifies the local discharge type corresponding to the local discharge signal according to the local discharge spectrum; According to the partial discharge type and the positioning accuracy, determining one of the high-frequency monitoring channel, the ultra-high-frequency monitoring channel and the ultrasonic monitoring channel as a positioning channel; According to the time difference between the partial discharge signal and each sensor in the positioning channel, the partial discharge position of the transformer is located through the arrival time difference fingerprint library of the transformer digital twin model.
2. According to the partial discharge monitoring method based on digital twins according to claim 1, It is characterized in that The step of spatially digitizing the three-dimensional display model of the transformer to form a three-dimensional digital model of the transformer includes: The smallest circumscribed cuboid of the three-dimensional display model of the transformer is defined as a scene; the bottom surface of the scene coincides with the ground where the transformer is located, the outside of the transformer is the external space of the scene, and the inside of the transformer is the internal space of the scene; Taking a vertex of the scene as an origin, dividing the scene into a plurality of cubes at a preset resolution on the XYZ coordinate axes; According to the serial number of the cube where any point of the scene is located, the coordinates of each point are quantized into digital coordinates, thereby forming the three-dimensional digital model of the transformer.
3. According to the partial discharge monitoring method based on digital twins according to claim 1, It is characterized in that The step of obtaining the time difference of the partial discharge signal reaching each sensor when each monitoring point inside the transformer is used as a partial discharge source, and establishing an arrival time difference fingerprint library corresponding to the high-frequency monitoring channel, the ultra-high frequency monitoring channel and the ultrasonic monitoring channel respectively according to the time difference, comprises: A partial discharge signal simulator is used to generate a partial discharge monitoring signal at each monitoring point inside the transformer as a partial discharge source; Calculating the shortest transmission path for transmitting the partial discharge monitoring signal to each of the sensors through a path planning algorithm; Obtaining the propagation speed of the partial discharge monitoring signal, and calculating the arrival time vector of each of the monitoring points according to the shortest transmission path and the propagation speed; The arrival time difference fingerprint library is established according to the arrival time vector.
4. According to the partial discharge monitoring method based on digital twins according to claim 3, It is characterized in that The calculating the shortest transmission path for transmitting the partial discharge monitoring signal to each of the sensors through a path planning algorithm includes: If the partial discharge monitoring signal is an ultrasonic signal, the shortest transmission path is a straight line transmission path between the partial discharge source and each of the ultrasonic sensors; If the partial discharge signal is an electromagnetic wave and there is an obstacle between the partial discharge source and the sensor, the shortest transmission path is the transmission path of the shortest distance from the partial discharge signal from the partial discharge source to the obstacle and after being reflected or diffracted by the obstacle to each of the ultra-high frequency sensors.
5. The partial discharge monitoring method based on digital twin according to claim 1, It is characterized in that The step of time synchronizing the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel comprises: Using synchronous sampling technology, a synchronous clock is assigned to the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel; the accuracy of the synchronous clock is not less than nanosecond level; Through the synchronous clock, the signal waveforms detected by the high-frequency monitoring channel, the ultra-high-frequency monitoring channel, and the ultrasonic monitoring channel are provided with synchronized timestamps.
6. The partial discharge monitoring method based on digital twin according to claim 1, It is characterized in that The step of establishing a multi-source fusion recognition model according to the high-frequency sensor, the ultra-high-frequency sensor and the ultrasonic sensor comprises: Identify partial discharge spectra of various partial discharge types by using the high frequency sensor, the ultra-high frequency sensor and the ultrasonic sensor to obtain data features corresponding to different partial discharge types; According to the data features, a deep learning network is trained to form the multi-source fusion recognition model.
7. The partial discharge monitoring method based on digital twin according to claim 1, It is characterized in that The method further comprises the following steps: Obtaining a partial discharge spectrum, a discharge amplitude, a discharge pulse number and a positioning result of the partial discharge signal; The partial discharge spectrum, the discharge amplitude, the number of discharge pulses and the positioning result are displayed on the transformer digital twin model.
8. A partial discharge monitoring device based on digital twins, It is characterized in that It includes at least one control processor and a memory for communicating with the at least one control processor; the memory stores instructions that can be executed by the at least one control processor, and the instructions are executed by the at least one control processor so that the at least one control processor can execute the local discharge monitoring method based on digital twins as described in any one of claims 1 to 7.
9. An electronic device, It is characterized in that Including the local discharge monitoring device based on digital twin as described in claim 8.
10. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores computer-executable instructions, and the computer-executable instructions are used to enable a computer to execute the partial discharge monitoring method based on digital twins as described in any one of claims 1 to 7.
