Partial discharge acoustic imaging detection positioning method and system, medium and product

Abstract

The invention discloses a partial discharge acoustic imaging detection positioning method and system, a medium and a product, and relates to the field of electrical engineering, and the method comprises the steps: obtaining a sound signal collected by a microphone array, and a video image collected by a camera; detecting an energy accumulation value of a plurality of sound sources in the sound signal within a preset duration; marking the sound source with the energy accumulation value exceeding a preset threshold value as a partial discharge sound source; determining position coordinates of a partial discharge sound source; according to sound characteristics of the partial discharge sound source, the discharge severity is evaluated, and the sound characteristics at least comprise frequency characteristics and amplitude distribution; mapping the position coordinates of the partial discharge sound source to the corresponding position of the video image to obtain a partial discharge sound imaging positioning map, and displaying the discharge severity of the partial discharge sound source in the partial discharge sound imaging positioning map. By implementing the method, the accuracy and precision of partial discharge acoustic imaging detection and positioning can be improved.

Description

Technical Field

[0001] The present application relates to the field of electrical engineering, and in particular to a method, system, medium and product for detecting and locating partial discharge acoustic imaging. Background Art

[0002] In the operation and maintenance of power systems, timely and accurate detection and location of partial discharge (PD) is particularly critical. Partial discharge usually indicates that the insulation materials of electrical equipment may be degrading or damaged. If this phenomenon is not discovered and handled in time, it may cause equipment failure or even power accidents. Detection of partial discharge can not only help maintenance personnel to carry out timely repairs, but also significantly extend the service life of electrical equipment and ensure the safe and stable operation of the power system.

[0003] Existing partial discharge detection technology mainly relies on electroacoustic measurement technology, which collects the acoustic wave signals generated by partial discharge through specific sensors (such as microphones) and then identifies the discharge event through acoustic signal analysis.

[0004] Although existing technologies can detect and locate partial discharge to some extent, it is often difficult to accurately assess the severity of the discharge and precisely locate the discharge point based solely on spectral analysis of the sound signal. This is especially true in complex or densely populated power systems, where single sound analysis is insufficient to provide sufficient positioning accuracy. Summary of the invention

[0005] The present application provides a local discharge acoustic imaging detection and positioning method, system, medium and product for improving the accuracy and precision of local discharge acoustic imaging detection and positioning.

[0006] In a first aspect, the present application provides a local discharge acoustic imaging detection and positioning method, which is applied to a detection and positioning system, and the method includes: obtaining a sound signal collected by a microphone array and a video image collected by a camera; detecting the energy accumulation value of multiple sound sources in the sound signal within a preset time length; marking the sound source whose energy accumulation value exceeds a preset threshold as a local discharge sound source; determining the position coordinates of the local discharge sound source; evaluating the discharge severity based on the sound characteristics of the local discharge sound source, the sound characteristics at least including frequency characteristics and amplitude distribution; mapping the position coordinates of the local discharge sound source to the corresponding position of the video image to obtain a local discharge acoustic imaging positioning map, and displaying the discharge severity of the local discharge sound source in the local discharge acoustic imaging positioning map.

[0007] By adopting the above technical solutions, the detection and positioning system realizes more comprehensive and accurate partial discharge detection and positioning by combining sound signals and video images. First, by analyzing the energy accumulation values ​​of multiple sound sources in the sound signal, the sound sources whose energy accumulation values ​​exceed the preset threshold are marked as partial discharge sound sources, so that the partial discharge sound sources that need attention can be effectively identified, reducing the possibility of misjudgment. Secondly, the detection and positioning system provides a clear direction for subsequent maintenance and processing by accurately determining the position coordinates of the partial discharge sound source. Finally, the position coordinates of the partial discharge sound source are combined with the video image to form an intuitive partial discharge acoustic imaging positioning map, which greatly improves the visualization and practicality of the detection results. This multi-dimensional, multi-data source analysis method significantly improves the accuracy, comprehensiveness and operability of partial discharge detection.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the detecting the energy cumulative values ​​of multiple sound sources in the sound signal within a preset time length specifically includes: performing time-frequency analysis on the sound signal to obtain a time-frequency spectrum diagram, the horizontal axis of the time-frequency spectrum diagram representing time, and the vertical axis representing frequency components, the time-frequency spectrum diagram including multiple frequency components, the multiple frequency components corresponding to the multiple sound sources, and different frequency components corresponding to different energy values ​​at different time points; based on the accumulation along the time axis of the time-frequency spectrum diagram, determining the energy cumulative values ​​of the multiple sound sources within the preset time length.

[0009] By adopting the above technical solution, a more in-depth and detailed analysis of the sound signal is achieved through time-frequency analysis technology. The generation of the time-frequency spectrum makes it possible to simultaneously observe the changes in the sound signal in two dimensions, time and frequency components. Since different frequency components correspond to different energy values ​​at different time points, and the frequency components correspond to the sound source, the energy accumulation values ​​of different frequency components within the preset time length can be calculated, which helps to identify and analyze the sound source of partial discharge and improve the stability and reliability of detection.

[0010] In combination with some embodiments of the first aspect, in some embodiments, determining the position coordinates of the local discharge sound source specifically includes: obtaining the arrival time difference of the sound signal corresponding to the local discharge sound source received by each microphone in the microphone array; establishing a hyperplane equation group based on the arrival time difference; and using the least squares method to solve the hyperplane equation group to obtain the three-dimensional coordinate estimate of the local discharge sound source as the position coordinates of the local discharge sound source.

[0011] By adopting the above technical solution, by analyzing the arrival time difference of the sound signal corresponding to the local discharge sound source received by each microphone in the microphone array, and then establishing a hyperplane equation group and solving it using the least squares method, the three-dimensional coordinate estimation value of the local discharge sound source can be obtained, thereby determining the position coordinates of the local discharge sound source, and improving the accuracy of localizing the local discharge sound source. Accurate three-dimensional positioning can not only help maintenance personnel quickly find the discharge point, but also provide important information for evaluating the potential impact of the discharge on surrounding equipment.

[0012] In combination with some embodiments of the first aspect, in some embodiments, the discharge severity is evaluated based on the sound characteristics of the local discharge sound source, and the sound characteristics at least include frequency characteristics and amplitude distribution, specifically including: extracting the frequency characteristics and amplitude distribution of the local discharge sound source; inputting the frequency characteristics and the amplitude distribution into a preset discharge severity evaluation model to obtain the discharge severity of the local discharge sound source.

[0013] By adopting the above technical solution, the frequency characteristics and amplitude distribution of the local discharge sound source are analyzed to evaluate the severity of the discharge. First of all, the frequency characteristics and amplitude distribution contain rich discharge information, which can reflect important characteristics such as the type, intensity and continuity of the discharge. By inputting these characteristics into the preset discharge severity assessment model, a more objective and accurate assessment result can be obtained. This assessment method based on acoustic characteristics can not only qualitatively judge the existence of discharge, but also quantitatively assess its discharge severity, providing an important basis for equipment maintenance decisions. In addition, this method can realize real-time evaluation, so as to timely discover the changing trend of discharge severity, improve the accuracy and early warning capability of power equipment status monitoring, and extend equipment life and reduce maintenance costs through preventive maintenance and timely intervention.

[0014] In combination with some embodiments of the first aspect, in some embodiments, after the step of mapping the position coordinate value of the local discharge sound source to the corresponding position of the video image to obtain a local discharge acoustic imaging localization map, and displaying the discharge severity of the local discharge sound source in the local discharge acoustic imaging localization map, the method also includes: if the discharge severity of the local discharge sound source exceeds a preset threshold, the local discharge acoustic imaging localization map is sent to the user.

[0015] By adopting the above technical solution, by setting a preset degree threshold and sending the partial discharge acoustic imaging location map to the user when the discharge severity of the partial discharge sound source exceeds the preset degree threshold, an intelligent abnormal warning function is realized. The partial discharge acoustic imaging location map shows all the partial discharge sound sources that deserve attention, avoiding the interference of a large number of low-risk events to maintenance personnel and improving work efficiency. Sending the partial discharge acoustic imaging location map to the user in a timely manner can help maintenance personnel quickly understand the problem, make accurate judgments and respond in time. This visual information transmission method is intuitive and clear, which helps to reduce misunderstandings and delays in the information transmission process and improve the safety, reliability and maintenance efficiency of the power system.

[0016] In combination with some embodiments of the first aspect, in some embodiments, before the step of inputting the frequency characteristics and the amplitude distribution into a preset discharge severity assessment model to obtain the discharge severity of the local discharge sound source, the method also includes: obtaining the frequency characteristics, amplitude distribution and corresponding discharge severity of multiple sound sources; marking the frequency characteristics and the amplitude distribution as input characteristics, and marking the discharge severity as output characteristics; training the preset model using the input characteristics and the output characteristics; and obtaining the discharge severity assessment model when the accuracy of the preset model exceeds a preset accuracy threshold.

[0017] By adopting the above technical solution, a large amount of sample data is obtained and machine learning training is performed to build a high-precision discharge severity assessment model. Taking frequency characteristics and amplitude distribution as input features and discharge severity as output features, the preset model can establish a complex nonlinear relationship between acoustic characteristics and discharge severity, which is more accurate and reliable than traditional linear assessment methods. The availability of the model is determined by setting a preset accuracy threshold, which ensures the high quality and reliability of the model. The discharge severity assessment model can learn various complex discharge patterns and sound characteristics, greatly improving the accuracy and applicability of the assessment.

[0018] In combination with some embodiments of the first aspect, in some embodiments, after the step of determining the position coordinates of the local discharge sound source, the method further includes: if the position coordinates of the local discharge sound source are in a preset first area, initiating emergency power outage measures; if the position coordinates of the local discharge sound source are in a preset second area, triggering an alarm condition, which is used to attract user attention, and the danger factor of the preset first area is higher than that of the preset second area.

[0019] By adopting the above technical solution, the location coordinates of the partial discharge sound source are compared with the preset area, and corresponding safety measures are taken to realize intelligent risk management. By pre-defining areas with different risk factors, the detection and positioning system can automatically determine the risk level according to the location coordinates of the partial discharge sound source, greatly improving the efficiency and accuracy of risk assessment. Emergency power outage measures are taken for preset areas with high risk factors (preset first area), which reflects the rapid response capability of the detection and positioning system and can effectively prevent the occurrence of serious accidents. For preset areas with low risk factors (preset second area), triggering alarm conditions can not only attract the attention of users, but also avoid unnecessary power outages, reflecting the flexibility and intelligence of the detection and positioning system. This hierarchical response mechanism can not only maximize the safety of the power system, but also minimize unnecessary power outages while ensuring safety, balancing safety and economy.

[0020] In a second aspect, an embodiment of the present application provides a detection and positioning system, which includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the detection and positioning system to perform the method described in the first aspect and any possible implementation method of the first aspect.

[0021] In a third aspect, an embodiment of the present application provides a computer program product comprising instructions, and when the above-mentioned computer program product runs on a detection and positioning system, the above-mentioned detection and positioning system executes the method described in the first aspect and any possible implementation method of the first aspect.

[0022] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, comprising instructions. When the instructions are executed on a detection and positioning system, the detection and positioning system executes the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It is understandable that the detection and positioning system provided in the second aspect, the computer program product provided in the third aspect, and the computer storage medium provided in the fourth aspect are all used to execute the method provided in the embodiment of the present application. Therefore, the beneficial effects that can be achieved can refer to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] One or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages: 1. Due to the use of multi-dimensional data fusion and intelligent analysis technology, the present invention can comprehensively and accurately detect and locate partial discharge, effectively solving the problems of insufficient detection accuracy and high misjudgment rate caused by a single data source in the prior art, thereby significantly improving the safe operation of the power system. The present invention constructs a multi-dimensional, high-precision detection and positioning system by combining sound signal analysis, video image processing and machine learning algorithms. The time-frequency analysis of sound signals can capture weak discharge characteristics, the real-time positioning of video images provides an intuitive spatial reference for the discharge source, and the machine learning algorithm realizes an intelligent assessment of the severity of the discharge. This fusion of multi-source data not only greatly improves the accuracy and reliability of detection, but also can adapt to complex power equipment environments, providing strong technical support for preventive maintenance and fault diagnosis of power systems, and significantly improving the safety and reliability of power systems.

[0025] 2. Due to the adoption of an intelligent assessment model based on acoustic features and an adaptive early warning mechanism, the present invention can accurately assess the severity of discharge and issue an early warning in a timely manner, effectively solving the problems of inaccurate judgment of the degree of discharge danger and untimely early warning in the prior art, thereby realizing early prevention and intelligent management of power system failures. The present invention establishes a high-precision discharge severity assessment model by analyzing the frequency characteristics and amplitude distribution of local discharge sound sources and combining machine learning algorithms. The discharge severity assessment model can not only accurately assess the current discharge status, but also predict its development trend. At the same time, the present invention also sets an adaptive early warning threshold, which can automatically trigger corresponding early warnings and treatment measures according to the risk level of different areas. This intelligent assessment and early warning mechanism greatly improves the safety management level of the power system, can timely detect potential risks before a fault occurs, and provide maintenance personnel with sufficient response time, effectively reducing the probability of major accidents, and also optimizing the allocation efficiency of maintenance resources.

[0026] 3. Due to the use of high-precision three-dimensional positioning technology and visual acoustic imaging methods, the present invention can accurately locate the discharge source and intuitively present the detection results, effectively solving the problems of inaccurate positioning and difficult to interpret detection results in the prior art, thereby realizing efficient and precise maintenance of power equipment. The present invention analyzes the time difference of the sound signal received by the microphone array and uses the least squares method to solve the hyperplane equation group to achieve high-precision three-dimensional positioning of the discharge source. This positioning method is not only suitable for a single device, but also can maintain high accuracy in a complex multi-device environment. At the same time, the present invention innovatively combines the positioning results with real-time video images to generate an intuitive local discharge acoustic imaging positioning map, and annotates the discharge severity in the local discharge acoustic imaging positioning map. This visual presentation method enables maintenance personnel to quickly and accurately identify the problem, greatly improving the efficiency of fault diagnosis and maintenance. In addition, this method of precise positioning and visual presentation also provides an important basis for preventive maintenance of equipment, which helps to formulate more accurate and targeted maintenance strategies, thereby extending the life of equipment, reducing maintenance costs, and improving the overall operating efficiency of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a flow chart of a method for detecting and locating partial discharge acoustic imaging in an embodiment of the present application; Figure 2 is another flow chart of the local discharge acoustic imaging detection and positioning method in the embodiment of the present application; Figure 3 It is a schematic diagram of the structure of a physical device of the detection and positioning system in an embodiment of the present application. DETAILED DESCRIPTION

[0028] The terms used in the following embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to be used as limitations to the present application. As used in the specification of the present application, the singular expressions "one", "a kind of", "above", "the" and "this" are intended to also include plural expressions, unless there is a clear indication to the contrary in the context. It should also be understood that the term "and / or" used in the present application refers to any or all possible combinations comprising one or more of the listed items.

[0029] In the following, the terms "first" and "second" are used for descriptive purposes only and are not to be understood as suggesting or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, unless otherwise specified, "plurality" means two or more.

[0030] The following is a description of the process of the method provided by this implementation. Figure 1 , which is a flow chart of a local discharge acoustic imaging detection and positioning method in an embodiment of the present application.

[0031] S101, obtaining sound signals collected by a microphone array and video images collected by a camera; Among them, microphone array refers to a sound collection device composed of multiple microphones arranged in a specific manner, which is used to collect sound signals from multiple directions. Sound signal refers to the electrical signal converted from the sound waves captured by the microphone array, which contains information about various sound sources in the detected area. Camera refers to an optoelectronic device used to capture video images. Video image refers to a dynamic picture composed of a series of static images continuously taken by the camera, which is used to represent real-time visual information of the detected area.

[0032] The detection and positioning system performs this step when starting partial discharge detection. Specifically, the detection and positioning system first activates the microphone array connected to it so that it starts collecting sound signals in the detected area. These sound signals may include background noise, equipment operation sounds, and potential partial discharge sounds. At the same time, the detection and positioning system also starts the camera and starts collecting video images of the detected area. The detection and positioning system will receive and store these sound signals and video images in real time to prepare for subsequent analysis and processing. The microphone array usually uses at least 4 microphones to ensure three-dimensional spatial positioning. The resolution and frame rate of the camera should be high enough to ensure that the details of the rapidly changing scene can be captured.

[0033] S102, detecting the energy accumulation value of multiple sound sources in the sound signal within a preset time length; The sound source refers to the object or location that generates the sound, which may include normally operating equipment, background noise in the detected area, and possible local discharge points. The preset duration refers to a period of time preset by the detection and positioning system for analyzing sound signals. The energy accumulation value refers to the sum of the energy of the sound signal generated by a sound source within the preset duration, which is used to indicate the sound intensity of the sound source within a certain period of time.

[0034] The detection and positioning system performs this step immediately after acquiring the sound signal. Specifically, the detection and positioning system first preprocesses the acquired sound signal, including denoising, filtering and other operations to improve the signal quality. Then, the detection and positioning system uses time-frequency analysis technology (such as short-time Fourier transform) to convert the sound signal into a time-frequency spectrum. In the time-frequency spectrum, the detection and positioning system identifies different frequency components, each of which corresponds to a sound source. For each identified sound source, the detection and positioning system calculates its energy value within a preset time length (usually a few seconds to tens of seconds), and accumulates it to obtain an energy accumulation value. This process is performed simultaneously for all identified sound sources for subsequent comparison and analysis. The detection and positioning system may use parallel computing technology to increase the processing speed to ensure that the energy accumulation value calculation of a large number of sound sources can be completed in real time.

[0035] Optionally, in general, detecting the energy accumulation values ​​of multiple sound sources in the sound signal within a preset time length can be achieved in the following manner: performing time-frequency analysis on the sound signal to obtain a time-frequency spectrum diagram, wherein the horizontal axis of the time-frequency spectrum diagram represents time, and the vertical axis represents frequency components, the time-frequency spectrum diagram includes multiple frequency components, and the multiple frequency components correspond to the multiple sound sources, and different frequency components correspond to different energy values ​​at different time points; based on the accumulation along the time axis of the time-frequency spectrum diagram, determining the energy accumulation values ​​of the multiple sound sources within the preset time length.

[0036] S103, marking the sound source whose energy cumulative value exceeds a preset threshold as a partial discharge sound source; The preset threshold refers to an energy accumulation value standard preset by the detection and positioning system, which is used to distinguish between normal sound sources and possible partial discharge sound sources. The partial discharge sound source indicates the location or equipment that is determined by the detection and positioning system as a possible partial discharge, and is the object that needs to be focused on and analyzed. Marking refers to the process of the detection and positioning system specially marking the partial discharge sound source in the internal data structure for subsequent priority processing and analysis.

[0037] The detection and positioning system performs this step immediately after completing the calculation of the energy accumulation values ​​of all sound sources. Specifically, the detection and positioning system first reads the preset threshold. The setting of the preset threshold is usually based on a large amount of historical data and expert experience, and may be adjusted according to different equipment types and environmental conditions. Then, the detection and positioning system compares the energy accumulation value of each sound source with the preset threshold one by one. If the energy accumulation value of a sound source exceeds the preset threshold, the detection and positioning system will mark it as a potential partial discharge sound source. This marking process may include setting a special flag bit in the internal data structure of the detection and positioning system, or storing the information of these partial discharge sound sources in a special data list. In order to improve accuracy, the detection and positioning system may also consider other factors, such as the frequency characteristics and duration of the sound source, to comprehensively determine whether to mark it as a partial discharge sound source, which is not limited here.

[0038] S104, determining the position coordinates of the local discharge sound source; The position coordinates refer to the values ​​used to indicate the precise position of the partial discharge sound source in three-dimensional space, usually including the coordinate values ​​in the three directions of x, y, and z. The partial discharge sound source indicates the location or equipment determined by the detection and positioning system as a possible location for partial discharge.

[0039] The detection and positioning system performs this step immediately after marking the local discharge sound source. Specifically, the detection and positioning system uses acoustic positioning technology to determine the precise location of the local discharge sound source. First, the detection and positioning system analyzes the time difference between the sound signals corresponding to the local discharge sound source received by different microphones in the microphone array, and then uses triangulation or time difference positioning algorithm to calculate the spatial coordinates of the local discharge sound source. In this process, it may also be necessary to consider the propagation speed of the sound signal in different media, as well as the possible reflection and refraction effects, so as to improve the positioning accuracy.

[0040] Optionally, in general, the position coordinates of the local discharge sound source can be determined by: obtaining the arrival time difference of the sound signal corresponding to the local discharge sound source received by each microphone in the microphone array; establishing a hyperplane equation group based on the arrival time difference; using the least squares method to solve the hyperplane equation group, and obtaining the three-dimensional coordinate estimate of the local discharge sound source as the position coordinates of the local discharge sound source.

[0041] Specifically, the detection and positioning system uses the time difference positioning method to calculate the arrival time difference of the sound signal to different microphones. Based on these arrival time differences, the detection and positioning system establishes a set of hyperplane equations. Then, the detection and positioning system uses the least squares method to solve this set of equations to obtain the three-dimensional coordinate estimate of the local discharge sound source. In order to improve the positioning accuracy, the detection and positioning system may perform multiple sampling and calculations and take the average value as the final result. In addition, the detection and positioning system may also combine the video images collected by the camera and use image processing technology for auxiliary positioning to further improve the positioning accuracy. Finally, the detection and positioning system stores the obtained position coordinates of the local discharge sound source in an internal data structure to prepare for subsequent visualization and analysis.

[0042] S105, evaluating the severity of the discharge according to the sound characteristics of the local discharge sound source, where the sound characteristics at least include frequency characteristics and amplitude distribution; Among them, sound characteristics refer to the unique properties of the sound generated by the partial discharge sound source, including at least frequency characteristics and amplitude distribution. Frequency characteristics represent the energy distribution of the partial discharge sound source at different frequencies, usually obtained through spectrum analysis; amplitude distribution refers to the amplitude statistical parameters of the sound signal corresponding to the partial discharge sound source, which is used to represent the change pattern of signal strength; discharge severity indicates the degree of damage caused by partial discharge to the equipment.

[0043] The detection and positioning system performs this step immediately after marking the local discharge sound source. Specifically, the detection and positioning system performs time domain analysis and frequency domain analysis on the sound signal corresponding to the collected local discharge sound source. In the frequency domain analysis, the signal spectrum is obtained by fast Fourier transform (FFT) or wavelet transform, and the distribution of the main frequency components is observed. Under normal circumstances, the frequency range of local discharge is usually between tens of kHz and several MHz. The higher the frequency, the more intense the discharge. At the same time, the amplitude distribution of the sound signal corresponding to the local discharge sound source is analyzed, including the calculation of amplitude statistical parameters such as the root mean square value and the peak factor. These amplitude statistical parameters can reflect the discharge intensity and stability. In addition, the repetition rate of the discharge, that is, the number of times the discharge occurs per unit time, needs to be considered. The higher the repetition rate, the more severe the discharge. By comparing these analysis results with the pre-established evaluation criteria, a quantitative or qualitative evaluation of the severity of the discharge can be given.

[0044] S106, mapping the position coordinates of the local discharge sound source to the corresponding position of the video image to obtain a local discharge sound imaging map, and displaying the discharge severity of the local discharge sound source in the local discharge sound imaging map.

[0045] Among them, the local discharge acoustic imaging localization map refers to a visual image formed by superimposing the location information of the local discharge sound source on the video image. The detection and positioning system performs this step immediately after completing the discharge severity assessment. Specifically, the detection and positioning system first extracts the frame image at the current moment from the stored video image. Then, the detection and positioning system converts the position coordinates of the local discharge sound source previously determined into two-dimensional image coordinates. The detection and positioning system draws a striking mark (such as a colored circle or arrow) at the corresponding position on the video image to indicate the location of the local discharge sound source. Next, the detection and positioning system selects appropriate colors or graphics (such as red for severe, yellow for moderate, and green for mild) to mark the discharge severity based on the previously assessed discharge severity. The detection and positioning system may also add text descriptions to the image to describe in detail the location of the local discharge sound source and the discharge severity. To enhance readability, the detection and positioning system may add a coordinate grid or scale to the video image. Finally, the detection and positioning system saves the processed image as a new local discharge acoustic imaging localization map. This intuitive visual representation method can help technicians quickly locate problems and assess risks, so as to take appropriate maintenance measures.

[0046] By adopting the above technical solutions, the detection and positioning system realizes more comprehensive and accurate partial discharge detection and positioning by combining sound signals and video images. First, by analyzing the energy accumulation values ​​of multiple sound sources in the sound signal, the sound sources whose energy accumulation values ​​exceed the preset threshold are marked as partial discharge sound sources, so that the partial discharge sound sources that need attention can be effectively identified, reducing the possibility of misjudgment. Secondly, the detection and positioning system provides a clear direction for subsequent maintenance and processing by accurately determining the position coordinates of the partial discharge sound source. Finally, the position coordinates of the partial discharge sound source are combined with the video image to form an intuitive partial discharge acoustic imaging positioning map, which greatly improves the visualization and practicality of the detection results. This multi-dimensional, multi-data source analysis method significantly improves the accuracy, comprehensiveness and operability of partial discharge detection.

[0047] The following is a more detailed description of the process of the method provided by this implementation. Figure 2 , is another flow chart of the local discharge acoustic imaging detection and positioning method in an embodiment of the present application.

[0048] S201, obtaining sound signals collected by a microphone array and video images collected by a camera; For details, please refer to step S101, which will not be described in detail here.

[0049] S202, detecting the energy accumulation value of multiple sound sources in the sound signal within a preset time length; For details, please refer to step S102, which will not be described in detail here.

[0050] S203, marking the sound source whose energy cumulative value exceeds a preset threshold as a partial discharge sound source; For details, please refer to step S103, which will not be described in detail here.

[0051] S204, determining the position coordinates of the local discharge sound source; For details, please refer to step S104, which will not be described in detail here.

[0052] S205, if the location coordinates of the partial discharge sound source are in a preset first area, initiating emergency power outage measures; The preset first area refers to an area with a high risk factor predefined by the detection and positioning system, which usually includes key equipment or locations prone to serious failures. The position coordinates represent the precise location of the partial discharge sound source in three-dimensional space. Emergency power outage measures refer to the safe operation of immediately cutting off the power supply of related equipment or areas when serious danger is detected.

[0053] The detection and positioning system performs this step immediately after determining the position coordinates of the local discharge sound source. Specifically, the detection and positioning system first compares the obtained position coordinates of the local discharge sound source with the boundary data of the preset first area, which may involve complex spatial calculations, such as the determination algorithm of whether a point is within a polygon. If the detection and positioning system determines that the position coordinates do fall within the preset first area, the emergency power outage procedure is immediately triggered. This procedure may include the following steps: First, the detection and positioning system sends a high-priority alarm to the central control room and activates the sound and light alarm device at the same time. Then, the detection and positioning system will send a cut-off command to the relevant circuit breakers to quickly cut off the power supply of all equipment in the preset first area. At the same time, the detection and positioning system may start the backup power supply to ensure the continuous operation of key safety systems and monitoring equipment.

[0054] S206: If the location coordinates of the partial discharge sound source are in the preset second area, triggering an alarm condition, the alarm condition is used to draw the user's attention, and the risk factor of the preset first area is higher than that of the preset second area; The preset second area refers to an area with a low risk factor predefined by the detection and positioning system, which usually includes secondary equipment or locations with low potential failure risks. The alarm condition refers to the trigger mechanism for the detection and positioning system to issue a warning signal. The user refers to the staff responsible for monitoring and maintaining the power system.

[0055] The detection and positioning system performs this step immediately after determining the position coordinates of the local discharge sound source. Specifically, the detection and positioning system first compares the position coordinates of the local discharge sound source with the boundary data of the preset second area. If the position coordinates fall within the preset second area, the detection and positioning system will trigger an alarm condition, that is, determine the discharge severity of the local discharge sound source, and map the position coordinates of the local discharge sound source to the corresponding position of the video image to obtain a local discharge acoustic imaging positioning map, and use the local discharge acoustic imaging positioning map to remind relevant maintenance personnel and management personnel.

[0056] S207, extracting the frequency characteristics and amplitude distribution of the local discharge sound source; For details, please refer to step S105, which will not be described in detail here.

[0057] S208, obtaining frequency characteristics, amplitude distribution and corresponding discharge severity of multiple sound sources; The detection and positioning system obtains multiple sound sources from historical data. For each sound source, the detection and positioning system repeatedly performs a frequency feature and amplitude distribution extraction process similar to S105. The discharge severity corresponding to each sound source can be obtained through historical maintenance records or expert evaluation, which is not limited here. Thus, the detection and positioning system obtains the frequency features, amplitude distribution and corresponding discharge severity of multiple sound sources.

[0058] S209, marking the frequency feature and the amplitude distribution as input features, and marking the discharge severity as output features; The detection and positioning system stores the collected frequency characteristics, amplitude distribution and corresponding discharge severity of the sound source into the data set D. The format of each data is (frequency characteristics, amplitude distribution, discharge severity). Among them, frequency characteristics and amplitude distribution are the input features of model training, and discharge severity is the output feature of model training. The detection and positioning system performs data preprocessing on the data set D and deletes the missing data and abnormal data in the data set D.

[0059] S210, using the input feature and the output feature to train a preset model; The detection and positioning system builds a LSTM-based recurrent neural network, which includes an input layer, two LSTM hidden layers, a fully connected layer, and an output layer. The input layer inputs frequency characteristics and amplitude distribution, the number of hidden layer nodes is set to 64, and the number of fully connected layer nodes is set to 32. The output layer outputs the severity of the discharge.

[0060] S211, when the accuracy of the preset model exceeds a preset accuracy threshold, obtaining the discharge severity assessment model; The detection and positioning system uses the Adam optimizer, the learning rate is set to 0.001, and the training batch size is 32. It can also be set according to the actual situation and is not limited here. 80% of the data in the data set D is divided into a training set and 20% is divided into a validation set. 100 epochs are trained and the model with the highest accuracy of the validation set is saved. It can also be set according to the actual situation and is not limited here. Epoch is the process in which the training data set passes through the neural network once. In machine learning and deep learning, epoch is a unit used to measure the number of times the entire training set is repeatedly learned. Specifically, when the neural network completes a forward calculation and back propagation process, that is, all data has been processed by the network once, this completes an epoch. The detection and positioning system uses binary cross entropy as the loss function and Early Stopping to prevent overfitting. When the accuracy of the preset model exceeds the preset accuracy threshold, the model training is determined to be completed and the discharge severity assessment model is obtained. Early Stopping is a technology in deep learning and machine learning to prevent model overfitting. It determines when to stop training by monitoring the performance of the model on the validation set.

[0061] S212, inputting the frequency characteristics and the amplitude distribution into a preset discharge severity assessment model to obtain the discharge severity of the local discharge sound source; The detection and positioning system inputs the input features in the validation set into the discharge severity assessment model, and then obtains the predicted output of the discharge severity assessment model. The predicted output of the discharge severity assessment model is compared with the actual output features in the validation set, and some performance indicators such as accuracy, precision, recall, F1 score, mean square error (MSE), etc. are used to evaluate the performance of the discharge severity assessment model. According to the performance of the discharge severity assessment model on the validation set, the parameters of the discharge severity assessment model are adjusted, including adjusting the learning rate, changing the model complexity (such as increasing or decreasing the number of layers or nodes of the neural network), modifying the regularization strength, etc. This process may require multiple iterations, each adjustment based on the previous learning results, so as to optimize the discharge severity assessment model.

[0062] S213, mapping the position coordinates of the local discharge sound source to the corresponding position of the video image to obtain a local discharge sound imaging localization map, and displaying the discharge severity of the local discharge sound source in the local discharge sound imaging localization map; For details, please refer to step S106, which will not be described in detail here.

[0063] S214: If the discharge severity of the local discharge sound source exceeds a preset threshold, the local discharge sound imaging localization map is sent to the user.

[0064] The detection and positioning system performs this step immediately after completing the discharge severity assessment of the partial discharge sound source. Specifically, the detection and positioning system first compares the assessed discharge severity with the preset severity threshold. The preset severity threshold may be determined based on historical data, expert experience and equipment specifications, and is not limited here. If the detection and positioning system determines that the discharge severity exceeds the preset severity threshold, it indicates that the detected partial discharge has reached a level that may threaten the safety of the equipment or the stability of the system. , the detection and positioning system will immediately trigger the image sending procedure. The detection and positioning system will first ensure that the partial discharge acoustic imaging positioning map is the latest generated, including the latest location coordinates and discharge severity of the partial discharge sound source. Then, the detection and positioning system will convert the partial discharge acoustic imaging positioning map into a format suitable for transmission (such as JPEG or PNG). Next, the detection and positioning system will select the appropriate sending channel based on the preset user contact information and preferences, including sending directly to the user's workstation through an encrypted internal network, through a secure mobile application push notification, or through an encrypted email.

[0065] By implementing this method, due to the use of multi-dimensional data fusion and intelligent analysis technology, the present invention can comprehensively and accurately detect and locate partial discharge, effectively solving the problems of insufficient detection accuracy and high misjudgment rate caused by a single data source in the prior art, thereby significantly improving the safe operation of the power system. The present invention constructs a multi-dimensional, high-precision detection and positioning system by combining sound signal analysis, video image processing and machine learning algorithms. The time-frequency analysis of the sound signal can capture weak discharge characteristics, the real-time positioning of the video image provides an intuitive spatial reference for the discharge source, and the machine learning algorithm realizes the intelligent evaluation of the severity of the discharge. This fusion of multi-source data not only greatly improves the accuracy and reliability of the detection, but also can adapt to the complex power equipment environment, providing strong technical support for the preventive maintenance and fault diagnosis of the power system, and significantly improving the safety and reliability of the power system. Due to the use of an intelligent evaluation model based on acoustic features and an adaptive early warning mechanism, the present invention can accurately evaluate the severity of the discharge and issue an early warning in a timely manner, effectively solving the problems of inaccurate judgment of the degree of discharge danger and untimely early warning in the prior art, thereby realizing the early prevention and intelligent management of power system faults. The present invention establishes a high-precision discharge severity assessment model by analyzing the frequency characteristics and amplitude distribution of the local discharge sound source and combining it with a machine learning algorithm. The discharge severity assessment model can not only accurately assess the current discharge status, but also predict its development trend. At the same time, the present invention also sets an adaptive warning threshold, which can automatically trigger corresponding warning and treatment measures according to the risk level of different areas. This intelligent assessment and warning mechanism greatly improves the safety management level of the power system, can timely discover potential risks before a fault occurs, and provide maintenance personnel with sufficient response time, effectively reducing the probability of major accidents, and also optimizing the allocation efficiency of maintenance resources. Due to the use of high-precision three-dimensional positioning technology and visual acoustic imaging methods, the present invention can accurately locate the discharge source and intuitively present the detection results, effectively solving the problems of inaccurate positioning and difficult to explain detection results in the prior art, thereby realizing efficient and accurate maintenance of power equipment. The present invention analyzes the time difference of the sound signal received by the microphone array and uses the least squares method to solve the hyperplane equation group to achieve high-precision three-dimensional positioning of the discharge source. This positioning method is not only applicable to a single device, but also can maintain high accuracy in a complex multi-device environment. At the same time, the present invention innovatively combines the positioning results with real-time video images to generate an intuitive partial discharge acoustic imaging positioning map, and annotates the discharge severity in the partial discharge acoustic imaging positioning map. This visual presentation method enables maintenance personnel to quickly and accurately identify the problem, greatly improving the efficiency of fault diagnosis and maintenance.In addition, this method of precise positioning and visual presentation also provides an important basis for the preventive maintenance of equipment, helping to formulate more accurate and targeted maintenance strategies, thereby extending equipment life, reducing maintenance costs, and improving the overall operating efficiency of the power system.

[0066] The following describes the detection and positioning system in the embodiment of the present invention from the perspective of hardware processing. Figure 3 , which is a schematic diagram of the structure of a physical device of the detection and positioning system in an embodiment of the present application.

[0067] It should be noted that Figure 3 The structure of the detection and positioning system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present invention.

[0068] like Figure 3 As shown, the detection and positioning system includes a central processing unit (CPU) 301, which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM) 302 or the program loaded from the storage part 308 to the random access memory (RAM) 303, such as executing the method described in the above embodiment. In RAM 303, various programs and data required for system operation are also stored. CPU 301, ROM 302 and RAM 303 are connected to each other through bus 304. Input / output (I / O) interface 305 is also connected to bus 304.

[0069] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a button switch, etc.; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator light, etc.; a storage section 308 including a hard disk, etc.; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, etc. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as needed. A removable medium 311, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 310 as needed so that a computer program read therefrom is installed into the storage section 308 as needed.

[0070] In particular, according to an embodiment of the present invention, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present invention includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a computer program for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through the communication part 309, and / or installed from a removable medium 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present invention are performed.

[0071] It should be noted that specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM), a flash memory, an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination thereof. In the present invention, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, apparatus, or device.

[0072] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architecture, functions and operations of the systems, methods and computer program products according to various embodiments of the present invention. Each box in the flowchart or block diagram may represent a module, a program segment, or a part of a code, and the above-mentioned module, program segment, or a part of a code contains one or more executable instructions for implementing the specified logical functions. It should also be noted that in some alternative implementations, the functions marked in the box may also occur in an order different from that marked in the accompanying drawings.

[0073] Specifically, the detection and positioning system of this embodiment includes a processor and a memory. The memory stores a computer program. When the computer program is executed by the processor, the partial discharge acoustic imaging detection and positioning method provided in the above embodiment is implemented.

[0074] As another aspect, the present invention further provides a computer-readable storage medium, which may be included in the detection and positioning system described in the above embodiment; or may exist independently without being assembled into the detection and positioning system. The above storage medium carries one or more computer programs, and when the above one or more computer programs are executed by a processor of the detection and positioning system, the detection and positioning system implements the partial discharge acoustic imaging detection and positioning method provided in the above embodiment.

[0075] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present application.

[0076] As used in the above embodiments, the term "when..." may be interpreted to mean "if..." or "after..." or "in response to determining..." or "in response to detecting...", depending on the context. Similarly, the phrases "upon determining..." or "if (the stated condition or event) is detected" may be interpreted to mean "if determining..." or "in response to determining..." or "upon detecting (the stated condition or event)" or "in response to detecting (the stated condition or event)", depending on the context.

[0077] Those skilled in the art can understand that to implement all or part of the processes in the above-mentioned embodiments, the processes can be completed by computer programs to instruct related hardware, and the programs can be stored in computer-readable storage media. When the programs are executed, they can include the processes of the above-mentioned method embodiments. The aforementioned storage media include: ROM or random access memory RAM, magnetic disk or optical disk and other media that can store program codes.

Claims

1. A method for detecting and locating partial discharge acoustic imaging, characterized in that: Applied to a detection and positioning system, the method comprises: Acquire the sound signal collected by the microphone array and the video image collected by the camera; Detecting the energy accumulation values ​​of multiple sound sources in the sound signal within a preset time period; Marking the sound source whose energy cumulative value exceeds a preset threshold as a partial discharge sound source; Determining the position coordinates of the local discharge sound source; Assessing the severity of the discharge according to the sound characteristics of the local discharge sound source, wherein the sound characteristics at least include frequency characteristics and amplitude distribution; The position coordinates of the local discharge sound source are mapped to the corresponding position of the video image to obtain a local discharge sound imaging localization map, and the discharge severity of the local discharge sound source is displayed in the local discharge sound imaging localization map.

2. The method according to claim 1, characterized in that The detecting of the energy accumulation values ​​of multiple sound sources in the sound signal within a preset time period specifically includes: Performing time-frequency analysis on the sound signal to obtain a time-frequency spectrum diagram, wherein the horizontal axis of the time-frequency spectrum diagram represents time, and the vertical axis represents frequency components, and the time-frequency spectrum diagram includes multiple frequency components, the multiple frequency components correspond to the multiple sound sources, and different frequency components correspond to different energy values ​​at different time points; Based on the accumulation of the time-frequency spectrum along the time axis, the energy accumulation values ​​of the multiple sound sources within the preset time length are determined.

3. The method according to claim 1, characterized in that Determining the position coordinates of the local discharge sound source specifically includes: Obtaining the arrival time difference of the sound signal corresponding to the partial discharge sound source received by each microphone in the microphone array; According to the arrival time difference, a hyperplane equation group is established; The least square method is used to solve the hyperplane equation group, and the three-dimensional coordinate estimation value of the local discharge sound source is obtained as the position coordinate of the local discharge sound source.

4. The method according to claim 1, characterized in that The discharge severity is evaluated according to the sound characteristics of the local discharge sound source, wherein the sound characteristics at least include frequency characteristics and amplitude distribution, and specifically include: Extracting the frequency characteristics and amplitude distribution of the local discharge sound source; The frequency characteristics and the amplitude distribution are input into a preset discharge severity assessment model to obtain the discharge severity of the local discharge sound source.

5. The method according to claim 1, characterized in that After the step of mapping the position coordinates of the local discharge sound source to the corresponding position of the video image to obtain a local discharge sound imaging localization map, and displaying the discharge severity of the local discharge sound source in the local discharge sound imaging localization map, the method further includes: If the discharge severity of the local discharge sound source exceeds a preset threshold, the local discharge sound imaging localization map is sent to the user.

6. The method according to claim 4, characterized in that Before the step of inputting the frequency characteristics and the amplitude distribution into a preset discharge severity assessment model to obtain the discharge severity of the partial discharge sound source, the method further includes: Obtain frequency characteristics, amplitude distribution and corresponding discharge severity of multiple sound sources; Marking the frequency feature and the amplitude distribution as input features, and marking the discharge severity as output feature; Using the input features and the output features to train a preset model; When the accuracy of the preset model exceeds a preset accuracy threshold, the discharge severity assessment model is obtained.

7. The method according to claim 1, characterized in that After the step of determining the position coordinates of the local discharge sound source, the method further comprises: If the location coordinates of the partial discharge sound source are within a preset first area, emergency power outage measures are initiated; If the position coordinates of the partial discharge sound source are in the preset second area, an alarm condition is triggered, and the alarm condition is used to attract the user's attention. The risk factor of the preset first area is higher than that of the preset second area.

8. A detection and positioning system, characterized in that: The detection and positioning system includes: one or more processors and a memory; the memory is coupled to the one or more processors, the memory is used to store computer program code, the computer program code includes computer instructions, and the one or more processors call the computer instructions to enable the detection and positioning system to execute the method described in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that: When the instruction is executed on a detection and positioning system, the detection and positioning system is caused to execute the method according to any one of claims 1 to 7.

10. A computer program product, characterized in that When the computer program product runs on a detection and positioning system, the detection and positioning system is enabled to perform the method according to any one of claims 1 to 7.

Images