Partial discharge characteristic spectrum construction method and device based on quantum detection technology, equipment and storage medium

Abstract

The invention discloses a partial discharge characteristic spectrum construction method and device based on a quantum detection technology, equipment and a storage medium. The method comprises the following steps: acquiring quantum detection signal data of to-be-detected high-voltage equipment through a preset light quantum sensor; performing feature extraction on the quantum detection signal data to obtain corresponding partial discharge feature information; classifying and marking the partial discharge feature information based on a preset defect type to obtain classified and marked partial discharge feature information; and constructing a partial discharge characteristic spectrum database according to the classified and labeled partial discharge characteristic information. According to the method, the quantum detection signal data generated by partial discharge can be accurately acquired in different scenes by using the light quantum sensor, and defect type labeling is carried out, so that the diversity of feature samples in the constructed partial discharge feature spectrum database is ensured, and rich data support is provided for subsequent state recognition and fault diagnosis of high-voltage equipment.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of discharge detection, and in particular to a partial discharge feature map construction method and device based on quantum detection technology, equipment and a storage medium. BACKGROUND

[0002] With the rapid development of the power system towards high voltage, large capacity and large-scale access of new energy, the operation reliability of high-voltage electrical equipment is crucial to the safety of the power grid. As a key manifestation of equipment insulation deterioration, the accurate detection and state evaluation of partial discharge has become the core link of preventive maintenance. At present, the power industry mainly relies on high-frequency current, ultra-high frequency electromagnetic wave and ultrasonic wave and other technical means to realize partial discharge detection.

[0003] Due to the existing partial discharge detection technology determined by its technical route, it is limited in its applicable equipment, defect type sensitivity, etc. Therefore, the sample coverage range of the discharge feature library constructed based on the detection data is limited, that is, the existing discharge feature library cannot fully reflect the differences in partial discharge characteristics under different equipment types, operating conditions and defect modes, making the subsequent state evaluation results of high-voltage equipment lack of universality and foresight.

[0004] Therefore, a more perfect method is needed to construct a partial discharge feature map to improve the accuracy and reliability of high-voltage equipment state monitoring and provide data support for high-voltage equipment state identification. SUMMARY

[0005] The main purpose of the present application is to provide a partial discharge feature map construction method and device based on quantum detection technology, equipment and a storage medium, which aims to solve the technical problem of single sample type in the discharge feature library constructed based on the existing partial discharge detection technology.

[0006] To achieve the above-mentioned purpose, the present application provides a partial discharge feature map construction method based on quantum detection technology, which is applied to a partial discharge feature map construction device provided with a preset light quantum sensor. The method comprises: acquiring quantum detection signal data of a high-voltage equipment to be tested by the preset light quantum sensor; extracting features from the quantum detection signal data to obtain corresponding partial discharge feature information; classifying and labeling the partial discharge feature information based on a preset defect type to obtain the classified and labeled partial discharge feature information; constructing a partial discharge feature map library according to the classified and labeled partial discharge feature information.

[0007] In an embodiment, the preset light quantum sensor comprises: a light source module, a polarization encoding module, and a detection module. The step of collecting quantum detection signal data of the high-voltage equipment to be detected by the preset light quantum sensor comprises: The light source module generates weak coherent light pulses, and the average photon number of the weak coherent light pulses is controlled at the single-photon level. The polarization encoding module modulates the polarization state of the weak coherent light pulses to generate photons with a preset polarization direction, so that the photons are transmitted in the space where the high-voltage equipment to be detected is located. The detection module obtains quantum detection signal data generated by the photons under the magnetic field interference of the high-voltage equipment to be detected.

[0008] In an embodiment, the detection module comprises: a single-photon avalanche diode and a polarization beam splitter. The step of obtaining quantum detection signal data generated by the photons under the magnetic field interference of the high-voltage equipment to be detected by the detection module comprises: The polarization beam splitter separates the photons according to different polarization directions and guides them to the corresponding single-photon avalanche diodes for detection to obtain the state change trajectory of the photons. Quantum detection signal data is generated based on the state change trajectory.

[0009] In an embodiment, the step of extracting features from the quantum detection signal data to obtain corresponding partial discharge feature information comprises: The quantum detection signal data is preprocessed to obtain effective detection signal data. The quantum detection signal data is subjected to feature extraction of polarization state change parameters, including: degree of polarization, polarization selection angle, and polarization mode distribution. According to the feature extraction result, the corresponding partial discharge feature information is determined.

[0010] In an embodiment, the step of classifying and labeling the partial discharge feature information based on a preset defect type to obtain the classified and labeled partial discharge feature information comprises: In the preset defect type, the current defect type corresponding to the partial discharge feature information is determined, and the preset defect type at least includes: corona discharge, suspended discharge, surface discharge, and free metal particle discharge. The feature labeling template corresponding to the current defect type is obtained, and the partial discharge feature information is classified and labeled based on the feature labeling template to obtain the classified and labeled partial discharge feature information.

[0011] In an embodiment, the step of constructing the partial discharge feature map library according to the classified and labeled partial discharge feature information comprises: initializing the feature map library corresponding to the to-be-tested high-voltage equipment; analyzing the classified and labeled partial discharge feature information based on a data mining technology, and generating the feature parameters corresponding to each preset defect type according to the analysis result; updating the feature map library according to each feature parameter, and constructing the partial discharge feature map library.

[0012] In an embodiment, the step of analyzing the classified and labeled partial discharge feature information based on a data mining technology, and generating the feature parameters corresponding to each preset defect type according to the analysis result comprises: performing high-discrimination feature screening on the classified and labeled partial discharge feature information by principal component analysis technology, and obtaining principal component feature parameters; determining the feature parameters corresponding to each preset defect type according to the principal component feature parameters.

[0013] In addition, to achieve the above-mentioned purpose, the present application also proposes a partial discharge feature map construction device, which comprises: a data acquisition module configured to acquire quantum detection signal data of a to-be-tested high-voltage equipment by a preset quantum sensor; a feature extraction module configured to perform feature extraction on the quantum detection signal data to obtain corresponding partial discharge feature information; a feature classification module configured to classify and label the partial discharge feature information based on preset defect types to obtain the classified and labeled partial discharge feature information; a map construction module configured to construct a partial discharge feature map library according to the classified and labeled partial discharge feature information.

[0014] In addition, to achieve the above-mentioned purpose, the present application also proposes a partial discharge feature map construction device, which comprises: a memory, a processor, and a partial discharge feature map construction program stored on the memory and executable on the processor, wherein the partial discharge feature map construction program is configured to implement the steps of the partial discharge feature map construction method based on quantum detection technology as described above.

[0015] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and the storage medium stores a partial discharge feature map construction program, wherein the partial discharge feature map construction program is executed by a processor to implement the steps of the partial discharge feature map construction method based on quantum detection technology as described above.

[0016] The application discloses a partial discharge feature map construction method based on quantum detection technology, and is applied to a partial discharge feature map construction device provided with a preset optical quantum sensor. The method comprises the following steps: collecting quantum detection signal data of a high-voltage device to be detected through the preset optical quantum sensor; extracting features of the quantum detection signal data to obtain corresponding partial discharge feature information; classifying and labeling the partial discharge feature information based on preset defect types to obtain classified and labeled partial discharge feature information; and constructing a partial discharge feature map library according to the classified and labeled partial discharge feature information.

[0017] Thanks to the high sensitivity and anti-interference capability of the optical quantum sensor, the quantum detection signal data generated by the partial discharge can be accurately collected, so that the accuracy and reliability of the partial discharge feature information extraction are improved. By constructing the partial discharge feature map library, the partial discharge features of different types of high-voltage devices under various operating states can be comprehensively covered, which provides rich data support for subsequent high-voltage device state recognition and fault diagnosis. Meanwhile, the step of classification and labeling helps to quickly and accurately identify the type of the partial discharge, and further improves the practicability and diagnosis efficiency of the map library. BRIEF DESCRIPTION OF DRAWINGS

[0018] The accompanying drawings, which are incorporated into and form a part of the specification, illustrate an embodiment consistent with the present application and, together with the description, serve to explain the principles of the application.

[0019] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the accompanying drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, for those skilled in the art, other drawings can also be obtained based on these drawings without creative labor.

[0020] Figure 1 The flowchart of the first embodiment of the partial discharge feature map construction method based on quantum detection technology of the present application is shown in the figure. Figure 2 The flowchart of the second embodiment of the partial discharge feature map construction method based on quantum detection technology of the present application is shown in the figure. Figure 3 The flowchart of the third embodiment of the partial discharge feature map construction method based on quantum detection technology of the present application is shown in the figure. Figure 4 The module structure diagram of the first embodiment of the partial discharge feature map construction device of the present application is shown in the figure. Figure 5 The structure diagram of the partial discharge feature map construction device in the embodiment of the present application is shown in the figure. DETAILED DESCRIPTION

[0021] It should be understood that the specific embodiments described herein are merely illustrative of the technical solutions of this application and are not intended to limit this application.

[0022] To better understand the technical solution of this application, a detailed description will be provided below in conjunction with the accompanying drawings and specific implementation methods.

[0023] This application provides a method for constructing partial discharge feature maps based on quantum detection technology, referencing... Figure 1 , Figure 1 This is a flowchart illustrating the first embodiment of the partial discharge feature map construction method based on quantum detection technology of this application. In this embodiment, the method includes: steps S10~S40: Step S10: Collect quantum detection signal data of the high voltage device under test using a preset optical quantum sensor.

[0024] It should be noted that the execution subject of the method in this embodiment can be a computing electronic device with data processing, network communication, and program execution capabilities, such as a mobile phone, personal computer, quantum signal monitor, or other electronic device capable of data communication with an optical quantum sensor. It can also be a partial discharge characteristic map construction device equipped with an optical quantum sensor. Here, a partial discharge characteristic map construction device equipped with an optical quantum sensor (hereinafter referred to as the "construction device") is selected as an example to illustrate this embodiment and the following embodiments.

[0025] It should be noted that the principle of optical quantum sensors is mainly based on the properties of photons, namely, photons can behave as both particles and waves. In quantum physics, the properties of photons can be measured, and the measurement result is not 100% deterministic, but rather exists with a certain probability. This is known as the quantum measurement principle. Utilizing this principle, optical quantum sensors can convert the physical quantity to be measured into the properties of photons for measurement. Through statistical analysis of the measurement results, the value of the physical quantity to be measured can be inferred, thereby achieving high-precision detection. In the embodiments of this application, the physical quantity to be measured can be partial discharge (PD), which is an early signal of insulation aging and potential breakdown in high-voltage power equipment.

[0026] It should be understood that the high-voltage equipment under test can be high-voltage equipment with different discharge defects in different scenarios, such as transformers, gas-insulated switchgear (GIS), power cables, and other power equipment that requires monitoring of insulation status. The device can be constructed based on one or more optical quantum sensors to collect signals at different locations on the high-voltage equipment, capturing the photon quantum state changes caused by internal discharges and obtaining quantum detection signal data.

[0027] Among them, the quantum detection signal can be a physical signal that the quantum states of photons, such as polarization direction, phase, and propagation path, change under the electromagnetic field disturbance generated by the partial discharge of high-voltage equipment.

[0028] In practical implementation, the optical quantum sensor utilizes a tunable pulsed laser to generate weak pulsed light, which is then adjusted to a quasi-single-photon state by a variable optical attenuator. A polarization element then assigns a specific polarization state to the photon as its initial quantum state. During free-space propagation, the transient strong electromagnetic field generated by partial discharge disturbs the photon's polarization state, phase, path, and other states. Finally, a single-photon avalanche diode, along with a polarization beam splitter and other analysis systems, records the trajectory of the photon's state changes, thereby obtaining the quantum detection signal data of the high-voltage device under test.

[0029] Step S20: Extract features from the quantum detection signal data to obtain corresponding partial discharge feature information.

[0030] It should be noted that, firstly, time-domain analysis can be performed on the quantum detection signal data to extract time-domain characteristic parameters such as pulse amplitude, pulse width, and pulse repetition rate. These parameters directly reflect the intensity and frequency of partial discharge. Next, frequency-domain analysis can be performed on the quantum detection signal data to extract frequency-domain characteristic parameters such as frequency components and bandwidth, in order to understand the frequency characteristics and energy distribution of partial discharge.

[0031] Furthermore, time-frequency analysis methods such as wavelet transform can be used to extract the characteristics of the signal at different time scales, such as wavelet energy and wavelet entropy, which can simultaneously reflect the time-domain variation characteristics and frequency-domain distribution characteristics of the signal.

[0032] Furthermore, in order to transform the raw signal data into more representative and discriminative feature information, laying the foundation for subsequent classification, labeling, and map construction, feature extraction of polarization variation parameters can also be performed based on quantum detection signal data. Step S20 includes: Steps S201~S203: Step S201: Preprocess the quantum detection signal data to obtain effective detection signal data.

[0033] It should be noted that various types of noise may exist in quantum detection signal data. These noise signals will be mixed in with the quantum detection signal and affect the accuracy of subsequent feature extraction. Therefore, preprocessing operations such as filtering and denoising, signal amplification and normalization can be performed on the acquired quantum detection signal data to obtain an effective detection signal.

[0034] Step S202: Extract features of polarization state change parameters from the quantum detection signal data. The polarization state change parameters include: degree of polarization, polarization selection angle, and polarization mode distribution.

[0035] It should be noted that the degree of polarization (DoP) is a parameter that measures the purity of photon polarization. It reflects the degree of certainty of the photon's polarization state. In partial discharge detection, the electromagnetic field disturbance generated by partial discharge causes changes in the photon's polarization state, thereby causing a change in the degree of polarization.

[0036] For example, when there is no partial discharge, the polarization state of the photon is relatively pure and the degree of polarization is high; however, when a partial discharge occurs, due to the disturbance of the electromagnetic field, the polarization state of the photon will depolarize, and the degree of polarization will decrease. The DoP value is generally between 0 and 1. The smaller the DoP value, the lower the purity of the polarization state.

[0037] The polarization selection angle refers to the angle by which the polarization direction of a photon deflects relative to its initial polarization direction after a change in polarization state. It reflects the degree to which the partial discharge electromagnetic field twists the polarization direction of the photon. For example, a photon with an initial horizontal polarization direction may have its polarization direction deflected at a certain angle due to the electromagnetic field after passing through a partial discharge region; this deflection angle is the polarization selection angle.

[0038] Polarization mode distribution describes the energy or photon number distribution of photons under different polarization modes (such as linear, circular, and ellipsoidal polarization). Perturbations in the electromagnetic field of partial discharge can alter the polarization modes of photons, thus changing their distribution. For example, in the absence of partial discharge, photons may primarily be in linear polarization mode; however, when partial discharge occurs, some photons may convert to ellipsoidal or circular polarization modes, leading to a change in the polarization mode distribution.

[0039] Step S203: Determine the corresponding partial discharge feature information based on the feature extraction results.

[0040] It should be understood that the result of this feature extraction can be the specific value of each polarization state change parameter determined by the quantum detection signal data, and thus it can be determined as the partial discharge feature information extracted from the quantum detection signal data.

[0041] In addition, the partial discharge characteristic information may also include the aforementioned time-domain characteristic parameters and frequency-domain characteristic parameters. Polarization state change parameters, time-domain characteristic parameters, and frequency-domain characteristic parameters are all different manifestations of partial discharge characteristic information. They can complement each other and jointly provide a comprehensive perspective for the identification and analysis of partial discharge.

[0042] In practical implementation, polarization state change parameters can be combined with time-domain and frequency-domain feature parameters for comprehensive analysis. For example, a feature vector can be constructed that includes parameters such as polarization degree, pulse amplitude, pulse width, and main frequency components, so as to facilitate subsequent classification of defect types based on the feature vector.

[0043] Step S30: Classify and label the partial discharge feature information based on the preset defect type to obtain the classified and labeled partial discharge feature information.

[0044] It should be understood that common types of partial discharge defects include corona discharge, floating discharge, surface discharge, and free metal particle discharge.

[0045] Because each defect type has unique partial discharge characteristics, accurately classifying these characteristics and labeling the corresponding defect types can quickly narrow down the fault range and improve diagnostic efficiency. During the labeling process, detailed information related to the partial discharge characteristics, such as equipment type, operating status, and environmental conditions, can also be recorded to gain a more comprehensive understanding of the complex relationship between partial discharge characteristics and equipment status in subsequent analysis.

[0046] It should be understood that feature standard templates corresponding to each preset defect type can be predefined for classifying and labeling partial discharge feature information: the extracted partial discharge feature information is compared with the feature labeling template, and the partial discharge feature information is classified and labeled according to the feature parameter range and mode specified in the feature labeling template.

[0047] For example, if the degree of polarization of the extracted partial discharge feature information is 0.4, the polarization selection angle conforms to the typical angle of corona discharge, the polarization mode distribution is mainly linear polarization, and the time domain and frequency domain characteristics are consistent with the template description of corona discharge, then this partial discharge feature information can be labeled as a corona discharge type.

[0048] Understandably, the labeled partial discharge feature information will include defect type labels and descriptions of feature parameters related to that defect type. This information will be integrated into the partial discharge feature map library, which can provide detailed classification data support for subsequent high-voltage equipment status identification and fault diagnosis.

[0049] Step S40: Construct a partial discharge feature map library based on the partial discharge feature information after classification and labeling.

[0050] It should be understood that integrating the categorized and labeled feature information into the map library to form a feature map allows for systematic organization and scientific integration. According to predetermined rules and structures, the partial discharge feature information of different equipment types, different operating states, and different defect types can be arranged and stored in an orderly manner.

[0051] At the same time, an efficient data retrieval and query mechanism should be established so that the required feature information can be retrieved quickly and accurately in subsequent high-voltage equipment status identification and fault diagnosis.

[0052] In addition, to ensure the timeliness and accuracy of the spectral library, it can be updated and maintained regularly: outdated or useless data can be deleted, equipment status information and annotation content can be updated, and the classification system and feature parameters of the spectral library can be optimized and adjusted according to the operation and maintenance of the equipment and technological development.

[0053] It should be noted that by constructing a comprehensive, accurate, and dynamically updated partial discharge characteristic spectrum library, rich data support can be provided for the condition monitoring of high-voltage equipment, helping operation and maintenance personnel to understand the health status of the equipment in a timely and accurate manner, and providing a strong basis for equipment maintenance decisions.

[0054] This embodiment leverages the high sensitivity and anti-interference capabilities of optical quantum sensors to accurately acquire quantum detection signal data generated by partial discharge, thereby improving the accuracy and reliability of partial discharge feature information extraction. By constructing a partial discharge feature map library, it can comprehensively cover the partial discharge characteristics of different types of high-voltage equipment under various operating conditions, providing rich data support for subsequent high-voltage equipment status identification and fault diagnosis. Simultaneously, the classification and labeling steps facilitate rapid and accurate identification of partial discharge types, further enhancing the practicality of the map library and diagnostic efficiency.

[0055] In the first embodiment of this application, and in the second embodiment of this application, the content that is the same as or similar to that in Embodiment 1 above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 2 , Figure 2 This is a flowchart illustrating the second embodiment of the partial discharge feature map construction method based on quantum detection technology in this application.

[0056] In this embodiment, the aforementioned preset optical quantum sensor includes a light source module, a polarization encoding module, and a detection module. These three modules work together to achieve highly sensitive detection of partial discharge in the high-voltage equipment under test.

[0057] To illustrate in detail how to acquire data from the high-voltage equipment under test based on quantum detection technology, step S10 specifically includes: steps S101~S103: Step S101: A weakly coherent light pulse is generated by the light source module, and the average number of photons in the weakly coherent light pulse is controlled at the level of a single photon.

[0058] It should be noted that the light source module is a key component of the optical quantum sensor, and its main function is to generate the optical signal used for detection. It can consist of a tunable pulsed laser and a variable optical attenuator (VOA).

[0059] Among them, the tunable pulsed laser can generate high-repetition-rate, low-energy light pulses, providing a stable light source for subsequent quantum detection. The variable optical attenuator is used to finely control the number of photons in each pulse.

[0060] In its implementation, the tunable pulsed laser first emits raw light pulses. These pulses have a high photon count and require attenuation to meet the requirements of quantum detection. Then, the light pulses are passed through a variable attenuator, precisely adjusting the average photon count of each pulse to the single-photon level. This operation puts the light pulses in a "quasi-single-photon" state, i.e., a weakly coherent light state.

[0061] The above process can improve the sensitivity and accuracy of detection, and avoid problems such as detector saturation or false triggering caused by excessive photon count during subsequent detection processes.

[0062] Step S102: The weak coherent light pulse is polarized and modulated using a polarization encoding module to generate photons with a preset polarization direction so that the photons can be transmitted in the space where the high voltage equipment under test is located.

[0063] It should be noted that the polarization encoding module is mainly used to modulate the polarization state of optical pulses. It typically contains various optical elements, such as polarizers, / 2 waveplate and / 4 waveplate, etc.

[0064] It should be understood that these components can precisely control the polarization state of photons, providing photons with specific polarization characteristics for subsequent quantum detection. Through polarization encoding, photons can be endowed with an initial quantum state, enabling them to effectively interact with the electromagnetic field generated by partial discharge during subsequent transmission and detection.

[0065] In the specific implementation, after the weakly coherent light pulse is output from the light source module, it enters the polarization encoding module: First, the light pulse passes through a polarizer, which restricts the polarization direction of the light to a specific direction, such as horizontal or vertical polarization; then, the light pulse sequentially passes through... / 2 waveplate and A 4-wave plate is used to further adjust the polarization state of the photon. By precisely controlling the angle and parameters of these waveplates, fine modulation of the photon polarization state can be achieved. This ultimately generates photons with preset polarization directions (such as horizontal polarization, vertical polarization, +45° polarization, -45° polarization, left-handed circular polarization, or right-handed circular polarization). These photons carry specific polarization information and propagate in the space where the high-voltage device under test is located, interacting with the electromagnetic field generated by partial discharge.

[0066] Step S103: Obtain quantum detection signal data generated by the photon under the magnetic field interference of the high voltage device under test through the detection module.

[0067] It should be noted that the detection module is responsible for capturing and recording the quantum detection signal data generated by photons under the interference of the magnetic field of the high-voltage equipment under test. It can be composed of a single-photon avalanche diode (SPAD) and a polarization beam splitter (PBS).

[0068] SPADs are highly sensitive photon detectors capable of detecting single photons under extremely low light intensity conditions. Based on the semiconductor avalanche principle, when a photon strikes the photocathode of a SPAD, an electron-hole pair is generated. Under a high reverse bias, this electron-hole pair gains sufficient energy to trigger an avalanche-like carrier multiplication process, forming a detectable macroscopic current pulse. This characteristic gives SPADs extremely high sensitivity, enabling them to detect the arrival of a single photon.

[0069] Photons polarization beams (PBSs) can be used to analyze changes in the polarization state of photons, thereby extracting information related to partial discharge. A PBS is an optical element that splits photons into different beams based on their polarization direction. Common PBSs include cubic polarization beamsplitters and thin-film polarization beamsplitters. A PBS typically consists of multiple optical surfaces coated with specific dielectric films, which exhibit different reflection and transmission properties for light with different polarization directions. For example, for linearly polarized light, a PBS can transmit horizontally polarized light while reflecting vertically polarized light.

[0070] It should be understood that photons can be separated according to different polarization directions using PBS and guided to the corresponding SPAD for detection to obtain the photon's state change trajectory; then, quantum detection signal data can be generated based on the state change trajectory.

[0071] Specifically, when photons with a specific polarization state propagate in the space where the high-voltage equipment under test is located, if partial discharge occurs, a transient strong electromagnetic field will be generated. This electromagnetic field will perturb the quantum properties of the photons, such as their polarization state, phase, and path.

[0072] The perturbed photons enter the detection module and are first analyzed for polarization using a combination of a photodiode (PBS) and a waveplate. These elements separate the photons according to different polarization directions and guide them to the corresponding SPADs for detection. For example, a photon with an initial polarization direction of 45 degrees may be split into horizontal and vertical polarization components after passing through the PBS, and then guided to the corresponding SPADs for detection.

[0073] By recording the number of photons received by each SPAD and the time series, the trajectory of photon polarization state changes can be constructed. For example, a graph showing the change in polarization direction of photons at different time points can be plotted, or the conversion probability and frequency of photons between different polarization states can be analyzed.

[0074] Finally, the time information from SPAD and the polarization state information from PBS are fused together to form complete quantum detection signal data. This data includes key parameters such as photon arrival time, polarization direction, and degree of polarization.

[0075] Furthermore, the obtained quantum detection signal data can be preliminarily processed and analyzed to remove noise and interference signals. Each photon's quantum detection signal data can be represented as a data packet for output, thus providing a foundation for subsequent feature extraction and further analysis. This embodiment can generate weakly coherent light pulses through a light source module, with the average number of photons in the weakly coherent light pulses controlled at the single-photon level. A polarization encoding module is used to modulate the polarization state of the weakly coherent light pulses, generating photons with a preset polarization direction, enabling photons to propagate in the space where the high-voltage device under test is located. A detection module acquires the quantum detection signal data generated by photons under the magnetic field interference of the high-voltage device under test, thereby achieving accurate acquisition of quantum detection signal data from the high-voltage device under test through a preset quantum sensor, providing high-quality data support for subsequent partial discharge feature extraction and analysis.

[0076] Based on the first and second embodiments of this application, in the third embodiment of this application, the content that is the same as or similar to that in embodiments one and two above can be referred to the above description, and will not be repeated hereafter. Based on this, please refer to... Figure 3 , Figure 3 This is a flowchart illustrating the third embodiment of the partial discharge feature map construction method based on quantum detection technology in this application.

[0077] In this embodiment, to specifically illustrate how to classify and label partial discharge feature information according to different preset defect types, step S30 includes: steps S301~S302: Step S301: Determine the current defect type corresponding to the partial discharge feature information from the preset defect types. The preset defect types include at least: corona discharge, suspension discharge, surface discharge, and free metal particle discharge.

[0078] It should be noted that the preset defect types include at least corona discharge, floating discharge, surface discharge, and free metal particle discharge. Each defect type has unique partial discharge characteristics, as detailed below: Corona discharge typically occurs at the tips or edges of high-voltage equipment, characterized by a high local electric field intensity and concentrated charge within a small area. The local discharge characteristics of corona discharge include low polarization degree, a specific polarization selection angle (e.g., biased towards a fixed direction), and polarization mode distribution (potentially concentrated in certain specific polarization modes). Simultaneously, in the time domain, corona discharge generates a series of small-amplitude, high-repetition-rate pulse signals; in the frequency domain, its frequency components are relatively concentrated in the lower frequency range.

[0079] Suspension discharge: This occurs when there are suspended conductors or particles inside the equipment. The partial discharge characteristics of suspension discharge include significant variations in polarization degree, unstable polarization selection angle, and unstable polarization mode distribution. Its time-domain characteristics are typically medium-amplitude pulses with narrow pulse widths; in the frequency domain, it has a rich frequency composition and may cover a wide frequency band.

[0080] Surface discharge occurs on the surface of insulating materials and typically develops along the solid-gas or liquid-gas interface. The partial discharge characteristics of surface discharge include a gradually decreasing degree of polarization, a relatively gentle change in the polarization selection angle, and a somewhat linear trend in the polarization mode distribution. In the time domain, surface discharge produces pulse signals of moderate amplitude and moderate repetition rate, with potentially complex pulse shapes; in the frequency domain, its frequency component distribution is complex and may contain multiple frequency peaks.

[0081] Free metal particle discharge: This is caused by free metal particles inside high-voltage equipment. These particles move under the influence of an electric field and collide with insulating materials or other components, resulting in discharge. The partial discharge characteristics of free metal particle discharge are characterized by irregular polarization degree variations, and a chaotic distribution of polarization selection angles and polarization modes. In the time domain, the pulse amplitude varies considerably, ranging from low to high, and the pulse repetition rate is unstable. In the frequency domain, it involves a wide range of frequency components, potentially spanning multiple frequency bands.

[0082] Step S302: Obtain the feature annotation template corresponding to the current defect type, and classify and annotate the partial discharge feature information based on the feature annotation template to obtain the classified and annotated partial discharge feature information.

[0083] It should be noted that the feature annotation template can be a predefined set of rules and format files that guide how to classify and annotate partial discharge feature information. It contains the typical feature parameter ranges and patterns corresponding to each preset defect type.

[0084] For example, for corona discharge, the template may specify that the degree of polarization is usually between 0.3 and 0.5, the polarization selection angle is concentrated around a certain angle, and the polarization mode distribution is mainly linear polarization; in the time domain, the pulse amplitude is generally within a certain range, the pulse width is relatively narrow, and the pulse repetition rate is relatively high; in the frequency domain, the main frequency components are concentrated in a certain frequency band.

[0085] It should be understood that the extracted partial discharge feature information is compared with the feature annotation template. Based on the feature parameter range and pattern specified in the feature annotation template, the partial discharge feature information is classified and labeled. The labeled partial discharge feature information may include a defect type label and a description of the feature parameters related to that defect type. This information will be integrated into the partial discharge feature map library, providing detailed classification data support for subsequent high-voltage equipment condition identification and fault diagnosis.

[0086] Furthermore, to specifically illustrate the process of constructing a partial discharge feature map based on partial discharge feature information, step S40 includes: steps S401~S403: Step S401: Initialize the feature map library corresponding to the high voltage device under test.

[0087] It should be understood that the initialization process may include operations such as creating the database structure, defining data fields and types, and setting indexes to ensure that the feature library can efficiently store and manage a large amount of partial discharge characteristic information. Initializing the feature library establishes a basic framework for subsequent data storage and analysis.

[0088] Step S402: Analyze the partial discharge feature information after classification and labeling based on data mining technology, and generate feature parameters corresponding to each preset defect type based on the analysis results.

[0089] It should be understood that principal component analysis (PCA) can be used to perform high-discrimination feature screening on the classified and labeled partial discharge feature information to obtain principal component feature parameters; and feature parameters corresponding to each preset defect type can be determined based on the principal component feature parameters.

[0090] It should be noted that PCA is a commonly used data mining technique that can transform multiple correlated variables into a few uncorrelated composite variables (principal components). In partial discharge feature analysis, PCA can extract the most representative and discriminative features from a large number of feature parameters.

[0091] First, the classified and labeled partial discharge feature information can be standardized to eliminate dimensional and order-of-magnitude differences between different feature parameters, ensuring that each feature parameter has equal importance. Then, the correlation coefficient matrix of the original feature parameters is calculated. The correlation coefficient matrix reflects the linear correlation between the various feature parameters, helping to determine which feature parameters have strong correlations. Next, the eigenvalues ​​and eigenvectors of the correlation coefficient matrix are solved, where the eigenvalues ​​represent the amount of information contained in each principal component, and the eigenvectors indicate the direction of the original feature parameters in the principal component coordinate system. Based on the magnitude of the eigenvalues, the first few principal components are selected. For example, principal components with a cumulative contribution rate reaching a certain threshold (e.g., 85%-95%) can be selected, thus reducing feature dimensionality while retaining most of the information. Finally, the original partial discharge feature information is projected onto the selected principal component space to obtain the principal component feature parameters. These principal component feature parameters are linear combinations of the original feature parameters, possessing better discriminative power and representativeness.

[0092] Understandably, principal component characteristic parameters reflect the core changes in partial discharge characteristic information, and after PCA processing, these parameters have a better ability to distinguish different defect types. Therefore, for each preset defect type (such as corona discharge, suspended discharge, surface discharge, and free metal particle discharge), the distribution and statistical characteristics of its corresponding principal component characteristic parameters can be analyzed.

[0093] For example, corona discharge may have high loading on some principal components, while suspension discharge may exhibit significant characteristics on others. Using this method, a set of characteristic parameters can be determined for each defect type. These parameters can effectively characterize the partial discharge features of that defect type, providing an accurate basis for subsequent updates to the feature map library and equipment status identification.

[0094] Step S403: Update the feature map library according to each of the aforementioned feature parameters to construct a partial discharge feature map library.

[0095] It should be noted that the specific numerical values, statistical characteristics (such as mean, variance, etc.), and relationship with defect types of feature parameters can be stored in the corresponding locations within the feature map library, along with related metadata such as the generation time of the feature parameters, the corresponding equipment information, and measurement conditions. This metadata helps in better understanding and using the feature parameters during subsequent queries and analyses.

[0096] It should be understood that partial discharge feature maps can be generated based on the feature parameters stored in the map library. Feature maps can be presented in various forms, such as scatter plots, histograms, and heatmaps, to intuitively show the distribution and variation patterns of feature parameters for different defect types.

[0097] For example, a scatter plot of principal component feature parameters versus defect types can be plotted, where each point represents a partial discharge event, its coordinates are determined by the principal component feature parameter values, and its color or shape indicates the defect type. This visualization method clearly shows the clustering and separation of different types of partial discharges in the feature parameter space.

[0098] It should also be noted that as monitoring of high-voltage equipment continues, new partial discharge characteristic information is constantly being generated, and it is necessary to integrate it into the spectrum library in a timely manner to maintain the timeliness and accuracy of the spectrum library.

[0099] In addition, necessary maintenance operations can be performed on the atlas library, such as data backup, index optimization, and data quality checks, to ensure the stable operation and efficient querying of the atlas library. For example, regularly checking the consistency and integrity of the data in the atlas library and promptly repairing or deleting erroneous data; optimizing the database index to improve query speed, thereby ensuring rapid data retrieval and analysis capabilities as the atlas library continues to grow in size.

[0100] This embodiment determines the current defect type corresponding to partial discharge feature information from preset defect types, including at least: corona discharge, suspended discharge, surface discharge, and free metal particle discharge. It obtains a feature annotation template corresponding to the current defect type and classifies and annotates the partial discharge feature information based on the template, obtaining classified and annotated partial discharge feature information, providing detailed classification data support for constructing a feature map library. Furthermore, it initializes the feature map library corresponding to the high-voltage equipment under test; analyzes the classified and annotated partial discharge feature information based on data mining technology, and generates feature parameters corresponding to each preset defect type based on the analysis results; updates the feature map library based on each feature parameter, constructing a partial discharge feature map library, which is beneficial for obtaining a more reliable and real-time partial discharge feature map library.

[0101] It should be noted that the above examples are only for understanding this application and do not constitute a limitation on the method for constructing partial discharge feature maps based on quantum detection technology. Any simple transformations based on this technical concept are within the protection scope of this application.

[0102] This application also provides a partial discharge feature map construction device. Please refer to... Figure 4 , Figure 4 This is a schematic diagram of the module structure of the partial discharge feature map construction device of this application. The device includes: Data acquisition module 401 is used to acquire quantum detection signal data of the high voltage device under test through a preset optical quantum sensor; Feature extraction module 402 is used to extract features from the quantum detection signal data to obtain corresponding partial discharge feature information; Feature classification module 403 is used to classify and label the partial discharge feature information based on a preset defect type to obtain the classified and labeled partial discharge feature information; The map construction module 404 is used to construct a partial discharge feature map library based on the partial discharge feature information after classification and labeling.

[0103] This embodiment leverages the high sensitivity and anti-interference capabilities of optical quantum sensors to accurately acquire quantum detection signal data generated by partial discharge, thereby improving the accuracy and reliability of partial discharge feature information extraction. By constructing a partial discharge feature map library, it can comprehensively cover the partial discharge characteristics of different types of high-voltage equipment under various operating conditions, providing rich data support for subsequent high-voltage equipment status identification and fault diagnosis. Simultaneously, the classification and labeling steps facilitate rapid and accurate identification of partial discharge types, further enhancing the practicality of the map library and diagnostic efficiency.

[0104] This application also provides a partial discharge feature map construction device, which includes: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to execute the partial discharge feature map construction method based on quantum detection technology in the first embodiment described above.

[0105] The following is for reference. Figure 5 , Figure 5 This is a schematic diagram of the partial discharge feature map construction device of this application. The partial discharge feature map construction device in the embodiments of this application may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Description), PMPs (Portable Media Players), etc., as well as fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The partial discharge feature map construction device shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of this application.

[0106] like Figure 5As shown, the partial discharge feature mapping construction device may include a processor 1001 (e.g., a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 1002 or a program loaded from a storage device 1003 into a random access memory (RAM) 1004. The RAM 1004 also stores various programs and data required for the operation of the partial discharge feature mapping construction device. The processor 1001, ROM 1002, and RAM 1004 are interconnected via a bus 1005. An input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, touchpad, keyboard, mouse, image sensor, microphone, accelerometer, gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), speaker, vibrator, etc.; storage devices 1003 including, for example, magnetic tape, hard disk, etc.; and communication devices 1009. Communication device 1009 allows the partial discharge feature mapping device to communicate wirelessly or wiredly with other devices to exchange data. Although the figure shows partial discharge feature mapping devices with various systems, it should be understood that implementation or possession of all the systems shown is not required. More or fewer systems may be implemented alternatively.

[0107] The partial discharge feature map construction device provided in this application employs the partial discharge feature map construction method based on quantum detection technology in the above embodiments, which can solve the technical problem of partial discharge feature map construction based on quantum detection technology. Compared with the prior art, the beneficial effects of the partial discharge feature map construction device provided in this application are the same as those of the partial discharge feature map construction method based on quantum detection technology provided in the above embodiments, and other technical features in this partial discharge feature map construction device are the same as those disclosed in the method of the previous embodiment, and will not be repeated here.

[0108] This application also provides a computer-readable storage medium having computer-readable program instructions (i.e., a computer program) stored thereon, the computer-readable program instructions being used to execute the partial discharge feature map construction method based on quantum detection technology in the above embodiments.

[0109] The computer-readable storage medium provided in this application may be, for example, a USB flash drive, but is not limited to, electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices, or any combination thereof. More specific examples of computer-readable storage media may include, but are not limited to: electrical connections having one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, system, or device. The program code contained on the computer-readable storage medium may be transmitted using any suitable medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination thereof.

[0110] The readable storage medium provided in this application is a computer-readable storage medium that stores computer-readable program instructions (i.e., a computer program) for executing the above-described method for constructing partial discharge feature maps based on quantum detection technology, thereby solving the technical problem of constructing partial discharge feature maps based on quantum detection technology. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as those of the partial discharge feature map construction method based on quantum detection technology provided in the above embodiments, and will not be repeated here.

[0111] It should be noted that, in this document, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or system. Unless otherwise specified, an element defined by the phrase "comprising one..." does not exclude the presence of other elements in the process, method, article, or system that includes that element.

[0112] The sequence numbers of the above embodiments of the present invention are merely for description and do not represent the superiority or inferiority of the embodiments. They are only some embodiments of this application and do not limit the patent scope of this application. All equivalent structural transformations made under the technical concept of this application and using the content of the specification and drawings of this application, or direct / indirect applications in other related technical fields, are included within the patent protection scope of this application.

Claims

1. A method for constructing a partial discharge feature map based on quantum detection technology, characterized in that, The method is applied to a partial discharge feature map construction device equipped with a preset optical quantum sensor, and the method includes: The quantum detection signal data of the high-voltage device under test is acquired through the preset optical quantum sensor; Feature extraction is performed on the quantum detection signal data to obtain the corresponding partial discharge feature information; The partial discharge feature information is classified and labeled based on a preset defect type to obtain the classified and labeled partial discharge feature information. A partial discharge feature map library is constructed based on the partial discharge feature information after classification and labeling.

2. The method as described in claim 1, characterized in that, The preset optical quantum sensor includes: a light source module, a polarization encoding module, and a detection module; The step of acquiring quantum detection signal data of the high-voltage device under test through the preset optical quantum sensor includes: The light source module generates weakly coherent light pulses, and the average number of photons in the weakly coherent light pulses is controlled at the level of a single photon. The weak coherent light pulse is polarized by a polarization encoding module to generate photons with a preset polarization direction so that the photons can be transmitted in the space where the high voltage equipment under test is located. The detection module acquires quantum detection signal data generated by the photons under the interference of the magnetic field of the high-voltage equipment under test.

3. The method as described in claim 2, characterized in that, The detection module includes: a single-photon avalanche diode and a polarization beam splitter; The step of acquiring quantum detection signal data generated by the photon under the magnetic field interference of the high-voltage equipment under test through the detection module includes: The photons are separated according to different polarization directions by the polarization beam splitter and guided to the corresponding single-photon avalanche diode for detection, thereby obtaining the trajectory of the photon's state change. Quantum detection signal data is generated based on the state change trajectory.

4. The method as described in claim 1, characterized in that, The step of extracting features from the quantum detection signal data to obtain corresponding partial discharge feature information includes: The quantum detection signal data is preprocessed to obtain effective detection signal data; The polarization state change parameters of the quantum detection signal data are extracted, including polarization degree, polarization selection angle and polarization mode distribution. The corresponding partial discharge feature information is determined based on the feature extraction results.

5. The method as described in claim 1, characterized in that, The step of classifying and labeling the partial discharge feature information based on a preset defect type to obtain the classified and labeled partial discharge feature information includes: The current defect type corresponding to the partial discharge feature information is determined from the preset defect types. The preset defect types include at least: corona discharge, suspension discharge, surface discharge, and free metal particle discharge. Obtain the feature annotation template corresponding to the current defect type, and classify and annotate the partial discharge feature information based on the feature annotation template to obtain the classified and annotated partial discharge feature information.

6. The method as described in claim 1, characterized in that, The step of constructing a partial discharge feature map library based on the classified and labeled partial discharge feature information includes: Initialize the feature map library corresponding to the high-voltage equipment under test; The partial discharge feature information after classification and labeling is analyzed based on data mining technology, and feature parameters corresponding to each preset defect type are generated based on the analysis results. The feature map library is updated according to each of the aforementioned feature parameters to construct a partial discharge feature map library.

7. The method as described in claim 6, characterized in that, The step of analyzing the classified and labeled partial discharge feature information based on data mining technology, and generating feature parameters corresponding to each preset defect type based on the analysis results, includes: Principal component analysis is used to perform high-discrimination feature screening on the classified and labeled partial discharge feature information to obtain principal component feature parameters. The feature parameters corresponding to each preset defect type are determined based on the principal component feature parameters.

8. A partial discharge feature map construction device, characterized in that, The device includes: The data acquisition module is used to acquire quantum detection signal data of the high-voltage device under test through a preset optical quantum sensor; The feature extraction module is used to extract features from the quantum detection signal data to obtain corresponding partial discharge feature information; The feature classification module is used to classify and label the partial discharge feature information based on a preset defect type, and obtain the classified and labeled partial discharge feature information. The map construction module is used to construct a partial discharge feature map library based on the partial discharge feature information after classification and labeling.

9. A partial discharge feature map construction device, characterized in that, The device includes: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the method for constructing a partial discharge feature map based on quantum detection technology as described in any one of claims 1 to 7.

10. A storage medium, characterized in that, The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, it implements the steps of the partial discharge feature map construction method based on quantum detection technology as described in any one of claims 1 to 7.

Images