An intelligent digital management method for an electrical product

Abstract

This application belongs to the field of data processing, and particularly relates to an intelligent digital management method for electrical products: setting a matching measuring device for the target object; an electro-optic crystal fiber sensor connected to a rotating electrode is mounted in the measuring device; the sensor is dynamically controlled by the rotating electrode to perform rotational motion to dynamically adjust the relative position between the sensor and the electric field where the target object is located; obtaining the motion trajectory of the sensor during the measurement process, and obtaining the electric field strength information measured for the target object at different relative positions through the sensor; inputting the motion trajectory and the electric field strength information into a measurement optimization model to optimize and adjust the electric field strength information, and executing a corresponding automatic management process for the target object based on the target electric field strength information. This method can improve the measurement accuracy, achieve real-time monitoring and automatic decision-making, and can also perform data-driven equipment maintenance and optimization, providing strong support for the management of electrical equipment.

Description

Technical Field

[0001] This application belongs to the field of data processing, and particularly relates to an intelligent digital management method for electrical products. Background Art

[0002] A high-voltage DC field will generate strong electromagnetic radiation, and this electromagnetic interference may affect the normal operation of the electronic components inside the measuring instrument.

[0003] In the related art, interference signals may be superimposed on the output signals of the sensors, resulting in deviations in the measurement data. For measurement devices based on electronic circuits, such as oscilloscopes, voltmeters, etc., these interferences may cause the displayed waveforms or values to jitter, distort, etc.

[0004] In addition, in the related art, in a high-voltage DC environment, the static electricity phenomenon is also relatively obvious. The accumulation of static electricity may damage the measurement devices and sensors. For example, electrostatic discharge may damage the sensitive components in the sensors or change their electrical properties, thereby affecting the measurement accuracy. Moreover, the electrostatic field may also interact with the measured DC electric field, generating a complex electric field distribution, which brings difficulties to the measurement.

[0005] Therefore, to solve the above at least one technical problem, there is an urgent need to propose a brand-new intelligent digital management solution for electrical products. Summary of the Invention

[0006] This application provides an intelligent digital management method for electrical products to propose a brand-new intelligent digital management solution for electrical products.

[0007] In a first aspect, this application provides an intelligent digital management method for electrical products, which is applied to the high-voltage DC field strength measurement scenario of the electrical device to be measured. The method includes:

[0008] Setting a matching measurement device for the target object; wherein, the target object is the electrical device to be measured; the measurement device is equipped with an electro-optic crystal fiber sensor connected to a rotating electrode;

[0009] Dynamically controlling the electro-optic crystal fiber sensor to perform a rotational motion through the rotating electrode to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located;

[0010] Obtaining the motion trajectory of the electro-optic crystal fiber sensor during the measurement process, and obtaining the electric field strength information measured for the target object at different relative positions through the electro-optic crystal fiber sensor; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field strength information;

[0011] Input the motion trajectory and the electric field intensity information into a measurement optimization model to optimize and adjust the electric field intensity information, and obtain the target electric field intensity information output finally; the measurement optimization model is used to simulate the change of the electric field intensity corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field intensity information based on the change situation;

[0012] Store the target electric field intensity information in a management database, and execute a corresponding automatic management process for the target object based on the target electric field intensity information.

[0013] In a second aspect, an intelligent digital management device for an electrical product provided by an embodiment of the present application is applied to a high-voltage DC field intensity measurement scenario of a to-be-tested electrical device. The device includes:

[0014] A setting unit configured to set a matching measurement device for a target object; wherein, the target object is a to-be-tested electrical device; an electro-optic crystal fiber sensor connected to a rotating electrode is mounted in the measurement device;

[0015] A control unit configured to dynamically control the electro-optic crystal fiber sensor to perform a rotating motion through the rotating electrode, so as to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located;

[0016] An acquisition unit configured to acquire the motion trajectory of the electro-optic crystal fiber sensor during the measurement process, and acquire the electric field intensity information obtained by measuring the target object at different relative positions through the electro-optic crystal fiber sensor; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field intensity information;

[0017] An adjustment unit configured to input the motion trajectory and the electric field intensity information into a measurement optimization model to optimize and adjust the electric field intensity information, and obtain the target electric field intensity information output finally; the measurement optimization model is used to simulate the change of the electric field intensity corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field intensity information based on the change situation;

[0018] A management unit configured to store the target electric field intensity information in a management database, and execute a corresponding automatic management process for the target object based on the target electric field intensity information.

[0019] In a third aspect, an embodiment of the present application provides a computing device, and the computing device includes:

[0020] At least one processor, a memory and an input / output unit;

[0021] Among them, the memory is used to store a computer program, and the processor is used to call the computer program stored in the memory to execute the intelligent digital management method of the electrical product in the first aspect.

[0022] In a fourth aspect, a computer-readable storage medium is provided, which includes instructions that, when the instructions are run on a computer, cause the computer to execute the intelligent digital management method of the electrical product in the first aspect.

[0023] In the technical solution provided by the embodiments of the present application, first, a matching measuring device is set for the target object; among them, the target object is the electrical equipment to be measured; the measuring device is equipped with an electro-optic crystal fiber sensor connected to a rotating electrode. Then, the rotating electrode is used to dynamically control the electro-optic crystal fiber sensor to perform a rotating motion, so as to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located. Then, the motion trajectory of the electro-optic crystal fiber sensor during the measurement process is obtained, and through the electro-optic crystal fiber sensor, the electric field intensity information obtained by measuring the target object at different relative positions is obtained; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field intensity information. Furthermore, the motion trajectory and the electric field intensity information are input into a measurement optimization model to optimize and adjust the electric field intensity information, and the finally output target electric field intensity information is obtained; the measurement optimization model is used to simulate the change of the electric field intensity corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field intensity information based on the change. Finally, the target electric field intensity information is stored in the management database, and the corresponding automatic management process is executed on the target object based on the target electric field intensity information.

[0024] In the technical solution of the present application, the use of the measurement optimization model can improve the measurement accuracy. Combining multi-position measurement and dynamic optimization can further reduce the accumulation of errors. In addition, by collecting optical signal data from multiple angles through the rotating electrode, the data integrity is further increased, which helps to finally obtain and associate and store three-dimensional electric field information. The automatic management is efficient, realizing real-time monitoring and automatic decision-making, and can also perform data-driven equipment maintenance and optimization, providing strong support for the management of electrical equipment. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The schematic embodiments of the present application and their descriptions are used to explain the present application, and do not constitute an improper limitation of the present application. In the drawings:

[0026] Figure 1 is a schematic flowchart of an intelligent digital management method for an electrical product according to an embodiment of the present application;

[0027] Figure 2 It is a schematic diagram of the principle of an intelligent digital management method for an electrical product according to an embodiment of the present application;

[0028] Figure 3 It is a schematic diagram of the structure of an intelligent digital management device for an electrical product according to an embodiment of the present application;

[0029] Figure 4 It is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Detailed implementation manners

[0030] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Apparently, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0031] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this application belongs. The terms used herein in the specification of this application are only for the purpose of describing specific embodiments and are not intended to limit this application.

[0032] The embodiments of the present application provide an intelligent digital management method for an electrical product.

[0033] Specifically, first, the electro-optic crystal fiber sensor is rotated by a rotating electrode to obtain the electric field intensity information at different positions. This method can comprehensively cover the electric field around the target electrical equipment, avoiding the limitations of single-point measurement. For example, for electrical equipment with complex shapes or uneven electric field distributions, single-position measurement may produce large errors due to local electric field anomalies. However, multi-position measurement combined with a measurement optimization model can comprehensively analyze and optimize the data at each position, making the finally output target electric field intensity information closer to the true value.

[0034] Furthermore, the measurement optimization model simulates the change of the electric field intensity according to the movement trajectory of the sensor and dynamically optimizes the measurement data. During the measurement process, errors caused by environmental factors (such as temperature, humidity, electromagnetic interference, etc.) can be detected and corrected in a timely manner. For example, if the measured value of the electric field intensity at a certain position shows abnormal fluctuations due to interference, the model can refer to the data at other positions and the normal electric field distribution law to adjust the abnormal value, thereby reducing the accumulation of errors and effectively improving the measurement accuracy.

[0035] Furthermore, the rotational motion of the sensor enables the acquisition of electric field intensity information in three-dimensional space. It is possible to obtain not only the electric field data at different planar positions but also take into account the electric field variations in the height direction. This is very important for accurately describing the electric field distribution around electrical equipment, especially for electrical equipment with a certain height or multi-layer structure. For example, in the measurement of high-voltage equipment in a substation, this method can completely record the changes in the electric field intensity of the equipment in the vertical and horizontal directions, providing comprehensive data support for subsequent electric field analysis and equipment evaluation.

[0036] Next, the motion trajectory and the electric field intensity information are input into the database together, making the data have spatio-temporal correlation. This associated storage method facilitates the subsequent dynamic analysis of the electric field distribution. For example, it is possible to trace the change process of the electric field intensity along a specific motion path, understand the gradient changes, peak positions of the electric field, and the relationships between different positions. This is of great significance for studying the spatial distribution characteristics and temporal evolution laws of the electric field.

[0037] Finally, based on the target electric field intensity information stored in the management database, the system can achieve real-time monitoring of electrical equipment. Once an abnormal change occurs in the electric field intensity, such as exceeding a preset safety threshold or not conforming to the normal operating rules, the system can automatically trigger the corresponding management process. For example, in the power system, if the electric field intensity around a high-voltage DC device suddenly increases, it may indicate a device failure or a change in the external environment. The system can automatically issue an alarm to notify the maintenance personnel for inspection, or take some emergency control measures according to preset rules, such as adjusting the device operating parameters, thereby improving the safety and reliability of the device operation. In addition, the large amount of accumulated electric field intensity data and motion trajectory data can provide data support for the maintenance and optimization of electrical equipment. By analyzing historical data, it is possible to predict the change trend of the device's electric field intensity and formulate a maintenance plan in advance. For example, according to the long-term change of the electric field intensity, it is possible to determine whether the insulation performance of the device has deteriorated, and then decide whether insulation maintenance or upgrade of the device is required. At the same time, these data can also be used to optimize the deployment of measurement devices and measurement strategies, further improving the measurement efficiency and accuracy.

[0038] Compared with the strong electric field interference problem in the related art, in the embodiments of the present application, in the first aspect, the electro-optic crystal fiber sensor measures by utilizing the characteristic that the crystal refractive index is proportional to the electric field strength. As a signal transmission medium, the optical fiber itself has good electrical insulation, which enables the sensor to effectively avoid the interference caused by the direct action of the electric field on the signal transmission part in a strong electric field environment. Compared with traditional electrical sensors, the optical fiber sensor is less likely to be affected by electromagnetic interference because the optical fiber transmits optical signals instead of electrical signals, and it is difficult for a strong electric field to directly interfere with the optical signals. Furthermore, by rotating the electrode to dynamically control the rotation of the sensor, the sensor can obtain the electric field strength information at different positions. This way of dynamically adjusting the relative position can disperse the strong electric field interference in space. For example, if local strong electromagnetic interference occurs at a certain specific position, resulting in a deviation in the measurement data, then as the sensor rotates, the data obtained at other positions can, to a certain extent, compensate for this deviation. Moreover, by obtaining data at multiple positions, the interference situation can be comprehensively evaluated to identify abnormal data points that may be affected by interference.

[0039] In the second aspect, the measurement optimization model can simulate the change of the electric field strength corresponding to the target object under the motion trajectory. When there is strong electric field interference, the interference signal usually causes fluctuations in the measurement data that do not conform to the normal electric field distribution law. The model can identify these abnormal fluctuation data points by learning the distribution characteristics and change laws of the normal electric field, and filter or correct them during the optimization adjustment process. For example, if the measured value of the electric field strength at a certain position deviates too much from the normal electric field strength change trend simulated by the model at this position, the model can reduce the weight of this data point or correct it with other data points. Furthermore, based on the dynamic optimization of the electric field strength information by the model, the measurement error caused by strong electric field interference can be corrected in a timely manner. Since the model is comprehensively optimized according to the motion trajectory and the measurement data at multiple positions, the cumulative error caused by interference can be reduced to a certain extent. For example, during the process of the sensor rotating one week, even if the data at some positions are affected by interference, the model can use the data at other positions that are not affected or less affected by interference to optimize the overall measurement result, making the finally output target electric field strength information more accurate.

[0040] In a third aspect, the target electric field intensity information is stored in the management database, so that a large amount of measurement data can be accumulated. By analyzing these historical data, the variation law of the measurement data under different strong electric field interference conditions can be understood. For example, when it is found that the fluctuation amplitude of the measurement data significantly increases within a certain period and is different from the distribution characteristics of the previous normal measurement data, it can be inferred that there may be strong electric field interference. At the same time, by comparing with the historical data, the current measurement data can be more accurately evaluated and corrected. Based on the target electric field intensity information, an automatic management process is executed, and the strong electric field interference situation can be automatically processed according to the preset rules. For example, if the detected electric field intensity information exceeds the normal range and it is determined that it is an abnormal situation caused by strong electric field interference, the automatic management process can activate the corresponding alarm mechanism to remind the operator to pay attention; or it can automatically adjust the working parameters of the measurement device, such as adjusting the rotation speed of the sensor, changing the measurement frequency, etc., to obtain more accurate data, thereby reducing the influence of strong electric field interference on the measurement result.

[0041] The technical solution of this application can improve the measurement accuracy by using the measurement optimization model, and further reduce the error accumulation by combining multi-position measurement and dynamic optimization. In addition, by collecting optical signal data at multiple angles through the rotating electrode, the data integrity is further increased, which helps to finally obtain three-dimensional electric field information and associate and store it. The automatic management is efficient, realizing real-time monitoring and automatic decision-making, and can also perform data-driven equipment maintenance and optimization, providing strong support for the management of electrical equipment.

[0042] The intelligent digital management solution for electrical products provided by the embodiments of this application can be executed by an electronic device, which can be a server, a server cluster, or a cloud server. The electronic device can also be a terminal device such as a mobile phone, a computer, a tablet computer, a wearable device, or a dedicated device (such as a dedicated terminal device with an intelligent digital management system for electrical products, etc.). In an alternative embodiment, a service program for executing the intelligent digital management solution for electrical products can be installed on the electronic device.

[0043] Figure 1 Schematic diagram of an intelligent digital management method for an electrical product provided by an embodiment of this application, as Figure 1 shown, the method includes the following steps:

[0044] 101. Set a matching measurement device for the target object; wherein, the target object is the electrical equipment to be measured; the measurement device is equipped with an electro-optic crystal fiber sensor connected to the rotating electrode;

[0045] 102. Dynamically control the electro-optic crystal fiber sensor to perform a rotational motion through the rotating electrode, so as to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located;

[0046] 103. Obtain the movement trajectory of the electro-optic crystal fiber sensor during the measurement process, and through the electro-optic crystal fiber sensor, obtain the electric field intensity information measured for the target object at different relative positions; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field intensity information.

[0047] 104. Input the movement trajectory and the electric field intensity information into the measurement optimization model, optimize and adjust the electric field intensity information, and obtain the target electric field intensity information of the final output; the measurement optimization model is used to simulate the change of the electric field intensity corresponding to the target object under the movement trajectory, and dynamically optimize the measured electric field intensity information based on the change situation.

[0048] 105. Store the target electric field intensity information in the management database, and execute the corresponding automatic management process for the target object based on the target electric field intensity information.

[0049] In the embodiments of the present application, the electro-optic crystal is one of the core components of this sensor. The electro-optic effect refers to the fact that when an external electric field acts on certain crystals, their refractive index will change. This change has a certain functional relationship with the electric field intensity. For example, for the linear electro-optic effect (Pockels effect), the change in the refractive index of the crystal is proportional to the electric field intensity. By detecting the change in the refractive index of the electro-optic crystal, the electric field intensity can be indirectly measured. The following specifically describes the components of the sensor:

[0050] Optical fiber transmission: The optical fiber plays a role in transmitting optical signals in this sensor. The optical signal propagates in the optical fiber and enters the electro-optic crystal. When an electric field acts on the electro-optic crystal, the refractive index of the crystal changes, resulting in changes in the polarization state, phase and other characteristics of the light. These changed optical signals are then transmitted out through the optical fiber for subsequent detection.

[0051] Rotating electrode: The design of the rotating electrode has its unique advantages. On the one hand, it can change the relative position between the electrode and the electric field, and different directions of electric field information can be obtained through rotation. Compared with traditional fixed electrodes, the rotating electrode can more comprehensively reflect the spatial distribution of the electric field. For example, in a high-voltage DC field, the direction of the electric field is fixed, but the electric field intensity at different positions may be different, and the rotating electrode can sample the electric field at different angles.

[0052] Electrode part: The rotating electrode needs to have good electrical conductivity and mechanical stability. Metals such as copper and aluminum are usually used to make the electrode. The shape and size of the electrode should be designed considering the effective coupling with the electric field. For example, the surface area and shape (such as spherical, disc-shaped, etc.) of the electrode will affect its interaction with the electric field. Moreover, the rotation axis of the electrode should ensure high-precision rotation, reducing mechanical friction and wobbling to ensure the accuracy of measurement.

[0053] Electro-optic crystal part: The selection of the electro-optic crystal should be determined according to factors such as the measured electric field strength range and wavelength. Common electro-optic crystals include lithium niobate (LiNbO3), lithium tantalate (LiTaO3), etc. The encapsulation of the crystal is also very important. It is necessary to ensure that the crystal can be stably placed in the sensor and has good optical and electrical connections with the electrode and optical fiber. For example, the coupling between the crystal and the optical fiber can be achieved by lens coupling or direct coupling to ensure that the optical signal can efficiently enter and exit the crystal.

[0054] Optical fiber part: The appropriate type of optical fiber should be selected, such as single-mode optical fiber or multi-mode optical fiber. Single-mode optical fiber has better transmission characteristics and is suitable for high-precision measurement. The length of the optical fiber should be determined according to the actual measurement environment and signal transmission requirements. At the same time, the connection points between the optical fiber and the electro-optic crystal and other optical components should be well sealed and fixed to prevent interference from external environmental factors (such as dust, water vapor, etc.) on the optical signal transmission.

[0055] The following is a detailed introduction to the implementation methods and effects of each step:

[0056] In 101, according to factors such as the type, voltage level, size, and environment of the electrical equipment to be measured, an electro-optic crystal fiber sensor with appropriate parameters and specifications, as well as a supporting rotating electrode and measuring device, are selected. For example, for high-voltage and large-size equipment, a sensor with high sensitivity, a large measurement range, and the ability to adapt to a strong electric field environment needs to be selected.

[0057] In this way, it is ensured that the measuring device is highly compatible with the target electrical equipment, laying a foundation for accurately measuring the electric field strength subsequently, improving the pertinence and reliability of the measurement, and avoiding measurement errors or even equipment damage caused by device mismatch.

[0058] In 102, using a motor drive control system, the rotation speed, angle, and direction of the rotating electrode are precisely controlled, so that the electro-optic crystal fiber sensor performs a stable and uniform rotational motion according to a preset trajectory or program, thereby realizing the dynamic adjustment of its relative position with respect to the target electric field.

[0059] Thus, by changing the position of the sensor, multi-directional electric field information can be obtained, more comprehensively reflecting the distribution of the electric field around the electrical equipment, effectively reducing the one-sidedness of the measurement data caused by a single position, and improving the integrity and representativeness of the data.

[0060] In 103, during the rotation of the sensor, a high-precision position monitoring device (such as a gyroscope, an encoder, etc.) is used to record its motion trajectory in real time. At the same time, through the optical detection system of the electro-optic crystal fiber sensor, the change of the optical signal is converted into an electrical signal, and then the electric field strength information at different positions is obtained.

[0061] In this way, the synchronous acquisition of the motion trajectory and the electric field strength information is realized. Not only can the value of the electric field strength be obtained, but also its corresponding spatial position is clarified, providing a rich and accurate data source for subsequent data analysis and model processing, and helping to deeply understand the spatial characteristics of the electric field.

[0062] In 104, the collected motion trajectory and electric field strength data are input into a pre-constructed and trained measurement optimization model. Through learning a large amount of historical data and known electric field distribution rules, the model uses algorithms (such as neural network algorithms, regression algorithms, etc.) to analyze and process the input data, identify and correct possible measurement errors and outliers, so as to optimize the electric field strength information.

[0063] In this way, the accuracy and stability of the electric field strength measurement are significantly improved, the influence of factors such as environmental interference and sensor error on the measurement result is effectively reduced, and the finally output target electric field strength information is closer to the true value, providing a more reliable basis for the evaluation and management of electrical equipment.

[0064] In 105, the optimized target electric field strength information is stored in the management database in a structured data form, and a corresponding index and query system are established. At the same time, according to the preset judgment conditions such as the electric field strength threshold and change trend, an automated management program is written. When specific conditions are met, corresponding operation instructions are automatically triggered, such as alarm notification, equipment adjustment, etc.

[0065] Thus, it is convenient for the long-term storage, query and analysis of the electric field strength data, providing historical data support for the operation status monitoring, fault diagnosis and performance evaluation of the equipment. The automatic management process based on these data can timely detect abnormal electric field conditions, quickly take measures, ensure the safe and stable operation of electrical equipment, and improve the intelligent level and efficiency of equipment management.

[0066] Combining the above steps, the electric field strength information around the electrical equipment is accurately obtained through dynamic measurement and data optimization and used for automatic management. The electro-optic crystal fiber sensor with rotational motion is used to obtain the electric field strength at different positions while recording the motion trajectory. With the help of the measurement optimization model, the trajectory is combined to simulate the electric field change and optimize the strength information. Finally, the stored information is used for automatic management to ensure the safe and efficient operation of the equipment.

[0067] As an alternative embodiment, before setting a matching measuring device for the target object in 101, the external shape image information of the target object may also be scanned; the external shape image information at least includes: the depth image information of the target object; the external shape image information is obtained from image data captured from multiple perspectives. Furthermore, based on the external shape image information, the target deployment position of the electro-optic crystal fiber sensor is predicted through an optimized deployment model.

[0068] Specifically, by obtaining the external shape image data containing depth image information, the external shape, structural characteristics of the target electrical device, and the spatial position relationship of different components can be clearly presented. Based on these detailed information, the optimized deployment model can accurately identify the regions where the electric field intensity changes are more critical and complex, such as near the electrodes of the device, and the parts where the electric field is easily distorted due to irregular shapes. Deploying the sensor in these key regions can more targeted obtain the information reflecting the overall electric field characteristics of the device, avoid missing important measurement points, and make the measurement data more comprehensively cover the electric field situation around the device.

[0069] The external shape image information obtained from multiple perspectives helps to understand the spatial form of the device from multiple dimensions. Based on this, the optimized deployment model can comprehensively consider the device characteristics from different perspectives, reasonably plan the deployment positions of multiple sensors, form an effective layout in three-dimensional space, and achieve a three-dimensional measurement of the electric field around the device, further improving the comprehensiveness of the measurement, rather than being limited to local or planar measurements only.

[0070] If the prediction of the target deployment position of the sensor is not made in advance based on the external shape image, it may be necessary to try different positions around the device on a large scale to obtain suitable data, which will consume a large amount of time and manpower. After determining the target position through the optimized deployment model, the sensor can be directly deployed at the position most likely to obtain effective data, reducing the number of blind attempts, thereby improving the overall efficiency of the measurement work. Especially when facing complex large electrical equipment, this advantage is more obvious.

[0071] Based on the electric field distribution characteristics of the device analyzed from the external shape image, the optimized deployment model can determine the number of sensors required and the best deployment position of each sensor, avoiding waste of resources caused by over-deployment of sensors or incomplete measurement data caused by insufficient number of sensors. The limited sensor resources can be reasonably configured to exert the maximum measurement efficiency.

[0072] Shape image information such as depth images can reflect the actual environmental conditions of the target object. For example, whether there are obstacles or other interference sources around the device. When optimizing the deployment model to predict the sensor position, these environmental factors can be taken into consideration, and a position with less interference and more accurate reflection of the electric field strength can be selected for deployment, thereby reducing the interference of external factors on the measurement results and improving the accuracy of the measurement and the reliability of the data.

[0073] Since the shape image information visually shows the true shape of the device, the optimization deployment model can simulate a more realistic electric field distribution based on this, and then accurately arrange the sensor positions according to the electric field distribution law. In this way, the data obtained by the sensor can more truly reflect the electric field state of the device, reduce the measurement error caused by unreasonable positions, and improve the accuracy of the measurement results.

[0074] After determining the sensor deployment position through the shape image information, there is a clear corresponding relationship between the subsequent measured electric field strength information and the spatial position of the device. When analyzing the data, the electric field strength data can be more intuitively interpreted in combination with the shape structure of the device, and the distribution characteristics and change trends of the electric field in different parts can be analyzed, which helps to better understand the electrical performance and operating status of the device and provides strong support for subsequent device management decisions.

[0075] Based on the sensor deployment determined by the shape image, the data measured each time has a standardized association method in terms of spatial position, which is convenient for unified comparison, analysis and integration of the measurement data under different times and working conditions, helps to establish a long-term device electric field monitoring database, and provides a coherent and reliable data basis for the whole life cycle management of the device.

[0076] As an optional embodiment, in the above steps, predicting the target deployment position of the electro-optic crystal fiber sensor based on the shape image information through the optimization deployment model includes:

[0077] Through the extraction layer in the optimization deployment model, extract the shape contour of the target object from the shape image information; through the construction layer in the optimization deployment model, establish a virtual three-dimensional model of the target object based on the extracted shape contour; through the prediction layer in the optimization deployment model, predict the deployment situation based on the virtual three-dimensional model and the sensor attribute information to obtain the sensor deployment scores corresponding to each candidate deployment position; the sensor attribute information at least includes: the electro-optic coefficient, transparency, and stability of the electro-optic crystal in the electro-optic crystal fiber sensor; through the optimization layer in the optimization deployment model, screen the deployment positions based on the sensor deployment scores to obtain the target deployment position of the target object.

[0078] In terms of principle, first, the extraction layer of the optimized deployment model is used to extract the contour of the target object from the shape image information. This step uses image recognition and processing technologies to identify the boundary and shape features of the target electrical equipment in the image, providing the basic contour information for subsequent 3D model construction. Next, the construction layer constructs a virtual 3D model based on the extracted contour. It uses computer graphics and 3D modeling algorithms to convert the 2D contour information into a model in 3D space, which can more realistically simulate the spatial shape and structure of the target object. This virtual 3D model can be regarded as a digital copy of the target electrical equipment in the computer, containing spatial information such as the geometric shape and size of the equipment. Then, the prediction layer predicts the deployment situation based on the virtual 3D model and sensor attribute information. Since the 3D model reflects the spatial structure of the equipment, combined with the attributes of the sensor (such as electro-optic coefficient, transparency, stability, etc.), it is possible to estimate the situation after deploying the sensor at different positions through means such as physical field simulation, mathematical calculation, or machine learning algorithms. For example, according to the theory of electric field distribution, combined with the shape of the equipment, parameters such as the electric field strength and electric field gradient at different positions are calculated, and at the same time, the influence of the sensor's own attributes on the measurement is considered, so as to generate a sensor deployment score for each candidate deployment position. Finally, the optimization layer selects the target deployment position according to these sensor deployment scores. By comparing the scores of each candidate position, the position with the highest score is selected as the target deployment position. This process can adopt methods such as sorting and threshold judgment to ensure that the selected position can meet the measurement requirements to the greatest extent, comprehensively considering the characteristics of the electric field distribution of the equipment and the performance advantages of the sensor.

[0079] Based on this principle, this method can bring various effects. In terms of measurement accuracy, by establishing a virtual 3D model and combining sensor attributes for prediction, the sensor can be accurately deployed in the key areas of electric field strength change or positions that can comprehensively reflect the electric field distribution, so as to obtain more accurate electric field strength information. For example, for the edges or near the electrodes of equipment with large electric field distortion, the sensors can be reasonably arranged to make the measurement data closer to the true value.

[0080] In terms of efficiency, it avoids the situation of repeated position adjustment that may be caused by random sensor deployment. Through model prediction and screening, the optimal deployment position is determined at one time, reducing the time cost of experiments and adjustments. Especially in the measurement scenarios of complex equipment or large-scale equipment groups, it can significantly improve work efficiency.

[0081] In terms of resource utilization, the attributes of the sensors are fully considered, enabling each sensor to exert its maximum performance advantages. For example, according to the characteristics of electro-optic crystals, the sensors are deployed at positions where their electro-optic coefficients, transparency, etc. can be fully utilized, avoiding waste of sensor resources and extending the service life of the sensors, because placing them in a more suitable environment can reduce damage caused by harsh environments or improper use.

[0082] In addition, this method also facilitates subsequent measurement data management and analysis. Since the deployment positions of the sensors are determined based on the shape and model of the target object, there is a clear correspondence between the measurement data and the spatial positions of the devices, which is convenient for in-depth interpretation in combination with the device structure in subsequent analysis and helps to better understand the electrical characteristics and operating status of the devices.

[0083] As an optional embodiment, in the above steps, the method for obtaining the sensor deployment scores corresponding to each candidate deployment position is expressed by the following formula: ; where represents the sensor deployment score corresponding to the i-th candidate deployment position, represents the weight corresponding to the j-th influencing factor, represents the value of the j-th influencing factor under the i-th candidate deployment position, represents the weight value of the interaction between multiple factors, represents the degree of influence of the k-th influencing factor on another influencing factor l, represents the degree of influence of the l-th influencing factor on another influencing factor k, and n and m are constants.

[0084] In this way, by introducing the weight value of the interaction between factors and splitting the factor sum, the interaction between different factors can be refined and quantified. This quantification method can more accurately describe the influence of the cooperation or restriction between various factors on the sensor deployment effect at different candidate deployment positions. Compared with the simple weighted summation formula, it can more deeply explore the internal relationship between factors, thus improving the accuracy and scientificity of the scores.

[0085] In the complex scenario of high-voltage DC field strength measurement of electrical equipment, there are various factors intertwined and influencing each other. This formula can well adapt to this complexity. Whether considering the mutual relationship between various attributes of the sensors themselves or the interaction between the sensor attributes and the characteristics of the device's electric field distribution, accurate scoring can be carried out by reasonably setting parameters, providing a more reliable basis for screening out the optimal sensor deployment positions.

[0086] The sensor deployment score calculated using this formula can effectively sort and compare each candidate deployment location. After comprehensively considering various factors and their interactions, the candidate location with a higher score is more likely to be the optimal sensor deployment location. This helps the optimization layer quickly and accurately screen out the target deployment location, avoiding the subjectivity and blindness that may be brought about by making deployment decisions solely based on experience or simple rules, and improving the rationality and effectiveness of sensor deployment.

[0087] In practical applications, if it is found that the influence of certain factors on the measurement results has changed, or there are new factors to be considered, by adjusting parameters such as the weights, interaction weights, and splitting factor sums in the formula, the calculation method of the sensor deployment score can be flexibly updated, so as to adapt to new deployment requirements and scenario changes, providing strong support for dynamically optimizing the sensor deployment strategy.

[0088] As an alternative embodiment, in 103, obtaining the motion trajectory of the electro-optic crystal fiber sensor during the measurement process includes:

[0089] Selecting a measurement center point from the target object as the origin of the measurement space coordinate system; establishing a measurement space coordinate system based on the origin and obtaining the position coordinates of each measurement point of the electro-optic crystal fiber sensor during the measurement process to construct corresponding displacement information; obtaining the real-time attitude and real-time acceleration of the electro-optic crystal fiber sensor during the measurement process; based on the real-time attitude and the real-time acceleration, constructing the corresponding motion state change information of the electro-optic crystal fiber sensor in the motion trajectory; using the displacement information and the motion state change information as the motion trajectory.

[0090] Specifically, selecting a measurement center point from the target object as the origin of the measurement space coordinate system aims to provide a unified and fixed reference benchmark for accurately describing the sensor position subsequently. For example, for an electrical device with a relatively regular shape, its geometric center can be selected as the origin; for an irregular device, a key position with relatively symmetric electric field distribution can be selected as the origin, making the measurement around the device more logical and convenient in terms of spatial positioning.

[0091] After establishing a measurement space coordinate system (such as a common Cartesian coordinate system) based on the determined origin, the position coordinates of each measurement point of the electro-optic crystal fiber sensor during the measurement process can be obtained. By recording the coordinate values corresponding to the positions of the sensor at different times, displacement information is constructed. This is actually using coordinates to quantify the position change of the sensor relative to the origin, just like marking the coordinates of different locations on a map to determine the movement path, clearly showing the position movement of the sensor in the space around the device.

[0092] During the movement of the sensor, the real-time attitude reflects its states such as angles and orientations in space, which can be obtained by means of high-precision attitude sensors (such as inertial measurement units integrated with gyroscopes, accelerometers, etc.). The real-time acceleration reflects the change in the movement speed of the sensor and is also obtained through corresponding acceleration measurement devices. These data are crucial for accurately grasping the dynamic characteristics of the sensor because just knowing the change in position coordinates is not sufficient to fully describe its movement, and attitude and acceleration information can further refine the movement details.

[0093] Based on the obtained real-time attitude and real-time acceleration, information on the change in the movement state is constructed. For example, a change in attitude means a change in the direction of the sensor, and a change in acceleration can reflect whether its movement is in an accelerating, decelerating, or uniform state, etc. By integrating the displacement information with the information on the change in the movement state, the movement trajectory of the sensor during the entire measurement process is completely outlined, clearly presenting the starting position, the path passed, the final position, and various state changes during the movement process.

[0094] In this way, through a clear measurement space coordinate system and the recording of the position coordinates of each measurement point, the position of the sensor relative to the target object in three-dimensional space can be accurately determined. One can not only know its final reached position but also clearly understand each point it has passed through. Combining the information on the change in the movement state, the movement trajectory of the sensor can be accurately reproduced in environments such as computer simulations later, which is very helpful for analyzing the measurement process, troubleshooting possible problems, and reviewing the data acquisition situation, etc.

[0095] The information on the change in the movement state constructed by obtaining the real-time attitude and real-time acceleration enables users to comprehensively master the movement characteristics of the sensor. When analyzing the measured electric field strength information, these movement characteristics can be associated and comprehensively considered. For example, when it is found that the electric field strength data at a certain position is abnormal, one can check the movement state of the sensor at that position (such as whether it passes through accelerating or stays steadily, etc.) to determine whether the movement state affects the measurement result, so as to process and interpret the data more scientifically.

[0096] Since the movement trajectory is completely recorded, including detailed displacements and changes in the movement state, the entire measurement process becomes more transparent and traceable. This helps to improve the reliability of the measurement result because the rationality of the data can be verified from the perspective of the movement trajectory. At the same time, when presenting the measurement situation to other people or in subsequent reports, the rich movement trajectory information can make the measurement result more interpretable, facilitating others to understand the scientificity and accuracy of the measurement.

[0097] Such detailed motion trajectory information can serve as an important basis for subsequent optimization of the measurement scheme. For example, if it is found that the trajectory coverage in a certain area during a certain measurement is not comprehensive enough or the motion state is not ideal, resulting in poor data quality, the motion mode of the sensor can be adjusted accordingly during the next measurement. Moreover, for cases where repeated measurements are required for comparison and verification, the previous motion trajectory can be used as a reference template to ensure the consistency and comparability of each measurement.

[0098] As an optional embodiment, in 103, the electric field intensity information obtained by measuring the target object at different relative positions through the electro-optic crystal fiber sensor includes:

[0099] Obtain the calibration compensation information of the electro-optic crystal fiber sensor; collect the corresponding optical signal change information at each measurement point through the electro-optic crystal fiber sensor; the optical signal change information at least includes: the phase change information of the electro-optic crystal fiber sensor; perform phase correction on the optical signal change information by using the calibration compensation information; based on the pre-set mapping relationship between the optical signal phase and the electric field intensity, convert the corrected optical signal change information into the corresponding electric field intensity information.

[0100] It can be understood that, first of all, the calibration compensation information of the electro-optic crystal fiber sensor is obtained because the sensor itself may have some systematic errors or be affected by environmental factors and deviate. This calibration compensation information can be obtained through pre-calibration experiments or theoretical calculations, and is used to correct the errors of the sensor during the measurement process.

[0101] When collecting the corresponding optical signal change information at each measurement point through the electro-optic crystal fiber sensor, the phase change information is particularly crucial. Due to the characteristics of the electro-optic crystal, the change in the electric field intensity will cause a change in the refractive index of the crystal, which in turn causes a change in the phase of the light when it propagates in the crystal. There is an inherent physical connection between this phase change of the optical signal and the electric field intensity.

[0102] Performing phase correction on the optical signal change information by using the calibration compensation information is to eliminate the interference of the sensor itself and external factors (such as temperature, mechanical stress, etc.) on the optical signal phase, so that the obtained phase change information can more accurately reflect the true change of the electric field intensity.

[0103] Finally, based on the pre-set mapping relationship between the optical signal phase and the electric field intensity, convert the corrected optical signal change information into the corresponding electric field intensity information. This mapping relationship is usually derived through experimental calibration or theoretical formulas based on the electro-optic effect. It establishes a quantitative conversion relationship between the optical signal phase change and the electric field intensity, thereby realizing the conversion from optical signal measurement to electric field intensity measurement.

[0104] In terms of accuracy, by correcting the optical signal change information with the calibration compensation information, the influence of sensor errors and environmental factors on the measurement results can be effectively reduced, making the converted electric field strength information more accurate. For example, it can correct the phase drift of the optical signal caused by temperature changes, thus more accurately reflecting the true value of the electric field strength.

[0105] In terms of reliability, the conversion based on the pre-set mapping relationship provides a reliable physical and mathematical basis for obtaining the electric field strength information. This standardized conversion process improves the reliability of the measurement results, making the data under different measurement conditions comparable, which is convenient for long-term monitoring and analysis of the electric field strength of electrical equipment.

[0106] From the perspective of measurement integrity, since the electric field strength information at different relative positions can be obtained and combined with the movement trajectory of the sensor, the spatial distribution of the electric field strength around the electrical equipment can be comprehensively depicted. This is of great value for deeply understanding the electric field characteristics of electrical equipment, evaluating its operating status, and performing subsequent fault diagnosis and other tasks.

[0107] Further optionally, before actual measurement, the electro-optic crystal fiber sensor needs to be calibrated. This can be achieved by conducting experiments in a standard electric field environment with a known electric field strength. For example, a standard electric field generator is used to generate a stable and known-intensity electric field, the sensor is placed in it, and the phase change of the optical signal at this time is recorded. By changing the electric field strength and repeating the measurement of the phase change of the optical signal, a standard curve of the electric field strength and the phase change of the optical signal is established. During this process, the error information caused by the sensor's own characteristics (such as the non-uniformity of the electro-optic crystal, micro-bending loss of the optical fiber, etc.) and environmental factors (such as temperature, humidity, etc.) is recorded at the same time. This error information is an important part of the calibration compensation information.

[0108] In addition to experimental calibration, the theoretical knowledge of the electro-optic effect can also be combined to calculate some possible error factors. For example, for an electro-optic crystal, according to the relationship between its electro-optic coefficient, electric field strength, and light refractive index (such as the Pockels effect formula), considering the influence of the non-ideality of the crystal internal structure on light propagation, the theoretically possible phase deviation is calculated. At the same time, considering the optical characteristics of the optical fiber, such as the refractive index distribution of the optical fiber, mode coupling, and other factors' potential influence on the phase of the optical signal, the compensation amount corresponding to these factors is estimated through a theoretical model and combined with the information obtained from experimental calibration to form complete calibration compensation information.

[0109] The electro-optic crystal fiber sensor operates based on the electro-optic effect. When the sensor is in an electric field environment, the electric field causes a change in the refractive index of the electro-optic crystal. During the measurement process, an optical signal is transmitted to the detector through an optical fiber, and the detector can detect the phase change information of the optical signal. For example, using an optical detection device such as an interferometer, the optical signal containing the phase change is interfered with a reference optical signal, and the phase change of the optical signal is obtained by analyzing the movement of the interference fringes or the change in optical intensity. When collecting the phase change information of the optical signal, it should be noted that various factors may affect it. In addition to the phase change caused by the electric field, the movement of the sensor (such as vibration, rotation, etc.) may cause slight deformation of the optical fiber, thereby changing the propagation path and phase of the light in the optical fiber. In addition, changes in the ambient temperature will also cause a change in the refractive index of the electro-optic crystal, thereby affecting the phase of the optical signal. Therefore, during the collection process, information such as the movement state of the sensor and the ambient temperature needs to be recorded simultaneously for subsequent comprehensive analysis and correction.

[0110] As an optional embodiment, in 103, the process of converting the corrected optical signal change information into the corresponding electric field strength information based on the mapping relationship is expressed by the following formula:

[0111]

[0112] Where, is the phase difference of the optical signal measured by the electro-optic crystal fiber sensor at the i-th position, is the electric field strength corresponding to the i-th position, is the optical signal propagation distance, is the optical signal wavelength, is the refractive index of the electro-optic crystal, is the electro-optical coefficient, and are the temperature correction coefficients, represents the optical intensity after propagation distance under the first temperature condition, represents the optical intensity after propagation distance under the second temperature condition.

[0113] During the phase correction process, based on the obtained correction compensation information, direct correction is performed on the phase change of the collected optical signal. For example, if the correction compensation information shows that at the current ambient temperature, the temperature will cause the phase drift of the optical signal, and the drift amount is a specific value, then subtract the phase drift amount caused by the temperature from the total measured phase change to eliminate the influence of temperature. Similarly, if it is determined through calibration experiments that the sensor itself has a fixed phase deviation, also subtract this fixed phase deviation from the total measured phase change. For the phase change caused by the movement of the sensor, according to the recorded motion states (such as acceleration, angular velocity, etc.) and the pre-established motion and phase change model, calculate the specific value of the phase deviation caused by the motion, and then perform the corresponding correction operation.

[0114] Since environmental factors and sensor states may change dynamically, the phase correction needs to be performed in real time. During the measurement process, the correction compensation information is continuously updated to adapt to these changes. For example, by real-time monitoring of the ambient temperature and using the dynamic model of temperature-phase change (which may be an empirical formula obtained by experimental fitting or a theoretical formula derived based on physical principles), calculate the phase deviation caused by temperature in real time and correct the phase of the optical signal in a timely manner. Similarly, for the phase change caused by the movement of the sensor, perform dynamic correction according to the real-time motion state feedback to ensure that the measured phase change of the optical signal can reflect the change caused by the electric field strength as accurately as possible.

[0115] To further improve the accuracy of the correction, an iterative optimization method can be adopted. After a preliminary correction, based on the difference between the converted electric field strength information and the expected value (such as the estimated value of the electric field strength obtained according to the known characteristics of the electrical equipment or other reference measurement methods), reverse infer the possible remaining phase error. Then, adjust the correction compensation information and perform the correction process again. Through multiple iterations, make the corrected phase change information of the optical signal more consistent with the phase change caused by the real electric field strength, thereby improving the accuracy of the electric field strength measurement.

[0116] In 104, input the motion trajectory and the electric field strength information into the measurement optimization model, optimize and adjust the electric field strength information, and obtain the final output target electric field strength information. In the embodiment of the present application, the measurement optimization model is used to simulate the change situation of the electric field strength corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field strength information based on the change situation.

[0117] As an alternative embodiment, first, a physical model of the electric field around the target electrical device is constructed based on electromagnetic theory. For simple geometries (such as spheres, cylinders, etc.), analytical solutions (such as Gauss's law, etc.) can be used to describe the electric field distribution. For electrical devices with complex shapes, numerical calculation methods (such as the finite element method, boundary element method) may be required to solve for the electric field. These methods divide the space around the device into discrete elements and, by combining boundary conditions such as the geometric shape and charge distribution of the device, solve Maxwell's equations to obtain the distribution of the electric field strength in space.

[0118] Integrate the motion trajectory information of the sensor into the electric field simulation. Consider that when the sensor is at different positions (determined by the motion trajectory), the electric field environment it is in is constantly changing. Based on the position coordinates, attitude, and motion speed of the sensor, determine the theoretical values of the electric field position and electric field strength corresponding to the sensor at each time step. At the same time, preprocess the measured electric field strength information, including data cleaning (removing obvious abnormal data points, such as outliers caused by electromagnetic interference) and normalization (mapping the electric field strength data to a specific range, such as [0,1], for convenient subsequent model processing), etc. For example, a neural network model (such as a multi-layer perceptron, convolutional neural network, recurrent neural network, etc.) or a traditional mathematical model (such as a regression model, interpolation model, etc.) can be selected to construct a measurement optimization model. Neural network models have strong non-linear fitting capabilities and can learn complex electric field strength change rules; traditional mathematical models can quickly obtain results through simple mathematical formula fitting when the data distribution has certain patterns. Taking a neural network as an example, construct a multi-layer perceptron model, where the input layer includes sensor position information (such as coordinates, attitude, etc.) and the original measured electric field strength value, and the output layer is the optimized electric field strength value.

[0119] Exemplarily, use the simulated theoretical values of the electric field strength (obtained by combining the motion trajectory and the electric field physical model) and the preprocessed actual measured electric field strength values as training data. Divide the training data into a training set, a validation set, and a test set, generally divided according to a certain ratio (such as 70% - 80% for training, 10% - 15% for validation, and 10% - 15% for testing).

[0120] During the training process, a loss function is defined to measure the difference between the model output and the true value (simulated theoretical electric field intensity value). For regression problems, commonly used loss functions include mean squared error (MSE), mean absolute error (MAE), etc. The parameters of the model (such as the weights and biases of the neural network) are adjusted through optimization algorithms (such as stochastic gradient descent, Adam, etc.) to continuously reduce the value of the loss function. During the training process, a validation set is used to monitor whether the model has overfitting (i.e., the model performs well on the training set but its performance deteriorates on the test set). If overfitting occurs, regularization methods (such as L1 and L2 regularization, Dropout, etc.) can be adopted to alleviate it.

[0121] During the actual measurement process, the real-time obtained sensor motion trajectory information and electric field intensity measurement data are input into the already trained measurement optimization model. The measurement optimization model optimizes the currently measured electric field intensity according to the input information and the previously learned law of electric field intensity change.

[0122] For example, the measurement optimization model can perform weighted adjustment on the currently measured electric field intensity value according to the change trend of the electric field intensity between the current position and the previous position of the sensor, as well as the simulated distribution of the electric field intensity in the surrounding space. If the currently measured value does not conform to the predicted change trend of the electric field intensity by the model and the difference exceeds a certain threshold, the model can correct the currently measured value through methods such as interpolation and fitting based on the measurement data and simulated data at surrounding positions, thus achieving dynamic optimization.

[0123] By simulating the change of the electric field intensity, the measurement optimization model can identify and correct errors in the measurement data. For example, when the sensor is affected by external electromagnetic interference or its own performance fluctuates, resulting in a deviation in the measured value of the electric field intensity, the model can judge whether the measured value is reasonable according to the electric field distribution law corresponding to the motion trajectory and correct it to a result closer to the true value. This kind of dynamic optimization can effectively reduce measurement errors and improve the accuracy of electric field intensity measurement.

[0124] The measurement optimization model can fuse the measurement data at different positions and different times and calibrate them. Since the sensor obtains the electric field intensity information at multiple positions during the motion process, the measurement optimization model can comprehensively consider these data, combine them with the electric field simulation results, make the measurement data more coordinated with each other, and avoid data inaccuracy problems caused by single-point measurement errors or local anomalies.

[0125] In the actual measurement environment, there are various noises (such as electromagnetic noise, noise caused by environmental vibration, etc.) that affect the stability of measurement data. The measurement optimization model can filter out the influence of these noises on the measurement data by learning the normal change law of the electric field strength. For example, for the small fluctuations in the measured value of the electric field strength caused by high-frequency electromagnetic noise, the model can regard these fluctuations as noises and smooth them according to the low-frequency characteristics of the electric field distribution and the trajectory information, so as to output more stable electric field strength data.

[0126] The measurement optimization model can evaluate the credibility of the measurement data. According to the input trajectory and measurement data, combined with the simulated change of the electric field strength, a credibility index is assigned to each measurement data point. For the data points with low credibility, lower weights can be given or further verification can be carried out in the subsequent analysis and decision-making process, so as to improve the reliability of the whole measurement data.

[0127] Based on the motion trajectory of the sensor and the optimized electric field strength data of the measurement, the spatial electric field distribution around the target electrical equipment can be reconstructed more accurately. Not only can the numerical value of the electric field strength be obtained, but also information such as the gradient change and anisotropy of the electric field strength in space can be understood. This is of great significance for comprehensively evaluating the electric field characteristics of electrical equipment and analyzing the influence of the electric field on the surrounding environment and equipment.

[0128] Since the measurement optimization model can optimize the electric field strength information in real time, it can effectively monitor the dynamic changes of the electric field around the electrical equipment. For example, during the processes of equipment startup, fault occurrence or load change, etc., the change of the electric field strength can be captured in time, providing more timely and accurate information for equipment condition monitoring and fault diagnosis.

[0129] As an optional embodiment, in 104, the specific implementation manner of optimizing and adjusting the electric field strength information to obtain the final output target electric field strength information is expressed by the following formula:

[0130]

[0131] Among them, represents the original measured electric field strength value corresponding weight coefficient, represents the weight coefficient corresponding to the electric field strength distribution function, represents the electric field strength value collected at the i-th position the electric field strength distribution function obtained by finite element simulation, represents the electric field strength value spatial position vector of, represents the electric field strength value spatial position vector of, represents the relative importance coefficient during the optimization adjustment process of the electric field strength at the j-th position. represents the optical signal phase corresponding to the j-th position, and m is a constant. The j-th position is the core position of the electric field strength distribution function corresponding to the i-th position.

[0132] In some embodiments, the intelligent digital management device of the electrical product can be deployed in a separable manner. Referring to Figure 2 , the intelligent digital management method of the electrical product provided by the embodiments of the present application can be based on Figure 2 an intelligent digital management system of an electrical product shown. The intelligent service analysis and optimization system can include a server 01 and a terminal device 02. The terminal device 02 can be a functional module set in the measuring device or other devices connected to the measuring device.

[0133] Specifically, the server 01 sets a matching measuring device for the target object; wherein, the target object is the electrical equipment to be measured; the measuring device is equipped with an electro-optic crystal fiber sensor connected to the rotating electrode. The terminal device 02 dynamically controls the electro-optic crystal fiber sensor to perform a rotating motion through the rotating electrode to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located. The terminal device 02 obtains the motion trajectory of the electro-optic crystal fiber sensor during the measurement process, and through the electro-optic crystal fiber sensor, the terminal device 02 obtains the electric field strength information measured on the target object at different relative positions; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field strength information. The terminal device 02 transmits the collected data to the server 01. The server 01 inputs the motion trajectory and the electric field strength information into the measurement optimization model to optimize and adjust the electric field strength information to obtain the finally output target electric field strength information; the measurement optimization model is used to simulate the change of the electric field strength corresponding to the target object under the motion trajectory and dynamically optimize the measured electric field strength information based on the change situation. Furthermore, the server 01 stores the target electric field strength information in the management database and executes the corresponding automatic management process for the target object based on the target electric field strength information.

[0134] It should be noted that the computing device involved in the embodiments of the present application can be a server and / or a terminal device.

[0135] The server involved in the embodiments of the present application can be an independent physical server, a server cluster or a distributed system composed of multiple physical servers, or a cloud server that provides basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communications, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms.

[0136] In the embodiments of the present application, the measurement optimization model can improve the measurement accuracy. By combining multi-position measurement and dynamic optimization, the error accumulation can be further reduced. In addition, by collecting optical signal data at multiple angles with a rotating electrode, the data integrity is further increased, which helps to finally obtain three-dimensional electric field information and associate and store it. The automated management is efficient, enabling real-time monitoring and automatic decision-making. It can also perform data-driven equipment maintenance and optimization, providing strong support for the management of electrical equipment.

[0137] In another embodiment of the present application, an intelligent digital management device for electrical products is also provided. Refer to Figure 3 As shown, this device is applied to the high-voltage DC field strength measurement scenario of the electrical equipment to be measured. The device includes the following units:

[0138] A setting unit configured to set a matching measurement device for the target object; where the target object is the electrical equipment to be measured; the measurement device is equipped with an electro-optic crystal fiber sensor connected to the rotating electrode;

[0139] A control unit configured to dynamically control the electro-optic crystal fiber sensor to perform a rotational movement through the rotating electrode, so as to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located;

[0140] An acquisition unit configured to acquire the movement trajectory of the electro-optic crystal fiber sensor during the measurement process, and acquire the electric field strength information obtained by measuring the target object at different relative positions through the electro-optic crystal fiber sensor; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field strength information;

[0141] An adjustment unit configured to input the movement trajectory and the electric field strength information into the measurement optimization model, optimize and adjust the electric field strength information, and obtain the finally output target electric field strength information; the measurement optimization model is used to simulate the change of the electric field strength corresponding to the target object under the movement trajectory, and dynamically optimize the measured electric field strength information based on the change;

[0142] A management unit configured to store the target electric field strength information in the management database, and execute the corresponding automatic management process for the target object based on the target electric field strength information.

[0143] Further optionally, before setting the matching measuring device for the target object, the setting unit is further configured to:

[0144] Scan the contour image information of the target object; the contour image information at least includes: the depth image information of the target object; the contour image information is from the image data captured from multiple perspectives;

[0145] Predict the target deployment position of the electro-optic crystal fiber sensor based on the contour image information through an optimized deployment model.

[0146] Further optionally, the setting unit, which predicts the target deployment position of the electro-optic crystal fiber sensor based on the contour image information through an optimized deployment model, is configured to:

[0147] Extract the contour of the target object from the contour image information through the extraction layer in the optimized deployment model;

[0148] Build a virtual three-dimensional model of the target object based on the extracted contour through the construction layer in the optimized deployment model;

[0149] Predict the deployment situation based on the virtual three-dimensional model and the sensor attribute information through the prediction layer in the optimized deployment model to obtain the sensor deployment scores corresponding to each candidate deployment position; the sensor attribute information at least includes: the electro-optic coefficient, transparency, and stability of the electro-optic crystal in the electro-optic crystal fiber sensor;

[0150] Screen the deployment positions based on the sensor deployment scores through the optimization layer in the optimized deployment model to obtain the target deployment position of the target object.

[0151] Further optionally, the acquisition method of the sensor deployment scores corresponding to each candidate deployment position is expressed by the following formula: ;

[0152] Wherein, represents the sensor deployment score corresponding to the i-th candidate deployment position, represents the weight corresponding to the j-th influencing factor, represents the value of the j-th influencing factor at the i-th candidate deployment position, represents the multi-factor interaction weight value, represents the influence degree of the k-th influencing factor on another influencing factor l, represents the influence degree of the l-th influencing factor on another influencing factor k, and n and m are constants.

[0153] Further optionally, the obtaining unit, which obtains the motion trajectory of the electro-optic crystal fiber sensor during the measurement process, is configured to:

[0154] Select a measurement center point from the target object as the origin of the measurement space coordinate system;

[0155] Establish a measurement space coordinate system based on the origin, and obtain the position coordinates of each measurement point of the electro-optic crystal fiber sensor during the measurement process, and construct the corresponding displacement information;

[0156] Obtain the real-time attitude and real-time acceleration of the electro-optic crystal fiber sensor during the measurement process;

[0157] Based on the real-time attitude and the real-time acceleration, construct the corresponding motion state change information of the electro-optic crystal fiber sensor in the motion trajectory;

[0158] Take the displacement information and the motion state change information as the motion trajectory.

[0159] Further optionally, the obtaining unit, which obtains the electric field strength information obtained by measuring the target object at different relative positions through the electro-optic crystal fiber sensor, is configured to:

[0160] Obtain the calibration compensation information of the electro-optic crystal fiber sensor;

[0161] Collect the corresponding optical signal change information at each measurement point through the electro-optic crystal fiber sensor; the optical signal change information at least includes: the phase change information of the electro-optic crystal fiber sensor;

[0162] Perform phase correction on the optical signal change information by using the calibration compensation information;

[0163] Based on the pre-set mapping relationship between the optical signal phase and the electric field strength, convert the corrected optical signal change information into the corresponding electric field strength information.

[0164] Further optionally, the process of converting the corrected optical signal change information into the corresponding electric field strength information based on the mapping relationship is expressed by the following formula:

[0165] ;

[0166] Wherein, is the optical signal phase difference measured by the electro-optic crystal fiber sensor at the i-th position, is the electric field strength corresponding to the i-th position, is the optical signal propagation distance, is the optical signal wavelength, is the refractive index of the electro-optic crystal, is the electro-optical coefficient, and is the temperature correction coefficient, represents the light intensity after passing through the propagation distance under the first temperature condition, represents the light intensity after passing through the propagation distance under the second temperature condition.

[0167] In the embodiments of the present application, the use of the measurement optimization model can improve the measurement accuracy. Combining multi-position measurement and dynamic optimization can further reduce error accumulation. In addition, by rotating the electrode to collect optical signal data from multiple angles, the data integrity is further increased, which helps to finally obtain three-dimensional electric field information and associate and store it. The automated management is efficient, realizing real-time monitoring and automatic decision-making. It can also perform data-driven equipment maintenance and optimization, providing strong support for the management of electrical equipment.

[0168] In another embodiment of the present application, an electronic device is further provided, including: a processor, a communication interface, a memory, and a communication bus. Among them, the processor, the communication interface, and the memory complete communication with each other through the communication bus;

[0169] The memory is used to store computer programs;

[0170] The processor is used to implement the intelligent digital management method of the electrical product described in the method embodiment when executing the program stored in the memory.

[0171] The communication bus mentioned in the above electronic device can be Figure 4 the communication bus 1140 in, and this communication bus 1140 can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. This communication bus 1140 can be divided into an address bus, a data bus, a control bus, etc.

[0172] For the sake of easy representation, Figure 4 only a thick line is used to represent it in, but it does not mean that there is only one bus or one type of bus.

[0173] The communication interface 1120 is used for communication between the above electronic device and other devices.

[0174] The memory 1130 may include a random access memory (RAM) or a non-volatile memory (non-volatile memory), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0175] The processor 1110 may be a general purpose processor, including a central processing unit (Central Processor).

[0176] It can also be a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components.

[0177] Accordingly, an embodiment of the present application further provides a computer-readable storage medium storing a computer program, which, when executed, can implement each step that can be executed by an electronic device in the above method embodiment.

Claims

1. An intelligent digital management method for electrical products, characterized in that: Applied to the scenario of high-voltage DC field strength measurement of electrical equipment to be tested, the method comprises: A matching measuring device is provided for the target object; wherein the target object is an electrical device to be measured; the measuring device is equipped with an electro-optical crystal fiber sensor connected to a rotating electrode; Dynamically controlling the electro-optic crystal fiber sensor to rotate by means of the rotating electrode to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located; Acquire the motion trajectory of the electro-optic crystal fiber sensor during the measurement process, and acquire the electric field strength information obtained by measuring the target object at different relative positions through the electro-optic crystal fiber sensor; the crystal refractive index in the electro-optic crystal fiber sensor is proportional to the electric field strength information; The motion trajectory and the electric field strength information are input into a measurement optimization model, and the electric field strength information is optimized and adjusted to obtain the target electric field strength information that is finally output; the measurement optimization model is used to simulate the change of the electric field strength corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field strength information based on the change; Storing the target electric field strength information in a management database, and executing a corresponding automatic management process on the target object based on the target electric field strength information; Among them, a physical model of the electric field around the target object is constructed based on electromagnetic theory; by dividing the space around the target object into discrete units, the Maxwell equations are solved in combination with the device geometry and charge distribution to obtain the simulated distribution of the electric field intensity in the surrounding space; the motion trajectory information of the electro-optical crystal fiber sensor is integrated into the electric field simulation; according to the position coordinates, posture and movement speed of the electro-optical crystal fiber sensor, the electric field position and electric field intensity theoretical value corresponding to the sensor at each time step are determined; The measurement optimization model performs weighted adjustment on the currently measured electric field strength value according to the changing trend of the electric field strength between the current position and the previous position of the electro-optical crystal fiber sensor, and the simulated distribution of the electric field strength in the surrounding space; if the currently measured electric field strength value does not match the predicted changing trend of the electric field strength, and the difference exceeds a certain threshold, the currently measured electric field strength value is corrected by interpolation and fitting according to the measurement data and simulated distribution of the surrounding positions; when the electric field strength measurement value of the electro-optical crystal fiber sensor is subject to external electromagnetic interference or its own performance fluctuations, resulting in deviations in the electric field strength measurement value, the electric field strength measurement value is judged to be reasonable according to the electric field distribution law corresponding to the motion trajectory information, and the electric field strength measurement value is corrected to a result closer to the true value.

2. The intelligent digital management method for electrical products according to claim 1, characterized in that: Before setting a matching measuring device for the target object, the method further includes: Scanning the appearance image information of the target object; the appearance image information at least includes: depth image information of the target object; the appearance image information comes from image data captured from multiple viewing angles; The target deployment position of the electro-optical crystal fiber sensor is predicted by optimizing the deployment model based on the appearance image information.

3. The intelligent digital management method for electrical products according to claim 2, characterized in that: The predicting the target deployment position of the electro-optical crystal fiber sensor by optimizing the deployment model based on the appearance image information includes: Extracting the outline of the target object from the outline image information by optimizing the extraction layer in the deployment model; By optimizing the construction layers in the deployment model, a virtual 3D model of the target object is established based on the extracted shape contours; By optimizing the prediction layer in the deployment model, the deployment situation is predicted based on the virtual three-dimensional model and sensor attribute information to obtain the sensor deployment score corresponding to each candidate deployment position; the sensor attribute information at least includes: the electro-optic coefficient, transparency, and stability of the electro-optic crystal in the electro-optic crystal fiber sensor; By optimizing the optimization layer in the deployment model, the deployment location is screened based on the sensor deployment score to obtain the target deployment location of the target object.

4. The intelligent digital management method for electrical products according to claim 3, characterized in that: The sensor deployment score corresponding to each candidate deployment location is obtained as follows: ； in, represents the sensor deployment score corresponding to the i-th candidate deployment location, represents the weight corresponding to the jth influencing factor, represents the value of the jth influencing factor under the i-th candidate deployment location, represents the multi-factor interaction weight value, It indicates the influence degree of the kth influencing factor on another influencing factor l. It represents the influence of the lth influencing factor on another influencing factor k, where n and m are constants.

5. The intelligent digital management method for electrical products according to claim 1, characterized in that: The obtaining of the motion trajectory of the electro-optical crystal fiber sensor during the measurement process includes: Select the measurement center point from the target object as the origin of the measurement space coordinate system; A measurement space coordinate system is established based on the origin, and the position coordinates of each measurement point of the electro-optical crystal fiber sensor during the measurement process are obtained to construct corresponding displacement information; Acquiring the real-time posture and real-time acceleration of the electro-optical crystal fiber sensor during the measurement process; Based on the real-time posture and the real-time acceleration, constructing the motion state change information corresponding to the electro-optical crystal fiber sensor in the motion trajectory; The displacement information and the motion state change information are used as the motion trajectory.

6. The intelligent digital management method for electrical products according to claim 5, characterized in that: The step of obtaining electric field strength information obtained by measuring the target object at different relative positions by means of the electro-optical crystal fiber sensor includes: Acquiring correction compensation information of the electro-optic crystal fiber sensor; The optical signal change information corresponding to each measuring point is collected by the electro-optic crystal fiber sensor; the optical signal change information at least includes: phase change information of the electro-optic crystal fiber sensor; Performing phase correction on the optical signal change information using the correction compensation information; Based on a preset mapping relationship between the optical signal phase and the electric field strength, the corrected optical signal change information is converted into corresponding electric field strength information.

7. The intelligent digital management method for electrical products according to claim 6, characterized in that: The process of converting the corrected optical signal change information into corresponding electric field strength information based on the mapping relationship is expressed as the following formula: ； in, is the optical signal phase difference measured by the electro-optic crystal fiber sensor at the i-th position, is the electric field intensity corresponding to the ith position, is the optical signal propagation distance, is the wavelength of the optical signal, is the refractive index of the electro-optic crystal, is the photoelectric coefficient, and is the temperature correction coefficient, Indicates the propagation distance under the first temperature condition The light intensity after Indicates the propagation distance under the second temperature condition After the light intensity.

8. An intelligent digital management device for electrical products, characterized in that: Applicable to the scenario of high-voltage DC field strength measurement of electrical equipment to be tested, the device comprises: A setting unit is configured to set a measuring device matching the target object; wherein the target object is an electrical device to be measured; the measuring device is equipped with an electro-optical crystal fiber sensor connected to a rotating electrode; a control unit configured to dynamically control the electro-optic crystal fiber sensor to perform rotational motion through the rotating electrode, so as to dynamically adjust the relative position between the electro-optic crystal fiber sensor and the electric field where the target object is located; an acquisition unit configured to acquire a motion trajectory of the electro-optical crystal fiber sensor during a measurement process, and acquire electric field strength information obtained by measuring a target object at different relative positions through the electro-optical crystal fiber sensor; a crystal refractive index in the electro-optical crystal fiber sensor is proportional to the electric field strength information; An adjustment unit is configured to input the motion trajectory and the electric field strength information into a measurement optimization model, optimize and adjust the electric field strength information, and obtain the target electric field strength information that is finally output; the measurement optimization model is used to simulate the change of the electric field strength corresponding to the target object under the motion trajectory, and dynamically optimize the measured electric field strength information based on the change; The adjustment unit is further configured to construct a physical model of the electric field around the target object based on electromagnetic theory; by dividing the space around the target object into discrete units, combining the device geometry and charge distribution, solving Maxwell's equations, and obtaining a simulated distribution of the electric field intensity in the surrounding space; integrating the motion trajectory information of the electro-optic crystal fiber sensor into the electric field simulation; and determining the electric field position and electric field intensity theoretical value corresponding to the sensor at each time step according to the position coordinates, posture and motion speed of the electro-optic crystal fiber sensor; The adjustment unit is further configured to perform weighted adjustment on the currently measured electric field strength value according to the electric field strength change trend between the current position and the previous position of the electro-optical crystal fiber sensor and the simulated distribution of the electric field strength in the surrounding space through the measurement optimization model; if the currently measured electric field strength value does not match the predicted electric field strength change trend, and the difference exceeds a certain threshold, the currently measured electric field strength value is corrected by interpolation and fitting according to the measurement data and simulated distribution of the surrounding positions; when the electric field strength measurement value of the electro-optical crystal fiber sensor is subject to external electromagnetic interference or its own performance fluctuations, resulting in a deviation in the electric field strength measurement value, judge whether the electric field strength measurement value is reasonable according to the electric field distribution law corresponding to the motion trajectory information, and correct the electric field strength measurement value to a result closer to the true value; The management unit is configured to store the target electric field strength information in a management database, and execute a corresponding automatic management process on the target object based on the target electric field strength information.

9. An electronic device, characterized in that: include: Memory for storing computer software programs; A processor is used to read and execute the computer software program, thereby implementing the intelligent digital management method of electrical products as described in any one of claims 1-7.

10. A non-transitory computer-readable storage medium, characterized in that: The storage medium stores a computer software program, and when the computer software program is executed by the processor, the intelligent digital management method for electrical products according to any one of claims 1 to 7 is implemented.

Images