DC insulating gas state evaluation method based on dark current measurement and related equipment

Abstract

The invention relates to the technical field of DC high-voltage GIS insulation, and discloses a DC insulating gas state evaluation method and related equipment based on dark current measurement, and the method comprises the steps: obtaining insulating gas dark current signals under different gas pressures, different guide rod roughness and different electric field characteristics; processing the obtained insulating gas dark current signal to obtain an average dark current value corresponding to each electric field intensity; and evaluating the insulation margin of the insulating gas under different conditions on the average dark current value based on an SVM algorithm, and completing the state evaluation of the insulating gas. According to the invention, through real-time measurement and processing of the dark current signal, real-time monitoring and dynamic evaluation of the state of the insulating gas can be realized.

Description

Technical Field

[0001] The invention relates to the technical field of DC high-voltage GIS insulation, and in particular to a DC insulating gas state assessment method based on dark current measurement and related equipment. Background Art

[0002] With the vigorous development of my country's ultra-high voltage power grid, as well as the further development of hydropower in the west and wind power resources in the southeast coast, the construction of ultra-high and ultra-high voltage direct current transmission projects will be further accelerated. DC field equipment is an important part of offshore converter stations and onshore converter stations. The higher the DC voltage level, the more space is needed for the power equipment to configure the converter station, especially for the air-insulated equipment used for switch operation and system reset in the DC field, such as disconnectors, grounding switches, current and voltage measurement systems, lightning arresters, gas-air bushings and cable connection equipment. Traditional open air-insulated DC field equipment occupies a large space, which limits the development of large-capacity and lightweight offshore platforms. my country's first flexible DC offshore wind power project, Jiangsu Rudong Offshore Wind Power Station, selected open DC field equipment. The DC gas-insulated switchgear GIS not only helps to reduce the footprint of onshore converter stations, but also helps to reduce the facility investment cost of offshore wind farms with large capacity and far from the shore. Compared with the DC field using air-insulated equipment, the space of the DC field using DC GIS can be reduced by 70%-95%, and it has higher reliability because the high-voltage components will not be affected by external dust, salty air, rain and snow, etc. Therefore, the research and development of DC GIS is the key to the future development of DC transmission technology.

[0003] DC field equipment is an important part of the DC system. The higher the DC voltage level, the more space is needed for the power equipment to be configured in the converter station, especially for the air-insulated equipment used for switch operation and system reset in the DC field, such as disconnectors, grounding switches, current and voltage measurement systems, lightning arresters, gas-air bushings and cable connection equipment. The DC gas-insulated switchgear (GIS) not only helps to reduce the floor space of the converter station, but also helps to reduce the facility investment cost of large-capacity new energy transmission equipment. Compared with the DC field using air-insulated equipment, the space of the DC field using DC GIS can be reduced by 70%-95%, and it has higher reliability because the high-voltage components will not be affected by external dust, salty air, rain and snow. At present, relevant research has been carried out internationally on the insulation problem of DC gas-insulated switchgear. For example, ABB has developed a ±320 kV DC GIS prototype, and Siemens has developed ±320 kV and ±500 kV DC GIS prototypes, providing important experience for the development of DC GIS. However, there is still no mature DC GIS product for engineering application, and no unified DC GIS insulation status detection and operation and maintenance method has been formed. Therefore, the evaluation of DC GIS gas insulation status under complex working conditions is an important means to achieve DC GIS operation and maintenance, and relevant research is urgently needed to provide important support for the localization of high-voltage DC GIS. Summary of the invention

[0004] In order to overcome the defects of the above-mentioned prior art, the purpose of the present invention is to provide a DC insulating gas state evaluation method and related equipment based on dark current measurement, so as to solve the technical problem of how to quickly detect the insulating gas state in the prior art.

[0005] The present invention is achieved through the following technical solutions: In a first aspect, the present invention provides a method for evaluating a DC insulating gas state based on dark current measurement, comprising: Obtain the insulating gas dark current signal under different gas pressures, different guide rod roughness and different electric field characteristics; The obtained insulating gas dark current signal is processed to obtain the average dark current value corresponding to each electric field strength; Based on the SVM algorithm, the insulation margin of the insulating gas under different conditions is evaluated by using the average dark current value to complete the state evaluation of the insulating gas.

[0006] Preferably, in the step of obtaining the insulating gas dark current signal under different gas pressures, different guide rod roughnesses and different electric field characteristics, the specific process is as follows: Set up an experimental device that can adjust gas pressure, guide rod roughness and electric field characteristics; Under multiple preset combinations of gas pressure, guide rod roughness and electric field characteristics, the dark current signal of the insulating gas is measured separately through the experimental device.

[0007] Preferably, in processing the acquired insulating gas dark current signal, the dark current signal at each electric field strength is filtered and smoothed, and then the average value of the dark current signal at each electric field strength is calculated to obtain the average dark current value corresponding to each electric field strength.

[0008] Preferably, the insulation margin of the insulating gas under different conditions is evaluated based on the average dark current value based on the SVM algorithm to complete the step of evaluating the state of the insulating gas, and the specific process is as follows: Adjust the feature vector format and select the training function and training parameter settings; Construct an SVM model, input the feature vector format into the SVM model, and set the training function and training parameters before training in the SVM model to obtain training samples; perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; The average dark current value corresponding to each electric field strength is input into the finally trained SVM model for testing to obtain the corresponding test training samples; Each test training sample is compared with the training sample to obtain a comparison result, and the insulation margin of the insulating gas under different conditions is evaluated through the comparison result.

[0009] Furthermore, in the step of comparing each test training sample with the training sample to obtain a comparison result, when the test training sample is the same as the training sample, the test training sample is qualified, otherwise it is unqualified.

[0010] In a second aspect, the present invention further provides a DC insulating gas state assessment system based on dark current measurement, comprising: A dark current signal acquisition module is used to obtain the dark current signal of insulating gas under different gas pressures, different guide rod roughness and different electric field characteristics; A signal processing module is used to process the obtained insulating gas dark current signal to obtain an average dark current value corresponding to each electric field strength; The evaluation module is used to evaluate the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm, so as to complete the state evaluation of the insulating gas.

[0011] Preferably, the evaluation module includes a data setting module, a model training module, a model testing module and a comparison module; Data setting module, used to adjust the feature vector format and select training functions and training parameter settings; The model training module is used to build the SVM model, input the feature vector format into the SVM model, and perform training in the SVM model after setting the training function and training parameters to obtain training samples; the training samples are back-tested in the SVM model to obtain the final trained SVM model; A model testing module is used to input the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; The comparison module is used to compare each test training sample with the training sample to obtain a comparison result, and evaluate the insulation margin of the insulating gas under different conditions through the comparison result.

[0012] In a third aspect, the present invention also provides a mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein when the processor executes the computer program, the steps of the DC insulating gas state assessment method based on dark current measurement as described above are implemented.

[0013] In a fourth aspect, the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the DC insulating gas state assessment method based on dark current measurement as described above.

[0014] In a fifth aspect, the present invention further provides a computer program product, comprising computer instructions, wherein the computer instructions instruct a computing device to execute operations corresponding to the DC insulating gas state assessment method based on dark current measurement as described above.

[0015] Compared with the prior art, the present invention has the following beneficial technical effects: The present invention provides a method for evaluating the state of a DC insulating gas based on dark current measurement. By acquiring the dark current signals of the insulating gas under different gas pressures, different guide rod roughnesses and different electric field characteristics, various factors affecting the state of the insulating gas can be comprehensively considered. This comprehensive data collection ensures the accuracy and reliability of the evaluation results. The SVM algorithm is introduced to evaluate the insulation margin of the average dark current value, thereby realizing the intelligence and automation of the evaluation process. The SVM algorithm not only improves the evaluation efficiency, but also reduces the errors caused by human factors, making the evaluation results more objective and accurate; the present invention can realize real-time monitoring and dynamic evaluation of the state of the insulating gas by measuring and processing the dark current signal in real time. This is of great significance for timely discovering the abnormal state of the insulating gas and preventing potential faults.

[0016] Furthermore, the application of the SVM algorithm makes the evaluation process more efficient, and can complete the processing and analysis of a large amount of data in a short time, thus improving the evaluation efficiency. This is particularly important for the evaluation of the insulating gas state of large-scale power systems, which can reduce labor costs and time costs.

[0017] Furthermore, through automated evaluation, errors caused by human factors are reduced. The SVM algorithm is data-driven and can objectively and accurately give evaluation results, avoiding the subjectivity and uncertainty of human judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 is a flow chart of a method for evaluating a DC insulating gas state based on dark current measurement in an embodiment of the present invention; Figure 2 Schematic diagram of raw dark current data measured by using a dark current measurement platform in an embodiment of the present invention; Figure 3 A data schematic diagram of processing the acquired insulating gas dark current signal in an embodiment of the present invention; Figure 4 Schematic diagram of the average dark current value corresponding to each electric field strength in an embodiment of the present invention; Figure 5 It is a flow chart of the algorithm of SVM in an embodiment of the present invention; Figure 6 Schematic diagram of the recognition effect and classification error of the test sample of SVM in an embodiment of the present invention; Figure 7 This is a schematic diagram of a DC insulating gas state assessment system based on dark current measurement in an embodiment of the present invention; Figure 8 This is a schematic diagram of the internal structure of the evaluation module in an embodiment of the present invention; In the figure: 1. Dark current signal acquisition module; 2. Signal processing module; 3. Evaluation module; 31. Data setting module; 32. Model training module; 33. Model testing module; 34. Comparison module. DETAILED DESCRIPTION

[0019] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0020] The object of the present invention is to provide a DC insulating gas state evaluation method based on dark current measurement and related equipment to solve the technical problem of how to quickly detect the insulating gas state in the prior art.

[0021] The present invention is further described in detail below in conjunction with the accompanying drawings: Example 1 See also Figure 1 In one embodiment of the present invention, a method for evaluating the state of a DC insulating gas based on dark current measurement is provided, comprising: Step 1, obtaining the insulating gas dark current signal under different gas pressures, different guide rod roughnesses and different electric field characteristics; Specifically, in the step of obtaining the insulating gas dark current signal under different gas pressures, different guide rod roughnesses and different electric field characteristics, the specific process is as follows: Set up an experimental device that can adjust gas pressure, guide rod roughness and electric field characteristics; Under multiple preset combinations of gas pressure, guide rod roughness and electric field characteristics, the dark current signal of the insulating gas is measured separately through the experimental device.

[0022] Step 2, processing the obtained insulating gas dark current signal to obtain the average dark current value corresponding to each electric field strength; Specifically, in processing the acquired insulating gas dark current signal, the dark current signal under each electric field strength is filtered and smoothed, and then the average value of the dark current signal under each electric field strength is calculated to obtain the average dark current value corresponding to each electric field strength.

[0023] Step 3, based on the SVM algorithm, the insulation margin of the insulating gas under different conditions is evaluated based on the average dark current value to complete the state evaluation of the insulating gas.

[0024] Specifically, the insulation margin of the insulating gas under different conditions is evaluated based on the average dark current value based on the SVM algorithm, and the step of completing the state evaluation of the insulating gas is as follows: S1, adjusting the feature vector format and selecting the training function and training parameter settings; S2, construct the SVM model, input the feature vector format into the SVM model, and set the training function and training parameters before training in the SVM model to obtain training samples; perform back-testing on the training samples in the SVM model to obtain the final trained SVM model, such as Figure 5 As shown; S3, inputting the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; S4, comparing each test training sample with the training sample to obtain a comparison result, and evaluating the insulation margin of the insulating gas under different conditions through the comparison result.

[0025] In the step of comparing each test training sample with the training sample to obtain a comparison result, if the test training sample is the same as the training sample, the test training sample is qualified, otherwise it is unqualified.

[0026] Specifically, in this embodiment, the format of the feature sample vector is adjusted based on the specific input format of the SVM training function and the test function; the radial basis kernel function is selected as the kernel function of the SVM program, which can solve the problem of linear inseparability of feature vectors in low-dimensional space by means of inner product.

[0027] The g parameter is set to 1 and the c parameter is set to 2 to ensure the fitting ability and corresponding generalization ability of the SVM model; in the process of creating and training the SVM model, the test sample feature vector in a specific format is input, and the kernel function, g parameter, and c parameter are set. After the training is completed, the training samples are back-tested to ensure the training effect of the training samples on the SVM model. The test sample feature vector is tested using the trained SVM model, and the prediction function based on LIBSVM can directly give the recognition accuracy of the SVM model.

[0028] In this embodiment, LIBSVM is used in MATLAB software to implement pattern recognition to identify the gas insulation margin under different gas types, different guide rod roughness, and different electric field characteristics; through SVM pattern recognition, the final recognition accuracy reaches more than 90%, and finally the insulation margin evaluation of the insulating gas is realized.

[0029] Wherein, in the method of the present invention, according to Figure 2 The figure shows the raw dark current data measured by the dark current measurement platform. The voltage is boosted once, and the voltage is boosted again after waiting for the dark current to stabilize. The Wiener filtering algorithm is used, with a filter order of 4, a cutoff frequency of 1 Hz, and a sampling frequency of 100 Hz. The filtered data is shown in FIG. Figure 3 As shown; after the dark current stabilizes, 200 data points are selected as the average value, which is the dark current value under the field strength, such as Figure 4 As shown; the g parameter of SVM is 1, the c parameter is 2, and the number of training feature vector samples is 200.

[0030] according to Figure 6 As shown in the figure, the recognition effect and classification error of the SVM test samples. 200 (50x4) feature vector samples were selected for SVM training, and then applied to 100 (25×4) test samples for pattern recognition. The final test accuracy of each pattern reached more than 90%. In summary, the present invention provides a method for evaluating the state of DC insulating gas based on dark current measurement. First, the dark current of insulating gas under different gas types, different guide rod roughness and different electric field characteristics is measured based on a coaxial structure dark current measurement platform, and then the dark current signal is filtered and the data is post-processed to obtain the average dark current value under the electric field strength. Then, the obtained dark current data is pattern recognized based on the SVM (support vector machine) algorithm to evaluate the insulation margin of the insulating gas under different conditions, thereby completing the evaluation of the state of the insulating gas. The present invention measures the dark current of the insulating gas in the DC GIS and uses the measured dark current signal to evaluate the state of the insulating gas. The recognition accuracy of this method exceeds 90%, and it can quickly and accurately detect the state of the insulating gas, providing an important means for the detection and operation and maintenance of the insulation performance of the DC GIS.

[0031] The present invention can comprehensively consider various factors affecting the state of insulating gas by acquiring the dark current signal of insulating gas under different gas pressures, different guide rod roughness and different electric field characteristics. This comprehensive data collection ensures the accuracy and reliability of the evaluation results. The SVM algorithm is introduced to evaluate the insulation margin of the average dark current value, realizing the intelligence and automation of the evaluation process. The SVM algorithm not only improves the evaluation efficiency, but also reduces the errors caused by human factors, making the evaluation results more objective and accurate; the present invention can realize real-time monitoring and dynamic evaluation of the state of insulating gas by measuring and processing the dark current signal in real time. This is of great significance for timely discovering the abnormal state of insulating gas and preventing potential faults.

[0032] Example 2 according to Figure 7 As shown, the present invention also provides a DC insulating gas state evaluation system based on dark current measurement, comprising: A dark current signal acquisition module 1 is used to acquire the dark current signal of the insulating gas under different gas pressures, different guide rod roughnesses and different electric field characteristics; The signal processing module 2 is used to process the obtained insulating gas dark current signal to obtain the corresponding average dark current value under each electric field strength; The evaluation module 3 is used to evaluate the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm, so as to complete the state evaluation of the insulating gas.

[0033] Among them, according to Figure 8 As shown, the evaluation module 1 includes a data setting module 31, a model training module 32, a model testing module 33 and a comparison module 34; A data setting module 31 is used to adjust the feature vector format and select training functions and training parameter settings; The model training module 32 is used to build an SVM model, input the feature vector format into the SVM model, and perform training in the SVM model after setting the training function and training parameters to obtain training samples; perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; The model testing module 33 is used to input the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; The comparison module 34 is used to compare each test training sample with the training sample to obtain a comparison result, and evaluate the insulation margin of the insulating gas under different conditions through the comparison result.

[0034] Example 3 The present invention also provides a mobile terminal, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, such as a DC insulating gas state evaluation program based on dark current measurement.

[0035] When the processor executes the computer program, the steps of the DC insulating gas state evaluation method based on dark current measurement are implemented, for example: Obtain the insulating gas dark current signal under different gas pressures, different guide rod roughness and different electric field characteristics; The obtained insulating gas dark current signal is processed to obtain the average dark current value corresponding to each electric field strength; Based on the SVM algorithm, the insulation margin of the insulating gas under different conditions is evaluated by using the average dark current value to complete the state evaluation of the insulating gas.

[0036] Alternatively, when the processor executes the computer program, the functions of each module in the above system are realized, for example: A dark current signal acquisition module 1 is used to acquire the dark current signal of the insulating gas under different gas pressures, different guide rod roughnesses and different electric field characteristics; The signal processing module 2 is used to process the obtained insulating gas dark current signal to obtain the corresponding average dark current value under each electric field strength; The evaluation module 3 is used to evaluate the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm, so as to complete the state evaluation of the insulating gas.

[0037] The evaluation module 3 includes a data setting module 31, a model training module 32, a model testing module 33 and a comparison module 34; A data setting module 31 is used to adjust the feature vector format and select training functions and training parameter settings; The model training module 32 is used to build an SVM model, input the feature vector format into the SVM model, and perform training in the SVM model after setting the training function and training parameters to obtain training samples; perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; The model testing module 33 is used to input the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; The comparison module 34 is used to compare each test training sample with the training sample to obtain a comparison result, and evaluate the insulation margin of the insulating gas under different conditions through the comparison result.

[0038] Exemplarily, the computer program may be divided into one or more modules / units, which are stored in the memory and executed by the processor to implement the present invention. The one or more modules / units may be a series of computer program instruction segments capable of implementing specific functions, which are used to describe the execution process of the computer program in the mobile terminal.

[0039] For example, the computer program may be divided into a dark current signal acquisition module 1, a signal processing module 2, an evaluation module 3, a data setting module 31, a model training module 32, a model testing module 33 and a comparison module 34; The specific functions of each module are as follows: A dark current signal acquisition module 1 is used to acquire the dark current signal of the insulating gas under different gas pressures, different guide rod roughnesses and different electric field characteristics; The signal processing module 2 is used to process the obtained insulating gas dark current signal to obtain the corresponding average dark current value under each electric field strength; The evaluation module 3 is used to evaluate the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm, so as to complete the state evaluation of the insulating gas.

[0040] The evaluation module includes a data setting module 31, a model training module 32, a model testing module 33 and a comparison module 34; A data setting module 31 is used to adjust the feature vector format and select training functions and training parameter settings; The model training module 32 is used to build an SVM model, input the feature vector format into the SVM model, and perform training in the SVM model after setting the training function and training parameters to obtain training samples; perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; The model testing module 33 is used to input the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; The comparison module 34 is used to compare each test training sample with the training sample to obtain a comparison result, and evaluate the insulation margin of the insulating gas under different conditions through the comparison result.

[0041] The mobile terminal may be a computing device such as a desktop computer, a notebook, a palm computer, a cloud server, etc. The mobile terminal may include, but is not limited to, a processor and a memory.

[0042] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the mobile terminal, and uses various interfaces and lines to connect various parts of the entire mobile terminal.

[0043] The memory may be used to store the computer programs and / or modules, and the processor implements various functions of the mobile terminal by running or executing the computer programs and / or modules stored in the memory and calling the data stored in the memory.

[0044] The memory may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory may include a high-speed random access memory, and may also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (SmartMediaCard, SMC), a secure digital (SecureDigital, SD) card, a flash card (FlashCard), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0045] Example 4 The present invention also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by a processor, the steps of the DC insulating gas state evaluation method based on dark current measurement are implemented.

[0046] If the module / unit integrated in the mobile terminal is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium.

[0047] Based on this understanding, the present invention implements all or part of the processes in the above method, and can also be completed by instructing related hardware through a computer program, and the computer program can be stored in a computer-readable storage medium, and when the computer program is executed by a processor, the steps of the above-mentioned aggregate reinforcement learning resource scheduling method can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form, etc.

[0048] The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electrical carrier signal, telecommunication signal and software distribution medium, etc.

[0049] It should be noted that the content contained in the computer-readable medium can be appropriately increased or decreased according to the requirements of legislation and patent practice in the jurisdiction. For example, in some jurisdictions, according to legislation and patent practice, computer-readable media does not include electrical carrier signals and telecommunication signals.

[0050] Example 5 A computer program product includes computer instructions, wherein the computer instructions instruct a computing device to execute operations corresponding to the DC insulating gas state assessment method based on dark current measurement as described above.

[0051] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the above embodiments, ordinary technicians in the relevant field should understand that the specific implementation methods of the present invention can still be modified or replaced by equivalents. Any modification or equivalent replacement that does not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A DC insulating gas state assessment method based on dark current measurement, characterized in that: include: Obtain the insulating gas dark current signal under different gas pressures, different guide rod roughness and different electric field characteristics; The obtained insulating gas dark current signal is processed to obtain the average dark current value corresponding to each electric field strength; Based on the SVM algorithm, the insulation margin of the insulating gas under different conditions is evaluated by using the average dark current value to complete the state evaluation of the insulating gas.

2. A DC insulating gas state assessment method based on dark current measurement according to claim 1, characterized in that: In the step of obtaining the insulating gas dark current signal under different gas pressures, different guide rod roughnesses and different electric field characteristics, the specific process is as follows: Set up an experimental device that can adjust gas pressure, guide rod roughness and electric field characteristics; Under multiple preset combinations of gas pressure, guide rod roughness and electric field characteristics, the dark current signal of the insulating gas is measured separately through the experimental device.

3. A DC insulating gas state assessment method based on dark current measurement according to claim 1, characterized in that: In processing the obtained insulating gas dark current signal, the dark current signal under each electric field strength is filtered and smoothed, and then the average value of the dark current signal under each electric field strength is calculated to obtain the average dark current value corresponding to each electric field strength.

4. The DC insulating gas state assessment method based on dark current measurement according to claim 1, characterized in that: In the step of evaluating the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm to complete the state evaluation of the insulating gas, the specific process is as follows: Adjust the feature vector format and select the training function and training parameter settings; Construct an SVM model, input the feature vector format into the SVM model, set the training function and training parameters, and then perform training in the SVM model to obtain training samples; Perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; The average dark current value corresponding to each electric field strength is input into the finally trained SVM model for testing to obtain the corresponding test training samples; Each test training sample is compared with the training sample to obtain a comparison result, and the insulation margin of the insulating gas under different conditions is evaluated through the comparison result.

5. A DC insulating gas state assessment method based on dark current measurement according to claim 4, characterized in that: In the step of comparing each test training sample with the training sample to obtain a comparison result, if the test training sample is the same as the training sample, the test training sample is qualified, otherwise it is unqualified.

6. A DC insulating gas state assessment system based on dark current measurement, characterized in that: include: A dark current signal acquisition module is used to obtain the dark current signal of insulating gas under different gas pressures, different guide rod roughness and different electric field characteristics; A signal processing module is used to process the obtained insulating gas dark current signal to obtain an average dark current value corresponding to each electric field strength; The evaluation module is used to evaluate the insulation margin of the insulating gas under different conditions based on the average dark current value based on the SVM algorithm, so as to complete the state evaluation of the insulating gas.

7. A DC insulating gas state assessment system based on dark current measurement according to claim 6, characterized in that: The evaluation module includes a data setting module, a model training module, a model testing module and a comparison module; Data setting module, used to adjust the feature vector format and select training functions and training parameter settings; The model training module is used to build the SVM model, input the feature vector format into the SVM model, and set the training function and training parameters before training in the SVM model to obtain training samples; Perform back-testing on the training samples in the SVM model to obtain the final trained SVM model; A model testing module is used to input the corresponding average dark current value under each electric field strength into the finally trained SVM model for testing to obtain the corresponding test training samples; The comparison module is used to compare each test training sample with the training sample to obtain a comparison result, and evaluate the insulation margin of the insulating gas under different conditions through the comparison result.

8. A mobile terminal comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the DC insulating gas state evaluation method based on dark current measurement as described in any one of claims 1 to 5 are implemented.

9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the DC insulating gas state evaluation method based on dark current measurement as described in any one of claims 1 to 5 are implemented.

10. A computer program product comprising computer instructions, characterized in that: The computer instructions instruct the computing device to execute operations corresponding to the DC insulating gas state assessment method based on dark current measurement as described in any one of claims 1-5.

Images