Method for detecting gas in transformer oil based on laser spectrum

Abstract

The invention discloses a method for detecting gas in transformer oil based on a laser spectrum, and belongs to the technical field of gas detection, and the method comprises the following steps: S1, collecting real-time data of the gas in the transformer oil, processing the real-time data of the gas in the transformer oil, and determining characteristic data of the gas in the transformer oil; s2, evaluating and optimizing the detection fault identification model of the gas in the transformer oil, and determining an optimal detection fault identification model of the gas in the transformer oil; and S3, predicting and analyzing the characteristic data of the gas in the transformer oil. According to the method, the problems that in the prior art, gas in transformer oil cannot be accurately detected, the fault property and type of the transformer cannot be effectively pre-judged, long-term stable operation of the transformer cannot be ensured, and the use effect of the transformer is poor are solved, the gas in the transformer oil can be accurately detected, and the detection accuracy is improved. The fault property and type of the transformer can be effectively pre-judged, long-term stable operation of the transformer can be ensured, and the use effect of the transformer is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of gas detection, in particular to a method for detecting gas in transformer oil based on laser spectroscopy. Background Art

[0002] Transformer equipment is the main body of the power system and the basis for ensuring power supply reliability. If a major device has a problem, it will often cause local and global system equipment to stop operating, resulting in power outages. Therefore, the safe and reliable operation of transformer equipment is particularly important. Transformers may fail during operation, causing abnormal changes in the bubbles in the oil. These bubbles contain different gases, such as The generation of these gases is often related to the deterioration of insulation materials. If they are not detected and treated in time, they may cause accidents.

[0003] Chinese patent publication number CN118465159A discloses a transformer oil testing box, comprising: a box body having a receiving cavity; an oil inlet pipe passing through a side wall of the box body; a heat-insulating structure arranged in the receiving cavity, the heat-insulating structure comprising a heating seat, a heat-conducting tube arranged above the heating seat, and a heat-conducting tube arranged in the heat-conducting tube, the heating seat having a heating cavity, the heat-conducting tube communicating with the heating cavity, a heat-conducting fluid arranged inside the heating cavity, and the heat-conducting fluid being able to flow from the heating cavity into the heat-conducting tube; an oil chromatography column, comprising a first connecting section, a heat-conducting section, and a second connecting section arranged in sequence, the first connecting section being connected to the oil inlet pipe at one end away from the heat-conducting section, and the heat-conducting section being arranged on the outside of the heat-conducting tube; a detector arranged in the receiving cavity, the second connecting section being connected to the detector at one end away from the heat-conducting section; the invention can effectively solve the problem of high energy consumption of the constant temperature box in the related art; however, the invention has the following defects: The existing methods cannot accurately detect the gas in the transformer oil, cannot effectively predict the nature and type of transformer faults, and cannot ensure the long-term stable operation of the transformer, resulting in poor transformer use effect. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for detecting gas in transformer oil based on laser spectroscopy, which can accurately detect gas in transformer oil, effectively predict the nature and type of transformer faults, ensure the long-term stable operation of the transformer, improve the use effect of the transformer, and solve the problems raised in the above-mentioned background technology.

[0005] To achieve the above object, the present invention provides the following technical solutions: The method for detecting gas in transformer oil based on laser spectroscopy includes the following steps: S1: collecting real-time data of gas in transformer oil based on laser spectroscopy, processing the real-time data of gas in transformer oil based on laser spectroscopy, and determining characteristic data of gas in transformer oil based on laser spectroscopy; S2: Based on the requirements of laser spectroscopy-based transformer oil gas detection, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed. The model is evaluated and optimized to determine the optimal transformer oil gas detection fault identification model based on laser spectroscopy. S3: Based on the optimal laser spectrum-based transformer oil gas detection fault identification model, predictive analysis is performed on the laser spectrum-based transformer oil gas characteristic data to determine the laser spectrum-based transformer oil gas detection fault identification result; S4: Develop an intelligent control scheme for transformer oil gas detection based on laser spectroscopy, and perform intelligent control of transformer oil gas detection based on laser spectroscopy according to the intelligent control scheme for transformer oil gas detection based on laser spectroscopy, so as to ensure long-term stable operation of the transformer.

[0006] Preferably, in S1, real-time data of gas in transformer oil based on laser spectroscopy is collected, and the following operations are performed: Take samples directly from the oil sampling port on the transformer to determine the transformer oil sample; The constant temperature vacuum degassing technology is used to efficiently degas transformer oil samples; Release the gas dissolved in the transformer oil sample while preventing the transformer oil sample from coming into contact with air, and introduce the degassed gas into the photoacoustic cell; A laser of a specific wavelength is emitted to illuminate the gas in the photoacoustic cell. When the gas molecules absorb the laser energy, their temperature rises and they release heat energy, which in turn generates pressure waves to determine the gas concentration. Obtain gas concentration, trend, gas ratio and gas change rate; Determine the real-time data of gas in transformer oil based on laser spectroscopy.

[0007] Preferably, in S1, the real-time data of gas in transformer oil based on laser spectroscopy is processed by performing the following operations: Obtain real-time data on gas in transformer oil based on laser spectroscopy; Cleaning and processing of real-time data of gas in transformer oil based on laser spectroscopy, including: Conduct consistency checks on real-time data of gas in transformer oil based on laser spectroscopy; According to the reasonable value range and mutual relationship of each variable in the real-time data of gas in transformer oil based on laser spectroscopy, check whether the real-time data of gas in transformer oil based on laser spectroscopy meets the requirements; Remove inconsistent data that is out of the normal range, logically unreasonable or contradictory in the real-time data of gas in transformer oil based on laser spectroscopy; Process invalid and missing values ​​of real-time data of gas in transformer oil based on laser spectroscopy; Remove invalid data and missing data that are of no value to the gas detection in transformer oil based on laser spectroscopy in real-time data of gas in transformer oil based on laser spectroscopy; Real-time data of gas in transformer oil based on laser spectroscopy that is valuable for gas detection in transformer oil based on laser spectroscopy is determined.

[0008] Preferably, determining real-time data of gas in transformer oil based on laser spectroscopy that is valuable for gas detection in transformer oil based on laser spectroscopy includes: Real-time monitoring removes invalid data that is of no value to gas detection in transformer oil based on laser spectroscopy; Extract the removed invalid data; Sort the invalid data according to the generation time corresponding to each invalid data, and obtain the data set corresponding to the invalid data; Retrieve the preset unit time period; wherein the value range of the preset unit time period is 3 minutes to 7 minutes; Dividing the data set corresponding to the invalid data according to the preset unit time period to obtain multiple invalid data groups; The invalid evaluation coefficient corresponding to each invalid data group is obtained by using the data generation time interval of the invalid data contained in the invalid data group; wherein the invalid evaluation coefficient is obtained by the following formula: ; Wherein, P represents the invalid evaluation coefficient; n represents the number of invalid data contained in each invalid data group; T c Indicates the duration of a unit time period; T i Indicates the generation time of the i-th invalid data; T i-1 Indicates the generation time of the i-1th invalid data; w i Indicates the weight value corresponding to the i-th invalid data; w i-1 Indicates the weight value corresponding to the i-1th invalid data; G i G represents the time interval between the generation time of the i-th invalid data and the most recent valid data with the same weight value as the i-th invalid data; i-1 G represents the time interval between the generation time of the most recent valid data with the same weight value as the i-1th invalid data and the i-th invalid data; pIt represents the average value of the data generation time interval corresponding to n invalid data; Comparing the invalid evaluation coefficient with a preset invalid evaluation coefficient threshold; extracting invalid evaluation coefficients exceeding the invalid evaluation coefficient threshold as target invalid evaluation coefficients; The invalid data is filled using the target invalid evaluation coefficient.

[0009] Preferably, filling invalid data with the target invalid evaluation coefficient includes: Extracting the invalid data group where each target invalid evaluation coefficient is located as the target invalid data group; Extracting the generation time corresponding to each invalid data in the invalid data group where each target invalid evaluation coefficient is located; According to the generation time corresponding to each invalid data, obtain the valid data before and after the generation time of each invalid data; Obtaining an invalid data compensation coefficient corresponding to the target invalid data group by using the valid data preceding and following the invalid data generation moment in combination with the target invalid evaluation coefficient; The invalid data compensation coefficient corresponding to the target invalid data group is obtained by the following formula: ; Where B represents the invalid data compensation coefficient corresponding to the target invalid data group; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; X p represents the average value of the data corresponding to the valid data; P represents the invalid evaluation coefficient; P0 represents the preset invalid evaluation coefficient threshold; X z Indicates the middle value of the data corresponding to the valid data; Obtaining replacement data corresponding to each invalid data in the target invalid data group using the invalid data compensation coefficient corresponding to the target invalid data group; Each invalid data in the target invalid data group is replaced by using the replacement data corresponding to each invalid data in the target invalid data group.

[0010] Preferably, obtaining the replacement data corresponding to each invalid data in the target invalid data group by using the invalid data compensation coefficient corresponding to the target invalid data group includes: Retrieve the invalid data compensation coefficient corresponding to the target invalid data group; Retrieve the valid data that is before and after the generation time of each invalid data in the target invalid data group; Obtaining a data reference value corresponding to each invalid data in the target invalid data group by using valid data that is before and after the generation time of each invalid data in the target invalid data group; The data reference value is obtained by the following formula: ; Among them, X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; P0 represents the preset invalid evaluation coefficient threshold; P z Indicates the median value of invalid evaluation coefficients corresponding to all invalid data groups; Obtaining replacement data corresponding to each invalid data by using the invalid data compensation coefficient corresponding to the target invalid data group and the data reference value corresponding to each invalid data in the target invalid data group; The replacement data corresponding to each invalid data is obtained by the following formula: ; Among them, X t Indicates the replacement data corresponding to each invalid data; X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 They respectively represent the data values ​​of the valid data before and after each invalid data generation moment; B represents the invalid data compensation coefficient corresponding to the target invalid data group.

[0011] Preferably, in S1, the real-time data of gas in transformer oil based on laser spectroscopy is processed, and the following operations are further performed: Acquire real-time data of gas in transformer oil based on laser spectroscopy, which is valuable for gas detection in transformer oil based on laser spectroscopy; Normalizing the real-time data of gas in transformer oil based on laser spectroscopy which is valuable for gas detection in transformer oil based on laser spectroscopy after cleaning; Eliminate the dimension difference between real-time data of gas in transformer oil based on laser spectroscopy; Determine the data standardization of real-time data of gas in transformer oil based on laser spectroscopy; Feature extraction of real-time gas data in transformer oil based on data standardization and laser spectroscopy; Extracting features that can reflect the valuable features for gas detection in transformer oil based on laser spectroscopy; The characteristic data of gas in transformer oil based on laser spectroscopy were determined.

[0012] Preferably, in S2, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed, and the transformer oil gas detection fault identification model based on laser spectroscopy is evaluated and optimized, and the following operations are performed: According to the needs of gas detection in transformer oil based on laser spectroscopy, historical gas concentration, trend, gas ratio and gas change rate are collected to determine the historical data of gas in transformer oil based on laser spectroscopy; Partitioning historical data of gas in transformer oil based on laser spectroscopy; Determine a gas detection training set and a gas detection test set; According to the requirements of gas detection in transformer oil based on laser spectroscopy, a neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is selected; Based on the gas detection training set, the selected neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is trained; Determine the fault identification model for gas detection in transformer oil based on laser spectroscopy; Based on the gas detection test set, the performance test and evaluation of the transformer oil gas detection fault identification model based on laser spectroscopy was conducted; Determine the performance test evaluation results of the transformer oil gas detection fault identification model based on laser spectroscopy; Analyze the performance test and evaluation results of the transformer oil gas detection fault identification model based on laser spectroscopy; Determine the parameter adjustment optimization scheme of the transformer oil gas detection fault identification model based on laser spectroscopy; Based on the parameter adjustment optimization scheme, the parameters of the transformer oil gas detection fault identification model based on laser spectroscopy are adjusted and optimized; The optimal fault identification model for gas detection in transformer oil based on laser spectroscopy was determined.

[0013] Preferably, in S3, predictive analysis is performed on characteristic data of gas in transformer oil based on laser spectroscopy, and the following operations are performed: Obtain gas characteristic data in transformer oil based on laser spectroscopy; Inputting the gas characteristic data in transformer oil based on laser spectroscopy into the optimal transformer oil gas detection fault identification model based on laser spectroscopy; Based on the optimal laser spectrum-based transformer oil gas detection fault identification model, the laser spectrum-based transformer oil gas characteristic data is predicted and analyzed; The fault identification results of gas detection in transformer oil based on laser spectroscopy were determined.

[0014] Preferably, in S4, intelligent management and control of gas detection in transformer oil based on laser spectroscopy is performed by performing the following operations: Obtaining transformer oil gas detection fault identification results based on laser spectroscopy; Analyze the fault identification results of gas detection in transformer oil based on laser spectroscopy; Determine an intelligent control solution for transformer oil gas detection based on laser spectroscopy; Intelligent control of gas detection in transformer oil based on laser spectroscopy is carried out according to the intelligent control solution of gas detection in transformer oil based on laser spectroscopy; Among them, based on the fault identification results of the transformer oil gas detection based on laser spectroscopy, the nature and type of the transformer fault are determined, timely early warning is given and intelligent management and control measures are formulated, the transformer fault is promptly repaired, and the transformer is regularly maintained and optimized according to the actual operating conditions, so that the transformer can operate stably in the long term.

[0015] Compared with the prior art, the present invention has the following beneficial effects: 1. The present invention directly samples the transformer oil through the oil sampling port on the transformer to determine the transformer oil sample, adopts constant temperature vacuum degassing technology to efficiently degas the transformer oil sample to release the gas dissolved in the transformer oil sample while preventing the transformer oil sample from contacting with air, introduces the degassed gas into a photoacoustic cell, emits a laser of a specific wavelength to irradiate the gas in the photoacoustic cell, and after the gas molecules absorb the laser energy, their temperature rises and heat energy is released, thereby generating pressure waves to determine the gas concentration, obtain the gas concentration, trend, gas ratio and gas change rate, and determine the real-time data of the gas in the transformer oil based on the laser spectrum.

[0016] 2. The present invention processes real-time data of gas in transformer oil based on laser spectroscopy to determine characteristic data of gas in transformer oil based on laser spectroscopy, constructs a fault identification model for gas detection in transformer oil based on laser spectroscopy according to the demand for gas detection in transformer oil based on laser spectroscopy, evaluates and optimizes the fault identification model for gas detection in transformer oil based on laser spectroscopy, determines an optimal fault identification model for gas detection in transformer oil based on laser spectroscopy, predicts and analyzes the characteristic data of gas in transformer oil based on laser spectroscopy based on the optimal fault identification model for gas detection in transformer oil based on laser spectroscopy, determines a fault identification result of gas detection in transformer oil based on laser spectroscopy, formulates an intelligent management and control scheme for gas detection in transformer oil based on laser spectroscopy, and intelligently manages gas detection in transformer oil based on laser spectroscopy according to the intelligent management and control scheme for gas detection in transformer oil based on laser spectroscopy. The gas in transformer oil can be accurately detected, the nature and type of transformer faults can be effectively predicted, the long-term stable operation of the transformer can be ensured, and the use effect of the transformer can be improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] Figure 1 The figure is a flow chart of the gas detection method in transformer oil based on laser spectroscopy of the present invention. DETAILED DESCRIPTION

[0018] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0019] In order to solve the existing problems of being unable to accurately detect gas in transformer oil, unable to effectively predict the nature and type of transformer faults, unable to ensure long-term stable operation of the transformer, and resulting in poor transformer performance, please refer to Figure 1 , this embodiment provides the following technical solutions: The method for detecting gas in transformer oil based on laser spectroscopy includes the following steps: S1: collecting real-time data of gas in transformer oil based on laser spectroscopy, processing the real-time data of gas in transformer oil based on laser spectroscopy, and determining characteristic data of gas in transformer oil based on laser spectroscopy; In this embodiment, real-time data of gas in transformer oil based on laser spectroscopy is collected by performing the following operations: Take samples directly from the oil sampling port on the transformer to determine the transformer oil sample; The constant temperature vacuum degassing technology is used to efficiently degas transformer oil samples; Release the gas dissolved in the transformer oil sample while preventing the transformer oil sample from coming into contact with air, and introduce the degassed gas into the photoacoustic cell; It should be noted that constant temperature vacuum degassing technology is an advanced process that improves gas purity by performing vacuum degassing treatment at constant temperature and pressure. It has the advantages of energy saving, environmental protection, and pollution-free, and is widely used in industrial production, scientific research experiments and other fields.

[0020] In constant temperature vacuum degassing technology, gas is pumped into vacuum equipment and degassed in an environment below atmospheric pressure. Compared with traditional vacuum degassing technology, constant temperature vacuum degassing technology has higher desorption efficiency and lower energy consumption. In practical applications, this technology can effectively reduce energy consumption in the gas treatment process, reduce environmental pollution, reduce operating costs, and improve product performance.

[0021] A laser of a specific wavelength is emitted to illuminate the gas in the photoacoustic cell. When the gas molecules absorb the laser energy, their temperature rises and they release heat energy, which in turn generates pressure waves to determine the gas concentration. Obtain gas concentration, trend, gas ratio and gas change rate; Determine the real-time data of gas in transformer oil based on laser spectroscopy.

[0022] In this embodiment, the real-time data of gas in transformer oil based on laser spectroscopy is processed by performing the following operations: Obtain real-time data on gas in transformer oil based on laser spectroscopy; Cleaning and processing of real-time data of gas in transformer oil based on laser spectroscopy, including: Conduct consistency checks on real-time data of gas in transformer oil based on laser spectroscopy; According to the reasonable value range and mutual relationship of each variable in the real-time data of gas in transformer oil based on laser spectroscopy, check whether the real-time data of gas in transformer oil based on laser spectroscopy meets the requirements; Remove inconsistent data that is out of the normal range, logically unreasonable or contradictory in the real-time data of gas in transformer oil based on laser spectroscopy; Process invalid and missing values ​​of real-time data of gas in transformer oil based on laser spectroscopy; Remove invalid data and missing data that are of no value to the gas detection in transformer oil based on laser spectroscopy in real-time data of gas in transformer oil based on laser spectroscopy; Determine the real-time data of gas in transformer oil based on laser spectroscopy that is valuable for gas detection in transformer oil based on laser spectroscopy; Normalizing the real-time data of gas in transformer oil based on laser spectroscopy which is valuable for gas detection in transformer oil based on laser spectroscopy after cleaning; Eliminate the dimension difference between real-time data of gas in transformer oil based on laser spectroscopy; Determine the data standardization of real-time data of gas in transformer oil based on laser spectroscopy; Feature extraction of real-time gas data in transformer oil based on data standardization and laser spectroscopy; Extracting features that can reflect the valuable features for gas detection in transformer oil based on laser spectroscopy; The characteristic data of gas in transformer oil based on laser spectroscopy were determined.

[0023] S2: Based on the requirements for transformer oil gas detection, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed. The model is evaluated and optimized to determine the optimal transformer oil gas detection fault identification model. In this embodiment, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed, and the transformer oil gas detection fault identification model based on laser spectroscopy is evaluated and optimized by performing the following operations: According to the needs of gas detection in transformer oil based on laser spectroscopy, historical gas concentration, trend, gas ratio and gas change rate are collected to determine the historical data of gas in transformer oil based on laser spectroscopy; Partitioning historical data of gas in transformer oil based on laser spectroscopy; Determine a gas detection training set and a gas detection test set; According to the requirements of gas detection in transformer oil based on laser spectroscopy, a neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is selected; Based on the gas detection training set, the selected neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is trained; Determine the fault identification model for gas detection in transformer oil based on laser spectroscopy; Based on the gas detection test set, the performance test and evaluation of the transformer oil gas detection fault identification model based on laser spectroscopy was conducted; Determine the performance test evaluation results of the transformer oil gas detection fault identification model based on laser spectroscopy; Analyze the performance test and evaluation results of the transformer oil gas detection fault identification model based on laser spectroscopy; Determine the parameter adjustment optimization scheme of the transformer oil gas detection fault identification model based on laser spectroscopy; Based on the parameter adjustment optimization scheme, the parameters of the transformer oil gas detection fault identification model based on laser spectroscopy are adjusted and optimized; The optimal fault identification model for gas detection in transformer oil based on laser spectroscopy was determined.

[0024] S3: Based on the optimal laser spectrum-based transformer oil gas detection fault identification model, predictive analysis is performed on the laser spectrum-based transformer oil gas characteristic data to determine the laser spectrum-based transformer oil gas detection fault identification result; In this embodiment, the following operations are performed to predict and analyze the characteristic data of gas in transformer oil based on laser spectroscopy: Obtain gas characteristic data in transformer oil based on laser spectroscopy; Inputting the gas characteristic data in transformer oil based on laser spectroscopy into the optimal transformer oil gas detection fault identification model based on laser spectroscopy; Based on the optimal laser spectrum-based transformer oil gas detection fault identification model, the laser spectrum-based transformer oil gas characteristic data is predicted and analyzed; The fault identification results of gas detection in transformer oil based on laser spectroscopy were determined.

[0025] S4: Develop an intelligent control scheme for transformer oil gas detection based on laser spectroscopy, and perform intelligent control of transformer oil gas detection based on laser spectroscopy according to the intelligent control scheme for transformer oil gas detection based on laser spectroscopy, so as to ensure long-term stable operation of the transformer.

[0026] In this embodiment, intelligent management and control of gas detection in transformer oil based on laser spectroscopy is performed by performing the following operations: Obtaining transformer oil gas detection fault identification results based on laser spectroscopy; Analyze the fault identification results of gas detection in transformer oil based on laser spectroscopy; Determine an intelligent control solution for transformer oil gas detection based on laser spectroscopy; Intelligent control of gas detection in transformer oil based on laser spectroscopy is carried out according to the intelligent control solution of gas detection in transformer oil based on laser spectroscopy; Among them, based on the fault identification results of the transformer oil gas detection based on laser spectroscopy, the nature and type of the transformer fault are determined, timely early warning is given and intelligent management and control measures are formulated, the transformer fault is promptly repaired, and the transformer is regularly maintained and optimized according to the actual operating conditions, so that the transformer can operate stably in the long term.

[0027] Specifically, the real-time data of gas in transformer oil based on laser spectroscopy that is valuable for gas detection in transformer oil based on laser spectroscopy is determined, including: Real-time monitoring removes invalid data that is of no value to gas detection in transformer oil based on laser spectroscopy; Extract the removed invalid data; Sort the invalid data according to the generation time corresponding to each invalid data, and obtain the data set corresponding to the invalid data; Retrieve the preset unit time period; wherein the value range of the preset unit time period is 3 minutes to 7 minutes; Dividing the data set corresponding to the invalid data according to the preset unit time period to obtain multiple invalid data groups; The invalid evaluation coefficient corresponding to each invalid data group is obtained by using the data generation time interval of the invalid data contained in the invalid data group; wherein the invalid evaluation coefficient is obtained by the following formula: ; Wherein, P represents the invalid evaluation coefficient; n represents the number of invalid data contained in each invalid data group; T c Indicates the duration of a unit time period; T i Indicates the generation time of the i-th invalid data; T i-1 Indicates the generation time of the i-1th invalid data; w i Indicates the weight value corresponding to the i-th invalid data; w i-1 Indicates the weight value corresponding to the i-1th invalid data; G i G represents the time interval between the generation time of the i-th invalid data and the most recent valid data with the same weight value as the i-th invalid data; i-1 G represents the time interval between the generation time of the most recent valid data with the same weight value as the i-1th invalid data and the i-th invalid data; p It represents the average value of the data generation time interval corresponding to n invalid data; Comparing the invalid evaluation coefficient with a preset invalid evaluation coefficient threshold; extracting invalid evaluation coefficients exceeding the invalid evaluation coefficient threshold as target invalid evaluation coefficients; The invalid data is filled using the target invalid evaluation coefficient.

[0028] The technical solution described above significantly reduces noise and interference in the data by real-time monitoring and removing invalid data that is not valuable for laser spectroscopy-based gas detection in transformer oil, thereby improving the accuracy and reliability of subsequent data analysis. Extracting the removed invalid data and sorting it by its generation time helps understand its distribution characteristics and generation patterns, providing a foundation for further data processing.

[0029] By dividing invalid data into preset time periods (3-7 minutes) and calculating the invalidity evaluation coefficient for each invalid data group, a more detailed assessment of the impact of invalid data on overall data quality can be achieved. By comparing the invalidity evaluation coefficient with a preset invalidity evaluation coefficient threshold, invalid data groups with the greatest impact on overall data quality can be intelligently identified—those corresponding to the target invalidity evaluation coefficient. By filling in the invalid data with the target invalidity evaluation coefficient, data integrity can be restored to a certain extent, minimizing the negative impact on subsequent data analysis. Overall, this technical solution, through a refined invalid data processing strategy, helps improve the real-time and accuracy of laser spectroscopy-based transformer oil gas detection, providing more reliable data support for transformer fault warning and condition monitoring. Furthermore, by effectively processing invalid data, this technical solution enhances the robustness of the entire detection system, enabling it to maintain more stable and reliable performance in complex and changing real-world operating environments.

[0030] In summary, this technical solution significantly improves the data quality and real-time performance of gas detection in transformer oil based on laser spectroscopy through a series of refined data processing steps, providing strong technical support for transformer fault warning and status monitoring.

[0031] Specifically, filling invalid data using the target invalid evaluation coefficient includes: Extracting the invalid data group where each target invalid evaluation coefficient is located as the target invalid data group; Extracting the generation time corresponding to each invalid data in the invalid data group where each target invalid evaluation coefficient is located; According to the generation time corresponding to each invalid data, obtain the valid data before and after the generation time of each invalid data; Obtaining an invalid data compensation coefficient corresponding to the target invalid data group by using the valid data preceding and following the invalid data generation moment in combination with the target invalid evaluation coefficient; The invalid data compensation coefficient corresponding to the target invalid data group is obtained by the following formula: ; Where B represents the invalid data compensation coefficient corresponding to the target invalid data group; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; X p represents the average value of the data corresponding to the valid data; P represents the invalid evaluation coefficient; P0 represents the preset invalid evaluation coefficient threshold; X z Indicates the middle value of the data corresponding to the valid data; Obtaining replacement data corresponding to each invalid data in the target invalid data group using the invalid data compensation coefficient corresponding to the target invalid data group; Each invalid data in the target invalid data group is replaced by using the replacement data corresponding to each invalid data in the target invalid data group.

[0032] The technical effect of the above technical solution is that by extracting a target invalid data set and replacing the invalid data within it, missing values ​​in the dataset can be effectively reduced, thereby improving data integrity. This is crucial for subsequent data analysis and model training, as missing data can lead to inaccurate results or reduced model performance. By calculating the invalid data compensation coefficient using adjacent valid data (i.e., valid data that precedes and follows the target invalid data) and the target invalid data evaluation coefficient, a more accurate estimate of the reasonable value of the invalid data can be achieved. This method takes into account the temporal nature of the data and the correlation between adjacent data, helping to generate replacement data that is closer to the true value.

[0033] This technical solution intelligently identifies and processes invalid data by calculating an invalid evaluation coefficient and an invalid data compensation coefficient. Compared to manually deleting or simply filling in invalid data, this method is more efficient and preserves more data information and structure. In applications such as laser spectroscopy-based gas detection in transformer oil, data accuracy and integrity are crucial to the model's predictive accuracy. Filling in invalid data reduces noise and missing values, thereby improving the model's predictive performance.

[0034] This technical solution enhances the robustness of the entire system through refined data processing strategies. Even when encountering large amounts of invalid data during actual operation, the system maintains data stability and reliability through intelligent identification and infill strategies. Furthermore, this technical solution is not only applicable to transformer oil gas detection based on laser spectroscopy but can also be extended to other scenarios requiring invalid data processing. By adjusting parameters and formulas, it can adapt to different datasets and application requirements.

[0035] In summary, this technical solution significantly improves data integrity, quality, and processing efficiency by utilizing the target invalidity evaluation coefficient and invalid data compensation coefficient to fill in invalid data. This provides more reliable data support for applications such as laser spectroscopy-based gas detection in transformer oil. Furthermore, this technical solution enhances system robustness and provides a flexible data processing solution.

[0036] Specifically, obtaining replacement data corresponding to each invalid data in the target invalid data group using the invalid data compensation coefficient corresponding to the target invalid data group includes: Retrieve the invalid data compensation coefficient corresponding to the target invalid data group; Retrieve the valid data that is before and after the generation time of each invalid data in the target invalid data group; Obtaining a data reference value corresponding to each invalid data in the target invalid data group by using valid data that is before and after the generation time of each invalid data in the target invalid data group; The data reference value is obtained by the following formula: ; Among them, X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; P0 represents the preset invalid evaluation coefficient threshold; P z Indicates the median value of invalid evaluation coefficients corresponding to all invalid data groups; Obtaining replacement data corresponding to each invalid data by using the invalid data compensation coefficient corresponding to the target invalid data group and the data reference value corresponding to each invalid data in the target invalid data group; The replacement data corresponding to each invalid data is obtained by the following formula: ; Among them, X t Indicates the replacement data corresponding to each invalid data; X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 They respectively represent the data values ​​of the valid data before and after each invalid data generation moment; B represents the invalid data compensation coefficient corresponding to the target invalid data group.

[0037] The technical effect of the above technical solution is to calculate the data baseline value corresponding to each invalid data point by combining adjacent valid data points (valid data with earlier and later time periods), a preset invalidity evaluation coefficient threshold, and the median invalidity evaluation coefficient value corresponding to all invalid data groups. This method not only considers the temporal nature of the data but also incorporates the overall evaluation of the invalid data, making the generated data baseline value closer to the true value, thereby improving data accuracy. Using the data baseline value and invalid data compensation coefficient to generate replacement data allows for more flexible handling of invalid data. This method not only considers the characteristics of the invalid data itself but also incorporates information from adjacent valid data, making the generated replacement data more consistent with the overall distribution and trend of the data.

[0038] This technical solution helps maintain data consistency by intelligently identifying and filling invalid data. The replaced data is closer in value and trend to the adjacent valid data, reducing data mutations and outliers and improving overall data quality. In data analysis and machine learning models, data accuracy and integrity are crucial to model performance. By replacing invalid data, noise and missing values ​​can be reduced, thereby improving model training and prediction accuracy.

[0039] This technical solution uses an automated data processing process to rapidly identify and replace invalid data. Compared to manual invalid data processing, this approach is more efficient and can handle large datasets. Through refined data processing strategies, this technical solution enhances the robustness of the entire system. Even when encountering large amounts of invalid data in actual operation, the system maintains data stability and reliability through intelligent identification and replacement strategies.

[0040] In summary, this technical solution significantly improves data accuracy, consistency, and overall quality by calculating data baseline values ​​and invalid data compensation coefficients to generate replacement data. It also enhances model performance, data processing efficiency, and system robustness, providing more reliable data support for data analysis and machine learning applications.

[0041] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0042] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

Claims

1. A method for detecting gas in transformer oil based on laser spectroscopy, characterized in that: The steps include: S1: collecting real-time data of gas in transformer oil based on laser spectrum, processing the real-time data of gas in transformer oil based on laser spectrum, and determining characteristic data of gas in transformer oil based on laser spectrum; S2: According to the demand for transformer oil gas detection based on laser spectroscopy, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed, and the transformer oil gas detection fault identification model based on laser spectroscopy is evaluated and optimized to determine the optimal transformer oil gas detection fault identification model based on laser spectroscopy; S3: Based on the optimal transformer oil gas detection fault identification model based on laser spectrum, predictive analysis is performed on the transformer oil gas characteristic data based on laser spectrum to determine the transformer oil gas detection fault identification result based on laser spectrum; S4: Develop an intelligent control scheme for transformer oil gas detection based on laser spectroscopy, and perform intelligent control on transformer oil gas detection based on laser spectroscopy according to the intelligent control scheme for transformer oil gas detection based on laser spectroscopy to ensure long-term stable operation of the transformer.

2. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 1, characterized in that: In S1, real-time data of gas in transformer oil based on laser spectroscopy is collected, and the following operations are performed: Take samples directly from the oil sampling port on the transformer to determine the transformer oil sample; The constant temperature vacuum degassing technology is used to efficiently degas transformer oil samples; The gas dissolved in the transformer oil sample is released, while the transformer oil sample is prevented from contacting with air, and the degassed gas is introduced into the photoacoustic cell; A laser of a specific wavelength is emitted to illuminate the gas in the photoacoustic cell. After the gas molecules absorb the laser energy, their temperature rises and they release heat energy, which in turn generates pressure waves to determine the gas concentration. Obtain gas concentration, trend, gas ratio and gas change rate; Determine the real-time data of gas in transformer oil based on laser spectroscopy.

3. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 2, characterized in that: In S1, the real-time data of gas in transformer oil based on laser spectroscopy is processed, and the following operations are performed: Obtain real-time data of gas in transformer oil based on laser spectroscopy; Cleaning and processing of real-time data of gas in transformer oil based on laser spectroscopy, including: Conduct consistency checks on real-time data of gas in transformer oil based on laser spectroscopy; According to the reasonable value range and mutual relationship of each variable in the real-time data of gas in transformer oil based on laser spectrum, check whether the real-time data of gas in transformer oil based on laser spectrum meets the requirements; Remove inconsistent data that is beyond the normal range, logically unreasonable or contradictory in the real-time data of gas in transformer oil based on laser spectroscopy; Process invalid and missing values ​​of real-time data of gas in transformer oil based on laser spectroscopy; Remove invalid data and missing data that are of no value to the gas detection in transformer oil based on laser spectroscopy in real-time data of gas in transformer oil based on laser spectroscopy; Real-time data of gas in transformer oil based on laser spectroscopy that is valuable for gas detection in transformer oil based on laser spectroscopy is determined.

4. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 3, characterized in that: Real-time data of gas in transformer oil based on laser spectroscopy that are valuable for gas in transformer oil detection based on laser spectroscopy are identified, including: Real-time monitoring removes invalid data that is of no value to gas detection in transformer oil based on laser spectroscopy; Extract the invalid data that has been removed; Sort the invalid data according to the generation time corresponding to each invalid data, and obtain the data set corresponding to the invalid data; Retrieve a preset unit time period; wherein the value range of the preset unit time period is 3min-7min; Dividing the data set corresponding to the invalid data according to the preset unit time period to obtain multiple invalid data groups; The invalid evaluation coefficient corresponding to each invalid data group is obtained by using the data generation time interval of the invalid data contained in the invalid data group; wherein the invalid evaluation coefficient is obtained by the following formula: ； Wherein, P represents the invalid evaluation coefficient; n represents the number of invalid data contained in each invalid data group; T c Indicates the duration corresponding to the unit time period; T i Indicates the generation time corresponding to the i-th invalid data; T i-1 Indicates the generation time of the i-1th invalid data; w i represents the weight value corresponding to the i-th invalid data; w i-1 Indicates the weight value corresponding to the i-1th invalid data; G i G represents the time interval between the generation time of the i-th invalid data and the most recent valid data with the same weight value corresponding to the i-th invalid data; i-1 G represents the time interval between the generation time of the most recent valid data with the same weight value as the i-1th invalid data and the i-th invalid data; p It represents the average value of the data generation time interval corresponding to n invalid data; Comparing the invalid evaluation coefficient with a preset invalid evaluation coefficient threshold; extracting invalid evaluation coefficients exceeding the invalid evaluation coefficient threshold as target invalid evaluation coefficients; The invalid data is filled using the target invalid evaluation coefficient.

5. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 4, characterized in that: Filling invalid data using the target invalid evaluation coefficient includes: Extracting the invalid data group where each target invalid evaluation coefficient is located as the target invalid data group; Extracting the generation time corresponding to each invalid data in the invalid data group where each target invalid evaluation coefficient is located; According to the generation time corresponding to each invalid data, obtain the valid data before and after the generation time of each invalid data; Obtain the invalid data compensation coefficient corresponding to the target invalid data group by using the valid data before and after each invalid data generation moment in combination with the target invalid evaluation coefficient; The invalid data compensation coefficient corresponding to the target invalid data group is obtained by the following formula: ； Wherein, B represents the invalid data compensation coefficient corresponding to the target invalid data group; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; X p represents the average value of the data corresponding to the valid data; P represents the invalid evaluation coefficient; P0 represents the preset invalid evaluation coefficient threshold; X z Indicates the middle value of the data corresponding to the valid data; Obtaining replacement data corresponding to each invalid data in the target invalid data group using the invalid data compensation coefficient corresponding to the target invalid data group; Each invalid data in the target invalid data group is replaced by the replacement data corresponding to each invalid data in the target invalid data group.

6. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 5, characterized in that: Acquiring replacement data corresponding to each invalid data in the target invalid data group using the invalid data compensation coefficient corresponding to the target invalid data group includes: Retrieve the invalid data compensation coefficient corresponding to the target invalid data group; Retrieve valid data with a time before and a time after each invalid data generation time in the target invalid data group; Acquire a data reference value corresponding to each invalid data in the target invalid data group by using valid data preceding and following the generation time of each invalid data in the target invalid data group; The data reference value is obtained by the following formula: ； Among them, X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 Respectively represent the data values ​​of the valid data before and after each invalid data generation moment; P0 represents the preset invalid evaluation coefficient threshold; P z Indicates the middle value of invalid evaluation coefficient corresponding to all invalid data groups; Obtain replacement data corresponding to each invalid data by using the invalid data compensation coefficient corresponding to the target invalid data group in combination with the data reference value corresponding to each invalid data in the target invalid data group; The replacement data corresponding to each invalid data is obtained by the following formula: ； Among them, X t Indicates the replacement data corresponding to each invalid data; X k Indicates the data reference value corresponding to each invalid data; X 01 and X 02 They respectively represent the data values ​​of the valid data before and after each invalid data generation moment; B represents the invalid data compensation coefficient corresponding to the target invalid data group.

7. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 6, characterized in that: In S1, the real-time data of gas in transformer oil based on laser spectroscopy is processed, and the following operations are also performed: Acquire real-time data of gas in transformer oil based on laser spectroscopy which is valuable for gas detection in transformer oil based on laser spectroscopy; Normalizing the real-time data of gas in transformer oil based on laser spectroscopy which is valuable for gas detection in transformer oil based on laser spectroscopy after cleaning; Eliminate the dimensional differences between real-time data of gas in transformer oil based on laser spectroscopy; Determine the real-time data of gas in transformer oil based on laser spectroscopy with data standardization; Feature extraction of real-time data of gas in transformer oil based on laser spectroscopy with data standardization; Extracting features that reflect the value of gas detection in transformer oil based on laser spectroscopy; The characteristic data of gas in transformer oil based on laser spectroscopy were determined.

8. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 7, characterized in that: In S2, a transformer oil gas detection fault identification model based on laser spectroscopy is constructed, and the transformer oil gas detection fault identification model based on laser spectroscopy is evaluated and optimized, and the following operations are performed: According to the demand for gas detection in transformer oil based on laser spectroscopy, historical gas concentration, trend, gas ratio and gas change rate are collected to determine the historical data of gas in transformer oil based on laser spectroscopy; Partitioning of historical data of gas in transformer oil based on laser spectroscopy; Determine a gas detection training set and a gas detection test set; According to the demand for gas detection in transformer oil based on laser spectroscopy, a neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is selected; Based on the gas detection training set, the selected neural network model framework suitable for gas detection in transformer oil based on laser spectroscopy is trained; Determine the fault identification model for gas detection in transformer oil based on laser spectroscopy; Based on the gas detection test set, the performance test and evaluation of the transformer oil gas detection fault identification model based on laser spectroscopy was carried out; Determine the performance test evaluation results of the fault identification model for gas detection in transformer oil based on laser spectroscopy; Analyze the performance test evaluation results of the transformer oil gas detection fault identification model based on laser spectroscopy; Determine the parameter adjustment optimization scheme of the transformer oil gas detection fault identification model based on laser spectroscopy; Based on the parameter adjustment optimization scheme, the parameters of the transformer oil gas detection fault identification model based on laser spectroscopy are adjusted and optimized; The optimal fault identification model for transformer oil gas detection based on laser spectroscopy was determined.

9. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 8, characterized in that: In S3, the characteristic data of gas in transformer oil based on laser spectrum is predicted and analyzed, and the following operations are performed: Obtain gas characteristic data in transformer oil based on laser spectroscopy; Inputting the gas characteristic data in transformer oil based on laser spectrum into the optimal transformer oil gas detection fault identification model based on laser spectrum; Based on the optimal transformer oil gas detection fault identification model based on laser spectroscopy, the characteristic data of transformer oil gas based on laser spectroscopy is predicted and analyzed; The fault identification results of gas detection in transformer oil based on laser spectroscopy were determined.

10. The method for detecting gas in transformer oil based on laser spectroscopy according to claim 9, characterized in that: In S4, intelligent control is performed on gas detection in transformer oil based on laser spectroscopy, and the following operations are performed: Obtain the results of transformer oil gas detection fault identification based on laser spectroscopy; Analyze the fault identification results of gas detection in transformer oil based on laser spectroscopy; Determine the intelligent control scheme for gas detection in transformer oil based on laser spectroscopy; Intelligent control of gas detection in transformer oil based on laser spectroscopy is carried out according to the intelligent control scheme of gas detection in transformer oil based on laser spectroscopy; Among them, based on the fault identification results of transformer oil gas detection based on laser spectroscopy, the nature and type of transformer fault are determined, timely early warning is given and intelligent management and control measures are formulated, the transformer fault is promptly repaired, and the transformer is regularly maintained and optimized according to the actual operating conditions, so that the transformer can operate stably for a long time.

Images