A method, system, product and medium for identifying mixed gases in transformer oil

Abstract

A transformer oil mixed gas identification method, system, product and medium, relate to the technical field of testing or analyzing materials by determining the chemical or physical properties of materials, the method comprises: obtaining a transformer internal structure diagram, determining the spatial position relationship of components and the corresponding temperature distribution characteristics, and obtaining the solubility difference in different spatial positions. Collect mixed gas concentration data at multiple detection points during operation, record initial gas concentration data when deviating from the threshold range, and correct gas concentration change data according to the solubility difference in different temperature zones. Calculate the spatio-temporal distribution characteristics of gas concentration, determine the gas accumulation area according to the spatial position relationship. Separate the mixed gas components by gas chromatography, compare the preset gas types with the content of each component, and determine the corresponding gas types in each internal area. The implementation of the method can improve the accuracy of transformer oil mixed gas type identification.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of testing or analyzing materials by determining the chemical or physical properties of the materials, and in particular to a transformer oil mixed gas identification method, system, product and medium. BACKGROUND

[0002] With the continuous expansion of the power grid scale and the continuous growth of power load, the safe and stable operation of the transformer as a key equipment in the power system is crucial to the guarantee of power supply. Internal faults of the transformer often cause decomposition of the insulating oil, generating various characteristic gases, and the types and contents of these gases can reflect the operation state and potential fault type of the transformer.

[0003] Currently, the identification of mixed gases in transformer oil is mainly through setting a sampling point at the top of the transformer oil tank, regularly collecting oil samples for offline analysis. After sampling, the mixed gases are separated by gas chromatography and other methods, and the fault type is judged according to the content ratio of various gases and combined with empirical rules.

[0004] During the actual operation of the transformer, the internal temperature distribution presents a large difference, and the oil temperature in different regions can differ by tens of degrees Celsius. This temperature difference can cause significant changes in the solubility of gases in the oil, making it difficult to accurately reflect the actual gas distribution state in the entire transformer interior with single-point sampling, increasing the difficulty of identifying gas types. SUMMARY

[0005] The present application provides a transformer oil mixed gas identification method, system, product and medium for improving the accuracy of transformer oil mixed gas type identification.

[0006] In a first aspect, the present application provides a transformer oil mixed gas identification method applied to a mixed gas identification system, which comprises: obtaining a transformer internal structure diagram, determining the spatial position relationship of each component inside the transformer and the temperature distribution characteristics corresponding to the spatial position relationship, and obtaining the solubility difference of the transformer at different spatial positions according to the temperature distribution characteristics; continuously collecting mixed gas concentration data of multiple detection points during the operation of the transformer, recording the initial gas concentration data of the multiple detection points when the mixed gas concentration data of the multiple detection points deviates from the operation threshold range, and correcting the gas concentration change data according to the solubility difference of different temperature zones to obtain the gas concentration change data; calculating the gas concentration spatiotemporal distribution characteristics based on the gas concentration change data, and determining the gas accumulation area inside the transformer according to the gas concentration spatiotemporal distribution characteristics and the spatial position relationship; separating the mixed gas components by gas chromatography to obtain the content of each component, and comparing the pre-set gas types in the gas accumulation area with the content of each component to determine the corresponding gas types of each region inside the transformer.

[0007] In the above embodiment, the internal structure diagram of the transformer is acquired, the temperature distribution characteristics are determined, the solubility difference at different spatial positions is calculated, and the temperature correction of the gas concentration data is realized. Based on the corrected data, the spatiotemporal distribution characteristics are calculated, the gas accumulation area is accurately located, the matching analysis is performed in combination with the preset gas type of the corresponding component of the area, and finally the accurate identification of the mixed gas in the transformer oil is realized, and the accuracy of the gas type identification is effectively improved.

[0008] In combination with some embodiments of the first aspect, in some embodiments, the step of calculating the spatiotemporal distribution characteristics of the gas concentration based on the gas concentration change data and determining the gas accumulation area of the gas in the transformer based on the spatiotemporal distribution characteristics of the gas concentration and the spatial position relationship specifically includes: establishing a gas concentration distribution model containing time and space dimensions based on the gas concentration change data, the gas concentration distribution model containing concentration data of a plurality of detection points at different times and spatial coordinate information of the detection points; calculating the gas concentration gradient and the gas diffusion direction based on the gas concentration distribution model, and obtaining the spatiotemporal distribution characteristics of the gas concentration based on the gas concentration gradient and the gas diffusion direction; and matching the spatiotemporal distribution characteristics of the gas concentration with the spatial position relationship of each component in the transformer, and determining the area with the largest change in the gas concentration as the gas accumulation area.

[0009] In the above embodiment, the gas concentration distribution model containing time and space dimensions is established, the concentration data and the spatial coordinate information of the detection points are combined, the gas concentration gradient and the diffusion direction are calculated. According to the matching relationship between the spatiotemporal distribution characteristics and the internal structure of the transformer, the area with the largest change in the gas concentration is located, accurate spatial positioning basis is provided for subsequent gas type identification, and the accuracy of the determination of the gas accumulation area is improved.

[0010] In some embodiments of the first aspect, in some embodiments, the step of separating the mixed gas components by gas chromatography to obtain the content of each component, comparing the preset gas species in the gas accumulation area with the content of each component to determine the corresponding gas species of each area inside the transformer, specifically comprises: obtaining the mixed gas sample by using an adaptive interval sampling method according to the distribution position of the gas accumulation area, separating the mixed gas sample by gas chromatography to obtain the response curve and component content of each gas component, and establishing the change relationship between the gas component content and time; extracting the type of transformer component where the gas accumulation area is located from the internal structure diagram of the transformer, obtaining the corresponding preset gas species dataset based on the component type, and the preset gas species dataset contains the typical content proportion relationship of various gas components under different fault types; the change relationship of the gas component content is matched with the typical content proportion relationship in the preset gas species dataset, and the similarity score is calculated according to the matching result, and the preset gas species with the highest similarity score is selected as the corresponding gas species of each area inside the transformer.

[0011] In the above embodiment, the mixed gas sample is obtained by using an adaptive interval sampling method, and the change relationship between the gas component content and time is established. The type of component where the gas accumulation area is located is extracted from the internal structure diagram of the transformer, the preset gas species dataset is obtained, and the pattern matching is performed by calculating the similarity score, which realizes the accurate identification of the gas species and reduces the misjudgment rate in the mixed gas identification process.

[0012] In some embodiments of the first aspect, before the step of obtaining the internal structure diagram of the transformer, determining the spatial position relationship of each component inside the transformer and the temperature distribution characteristics corresponding to the spatial position relationship, and obtaining the solubility difference of the transformer at different spatial positions according to the temperature distribution characteristics, the method further comprises: obtaining the historical data of the mixed gas concentration of multiple detection points in the transformer tank, calculating the time difference of the maximum gas concentration detected by each detection point; obtaining the running threshold range during normal operation according to the ratio of the maximum concentration values of each detection point.

[0013] In the above embodiment, the historical data of the mixed gas concentration of multiple detection points is obtained, the time difference of the maximum gas concentration between the detection points is calculated, and the threshold range of normal operation is established according to the ratio of the maximum concentration values of each detection point. Based on the running benchmark established by the time difference and the concentration ratio, the dynamic monitoring standard of the gas concentration change is formed, the identification sensitivity of the abnormal state of the gas is improved, and the accuracy of the mixed gas identification is enhanced.

[0014] In some embodiments of the first aspect, after the step of comparing the preset gas species in the gas accumulation area with the component content obtained by separating the mixed gas components by gas chromatography to determine the gas species corresponding to each region inside the transformer, the method further comprises: establishing a gas diffusion path diagram according to the gas species corresponding to each region inside the transformer, the gas diffusion path diagram including the diffusion path and diffusion time of the gas from the generation location to the detection point; based on the gas diffusion path diagram, combining the gas concentration spatiotemporal distribution characteristics and temperature distribution characteristics, calculating the diffusion rate of the gas on different diffusion paths; when new gas concentration change data is detected, reversely positioning the gas generation location according to the diffusion rate to determine the gas source location; positioning the transformer according to the gas source location to obtain the transformer fault location.

[0015] In the above embodiments, the gas diffusion path diagram is established based on the gas species, and the diffusion rate on different diffusion paths is calculated by combining the gas concentration spatiotemporal distribution characteristics and temperature distribution characteristics. The gas generation location is reversely positioned according to the diffusion rate to accurately identify the gas source location, thereby enhancing the accuracy of the transformer fault location positioning and forming a complete gas tracking positioning mechanism.

[0016] In some embodiments of the first aspect, after the step of comparing the preset gas species in the gas accumulation area with the component content obtained by separating the mixed gas components by gas chromatography to determine the gas species corresponding to each region inside the transformer, the method further comprises: establishing a fault feature library according to the gas source location and the gas species, the fault feature library including gas combination characteristics and gas generation regularity under different fault types; constructing a fault prediction model based on the fault feature library, the fault prediction model taking the gas combination characteristics and the gas generation regularity as input parameters; evaluating the transformer operating state by using the fault prediction model, predicting the potential fault risk, and generating fault warning information according to the prediction result.

[0017] In the above embodiments, the fault feature library is established according to the gas source location and the gas species, and the fault prediction model including the gas combination characteristics and the gas generation regularity is constructed. The transformer operating state is evaluated by using the fault prediction model, and the fault warning information is generated, thereby establishing a linkage mechanism of gas species identification and fault prediction and enhancing the accuracy and foresight of the transformer operating state evaluation.

[0018] In some embodiments of the first aspect, in some embodiments, after the step of comparing the preset gas types in the gas accumulation area with the component contents obtained by separating the mixed gas components by gas chromatography to determine the gas types corresponding to each area inside the transformer, the method further comprises: calculating the spatial distance difference value between the gas accumulation area of the target transformer and the gas accumulation area of each type of transformer and the coincidence degree of the gas type combination, determining the transformer with a spatial distance difference value less than a first preset threshold and a gas type combination coincidence degree greater than a second preset threshold as a similar transformer; performing area matching on the gas accumulation area of the similar transformer, and comparing the gas types of each gas accumulation area in the target transformer with the corresponding area of the similar transformer; and if the difference value of the gas type and the main gas type of the corresponding target area of the similar transformer exceeds a preset difference threshold, increasing the sampling point density and sampling frequency of the target area.

[0019] In the above embodiments, the spatial distance difference value and the gas type combination coincidence degree between the target transformer and each type of transformer are calculated, and similar transformers are screened out for area matching. When the difference value of the gas type and the main gas type of the corresponding area of the similar transformer exceeds a preset difference threshold, the sampling point density and sampling frequency of the target area are increased, forming an adaptive sampling mechanism based on similarity analysis, and improving the data acquisition quality of mixed gas identification.

[0020] In the second aspect, the embodiments of the present application provide a mixed gas identification system, which comprises: one or more processors and a memory; the memory is coupled to the one or more processors, and the memory is used to store computer program codes, the computer program codes comprising computer instructions, and the one or more processors invoke the computer instructions to enable the mixed gas identification system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0021] In the third aspect, the embodiments of the present application provide a computer program product comprising instructions, which, when executed on a mixed gas identification system, enable the mixed gas identification system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0022] In the fourth aspect, the embodiments of the present application provide a computer readable storage medium comprising instructions, which, when executed on a mixed gas identification system, enable the mixed gas identification system to perform the method described in the first aspect and any possible implementation manner of the first aspect.

[0023] It can be understood that the mixed gas identification system provided by the second aspect, the computer program product provided by the third aspect and the computer storage medium provided by the fourth aspect are all used to execute the method provided by the embodiments of the present application. Therefore, the beneficial effects that can be achieved are referred to the beneficial effects in the corresponding method, which will not be repeated here.

[0024] The one or more technical solutions provided in the embodiments of the present application have at least the following technical effects or advantages:

[0025] 1. The present application calculates the solubility difference of different spatial positions by obtaining the internal structure diagram of the transformer and determining the temperature distribution characteristics, realizes the temperature correction of the gas concentration data. Based on the corrected data, the space-time distribution characteristics are calculated, the gas accumulation area is accurately located, and the matching analysis is carried out combined with the preset gas species of the corresponding components in the area, and finally the accurate identification of the mixed gas in the transformer oil is realized, which effectively improves the accuracy of gas species identification.

[0026] 2. The present application calculates the gas concentration gradient and diffusion direction by combining the concentration data of the detection point with the spatial coordinate information through establishing a gas concentration distribution model containing time and space dimensions. According to the matching relationship between the space-time distribution characteristics and the internal structure of the transformer, the area with the largest change of gas concentration is located, which provides accurate spatial positioning basis for subsequent gas species identification and improves the accuracy of gas accumulation area determination.

[0027] 3. The present application obtains mixed gas samples by using adaptive interval sampling method, establishes the change relationship between gas component content and time. The type of component in which the gas accumulation area is located is extracted from the internal structure diagram of the transformer, the preset gas species dataset is obtained, and the pattern matching is realized by calculating the similarity score, which realizes the accurate identification of gas species and reduces the misjudgment rate in the process of mixed gas identification. BRIEF DESCRIPTION OF DRAWINGS

[0028] Figure 1 is a flowchart of the mixed gas identification method in the transformer oil in the embodiments of the present application;

[0029] Figure 2 is another flowchart of the mixed gas identification method in the transformer oil in the embodiments of the present application;

[0030] Figure 3 is a schematic diagram of an entity device structure of the mixed gas identification system in the embodiments of the present application. DETAILED DESCRIPTION

[0031] The terminology used in the following embodiments of the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the description of the application, the singular forms "a", "an" and "the" are intended to include plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or", as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0032] Hereinafter, the terms "first", "second" are only used for the purpose of description, and cannot be understood as implying or suggesting relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined with "first", "second" can explicitly or implicitly include one or more of the features, and in the description of the embodiments of the present application, the meaning of "a plurality of" is two or more, unless otherwise specified.

[0033] In order to facilitate understanding, the application scenarios of the embodiments of the present application are introduced as follows.

[0034] There are multiple functional components in a transformer, such as windings, cores, bushings, etc. Each component will produce a specific kind of characteristic gas when it fails. For example, C2H4 is mainly produced when the winding overheats, while CH4 and H2 may be produced when the core fails. However, due to the uneven temperature distribution inside the transformer, the solubility of the same gas in different temperature zones differs significantly, resulting in that the detected gas concentration data cannot directly reflect the true situation. At the same time, due to the lack of systematic analysis of the pre-set gas types of different components, it is difficult to accurately correspond the detected gas to the specific transformer component.

[0035] The method of the related art, when performing gas analysis, can obtain the content of various gases through gas chromatography, but cannot associate these gases with specific transformer components. For example, when detecting that the mixed gas contains H2, CH4 and C2H4, since there is no correspondence between component types and gas types, and the influence of temperature on solubility is not considered, it is impossible to determine whether these gases come from winding overheating, core failure or problems of other components. This analysis method ignores the combination characteristics of characteristic gases produced by different components when they fail, and reduces the accuracy of gas identification.

[0036] The system adopting the method of the application first establishes a complete transformer structure diagram, accurately records the spatial positions of each component and the corresponding temperature distribution characteristics. After the system detects gas anomalies through multi-point monitoring, it determines the gas accumulation area through temperature correction and space-time distribution analysis. More importantly, the system can identify the specific transformer component type (such as high-voltage winding, low-voltage lead, etc.) corresponding to the accumulation area and call the preset gas species data set of the type of component. These data sets contain the characteristic gas combinations and their typical proportion relationships that each component may produce under different fault types. For example, when the system detects gas accumulation in the high-voltage winding area, it compares the gas components obtained through gas chromatographic analysis with the preset gas species of the type of winding, thereby accurately identifying the specific gas species in the accumulation area. This preset gas species matching method based on component type significantly improves the accuracy and relevance of mixed gas identification.

[0037] For ease of understanding, the method provided by the present embodiment is described in the flow below in combination with the above scenario. Please refer to Figure 1 , which is a flowchart of the method for identifying mixed gases in transformer oil in the embodiment of the application.

[0038] S101, obtain a transformer internal structure diagram, determine the spatial position relationship of each component inside the transformer and the temperature distribution characteristics corresponding to the spatial position relationship, and obtain the solubility difference of the transformer at different spatial positions according to the temperature distribution characteristics.

[0039] The transformer internal structure diagram represents the engineering drawing of the layout, installation position and mutual connection relationship of each functional component inside the transformer; the spatial position relationship refers to the relative position and distance relationship between each component inside the transformer; the temperature distribution characteristics are used to represent the temperature distribution law and change characteristics of each part of the transformer during operation; and the solubility difference represents the difference in the solubility of gas in transformer oil due to different temperatures.

[0040] Specifically, this step is performed before the transformer is put into operation. By obtaining the design drawing and technical document of the transformer, the internal structure layout of the transformer is analyzed to determine the spatial distribution of each functional component such as the core, winding, bushing, etc. Combined with the operating parameters and thermal field simulation analysis of the transformer, a temperature field distribution model is established to calculate the temperature distribution characteristics of different regions. Based on the relationship curve between the solubility of gas in oil and temperature, the gas solubility difference data of different temperature regions are obtained.

[0041] In some embodiments, the temperature distribution characteristics and the solubility difference can be obtained by: optionally, installing temperature sensors at key positions of the transformer, collecting actual operation data, and establishing an accurate three-dimensional temperature field distribution model in combination with thermal field calculation software; optionally, based on the structural parameters and operating conditions of the transformer, using a finite element analysis method to simulate the thermal field to obtain the steady-state and transient temperature distribution; and optionally, estimating the temperature rise and temperature gradient of each region through theoretical calculation and empirical formula. It can be understood that other temperature field analysis methods can also be used to obtain the temperature distribution characteristics, which are not limited here.

[0042] S102, continuously collecting mixed gas concentration data of multiple detection points during the operation of the transformer, recording initial gas concentration data of the multiple detection points when the mixed gas concentration data of the multiple detection points deviates from the operating threshold range, and correcting the gas concentration change data according to the solubility difference of different temperature zones to obtain the gas concentration change data.

[0043] In the formula, the detection point represents a sensor position installed in the transformer oil tank for collecting gas concentration data; the mixed gas concentration data refers to the content data of various characteristic gases collected by the detection point; the operating threshold range represents the allowable fluctuation range of the gas concentration when the transformer is normally operated; and the gas concentration change data is used to represent the change trend of the gas concentration over time.

[0044] Specifically, this step is continuously performed during the operation of the transformer, and the gas concentration data is synchronously collected through multiple detection points to monitor the change of the gas concentration in real time. When it is detected that the gas concentration exceeds the normal operation threshold, the initial concentration value of each detection point is recorded as the baseline data. Considering the influence of temperature on the solubility of gas, the gas concentration data of different temperature zones is corrected according to the solubility difference data obtained in step S101 to eliminate the interference of the temperature factor.

[0045] In some embodiments, the collection and correction of the gas concentration data can be achieved by: optionally, using an optical fiber sensor array to arrange multiple detection points in the transformer oil tank to realize real-time online monitoring of the gas concentration; optionally, based on the temperature coefficient of gas solubility, establishing a concentration correction model to perform temperature compensation on the original data; and optionally, determining the normal operation threshold through data statistical analysis to establish an abnormal detection rule. It can be understood that other gas detection and data processing methods can also be used to achieve this step, which is not limited here.

[0046] S103, calculating the gas concentration space-time distribution characteristics based on the gas concentration change data, and determining the gas accumulation region of the transformer based on the gas concentration space-time distribution characteristics and the spatial position relationship.

[0047] The gas concentration spatial-temporal distribution feature represents the change law of the gas concentration in the time and space dimensions; the gas concentration gradient refers to the change rate of the gas concentration in the space; the gas diffusion direction is used to represent the migration trend of the gas in the transformer oil; the gas accumulation area represents the main area where the gas is accumulated in the transformer; and the concentration distribution model refers to a mathematical model describing the change of the gas concentration with time and space.

[0048] Specifically, this step is performed after the corrected gas concentration change data is obtained. First, the concentration data and spatial coordinate information of each detection point are integrated to establish a gas concentration distribution model containing time and space information. The concentration difference and spatial distance between adjacent detection points are calculated to obtain the gas concentration gradient. The diffusion direction of the gas is analyzed in combination with the temperature field distribution and the oil flow field characteristics. The gas concentration spatial-temporal distribution feature is matched and analyzed with the internal structure of the transformer to determine the area with the most significant change in gas concentration as the gas accumulation area.

[0049] In some embodiments, the calculation of the gas concentration spatial-temporal distribution feature and the determination of the gas accumulation area can be achieved in various ways: optionally, a three-dimensional interpolation algorithm is used to reconstruct the concentration data of discrete detection points in space to establish a continuous concentration distribution field, the concentration gradient in each direction is calculated by partial derivative, the gas diffusion path is determined in combination with the oil flow field simulation, and finally the high-concentration area is identified through clustering analysis; optionally, a dynamic diffusion model is established based on the time series data of the detection points to analyze the time evolution characteristics of the gas concentration, calculate the concentration change rate and accumulation, and divide the potential accumulation area in combination with the structure characteristics of the transformer to determine the final gas accumulation area by setting a threshold. It can be understood that other data analysis and pattern recognition methods can also be used to determine the gas accumulation area, which is not limited here.

[0050] This step specifically includes:

[0051] According to the gas concentration change data, a gas concentration distribution model containing time and space dimensions is established, which contains concentration data of multiple detection points at different times and spatial coordinate information of the detection points.

[0052] The gas concentration distribution model refers to a mathematical model describing the distribution state of the gas in the transformer, containing the change characteristics of two dimensions of time and space; the concentration data represent the gas content values measured by each detection point, in units of ppm or μL / L; and the spatial coordinate information of the detection point contains three-dimensional position information (x, y, z) of the detection point in the transformer.

[0053] The process of establishing the gas concentration distribution model starts with data collection. First, determine the arrangement scheme of detection points, install gas sensors at key parts of the transformer, and record the precise spatial coordinates of each sensor. Perform continuous sampling at each detection point with a sampling interval of 1 hour, and record data for at least 168 hours (7 days). The collected data includes gas concentration values and corresponding timestamps. Organize the collected data into a three-dimensional matrix form, where the x, y, and z axes represent spatial coordinates, the fourth dimension represents time, and the matrix element values are the gas concentrations of the corresponding space-time points. Use a three-dimensional interpolation algorithm to perform spatial interpolation on the discrete detection point data to generate a continuous concentration distribution field. Use a spline interpolation method in the time dimension to obtain the continuous change curve of concentration over time. Finally, establish a complete four-dimensional concentration distribution model to describe the dynamic change process of gas concentration in time and space.

[0054] According to the gas concentration distribution model, calculate the gas concentration gradient and gas diffusion direction, and obtain the gas concentration spatiotemporal distribution characteristics according to the gas concentration gradient and gas diffusion direction.

[0055] Among them, the gas concentration gradient represents the concentration change rate per unit distance, reflecting the degree of concentration field change; the gas diffusion direction refers to the main direction of gas molecule movement, determined by the normal vector of the concentration field contour surface; the gas concentration spatiotemporal distribution characteristics include the spatial distribution characteristics and temporal evolution characteristics of the concentration field.

[0056] Based on the established concentration distribution model, calculate the concentration gradient and diffusion direction. In the spatial dimension, use the central difference method to calculate the concentration gradient vector of each point: ∇C=(∂C / ∂x, ∂C / ∂y, ∂C / ∂z). The modulus of the gradient vector represents the concentration change rate, and the direction points to the direction of the fastest concentration increase. At each spatial point, calculate the contour surface of the local concentration field, and the normal vector of the contour surface is the diffusion direction of that point. Analyze the time series data to calculate the time derivative of the concentration ∂C / ∂t, which describes the rate of change of the concentration over time. Integrate the spatial gradient and time derivative information to construct the spatiotemporal distribution characteristic descriptor of the gas concentration. This descriptor includes: spatial distribution characteristics (gradient field distribution, diffusion direction field) and temporal evolution characteristics (concentration change rate, periodicity characteristics).

[0057] Match the gas concentration spatiotemporal distribution characteristics with the spatial position relationship of each component inside the transformer to determine the region with the largest gas concentration change as the gas accumulation region.

[0058] Among them, the spatial position relationship represents the relative position relationship between the gas concentration field and the structural components of the transformer; the gas accumulation region refers to the spatial region where the gas concentration continuously increases and maintains at a high level, which is usually closely related to the fault location.

[0059] When performing spatial matching, first align the three-dimensional structure model of the transformer with the concentration distribution model in coordinates. Calculate the average concentration value and concentration change rate around each structural component. Identify areas where the concentration change rate exceeds a set threshold (such as 0.5 ppm / h), and mark these areas as potential gas accumulation areas. For each potential area, calculate the spatial second derivative of the concentration field to determine if the area is a local maximum point. Select the area with the highest concentration value and negative second derivative as the main gas accumulation area. Record the spatial range, center coordinates, and corresponding structural component information of the accumulation area. By continuously monitoring the evolution of the accumulation area, verify the stability of the area identification result. The final determined gas accumulation area is the key focus area for fault diagnosis.

[0060] S104, separate the components of the mixed gas by gas chromatography to obtain the content of each component, and compare the preset gas species in the gas accumulation area with the content of each component to determine the corresponding gas species of each area inside the transformer.

[0061] Wherein, the gas chromatography refers to an analysis method that separates different gas components in the fixed phase and flow phase according to the difference in distribution coefficient; the response curve represents the change curve of the detector output signal with time in the chromatographic analysis process; the component content refers to the concentration or volume ratio of various gases in the mixed gas; the preset gas species data set is used to represent the characteristic gases and their typical content ratio relationship that may be generated under different types of faults; the similarity score represents the matching degree of the measured gas components and the preset data.

[0062] Specifically, this step is performed after determining the gas accumulation area. First, according to the location characteristics of the accumulation area, an adaptive sampling strategy is used to obtain a gas sample. The sample is analyzed using a gas chromatograph, and the response curve of each component is recorded. The component content is calculated by integration. Extract the component information corresponding to the accumulation area from the transformer structure diagram, query the preset gas species data set to obtain possible gas characteristics. Perform pattern matching between the measured gas component content and the preset data, calculate the similarity score, and select the most matched gas species as the characteristic gas of the area.

[0063] In some embodiments, the analysis of mixed gas components and the determination of gas species can be achieved in various ways: optionally, a programmed temperature gas chromatography method is used, the carrier gas flow rate and column temperature program are optimized to improve the chromatographic resolution, the content of each component is quantitatively analyzed by external standard method, the change curve of component content with time is established, and the characteristic matching is carried out by using pattern recognition algorithm; alternatively, a multi-dimensional gas feature vector is established, which contains component content, generation rate, ratio relationship and other parameters, a classification model based on support vector machine is constructed, model training is combined with historical case data to realize automatic identification of gas species. It can be understood that other analytical chemistry and machine learning methods can also be used to identify the gas species, which are not limited here.

[0064] This step specifically includes:

[0065] According to the distribution position of the gas accumulation area, a self-adaptive interval sampling method is used to obtain a mixed gas sample, the mixed gas sample is separated by gas chromatography, the response curve and component content of each gas component are obtained, and the change relationship between the gas component content and time is established.

[0066] Among them, the self-adaptive interval sampling method refers to a sampling strategy that dynamically adjusts the sampling time interval according to the gas concentration change rate; the mixed gas sample refers to a sample containing multiple gas components extracted from the transformer oil; the gas chromatography is an analysis method that separates different gas components in the stationary phase and the mobile phase according to the difference in distribution coefficient; the response curve represents the change curve of the detector output signal with time during chromatographic analysis.

[0067] When performing gas component analysis, first arrange sampling points in the gas accumulation area. The sampling interval adopts a self-adaptive control strategy: when the concentration change rate is greater than 1 ppm / h, the sampling interval is set to 2 hours; when the change rate is between 0.1-1 ppm / h, the sampling interval is set to 6 hours; when the change rate is less than 0.1 ppm / h, the sampling interval is set to 12 hours. Use a gas extraction device to extract dissolved gas from the transformer oil, and the sample volume extracted each time is 50 mL. Inject the sample into a gas chromatograph for analysis, and the chromatographic conditions are set as follows: the carrier gas is helium, the flow rate is 30 mL / min, the column temperature is 60°C, and the detector temperature is 200°C. Record the complete chromatogram, identify each gas component by retention time. Integrate the chromatographic peaks, calculate the content of each component according to the peak area and the standard curve. Establish the change curve of the content of each gas component with time within 24 hours, and the curve is continuously processed by using piecewise linear interpolation method.

[0068] From the transformer internal structure diagram, the type of transformer component where the gas accumulation area is located is extracted, and based on the component type, the corresponding preset gas species data set is obtained, which contains the typical content ratio relationship of various gas components under different fault types.

[0069] wherein the transformer internal structure diagram represents engineering drawings of the spatial layout and connection relationship of each component of the transformer; the component type includes functional units such as winding, core, bushing, etc.; the preset gas species dataset is a gas characteristic database established according to historical fault cases and theoretical analysis; and the typical content proportion relationship refers to the relative content proportion of characteristic gases under different fault types.

[0070] When extracting the component information of the gas accumulation area, first, the area center coordinates are substituted into the transformer three-dimensional structure model. The component type where the coordinate point is located is identified, and the basic characteristics of the component are recorded, including material properties, working temperature, stress distribution and other information. According to the component type, the preset gas species dataset is searched, which contains the characteristic gas information generated by each component under different fault modes. The structure of the dataset is: component type-fault type-gas component-content proportion. For example, for winding overheating fault, the typical gas component proportion is: C2H4:C2H6:CH4=3:1:1. For core grounding fault, the typical proportion is: H2:CH4:C2H6=4:2:1. Extract all gas proportion data related to the current component type to form a set of characteristic templates to be matched.

[0071] The change relationship of the gas component content is matched with the typical content proportion relationship in the preset gas species dataset, and the similarity score is calculated according to the matching result, and the preset gas species with the highest similarity score is selected as the gas species corresponding to each area inside the transformer.

[0072] wherein the pattern matching refers to the process of comparing the measured gas component data with the preset characteristic template; the similarity score represents the matching degree of the measured data and the characteristic template; and the preset gas species refers to the most likely gas combination type determined according to the matching result.

[0073] When performing pattern matching, first, the measured gas component data is standardized. The content ratio between each component is calculated to construct a feature vector. For each characteristic template in the preset dataset, the cosine similarity between the measured feature vector and the template feature vector is calculated. The similarity calculation formula is: cos(θ)=(A·B) / (|A|·|B|), wherein A is the measured feature vector and B is the template feature vector. The Euclidean distance is also calculated as an auxiliary evaluation index. The similarity score and the distance score are combined according to the weight of 0.7:0.3 to obtain a comprehensive score. The gas species corresponding to the characteristic template with the highest comprehensive score is selected as the characteristic gas combination of the area. The matching result is recorded, including the gas species, the matching score and the suboptimal matching result, which provides a basis for subsequent fault diagnosis.

[0074] In some embodiments, step 101 can further include the following steps before step 101:

[0075] The historical data of mixed gas concentration of multiple detection points in the transformer oil tank is obtained, and the time difference of maximum gas concentration detected by each detection point is calculated.

[0076] In the formula, the historical data of mixed gas concentration represents the content record of dissolved gas in the transformer oil in the past period of time, and the unit is μL / L or ppm; the detection point refers to the position of the gas sensor installed in the transformer oil tank; and the concentration maximum time difference refers to the time interval of reaching the gas concentration peak of different detection points, reflecting the time characteristics of gas diffusion process.

[0077] When obtaining the historical data, first, the time range of data collection is determined, and usually the continuous monitoring data of the last 30 days is selected. For the data of each detection point, 5 minutes is used as the basic sampling interval, and the concentration values of characteristic gases such as C2H2, CH4, C2H4, C2H6 and H2 are recorded. The original data is preprocessed, including outlier rejection and data smoothing. The 3σ criterion is used for outlier rejection, that is, the data points deviating from the mean value by more than 3 times the standard deviation are marked as outliers. The 5-point moving average method is used for data smoothing to reduce the influence of random fluctuations. For the processed data sequence, the concentration peak and its occurrence time of each detection point are identified. The time difference between adjacent detection points reaching the peak is calculated and recorded as Δt. Taking the nearest detection point pair as an example, if detection point A reaches the peak of 100 ppm at t1, and detection point B reaches the peak of 80 ppm at t2, then the time difference Δt=t2-t1. The time difference data of all detection point pairs are arranged in matrix form for subsequent analysis.

[0078] The running threshold range in normal operation is obtained according to the ratio of the maximum concentration value of each detection point.

[0079] In the formula, the ratio of the maximum concentration value represents the ratio of the maximum concentration of gas detected by adjacent detection points; and the running threshold range refers to the reasonable change interval of gas concentration ratio in the normal operation state of the transformer.

[0080] When calculating the running threshold range, first calculate the maximum concentration ratio r = Cmax1 / Cmax2 for each pair of adjacent detection points, where Cmax1 and Cmax2 are the maximum concentration values detected by the two detection points, respectively. Calculate the mean μ and standard deviation σ of the concentration ratio data of all detection point pairs. Based on the normal distribution characteristics, define the interval [μ-2σ, μ+2σ] as the threshold range for normal operation, which contains about 95% of the normal operation data. For example, the concentration ratio statistics of a pair of detection points are: mean μ = 1.2, standard deviation σ = 0.1, then the running threshold range is [1.0, 1.4]. Establish an independent threshold range for each pair of detection points to form a complete threshold matrix. When the measured concentration ratio exceeds the threshold range, it indicates that the gas distribution is abnormal and further analysis is needed. The calculation results of the threshold range are recorded in the database as a reference standard for subsequent monitoring.

[0081] The method provided by the embodiment is further described in more detail below. Please refer to Figure 2 , which is another flowchart of the method for identifying mixed gases in transformer oil in the embodiment of the present application.

[0082] S201, establish a gas diffusion path diagram according to the gas species corresponding to each region inside the transformer, which contains the diffusion path and diffusion time of the gas from the generation position to the detection point.

[0083] Wherein, the gas diffusion path diagram represents a spatial network structure diagram describing the migration process of the gas in the transformer oil, containing migration path, node position and transmission time, etc. information; the diffusion path refers to the actual motion trajectory of the gas molecules in the transformer oil from the generation position to the detection point, which is affected by the oil flow velocity field and temperature field; the diffusion time represents the time interval required for the gas to transmit from the initial generation position to a specific detection point, which is related to path length, oil flow velocity and temperature distribution, etc. factors.

[0084] After determining the corresponding gas species of each region, the gas diffusion path diagram is constructed. First, the internal oil channel layout is obtained by analyzing the transformer structure diagram, including the main oil channel, auxiliary oil channel, and natural convection channel, etc., to establish a complete oil flow channel network model. All detection points and possible gas generation locations are marked as network nodes, and the connectivity between nodes is analyzed using graph theory. For each oil flow channel, a three-dimensional model is established and simulated using computational fluid dynamics software to calculate the oil flow velocity field distribution under steady-state conditions. Based on the physical and chemical properties of different gases, such as molecular weight, diffusion coefficient, etc., combined with the oil flow field characteristics, the motion trajectory of the gas in each channel is calculated. Through numerical integration method, the time required for the gas to reach the detection point from the generation location along each possible path is calculated. Finally, a multi-level path diagram is formed, including the main diffusion channel, secondary diffusion channel, and emergency channel, each channel is marked with detailed spatial coordinate information and transmission time data. This path diagram provides important spatial topology information for subsequent gas source positioning and fault diagnosis.

[0085] In S202, based on the gas diffusion path diagram, the diffusion rate of the gas on different diffusion paths is calculated combined with the spatiotemporal distribution characteristics of the gas concentration and the temperature distribution characteristics.

[0086] wherein the diffusion rate represents the migration speed of gas molecules in the transformer oil, including the comprehensive effect of convective diffusion and molecular diffusion two mass transfer mechanisms; the spatiotemporal distribution characteristics of the concentration describe the variation law of the gas concentration in the time and space dimensions, reflecting the diffusion process of the gas inside the transformer; the temperature distribution characteristics represent the temperature field distribution state of each region of the transformer, affecting the diffusion coefficient of the gas and the flow characteristics of the oil.

[0087] Based on the established gas diffusion path diagram, the diffusion rate is accurately calculated. First, the gas concentration data of each detection point is analyzed in time sequence, and the rate of change of the concentration with time is calculated by numerical difference method. For each diffusion path, the spatial coordinate information of the detection points at both ends of the path is extracted, and the actual length and geometric characteristics (such as curvature, cross-sectional area change, etc.) of the path are calculated. Combined with the concentration data of the detection points, the concentration gradient on the path is calculated. Considering the influence of temperature on the diffusion process of the gas, a modified Fick diffusion equation is used for modeling. In the specific calculation, the average temperature and temperature gradient on the path are first obtained, and the actual diffusion coefficient is calculated according to the temperature dependence of the diffusion coefficient of the gas. The diffusion coefficient, concentration gradient, and path geometric parameters are substituted into the diffusion equation to solve the diffusion flux of the gas. For the regions with forced convection, the contribution of the oil flow velocity is superimposed to obtain the comprehensive mass transfer flux. By dividing the mass transfer flux by the effective cross-sectional area of the path, the diffusion rate of the gas on the path is obtained. Repeat the above process to complete the rate calculation of all diffusion paths, and establish a complete diffusion rate database. These data provide quantitative basis for subsequent fault source positioning.

[0088] S203, when detecting new gas concentration change data, the gas generation position is inversely located according to the diffusion rate, and the gas source position is determined.

[0089] Wherein, the gas concentration change data represents the real-time acquisition of the dynamic change information of the gas concentration of the detection point, including the concentration value and the corresponding time stamp; the inverse positioning process refers to the use of detection data and known diffusion characteristics to deduce the initial generation position of the gas; the gas source position represents the accurate spatial position of the initial generation of the fault gas, corresponding to the specific fault point inside the transformer.

[0090] In the process of transformer operation, the gas concentration data is continuously monitored, and when abnormal changes are detected, the inverse positioning algorithm is started. First, the data of all detection points is preprocessed, including noise filtering, data smoothing and outlier detection. Extract the time when each detection point first detects significant changes in gas concentration as the time marker of the arrival of the gas at this point. Combined with the calculated diffusion rate data, an equation set based on space-time relationship is established. The equation set contains the spatial coordinates of each detection point, the detection time and the diffusion rate on the corresponding path, and the three-dimensional coordinates of the gas source are unknown. The least square method is used to solve the equation set, and the square error sum of the calculated theoretical transmission time and the actual detection time is minimized through iterative optimization. In the optimization process, the influence of measurement error and model error is considered, and a weight coefficient is introduced for correction. When the iteration converges, the optimal gas source position coordinates are obtained. Match the coordinates with the transformer structure diagram to determine the specific location of the fault, providing accurate spatial positioning information for subsequent maintenance and processing. Through continuous updating and improvement of the positioning algorithm, the accuracy of the source positioning is continuously improved.

[0091] S204, according to the gas source position, the transformer is positioned, and the transformer fault position is obtained.

[0092] Wherein, the gas source position represents the generation coordinate point of the fault gas inside the transformer; the transformer fault position refers to the specific component or area position causing the gas generation; the positioning process represents the conversion process of mapping the gas source position to the actual structure of the transformer.

[0093] After obtaining the spatial coordinates of the gas source, it is converted into the fault location in the actual structure of the transformer. First, a three-dimensional structural model of the transformer is established, including the precise position information of all functional components such as windings, cores, bushings, and leads. The gas source coordinate point is imported into the three-dimensional model, and the structural part where the point is located is determined through spatial coordinate transformation. Combined with the geometric size and installation position of the components, the shortest distance from the source point to the surface of each component is calculated. Set the distance threshold to 50 mm, and mark the components with a distance less than the threshold as potential fault locations. For each potential fault location, analyze its working characteristics and stress distribution, and evaluate the reasonableness of the mechanism of generating fault gas. Considering factors such as component stress, temperature distribution, and electric field distribution, the final fault location is determined. The fault location is marked with the numbering method in the equipment drawings, and is accurate to the specific component unit, such as "A-phase high-voltage winding third laminated plate" or "B-phase low-voltage lead second elbow". At the same time, the surrounding environmental characteristics of the fault location are recorded, providing complete spatial information for maintenance and treatment.

[0094] S205, establishing a fault feature library according to the gas source location and the gas type, the fault feature library including gas combination features and gas generation rules under different fault types.

[0095] Among them, the fault feature library represents a data set recording the correspondence between the transformer fault type and the gas feature; the gas combination feature refers to the type and proportion of characteristic gas generated by different types of faults; and the gas generation rule represents a mathematical model of the change of gas concentration over time.

[0096] The process of establishing the fault feature library starts from data collection. Collect the gas source location data in historical fault cases, including spatial coordinates, component types, and surrounding environment information. For each fault case, extract the gas component data obtained by gas chromatography analysis, and record the content and ratio of various gases. Through time series analysis, calculate the change rate of gas concentration, fit the concentration-time curve, and extract the characteristic parameters such as growth rate and saturation value. For each fault type, statistics the typical gas combination mode, including the main gas type, secondary gas type, and content range. Establish a gas generation rule model to describe the complete evolution process of gas concentration from fault occurrence to stability. Store all feature data by fault type to form a structured feature library. Each record contains complete information such as fault location, fault type, gas combination feature, and concentration change curve, facilitating subsequent pattern matching and fault prediction.

[0097] S206, constructing a fault prediction model based on the fault feature library, the fault prediction model taking the gas combination feature and the gas generation rule as input parameters.

[0098] Wherein, the fault prediction model represents a mathematical model for predicting potential transformer faults; the input parameters include real-time monitored gas data and historical features extracted from the feature library; the prediction result represents a quantitative assessment of the fault type and development trend.

[0099] A prediction model is constructed based on the complete fault feature library. First, the data in the feature library is preprocessed, including data standardization, feature dimensionality reduction, and outlier processing. Key feature parameters are selected as model inputs, including gas species combinations, concentration ratios, and change rates. A multi-layer prediction model is constructed using machine learning methods: the first layer uses support vector machines for fault type identification, the second layer uses neural networks to predict fault development trends, and the third layer uses decision trees to assess fault severity. During model training, the feature library data is divided into training and validation sets in a 7:3 ratio. Cross-validation is used to optimize model parameters and improve prediction accuracy. For each new monitoring data point, the three-layer model is analyzed in sequence to obtain the probability distribution of the fault type, the time curve of the development trend, and the quantitative score of the severity. A standardized evaluation report is generated based on the prediction results, including specific fault diagnosis conclusions and handling suggestions.

[0100] S207, using the fault prediction model to evaluate the transformer operating state, predict the potential fault risk, and generate fault warning information according to the prediction result.

[0101] Wherein, the transformer operating state represents the working condition of the transformer at a certain time, including load level, temperature distribution, and gas content parameters; the potential fault risk refers to the probability and severity of future faults evaluated by the prediction model; the fault warning information includes fault type judgment, development trend prediction, and handling suggestions.

[0102] When evaluating the real-time state of the transformer, first collect the operating parameter data, including gas concentration, temperature value, and load current at each detection point. Input these data into the first layer of the fault prediction model, and calculate the probability distribution of the current state belonging to various fault types using support vector machines. Select the three fault types with the highest probability and input them into the second layer neural network of the prediction model to calculate the fault development trend. The neural network uses a time series prediction method to predict the gas concentration changes in the next 24 hours, 72 hours, and 7 days. For each time point prediction result, evaluate the fault severity using a decision tree model and divide it into four levels: normal, attention, warning, and danger. When the prediction result shows that the severity of a certain time point reaches the warning or danger level, trigger the fault warning mechanism. The generated warning information includes: fault type and probability, gas concentration trend chart, predicted time to reach the critical value, recommended handling measures, and operating parameters that need to be focused on. The warning information is pushed in different ways according to the severity to ensure that relevant personnel obtain fault risk information in a timely manner.

[0103] S208, calculate the spatial distance difference value between the gas accumulation region of the target transformer and the gas accumulation region of each type of transformer and the coincidence degree of the gas species combination, and determine the transformer with a spatial distance difference value less than a first preset threshold and a gas species combination coincidence degree greater than a second preset threshold as a similar transformer.

[0104] Wherein, the spatial distance difference value represents the relative position deviation of the gas accumulation regions of the two transformers in three-dimensional space; the coincidence degree of the gas species combination refers to the similarity of the detected gas species and their proportions in the two transformers; the similar transformer refers to other transformers with high similarity in structural characteristics and fault characteristics to the target transformer.

[0105] When performing similar transformer screening, first, the gas accumulation region coordinates of the target transformer are standardized to a unified spatial reference system. For each transformer in the database, the Euclidean distance between its gas accumulation region and the corresponding region of the target transformer is calculated. The calculation of the spatial distance difference value takes into account the shape and size of the region, using two indicators: the barycentric distance and the contour overlap degree. At the same time, the coincidence degree of the gas species combination is calculated. The specific method is: normalize the content of each gas to construct a feature vector, and calculate the cosine similarity between the vectors. Set the first preset threshold to 20% of the standardized spatial distance, and the second preset threshold to 0.8 of the gas coincidence degree. Screen the transformers that meet the double threshold conditions as the similar transformer set. For the screened similar transformers, establish a one-to-one correspondence relationship of the gas accumulation region, providing a basis for subsequent detailed comparison.

[0106] S209, region matching of the gas accumulation region of the similar transformer, comparing the gas species of each gas accumulation region in the target transformer with the corresponding region of the similar transformer.

[0107] Wherein, region matching means establishing a spatial correspondence between the gas accumulation regions of the target transformer and the similar transformer; the corresponding region refers to the transformer parts that correspond to each other in spatial position and functional characteristics; the gas species comparison refers to analyzing the similarities and differences of gas components at the same position in different transformers.

[0108] Region matching analysis is performed for each similar transformer. The gas accumulation region is divided into several sub-regions, and each sub-region corresponds to a functional unit of the transformer. A region feature descriptor is established, including spatial position, geometric shape, component type, and other information. A feature matching algorithm is used to calculate the matching degree between each sub-region of the target transformer and the similar transformer. The matching degree calculation comprehensively considers spatial position similarity, structural feature similarity, and functional attribute similarity. After determining the region correspondence, the gas species of each region is compared in detail. The differences in gas species are recorded, including component differences, content differences, and time sequence feature differences. For each difference point, the cause is analyzed, and whether the monitoring strategy needs to be adjusted is evaluated. The comparison results are used to optimize the sampling scheme and update the fault feature library.

[0109] S210, if the gas species difference value exceeds the preset difference threshold value, the sampling point density and the sampling frequency of the target region are increased.

[0110] wherein the gas species difference value represents a quantitative difference index of the gas component content in the corresponding regions of the two transformers; the main gas species refers to the gas component whose content ratio exceeds 10% in a specific region; the sampling point density represents the number of gas detection points arranged per unit volume; the sampling frequency refers to the time interval for gas sampling analysis of each detection point; the preset difference threshold value represents the standard value for judging whether the gas species difference is significant, which is usually set to 20%.

[0111] After completing the region matching of the similar transformer, the gas species difference analysis is performed for each target region. First, the gas component information of each region is extracted from the gas chromatogram data, and the content percentage of each gas is calculated. For the gas component whose content exceeds 10%, it is recorded as the main gas species of the region. The difference value of the main gas species of the corresponding region of the target transformer and the similar transformer is calculated, and the specific calculation method is as follows: for each main gas, the relative deviation of the gas content in the two transformers is calculated, and the root mean square value of all main gas relative deviations is taken as the difference value. When the difference value exceeds 20%, the monitoring scheme of the region needs to be adjusted. The specific method of increasing the sampling point density is: based on the original detection points, new detection points are added according to the principle of uniform distribution, so that the detection point spacing is reduced to half of the original. At the same time, the sampling frequency is increased, and the sampling time interval is shortened from the original 6 hours to 2 hours. The newly added detection points are calibrated and the data quality is verified to ensure the accuracy of the monitoring data. The high-density monitoring data is collected for at least 7 days to analyze the causes of the gas species difference. By increasing the monitoring intensity, more detailed gas distribution information is obtained, which provides more reliable data support for fault diagnosis.

[0112] The mixed gas identification system in the embodiment of the present application is described from the perspective of hardware processing. Please refer toFigure 3 Fig. 1 is a schematic diagram of an example of a mixed gas recognition system according to an embodiment of the present application.

[0113] It should be noted that Figure 3 The structure of the mixed gas recognition system shown is merely an example and should not impose any limitation on the functions and the range of use of the embodiments of the present application.

[0114] As Figure 3 shown, the mixed gas recognition system includes a central processing unit (CPU) 301 which can perform various appropriate actions and processes, such as executing the methods described in the above embodiments, in accordance with a program stored in a read-only memory (ROM) 302 or a program loaded from a storage section 308 into a random access memory (RAM) 303. In the RAM 303, various programs and data required for the operation of the system are also stored. The CPU 301, the ROM 302, and the RAM 303 are connected to each other through a bus 304. An input / output (I / O) interface 305 is also connected to the bus 304.

[0115] The following components are connected to the I / O interface 305: an input section 306 including an audio input device, a push button switch, and the like; an output section 307 including a liquid crystal display (LCD) and an audio output device, an indicator lamp, and the like; the storage section 308 including a hard disk and the like; and a communication section 309 including a network interface card such as a LAN (Local Area Network) card, a modem, and the like. The communication section 309 performs communication processing via a network such as the Internet. A drive 310 is also connected to the I / O interface 305 as necessary. A removable media 311 such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, and the like is attached to the drive 310 as necessary, so that a computer program read therefrom is installed in the storage section 308 as necessary.

[0116] In particular, the processes described above with reference to the flowcharts can be implemented as a computer software program according to embodiments of the present application. For example, an embodiment of the present application includes a computer program product comprising a computer program carried on a computer readable medium, the computer program containing a computer program for executing the methods shown in the flowcharts. In such an embodiment, the computer program can be downloaded and installed from a network by the communication section 309 and / or installed from the removable media 311. When the computer program is executed by the central processing unit (CPU) 301, various functions defined in the present application are performed.

[0117] Note that specific examples of computer readable storage media can include but are not limited to an electrical connection having one or more wires, a portable computer diskette, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or Flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the present disclosure, computer readable storage media can be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.

[0118] The flow diagrams and the block diagrams in the drawings are illustrations of architectures, functional processes, and operational processes, according to various embodiments of the present disclosure. Each block in the flow diagrams and the block diagrams can represent a module, a procedure, or a part of code that comprises one or more executable instructions for implementing the specific logical functions specified for the block. It should also be noted that in some alternative implementations, the functions noted in the blocks can occur out of the order noted in the figures.

[0119] Specifically, the mixed gas identification system in the embodiment includes a processor and a memory, and the memory stores a computer program. When the computer program is executed by the processor, the transformer oil mixed gas identification method provided in the above embodiment is implemented.

[0120] As another aspect, the present disclosure also provides a computer readable storage medium. The storage medium can be included in the mixed gas identification system described in the above embodiments, or can exist independently without being assembled into the mixed gas identification system. The storage medium carries one or more computer programs. When the one or more computer programs are executed by a processor of the mixed gas identification system, the mixed gas identification system implements the transformer oil mixed gas identification method provided in the above embodiments.

[0121] The above embodiments are only used to illustrate the technical solutions of the present disclosure, rather than limiting them. Although the present disclosure has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that the technical solutions recorded in the foregoing embodiments can be modified, or some technical features can be replaced by equivalent technical features. Such modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present disclosure.

[0122] In the above embodiments, the term "when" can be interpreted to mean "if" or "after" or "in response to determining" or "in response to detecting" depending on the context. Similarly, the phrase "on determining" or "if detecting (a stated condition or event)" can be interpreted to mean "if determining" or "in response to determining" or "on detecting (a stated condition or event)" or "in response to detecting (a stated condition or event)" depending on the context.

[0123] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be implemented by a computer program instructing the relevant hardware to complete, and the program can be stored in a computer readable storage medium. When the program is executed, the processes of the above-mentioned embodiments can be included. The aforementioned storage medium includes ROM, random access memory (RAM), magnetic disk or optical disk, and various storage media that can store program codes.

Claims

1. A method for identifying a mixed gas in transformer oil, characterized by, The method is applied to a mixed gas identification system, and the method comprises: An internal structure diagram of a transformer is acquired, spatial position relationships of internal components of the transformer are determined, temperature distribution characteristics corresponding to the spatial position relationships are determined, and solubility differences of the transformer at different spatial positions are obtained according to the temperature distribution characteristics; Mixed gas concentration data of multiple detection points are continuously collected during operation of the transformer, initial gas concentration data of the multiple detection points are recorded when the mixed gas concentration data of the multiple detection points deviate from a running threshold range, and gas concentration change data is obtained by correcting the initial gas concentration data according to solubility differences of different temperature zones; Gas concentration spatiotemporal distribution characteristics are calculated based on the gas concentration change data, and a gas accumulation area of gas in the transformer is determined according to the gas concentration spatiotemporal distribution characteristics and the spatial position relationships; Gas component contents are obtained by separating mixed gas components by using a gas chromatography method, preset gas types in the gas accumulation area are compared with the gas component contents, and gas types corresponding to each area in the transformer are determined.

2. The method of claim 1, wherein, The step of calculating gas concentration spatiotemporal distribution characteristics based on the gas concentration change data and determining a gas accumulation area of gas in the transformer according to the gas concentration spatiotemporal distribution characteristics and the spatial position relationships specifically comprises: A gas concentration distribution model containing time and space dimensions is established according to the gas concentration change data, the gas concentration distribution model contains concentration data of the multiple detection points at different times and spatial coordinate information of the detection points; Gas concentration gradients and gas diffusion directions are calculated according to the gas concentration distribution model, and gas concentration spatiotemporal distribution characteristics are obtained according to the gas concentration gradients and the gas diffusion directions; The gas concentration spatiotemporal distribution characteristics are matched with the spatial position relationships of the internal components of the transformer, and an area with the largest gas concentration change is determined as the gas accumulation area.

3. The method of claim 1, wherein, The step of obtaining gas component contents by separating mixed gas components by using a gas chromatography method, comparing preset gas types in the gas accumulation area with the gas component contents, and determining gas types corresponding to each area in the transformer specifically comprises: Mixed gas samples are acquired by using a self-adaptive interval sampling mode according to distribution positions of the gas accumulation area, The mixed gas samples are separated by using a gas chromatography method, response curves and component contents of the gas components are obtained, and a change relationship between the gas component contents and time is established; A transformer component type in which the gas accumulation area is located is extracted from the internal structure diagram of the transformer, a preset gas type data set corresponding to the component type is acquired based on the component type, the preset gas type data set contains typical content proportion relationships of various gas components under different fault types, The change relationship of the gas component contents is compared with the typical content proportion relationships in the preset gas type data set The mode matching is performed, a similarity score is calculated according to a matching result, and a preset gas type with the highest similarity score is selected as a gas type corresponding to each region inside the transformer.

4. The method of claim 1, wherein, Before the step of obtaining a structure diagram of the transformer, determining a spatial position relationship of each component inside the transformer and a temperature distribution feature corresponding to the spatial position relationship, and obtaining a solubility difference of the transformer at different spatial positions according to the temperature distribution feature, the method further comprises: obtaining historical data of mixed gas concentration of a plurality of detection points in an oil tank of the transformer, and calculating a time difference of maximum gas concentration detected by each detection point; An operation threshold range during normal operation is obtained according to a ratio of the maximum concentration values of each detection point.

5. The method of claim 1, wherein, After the step of separating mixed gas components by using a gas chromatography method to obtain component contents, comparing the preset gas types in the gas accumulation region with the component contents to determine the gas type corresponding to each region inside the transformer, the method further comprises: A gas diffusion path diagram is established according to the gas type corresponding to each region inside the transformer, the gas diffusion path diagram includes a diffusion path and a diffusion time of gas from a generation position to a detection point; Based on the gas diffusion path diagram, the diffusion rate of gas on different diffusion paths is calculated in combination with the gas concentration spatiotemporal distribution feature and the temperature distribution feature; When new gas concentration change data is detected, the gas generation position is reversely located according to the diffusion rate, and a gas source position is determined; The transformer is located according to the gas source position, and a transformer fault position is obtained.

6. The method of claim 5, wherein, After the step of separating mixed gas components by using a gas chromatography method to obtain component contents, comparing the preset gas types in the gas accumulation region with the component contents to determine the gas type corresponding to each region inside the transformer, the method further comprises: A fault feature library is established according to the gas source position and the gas type, the fault feature library includes gas combination features and gas generation rules under different fault types; A fault prediction model is constructed based on the fault feature library, the fault prediction model takes the gas combination features and the gas generation rules as input parameters; The fault prediction model is used to evaluate the operation state of the transformer, predict potential fault risks, and generate fault warning information according to the prediction result.

7. The method of claim 1, wherein, After the step of separating mixed gas components by using a gas chromatography method to obtain component contents, comparing the preset gas types in the gas accumulation region with the component contents to determine the gas type corresponding to each region inside the transformer, the method further comprises: The spatial distance difference value and the coincidence degree of gas type combination between the gas accumulation region of the target transformer and the gas accumulation regions of each type of transformer are calculated, and the transformer with the spatial distance difference value less than a first preset threshold value and the gas type combination coincidence degree greater than a second preset threshold value is determined as a similar transformer. The gas accumulation areas of the similar transformer are regionally matched, and the gas types of each of the gas accumulation areas in the target transformer and the corresponding areas of the similar transformer are compared; If the difference between the gas type and the main gas type of the corresponding target area of the similar transformer exceeds a preset difference threshold, the sampling point density and sampling frequency of the target area are increased.

8. A mixed gas identification system characterized by, The mixed gas identification system comprises one or more processors and a memory; the memory is coupled with the one or more processors, and the memory is used to store computer program codes, the computer program codes comprise computer instructions, and the one or more processors invoke the computer instructions to enable the mixed gas identification system to perform the method in any one of claims 1-7.

9. A computer-readable storage medium comprising instructions, characterized in that, When the instructions run on the mixed gas identification system, the mixed gas identification system is enabled to perform the method in any one of claims 1-7.

10. A computer program product, characterised in that, When the computer program product runs on the mixed gas identification system, the mixed gas identification system is enabled to perform the method in any one of claims 1-7.

Images