Transformer oil detection method and device, computer equipment, storage medium and computer program product

Abstract

The invention relates to a transformer oil detection method and device, computer equipment, a storage medium and a computer program product. The method comprises the following steps: separating to-be-detected transformer oil to obtain to-be-detected gas corresponding to the transformer oil; the transformer oil is acquired through a plurality of oil extraction ports of a to-be-detected transformer; acquiring a photoacoustic signal corresponding to the gas to be detected; determining a current acetylene content value corresponding to the to-be-detected gas according to the photoacoustic signal; extracting a feature vector of the current acetylene content value; respectively inputting the feature vectors into a plurality of trained transformer oil detection models to obtain target prediction probabilities of the transformer oil under various preset detection results; and screening out the preset detection result with the maximum target prediction probability from the various preset detection results, and taking the preset detection result as a target detection result corresponding to the transformer oil. By adopting the method, the detection accuracy of the transformer oil can be improved.

Description

Technical Field

[0001] The present application relates to the field of power grid technology, and in particular to a transformer oil detection method, device, computer equipment, computer-readable storage medium, and computer program product. Background Art

[0002] In the power system, testing the transformer oil in the transformer is crucial to ensure the safe operation of the transformer.

[0003] In traditional technology, manual detection is generally used in the process of testing transformer oil; however, this manual detection method has subjective factors and is prone to errors, resulting in low accuracy in transformer oil detection. Summary of the invention

[0004] Based on this, it is necessary to provide a transformer oil detection method, device, computer equipment, computer readable storage medium and computer program product that can improve the detection accuracy of transformer oil in response to the above technical problems.

[0005] In a first aspect, the present application provides a transformer oil detection method, comprising:

[0006] The transformer oil to be tested is separated and processed to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be tested;

[0007] Acquiring a photoacoustic signal corresponding to the gas to be detected;

[0008] Determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal;

[0009] Extracting a feature vector of the current acetylene content value;

[0010] Inputting the feature vectors into a plurality of trained transformer oil detection models respectively to obtain target prediction probabilities of the transformer oil under various preset detection results;

[0011] From the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil.

[0012] In one embodiment, before the transformer oil to be detected is separated to obtain the gas to be detected corresponding to the transformer oil, the method further includes:

[0013] Acquire structural information and oil flow path information of the transformer to be tested;

[0014] Extracting key structural information from the structural information, and extracting key oil flow path information from the oil flow path information;

[0015] According to the key structural information and the key oil flow path information, a plurality of oil extraction ports of the transformer to be inspected are determined.

[0016] In one embodiment, extracting the feature vector of the current acetylene content value includes:

[0017] Obtain the target data type corresponding to the current acetylene content value;

[0018] According to the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the current acetylene content value;

[0019] The historical acetylene content value corresponding to the gas to be detected is obtained, and the current acetylene content value is used as the main data, and the historical acetylene content value is used as the auxiliary data, which are input into the target feature extraction model to obtain the feature vector.

[0020] In one embodiment, the feature vectors are respectively input into a plurality of trained transformer oil detection models to obtain target prediction probabilities of the transformer oil under various preset detection results, including:

[0021] Inputting the feature vectors into the multiple trained transformer oil detection models respectively, and obtaining the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model;

[0022] Performing verification processing on the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model to obtain a verification result;

[0023] In the case where the verification result meets the preset verification result, the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model is weighted summed to obtain the target predicted probability.

[0024] In one embodiment, after selecting the preset detection result with the largest target prediction probability from the various preset detection results as the target detection result corresponding to the transformer oil, the method further includes:

[0025] When the target detection result indicates that the transformer oil is abnormal, obtaining identification information corresponding to the transformer to be detected;

[0026] Generate warning information corresponding to the transformer to be detected according to the target detection result and the identification information;

[0027] The warning information is sent to a target terminal associated with the transformer to be detected.

[0028] In one embodiment, each trained transformer oil detection model is trained in the following manner:

[0029] The sample transformer oil is separated and processed to obtain a sample gas corresponding to the sample transformer oil; the sample transformer oil is obtained by collecting from multiple oil extraction ports of the sample transformer;

[0030] Acquiring a sample photoacoustic signal corresponding to the sample gas;

[0031] Determining a current sample acetylene content value corresponding to the sample gas according to the sample photoacoustic signal;

[0032] Extracting a sample feature vector of the acetylene content value of the current sample;

[0033] Inputting the sample feature vectors into each transformer oil detection model to be trained respectively, and obtaining the predicted detection results corresponding to the sample transformer oil output by each transformer oil detection model to be trained;

[0034] The actual detection result corresponding to the sample transformer oil is obtained, and according to the difference between the predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained and the actual detection result, each transformer oil detection model to be trained is iteratively trained to obtain each trained transformer oil detection model.

[0035] In a second aspect, the present application also provides a transformer oil detection device, comprising:

[0036] A gas acquisition module is used to separate and process the transformer oil to be detected to obtain the gas to be detected corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be detected;

[0037] A signal acquisition module, used to acquire the photoacoustic signal corresponding to the gas to be detected;

[0038] A content determination module, used to determine the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal;

[0039] A feature extraction module, used to extract a feature vector of the current acetylene content value;

[0040] A probability determination module, used to input the feature vectors into a plurality of trained transformer oil detection models respectively, to obtain a target prediction probability of the transformer oil under various preset detection results;

[0041] The result determination module is used to select the preset detection result with the largest target prediction probability from the various preset detection results as the target detection result corresponding to the transformer oil.

[0042] In a third aspect, the present application further provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the following steps are implemented:

[0043] The transformer oil to be tested is separated and processed to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be tested;

[0044] Acquiring a photoacoustic signal corresponding to the gas to be detected;

[0045] Determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal;

[0046] Extracting a feature vector of the current acetylene content value;

[0047] Inputting the feature vectors into a plurality of trained transformer oil detection models respectively to obtain target prediction probabilities of the transformer oil under various preset detection results;

[0048] From the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil.

[0049] In a fourth aspect, the present application further provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the following steps are implemented:

[0050] The transformer oil to be tested is separated and processed to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be tested;

[0051] Acquiring a photoacoustic signal corresponding to the gas to be detected;

[0052] Determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal;

[0053] Extracting a feature vector of the current acetylene content value;

[0054] Inputting the feature vectors into a plurality of trained transformer oil detection models respectively to obtain target prediction probabilities of the transformer oil under various preset detection results;

[0055] From the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil.

[0056] In a fifth aspect, the present application further provides a computer program product, including a computer program, which implements the following steps when executed by a processor:

[0057] The transformer oil to be tested is separated and processed to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be tested;

[0058] Acquiring a photoacoustic signal corresponding to the gas to be detected;

[0059] Determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal;

[0060] Extracting a feature vector of the current acetylene content value;

[0061] Inputting the feature vectors into a plurality of trained transformer oil detection models respectively to obtain target prediction probabilities of the transformer oil under various preset detection results;

[0062] From the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil.

[0063] The above-mentioned transformer oil detection method, device, computer equipment, storage medium and computer program product first collect data from multiple oil extraction ports of the transformer to be detected to obtain the transformer oil to be detected, and separate the transformer oil to be detected to obtain the gas to be detected corresponding to the transformer oil, and then obtain the photoacoustic signal corresponding to the gas to be detected. Then, based on the photoacoustic signal, the current acetylene content value corresponding to the gas to be detected is determined, and the characteristic vector of the current acetylene content value is extracted. Then, the characteristic vectors are respectively input into multiple trained transformer oil detection models to obtain the target prediction probability of the transformer oil under various preset detection results. Finally, from the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil. In this way, in the process of testing transformer oil, by collecting data from multiple oil extraction ports of the transformer to be tested, a more comprehensive and representative transformer oil can be obtained, so that the subsequently obtained gas to be tested can more accurately reflect the current acetylene content value, and then through a series of processing such as feature extraction and probability screening, the target detection result corresponding to the transformer oil can be obtained more accurately, which is conducive to improving the determination accuracy of the target detection result corresponding to the transformer oil, thereby improving the detection accuracy of the transformer oil; moreover, the entire process does not require human intervention, avoiding the subjective factors in manual detection, which is prone to errors and leads to the defect of low detection accuracy of the transformer oil, and further improves the detection accuracy of the transformer oil. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] In order to more clearly illustrate the technical solutions in the embodiments of the present application or related technologies, the drawings required for use in the embodiments of the present application or related technical descriptions will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without paying creative work.

[0065] Figure 1 A schematic diagram of a flow chart of a transformer oil detection method in one embodiment;

[0066] Figure 2 A schematic flow chart of a transformer oil detection method in another embodiment;

[0067] Figure 3 A schematic diagram of a process for a transformer multi-channel oil acetylene parallel measurement photoacoustic spectroscopy detection method according to an embodiment;

[0068] Figure 4 A structural block diagram of a transformer oil detection device in one embodiment;

[0069] Figure 5FIG. 4 is a diagram showing the internal structure of a computer device in one embodiment. DETAILED DESCRIPTION

[0070] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0071] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data used for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of relevant data must comply with relevant regulations.

[0072] In an exemplary embodiment, Figure 1 As shown, a transformer oil detection method is provided. This embodiment uses the method applied to a server as an example for illustration. It can be understood that the method can also be applied to a terminal, and can also be applied to a system including a terminal and a server, and is implemented through the interaction between the terminal and the server. The terminal can be, but is not limited to, various personal computers, laptops, smart phones, and tablet computers; the server can be implemented as an independent server or a server cluster composed of multiple servers. In this embodiment, the method includes the following steps:

[0073] Step S101, separating and processing the transformer oil to be tested to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting from multiple oil extraction ports of the transformer to be tested.

[0074] Among them, transformer oil refers to the oil sample in the transformer.

[0075] The gas to be detected refers to the gas obtained by separating the transformer oil to be detected.

[0076] The transformer to be tested refers to a transformer that needs to be tested.

[0077] The oil extraction port refers to the position in the transformer to be tested for collecting transformer oil.

[0078] Exemplarily, the server determines multiple oil extraction ports of the transformer to be tested; then, the server collects data from the multiple oil extraction ports of the transformer to be tested to obtain the transformer oil to be tested; then, the server separates the gas and liquid in the transformer oil to be tested to obtain the gas to be tested corresponding to the transformer oil.

[0079] Step S102, obtaining a photoacoustic signal corresponding to the gas to be detected.

[0080] The photoacoustic signal refers to the signal generated by the gas to be detected based on the photoacoustic effect.

[0081] Exemplarily, the server introduces the gas to be detected into the photoacoustic cell, and determines the light source corresponding to the gas to be detected based on the absorption spectrum characteristics of the gas to be detected; then, the server irradiates the light source onto the gas to be detected in the photoacoustic cell according to a preset light path, and obtains a photoacoustic signal corresponding to the gas to be detected.

[0082] Step S103, determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal.

[0083] The current acetylene content value refers to the acetylene content value of the gas to be detected within the current time.

[0084] Exemplarily, the server queries the corresponding relationship between the photoacoustic signal and the acetylene content value based on the photoacoustic signal, and obtains the current acetylene content value corresponding to the gas to be detected.

[0085] Step S104, extracting the feature vector of the current acetylene content value.

[0086] The feature vector is used to represent the characterization vector of the current acetylene content value.

[0087] Exemplarily, the server inputs the current acetylene content value into the feature extraction model, and performs feature extraction processing on the current acetylene content value through the feature extraction model to obtain a feature vector of the current acetylene content value.

[0088] Step S105 , respectively inputting the feature vectors into a plurality of trained transformer oil detection models to obtain target prediction probabilities of transformer oil under various preset detection results.

[0089] The transformer oil detection model refers to a network model that can use the characteristic vector of the current acetylene content value corresponding to the gas to be detected to obtain the target detection result corresponding to the transformer oil.

[0090] It should be noted that the structures corresponding to multiple trained transformer oil detection models are different, such as RNN (Recurrent Neural Network) structure, CNN (Convolutional Neural Network) structure, etc.

[0091] The preset test result refers to a preset test result, including the transformer oil having an abnormality and the transformer oil not having an abnormality. It should be noted that the preset test result depends on the situation.

[0092] Among them, the target prediction probability is used to indicate the comprehensive possibility of determining that the preset detection result is correct.

[0093] Exemplarily, the server inputs the feature vectors into multiple trained transformer oil detection models respectively, and obtains the predicted probability of transformer oil under various preset detection results output by each trained transformer oil detection model; then, the server performs weighted summation processing on the predicted probability of transformer oil under various preset detection results output by each trained transformer oil detection model, and obtains the target predicted probability of transformer oil under various preset detection results.

[0094] Step S106, screening out the preset detection result with the largest target prediction probability from various preset detection results as the target detection result corresponding to the transformer oil.

[0095] Among them, the target detection result refers to the preset detection result with the highest target prediction probability.

[0096] Exemplarily, the server selects a preset detection result with the highest target prediction probability from various preset detection results, and uses the preset detection result as the target detection result corresponding to the transformer oil.

[0097] In the above transformer oil detection method, the transformer oil to be detected is firstly collected through multiple oil extraction ports of the transformer to be detected, and the transformer oil to be detected is separated and processed to obtain the gas to be detected corresponding to the transformer oil, and then the photoacoustic signal corresponding to the gas to be detected is obtained. Then, according to the photoacoustic signal, the current acetylene content value corresponding to the gas to be detected is determined, and the characteristic vector of the current acetylene content value is extracted. Then, the characteristic vectors are respectively input into multiple trained transformer oil detection models to obtain the target prediction probability of the transformer oil under various preset detection results. Finally, from the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil. In this way, in the process of testing transformer oil, by collecting data from multiple oil extraction ports of the transformer to be tested, a more comprehensive and representative transformer oil can be obtained, so that the subsequently obtained gas to be tested can more accurately reflect the current acetylene content value, and then through a series of processing such as feature extraction and probability screening, the target detection result corresponding to the transformer oil can be obtained more accurately, which is conducive to improving the determination accuracy of the target detection result corresponding to the transformer oil, thereby improving the detection accuracy of the transformer oil; moreover, the entire process does not require human intervention, avoiding the subjective factors in manual detection, which is prone to errors and leads to the defect of low detection accuracy of the transformer oil, and further improves the detection accuracy of the transformer oil.

[0098] In an exemplary embodiment, the above step S101, before separating the transformer oil to be tested and obtaining the gas to be tested corresponding to the transformer oil, specifically includes the following contents: acquiring structural information and oil flow path information of the transformer to be tested; extracting key structural information from the structural information, and extracting key oil flow path information from the oil flow path information; and determining multiple oil extraction ports of the transformer to be tested based on the key structural information and the key oil flow path information.

[0099] The structural information is used to represent information related to the structure of the transformer to be detected.

[0100] The oil flow path information is used to represent the path information of the transformer oil in the transformer to be tested.

[0101] Among them, the key structural information is used to represent structural information whose importance is greater than a preset importance, such as the core and winding of the transformer to be tested.

[0102] Among them, the key oil flow path information is used to represent the oil flow path information whose importance is greater than the preset importance, such as the path information of the transformer oil in the main channel of the transformer to be detected.

[0103] Exemplarily, the server obtains the operating time and load information of multiple candidate transformers; then, the server selects the candidate transformers whose operating time is greater than the preset operating time and whose load information is greater than the preset load information from the multiple candidate transformers as the transformer to be detected; then, the server obtains the identification information of the transformer to be detected, and obtains the structural information and oil flow path information corresponding to the identification information as the structural information and oil flow path information of the transformer to be detected; then, the server inputs the structural information and the oil flow path information into the importance prediction model, and obtains the importance of each structural information and the importance of each oil flow path information according to the importance prediction model; then, the server selects the structural information whose importance is greater than the preset importance from each structural information as the key structural information, and selects the oil flow path information whose importance is greater than the preset importance from each oil flow path information as the key oil flow path information; then, the server determines multiple oil intake ports of the transformer to be detected based on the key structural information and the key oil flow path information.

[0104] In this embodiment, by first obtaining the overall structural information and oil flow path information of the transformer to be tested, and then screening out the key structural information and key oil flow path information, multiple oil extraction ports can be accurately determined, avoiding the problem of blind sampling resulting in the sample being unable to fully reflect the true situation of the transformer.

[0105] In an exemplary embodiment, the above step S104, extracting the feature vector of the current acetylene content value, specifically includes the following contents: obtaining the target data type corresponding to the current acetylene content value; according to the target data type, querying the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the current acetylene content value; obtaining the historical acetylene content value corresponding to the gas to be detected, and using the current acetylene content value as the main data and the historical acetylene content value as the auxiliary data, inputting them into the target feature extraction model to obtain the feature vector.

[0106] The target data type refers to the data type corresponding to the current acetylene content value, such as numerical data and interval data.

[0107] The corresponding relationship between the data type and the feature extraction model is used to represent the association information between the data type and the feature extraction model. For example, the numerical data corresponds to the linear regression model, and the interval data corresponds to the decision tree model.

[0108] The target feature extraction model refers to the feature extraction model corresponding to the current acetylene content value.

[0109] The historical acetylene content value refers to the acetylene content value of the gas to be detected within a historical period (such as the past week, the past month, etc.).

[0110] Among them, the main data may refer to data with a larger corresponding weight.

[0111] Among them, auxiliary data may refer to data with a smaller corresponding weight.

[0112] Exemplarily, the server identifies the data type corresponding to the current acetylene content value according to preset rules as the target data type; then, the server queries the correspondence between the data type and the feature extraction model according to the target data type, and obtains the feature extraction model corresponding to the current acetylene content value as the target feature extraction model; then, the server obtains the historical acetylene content value corresponding to the gas to be detected from the database; then, the server uses the current acetylene content value as the main data and the historical acetylene content value as the auxiliary data, and inputs them into the target feature extraction model, and obtains the feature vector through the target feature extraction model.

[0113] In this embodiment, by first determining the target data type corresponding to the current acetylene content value, and then selecting the target feature extraction model based on the correspondence between the data type and the feature extraction model, it is possible to ensure that the selected model is highly compatible with the data type; moreover, the current acetylene content value is used as the main data, and the historical acetylene content value is combined as auxiliary data to input into the target feature extraction model, thereby achieving effective integration of data from different time stages, which is beneficial to improving the accuracy of determining the feature vector.

[0114] In an exemplary embodiment, the above step S105, respectively inputting the feature vector into multiple trained transformer oil detection models to obtain the target prediction probability of transformer oil under various preset detection results, specifically includes the following contents: respectively inputting the feature vector into multiple trained transformer oil detection models to obtain the prediction probability of transformer oil under various preset detection results output by each trained transformer oil detection model; verifying the prediction probability of transformer oil under various preset detection results output by each trained transformer oil detection model to obtain a verification result; when the verification result meets the preset verification result, performing weighted summation processing on the prediction probability of transformer oil under various preset detection results output by each trained transformer oil detection model to obtain the target prediction probability.

[0115] The prediction probability is used to indicate the possibility that each trained transformer oil detection model determines that the preset detection result is correct.

[0116] The verification result is used to indicate whether the difference between the predicted probabilities of transformer oil output by each trained transformer oil detection model under various preset detection results is greater than the preset difference.

[0117] Among them, the preset verification result is used to indicate that the difference between the predicted probabilities of transformer oil output by each trained transformer oil detection model under various preset detection results is not greater than the preset difference, such as when the predicted probabilities of transformer oil output under various preset detection results differ by less than or equal to 0.8, such as (0.7, 0.3), (0.2, 0.8) respectively. It should be noted that when the predicted probabilities of transformer oil output under various preset detection results are (0.01, 0.99), (0.95, 0.05), that is, when the difference between the values ​​of the predicted probabilities is greater than 0.8, it means that the predicted probabilities of transformer oil output by the trained transformer oil detection model under various preset detection results differ by more than the preset difference.

[0118] Exemplarily, the server inputs the feature vectors into multiple trained transformer oil detection models respectively, and obtains the predicted probability of transformer oil output by each trained transformer oil detection model under various preset detection results; then, the server performs difference processing on the predicted probability of transformer oil output by each trained transformer oil detection model under various preset detection results, and obtains the predicted probability difference corresponding to each trained transformer oil detection model; then, the server verifies these predicted probability differences to obtain verification results; then, when the verification results meet the preset verification results, the server performs weighted sum processing on the predicted probability of transformer oil output by each trained transformer oil detection model under various preset detection results to obtain the target prediction probability.

[0119] In this embodiment, by verifying the predicted probabilities output by each model, unreasonable results that may be caused by model abnormalities and other reasons can be screened out, thereby ensuring that relatively reliable data are used in subsequent calculations, further optimizing the prediction results, and enabling the obtained target prediction probability to more accurately reflect the actual state of the transformer oil.

[0120] In an exemplary embodiment, the above step S106, after screening out the preset detection result with the largest target prediction probability from various preset detection results as the target detection result corresponding to the transformer oil, specifically includes the following contents: when the target detection result indicates that there is an abnormality in the transformer oil, obtaining identification information corresponding to the transformer to be detected; generating early warning information corresponding to the transformer to be detected based on the target detection result and the identification information; and sending the early warning information to the target terminal associated with the transformer to be detected.

[0121] The identification information refers to information used to uniquely distinguish a transformer, such as a transformer number.

[0122] Among them, the early warning information is used to indicate the alarm information of abnormality of the transformer to be detected.

[0123] The target terminal refers to the terminal associated with the transformer to be detected.

[0124] Exemplarily, when the target detection result indicates that there is an abnormality in the transformer oil, the server obtains the identification information corresponding to the transformer to be detected from the database; then, the server obtains the preset warning information template, and combines the preset warning information template, the target detection result and the identification information to obtain the warning information corresponding to the transformer to be detected; then, the server determines the terminal associated with the transformer to be detected as the target terminal; finally, the server sends the warning information to the target terminal.

[0125] In this embodiment, early warning information is generated based on the target detection results and identification information, so that the abnormal situation of the transformer can be conveyed to the personnel who need to know it in the first time, so that the relevant personnel can prepare corresponding measures in advance, etc., and thus can more efficiently deal with possible transformer failures, which is conducive to improving the timeliness of transformer fault handling.

[0126] In an exemplary embodiment, the transformer oil detection method provided by the present application also includes a training step for each trained transformer oil detection model, specifically including the following contents: separating and processing the sample transformer oil to obtain a sample gas corresponding to the sample transformer oil; the sample transformer oil is obtained by collecting multiple oil extraction ports of the sample transformer; obtaining a sample photoacoustic signal corresponding to the sample gas; determining the current sample acetylene content value corresponding to the sample gas according to the sample photoacoustic signal; extracting a sample feature vector of the current sample acetylene content value; inputting the sample feature vector into each transformer oil detection model to be trained respectively to obtain a predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained; obtaining the actual detection result corresponding to the sample transformer oil, and iteratively training each transformer oil detection model to be trained according to the difference between the predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained and the actual detection result, to obtain each trained transformer oil detection model.

[0127] The sample transformer oil refers to the transformer oil used to train each transformer oil detection model to be trained.

[0128] The sample gas refers to the gas obtained by separating the sample transformer oil.

[0129] The sample transformer refers to the transformer in which the sample transformer oil is located.

[0130] The sample photoacoustic signal refers to the signal generated by the sample gas based on the photoacoustic effect.

[0131] The current sample acetylene content value refers to the acetylene content value of the sample gas at the current time.

[0132] The sample feature vector refers to the feature vector of the current sample acetylene content value.

[0133] Among them, each transformer oil detection model to be trained has a different corresponding structure, such as RNN structure, CNN structure, etc.

[0134] The predicted detection result refers to the predicted value of the detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained.

[0135] The actual test result refers to the actual value of the test result corresponding to the sample transformer oil.

[0136] Exemplarily, in response to a model training instruction for each transformer oil detection model to be trained, the server collects samples from multiple oil extraction ports of a sample transformer to obtain sample transformer oil; then, the server separates and processes the sample transformer oil to obtain sample gas corresponding to the sample transformer oil; then, the server obtains a sample photoacoustic signal corresponding to the sample gas; then, the server determines the current sample acetylene content value corresponding to the sample gas based on the sample photoacoustic signal; then, the server extracts a sample feature vector of the current sample acetylene content value; then, the server inputs the sample feature vector into each transformer oil detection model to be trained, and obtains a sample output of each transformer oil detection model to be trained. The server obtains the predicted test result corresponding to the sample transformer oil; then, the server obtains the actual test result corresponding to the sample transformer oil, and obtains the loss value according to the difference between the predicted test result corresponding to the sample transformer oil output by each transformer oil detection model to be trained and the actual test result; then, the server adjusts the model parameters of each transformer oil detection model to be trained according to the loss value; then, the server re-trains each transformer oil detection model after the model parameters are adjusted until the loss value obtained by each trained transformer oil detection model is less than the loss value threshold, then stops training, and uses each trained transformer oil detection model as each trained transformer oil detection model.

[0137] In this embodiment, by pre-training the transformer oil detection model, it is convenient in practical applications to predict the target detection result corresponding to the transformer oil after obtaining the current acetylene content value of the gas to be detected corresponding to the transformer oil; moreover, the transformer oil detection model receives new data in each round of iteration, and performs internal model improvement and optimization, so as to be able to make predictions more effectively, which is beneficial to improving the prediction accuracy of the transformer oil detection model.

[0138] In an exemplary embodiment, Figure 2 As shown, another transformer oil detection method is provided, which is described by taking the application of the method to a server as an example, and includes the following steps:

[0139] Step S201, obtaining structural information and oil flow path information of the transformer to be tested; extracting key structural information from the structural information, and extracting key oil flow path information from the oil flow path information; and determining multiple oil intake ports of the transformer to be tested based on the key structural information and the key oil flow path information.

[0140] Step S202, separating and processing the transformer oil to be tested to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting from multiple oil extraction ports of the transformer to be tested.

[0141] Step S203, obtaining the photoacoustic signal corresponding to the gas to be detected.

[0142] Step S204, determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal.

[0143] Step S205, obtaining the target data type corresponding to the current acetylene content value; according to the target data type, querying the correspondence between the data type and the feature extraction model, and obtaining the target feature extraction model corresponding to the current acetylene content value.

[0144] Step S206, obtaining the historical acetylene content value corresponding to the gas to be detected, and taking the current acetylene content value as the main data and the historical acetylene content value as the auxiliary data, inputting them into the target feature extraction model to obtain the feature vector.

[0145] Step S207, respectively inputting the feature vectors into a plurality of trained transformer oil detection models to obtain the predicted probability of the transformer oil under various preset detection results output by each trained transformer oil detection model.

[0146] Step S208, verifying the predicted probability of transformer oil under various preset detection results output by each trained transformer oil detection model to obtain a verification result.

[0147] Step S209, when the verification result meets the preset verification result, the predicted probability of transformer oil under various preset detection results output by each trained transformer oil detection model is weighted and summed to obtain the target predicted probability.

[0148] Step S210, screening out the preset detection result with the largest target prediction probability from various preset detection results as the target detection result corresponding to the transformer oil.

[0149] In the above transformer oil detection method, in the process of detecting the transformer oil, by collecting data from multiple oil extraction ports of the transformer to be detected, a more comprehensive and representative transformer oil can be obtained, so that the gas to be detected obtained subsequently can more accurately reflect the current acetylene content value, and then through a series of processing such as feature extraction and probability screening, the target detection result corresponding to the transformer oil can be obtained more accurately, which is conducive to improving the determination accuracy of the target detection result corresponding to the transformer oil, thereby improving the detection accuracy of the transformer oil; moreover, the entire process does not require human intervention, avoiding the subjective factors in the manual detection method, which is prone to errors and leads to the defect of low detection accuracy of the transformer oil, and further improving the detection accuracy of the transformer oil.

[0150] In an exemplary embodiment, in order to more clearly illustrate the transformer oil detection method provided in the embodiment of the present application, the transformer oil detection method is specifically described below with a specific embodiment. In one embodiment, Figure 3 As shown, the present application also provides a transformer multi-channel oil acetylene parallel measurement photoacoustic spectroscopy detection method. In the process of detecting transformer oil, the transformer oil to be detected is first collected through multiple oil extraction ports of the transformer to be detected, and the transformer oil to be detected is separated and processed to obtain the gas to be detected corresponding to the transformer oil, and then the photoacoustic signal corresponding to the gas to be detected is obtained. Then, according to the photoacoustic signal, the current acetylene content value corresponding to the gas to be detected is determined, and the characteristic vector of the current acetylene content value is extracted. Then, the characteristic vectors are respectively input into multiple trained transformer oil detection models to obtain the target prediction probability of transformer oil under various preset detection results. Finally, from various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil. Specifically including the following contents:

[0151] The multi-channel parallel measurement architecture involved in this embodiment includes a multi-channel sampling system, an oil-gas separation unit, a photoacoustic spectroscopy detection unit, a field control and data acquisition processing unit, and a station control server.

[0152] 1. Multi-channel sampling system: The multi-channel sampling system is the core component of this embodiment, which collects oil samples from multiple oil extraction ports of the transformer at the same time. This design significantly improves the efficiency and coverage of detection. Compared with traditional single-channel sampling, multi-channel sampling can more comprehensively reflect the distribution of dissolved gases in transformer oil.

[0153] The device includes at least three independent oil extraction ports, each of which is connected to an oil sampling unit for collecting oil samples from different locations of the transformer. This allows the device to obtain a large amount of detection data in a short period of time, greatly improving the quality of the dissolved gas volume fraction-time series, and can use the degassing theoretical model to accurately and quickly predict the dissolved gas equilibrium volume fraction. In addition, the multi-channel sampling system can also simulate the process of local gas generation and slow dissolution and diffusion in real large transformers, thereby improving the applicability and accuracy of monitoring.

[0154] Each oil sampling port is designed to be able to operate independently to ensure that the oil samples collected from different locations are representative. The location of the oil sampling port should be carefully selected according to the structure of the transformer and the oil flow path to maximize the accuracy of the detection. The oil sampling collection unit connected to each oil sampling port should have the ability to accurately control the sampling volume and sampling speed. These units should also be equipped with anti-pollution measures to ensure that the oil samples are not contaminated by the outside world during the collection process. In order to ensure the comparability of the data, all sampling units should be able to operate synchronously. This may require a central control system to coordinate the actions of the various sampling units.

[0155] 2. Oil-gas separation unit: Each oil sample collection unit is connected to an oil-gas separation unit, which is used to separate the gas and liquid in the collected oil sample for subsequent spectral detection. The design of the oil-gas separation unit ensures the purity of the gas, thereby improving the accuracy of the detection.

[0156] The oil-gas separation unit is designed to efficiently separate gas and liquid while minimizing gas loss.

[0157] 3. Photoacoustic spectroscopy detection unit: Each oil and gas separation unit is connected to a photoacoustic spectroscopy detection unit, which uses laser photoacoustic spectroscopy technology to detect the acetylene content of the separated gas. It has the advantages of strong target selectivity, short reaction time, and no damage to the sample, and is suitable for online monitoring. In order to distinguish the photoacoustic signals of different gases, the detection unit should have high spectral resolution, use high-quality spectrometers and advanced signal processing technology. Equipped with powerful data processing capabilities, it can analyze the detection data in real time and identify the presence and concentration of acetylene.

[0158] 4. On-site control and data acquisition processing unit: Each photoacoustic spectroscopy detection unit is connected to a on-site control and data acquisition processing unit to control the detection process, collect detection data, and perform preliminary processing. The design of these units ensures real-time processing and analysis of data, providing support for subsequent decision-making.

[0159] The field control unit is equipped with an intuitive user interface, which is convenient for operators to monitor and control the detection process. The data acquisition and processing unit can collect data from each photoacoustic spectroscopy detection unit in real time, and perform preliminary data processing and storage. The field control and data acquisition and processing unit has a high-speed and stable communication interface to transmit data to the station control server.

[0160] 5. Station control server: All data from the field control and data acquisition processing units are transmitted to the station control server via optical cables. The station control server is responsible for the final processing, storage and remote monitoring of the data. The design of the station control server makes remote monitoring and data analysis possible, improving the flexibility and response speed of monitoring.

[0161] The station control server has enough storage space to save historical data for trend analysis and fault diagnosis, and can handle large amounts of data from multiple field control and data acquisition processing units. The station control server supports remote access to achieve remote monitoring.

[0162] like Figure 3 As shown, the device includes three independent oil extraction ports (1), each of which is connected to an oil sample collection unit (2), the oil sample collection unit is connected to an oil-gas separation unit (3), and the oil-gas separation unit is connected to a photoacoustic spectroscopy detection unit (4). Each photoacoustic spectroscopy detection unit is connected to a field control and data acquisition processing unit (5), and all field control and data acquisition processing units are connected to a station control server (7). The station control server (7) is responsible for receiving data from each field control and data acquisition processing unit (5), performing centralized processing and analysis, and feeding back the results to the operation and maintenance personnel so that maintenance measures can be taken in a timely manner. This multi-channel parallel measurement architecture enables the device to achieve rapid, accurate, and real-time monitoring of the acetylene content in the transformer oil, effectively improving the operating safety and maintenance efficiency of the transformer. Not only does it improve the efficiency of monitoring, it also helps to promptly discover potential faults of the transformer, thereby taking preventive measures to avoid possible accidents and losses.

[0163] In the above embodiment, during the detection of transformer oil, more comprehensive and representative transformer oil can be obtained by collecting data from multiple oil extraction ports of the transformer to be detected, so that the gas to be detected obtained subsequently can more accurately reflect the current acetylene content value, and then through a series of processing such as feature extraction and probability screening, the target detection result corresponding to the transformer oil can be obtained more accurately, which is conducive to improving the determination accuracy of the target detection result corresponding to the transformer oil, thereby improving the detection accuracy of the transformer oil; moreover, the whole process does not require manual intervention, avoiding the defect of low detection accuracy of the transformer oil caused by subjective factors in the manual detection method, which is prone to errors, and further improves the detection accuracy of the transformer oil.

[0164] It should be understood that, although the various steps in the flowcharts involved in the above-mentioned embodiments are displayed in sequence according to the indication of the arrows, these steps are not necessarily executed in sequence according to the order indicated by the arrows. Unless there is a clear explanation in this article, the execution of these steps does not have a strict order restriction, and these steps can be executed in other orders. Moreover, at least a part of the steps in the flowcharts involved in the above-mentioned embodiments can include multiple steps or multiple stages, and these steps or stages are not necessarily executed at the same time, but can be executed at different times, and the execution order of these steps or stages is not necessarily to be carried out in sequence, but can be executed in turn or alternately with other steps or at least a part of the steps or stages in other steps.

[0165] Based on the same inventive concept, the embodiment of the present application also provides a transformer oil detection device for implementing the transformer oil detection method involved above. The implementation scheme for solving the problem provided by the device is similar to the implementation scheme recorded in the above method, so the specific limitations in one or more transformer oil detection device embodiments provided below can refer to the limitations of the transformer oil detection method above, and will not be repeated here.

[0166] In an exemplary embodiment, Figure 4 As shown, a transformer oil detection device is provided, including: a gas acquisition module 401, a signal acquisition module 402, a content determination module 403, a feature extraction module 404, a probability determination module 405 and a result determination module 406, wherein:

[0167] The gas acquisition module 401 is used to separate the transformer oil to be detected and obtain the gas to be detected corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be detected.

[0168] The signal acquisition module 402 is used to acquire the photoacoustic signal corresponding to the gas to be detected.

[0169] The content determination module 403 is used to determine the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal.

[0170] The feature extraction module 404 is used to extract the feature vector of the current acetylene content value.

[0171] The probability determination module 405 is used to input the feature vectors into a plurality of trained transformer oil detection models respectively to obtain the target prediction probability of the transformer oil under various preset detection results.

[0172] The result determination module 406 is used to select the preset detection result with the largest target prediction probability from various preset detection results as the target detection result corresponding to the transformer oil.

[0173] In an exemplary embodiment, the transformer oil detection device also includes an oil extraction port determination module, which is used to obtain structural information and oil flow path information of the transformer to be detected; extract key structural information from the structural information, and extract key oil flow path information from the oil flow path information; and determine multiple oil extraction ports of the transformer to be detected based on the key structural information and the key oil flow path information.

[0174] In an exemplary embodiment, the feature extraction module 404 is also used to obtain the target data type corresponding to the current acetylene content value; according to the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the current acetylene content value; obtain the historical acetylene content value corresponding to the gas to be detected, and use the current acetylene content value as the main data and the historical acetylene content value as the auxiliary data, input them into the target feature extraction model to obtain a feature vector.

[0175] In an exemplary embodiment, the probability determination module 405 is also used to input the feature vectors into multiple trained transformer oil detection models respectively to obtain the predicted probability of the transformer oil output by each trained transformer oil detection model under various preset detection results; verify the predicted probability of the transformer oil output by each trained transformer oil detection model under various preset detection results to obtain a verification result; when the verification result meets the preset verification result, the predicted probability of the transformer oil output by each trained transformer oil detection model under various preset detection results is weighted and summed to obtain a target predicted probability.

[0176] In an exemplary embodiment, the transformer oil detection device also includes an information sending module, which is used to obtain identification information corresponding to the transformer to be detected when the target detection result indicates that there is an abnormality in the transformer oil; generate early warning information corresponding to the transformer to be detected based on the target detection result and the identification information; and send the early warning information to the target terminal associated with the transformer to be detected.

[0177] In an exemplary embodiment, the transformer oil detection device also includes a model training module, which is used to separate and process the sample transformer oil to obtain a sample gas corresponding to the sample transformer oil; the sample transformer oil is obtained by collecting from multiple oil extraction ports of the sample transformer; a sample photoacoustic signal corresponding to the sample gas is obtained; based on the sample photoacoustic signal, a current sample acetylene content value corresponding to the sample gas is determined; a sample feature vector of the current sample acetylene content value is extracted; the sample feature vector is input into each transformer oil detection model to be trained respectively to obtain a predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained; an actual detection result corresponding to the sample transformer oil is obtained, and based on the difference between the predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained and the actual detection result, each transformer oil detection model to be trained is iteratively trained to obtain each trained transformer oil detection model.

[0178] Each module in the above transformer oil detection device can be implemented in whole or in part by software, hardware and a combination thereof. Each module can be embedded in or independent of a processor in a computer device in the form of hardware, or can be stored in a memory in a computer device in the form of software, so that the processor can call and execute operations corresponding to each module.

[0179] In an exemplary embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as shown in FIG. Figure 5 As shown. The computer device includes a processor, a memory, an input / output interface (Input / Output, referred to as I / O) and a communication interface. Among them, the processor, the memory and the input / output interface are connected through a system bus, and the communication interface is connected to the system bus through the input / output interface. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as the current acetylene content value and the target prediction probability. The input / output interface of the computer device is used to exchange information between the processor and an external device. The communication interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a transformer oil detection method is implemented.

[0180] Those skilled in the art will understand that Figure 5The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0181] In an exemplary embodiment, a computer device is further provided, including a memory and a processor, wherein a computer program is stored in the memory, and the processor implements the steps in the above-mentioned method embodiments when executing the computer program.

[0182] In an exemplary embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above-mentioned method embodiments are implemented.

[0183] In an exemplary embodiment, a computer program product is provided, including a computer program, and when the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0184] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to the memory, database or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memory. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. As an illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM). The database involved in each embodiment provided in this application may include at least one of a relational database and a non-relational database. Non-relational databases may include distributed databases based on blockchains, etc., but are not limited to this. The processor involved in each embodiment provided in this application may be a general-purpose processor, a central processing unit, a graphics processor, a digital signal processor, a programmable logic device, a data processing logic device based on quantum computing, etc., but are not limited to this.

[0185] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0186] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the attached claims.

Claims

1. A transformer oil detection method, characterized in that: The method comprises: The transformer oil to be tested is separated and processed to obtain the gas to be tested corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be tested; Acquiring a photoacoustic signal corresponding to the gas to be detected; Determining the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal; Extracting a feature vector of the current acetylene content value; Inputting the feature vectors into a plurality of trained transformer oil detection models respectively to obtain target prediction probabilities of the transformer oil under various preset detection results; From the various preset detection results, the preset detection result with the largest target prediction probability is screened out as the target detection result corresponding to the transformer oil.

2. The method according to claim 1, characterized in that: Before separating the transformer oil to be detected to obtain the gas to be detected corresponding to the transformer oil, the method further includes: Acquire structural information and oil flow path information of the transformer to be tested; Extracting key structural information from the structural information, and extracting key oil flow path information from the oil flow path information; According to the key structural information and the key oil flow path information, a plurality of oil extraction ports of the transformer to be inspected are determined.

3. The method according to claim 1, characterized in that The step of extracting the feature vector of the current acetylene content value comprises: Obtain the target data type corresponding to the current acetylene content value; According to the target data type, query the correspondence between the data type and the feature extraction model to obtain the target feature extraction model corresponding to the current acetylene content value; The historical acetylene content value corresponding to the gas to be detected is obtained, and the current acetylene content value is used as the main data, and the historical acetylene content value is used as the auxiliary data, which are input into the target feature extraction model to obtain the feature vector.

4. The method according to claim 1, characterized in that: The feature vectors are respectively input into a plurality of trained transformer oil detection models to obtain target prediction probabilities of the transformer oil under various preset detection results, including: Inputting the feature vectors into the multiple trained transformer oil detection models respectively, and obtaining the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model; Performing verification processing on the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model to obtain a verification result; In the case where the verification result meets the preset verification result, the predicted probability of the transformer oil under the various preset detection results output by each trained transformer oil detection model is weighted summed to obtain the target predicted probability.

5. The method according to claim 1, characterized in that: After selecting the preset detection result with the largest target prediction probability from the various preset detection results as the target detection result corresponding to the transformer oil, the method further includes: When the target detection result indicates that the transformer oil is abnormal, obtaining identification information corresponding to the transformer to be detected; Generate warning information corresponding to the transformer to be detected according to the target detection result and the identification information; The warning information is sent to a target terminal associated with the transformer to be detected.

6. The method according to any one of claims 1 to 5, characterized in that: Each trained transformer oil detection model is trained in the following way: The sample transformer oil is separated and processed to obtain a sample gas corresponding to the sample transformer oil; the sample transformer oil is obtained by collecting from multiple oil extraction ports of the sample transformer; Acquiring a sample photoacoustic signal corresponding to the sample gas; Determining a current sample acetylene content value corresponding to the sample gas according to the sample photoacoustic signal; Extracting a sample feature vector of the acetylene content value of the current sample; Inputting the sample feature vectors into each transformer oil detection model to be trained respectively, and obtaining the predicted detection results corresponding to the sample transformer oil output by each transformer oil detection model to be trained; The actual detection result corresponding to the sample transformer oil is obtained, and according to the difference between the predicted detection result corresponding to the sample transformer oil output by each transformer oil detection model to be trained and the actual detection result, each transformer oil detection model to be trained is iteratively trained to obtain each trained transformer oil detection model.

7. A transformer oil detection device, characterized in that: The device comprises: A gas acquisition module is used to separate and process the transformer oil to be detected to obtain the gas to be detected corresponding to the transformer oil; the transformer oil is obtained by collecting multiple oil extraction ports of the transformer to be detected; A signal acquisition module, used to acquire the photoacoustic signal corresponding to the gas to be detected; A content determination module, used to determine the current acetylene content value corresponding to the gas to be detected according to the photoacoustic signal; A feature extraction module, used to extract a feature vector of the current acetylene content value; A probability determination module, used to input the feature vectors into a plurality of trained transformer oil detection models respectively, to obtain a target prediction probability of the transformer oil under various preset detection results; The result determination module is used to select the preset detection result with the largest target prediction probability from the various preset detection results as the target detection result corresponding to the transformer oil.

8. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images