Online detection method for gas in transformer oil based on photoacoustic spectrum self-correction

Abstract

The invention discloses an on-line detection method for gas in transformer oil based on photoacoustic spectrum self-correction, and relates to the technical field of spectrum detection and power equipment state monitoring, and the method comprises the following steps: S1, emitting modulation laser with a specific wavelength to a gas sample released by the transformer oil through a laser, and exciting gas molecules to generate photoacoustic signals; and S2, detecting the photoacoustic signal by using a photoacoustic sensor, converting the signal into an electric signal, and outputting the electric signal. According to the online detection method for the gas in the transformer oil, the correction coefficient is adjusted in real time through a self-correction algorithm, errors caused by light path changes and sensor aging are effectively compensated, the precision and stability of long-term detection are remarkably improved, and the detection accuracy is improved by combining a gas spectrum database and a mode recognition algorithm. According to the method, accurate qualitative and quantitative analysis of various gases is realized, the problem of cross sensitivity of multiple components is solved, and the method also has temperature and pressure compensation functions and can automatically adapt to environmental changes.

Description

Technical Field

[0001] The present invention relates to the technical fields of spectral detection and power equipment condition monitoring, and particularly to an on-line gas detection method for transformer oil based on photoacoustic spectroscopy self-calibration. Background Art

[0002] The composition and concentration changes of dissolved gases in transformer oil are closely related to the types of internal faults of power equipment. Therefore, real-time monitoring of the gases in the oil is an important means to ensure the safe operation of the power system. At present, traditional off-line detection methods require regular manual sampling and analysis by a gas chromatograph, which have problems such as long detection cycles and poor timeliness, and are difficult to meet the requirements of modern smart grids for real-time monitoring of equipment status. In on-line detection technologies, although some methods based on electrochemical sensors or infrared spectroscopy can achieve continuous monitoring, they are limited by factors such as sensor drift, environmental interference, and multi-component cross-sensitivity, and it is difficult to guarantee long-term detection accuracy. Especially under complex working conditions, factors such as temperature and pressure fluctuations and optical path attenuation will significantly affect the reliability of detection results, leading to an increased risk of misjudgment or missed judgment.

[0003] In the prior art, there is still room for improvement in the gas identification accuracy and system stability of traditional photoacoustic spectroscopy detection methods. For example, traditional methods rely on fixed calibration coefficients and cannot dynamically compensate for errors caused by optical path changes and sensor aging; when detecting multi-gas mixtures, they are easily interfered by overlapping characteristic spectra, and the qualitative classification accuracy needs to be improved; at the same time, there is a lack of an adaptive compensation mechanism for environmental parameter changes, resulting in detection results being easily affected by temperature and pressure fluctuations. In addition, the self-checking and fault diagnosis capabilities of existing systems are limited, and it is difficult to achieve intelligent operation and maintenance throughout the equipment life cycle. In response to this, we propose an on-line gas detection method for transformer oil based on photoacoustic spectroscopy self-calibration. Summary of the Invention

[0004] To solve the above technical problems and provide an on-line gas detection method for transformer oil based on photoacoustic spectroscopy self-calibration, the present technical solution solves the above problems.

[0005] To achieve the above object, the technical solution adopted by the present invention is as follows: An on-line gas detection method for transformer oil based on photoacoustic spectroscopy self-calibration, comprising the following steps: S1. Emitting a modulated laser with a specific wavelength to the gas sample released from the transformer oil through a laser to excite gas molecules to generate photoacoustic signals; S2. Detecting the photoacoustic signals by a photoacoustic sensor and converting the signals into electrical signals for output; S3. Preprocessing the electrical signals, including filtering, amplifying, and analog-to-digital conversion, to obtain digital signals; S4. Analyze the digital signal based on the self - calibration algorithm, dynamically adjust the calibration coefficient according to the gas type and concentration, and quantitatively map the signal amplitude and gas concentration; S5. Combine the gas spectral database, and qualitatively classify the gas through characteristic wavelength matching and pattern recognition algorithms; S6. Based on the results of qualitative classification, output the gas type, concentration and abnormal alarm information.

[0006] Preferably, in the S1 step, the wavelength range of the modulated laser is from 3 microns to 12 microns in the infrared band. The laser modulation frequency is determined by the ratio of the speed of light to twice the length of the photoacoustic cell resonator cavity, and the modulation depth is from one - quarter to one - half of the laser wavelength; The gas sample is separated from the transformer oil through a polytetrafluoroethylene permeable membrane and introduced into the photoacoustic cell. The thickness of the permeable membrane is from 0.1 mm to 0.5 mm, and the permeation rate is adjusted by a temperature controller with a temperature control accuracy of ±0.1 degrees Celsius.

[0007] Preferably, the photoacoustic cell adopts a cylindrical resonator cavity structure, the inner wall is coated with a gold film with a reflectivity greater than 98%, and the incident window and the exit window made of zinc selenide are provided at both ends of the cavity; The Q value of the resonator cavity is determined by the ratio of the resonance frequency to the half - height width of the resonance peak, and the Q value is not less than 1000; The photoacoustic sensor is an array containing at least three piezoelectric microphones. The microphones are symmetrically distributed at 120 degrees. When synthesizing the signals, the weight coefficients are dynamically allocated according to the signal - to - noise ratio of each microphone and weighted average is performed.

[0008] Preferably, the pre - processing of the electrical signal in the S3 step specifically includes: Use a band - pass filter to remove low - frequency mechanical noise and high - frequency electromagnetic interference. The pass - band range is offset by 10 Hz above and below the center frequency; The signal amplification uses a programmable gain amplifier, and the gain coefficient is adaptively adjusted according to the amplitude of the original signal: when the amplitude of the original signal is less than 1 mV, the gain is 1000 times; when it is between 1 mV and 10 mV, the gain is 100 times; when it is greater than or equal to 10 mV, the gain is 10 times; The analog - to - digital conversion uses a 24 - bit Σ - Δ analog - to - digital converter, the sampling rate is not less than 10 kHz, and the quantization error is less than 0.1%.

[0009] Preferably, the implementation of the self - calibration algorithm in the S4 step includes the following steps: Establish an initial linear relationship model between the photoacoustic signal amplitude and the gas concentration. The model consists of the product of the initial sensitivity coefficient and the gas concentration plus the background noise offset; Inject a standard gas sample into the photoacoustic cell to obtain the measured signal, and calculate the absolute difference between the measured signal and the theoretical signal calculated based on the current correction coefficient and the standard concentration as the error; Use the gradient descent method to iteratively update the sensitivity coefficient and the background noise offset until the error is less than the set threshold, form a corrected linear relationship model, and use the corrected model for real-time gas concentration calculation; The gradient descent method of the self-correction algorithm is specifically as follows: Set the learning rate to 0.01 and the maximum number of iterations to 1000; In each iteration, update these two parameters at a fixed learning rate according to the partial derivatives of the sensitivity coefficient and the background noise offset with respect to the current error; Terminate the iteration when the change in error for 5 consecutive iterations is less than 0.00001.

[0010] Preferably, the gas spectral database in step S5 includes the characteristic absorption wavelengths of 10 gases including hydrogen, carbon monoxide, methane, acetylene, ethylene, ethane, carbon dioxide, oxygen, nitrogen, and water vapor, and the corresponding photoacoustic signal reference spectral lines. The database automatically updates the standard spectral line data according to the set threshold, and supports users to perform local calibration by injecting gas samples with known concentrations. The calibration data is stored in JSON format.

[0011] Preferably, the qualitative classification of the gas in step S5 is specifically as follows: Adopt an algorithm combining principal component analysis and support vector machine to qualitatively classify the gas. The method steps are as follows: Perform data preprocessing and standardization on the photoacoustic intensity values corresponding to the characteristic wavelengths of the photoacoustic spectrum signal, perform principal component analysis for dimensionality reduction, calculate the covariance matrix of the standardized data, and perform eigenvalue decomposition on this matrix to obtain the eigenvalues arranged in descending order and the corresponding eigenvectors; Select the first several principal components with a cumulative contribution rate exceeding 95%, project the original data into the new space composed of these principal component eigenvectors, and form a low-dimensional data set; Divide the data set into a training set and a test set, with labels corresponding to different gas types, and select a Gaussian kernel function to map the data into a high-dimensional space. Find the maximum margin hyperplane by solving a convex optimization problem, adopt an optimization algorithm to balance the model complexity and the classification error, introduce a penalty factor to adjust the tolerance for misclassified samples, and use slack variables to handle non-linearly separable data; Adopt the "one-vs-rest" strategy to train a binary classifier for each type of gas separately. Finally, determine the category of the sample through a voting mechanism. In the model training stage, optimize the parameters through grid search and cross-validation. Traverse the candidate value combinations of the penalty factor and the kernel function parameters, and evaluate the classification accuracy of each group of parameters in combination with cross-validation; After completing parameter optimization, input the test samples into the trained model, calculate the results of the weighted kernel function of the support vector and the bias term, and determine the gas category of the sample through the sign function.

[0012] Preferably, it further includes a temperature and pressure compensation module, and its implementation method is as follows: Collect the temperature and pressure data in the photoacoustic cell in real time; According to the standard temperature of 298K and the standard pressure of 101.325 kPa, perform temperature and pressure normalization correction on the gas concentration; When the temperature fluctuation exceeds ±2K or the pressure fluctuation exceeds ±5 kPa, trigger the self-calibration algorithm to recalibrate.

[0013] Preferably, the triggering logic of the abnormal alarm is as follows: When the concentration of a single gas exceeds the preset threshold, immediately trigger a first-level alarm, where the hydrogen threshold is 100 ppm, acetylene is 5 ppm, and carbon monoxide is 350 ppm; When the concentrations of three or more gases reach 50% of the threshold and last for 30 minutes simultaneously, trigger a second-level alarm; The alarm information is uploaded to the cloud platform through the wireless network module, and a diagnostic report including exponential trend prediction is generated.

[0014] Preferably, it further includes a system self-check function: Automatically detect the laser power at zero o'clock every day. When the power deviation exceeds ±5%, switch to the standby laser source; Monitor the spot position deviation through the CCD camera every week. When the deviation exceeds 50 microns, start the piezoelectric ceramic regulator to correct the optical path; Based on the signal-to-noise ratio, Q value, and temperature drift rate parameters, use the decision tree model to diagnose the failure types of laser aging, microphone failure, or gas path blockage.

[0015] Compared with the prior art, the beneficial effects of the present invention are as follows: The on-line gas detection method in transformer oil proposed by the present invention adjusts the calibration coefficient in real time through a self-calibration algorithm, effectively compensates for the errors caused by the optical path change and sensor aging, significantly improves the accuracy and stability of long-term detection, combines the gas spectral database and the pattern recognition algorithm, realizes the precise qualitative and quantitative analysis of multiple gases, overcomes the problem of multi-component cross-sensitivity. This method also has temperature and pressure compensation functions, can automatically adapt to environmental changes, ensure the accuracy of detection results. Its abnormal alarm mechanism can timely detect potential faults and upload them to the cloud through the wireless network, providing timely and effective decision-making support for maintenance personnel. The system self-check function further enhances the reliability and maintainability of the equipment, reducing the operation and maintenance costs. In summary, this method not only improves the sensitivity and accuracy of gas detection in transformer oil, but also provides strong technical support for the preventive maintenance of power equipment, which is of great significance for ensuring the safe and stable operation of the power system. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 is the flowchart of the method of the present invention; Figure 2 is the key node diagram of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0017] The following description is used to disclose the present invention so that those skilled in the art can implement the present invention. The preferred embodiments in the following description are only examples, and those skilled in the art can think of other obvious variations.

[0018] Referring to Figure 1 as shown, the on-line gas detection method in transformer oil based on photoacoustic spectroscopy self-calibration includes the following steps: The equipment status is evaluated by real-time monitoring of the dissolved gases in the transformer oil. This method uses the photoacoustic signals generated by the interaction of laser with gas molecules at specific wavelengths, combines self-calibration algorithms and spectral database analysis, can accurately identify the gas types and quantify the concentrations, providing key data support for the preventive maintenance of power equipment.

[0019] The detection process starts with the excitation of the laser light source. The system uses a wavelength-tunable semiconductor laser, and emits a laser beam with a specific frequency through modulation technology. These laser beams are focused by the optical path system and then injected into the gas sample released from the transformer oil sample. When the laser wavelength matches the vibration-rotation energy level transition frequency of the target gas molecules, the gas will absorb light energy and convert it into heat energy, causing periodic thermal expansion, and then generating photoacoustic signals consistent with the laser modulation frequency. This photoacoustic effect has high sensitivity and selectivity, and can effectively distinguish different gas components.

[0020] As the core component for signal acquisition, the photoacoustic sensor uses a highly sensitive microphone or piezoelectric ceramic device to convert the pressure wave generated by the thermal expansion of gas molecules into an electrical signal. Since the photoacoustic signal is usually relatively weak, it needs to go through multiple stages of amplification and filtering. The preprocessing module includes a low-noise preamplifier, a band-pass filter, and an analog-to-digital converter, which can effectively suppress environmental noise interference and convert the analog signal into a digital signal, providing a stable basis for subsequent signal analysis.

[0021] The self-calibration algorithm is the key innovation of this method. The system dynamically adjusts the calibration coefficient by combining the amplitude of the photoacoustic signal collected in real time with the gas concentration inversion model. This adaptive mechanism can compensate for measurement errors caused by environmental factors such as optical path attenuation and sensor drift, ensuring the detection accuracy can still be maintained under complex working conditions. The algorithm realizes the self-calibration and performance improvement of the detection system by establishing a non-linear mapping relationship between the signal amplitude and the gas concentration, and optimizing the model parameters using historical data and real-time feedback.

[0022] Qualitative analysis relies on the gas spectral database and pattern recognition technology. The system has a built-in database containing the absorption spectra of various characteristic gases (such as hydrogen, methane, carbon monoxide, etc.). By comparing the spectral data collected in real time with the database and using the correlation coefficient matching or neural network classification algorithm, the gas type can be quickly determined. This pattern recognition technology can not only identify single gases but also analyze the components of mixed gases, improving the reliability of the detection results.

[0023] Finally, the system compares the gas concentration data obtained from quantitative analysis with the preset threshold, and combines the gas generation rate and gas production trend to judge the operating state of the equipment. When abnormal gas concentrations or sudden changes in gas production rates are detected, the alarm mechanism is immediately triggered to prompt the operation and maintenance personnel to carry out repairs. The detection results are displayed in an intuitive form, including the real-time concentration curves of each gas component, historical trend analysis, and equipment health status assessment reports, providing strong support for the intelligent operation and maintenance of the power system.

[0024] This method has the advantages of on-line monitoring, real-time response, multi-component detection, etc., which can effectively make up for the deficiencies of traditional off-line detection with long detection cycles and poor timeliness. By combining photoacoustic spectroscopy technology with the self-calibration algorithm, the sensitivity and anti-interference ability of gas detection have been significantly improved, providing a reliable technical means for the condition-based maintenance of oil-filled power equipment such as transformers. With the continuous development of sensor technology and artificial intelligence algorithms, this detection method will play an increasingly important role in the power system, contributing to the safe and stable operation of the smart grid.

[0025] In the S1 step, the wavelength range of the modulated laser is from 3 to 12 micrometers in the infrared band, and the laser modulation frequency is determined by the ratio of the speed of light to twice the length of the photoacoustic cell resonance cavity. The laser modulation frequency satisfies:

[0026] wherein is the laser modulation frequency, is the speed of light, is the length of the photoacoustic cell resonator cavity, and the modulation depth is from one - quarter to one - half of the laser wavelength; The gas sample is separated from the transformer oil through a polytetrafluoroethylene permeable membrane and introduced into the photoacoustic cell. The thickness of the permeable membrane is from 0.1 mm to 0.5 mm, and the permeation rate is adjusted by a temperature controller with a temperature control accuracy of ±0.1 °C.

[0027] The photoacoustic cell adopts a cylindrical resonator cavity structure, with a gold film with a reflectivity greater than 98% plated on the inner wall, and an incident window and an exit window made of zinc selenide are provided at both ends of the cavity. Through the high reflectivity (>98%) of the gold - plated inner wall, the scattering and absorption losses of the photoacoustic signal on the cavity wall can be significantly reduced, thereby reducing the full - width at half - maximum Δf of the resonance peak and increasing the Q value. The axisymmetric characteristic of the cylindrical structure is beneficial to maintaining a stable axial standing - wave mode, reducing the interference of higher - order modes, and further suppressing the energy dispersion. The zinc selenide window material has a low absorption rate (<0.1%) and a high transmittance (>90%) in the infrared band, which can minimize the transmission loss. In addition, the optimized design of the cavity length and diameter (aspect ratio ≥5:1) can enhance the acoustic resonance efficiency and reduce the energy leakage caused by the boundary conditions. According to the acoustic resonance theory, the Q value can be approximately expressed as: ; wherein is the propagation time of the sound wave in the cavity, is the absorption coefficient of the cavity wall material, is the cavity perimeter, is the window transmission loss coefficient, is the window area. By gold - plating the inner wall ( ≈0.02), using a zinc selenide window ( ≈0.05) and optimizing the aspect ratio, it can ensure that the denominator term approaches 1, thus meeting the design requirement of Q value ≥1000.

[0028] The Q value of the resonator cavity is determined by the ratio of the resonance frequency to the full - width at half - maximum of the resonance peak, and the Q value of the resonator cavity satisfies: ; wherein is the quality factor of the resonator cavity, is the resonance frequency, is the full - width at half - maximum of the resonance peak; The photoacoustic sensor is a microphone array, including at least 3 piezoelectric microphones symmetrically distributed at 120°, and the signal synthesis adopts a weighted average algorithm: ; wherein is the total photoacoustic signal after synthesis, is the total number of microphones, is the weight coefficient of the th microphone. The weight coefficient allocation logic of the microphone array is based on the real-time signal quality of each channel: the system continuously monitors the signal-to-noise ratio of each microphone, and preferentially assigns a larger weight to the channel with a higher signal-to-noise ratio. When the signal of a certain microphone is contaminated by noise due to position or environmental interference, its weight is automatically reduced; while the weight of the microphone with clear signal and low background noise is dynamically increased. At the same time, the symmetrically arranged microphones cover the cavity sound field through spatial complementarity, and the weight allocation combines the correlation analysis between channels to avoid redundant noise superposition. Finally, the data of each channel are fused by weighted average, while retaining the effective sound pressure fluctuation characteristics, suppressing random interference and local outliers, and maximizing the overall signal-to-noise ratio., is the photoacoustic signal of the th microphone, which is dynamically allocated according to the signal-to-noise ratio. The symmetric distribution of the microphone layout can evenly capture the sound pressure fluctuations at different positions in the cavity, effectively cancel the local noise interference through spatial averaging, and improve the spatial consistency of the signal. The weight coefficient of each microphone is dynamically allocated according to its real-time signal-to-noise ratio, and the data of the channel with high signal quality are preferentially used. When synthesizing the total signal, random noise is further suppressed, and the intensity of the effective photoacoustic signal is enhanced. This design not only optimizes the redundancy of signal acquisition, but also reduces the influence of environmental vibration or electromagnetic interference on the detection sensitivity through multi-channel cooperation, and finally realizes the signal output with high signal-to-noise ratio, laying a foundation for the accurate inversion of gas concentration.

[0029] The preprocessing of the electrical signal in the step S3 specifically includes: A band-pass filter is used to remove low-frequency mechanical noise and high-frequency electromagnetic interference, and the passband range is offset by 10 Hz above and below the center frequency; The signal amplification uses a programmable gain amplifier, and the gain coefficient is adaptively adjusted according to the amplitude of the original signal: when the amplitude of the original signal is less than 1 mV, the gain is 1000 times; when it is between 1 mV and 10 mV, the gain is 100 times; when it is greater than or equal to 10 mV, the gain is 10 times. Specifically: ; In the formula, is the gain coefficient of the programmable gain amplifier, is the amplitude of the original signal.

[0030] The analog-to-digital conversion uses a 24-bit Σ-Δ analog-to-digital converter, the sampling rate is not less than 10 kHz, and the quantization error is less than 0.1%.

[0031] The implementation of the self - calibration algorithm in step S4 includes the following steps: Establish an initial linear relationship model between the photoacoustic signal amplitude and the gas concentration. The model is composed of the product of the initial sensitivity coefficient and the gas concentration plus the background noise offset; the initial relationship model is: ; where, is the photoacoustic signal amplitude, is the initial sensitivity coefficient, is the gas concentration, is the background noise offset; Inject a standard gas sample into the photoacoustic cell to obtain the measured signal, and calculate the absolute difference between the measured signal and the theoretical signal calculated based on the current calibration coefficient and the standard concentration as the error: ; where, is the absolute error between the measured signal and the theoretical signal, is the measured signal value, is the calibration coefficient, is the standard gas concentration, is the baseline offset; Use the gradient descent method to iteratively update the sensitivity coefficient and the background noise offset until the error is less than the set threshold, forming a calibrated linear relationship model, and use the calibrated model for real - time gas concentration calculation. The updated model is: ; where, is the final gas concentration result after calibration, is the sensitivity of the sensor to the change in gas concentration, is the original gas concentration measurement value, is the baseline noise or zero - point drift of the sensor. Use the calibrated model for real - time gas concentration calculation.

[0032] The gradient descent method of the self - calibration algorithm is specifically: Set the learning rate to 0.01 and the maximum number of iterations to 1000 times; Update the coefficient each iteration: ; In the formula, is the sensitivity coefficient of the th iteration, is the sensitivity coefficient of the th iteration, is the learning rate, is the partial derivative of the error with respect to .

[0033] ; In the formula, is the background noise offset of the -th iteration, is the background noise offset of the -th iteration, is the partial derivative of the error with respect to the background offset, and the partial derivative is calculated as: ; In the formula, is the partial derivative of the error with respect to , is the measured signal amplitude, is the standard gas concentration, is the background noise offset of the -th iteration.

[0034] ;When the error change amount of 5 consecutive iterations is less than 0.00001, the iteration is terminated. The system uses the mean square error between the measured signal and the theoretical signal as the loss function, and determines the parameter adjustment direction by calculating the partial derivatives of the error with respect to the sensitivity coefficient and the background noise offset. In each iteration, the algorithm first calculates the prediction error under the current parameters, and then adjusts the sensitivity coefficient according to the partial derivative of the error with respect to the sensitivity coefficient (i.e., the sensitivity of the error to the change of the sensitivity coefficient), so that it is updated in the direction of reducing the error. At the same time, the algorithm calculates the partial derivative of the error with respect to the background noise offset (i.e., the sensitivity of the error to the change of the background offset), and synchronously corrects the background noise offset. The learning rate controls the step size of parameter update to avoid oscillation caused by too large adjustment amplitude. When the error change tends to be stable or reaches the maximum number of iterations, the algorithm terminates and outputs the optimized parameters, finally realizing the dynamic calibration of the sensitivity coefficient and the background noise, and ensuring the accuracy of the gas concentration inversion model.

[0035] The gas spectral database in the S5 step contains the characteristic absorption wavelengths of 10 gases including hydrogen, carbon monoxide, methane, acetylene, ethylene, ethane, carbon dioxide, oxygen, nitrogen and water vapor and the corresponding photoacoustic signal reference spectral lines. The database automatically updates the standard spectral line data according to the set threshold, and supports the user to perform local calibration by injecting gas samples with known concentrations. The calibration data is stored in JSON format.

[0036] The specific qualitative classification of the gas in the S5 step is as follows: In the gas qualitative classification link, we adopted a hybrid algorithm combining principal component analysis and support vector machine to achieve accurate identification of gas categories through multi-dimensional data processing and intelligent model construction. First, the photoacoustic spectroscopy signal is preprocessed. Input data: The photoacoustic intensity values corresponding to the characteristic wavelengths of the photoacoustic spectroscopy signal form the original data set.

[0037] Standardization processing: Standardize each characteristic dimension to eliminate the dimension difference: ; where is the value of the th feature of the th sample in the standardized data set, is the value of the th feature of the th sample in the original data set, is the mean value of the th feature, used to measure the average level of this feature, is the standard deviation of the th feature, used to measure the dispersion degree of the data of this feature. The core of this step is to eliminate instrument noise and environmental interference to ensure the reliability of subsequent analysis. We perform standardization processing on the photoacoustic intensity values corresponding to the characteristic wavelengths to make the characteristic data with different dimensions at the same dimension level and avoid affecting the model training effect due to data scale differences.

[0038] Next, perform principal component analysis for dimensionality reduction, which is a key step to solve the problem of high-dimensional data redundancy. We first calculate the covariance matrix of the standardized data and extract the principal components of the data through eigenvalue decomposition technology. Covariance matrix calculation: Calculate the covariance matrix of the standardized data : ; where is the covariance matrix of the standardized data , used to measure the correlation between features, is the transpose matrix of the standardized data set , is the number of samples. The core reason for choosing principal component analysis (PCA) over other dimensionality reduction methods lies in its suitability for spectral data: in the high-dimensional features of photoacoustic spectroscopy, there is often a large amount of redundant information caused by gas absorption peak overlap or instrument noise. By extracting the principal components in the direction of the maximum variance, PCA can compress irrelevant fluctuations and noise while retaining the key features for gas classification (such as the intensity differences corresponding to specific absorption wavelengths), significantly enhancing the generalization ability of the classification model. In addition, the linear transformation property of PCA is highly compatible with the kernel function processing of subsequent support vector machines, which can not only avoid the computational complexity problems of non-linear dimensionality reduction methods (such as t-SNE), but also construct clear separable boundaries for different gas categories. This dimensionality reduction strategy is particularly suitable for the multi-component recognition scenario of mixed gases. Through the physical meaning of the principal components (such as the correlation between the principal components and the absorption spectra of specific gases), the classification results can be intuitively explained, enhancing the interpretability and reliability of the detection system.

[0039] Eigenvalue decomposition: Perform eigen-decomposition on the covariance matrix to obtain the eigenvalues and the corresponding eigenvectors . The magnitudes of the eigenvalues reflect the contribution degrees of the respective principal components to the data variance. After arranging them in descending order, select the first several principal components whose cumulative contribution rate exceeds 95%. Principal component selection: Select the number of principal components according to the cumulative contribution rate of the eigenvalues (usually taking the cumulative contribution rate > 95%): The specific cumulative contribution rate is: ; where, is the covariance matrix 's th eigenvalue. The larger the eigenvalue, the more information the corresponding principal component contains. is the number of principal components, is the number of eigenvalues. These principal components form a new feature space, which can not only retain the main information of the original data but also effectively reduce the dimension. After projecting the original data into this low-dimensional space, a new data set is formed, providing a more efficient input for subsequent classification tasks. The finally dimension-reduced data set is: ; where, is the dimension-reduced data set, is the projection matrix composed of the first eigenvectors.

[0040] In the data partitioning stage, we divide the dataset into a training set and a test set according to a certain ratio. The training set is used for learning model parameters, and the test set is used to evaluate the model's generalization ability. The label system corresponds to different gas types, and through supervised learning, the model is guided to establish the mapping relationship between input features and gas categories. When constructing the support vector machine model, the Gaussian kernel function is selected as the non-linear mapping tool to map low-dimensional data to a high-dimensional feature space to solve the non-linearly separable problem. Specifically: ; Among them, and are two sample vectors in the dataset after dimensionality reduction, is the kernel parameter, which controls the locality of the kernel function. The larger is, the more local the kernel function is. In the gas classification task, the Gaussian kernel function converts low-dimensional features into a high-dimensional space through non-linear mapping, and can effectively distinguish the subtle differences of different gas absorption peaks in spectral data. The value of γ directly affects the sensitivity of the classification boundary: when γ is small, the kernel function has a wide coverage range, and the model tends to global features, which is suitable for the smooth separation of overlapping absorption peaks in mixed gases; when γ is large, the kernel function focuses on local features, which is more suitable for the sharp distinction requirements of single gas absorption peaks. In practical applications, the value range of γ is usually determined by cross-validation combined with grid search. Considering the characteristics of photoacoustic spectroscopy data (such as signal-to-noise ratio, absorption peak density), a γ value between 0.01 and 1 is preferably selected to balance the model's generalization ability and classification accuracy. SVM finds the maximum margin hyperplane by solving the following convex optimization problem: ; Among them, is the normal vector of the hyperplane, is the bias term of the hyperplane, are slack variables, which are used to handle the misclassification of samples, is the penalty factor, which is used to balance the complexity of the model and the cost of misclassification, is the number of samples. By solving the convex optimization problem to find the maximum margin hyperplane, the position of this hyperplane determines the decision boundary between different categories.

[0041] To balance the model complexity and classification error, we introduce a penalty factor to adjust the tolerance for misclassified samples. For data with noise or non-linearly separable, the slack variables allow some samples to cross the hyperplane, thereby improving the model's robustness. Specifically: ; Among them, is the class label of the th sample, is the normal vector of the hyperplane, is the transpose operation of a matrix or vector, is the kernel mapping function, is the offset of the hyperplane relative to the origin. The classification strategy adopts the "one-vs.-rest" method, and a binary classifier is trained for each gas category. Each binary classifier distinguishes the current category from all other categories, and finally, the voting mechanism is used to comprehensively combine the judgment results of all binary classifiers to determine the final category attribution of the sample.

[0042] In the model training stage, parameter optimization is a crucial step in improving performance. We adopt the method of grid search combined with cross-validation to systematically traverse the candidate value combinations of the penalty factor and the kernel function parameters. Each set of parameter combinations corresponds to a model instance, and its classification accuracy is evaluated through cross-validation. The parameter combination with the highest accuracy is selected as the final model parameter. This method effectively avoids overfitting and ensures the stability of the model on different data subsets.

[0043] After completing the parameter optimization, the model enters the testing stage. When inputting the test samples, the model calculates the results of the weighted kernel function of the support vectors and the bias term, and determines the category to which the sample belongs through the sign function. The whole process realizes the end-to-end automated analysis from the original spectral signal to the gas category, which not only retains the essential characteristics of the spectral data but also improves the classification efficiency and accuracy through machine learning algorithms. This method significantly reduces the computational complexity while ensuring the recognition accuracy and is applicable to real-time monitoring and online analysis scenarios.

[0044] It also includes a temperature and pressure compensation module, and its implementation method is as follows: Real-time collect the temperature and pressure data in the photoacoustic cell; According to the standard temperature of 298K and the standard pressure of 101.325 kPa, perform temperature and pressure normalization correction on the gas concentration, and its normalization correction formula is: The actually measured gas concentration needs to be multiplied by the ratio of the measured pressure to the standard pressure and then multiplied by the ratio of the standard temperature to the measured temperature. For example, if the actually measured pressure is , and the temperature is , the corrected concentration is: ; In the formula, is the corrected standard concentration, representing the concentration value of the gas under standard temperature and pressure, is the actually measured concentration, the original concentration obtained by inverting the photoacoustic signal, is the standard pressure value (kPa), is the standard temperature value (Kelvin, K). This formula is based on the ideal gas law, and through the linear proportional relationship between pressure and temperature, it eliminates the influence of environmental parameter fluctuations on the gas volume concentration, ensuring that the detection results are comparable to the data under standard conditions.

[0045] When the temperature fluctuation exceeds ±2K or the pressure fluctuation exceeds ±5 kPa, the self-calibration algorithm is triggered to recalibrate.

[0046] Preferably, the triggering logic of the abnormal alarm is as follows: When the concentration of a single gas exceeds the preset threshold, a first-level alarm is immediately triggered. The threshold for hydrogen is 100 ppm, for acetylene is 5 ppm, and for carbon monoxide is 350 ppm. When the concentrations of three or more gases reach 50% of the threshold and last for 30 minutes, a second-level alarm is triggered. The alarm information is uploaded to the cloud platform through the wireless network module, and a diagnostic report including exponential trend prediction is generated.

[0047] It also includes a system self-check function: In the system self-check function module, the device ensures long-term stable operation through a multi-dimensional monitoring mechanism. At zero o'clock every day, the system automatically triggers the laser power detection program, and the photodetector built-in in real-time collects the laser output power data and compares it with the reference value. When the detected power fluctuation exceeds the preset threshold, the system will immediately start the redundant switching mechanism, seamlessly access the backup laser source, and generate maintenance prompt information for technicians to refer to. This preventive maintenance strategy effectively avoids detection errors caused by the performance attenuation of the laser.

[0048] At a fixed time every week, the system will call a high-precision CCD camera to perform optical alignment detection on the optical path system. By analyzing the imaging position of the light spot on the detector array, the central offset of the light spot is calculated in real-time. When the offset exceeds the allowable range, the system automatically activates the micro-displacement adjustment mechanism driven by piezoelectric ceramics, adjusts the angle of the mirror through mechanical compensation with nanometer-level precision, and ensures that the laser beam is always focused on the central area of the gas chamber. This closed-loop correction process can effectively offset the optical path drift caused by environmental temperature changes or mechanical vibrations.

[0049] In terms of equipment health status monitoring, the system integrates an intelligent diagnosis module based on multi-parameter fusion. By collecting key parameters such as the signal-to-noise ratio of photoacoustic signals, the Q value of the laser, and the environmental temperature drift rate in real time, a decision tree model is constructed for fault mode recognition. When an abnormal decrease in the signal-to-noise ratio is detected, the system will further analyze the change trend of the Q value curve to distinguish whether it is a performance decline caused by laser aging or signal attenuation caused by reduced microphone sensitivity. If the temperature drift rate is simultaneously monitored to exceed the normal range, an air path blockage warning will be triggered, and the blockage location will be located by analyzing the temperature gradient distribution. This hierarchical diagnosis mechanism can quickly locate the root cause of the fault, provide accurate repair guidance for maintenance personnel, and significantly improve the usability and reliability of the system.

[0050] The above shows and describes the basic principles, main features and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited by the above embodiments. What is described in the above embodiments and the specification is only the principle of the present invention. Without departing from the spirit and scope of the present invention, the present invention will have various changes and improvements, and these changes and improvements all fall within the scope of the present invention claimed. The scope of protection required by the present invention is defined by the appended claims and their equivalents.

Claims

1. An online detection method for gas in transformer oil based on self-calibration of photoacoustic spectroscopy, characterized in that: The following steps are involved: S1. The laser emits a modulated laser of a specific wavelength to the gas sample released from the transformer oil to excite the gas molecules to generate photoacoustic signals. S2, using a photoacoustic sensor to detect the photoacoustic signal and convert the signal into an electrical signal for output; S3, preprocessing the electrical signal, including filtering, amplification and analog-to-digital conversion, to obtain a digital signal; S4, analyzing the digital signal based on the self-correction algorithm, dynamically adjusting the correction coefficient according to the gas type and concentration, and quantitatively mapping the signal amplitude and gas concentration; S5. Combined with the gas spectrum database, the gas is qualitatively classified through characteristic wavelength matching and pattern recognition algorithm; S6. Based on the results of qualitative classification, output gas type, concentration and abnormal alarm information.

2. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The wavelength range of the modulated laser in step S1 is 3 to 12 microns in the infrared band, the laser modulation frequency is determined by the ratio of the speed of light to twice the length of the photoacoustic cell resonant cavity, and the modulation depth is one quarter to one half of the laser wavelength; The gas sample is separated from the transformer oil and introduced into the photoacoustic cell through a polytetrafluoroethylene permeable membrane with a thickness of 0.1 mm to 0.5 mm. The permeation rate is adjusted by a temperature controller with a temperature control accuracy of ±0.1 degrees Celsius.

3. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 2, characterized in that: The photoacoustic cell adopts a cylindrical resonant cavity structure, the inner wall of which is plated with a gold film with a reflectivity greater than 98%, and an incident window and an exit window made of zinc selenide are provided at both ends of the cavity; The Q value of the resonant cavity is determined by the ratio of the resonant frequency to the half-height width of the resonant peak, and the Q value is not less than 1000; The photoacoustic sensor is an array of at least three piezoelectric microphones, which are symmetrically distributed at 120 degrees. When synthesizing signals, weight coefficients are dynamically allocated according to the signal-to-noise ratio of each microphone and weighted averaging is performed.

4. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The preprocessing of the electrical signal in step S3 specifically includes: A bandpass filter is used to remove low-frequency mechanical noise and high-frequency electromagnetic interference, and the passband range is 10 Hz above and below the center frequency; The signal amplification adopts a programmable gain amplifier, and the gain coefficient is adaptively adjusted according to the original signal amplitude: when the original signal amplitude is less than 1 millivolt, the gain is 1000 times, when it is 1 millivolt to 10 millivolts, the gain is 10 times, and when it is greater than or equal to 10 millivolts, the gain is 10 times; The analog-to-digital conversion uses a 24-bit Σ-Δ analog-to-digital converter with a sampling rate of no less than 10 kHz and a quantization error of less than 0.1%.

5. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The implementation of the self-correction algorithm in step S4 comprises the following steps: Establish an initial linear relationship model between the photoacoustic signal amplitude and the gas concentration. The model is composed of the product of the initial sensitivity coefficient and the gas concentration plus the background noise offset. The measured signal is obtained by injecting the standard gas sample into the photoacoustic cell, and the absolute difference between the measured signal and the theoretical signal calculated based on the current correction coefficient and the standard concentration is calculated as the error; The sensitivity coefficient and the background noise offset are iteratively updated using the gradient descent method until the error is less than the set threshold, forming a corrected linear relationship model, and the corrected model is used for real-time gas concentration calculation; The gradient descent method of the self-correction algorithm is specifically: Set the learning rate to 0.01 and the maximum number of iterations to 1000; In each iteration, the two parameters are updated at a fixed learning rate according to the partial derivatives of the current error with respect to the sensitivity coefficient and the background noise offset; The iteration is terminated when the error change for 5 consecutive iterations is less than 0.00001.

6. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The gas spectrum database in step S5 contains characteristic absorption wavelengths and corresponding photoacoustic signal reference spectra of 10 gases, including hydrogen, carbon monoxide, methane, acetylene, ethylene, ethane, carbon dioxide, oxygen, nitrogen and water vapor. The database automatically updates the standard spectrum line data according to the set threshold, and supports users to perform local calibration by injecting gas samples of known concentration. The calibration data is stored in JSON format.

7. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The qualitative classification of the gas in step S5 is specifically as follows: The algorithm combining principal component analysis and support vector machine is used to qualitatively classify gases. The method steps are as follows: The photoacoustic intensity values ​​corresponding to the characteristic wavelengths of the photoacoustic spectroscopy signals were preprocessed and standardized, and the principal component analysis was performed to reduce the dimension, the covariance matrix of the standardized data was calculated, and the eigenvalue decomposition of the matrix was performed to obtain the eigenvalues ​​and corresponding eigenvectors arranged in order of size; Select the first several principal components whose cumulative contribution rate exceeds 95%, and project the original data into a new space formed by the eigenvectors of these principal components to form a low-dimensional data set; The data set is divided into a training set and a test set, with labels corresponding to different gas types. A Gaussian kernel function is selected to map the data to a high-dimensional space. The maximum margin hyperplane is found by solving a convex optimization problem. An optimization algorithm is used to balance the model complexity and classification error. A penalty factor is introduced to adjust the tolerance for misclassified samples, and slack variables are used to process nonlinearly separable data. A "one-to-many" strategy is adopted to train a binary classifier for each type of gas separately, and finally the category of the sample is determined through a voting mechanism. In the model training stage, the parameters are optimized through grid search and cross-validation; the candidate value combinations of penalty factors and kernel function parameters are traversed, and the classification accuracy of each set of parameters is evaluated in combination with cross-validation; After completing the parameter optimization, the test sample is input into the trained model. According to the weighted kernel function calculation results of the support vector and the bias term, the gas category of the sample is determined by the sign function.

8. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: It also includes a temperature and pressure compensation module, which is implemented as follows: Real-time collection of temperature and pressure data in the photoacoustic cell; According to the standard temperature of 298K and the standard pressure of 101.325 kPa, the gas concentration is normalized and corrected by temperature and pressure; When the temperature fluctuation exceeds ±2K or the pressure fluctuation exceeds ±5 kPa, the self-correction algorithm is triggered to recalibrate.

9. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: The triggering logic of the abnormal alarm is: When the concentration of a single gas exceeds the preset threshold, a level 1 alarm is triggered immediately, with the hydrogen threshold being 100ppm, acetylene being 5ppm, and carbon monoxide being 350ppm; When the concentration of three or more gases reaches 50% of the threshold at the same time and lasts for 30 minutes, a level 2 alarm is triggered; The alarm information is uploaded to the cloud platform through the wireless network module, and a diagnostic report including index trend forecast is generated.

10. The method for online detection of gas in transformer oil based on photoacoustic spectroscopy self-calibration according to claim 1, characterized in that: Also includes system self-check function: The laser power is automatically detected at zero o'clock every day, and the backup laser source is switched when the power deviation exceeds ±5%; The light spot position deviation is monitored weekly by a CCD camera. When the deviation exceeds 50 microns, the piezoelectric ceramic regulator is activated to correct the light path. Based on the signal-to-noise ratio, Q value and temperature drift rate parameters, a decision tree model is used to diagnose the fault types of laser aging, microphone failure or gas path blockage.

Images