Gas chromatography detection optimization method and device of transformer, terminal equipment and storage medium

Abstract

The invention discloses a gas chromatography detection optimization method and device of a transformer, terminal equipment and a storage medium. The method comprises the following steps: acquiring gas chromatography original data; carrying out filtering and noise reduction according to the gas chromatography original data to obtain a gas chromatography data sequence; judging whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold value or not according to the gas chromatography data sequence; under the condition that the peak width is smaller than or equal to a preset peak width threshold value, taking the chromatographic peak height of the gas chromatography data sequence as a gas chromatography detection result; under the condition that the peak width is greater than a preset peak width threshold value, judging whether the ratio of the peak width to the peak width of the gas chromatography data sequence is smaller than a preset height-width ratio threshold value or not; if yes, taking the chromatographic peak height as a gas chromatography detection result; and if not, calculating the peak area of the gas chromatography data sequence according to the gas chromatography data sequence, and taking the peak area as a gas chromatography detection result. By implementing the method, the accuracy of a gas chromatography detection result is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of transformer fault monitoring, and in particular to a gas chromatography detection optimization method, device, terminal equipment and storage medium for transformers. Background Art

[0002] Transformers are important equipment in the power system. They play the role of power conversion and hub in the power network, and directly affect the safe operation of the power system. The changes in the oil and gas composition in oil-immersed power transformers are mainly related to the insulating oil and the environmental conditions in which they are located. When a latent fault occurs inside the transformer, under the action of heat and electricity, the transformer oil and solid insulating materials gradually age and decompose, producing different types of gases and dissolving in the transformer oil. By collecting transformer oil samples, using a degassing device to separate the gas dissolved in the oil, and then using gas chromatography to analyze the type, content and proportion of the gas, the operating status and fault type of the transformer can be determined. At present, an important step in gas chromatography is to accurately identify the peaks in the chromatogram. Excessive baseline noise, intra-column factors (such as chromatographic column performance), and extra-column factors (such as the volume of the injection port) will affect the peaks of the chromatogram, resulting in low data recognition accuracy of dissolved gas in transformer oil. Summary of the invention

[0003] The embodiments of the present invention provide a method, an apparatus, a terminal device and a storage medium for optimizing gas chromatography detection of a transformer, which can effectively solve the problem of low accuracy in data recognition of dissolved gas in transformer oil in the prior art.

[0004] An embodiment of the present invention provides a gas chromatography detection optimization method for a transformer, comprising:

[0005] Obtain gas chromatography raw data in real time within a preset period;

[0006] Performing filtering and noise reduction on the gas chromatography raw data to obtain a gas chromatography data sequence after noise reduction;

[0007] Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold;

[0008] When the peak width is less than or equal to the preset peak width threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result;

[0009] In the case where the peak width is greater than a preset peak width threshold, determining whether the peak-to-peak width ratio of the gas chromatographic data sequence is less than a preset height-to-width ratio threshold;

[0010] If yes, the chromatographic peak height of the gas chromatography data sequence is taken as the gas chromatography detection result;

[0011] If not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result.

[0012] Further, filtering and denoising are performed on the gas chromatography raw data to obtain a denoised gas chromatography data sequence, including:

[0013] Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization;

[0014] Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction;

[0015] Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix;

[0016] Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period;

[0017] Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

[0018] Further, performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold comprises:

[0019] Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence;

[0020] identifying peaks of the gas chromatography data sequence based on the first derivative sequence;

[0021] At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence;

[0022] According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

[0023] Furthermore, the method further includes: judging whether the second derivative sequence changes monotonically according to the second derivative sequence;

[0024] If yes, the chromatographic peak height of the gas chromatography data sequence is taken as the gas chromatography detection result;

[0025] If not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result.

[0026] Further, calculating the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence comprises:

[0027] Determining the baseline of the corresponding chromatogram according to the gas chromatography data sequence;

[0028] Obtaining peak boundaries of the chromatogram according to the baseline identification;

[0029] The peak area of ​​the gas chromatography data sequence is calculated according to the peak boundary.

[0030] As an improvement of the above solution, another embodiment of the present invention provides a gas chromatography detection optimization device for a transformer, comprising:

[0031] A chromatographic data acquisition module is used to acquire gas chromatographic raw data in real time within a preset period of time;

[0032] A filtering and denoising module, used for filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence;

[0033] A first judgment module, used for judging the chromatographic peak type according to the gas chromatography data sequence, and judging whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold;

[0034] A first detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak width is less than or equal to a preset peak width threshold;

[0035] A second judgment module is used to judge whether the peak-to-peak width ratio of the gas chromatographic data sequence is less than a preset height-to-width ratio threshold when the peak width is greater than a preset peak width threshold;

[0036] A second detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak-to-peak width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold;

[0037] The third detection optimization module is used to calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence when the peak-to-peak width ratio of the gas chromatography data sequence is greater than or equal to a preset aspect ratio threshold, and use the peak area as the gas chromatography detection result.

[0038] Furthermore, the filtering and denoising module is used to perform filtering and denoising on the gas chromatography raw data to obtain a denoised gas chromatography data sequence;

[0039] Filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence, including:

[0040] Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization;

[0041] Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction;

[0042] Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix;

[0043] Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period;

[0044] Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

[0045] Furthermore, the first judgment module is used to perform chromatographic peak type judgment based on the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold;

[0046] Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold includes:

[0047] Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence;

[0048] identifying peaks of the gas chromatography data sequence based on the first derivative sequence;

[0049] At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence;

[0050] According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

[0051] Another embodiment of the present invention provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, and when the processor executes the computer program, a gas chromatography detection optimization method for a transformer as described in the above embodiment is implemented.

[0052] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the gas chromatography detection optimization method for a transformer described in the above embodiment.

[0053] By implementing the present invention, at least the following beneficial effects are achieved:

[0054] The present invention provides a gas chromatography detection optimization method, device, terminal equipment and storage medium for transformers. The method can acquire gas chromatography raw data in real time within a preset time period; filter and reduce noise according to the gas chromatography raw data to obtain a gas chromatography data sequence after noise reduction; perform chromatographic peak type judgment according to the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold; when the peak width is less than or equal to the preset peak width threshold, use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result; when the peak width is greater than the preset peak width threshold, judge whether the peak-to-peak width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold; if so, use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result; if not, calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence, and use the peak area as the gas chromatography detection result. Through filtering and noise reduction processing, the noise and interference in the gas chromatography raw data can be effectively removed to obtain a smoother gas chromatography data sequence, which is crucial for subsequent peak type judgment, peak height and peak area calculation, thereby improving the accuracy of the entire gas chromatography detection results; at the same time, according to the different chromatographic peak types, the peak height or peak area is used as the gas chromatography detection result, which helps to cope with the influence of different complex factors and improve the accuracy of the gas chromatography detection results under different chromatogram influencing factors. BRIEF DESCRIPTION OF THE DRAWINGS

[0055] Figure 1 It is a flow chart of a gas chromatography detection optimization method for a transformer provided by an embodiment of the present invention;

[0056] Figure 2 It is another flow chart of a gas chromatography detection optimization method for a transformer provided by an embodiment of the present invention;

[0057] Figure 3It is a structural schematic diagram of a gas chromatography detection optimization device for a transformer provided by one embodiment of the present invention. DETAILED DESCRIPTION

[0058] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0059] See also Figure 1 , is a flow chart of a gas chromatography detection optimization method for a transformer provided by an embodiment of the present invention, comprising:

[0060] S1. Real-time acquisition of gas chromatography raw data within a preset period of time;

[0061] S2, filtering and denoising the gas chromatography raw data to obtain a denoised gas chromatography data sequence;

[0062] S3, performing chromatographic peak type judgment according to the gas chromatography data sequence, and judging whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold;

[0063] S4. When the peak width is less than or equal to a preset peak width threshold, taking the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result;

[0064] S5. When the peak width is greater than a preset peak width threshold, determining whether the peak-to-peak width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold;

[0065] S6. If yes, taking the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result;

[0066] S7. If not, calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence, and use the peak area as the gas chromatography detection result.

[0067] Specifically, gas chromatography is based on the difference in the distribution coefficients of different substances between the stationary phase and the mobile phase for separation. The components in the sample are repeatedly distributed in the chromatographic column with the flow of the carrier gas. Due to the different affinities between the two phases, the time for them to flow out of the chromatographic column is also different, thus achieving separation. Common detectors used in gas chromatography detection include flame ionization detector (FID), thermal conductivity detector (TCD), etc. These detectors can convert the outflowing components into electrical signals to draw a chromatogram. Kalman filtering is an efficient recursive filter that can estimate the state of a dynamic system from a series of measurements containing noise. It does not need to store historical states, is simple to calculate, and is suitable for use in embedded systems with limited resources. The basic dynamic model of Kalman filtering can be represented by a Markov chain, which is built on a linear operator disturbed by Gaussian noise. The state of the system is represented by a vector whose elements are real numbers. With each increase in discrete time, this linear operator will act on the current state, produce a new state, and introduce some noise. Traditional Kalman filtering only performs filtering and smoothing on the original data and does not participate in the calculation of the peak value.

[0068] In a preferred embodiment of the present invention, the preset peak width threshold represents the threshold of the peak width in the chromatogram; the preset aspect ratio threshold represents the threshold of the ratio of the peak height to the peak width in the chromatogram; the gas chromatography raw data represents the voltage signal value and other raw data collected from the sensor, which are data that have not been filtered. First, the gas chromatography raw data is acquired in real time within a preset time period, and then filtering and denoising is performed based on the gas chromatography raw data to obtain a gas chromatography data sequence after denoising; a chromatographic peak type judgment is performed based on the gas chromatography data sequence to determine whether the peak width of the gas chromatography data sequence is less than the preset peak width threshold; when the peak width is less than or equal to the preset peak width threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; if Figure 2 As shown, when the peak width is greater than the preset peak width threshold, it is determined whether the peak-to-peak width ratio of the gas chromatography data sequence is less than the preset height-to-width ratio threshold; if so, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; if not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result. After the gas chromatography detection result is obtained, it is provided for subsequent further chromatographic analysis. The chromatographic data is filtered and smoothed, and the peak type is judged to improve the accuracy of peak type recognition, so as to effectively solve the problem of poor data accuracy caused by factors such as the susceptibility to interference and unstable peaks in gas chromatography detection of gas in transformer oil.

[0069] Preferably, filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence comprises:

[0070] Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization;

[0071] Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction;

[0072] Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix;

[0073] Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period;

[0074] Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

[0075] Specifically, the preset time period is divided into multiple sub-periods, and gas chromatography raw data is obtained in each sub-period; the first gas chromatography raw data represents the gas chromatography raw data obtained in the current sub-period; the second gas chromatography raw data represents the gas chromatography raw data randomly selected from the gas chromatography raw data of the sub-period before the current sub-period; the number of first gas chromatography raw data is equal to the number of second gas chromatography raw data. The Kalman filter algorithm is mainly divided into the following two steps. In the prediction step, the state and covariance matrix of the current moment are predicted according to the state equation of the system and the state estimate of the previous moment; in the update step, the Kalman gain is calculated according to the observed value and the predicted value at the current moment, and then the state estimate and the covariance matrix are updated. By repeating these two steps continuously, real-time estimation and updating of the system state can be achieved.

[0076] In a preferred embodiment of the present invention, in the prediction stage of the traditional Kalman filter method, the filter predicts the current state and error based on the prediction results of the previous step. Specifically, the state transfer matrix is ​​multiplied by the state estimate value of the previous moment to obtain the predicted value of the current state, and the process noise covariance matrix is ​​added at the same time. Then, based on the linear stochastic differential equation and the measurement equation, the state prediction process is first considered, assuming that the state space equation of the linear discrete system is:

[0077] Where A is the state matrix; H is the output matrix; X(k) is the system state at time k; Y(k) is the system output at time k, i.e. the observed value; ν(k) is the process noise, which obeys a Gaussian distribution with a mean of 0 and a variance of Qk; ω(k) is the sensor measurement noise, which obeys a Gaussian distribution with a mean of 0 and a variance of Rk; ν(k) and ω(k) are independent of each other.

[0078] Then the state prediction is realized based on the state estimation of the previous period and the state transfer equation, that is, represents the predicted value of the state at time k+1 at time k, Represents the state estimate at time k. The covariance matrix of the prediction process is: P(k+1|k)=AP(k|k)A^T+Qk, where P(k|k) is the state estimate error covariance matrix at time k, and Qk is the covariance matrix of process noise. In the update phase, the filter uses the current measurement and prediction values ​​to calculate the new state value and error. The Kalman gain is a key parameter that determines the weight of the new measurement in the state estimation. The optimal estimate of the current state and the updated value of the error covariance matrix can be calculated using the current measurement, state prediction, and Kalman gain.

[0079] In the state observation update process, the observation prediction value is first calculated based on the current observation value and observation matrix. The observation prediction value is: in, represents the predicted value of the observed value at time k, H is the observation matrix, is the estimated value of the state at time k.

[0080] The covariance matrix of observation prediction is: S(k)=HP(k|k)H T +Rk, where P(k|k) is the state estimation error covariance matrix at time k, and Rk is the covariance matrix of the measurement noise.

[0081] Kalman gain is expressed as: K(k) = P(k|k)H T S(k) -1 , where P(k|k) is the state estimation error covariance matrix at time k, H is the observation matrix, and S(k) is the covariance matrix of observation prediction.

[0082] The state update formula is:

[0083] The covariance update formula is: P(k|k)=(IK(k)H)P(k|k-1), where I is the identity matrix.

[0084] In a preferred embodiment of the present invention, the above filtering calculation process is performed on a series of limited data, such as N data D1, D2, ... Dn sampled at the same time. After the above process, the filtering processing result is output. In the improved Kalman filtering method of this embodiment, after the above process is completed, the back end adds M newly collected raw data (M < N), and then randomly selects M raw data from the front end of the aforementioned N data, and finally repeats the aforementioned traditional Kalman filtering process for the newly obtained N mixed data. The size of M depends on the noise level of the current system raw data. The greater the noise, the smaller the value of M, which can be determined according to the actual situation. That is, based on the initialized state estimation, observation matrix and covariance matrix, the filtering update operation is performed according to the current gas chromatography raw data, the current state estimation and the current covariance matrix until the preset number of filtering updates is reached to obtain the gas chromatography data sequence after noise reduction. According to the observation matrix and the current covariance matrix, the covariance matrix is ​​updated; according to the observation matrix, the current estimate and the current covariance matrix, the state estimate is updated; according to the first gas chromatography raw data acquired in the current sub-period and the second gas chromatography raw data randomly selected in the previous period, the current gas chromatography raw data is updated; wherein the preset period is divided into a plurality of sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and the covariance matrix, respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

[0085] Schematically, performing chromatographic peak type judgment according to the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold includes:

[0086] Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence;

[0087] identifying peaks of the gas chromatography data sequence based on the first derivative sequence;

[0088] At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence;

[0089] According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

[0090] In a preferred embodiment of the present invention, a first derivative is calculated based on the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence; the first derivative sequence can be used to determine whether a peak appears. If the first derivative changes continuously and monotonically within a certain period of time and passes through zero, such as increasing first and then decreasing and passing through zero, and then continuing to decrease and then increasing to near zero, it can be considered that a peak appears, and the peak value of the gas chromatography data sequence can be identified based on the first derivative sequence. After the peak value is identified, a second derivative is performed at the peak value based on the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence, and based on the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold.

[0091] Specifically, judging whether the second derivative sequence changes monotonically according to the second derivative sequence;

[0092] If yes, the chromatographic peak height of the gas chromatography data sequence is taken as the gas chromatography detection result;

[0093] If not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result.

[0094] If the second derivative sequence changes monotonically, it is considered a normal peak. If there is a non-monotonic change, it may be a shoulder peak or a double peak, which are both classified as abnormal peak types.

[0095] Preferably, calculating the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence comprises:

[0096] Determining the baseline of the corresponding chromatogram according to the gas chromatography data sequence;

[0097] Obtaining peak boundaries of the chromatogram according to the baseline identification;

[0098] The peak area of ​​the gas chromatography data sequence is calculated according to the peak boundary.

[0099] By implementing this embodiment, gas chromatography raw data is acquired in real time within a preset time period; filtering and denoising are performed on the gas chromatography raw data to obtain a denoised gas chromatography data sequence; chromatographic peak type judgment is performed on the gas chromatography data sequence to determine whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold; when the peak width is less than or equal to the preset peak width threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; when the peak width is greater than the preset peak width threshold, it is determined whether the peak-to-peak-width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold; if so, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; if not, the peak area of ​​the gas chromatography data sequence is calculated based on the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result. Through filtering and noise reduction processing, the noise and interference in the gas chromatography raw data can be effectively removed to obtain a smoother gas chromatography data sequence, which is crucial for subsequent peak type judgment, peak height and peak area calculation, thereby improving the accuracy of the entire gas chromatography detection results; at the same time, according to the different chromatographic peak types, the peak height or peak area is used as the gas chromatography detection result, which helps to cope with the influence of different complex factors and improve the accuracy of the gas chromatography detection results under different chromatogram influencing factors.

[0100] See also Figure 3 , is a schematic diagram of the structure of a gas chromatography detection optimization device for a transformer provided by an embodiment of the present invention, comprising:

[0101] A chromatographic data acquisition module is used to acquire gas chromatographic raw data in real time within a preset period of time;

[0102] A filtering and denoising module, used for filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence;

[0103] A first judgment module, used for judging the chromatographic peak type according to the gas chromatography data sequence, and judging whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold;

[0104] A first detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak width is less than or equal to a preset peak width threshold;

[0105] A second judgment module is used to judge whether the peak-to-peak width ratio of the gas chromatographic data sequence is less than a preset height-to-width ratio threshold when the peak width is greater than a preset peak width threshold;

[0106] A second detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak-to-peak width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold;

[0107] The third detection optimization module is used to calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence when the peak-to-peak width ratio of the gas chromatography data sequence is greater than or equal to a preset aspect ratio threshold, and use the peak area as the gas chromatography detection result.

[0108] Specifically, the filtering and denoising module is used to perform filtering and denoising on the gas chromatography raw data to obtain a denoised gas chromatography data sequence;

[0109] Filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence, including:

[0110] Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization;

[0111] Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction;

[0112] Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix;

[0113] Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period;

[0114] Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

[0115] Preferably, the first judgment module is used to perform chromatographic peak type judgment based on the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold;

[0116] Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold includes:

[0117] Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence;

[0118] identifying peaks of the gas chromatography data sequence based on the first derivative sequence;

[0119] At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence;

[0120] According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

[0121] The present invention provides a gas chromatography detection optimization device for a transformer. According to a chromatographic data acquisition module, gas chromatography raw data is acquired in real time within a preset time period; in a filtering and noise reduction module, filtering and noise reduction are performed according to the gas chromatography raw data to obtain a gas chromatography data sequence after noise reduction; in a first judgment module, chromatographic peak type judgment is performed according to the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold; through the first detection optimization module, when the peak width is less than or equal to the preset peak width threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; through the second judgment module, Module, when the peak width is greater than the preset peak width threshold, determine whether the peak-to-peak width ratio of the gas chromatography data sequence is less than the preset height-to-width ratio threshold; according to the second detection optimization module, when the peak-to-peak width ratio of the gas chromatography data sequence is less than the preset height-to-width ratio threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; through the third detection optimization module, when the peak-to-peak width ratio of the gas chromatography data sequence is greater than or equal to the preset height-to-width ratio threshold, calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence, and use the peak area as the gas chromatography detection result. Through filtering and noise reduction processing, the noise and interference in the gas chromatography raw data are effectively removed to obtain a smoother gas chromatography data sequence, which is crucial for subsequent peak type judgment, peak height and peak area calculation, thereby improving the accuracy of the entire gas chromatography detection result; at the same time, according to the different chromatographic peak types, the peak height or peak area is used as the gas chromatography detection result, which helps to deal with the influence of different complex factors and improve the accuracy of the gas chromatography detection result under different chromatogram influencing factors.

[0122] It should be noted that the device embodiments described above are merely schematic, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. In addition, in the accompanying drawings of the device embodiments provided by the present invention, the connection relationship between the modules indicates that there is a communication connection between them, which may be specifically implemented as one or more communication buses or signal lines. A person of ordinary skill in the art may understand and implement it without paying any creative effort.

[0123] Those skilled in the art can clearly understand that, for the sake of convenience and brevity, the specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0124] Another embodiment of the present invention further provides a terminal device, including a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein the processor implements a gas chromatography detection optimization method for a transformer as described in the above embodiment when executing the computer program. The terminal device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The terminal device may include, but is not limited to, a processor and a memory.

[0125] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the terminal device, and uses various interfaces and lines to connect various parts of the entire terminal device.

[0126] The memory can be used to store the computer program, and the processor realizes various functions of the terminal device by running or executing the computer program stored in the memory and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, at least one application required for a function, etc.; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device or other volatile solid-state storage device.

[0127] Another embodiment of the present invention provides a computer-readable storage medium, which includes a stored computer program, wherein when the computer program is running, the device where the computer-readable storage medium is located is controlled to execute the gas chromatography detection optimization method for a transformer described in the above embodiment.

[0128] The storage medium is a computer-readable storage medium, and the computer program is stored in the computer-readable storage medium. When the computer program is executed by the processor, the steps of each of the above-mentioned method embodiments can be implemented. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium.

[0129] The above is a preferred embodiment of the present invention. It should be pointed out that a person skilled in the art can make several improvements and modifications without departing from the principle of the present invention. These improvements and modifications are also considered to be within the scope of protection of the present invention.

Claims

1. A gas chromatography detection optimization method for transformers, characterized in that: include: Obtain gas chromatography raw data in real time within a preset period; Performing filtering and noise reduction on the gas chromatography raw data to obtain a gas chromatography data sequence after noise reduction; Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold; When the peak width is less than or equal to the preset peak width threshold, the chromatographic peak height of the gas chromatography data sequence is used as the gas chromatography detection result; In the case where the peak width is greater than a preset peak width threshold, determining whether the peak-to-peak width ratio of the gas chromatographic data sequence is less than a preset height-to-width ratio threshold; If yes, the chromatographic peak height of the gas chromatography data sequence is taken as the gas chromatography detection result; If not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result.

2. A gas chromatography detection optimization method for transformers as claimed in claim 1, characterized in that: Filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence, including: Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization; Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction; Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix; Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period; Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

3. The gas chromatography detection optimization method for a transformer according to claim 1, characterized in that: Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold includes: Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence; identifying peaks of the gas chromatography data sequence based on the first derivative sequence; At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence; According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

4. A gas chromatography detection optimization method for transformers as claimed in claim 3, characterized in that: Also includes: According to the second derivative sequence, determining whether the second derivative sequence changes monotonically; If yes, the chromatographic peak height of the gas chromatography data sequence is taken as the gas chromatography detection result; If not, the peak area of ​​the gas chromatography data sequence is calculated according to the gas chromatography data sequence, and the peak area is used as the gas chromatography detection result.

5. The gas chromatography detection optimization method for transformer according to claim 1, characterized in that: Calculating the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence comprises: Determining the baseline of the corresponding chromatogram according to the gas chromatography data sequence; Obtaining peak boundaries of the chromatogram according to the baseline identification; The peak area of ​​the gas chromatography data sequence is calculated according to the peak boundary.

6. A gas chromatography detection optimization device for a transformer, characterized in that: include: A chromatographic data acquisition module is used to acquire gas chromatographic raw data in real time within a preset period of time; A filtering and denoising module, used for filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence; A first judgment module, used for judging the chromatographic peak type according to the gas chromatography data sequence, and judging whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold; A first detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak width is less than or equal to a preset peak width threshold; A second judgment module is used to judge whether the peak-to-peak width ratio of the gas chromatographic data sequence is less than a preset height-to-width ratio threshold when the peak width is greater than a preset peak width threshold; A second detection optimization module, configured to use the chromatographic peak height of the gas chromatography data sequence as the gas chromatography detection result when the peak-to-peak width ratio of the gas chromatography data sequence is less than a preset height-to-width ratio threshold; The third detection optimization module is used to calculate the peak area of ​​the gas chromatography data sequence according to the gas chromatography data sequence when the peak-to-peak width ratio of the gas chromatography data sequence is greater than or equal to a preset aspect ratio threshold, and use the peak area as the gas chromatography detection result.

7. A gas chromatography detection optimization device for a transformer as claimed in claim 6, characterized in that: The filtering and denoising module is used to perform filtering and denoising on the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence; Filtering and denoising the gas chromatographic raw data to obtain a denoised gas chromatographic data sequence, including: Get the state estimate, observation matrix and covariance matrix of Kalman filter initialization; Performing a filtering and updating operation according to the current gas chromatographic raw data, the current state estimation and the current covariance matrix until a preset number of filtering and updating times is reached, thereby obtaining a gas chromatographic data sequence after noise reduction; Update the covariance matrix based on the observation matrix and the current covariance matrix; Update the state estimate based on the observation matrix, the current estimate, and the current covariance matrix; Update the current gas chromatographic raw data according to the first gas chromatographic raw data acquired in the current sub-period and the second gas chromatographic raw data randomly selected in the previous period; Among them, the preset time period is divided into multiple sub-periods; the current state estimate and the current covariance matrix during the first filtering update operation are the initialized state estimate and covariance matrix respectively; the number of the first gas chromatography raw data is equal to the number of the second gas chromatography raw data.

8. The gas chromatography detection optimization device for transformer according to claim 6, characterized in that: The first judgment module is used to perform chromatographic peak type judgment based on the gas chromatography data sequence to judge whether the peak width of the gas chromatography data sequence is less than a preset peak width threshold; Performing chromatographic peak type judgment according to the gas chromatographic data sequence to judge whether the peak width of the gas chromatographic data sequence is less than a preset peak width threshold includes: Calculating a first-order derivative according to the gas chromatography data sequence to obtain a first derivative sequence of the gas chromatography data sequence; identifying peaks of the gas chromatography data sequence based on the first derivative sequence; At the peak, performing a second-order derivative according to the first derivative sequence to obtain a second derivative sequence of the gas chromatography data sequence; According to the first derivative sequence and the second derivative sequence, it is determined whether the peak width of the gas chromatography data sequence is smaller than a preset peak width threshold.

9. A terminal device, characterized in that: The method comprises a processor, a memory, and a computer program stored in the memory and configured to be executed by the processor, wherein when the processor executes the computer program, a gas chromatography detection optimization method for a transformer as claimed in any one of claims 1 to 5 is implemented.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium includes a stored computer program, wherein when the computer program is executed, the device where the computer-readable storage medium is located is controlled to execute a gas chromatography detection optimization method for a transformer as described in any one of claims 1 to 5.

Images