On-line monitoring and fault diagnosis method for on-load tap-changer of transformer

Abstract

The invention provides a transformer on-load tap-changer on-line monitoring and fault diagnosis method, and relates to the technical field of electrics. The method comprises the following steps: acquiring electric arc energy and on-load tap-changer contact position information generated during the switching action of a transformer on-load tap-changer; determining a switching performance score; acquiring operation data of the on-load tap-changer of the transformer; inputting the operation data into a trained fault probability prediction model, and obtaining predicted fault probability data during the switching action of the transformer on-load tap-changer; determining whether the transformer on-load tap-changer meets a preset target condition or not; if the on-load tap-changer of the transformer meets the preset target condition, determining that the state of the on-load tap-changer of the transformer is a normal state; and if the transformer on-load tap-changer does not meet the preset target condition, determining that the state of the transformer on-load tap-changer is a fault state. According to the invention, the state of the on-load tap-changer can be comprehensively monitored according to the switching performance and the predicted fault probability.

Description

Technical Field

[0001] The present invention relates to the field of electrical technology, and in particular to an on-line monitoring and fault diagnosis method for a on-load tap-changer of a transformer. Background Art

[0002] In the related art, CN113267724A relates to an on-line monitoring system for an on-load tap-changer of a transformer. The system includes: a plurality of signal acquisition devices and a processing device; the plurality of signal acquisition devices are respectively arranged corresponding to a plurality of main contacts of the on-load tap-changer, and the plurality of signal acquisition devices are used to respectively acquire the optical signals generated when the corresponding main contacts perform disconnection operations, and convert the optical signals into electrical signals; the processing device is used to receive the plurality of electrical signals sent by the plurality of signal acquisition devices, and output a warning message when the amplitude of at least one of the plurality of electrical signals is greater than a preset amplitude threshold. The monitoring result provided by this solution is more accurate; and the system can monitor the on-load tap-changer under the condition that the transformer does not stop, does not affect the normal operation of the transformer, can monitor the on-load tap-changer in real time, improves the monitoring sensitivity of the on-load tap-changer, and can effectively monitor the faults of the on-load tap-changer.

[0003] CN113960463A discloses an on-line monitoring and fault diagnosis method for an on-load tap-changer of a voltage regulating transformer. The method includes: collecting the vibration acoustic fingerprint signal and the driving motor current signal of the on-load tap-changer; performing data analysis on the vibration acoustic fingerprint signal and the driving motor current signal to obtain a signal analysis result; extracting characteristic parameters for fault diagnosis of the on-load tap-changer according to the signal analysis result; combining the characteristic parameters, fault data, factory data and historical data to obtain a fault diagnosis result of the on-load tap-changer. This solution can realize the status monitoring and fault diagnosis of the on-load tap-changer of the voltage regulating transformer according to the vibration acoustic fingerprint and the driving motor current under the live state, which not only does not affect the normal operation of the transformer, has no electrical connection with the equipment, but also has the advantages of high safety and reliability.

[0004] Therefore, in the related art, although the status monitoring of the on-load tap-changer of the transformer can be realized, the related art does not consider the influence of switching performance and predicted fault probability on the fault diagnosis result, that is, the status of the on-load tap-changer cannot be comprehensively monitored according to the switching performance and predicted fault probability. Summary of the Invention

[0005] The present invention provides an on-line monitoring and fault diagnosis method for an on-load tap-changer of a transformer, which can solve the technical problem that the related art cannot comprehensively monitor the status of the on-load tap-changer according to the switching performance and predicted fault probability.

[0006] According to the present invention, there is provided an on-line monitoring and fault diagnosis method for a on-load tap-changer of a transformer, including:

[0007] Obtaining the arc energy generated when the on-load tap-changer of the transformer switches and the contact position information of the on-load tap-changer during the current monitoring period;

[0008] Determining a switching performance score according to the arc energy and the contact position information of the on-load tap-changer;

[0009] During the current monitoring period, obtaining the operating data of the on-load tap-changer of the transformer, wherein the operating data includes the vibration and acoustic signal, the motor current signal and the contact temperature generated when the on-load tap-changer of the transformer switches;

[0010] Inputting the operating data into a trained fault probability prediction model to obtain the predicted fault probability data when the on-load tap-changer of the transformer switches during the current monitoring period;

[0011] Determining whether the on-load tap-changer of the transformer meets a preset target condition according to the predicted fault probability data and the switching performance score;

[0012] If the on-load tap-changer of the transformer meets the preset target condition, determining that the state of the on-load tap-changer of the transformer is a normal state;

[0013] If the on-load tap-changer of the transformer does not meet the preset target condition, determining that the state of the on-load tap-changer of the transformer is a fault state.

[0014] Further, determining the switching performance score according to the arc energy and the contact position information of the on-load tap-changer includes:

[0015] Setting a normal range of the arc energy;

[0016] Obtaining the voltage value corresponding to the contact position information of the on-load tap-changer;

[0017] Setting the voltage value corresponding to the target tap position of the on-load tap-changer of the transformer as the voltage value corresponding to the target position information;

[0018] Determining the switching performance score according to the arc energy, the voltage value corresponding to the contact position information of the on-load tap-changer, the normal range of the arc energy and the voltage value corresponding to the target position information.

[0019] Further, determining the switching performance score according to the arc energy, the voltage value corresponding to the contact position information of the on-load tap-changer, the normal range of the arc energy and the voltage value corresponding to the target position information includes:

[0020] According to the formula ,

[0021] Determine the switching performance score , where is the arc energy generated during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is the minimum value of the arc energy, is the maximum value of the arc energy, is the voltage value corresponding to the on-load tap-changer contact position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is the voltage value corresponding to the target position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, and both i and N are positive integers, and if is a conditional function.

[0022] Furthermore, the training steps of the fault probability prediction model include:

[0023] Obtain the historical operation data of the on-load tap-changer of the transformer in the historical monitoring period, where the historical operation data includes the historical vibration acoustic signal, historical motor current signal, and historical contact temperature generated during the switching operation of the on-load tap-changer of the transformer;

[0024] Obtain the historical fault probability data during the switching operation of the on-load tap-changer of the transformer in multiple historical monitoring periods;

[0025] Process the historical operation data through the fault probability prediction model to obtain the historical predicted fault probability data during the switching operation of the on-load tap-changer of the transformer in multiple historical monitoring periods;

[0026] Determine the loss function of the fault probability prediction model according to the historical operation data, the historical fault probability data, and the historical predicted fault probability data;

[0027] Train the fault probability prediction model according to the loss function of the fault probability prediction model to obtain the trained fault probability prediction model.

[0028] Furthermore, determining the loss function of the fault probability prediction model according to the historical operation data, the historical fault probability data, and the historical predicted fault probability data includes:

[0029] According to the formula ,

[0030] Determine the loss function of the fault probability prediction model , where is the historical fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period, is the historical predicted fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period, is the historical vibration and acoustic signal when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period, is the normal vibration and acoustic signal when the on-load tap-changer of the transformer makes a switching operation, is the historical motor current signal when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period, is the normal motor current signal when the on-load tap-changer of the transformer makes a switching operation, is the historical contact temperature when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period, is the normal contact temperature when the on-load tap-changer of the transformer makes a switching operation, is the number of historical monitoring periods in the s-th training batch, S is the number of training batches, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, h ≤ , s ≤ S, and i, h, s, N, and S are all positive integers.

[0031] Further, according to the predicted fault probability data and the switching performance score, determining whether the on-load tap-changer of the transformer meets the preset target conditions includes:

[0032] Setting a fault probability threshold and a switching performance score threshold;

[0033] According to the predicted fault probability data, the switching performance score, the fault probability threshold, and the switching performance score threshold, determining whether the on-load tap-changer of the transformer meets the preset target conditions.

[0034] Further, according to the predicted fault probability data, the switching performance score, the fault probability threshold, and the switching performance score threshold, determining whether the on-load tap-changer of the transformer meets the preset target conditions includes:

[0035] According to the formula , ,

[0036] determining the first condition C1 and the second condition C2, where, is the predicted fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the current monitoring period, is the failure probability threshold, and F is a piecewise function obtained by comparing the predicted failure probability data at the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period with the failure probability threshold. is the preset average failure probability data within a monitoring period. is the switching performance score. is the switching performance score threshold, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, and both i and N are positive integers. The first condition C1 and the second condition C2 are the preset target conditions.

[0037] When the first condition C1 and the second condition C2 are both satisfied, it is determined that the on-load tap-changer of the transformer meets the preset target conditions.

[0038] Technical effects: According to the present invention, the switching performance of the on-load tap-changer is comprehensively monitored through the arc energy and the contact position information, so as to evaluate the state of the on-load tap-changer. By analyzing the operation data through the trained fault probability prediction model, the fault probability of the on-load tap-changer of the transformer can be predicted, which helps the normal operation of the on-load tap-changer of the transformer and timely warning when a fault occurs, reduces the risk of fault occurrence, and improves the reliability and stability of the on-load tap-changer of the transformer. When determining the switching performance score, the switching performance score can be determined through the arc energy, the voltage value corresponding to the contact position information of the on-load tap-changer, the normal range of the arc energy, and the voltage value corresponding to the target position information. The two parameters of the arc energy and the voltage value corresponding to the contact position information respectively reflect the electrical performance and mechanical performance during the switching process of the switch, improving the comprehensiveness and reliability of the switching performance score. When determining the loss function of the fault probability prediction model, the influence of the historical contact temperature on the fault probability can be used to determine the influence of the above data on the error of the historical predicted fault probability data. Then, based on this influence and the relative error between the historical fault probability data and the historical predicted fault probability data, and based on the characteristics that the more similar the vibration acoustic signal and the historical motor current signal are to the normal vibration acoustic signal and the normal motor current signal during the switching operation of the on-load tap-changer of the transformer, the greater the reference value, and the lower the accuracy with the shorter time interval from the first training batch, weights are set. Thus, the errors output by the fault probability prediction model during multiple switching operations of the on-load tap-changer of the transformer in each historical monitoring period of the s-th batch are weighted and summed to obtain the loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and enhancing the accuracy of the fault probability prediction model. When determining whether the on-load tap-changer of the transformer meets the preset target conditions, the first condition and the second condition can be determined based on the predicted fault probability data, the switching performance score, the fault probability threshold, and the switching performance score threshold. When both the first condition and the second condition are met, it can be determined that the on-load tap-changer of the transformer meets the preset target conditions. Quantifying the predicted fault probability data and the switching performance score improves the accuracy of judging the preset target conditions and realizes the comprehensive evaluation of the state of the on-load tap-changer of the transformer. Description of the Drawings

[0039] Figure 1 Exemplarily shows a schematic flow chart of the on-line monitoring and fault diagnosis method for the on-load tap-changer of a transformer according to an embodiment of the present invention. Detailed Embodiments

[0040] Hereinafter, the technical solutions of the present invention will be described in detail with specific embodiments. These specific embodiments can be combined with each other, and the same or similar concepts or processes may not be repeated in some embodiments.

[0041] Figure 1 Exemplarily shown is a schematic flow diagram of an on-line monitoring and fault diagnosis method for a on-load tap-changer of a transformer according to an embodiment of the present invention. The method includes:

[0042] Step S101, obtaining the arc energy generated when the on-load tap-changer of the transformer switches and the contact position information of the on-load tap-changer during the current monitoring period;

[0043] Step S102, determining a switching performance score according to the arc energy and the contact position information of the on-load tap-changer;

[0044] Step S103, obtaining the operation data of the on-load tap-changer of the transformer during the current monitoring period, where the operation data includes the vibration and acoustic signals, motor current signals, and contact temperatures generated when the on-load tap-changer of the transformer switches;

[0045] Step S104, inputting the operation data into a trained fault probability prediction model to obtain the predicted fault probability data when the on-load tap-changer of the transformer switches during the current monitoring period;

[0046] Step S105, determining whether the on-load tap-changer of the transformer meets the preset target conditions according to the predicted fault probability data and the switching performance score;

[0047] Step S106, if the on-load tap-changer of the transformer meets the preset target conditions, determining that the state of the on-load tap-changer of the transformer is a normal state;

[0048] Step S107, if the on-load tap-changer of the transformer does not meet the preset target conditions, determining that the state of the on-load tap-changer of the transformer is a fault state.

[0049] According to the on-line monitoring and fault diagnosis method for the on-load tap-changer of the transformer according to the embodiment of the present invention, through the arc energy and contact position information, the switching performance of the on-load tap-changer is comprehensively monitored, so as to evaluate the state of the on-load tap-changer. By analyzing the operation data through a trained fault probability prediction model, the fault probability of the on-load tap-changer of the transformer can be predicted, which helps the normal operation of the on-load tap-changer of the transformer and timely warning when a fault occurs, reduces the risk of fault occurrence, and improves the reliability and stability of the on-load tap-changer of the transformer.

[0050] According to an embodiment of the present invention, in step S101, each monitoring period can be set to half an hour, one hour, etc., and the present invention does not limit this. The arc energy is the energy generated by the arc discharge between the contacts of the on-load tap-changer during the switching process of the on-load tap-changer. The on-load tap-changer can be equipped with a position sensor (such as an encoder, a potentiometer or an optoelectronic sensor) for real-time feedback of the position of the contacts of the on-load tap-changer. Connecting a voltage sensor and a current sensor to the on-load tap-changer of the transformer can accurately record the arc voltage and arc current during the arc discharge, and then calculate the arc energy by integrating the product of the arc current and the arc voltage.

[0051] According to an embodiment of the present invention, in step S102, a switching performance score is determined based on the arc energy and the contact position information of the on-load tap-changer.

[0052] According to an embodiment of the present invention, step S102 includes: setting a normal range of the arc energy; obtaining the voltage value corresponding to the contact position information of the on-load tap-changer; setting the voltage value corresponding to the target tap position of the on-load tap-changer of the transformer as the voltage value corresponding to the target position information; and determining a switching performance score based on the arc energy, the voltage value corresponding to the contact position information of the on-load tap-changer, the normal range of the arc energy, and the voltage value corresponding to the target position information.

[0053] According to an embodiment of the present invention, a normal range of the arc energy is set. For example, for a small or low-voltage switch: the normal range of the arc energy of the on-load tap-changer of the transformer is 0 to 100 J; for a large or high-voltage switch: the normal range of the arc energy of the on-load tap-changer of the transformer is 0 to 200 J. While the position sensor obtains the contact position information of the on-load tap-changer, it can also output the voltage value corresponding to the contact position information of the on-load tap-changer. For example, the potentiometer will output a voltage signal corresponding to the position. If the voltage range of the position signal is 0 V to 10 V, the tap position number of the on-load tap-changer of the transformer is 1 to 10, and the corresponding contact position information of the on-load tap-changer is 7.5, then the measured output voltage (the voltage value corresponding to the contact position information of the on-load tap-changer) is 7.5 V. Setting the voltage value corresponding to the target tap position of the on-load tap-changer of the transformer as the voltage value corresponding to the target position information. For example, if the target tap position for the switching of the on-load tap-changer of the transformer is 5, then the voltage value corresponding to the target position information is 5 V. When the measured output voltage (the voltage value corresponding to the contact position information of the on-load tap-changer) is 4.8 V, a position deviation will occur.

[0054] According to an embodiment of the present invention, a switching performance score is determined based on the arc energy, the voltage value corresponding to the on-load tap-changer contact position information, the normal range of the arc energy, and the voltage value corresponding to the target position information, including: determining the switching performance score according to formula (1) , (1),

[0055] wherein, is the arc energy generated during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is the minimum value of the arc energy, is the maximum value of the arc energy, is the voltage value corresponding to the on-load tap-changer contact position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is the voltage value corresponding to the target position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, and both i and N are positive integers, and if is a conditional function.

[0056] According to an embodiment of the present invention, in formula (1), when the arc energy generated during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period is within the normal range of the arc energy, the value of the conditional function is 1, otherwise, the value of the conditional function is 0. When the arc energy exceeds the normal range of the arc energy, the contact wears severely, and the switching performance of the on-load tap-changer of the transformer is worse. represents averaging the conditional functions corresponding to the arc energy generated during each switching operation of the on-load tap-changer of the transformer in the current monitoring period, and the ratio of the switching operations with the arc energy within the normal range of the arc energy can be obtained. The larger this ratio is, the more normal the arc energy values are, and the better the switching performance of the on-load tap-changer of the transformer. is the relative difference between the voltage value corresponding to the on-load tap-changer contact position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period and the voltage value corresponding to the target position information during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is 1 minus the average value of this relative difference. The larger this average value is, the less the deviation between the measured position (on-load tap-changer contact position information) and the target position information, and the better the switching performance of the on-load tap-changer of the transformer. Multiplying the above two items, namely, and gives the switching performance score. The larger this switching performance score is, the better the switching performance of the on-load tap-changer of the transformer.

[0057] In this way, the switching performance score can be determined based on the arc energy, the voltage value corresponding to the on-load tap-changer contact position information, the normal range of the arc energy, and the voltage value corresponding to the target position information. The two parameters of the arc energy and the voltage value corresponding to the contact position information respectively reflect the electrical performance and mechanical performance during the switch switching process, improving the comprehensiveness and reliability of the switching performance score.

[0058] According to an embodiment of the present invention, in step S103, the acceleration sensor is installed on the outer side wall of the on-load tap-changer of the transformer. It is selected at a position 15 - 20 cm downward parallel to the vertical drive rod from the top. The vibration acoustic signal is the mechanical vibration acoustic signal generated by the on-load tap-changer of the transformer during the switching operation, which can reflect the mechanical performance and operating state of the switch. The motor current signal is the working current of the motor during the switching operation of the on-load tap-changer of the transformer. By monitoring the change of the motor current through the current transformer, the operating state and load condition of the motor can be understood. The contact temperature is collected by the temperature sensor, and the change of the contact temperature can reflect the contact condition and thermal load state of the contact, which is of great significance for evaluating the electrical performance and safety of the on-load tap-changer.

[0059] According to an embodiment of the present invention, in step S104, the operation data is input into the trained fault probability prediction model. The fault probability prediction model can be a neural network model, which is trained based on a large amount of sample data through machine learning or deep learning techniques to obtain the predicted fault probability data when the on-load tap-changer of the transformer switches during the current monitoring period.

[0060] According to an embodiment of the present invention, the above-mentioned fault probability prediction model can be trained before use. The training steps of the fault probability prediction model include: obtaining the historical operation data of the on-load tap-changer of the transformer in the historical monitoring period, where the historical operation data includes the historical vibration acoustic signal, historical motor current signal, and historical contact temperature generated when the on-load tap-changer of the transformer switches; obtaining the historical fault probability data when the on-load tap-changer of the transformer switches in multiple historical monitoring periods; processing the historical operation data through the fault probability prediction model to obtain the historical predicted fault probability data when the on-load tap-changer of the transformer switches in multiple historical monitoring periods; determining the loss function of the fault probability prediction model according to the historical operation data, the historical fault probability data, and the historical predicted fault probability data; training the fault probability prediction model according to the loss function of the fault probability prediction model to obtain the trained fault probability prediction model.

[0061] According to an embodiment of the present invention, the on-load tap-changer switching operations in multiple historical monitoring cycles are divided into different training batches, and the number of historical monitoring cycles in each training batch is the same, so as to train the fault probability prediction model for different training batches. For example, , where H is the number of historical monitoring cycles, , , …, are the numbers of historical monitoring cycles in the 1st, 2nd, …, Sth training batches respectively. In each historical monitoring cycle, historical fault probability data can be obtained from the recorded occurrence probabilities of on-load tap-changer faults. For example, if a fault accident occurs during the on-load tap-changer switching operation, the historical fault probability data is 1; if no fault accident occurs during the on-load tap-changer switching operation, the historical fault probability data is 0. Among them, the fault accidents include contact wear, synchronization problems, drive mechanism problems, brake failures, short circuits in the power system, fires, etc. The greater the difference between the vibration acoustic signal and the motor current signal generated during the on-load tap-changer switching operation and the normal vibration acoustic signal and normal motor current signal generated during the on-load tap-changer switching operation, the higher the fault occurrence probability during the on-load tap-changer switching operation. For example, if the waveform of the vibration acoustic signal is distorted, with an increase in high-frequency components and a decrease in low-frequency components, etc., and the difference from the normal vibration acoustic signal is greater, the occurrence probability of faults such as increased contact looseness, wear or jamming of the on-load tap-changer increases. If the amplitude of the motor current signal increases or decreases and the phase shifts, the occurrence probability of faults such as motor overload, short circuit or open circuit increases. The higher the contact temperature, the higher the fault occurrence probability during the on-load tap-changer switching operation. For example, high temperature will accelerate the oxidation corrosion and mechanical deformation of the contact surface, resulting in melting and sputtering of the contact material, and in severe cases, the contact will be burned out. The fault probability prediction model can predict the historical predicted fault probability data during the on-load tap-changer switching operations in multiple historical monitoring cycles based on the above relationships between the vibration acoustic signal, the motor current signal, the contact temperature and the fault occurrence probability during the on-load tap-changer switching operation, and based on the historical operation data. The loss function is determined according to the relative difference between the historical fault probability data and the historical predicted fault probability data. By performing feedback adjustment on the loss function, the trained fault probability prediction model is obtained.

[0062] According to an embodiment of the present invention, determining the loss function of the fault probability prediction model according to the historical operation data, the historical fault probability data and the historical predicted fault probability data includes: determining the loss function of the fault probability prediction model according to formula (2) , (2),

[0063] where, is the historical fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the historical predicted fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the historical vibration and acoustic signal when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the normal vibration and acoustic signal when the on-load tap-changer of the transformer makes a switching operation. is the historical motor current signal when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the normal motor current signal when the on-load tap-changer of the transformer makes a switching operation. is the historical contact temperature when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the normal contact temperature when the on-load tap-changer of the transformer makes a switching operation. is the number of historical monitoring periods in the s-th training batch, S is the number of training batches, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, h ≤ , s ≤ S, and i, h, s, N, and S are all positive integers.

[0064] According to an embodiment of the present invention, in formula (2), is the relative difference between the historical fault probability data and the historical predicted fault probability data when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the ratio of the historical contact temperature to the normal contact temperature when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. The larger this ratio is, the higher the historical contact temperature is, and the greater the probability of a fault occurring when the on-load tap-changer of the transformer makes a switching operation. That is, the historical contact temperature is positively correlated with the fault probability. When the historical contact temperature is higher, it will accelerate the oxidation corrosion and mechanical deformation on the surface of the contact, resulting in melting and sputtering of the contact material, and in severe cases, faults such as contact burnout will occur. Therefore, the larger the historical contact temperature is relative to the normal contact temperature, that is, the larger the value of, the greater the impact on the error of the historical predicted fault probability data. is the similarity between the historical vibration and acoustic signal and the normal vibration and acoustic signal when the on-load tap-changer of the transformer makes the i-th switching operation in the h-th historical monitoring period. is the similarity between the historical motor current signal at the i-th switching operation of the on-load tap-changer of the transformer in the h-th historical monitoring period and the normal motor current signal at the switching operation of the on-load tap-changer of the transformer. To achieve a similar fault probability detection effect, if the historical vibration-acoustic signal and the historical motor current signal are closer to the normal vibration-acoustic signal and the normal motor current signal, that is, and the larger the value of, the more similar the conditions of the vibration-acoustic signal and the historical motor current signal at the switching operation of the on-load tap-changer of the transformer are to the conditions of the normal vibration-acoustic signal and the normal motor current signal, and the greater its reference value. Therefore, its weight is higher. represents the sum of multiplying the relative error of the historical predicted fault probability data at multiple switching operations of the on-load tap-changer of the transformer in each historical monitoring period of the s-th training batch by the corresponding weight. is the weight of the s-th training batch, which is used to reasonably weight the relative errors of different training batches in the loss function. For the historical monitoring period of the s + 1-th training batch, the accuracy of the (s + 1)-th historical predicted fault probability data output by the fault probability prediction model is usually higher than the accuracy of the historical predicted fault probability data of the s-th training batch. That is, the shorter the time interval between a certain training batch and the 1st training batch, the less accurate its prediction result. To improve the training efficiency, the higher its weight is set. Conversely, the more accurate the prediction result is, the lower its weight is. Thus, a higher weight can be assigned to the item with lower accuracy, thereby enhancing the training intensity and training efficiency. Multiply the above and two items, which can represent the loss function of the fault probability prediction model.

[0065] According to an embodiment of the present invention, in the process of training the fault probability prediction model, by performing backpropagation on the loss function, some parameters inside the model are adjusted to reduce the value of the loss function of the fault probability prediction model, thereby improving the accuracy of the fault probability prediction model and obtaining the trained fault probability prediction model.

[0066] In this way, based on the influence of the historical contact temperature on the failure probability, the influence of the above data on the error of the historical predicted failure probability data can be determined. Then, based on this influence and the relative error between the historical failure probability data and the historical predicted failure probability data, and based on the characteristics that the closer the vibration-acoustic signal and the historical motor current signal during the switching operation of the on-load tap-changer of the transformer are to the normal vibration-acoustic signal and the normal motor current signal, the greater the reference value, weights are set, and also based on the characteristic that the shorter the time interval from the first training batch, the lower the accuracy, weights are set. Thus, the errors output by the failure probability prediction model during multiple switching operations of the on-load tap-changer of the transformer in each historical monitoring period of the s-th batch are weighted and summed to obtain the loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and enhancing the accuracy of the failure probability prediction model.

[0067] According to an embodiment of the present invention, in step S105, based on the predicted failure probability data and the switching performance score, it is determined whether the on-load tap-changer of the transformer meets the preset target conditions.

[0068] According to an embodiment of the present invention, step S105 includes: setting a failure probability threshold and a switching performance score threshold; based on the predicted failure probability data, the switching performance score, the failure probability threshold, and the switching performance score threshold, it is determined whether the on-load tap-changer of the transformer meets the preset target conditions.

[0069] According to an embodiment of the present invention, when setting the failure probability threshold and the switching performance score threshold, for example, the failure probability threshold can be set to 70%. If the predicted failure probability data exceeds the failure probability threshold, it indicates that a failure accident occurs during the switching operation of the on-load tap-changer of the transformer. The switching performance score threshold can be set to 0.9. If the switching performance score exceeds the switching performance score threshold, it indicates that the switching performance during the switching operation of the on-load tap-changer of the transformer is normal and no failure accident occurs.

[0070] According to an embodiment of the present invention, based on the predicted failure probability data, the switching performance score, the failure probability threshold, and the switching performance score threshold, determining whether the on-load tap-changer of the transformer meets the preset target conditions includes: determining the first condition C1 and the second condition C2 according to formulas (3) and (4), (3), (4),

[0071] where, is the predicted failure probability data during the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period, is the failure probability threshold, and F is a piecewise function obtained by comparing the predicted failure probability data at the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period with the failure probability threshold. is the preset average failure probability data within a monitoring period. is the switching performance score. is the switching performance score threshold, N is the number of switching operations of the on-load tap-changer of the transformer in the monitoring period, i ≤ N, and both i and N are positive integers. The first condition C1 and the second condition C2 are the preset target conditions; when the first condition C1 and the second condition C2 are both satisfied, it is determined that the on-load tap-changer of the transformer meets the preset target conditions.

[0072] According to an embodiment of the present invention, in formula (3), indicates that when the predicted failure probability data at the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period is greater than or equal to the failure probability threshold, the value is 1; when the predicted failure probability data at the i-th switching operation of the on-load tap-changer of the transformer in the current monitoring period is less than the failure probability threshold, the value is 0. If the predicted failure probability data is relatively large, it indicates that the probability of failure during the switching operation of the on-load tap-changer of the transformer in the current monitoring period is relatively high. In the first condition of formula (4), indicates that the average value of F at all times in the current monitoring period is less than the preset average failure probability data within a monitoring period. Among them, the range of the preset average failure probability data can be from 0.55 to 0.6, that is, when the failure probability is lower than the threshold within the monitoring period, it indicates that no failure occurs during the switching operation of the on-load tap-changer of the transformer. In the second condition, being the switching performance score greater than or equal to the switching performance score threshold indicates that the switching performance of the on-load tap-changer of the transformer during the switching operation is good and no failure occurs.

[0073] In this way, based on the predicted failure probability data, switching performance score, failure probability threshold, and switching performance score threshold, the first condition and the second condition can be determined. When the first condition and the second condition are both satisfied, it can be determined that the on-load tap-changer of the transformer meets the preset target conditions, and the predicted failure probability data and switching performance score are quantified, improving the accuracy of judging the preset target conditions and realizing a comprehensive assessment of the state of the on-load tap-changer of the transformer.

[0074] According to an embodiment of the present invention, in step S106, if the on-load tap-changer of the transformer meets the preset target conditions, it is determined that the state of the on-load tap-changer of the transformer is currently normal, that is, the on-load tap-changer of the transformer can maintain stable performance and has a low failure risk in the current operating environment.

[0075] According to an embodiment of the present invention, in step S107, if the on-load tap-changer of the transformer does not meet the preset target conditions, it is determined that the current state of the on-load tap-changer of the transformer is in a faulty state, that is, there is a performance degradation or potential safety hazard in the on-load tap-changer of the transformer under the current operating environment, and corresponding maintenance or repair measures need to be taken immediately.

[0076] The on-line monitoring and fault diagnosis method for the on-load tap-changer of a transformer according to the embodiment of the present invention comprehensively monitors the switching performance of the on-load tap-changer through arc energy and contact position information, so as to evaluate the state of the on-load tap-changer. By analyzing the operation data through the trained fault probability prediction model, the fault probability of the on-load tap-changer of the transformer can be predicted, which helps the normal operation of the on-load tap-changer of the transformer and timely warning when a fault occurs, reduces the risk of fault occurrence, and improves the reliability and stability of the on-load tap-changer of the transformer. When determining the switching performance score, the switching performance score can be determined through the arc energy, the voltage value corresponding to the contact position information of the on-load tap-changer, the normal range of the arc energy, and the voltage value corresponding to the target position information. The two parameters of the voltage value corresponding to the arc energy and the contact position information respectively reflect the electrical performance and mechanical performance during the switching process of the switch, improving the comprehensiveness and reliability of the switching performance score. When determining the loss function of the fault probability prediction model, the influence of the historical contact temperature on the fault probability can be used to determine the influence of the above data on the error between the historical predicted fault probability data, so as to be based on this influence and the relative error between the historical fault probability data and the historical predicted fault probability data, and based on the characteristics that the vibration acoustic signal and the historical motor current signal during the switching operation of the on-load tap-changer of the transformer are more similar to the normal vibration acoustic signal and the normal motor current signal, the greater the reference value, set weights, and the shorter the time interval from the first training batch, the lower the accuracy, set weights, so as to perform a weighted sum of the errors output by the fault probability prediction model during multiple switching operations of the on-load tap-changer of the transformer in each historical monitoring period of the s-th batch, obtain the loss function, so as to improve the design accuracy and objectivity of the loss function, thereby improving the training efficiency during the training process and improving the accuracy of the fault probability prediction model. When determining whether the on-load tap-changer of the transformer meets the preset target conditions, the first condition and the second condition can be determined based on the predicted fault probability data, the switching performance score, the fault probability threshold, and the switching performance score threshold. When both the first condition and the second condition are met, it can be determined that the on-load tap-changer of the transformer meets the preset target conditions, and the predicted fault probability data and the switching performance score are quantified, improving the accuracy of judging the preset target conditions and realizing the comprehensive evaluation of the state of the on-load tap-changer of the transformer.

[0077] The present invention may be a method, apparatus, system, and / or computer program product. The computer program product may include a computer-readable storage medium having thereon computer-readable program instructions for performing various aspects of the present invention.

[0078] Those skilled in the art should understand that the embodiments of the present invention described above and shown in the accompanying drawings are only examples and do not limit the present invention. The objectives of the present invention have been fully and effectively achieved. The functions and structural principles of the present invention have been shown and described in the embodiments, and the embodiments of the present invention may have any variations or modifications without departing from the said principles.

Claims

1. A method for online monitoring and fault diagnosis of a transformer on-load tap changer, characterized in that: include: Obtain the arc energy and contact position information of the on-load tap changer generated during the on-load tap changer switching action of the transformer in the current monitoring period; determining a switching performance score according to the arc energy and the contact position information of the on-load tap changer; In the current monitoring cycle, the operation data of the transformer on-load tap changer is obtained, wherein the operation data includes a vibration acoustic signal, a motor current signal and a contact temperature generated during a switching action of the transformer on-load tap changer; Inputting the operating data into a trained fault probability prediction model to obtain predicted fault probability data of the transformer on-load tap changer switching action in the current monitoring period; Determining whether the transformer on-load tap changer meets a preset target condition according to the predicted fault probability data and the switching performance score; If the transformer on-load tap changer meets the preset target condition, determining that the transformer on-load tap changer is in a normal state; If the transformer on-load tap changer does not meet the preset target condition, it is determined that the transformer on-load tap changer is in a fault state.

2. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 1, characterized in that: Determining a switching performance score according to the arc energy and the contact position information of the on-load tap changer includes: Set the normal range of arc energy; Obtaining a voltage value corresponding to the contact position information of the on-load tap changer; The voltage value corresponding to the target tap position of the transformer on-load tap changer is set to the voltage value corresponding to the target position information; A switching performance score is determined according to the arc energy, the voltage value corresponding to the on-load tap changer contact position information, the normal range of the arc energy and the voltage value corresponding to the target position information.

3. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 2, characterized in that: Determining a switching performance score according to the arc energy, the voltage value corresponding to the on-load tap changer contact position information, the normal range of the arc energy and the voltage value corresponding to the target position information includes: According to the formula ， Determining the switching performance score ,in, is the arc energy generated by the transformer on-load tap changer during the i-th switching action in the current monitoring period, is the minimum arc energy, is the maximum arc energy, is the voltage value corresponding to the contact position information of the on-load tapchanger during the i-th switching action of the transformer on-load tapchanger in the current monitoring period, is the voltage value corresponding to the target position information when the transformer on-load tap changer performs the i-th switching action in the current monitoring period, N is the number of switching actions of the transformer on-load tap changer in the monitoring period, i≤N, and i and N are both positive integers, and if is a conditional function.

4. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 1, characterized in that: The training steps of the fault probability prediction model include: Acquiring historical operation data of the transformer on-load tap changer during a historical monitoring period, wherein the historical operation data includes historical vibration acoustic signals, historical motor current signals, and historical contact temperatures generated during the switching action of the transformer on-load tap changer; Obtain historical fault probability data of transformer on-load tap changer switching actions during multiple historical monitoring cycles; The historical operation data is processed by a fault probability prediction model to obtain historical predicted fault probability data of the transformer on-load tap changer switching action during multiple historical monitoring periods; Determining a loss function of the failure probability prediction model according to the historical operation data, the historical failure probability data and the historical predicted failure probability data; The fault probability prediction model is trained according to the loss function of the fault probability prediction model to obtain the trained fault probability prediction model.

5. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 4, characterized in that: Determining a loss function of the fault probability prediction model according to the historical operation data, the historical fault probability data, and the historical predicted fault probability data includes: According to the formula ， Determine the loss function of the failure probability prediction model ,in, is the historical fault probability data of the transformer on-load tap changer at the i-th switching action in the h-th historical monitoring cycle, is the historical predicted fault probability data of the transformer on-load tap changer at the i-th switching action in the h-th historical monitoring cycle, is the historical vibration acoustic signal of the transformer on-load tap changer during the i-th switching action in the h-th historical monitoring cycle, It is the normal vibration acoustic signal of the transformer on-load tap changer during switching action. is the historical motor current signal of the transformer on-load tap changer during the i-th switching action in the h-th historical monitoring cycle, It is the normal motor current signal when the transformer on-load tap changer is switching. is the historical contact temperature of the transformer on-load tapchanger during the i-th switching action in the h-th historical monitoring cycle, It is the normal contact temperature of the transformer on-load tap changer during switching action. is the number of historical monitoring cycles of the sth training batch, S is the number of training batches, N is the number of switching actions of the transformer on-load tap changer in the monitoring cycle, i≤N, h≤ , s≤S, and i, h, s, N, and S are both positive integers.

6. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 1, characterized in that: Determining whether the transformer on-load tap changer meets a preset target condition according to the predicted fault probability data and the switching performance score includes: Set the fault probability threshold and switching performance score threshold; It is determined whether the transformer on-load tap changer meets a preset target condition according to the predicted fault probability data, the switching performance score, the fault probability threshold and the switching performance score threshold.

7. The transformer on-load tap changer online monitoring and fault diagnosis method according to claim 6, characterized in that: Determining whether the transformer on-load tap changer meets a preset target condition according to the predicted fault probability data, the switching performance score, the fault probability threshold, and the switching performance score threshold includes: According to the formula ， ， Determine the first condition C1 and the second condition C2, where: is the predicted fault probability data of the transformer on-load tap changer at the i-th switching action in the current monitoring period, is the fault probability threshold, F is the piecewise function that compares the predicted fault probability data of the transformer on-load tap changer at the i-th switching action in the current monitoring period with the fault probability threshold, is the preset average failure probability data within a monitoring period, Score the switching performance, is the switching performance scoring threshold, N is the number of switching actions of the transformer on-load tap changer in the monitoring period, i≤N, and i and N are both positive integers, the first condition C1 and the second condition C2 are the preset target conditions; When the first condition C1 and the second condition C2 are satisfied at the same time, it is determined that the transformer on-load tap changer meets the preset target condition.

Images