Generator inter-turn short circuit fault diagnosis method, device, equipment and storage medium

Abstract

The present invention belongs to the technical field of generator fault detection, and discloses a generator turn-to-turn short-circuit fault diagnosis method, device, equipment and storage medium. The method includes: calculating the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test, so as to obtain a base reference value of the turn-to-turn short-circuit trend criterion; based on the base reference value and in combination with the reference turn-to-turn short-circuit trend criterion static threshold under different working conditions, obtaining the target turn-to-turn short-circuit trend criterion static threshold corresponding to each working condition; predicting the turn-to-turn short-circuit trend of the generator according to the target turn-to-turn short-circuit trend criterion static threshold; when the generator has a turn-to-turn short-circuit trend, obtaining the operating data of the generator; and determining the degree of the turn-to-turn short-circuit according to the operating data. Taking full advantage of the advantages of big data for physical modeling and machine learning, a quantitative criterion is given for the trend and degree of the rotor turn-to-turn short-circuit, so as to achieve accurate prediction of generator faults.

Description

Technical Field

[0001] The present invention relates to the technical field of generator fault detection, and in particular to a generator turn-to-turn short circuit fault diagnosis method, device, equipment and storage medium. Background Art

[0002] At present, the diagnostic methods used for synchronous generator rotor turn-to-turn short circuit are mainly divided into two categories: offline detection and online detection. Offline detection refers to the necessary manual inspection of the unit in a planned manner through various detection instruments other than the equipment when the generator set is shut down; online detection refers to the use of sensor technology to detect and feedback the operating status of the unit in real time through the sensor equipment directly installed on the unit when the generator set is online.

[0003] Offline detection methods mainly include no-load and short-circuit characteristic test methods, AC impedance and loss methods, repetitive pulse waveform method (RSO), distributed voltage method, DC resistance method and open transformer method. Common online detection methods mainly include: detection coil method, model-based methods such as multi-loop method and finite element analysis method, data-driven methods such as neural network method, etc. Offline detection methods require fault detection after the unit is shut down. The general unit shutdown and maintenance time is based on experience, and fixed maintenance and troubleshooting time is arranged. It cannot achieve real-time detection of faults, and it is difficult to ensure that the fault is discovered in time in the early stage of the fault to curb its development. For online fault diagnosis methods, model-based methods can better explain the relationship between physical principles and various physical quantities of the generator.

[0004] Compared with offline detection, online detection can monitor the operating status of the generator in real time, is not limited by the maintenance schedule of the unit, and can detect faults in time. However, the operating conditions of the generator set are very complicated. During the operation, the magnetic field and electric field inside the generator are coupled with each other, and each operating physical quantity shows a nonlinear relationship. The generator fault diagnosis model established by the traditional mathematical modeling method simplifies and idealizes the actual operating conditions of the generator to a certain extent. Such a processing method will cause a certain discrepancy between the theoretical analysis and the actual situation. In addition, the model-based method requires a large number of accurate and reliable motor body parameters, and the missing parameters can only be simplified in the process of model establishment. The data-driven method has less dependence on the parameters of the complex equipment body and has a strong ability to mine the potential relationship between data. It can overcome the shortcomings of weak harmonic characteristics under minor fault conditions and difficulty in accurately extracting fault harmonic characteristics. However, the disadvantage of the data-driven method is that most of the results are not easy to explain their physical meaning.

[0005] The above contents are only used to assist in understanding the technical solution of the present invention and do not constitute an admission that the above contents are prior art. Summary of the invention

[0006] The main purpose of the present invention is to provide a method, device, equipment and storage medium for diagnosing motor inter-turn short-circuit faults, aiming to solve the technical problems that offline test diagnosis is limited by the maintenance schedule of the unit and the low sensitivity and accuracy of online diagnosis.

[0007] To achieve the above object, the present invention provides a method for diagnosing a motor turn-to-turn short circuit fault, the method comprising the following steps:

[0008] Calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is turned on or during no-load test, so as to obtain the base reference value of the turn-to-turn short-circuit trend criterion;

[0009] Based on the base reference value and in combination with the reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions, a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition is obtained;

[0010] Predicting the inter-turn short circuit trend of the generator according to the target inter-turn short circuit trend criterion static threshold;

[0011] When the generator has a tendency of inter-turn short circuit, obtain the operation data of the generator;

[0012] The degree of inter-turn short circuit is determined according to the operating data.

[0013] Optionally, the calculation of the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test to obtain a base reference value for the turn-to-turn short circuit trend criterion includes:

[0014] Obtain the excitation current and the vibration value of the steam excitation side of the generator when the generator is started or tested at no-load under the preset generator parameters;

[0015] Calculating the covariance and standard deviation between the excitation current and the vibration value of the steam excitation side of the generator;

[0016] The Pearson correlation coefficient between the excitation current and the vibration of each part of the generator is calculated according to the covariance and the standard deviation to obtain a base reference value of the turn-to-turn short circuit trend criterion.

[0017] Optionally, the generator turn-to-turn short circuit fault diagnosis method further includes:

[0018] Obtain historical operating data of the generator;

[0019] Identifying the leading phase operation condition of the generator and the lagging phase operation condition of each different active power according to the historical operation data;

[0020] Under the phase leading operation condition, when the phase leading depth is greater than the first preset depth or the continuous phase leading operation time is greater than the first preset duration, the Pearson correlation coefficient during the phase leading test is used as the reference turn-to-turn short circuit trend criterion static threshold value under the phase leading operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value;

[0021] Under the delayed phase operation condition, when the load rate is greater than the first preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value, and the second threshold value is greater than the first threshold value;

[0022] Under the delayed phase operation condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate, and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value;

[0023] Under the delayed phase operation condition, when the load rate is less than the second preset load rate and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value;

[0024] Under the alternating working condition of leading phase and lagging phase, a Pearson correlation coefficient greater than a third threshold is used as a static threshold of a reference turn-to-turn short circuit trend criterion, and the third threshold is greater than the second threshold.

[0025] Optionally, the step of obtaining a target turn-to-turn short circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with a reference turn-to-turn short circuit trend criterion static threshold value under different working conditions includes:

[0026] Under the phase-leading operation condition, when the phase-leading depth is greater than the second preset depth or the continuous phase-leading operation time is greater than the second preset duration, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the phase-leading operation condition, the second preset depth is greater than the first preset depth, and the second preset duration is greater than the first preset duration;

[0027] Under the delayed phase operation condition, when the load rate is greater than the first preset load rate and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition;

[0028] Under the delayed phase operation condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate, and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition;

[0029] Under the delayed phase operation condition, when the load rate is less than the second preset load rate and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition;

[0030] Under the alternating working conditions of leading and lagging phases, the reference turn-to-turn short-circuit trend criterion static threshold is used as the corresponding target turn-to-turn short-circuit trend criterion static threshold.

[0031] Optionally, determining the degree of inter-turn short circuit according to the operating data includes:

[0032] Establish dynamic excitation current model under different working conditions;

[0033] Inputting the operation data into the dynamic excitation current model to calculate the excitation current calculation value;

[0034] Get the current measured value of the excitation current;

[0035] The degree of inter-turn short circuit is calculated according to the calculated value of the excitation current and the current measured value of the excitation current.

[0036] Optionally, inputting the operating data into the dynamic excitation current model to calculate the excitation current calculation value includes:

[0037] Extracting the generator phase voltage, generator phase current, generator power factor angle, generator stator DC resistance, generator synchronous reactance and operating condition coefficient corresponding to the current operating condition from the operating data;

[0038] The excitation current calculation value is obtained based on the dynamic excitation current model according to the generator phase voltage, the generator phase current, the generator power factor angle, the DC resistance of the generator stator, the synchronous reactance of the generator and the operating condition coefficient corresponding to the current operating condition.

[0039] Optionally, the generator turn-to-turn short circuit fault diagnosis method further includes:

[0040] Obtain excitation current, excitation voltage, rotor DC resistance, and inlet hydrogen temperature;

[0041] Calculating the average temperature rise of the rotor under different working conditions according to the excitation current, the excitation voltage, the rotor DC resistance and the inlet hydrogen temperature;

[0042] The average rotor temperature rise is compared with the calculated temperature rise output by the rotor temperature model, the rotor temperature rise in the motor temperature rise test and the calibrated rotor temperature rise in the manual, and the rotor turn-to-turn state is determined based on the comparison results.

[0043] In addition, to achieve the above-mentioned purpose, the present invention also provides a motor turn-to-turn short circuit fault diagnosis device, the motor turn-to-turn short circuit fault diagnosis device comprising:

[0044] A calculation module is used to calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test, so as to obtain a base reference value for the inter-turn short-circuit trend criterion;

[0045] The calculation module is further used to obtain a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with a reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions;

[0046] A diagnostic module, used for predicting the inter-turn short circuit trend of the generator according to the target inter-turn short circuit trend criterion static threshold;

[0047] The acquisition module is used to acquire the operating data of the generator when there is a tendency of inter-turn short circuit in the generator; the calculation module is also used to determine the degree of inter-turn short circuit according to the operating data.

[0048] In addition, to achieve the above-mentioned purpose, the present invention also proposes a motor inter-turn short-circuit fault diagnosis device, which includes: a memory, a processor, and a motor inter-turn short-circuit fault diagnosis program stored in the memory and executable on the processor, and the motor inter-turn short-circuit fault diagnosis program is configured to implement the steps of the motor inter-turn short-circuit fault diagnosis method as described above.

[0049] In addition, to achieve the above-mentioned purpose, the present invention also proposes a storage medium, on which a motor turn-to-turn short-circuit fault diagnosis program is stored. When the motor turn-to-turn short-circuit fault diagnosis program is executed by a processor, the steps of the motor turn-to-turn short-circuit fault diagnosis method as described above are implemented.

[0050] The present invention calculates the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test to obtain a base reference value for the inter-turn short-circuit trend criterion; based on the base reference value and in combination with the reference inter-turn short-circuit trend criterion static threshold under different working conditions, the target inter-turn short-circuit trend criterion static threshold corresponding to each working condition is obtained; the inter-turn short-circuit trend of the generator is predicted according to the target inter-turn short-circuit trend criterion static threshold; when the generator has an inter-turn short-circuit trend, the operating data of the generator is obtained; and the degree of the inter-turn short-circuit is determined according to the operating data. The advantages of physical modeling and machine learning of big data are fully utilized to provide quantitative criteria for the trend and degree of rotor inter-turn short-circuit, thereby achieving accurate prediction of generator failures. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a schematic flow chart of a first embodiment of a method for diagnosing a motor turn-to-turn short-circuit fault according to the present invention;

[0052] Figure 2 It is a flow chart of a second embodiment of a method for diagnosing a motor turn-to-turn short-circuit fault according to the present invention;

[0053] Figure 3 This is a structural block diagram of the first embodiment of the motor turn-to-turn short-circuit fault diagnosis device of the present invention.

[0054] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0055] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0056] The embodiment of the present invention provides a method for diagnosing a motor turn-to-turn short circuit fault. Figure 1 , Figure 1 The figure is a flow chart of a first embodiment of a method for diagnosing a motor turn-to-turn short circuit fault according to the present invention.

[0057] In this embodiment, the motor turn-to-turn short circuit fault diagnosis method includes the following steps:

[0058] Step S10: Calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test, so as to obtain a base reference value for the turn-to-turn short-circuit trend criterion.

[0059] In this embodiment, the executor of this embodiment is a motor turn-to-turn short-circuit fault diagnosis device, wherein the motor turn-to-turn short-circuit fault diagnosis device has functions such as data processing, data communication and program running. The motor turn-to-turn short-circuit fault diagnosis device can be a computer terminal device or other network device, and of course it can also be other devices with similar functions, and this embodiment does not limit this.

[0060] It should be noted that the diagnostic methods currently used for synchronous generator rotor turn-to-turn short circuits are mainly divided into two categories: offline detection and online detection. Offline detection refers to the planned necessary manual inspection of the unit through various detection instruments outside the equipment when the generator set is shut down; online detection refers to the real-time detection and real-time feedback of the operating status of the unit through the sensor equipment directly installed on the unit when the generator set is online. Offline detection methods mainly include no-load and short-circuit characteristic test methods, AC impedance and loss methods, repetitive pulse waveform method (RSO), distributed voltage method, DC resistance method and open transformer method. Common online detection methods mainly include: detection coil method, model-based methods such as multi-loop method and finite element analysis method, data-driven methods such as neural network method, etc. Offline detection methods require fault detection after the unit is shut down. The general unit shutdown and maintenance time is based on experience, and a fixed maintenance and troubleshooting time is arranged. It is not possible to detect the fault in real time, and it is difficult to ensure that the fault is discovered in time in the early stage of the fault and curb its development. For online fault diagnosis methods, model-based methods can better explain the relationship between physical principles and various physical quantities of the generator. Compared with offline detection, online detection can monitor the operating status of the generator in real time, is not limited by the maintenance schedule of the unit, and can detect faults in time. However, the operating conditions of the generator set are very complicated. During the operation, the magnetic field and electric field inside the generator are coupled with each other, and each operating physical quantity shows a nonlinear relationship. The generator fault diagnosis model established by the traditional mathematical modeling method simplifies and idealizes the actual operating conditions of the generator to a certain extent. Such a processing method will cause a certain discrepancy between the theoretical analysis and the actual situation. In addition, the model-based method requires a large number of accurate and reliable motor body parameters, and the missing parameters can only be simplified in the process of model establishment. The data-driven method has less dependence on the parameters of the complex equipment body and has a strong ability to mine the potential relationship between data. It can overcome the shortcomings of weak harmonic characteristics under minor fault conditions and difficulty in accurately extracting fault harmonic characteristics. However, the disadvantage of the data-driven method is that most of the results are not easy to explain their physical meaning.

[0061] In order to solve the above technical problems, in this embodiment, the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or in the no-load test is calculated to obtain the base reference value of the inter-turn short-circuit trend criterion; based on the base reference value and combined with the reference inter-turn short-circuit trend criterion static threshold under different working conditions, the target inter-turn short-circuit trend criterion static threshold corresponding to each working condition is obtained; the inter-turn short-circuit trend of the generator is predicted according to the target inter-turn short-circuit trend criterion static threshold; when the generator has an inter-turn short-circuit trend, the operating data of the generator is obtained; and the degree of inter-turn short-circuit is determined according to the operating data. By making full use of the advantages of big data for physical modeling and machine learning, quantitative criteria are given for the trend and degree of rotor inter-turn short-circuit, and accurate prediction of generator faults is achieved, which can be specifically achieved in the following way.

[0062] In the specific implementation, in this embodiment, the short-circuit trend of the generator rotor turn-to-turn is first predicted. Specifically, in this embodiment, the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or the no-load test needs to be calculated to obtain the base reference value of the short-circuit trend criterion between the turn-to-turn short circuit. Specifically, the excitation current and the vibration value of the steam-excitation side of the generator when the generator is started or the no-load test need to be obtained under the preset generator parameters. The preset generator parameters include the active power of the generator P=0, the stator voltage of the generator is the rated voltage, and the stator current of the generator is 0. Under this condition, the excitation current and the vibration value of the steam-excitation side of the generator can be obtained according to a 5s period, and then the covariance and standard deviation between the excitation current and the vibration value of the steam-excitation side of the generator are calculated. Finally, the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator is calculated according to the covariance and the standard deviation to obtain the base reference value of the short-circuit trend criterion between the turn-to-turn short circuit. The calculation formula is as follows:

[0063]

[0064] Where X represents the excitation current, Y represents the vibration value, cov(X,Y) represents the covariance, σ X ,σ Y Indicates standard deviation. The physical meaning of the Pearson correlation coefficient between excitation current and vibration: positive correlation means that the vibration increases with the increase of excitation current, and negative correlation means that the vibration increases with the decrease of excitation current. Correlation strength: |ρ|=0.8~1.0, extremely strong correlation; |ρ|=0.6~0.8, strong correlation; |ρ|=0.4~0.6, moderate correlation; |ρ|=0.2~0.4, weak correlation; |ρ|=0~0.2, no correlation.

[0065] Step S20: obtaining a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with the reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions.

[0066] It should be noted that, in this embodiment, the base reference value of the turn-to-turn short-circuit trend criterion can be calculated according to the above formula. Furthermore, in this embodiment, the final target turn-to-turn short-circuit trend criterion static threshold value needs to be calculated in combination with each operating condition. Specifically, in this embodiment, the historical operating data of the generator can be obtained; the leading phase operating condition of the generator and the delayed phase operating conditions of each different active power can be identified according to the historical operating data. For example, the daily historical operating data of the generator can be analyzed according to the operating conditions, and the leading phase operating condition of the generator and the delayed phase operating conditions of different active powers can be distinguished. The operating conditions are divided into leading phase operating conditions, delayed phase operating conditions, and leading and delayed phase interactive conditions.

[0067] For the leading phase operation condition, when the leading phase depth is greater than the first preset depth or the continuous leading phase operation time is greater than the first preset time, the Pearson correlation coefficient during the leading phase test is used as the static threshold of the reference turn-to-turn short-circuit trend criterion under the leading phase operation condition. However, it is necessary to ensure that the reference turn-to-turn short-circuit trend criterion static threshold is greater than the first threshold. For example, when the leading phase depth is greater than -90MVAR, or the continuous leading phase operation time is greater than 0.5h, if the absolute value of the Pearson correlation coefficient of the excitation current and vibration is greater than 0.8, which is a strong correlation, it can be used as the reference turn-to-turn short-circuit trend criterion static threshold under the leading phase condition.

[0068] For the late phase operating condition, it can be divided into three cases. The first case is when the load rate is greater than the first preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no load is used as the static threshold of the reference turn-to-turn short-circuit trend criterion under the late phase operating condition. However, it is necessary to ensure that the reference turn-to-turn short-circuit trend criterion static threshold is greater than the second threshold. For example, when the load rate is greater than 90% and there is no leading phase condition, the absolute value of the Pearson correlation coefficient of the excitation current and vibration is greater than 0.85, which is a strong correlation, and it is used as the reference turn-to-turn short-circuit trend criterion static threshold under the late phase condition. The second situation is when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no-load is used as the static threshold value of the reference turn-to-turn short-circuit trend criterion under the lagging phase operation condition, but it is necessary to ensure that the reference turn-to-turn short-circuit trend criterion static threshold value is greater than the first threshold value. For example, when the load rate is between 50% and 90% and there is no leading phase condition, the absolute value of the Pearson correlation coefficient of the excitation current and vibration is greater than 0.8, which is a strong correlation, and it is used as the static threshold value of the reference turn-to-turn short-circuit trend criterion under the lagging phase condition. The third case is when the load rate is less than the second preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no-load is used as the static threshold value of the reference turn-to-turn short-circuit trend criterion under the lagging phase operating condition, but it is necessary to ensure that the reference turn-to-turn short-circuit trend criterion static threshold value is greater than the second threshold value. For example, when the load rate is less than 50% and there is no leading phase condition, the absolute value of the Pearson correlation coefficient of the excitation current and vibration is greater than 0.85, which is a strong correlation, and it is used as the static threshold value of the reference turn-to-turn short-circuit trend criterion under the lagging phase condition.

[0069] For the working condition of the leading phase and the lagging phase, the Pearson correlation coefficient greater than the third threshold is used as the static threshold of the reference turn-to-turn short-circuit trend criterion. It should be emphasized that the third threshold is greater than the second threshold. For example, the absolute value of the Pearson correlation coefficient between the excitation current and the vibration is greater than 0.9, which is a strong correlation. It is used as the static threshold of the reference turn-to-turn short-circuit trend criterion when the lagging phase and the leading phase interact. The above thresholds, preset depths, preset durations, and preset loads are set for illustrative purposes only and are not used to limit this embodiment. In specific implementations, they can be adaptively adjusted according to actual needs.

[0070] After obtaining the reference turn-to-turn short-circuit trend criterion static threshold value under each operating condition, the target turn-to-turn short-circuit trend criterion static threshold value is obtained by combining the above-mentioned base reference value for addition calculation. Specifically, under the leading phase operation condition, when the leading phase depth is greater than the second preset depth or the continuous leading phase operation time is greater than the second preset duration, the corresponding target turn-to-turn short-circuit trend criterion static threshold value is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold value under the leading phase operation condition, the second preset depth is greater than the first preset depth, and the second preset duration is greater than the first preset duration; under the lagging phase operation condition, when the load rate is greater than the first preset load rate and there is no leading phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold value is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold value under the lagging phase operation condition. the static threshold value of the target turn-to-turn short-circuit trend criterion is calculated according to the static threshold value of the potential criterion; under the delayed phase operating condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate and there is no leading phase condition, the corresponding static threshold value of the target turn-to-turn short-circuit trend criterion is calculated according to the base reference value and the reference static threshold value of the turn-to-turn short-circuit trend criterion under the delayed phase operating condition; under the delayed phase operating condition, when the load rate is less than the second preset load rate and there is no leading phase condition, the corresponding static threshold value of the target turn-to-turn short-circuit trend criterion is calculated according to the base reference value and the reference static threshold value of the turn-to-turn short-circuit trend criterion under the delayed phase operating condition; under the alternating working condition of leading phase and delayed phase, the reference static threshold value of the turn-to-turn short-circuit trend criterion is used as the corresponding static threshold value of the target turn-to-turn short-circuit trend criterion. For example, taking the leading phase condition as an example, when the leading phase depth is greater than -30MVAR and the continuous leading phase operation time is greater than 1h, the absolute value of the Pearson correlation coefficient of the excitation current and vibration + the Pearson correlation coefficient during the leading phase test is used to obtain the static threshold value of the target turn-to-turn short-circuit trend criterion during the leading phase condition. If the conditions are not met, for example, the leading phase depth is less than -30MVAR, no calculation is performed.

[0071] Step S30: predicting the turn-to-turn short-circuit trend of the generator according to the target turn-to-turn short-circuit trend criterion static threshold.

[0072] Based on the above-obtained target inter-turn short-circuit trend criterion static threshold, the inter-turn short-circuit trend of the generator can be predicted. Specifically, it can be determined that the duration of reaching the target inter-turn short-circuit trend criterion static threshold reaches a certain duration, for example, it can be set to three days, and then it is considered that there is a short-circuit trend between the turns of the generator. If the above conditions cannot be continuously met within three days according to the operating parameters of the generator, it is determined that there is no short-circuit trend.

[0073] Step S40: When the generator has a turn-to-turn short circuit tendency, the operation data of the generator is obtained.

[0074] Step S50: determining the degree of inter-turn short circuit according to the operating data.

[0075] In this embodiment, after determining that there is a short-circuit trend between the generator turns, the degree of the short-circuit between the turns can be quantified according to the real-time operation data of the generator. In this embodiment, the calculation can be performed according to the dynamic excitation current model.

[0076] Furthermore, in this embodiment, the inter-turn condition of the generator rotor can also be calculated. The specific process is to first calculate the average temperature rise of the rotor. The calculation formula is △θ x =θ x -θ H , where θ x =KR x -235, of which, R0 is the resistance value when the rotor winding temperature is θ0, R X Calculate the resistance value of the rotor at any time, its value is R X =U F / I F (Where: U F is the excitation voltage, I F is the excitation current), θ H is the inlet hydrogen temperature. The calculated average rotor temperature rise is then compared with the calculated temperature rise output by the rotor temperature model, the rotor temperature rise in the motor temperature rise test, and the calibrated rotor temperature rise in the manual. The rotor temperature model is a pre-built known model, and the model building process is not described here. After the comparison, the temperature rise of the rotor can be determined. At the same time, the state of the rotor turns can be determined by combining the above-mentioned short-circuit trend and the judgment of the short-circuit degree. For example, after the short-circuit trend is determined and the short-circuit degree is obtained, the rotor is found to be close to the calculated temperature rise output by the rotor temperature model, the rotor temperature rise in the motor temperature rise test, and the calibrated rotor temperature rise in the manual. These temperature thresholds can be determined through temperature rise comparison, then it can be determined that the rotor is in a more serious heating state at this time.

[0077] This embodiment calculates the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during the no-load test to obtain the base reference value of the inter-turn short-circuit trend criterion; based on the base reference value and in combination with the reference inter-turn short-circuit trend criterion static threshold under different working conditions, the target inter-turn short-circuit trend criterion static threshold corresponding to each working condition is obtained; the inter-turn short-circuit trend of the generator is predicted according to the target inter-turn short-circuit trend criterion static threshold; when the generator has an inter-turn short-circuit trend, the operating data of the generator is obtained; and the degree of the inter-turn short-circuit is determined according to the operating data. Taking full advantage of the advantages of big data for physical modeling and machine learning, quantitative criteria are given for the trend and degree of rotor inter-turn short-circuit, thus realizing accurate prediction of generator faults.

[0078] refer to Figure 2 , Figure 2 It is a flow chart of a second embodiment of a method for diagnosing motor turn-to-turn short-circuit faults according to the present invention.

[0079] Based on the first embodiment, in the motor turn-to-turn short circuit fault diagnosis method of this embodiment, step S50 specifically includes:

[0080] Step S501: establishing a dynamic excitation current model under different working conditions.

[0081] In the specific implementation, the dynamic excitation current model in this embodiment is further established on the basis of the static excitation current model. Specifically, by classifying and analyzing the generator operation data, according to the influence of various operating parameters of the steam turbine generator excitation current, the static excitation current model is obtained according to linear regression. f =A×

(U×cosφ+I×r a ) 2 +(U×sinφ+I×x s ) 2

[0082] Furthermore, based on the static calculation model, machine learning and deep learning algorithms are used, combined with the characteristics of different working conditions of the generator, to find a suitable dynamic model algorithm for the excitation current. According to the electromagnetic principle, combined with the characteristics of different working conditions, the dynamic model of the excitation current is built and trained: 1) Working condition model: According to the different active power and reactive power values ​​of the generator operation, the representative working conditions are named, such as: "generator no-load", representing the generator state with active power of 0, rated stator voltage and stator current of 0; "generator leading phase", representing the working condition when the reactive power is less than 0; "generator high load operation", representing the working condition when the active power is greater than 90% of the rated active power; "generator normal working condition 210", representing the working condition when the active power is less than 210MW; "generator normal working condition 210-240", representing the working condition when the active power is in the range of 210 to 240MW; and so on. 2) Electromagnetic principle modeling Based on the electromagnetic principle, a dynamic model is created according to different operating conditions of the generator. Different linear regression algorithms such as LINEAR (linear mapping regression), LAR (variable selection regression algorithm), and HUBER (weighted fitting circle) are tried. According to the better fit, a suitable combination algorithm is selected to optimize the excitation current model. 3) Combined with the electromagnetic principle model, historical data is used to train a suitable dynamic excitation current model in combination with different operating conditions, and a model with better fit is selected to determine the dynamic algorithm combination.

[0083] Step S502: inputting the operation data into the dynamic excitation current model to calculate the excitation current calculation value.

[0084] The excitation current calculation value can be calculated by inputting the above-obtained operating data into the above-obtained dynamic excitation model. The excitation current calculation value can better reflect the magnitude of the excitation current under different working conditions.

[0085] Step S503: Obtain the current measured value of the excitation current.

[0086] Step S504: Calculate the degree of inter-turn short circuit according to the calculated value of the excitation current and the current measured value of the excitation current.

[0087] For those that meet the preliminary criterion of the rotor inter-turn short-circuit trend, dynamic grading criteria such as the deviation between the output value of the excitation current model and the actual value and the deviation of the historical data of the excitation current under the same load are introduced to form a rotor inter-turn short-circuit degree criterion model. Therefore, before calculating the inter-turn short-circuit degree, it is also necessary to obtain the current measured value of the excitation current in this embodiment. Finally, the inter-turn short-circuit degree is calculated based on the calculated value of the excitation current and the current measured value of the excitation current. The calculation formula is as follows: T a =|(I f -I f计算 )| / I f计算 × 100%, where If Indicates the actual measured value of the current excitation current, I f计算 Indicates the calculated value of the excitation current. In actual calculation, T a The value needs to be accurate to three decimal places.

[0088] In this embodiment, a dynamic excitation current model under different working conditions is established, the operating data is input into the dynamic excitation current model to calculate the excitation current calculated value, the current excitation current measured value is obtained, and the degree of inter-turn short circuit is calculated according to the excitation current calculated value and the current excitation current measured value. In this way, a quantitative criterion is given for the degree of inter-turn short circuit, thereby achieving accurate prediction of generator faults.

[0089] In addition, an embodiment of the present invention further proposes a storage medium, on which a motor turn-to-turn short-circuit fault diagnosis program is stored. When the motor turn-to-turn short-circuit fault diagnosis program is executed by a processor, the steps of the motor turn-to-turn short-circuit fault diagnosis method described above are implemented.

[0090] Reference Figure 3 , Figure 3 This is a structural block diagram of the first embodiment of the motor turn-to-turn short-circuit fault diagnosis device of the present invention.

[0091] like Figure 3 As shown, the motor turn-to-turn short circuit fault diagnosis device proposed in the embodiment of the present invention includes:

[0092] The calculation module 10 is used to calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is turned on or during a no-load test, so as to obtain a base reference value of the turn-to-turn short circuit trend criterion;

[0093] The calculation module 10 is further used to obtain a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with a reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions;

[0094] A diagnosis module 20, configured to predict the turn-to-turn short circuit trend of the generator according to the target turn-to-turn short circuit trend criterion static threshold;

[0095] An acquisition module 30, used for acquiring the operation data of the generator when there is a tendency of inter-turn short circuit in the generator;

[0096] The calculation module 10 is further used to determine the degree of inter-turn short circuit according to the operation data.

[0097] This embodiment calculates the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during the no-load test to obtain the base reference value of the inter-turn short-circuit trend criterion; based on the base reference value and in combination with the reference inter-turn short-circuit trend criterion static threshold under different working conditions, the target inter-turn short-circuit trend criterion static threshold corresponding to each working condition is obtained; the inter-turn short-circuit trend of the generator is predicted according to the target inter-turn short-circuit trend criterion static threshold; when the generator has an inter-turn short-circuit trend, the operating data of the generator is obtained; and the degree of the inter-turn short-circuit is determined according to the operating data. Taking full advantage of the advantages of big data for physical modeling and machine learning, quantitative criteria are given for the trend and degree of rotor inter-turn short-circuit, thus realizing accurate prediction of generator faults.

[0098] An embodiment of the present application also provides a motor turn-to-turn short-circuit fault diagnosis device, including a processor, a communication interface, a memory and a communication bus, wherein the processor, the communication interface and the memory communicate with each other through the communication bus, and the memory is used to store computer programs; the processor is used to implement the above-mentioned motor turn-to-turn short-circuit fault diagnosis method when executing the program stored in the memory.

[0099] The communication bus mentioned in the above-mentioned motor turn-to-turn short-circuit fault diagnosis device can be a Peripheral Component Interconnect (PCI) bus or an Extended Industry Standard Architecture (EISA) bus, etc. The communication bus can be divided into an address bus, a data bus, a control bus, etc.

[0100] The communication interface is used for communication between the above-mentioned motor turn-to-turn short-circuit fault diagnosis device and other devices.

[0101] The memory may include a random access memory (RAM) or a non-volatile memory (NVM), such as at least one disk memory. Optionally, the memory may also be at least one storage device located away from the aforementioned processor.

[0102] The above-mentioned processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, and discrete hardware components.

[0103] In the above embodiments, it can be implemented in whole or in part by software, hardware, firmware or any combination thereof. When implemented using software, it can be implemented in whole or in part in the form of a computer program product. The computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, the process or function described in the embodiment of the present application is generated in whole or in part. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions may be stored in a computer-readable storage medium, or transmitted from one computer-readable storage medium to another computer-readable storage medium, for example, the computer instructions may be transmitted from a website site, computer, server or data center by wired (e.g., coaxial cable, optical fiber, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) mode to another website site, computer, server or data center. The computer-readable storage medium may be any available medium that a computer can access or a data storage device such as a server or data center that includes one or more available media integrated. The available medium may be a magnetic medium, (e.g., a floppy disk, a hard disk, a tape), an optical medium (e.g., a DVD), or a semiconductor medium (e.g., a solid-state drive Solid State Disk (SSD)), etc.

[0104] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0105] Each embodiment in this specification is described in a related manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.

[0106] The above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present invention.

[0107] It should be understood that the above is only an example and does not constitute any limitation on the technical solution of the present invention. In specific applications, technicians in this field can make settings as needed, and the present invention does not limit this.

[0108] It should be noted that the workflow described above is merely illustrative and does not limit the scope of protection of the present invention. In practical applications, technicians in this field can select part or all of them according to actual needs to achieve the purpose of the present embodiment, and no limitation is made here.

[0109] In addition, for technical details not fully described in this embodiment, reference can be made to the motor turn-to-turn short-circuit fault diagnosis method provided in any embodiment of the present invention, and will not be repeated here.

[0110] In addition, it should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, article or system including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or system. In the absence of further restrictions, an element defined by the sentence "comprises a ..." does not exclude the existence of other identical elements in the process, method, article or system including the element.

[0111] The serial numbers of the above embodiments of the present invention are only for description and do not represent the advantages or disadvantages of the embodiments.

[0112] Through the description of the above implementation methods, those skilled in the art can clearly understand that the above-mentioned embodiment methods can be implemented by means of software plus a necessary general hardware platform, and of course by hardware, but in many cases the former is a better implementation method. Based on such an understanding, the technical solution of the present invention, or the part that contributes to the prior art, can be embodied in the form of a software product, which is stored in a storage medium (such as a read-only memory (ROM) / RAM, a magnetic disk, or an optical disk), and includes a number of instructions for a terminal device (which can be a mobile phone, a computer, a server, or a network device, etc.) to execute the methods described in each embodiment of the present invention.

[0113] The above are only preferred embodiments of the present invention, and are not intended to limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

[0114] It is understandable that the system provided by the embodiment of the present invention corresponds to the method provided by the embodiment of the present invention, and the explanation, examples and beneficial effects of the relevant contents can refer to the corresponding parts in the above method.

Claims

1. A generator turn-to-turn short circuit fault diagnosis method, characterized in that: The generator turn-to-turn short circuit fault diagnosis method comprises: Calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is turned on or during no-load test, so as to obtain the base reference value of the turn-to-turn short-circuit trend criterion; The calculation of the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is turned on or during a no-load test to obtain a base reference value for the turn-to-turn short-circuit trend criterion includes: Obtain the excitation current and the vibration value of the steam excitation side of the generator when the generator is started or tested at no-load under the preset generator parameters; Calculating the covariance and standard deviation between the excitation current and the vibration value of the steam excitation side of the generator; Calculating the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator according to the covariance and the standard deviation to obtain a base reference value of the turn-to-turn short circuit trend criterion; Obtain historical operating data of the generator; Identifying the leading phase operation condition of the generator and the lagging phase operation condition of each different active power according to the historical operation data; Under the phase leading operation condition, when the phase leading depth is greater than the first preset depth or the continuous phase leading operation time is greater than the first preset duration, the Pearson correlation coefficient during the phase leading test is used as the reference turn-to-turn short circuit trend criterion static threshold value under the phase leading operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is greater than the first preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value, and the second threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate, and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is less than the second preset load rate and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value; Under the alternating working condition of leading phase and lagging phase, a Pearson correlation coefficient greater than a third threshold is used as a static threshold of a reference turn-to-turn short circuit trend criterion, and the third threshold is greater than the second threshold; Based on the base reference value and in combination with the reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions, a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition is obtained; Predicting the inter-turn short circuit trend of the generator according to the target inter-turn short circuit trend criterion static threshold; When the generator has a tendency of inter-turn short circuit, obtain the operation data of the generator; The degree of inter-turn short circuit is determined according to the operating data.

2. The generator turn-to-turn short circuit fault diagnosis method according to claim 1, characterized in that: The method of obtaining the target turn-to-turn short circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with the reference turn-to-turn short circuit trend criterion static threshold value under different working conditions includes: Under the phase-leading operation condition, when the phase-leading depth is greater than the second preset depth or the continuous phase-leading operation time is greater than the second preset duration, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the phase-leading operation condition, the second preset depth is greater than the first preset depth, and the second preset duration is greater than the first preset duration; Under the delayed phase operation condition, when the load rate is greater than the first preset load rate and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition; Under the delayed phase operation condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate, and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition; Under the delayed phase operation condition, when the load rate is less than the second preset load rate and there is no advanced phase condition, the corresponding target turn-to-turn short-circuit trend criterion static threshold is calculated according to the base reference value and the reference turn-to-turn short-circuit trend criterion static threshold under the delayed phase operation condition; Under the alternating working conditions of leading and lagging phases, the reference turn-to-turn short-circuit trend criterion static threshold is used as the corresponding target turn-to-turn short-circuit trend criterion static threshold.

3. The generator turn-to-turn short circuit fault diagnosis method according to claim 1, characterized in that: Determining the degree of inter-turn short circuit according to the operation data includes: Establish dynamic excitation current model under different working conditions; Inputting the operation data into the dynamic excitation current model to calculate the excitation current calculation value; Get the current measured value of excitation current; The degree of inter-turn short circuit is calculated according to the calculated value of the excitation current and the current measured value of the excitation current.

4. The generator turn-to-turn short circuit fault diagnosis method according to claim 3, characterized in that: The step of inputting the operation data into the dynamic excitation current model to calculate the excitation current calculation value includes: Extracting the generator phase voltage, generator phase current, generator power factor angle, generator stator DC resistance, generator synchronous reactance and operating condition coefficient corresponding to the current operating condition from the operating data; The excitation current calculation value is obtained based on the dynamic excitation current model according to the generator phase voltage, the generator phase current, the generator power factor angle, the DC resistance of the generator stator, the synchronous reactance of the generator and the operating condition coefficient corresponding to the current operating condition.

5. The generator turn-to-turn short circuit fault diagnosis method according to any one of claims 1 to 4, characterized in that: The generator turn-to-turn short circuit fault diagnosis method further includes: Obtain excitation current, excitation voltage, rotor DC resistance, and inlet hydrogen temperature; Calculating the average temperature rise of the rotor under different working conditions according to the excitation current, the excitation voltage, the rotor DC resistance and the inlet hydrogen temperature; The average rotor temperature rise is compared with the calculated temperature rise output by the rotor temperature model, the rotor temperature rise in the motor temperature rise test and the calibrated rotor temperature rise in the manual, and the rotor turn-to-turn state is determined based on the comparison results.

6. A generator turn-to-turn short-circuit fault diagnosis device, characterized in that: The generator turn-to-turn short-circuit fault diagnosis device comprises: A calculation module is used to calculate the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator when the generator is started or during a no-load test, so as to obtain a base reference value for the inter-turn short-circuit trend criterion; Wherein, the calculation module is further used to obtain the excitation current and the vibration value of the steam excitation side of the generator when the generator is started or tested at no-load under preset generator parameters; Calculating the covariance and standard deviation between the excitation current and the vibration value of the steam excitation side of the generator; Calculating the Pearson correlation coefficient between the excitation current and the vibration of each part of the generator according to the covariance and the standard deviation to obtain a base reference value of the turn-to-turn short circuit trend criterion; Obtain historical operating data of the generator; Identifying the leading phase operation condition of the generator and the lagging phase operation condition of each different active power according to the historical operation data; Under the phase leading operation condition, when the phase leading depth is greater than the first preset depth or the continuous phase leading operation time is greater than the first preset duration, the Pearson correlation coefficient during the phase leading test is used as the reference turn-to-turn short circuit trend criterion static threshold value under the phase leading operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is greater than the first preset load rate and there is no leading phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value, and the second threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is greater than or equal to the second preset load rate, less than or equal to the first preset load rate, and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the first threshold value; Under the delayed phase operation condition, when the load rate is less than the second preset load rate and there is no advanced phase condition, the Pearson correlation coefficient at no load is used as the reference turn-to-turn short circuit trend criterion static threshold value under the delayed phase operation condition, and the reference turn-to-turn short circuit trend criterion static threshold value is greater than the second threshold value; Under the alternating working condition of leading phase and lagging phase, a Pearson correlation coefficient greater than a third threshold is used as a static threshold of a reference turn-to-turn short circuit trend criterion, and the third threshold is greater than the second threshold; The calculation module is further used to obtain a target turn-to-turn short-circuit trend criterion static threshold value corresponding to each working condition based on the base reference value and in combination with a reference turn-to-turn short-circuit trend criterion static threshold value under different working conditions; A diagnostic module, used for predicting the inter-turn short circuit trend of the generator according to the target inter-turn short circuit trend criterion static threshold; An acquisition module, used for acquiring the operation data of the generator when there is a tendency of inter-turn short circuit in the generator; The calculation module is further used to determine the degree of inter-turn short circuit according to the operation data.

7. A generator turn-to-turn short-circuit fault diagnosis device, characterized in that: The generator turn-to-turn short-circuit fault diagnosis device includes: a memory, a processor, and a generator turn-to-turn short-circuit fault diagnosis program stored in the memory and executable on the processor, wherein the generator turn-to-turn short-circuit fault diagnosis program is configured to implement the steps of the generator turn-to-turn short-circuit fault diagnosis method as described in any one of claims 1 to 5.

8. A storage medium, characterized in that: The storage medium stores a generator turn-to-turn short-circuit fault diagnosis program, which, when executed by a processor, implements the steps of the generator turn-to-turn short-circuit fault diagnosis method according to any one of claims 1 to 5.

Images