Processing method and system for alpha test data of stator coil bar of power generator

Abstract

The present invention relates to the technical field of power generator stator coil bar safety detection. Disclosed are a processing method and system for ALPHA test data of a stator coil bar of a power generator. The method comprise the following steps: acquiring ALPHA test data of a stator coil bar of a power generator on the basis of an ALPHA test unit, and calculating the acquired ALPHA test data; determining a health level of a stator of the power generator on the basis of an acquired calculation result; acquiring historical data, generating a curve trend chart on the basis of the determined health level of the stator of the power generator, and calculating a trend on the basis of the curve trend chart; and generating a maintenance scheme on the basis of the trend. The present invention can perform real-time updating on the basis of the change of data, and finally can more visually present a future state of the stator coil bar of the power generator on the basis of the generated curve trend chart, so that early-warning can be provided for workers, and compared with the prior art that a danger can be detected only when current occurs, and early-warning can be provided, the present invention can greatly reduce the occurrence of dangers.

Description

A method and system for processing ALPHA test data of generator stator bars Technical Field

[0001] This invention relates to the field of generator stator bar safety testing technology, and in particular to a method and system for processing generator stator bar ALPHA test data. Background Technology

[0002] During generator operation, there is a risk of partial discharge within the stator bars in the stator slots. By detecting the contact state between the stator bars and the stator core slots, the corona discharge state within the stator bar slots can be effectively assessed. This is achieved through the stator bar ALPHA test.

[0003] Traditional methods involve manually recording test data and calculating the ALPHA coefficient, processing the data and assessing stator health in a manual or semi-manual manner. This is inefficient, and existing manual methods struggle to track historical data. Furthermore, the inability to store, track, and study historical data hinders the prevention of stator slot discharges, resulting in damage being detected only after discharges have occurred.

[0004] Summary of the Invention

[0005] In view of the problems existing in the processing of ALPHA test data of generator stator bars and the existing systems, this invention is proposed.

[0006] Therefore, the problem that this invention aims to solve is that it cannot provide tracking and research of historical data storage, and thus cannot prevent discharge in the stator slots. As a result, in actual use, damage can only be detected after discharge has occurred.

[0007] To solve the above-mentioned technical problems, the present invention provides the following technical solution:

[0008] In a first aspect, embodiments of the present invention provide a method for processing ALPHA test data of generator stator bars, which includes the following steps:

[0009] The generator stator bars were obtained from the ALPHA test unit, and calculations were performed on the obtained ALPHA test data.

[0010] The health level of the generator stator is determined by the obtained calculation results;

[0011] Historical data is obtained, and a trend curve is generated based on the assessed health level of the generator stator. The trend is then calculated based on the trend curve.

[0012] Maintenance solutions are generated by following trends.

[0013] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the generator stator bar ALPHA test data includes measurement time, test number, slot number, horizontal position, vertical position, input voltage, input current, and contact resistance R. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3;

[0014] Data from the ALPHA experiment is stored in a CSV file, and data obtained in the same batch is saved in the same slot.

[0015] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the calculation method for the acquired ALPHA test data includes:

[0016] Identify the slot numbers in the acquired ALPHA experimental data, generate the corresponding number of table rows based on the number of slot numbers, and input the slot numbers into the corresponding table.

[0017] Construct an ALPHA coefficient calculation model to incorporate the contact resistance R from the ALPHA experimental data. c The measured voltages U0, U1, U2, and U3 are input into the ALPHA coefficient calculation model to obtain three ALPHA coefficients.

[0018] Enter the three ALPHA coefficients obtained into the corresponding tables according to the slot number;

[0019] The mathematical expression for the ALPHA coefficient calculation model is as follows:

[0020] In the formula, a1, a2, and a3 represent three ALPHA coefficients, and R c U0, U1, U2, and U3 are represented as contact resistance, while U0, U1, U2, and U3 are all represented as measured voltages.

[0021] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the method for determining the health level of the generator stator includes:

[0022] Based on historical data, the health level of the generator stator is set into high-risk, medium-risk, low-risk, and no-risk ranges.

[0023] The system judges the input ALPHA coefficient. When the ALPHA coefficient is in the high-risk range, it obtains the judgment results of the other two ALPHA coefficients in the same batch. When the other two ALPHA coefficients are in the high-risk range, it activates the alarm program and outputs a damage warning. When the other two ALPHA coefficients are not in the high-risk range but are in the medium-risk range, it activates the alarm program and outputs a damage warning and the horizontal and vertical positions associated with the ALPHA coefficient. When the other two ALPHA coefficients are not in the high-risk or medium-risk range but are in the low-risk range, it outputs a damage warning and the horizontal and vertical positions associated with the ALPHA coefficient. When the other two ALPHA coefficients are in the no-risk range, it generates a manual verification option and uses the manual output selection as the judgment result of the ALPHA coefficient.

[0024] An adaptive model is constructed to update the high-risk, medium-risk, low-risk, and risk-free intervals based on the judgment results and operating status of the generator stator.

[0025] Methods for outputting the horizontal and vertical positions associated with ALPHA coefficients include:

[0026] Identify the measurement voltages U0, U1, U2, or U3 involved in the ALPHA coefficient, then obtain the detection position of the measurement voltage based on the involved measurement voltage, and finally obtain the horizontal and vertical positions corresponding to the measurement voltage.

[0027] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the method for determining the health level of the generator stator further includes:

[0028] When the ALPHA coefficient is determined to be in the high-risk range, the corresponding slot number L is retrieved from the CSV file, and CSV files corresponding to slot numbers L-1 and L+1 are output. The contact resistance R corresponding to slot numbers L-1 and L+1 is then obtained from the output CSV files. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3;

[0029] Then, based on the ALPHA coefficient calculation model, the data corresponding to slot L-1 and slot L+1 are calculated to generate ALPHA coefficient A corresponding to slot L-1 and ALPHA coefficient B corresponding to slot L+1. Finally, ALPHA coefficient A and ALPHA coefficient B are judged.

[0030] When the ALPHA coefficient A is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L-2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient A-1 corresponding to slot L-2. This step is repeated until the ALPHA coefficient An corresponding to slot L-(n+1) is in the no-risk range.

[0031] When the ALPHA coefficient B is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L+2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient B+1 corresponding to slot L+2. This step is repeated until the ALPHA coefficient B+n corresponding to slot L+(n+1) is in the risk-free range.

[0032] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the method for establishing the curve trend graph includes:

[0033] A security authentication and authorization protocol is set up, and historical ALPHA test data of the unit is read through the REST standard interface. The historical data is input into the cloud data platform, and an initial prediction model for the curve trend is trained through machine learning algorithms. Then, the error rate between the prediction result and the actual result is calculated until the error rate is less than the set value. The prediction model of the curve trend is output, and finally, the prediction health level result is calculated through the prediction model. The prediction health level result is displayed on the curve to obtain the curve trend.

[0034] As a preferred embodiment of the method for processing ALPHA test data of generator stator bars according to the present invention, the method of using the adaptive model includes:

[0035] The ALPHA coefficient calculation model is used to determine the health level of the generator stator. A time threshold T is set, and ALPHA test data of the generator stator bar at the same location before T hours are extracted. The generator stator bar ALPHA test data is input, and the trend is calculated using the ALPHA coefficient calculation model to obtain the predicted health level. The actual health level and the predicted health level are then compared.

[0036] If the judgment results are the same, no change instruction is given;

[0037] When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted downward according to the changes and fluctuations.

[0038] When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted upward according to the fluctuation.

[0039] The expression for the adaptive model is:

[0040] W new =W old -γL

[0041] In the formula, γ represents the learning rate, and L represents the adjustment threshold.

[0042] Secondly, embodiments of the present invention provide a system for processing ALPHA test data of generator stator bars, which includes a data acquisition and preprocessing module, a data analysis and calculation module, a risk assessment module, and a prediction module;

[0043] The data acquisition and preprocessing module is responsible for collecting ALPHA test data of generator stator bars, including measurement time, test number, slot number, horizontal position, and vertical position, and performing preliminary data processing and storing the data in a CSV format file.

[0044] The data analysis and calculation module is used to construct an ALPHA coefficient calculation model based on ALPHA test data and calculate the specific ALPHA coefficient.

[0045] The risk assessment module analyzes and calculates the ALPHA coefficient, combines historical data and preset risk ranges to determine the health level of the generator stator;

[0046] The prediction module uses historical ALPHA test data and current measurement results to generate a curve trend graph, calculate the trend, and predict the future health status of the generator stator.

[0047] Thirdly, embodiments of the present invention provide a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor executes the computer program to implement any step of the above-described method for processing generator stator bar ALPHA test data.

[0048] Fourthly, embodiments of the present invention provide a computer-readable storage medium having a computer program stored thereon, wherein: when the computer program is executed by a processor, it implements any step of the above-described method for processing generator stator bar ALPHA test data.

[0049] The beneficial effects of this invention are as follows: By automatically recording data, operators can easily track and study historical data, and by integrating the data, an adaptive model can be obtained, which can further ensure the accuracy of the ALPHA coefficient calculation model. At the same time, it can be updated in real time according to data changes. Finally, the generated curve trend chart can more intuitively show the future state of the generator stator bars, which can play an early warning role for the staff. Compared with the previous method of detecting danger only when current appears, the early warning method can greatly reduce the occurrence of danger. Attached Figure Description

[0050] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. Wherein:

[0051] Figure 1 is a flowchart of the method for processing ALPHA test data of generator stator bars.

[0052] Figure 2 is a schematic diagram of the CSV format file for processing ALPHA test data of generator stator bars.

[0053] Figure 3 is a schematic diagram of the health level assessment method for processing ALPHA test data of generator stator bars. Detailed Implementation

[0054] To make the above-mentioned objects, features, and advantages of the present invention more apparent and understandable, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present invention, and not all of them. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the protection scope of the present invention.

[0055] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0056] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in different places in this specification does not necessarily refer to the same embodiment, nor is it a single or selective embodiment that is mutually exclusive with other embodiments.

[0057] This invention is described in detail with reference to the schematic diagrams. When detailing the embodiments of this invention, for ease of explanation, the cross-sectional views illustrating the device structure may be partially enlarged, not adhering to the usual scale. Furthermore, the schematic diagrams are merely examples and should not be construed as limiting the scope of protection of this invention. In actual fabrication, the three-dimensional spatial dimensions of length, width, and depth should be included.

[0058] Furthermore, in the description of this invention, it should be noted that the terms "upper," "lower," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings. These terms are used solely for the convenience of describing the invention and for simplifying the description, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on the invention. In addition, the terms "first," "second," or "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0059] Unless otherwise explicitly specified and limited, the terms "installation," "connection," and "joining" in this invention should be interpreted broadly. For example, they can refer to fixed connections, detachable connections, or integral connections; similarly, they can refer to mechanical connections, electrical connections, or direct connections, or indirect connections through an intermediate medium, or internal connections between two components. Those skilled in the art can understand the specific meaning of the above terms in this invention based on the specific circumstances.

[0060] Example 1

[0061] Referring to Figures 1-3, the first embodiment of the present invention provides a method for processing ALPHA test data of generator stator bars, including the following steps:

[0062] S1. Obtain ALPHA test data of generator stator bars from the ALPHA test unit and perform calculations on the obtained ALPHA test data.

[0063] As shown in Figure 2, the ALPHA test data for the generator stator bars includes measurement time, test number, slot number, horizontal position, vertical position, input voltage, input current, and contact resistance R. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3;

[0064] Data from the ALPHA experiment is stored in a CSV file, and data obtained in the same batch is saved in the same slot.

[0065] S2. Based on the obtained calculation results, determine the health level of the generator stator.

[0066] The calculation methods for the acquired ALPHA experimental data include:

[0067] Identify the slot numbers in the acquired ALPHA experimental data, generate the corresponding number of table rows based on the number of slot numbers, and input the slot numbers into the corresponding table.

[0068] Construct an ALPHA coefficient calculation model to incorporate the contact resistance R from the ALPHA experimental data. c The measured voltages U0, U1, U2, and U3 are input into the ALPHA coefficient calculation model to obtain three ALPHA coefficients.

[0069] Enter the three ALPHA coefficients obtained into the corresponding tables according to the slot number;

[0070] The mathematical expression for the ALPHA coefficient calculation model is as follows:

[0071] In the formula, a1, a2, and a3 represent three ALPHA coefficients, and R c U0, U1, U2, and U3 are represented as contact resistance, while U0, U1, U2, and U3 are all represented as measured voltages.

[0072] Methods for determining the health level of a generator stator include:

[0073] Based on historical data, the health level of the generator stator is set into high-risk, medium-risk, low-risk, and no-risk ranges.

[0074] The system assesses the input ALPHA coefficient. If the ALPHA coefficient is in a high-risk range, it retrieves the assessment results of the other two ALPHA coefficients in the same batch. If the other two ALPHA coefficients are in a high-risk range, it initiates an alarm program and outputs a damage warning. If the other two ALPHA coefficients are in a medium-risk range but not a high-risk range, it initiates an alarm program and outputs a damage warning along with the associated horizontal and vertical positions of the ALPHA coefficient. If the other two ALPHA coefficients are in a low-risk range but not a high-risk or medium-risk range, it outputs a damage warning along with the associated horizontal and vertical positions of the ALPHA coefficient. If the other two ALPHA coefficients are in a risk-free range, it generates a manual verification option and uses the manual selection as the assessment result for the ALPHA coefficient.

[0075] An adaptive model is constructed to update the high-risk, medium-risk, low-risk, and risk-free intervals based on the judgment results and operating status of the generator stator.

[0076] Methods for outputting the horizontal and vertical positions associated with ALPHA coefficients include:

[0077] Identify the measurement voltage U0, U1, U2, or U3 involved in the ALPHA coefficient, then obtain the detection position of the measurement voltage based on the involved measurement voltage, and finally obtain the horizontal and vertical positions corresponding to the measurement voltage.

[0078] Methods for assessing the health level of a generator stator also include,

[0079] When the ALPHA coefficient is determined to be in the high-risk range, the corresponding slot number L is retrieved from the CSV file, and CSV files corresponding to slot numbers L-1 and L+1 are output. The contact resistance R corresponding to slot numbers L-1 and L+1 is then obtained from the output CSV files. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3;

[0080] Then, based on the ALPHA coefficient calculation model, the data corresponding to slot L-1 and slot L+1 are calculated to generate ALPHA coefficient A corresponding to slot L-1 and ALPHA coefficient B corresponding to slot L+1. Finally, ALPHA coefficient A and ALPHA coefficient B are judged.

[0081] When the ALPHA coefficient A is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L-2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient A-1 corresponding to slot L-2. This step is repeated until the ALPHA coefficient An corresponding to slot L-(n+1) is in the no-risk range.

[0082] When the ALPHA coefficient B is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L+2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient B+1 corresponding to slot L+2. This step is repeated until the ALPHA coefficient B+n corresponding to slot L+(n+1) is in the no-risk range.

[0083] As shown in Figure 3, when the ALPHA coefficient A is in a high-risk range, the slot number corresponding to ALPHA coefficient A is obtained, and slot number 10 is used. Slot numbers surrounding slot number 10, namely slot numbers 11 and 9, are extracted. Simultaneously, the data information corresponding to slot numbers 11 and 9 is obtained, and the ALPHA coefficient calculation model is used to calculate the health level. It is then determined whether the calculated health level falls within a risk-free range. If neither falls within a risk-free range, slot numbers 12 and 8 are extracted, and their corresponding data information is obtained. The data information is calculated again, and the calculation result for slot number 8 is a risk-free range, while the calculation result for slot number 12 is a low-risk range. The extraction of slot numbers surrounding slot number 8 is then stopped, and only slot number 13 is extracted. The data information corresponding to slot number 13 is then obtained, and the ALPHA coefficient calculation model is used to calculate the health level. When the result is a risk-free range, the calculation stops, and the locations corresponding to all high-risk ranges are predicted as fault occurrence points.

[0084] S3. Obtain historical data, generate a curve trend chart of the judged health level of the generator stator, and calculate the trend based on the curve trend chart.

[0085] Methods for creating curve trend charts include:

[0086] A security authentication and authorization protocol is set up, and historical ALPHA test data of the unit is read through the REST standard interface. The historical data is input into the cloud data platform, and an initial prediction model for the curve trend is trained through machine learning algorithms. Then, the error rate between the prediction result and the actual result is calculated until the error rate is less than the set value. The prediction model of the curve trend is output, and finally, the prediction health level result is calculated through the prediction model. The prediction health level result is displayed on the curve to obtain the curve trend.

[0087] The methods for using adaptive models include,

[0088] Obtain the ALPHA coefficient calculation model's assessment of the generator stator's health level, set a time threshold T, extract ALPHA test data of the generator stator bars at the same location T hours ago, input the generator stator bar ALPHA test data, and then calculate the trend using the ALPHA coefficient calculation model to obtain the predicted health level. Finally, make a judgment between the actual health level and the predicted health level.

[0089] If the judgment results are the same, no change instruction is given;

[0090] When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted downward according to the changes and fluctuations.

[0091] When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted upward according to the fluctuation.

[0092] As can be seen from the table above, the error rate is minimized when the time threshold T = 24h.

[0093] The expression for the adaptive model is:

[0094] W new =W old -γL

[0095] In the formula, γ represents the learning rate, and L represents the adjustment threshold.

[0096] S4. Generate maintenance solutions by following trends.

[0097] In summary, the system's automatic recording method allows operators to easily track and study historical data. By integrating the data, an adaptive model can be obtained, further ensuring the accuracy of the ALPHA coefficient calculation model. Furthermore, the system can update in real time based on data changes, and the generated trend charts can more intuitively represent the future state of the generator stator bars, providing early warnings for staff. Compared to the previous method of detecting danger only when current occurs, this early warning method can greatly reduce the occurrence of dangers.

[0098] Example 2

[0099] Based on the first embodiment, this embodiment further provides a system for processing generator stator bar ALPHA test data, including a data acquisition and preprocessing module, a data analysis and calculation module, a risk assessment module, and a prediction module;

[0100] The data acquisition and preprocessing module is responsible for collecting ALPHA test data of generator stator bars, including measurement time, test number, slot number, horizontal position, and vertical position, and performing preliminary data processing and storing the data in a CSV format file.

[0101] The data analysis and calculation module is used to construct an ALPHA coefficient calculation model based on ALPHA test data and calculate the specific ALPHA coefficient.

[0102] The risk assessment module analyzes and calculates the ALPHA coefficient, combines historical data and preset risk ranges to determine the health level of the generator stator;

[0103] The prediction module uses historical ALPHA test data and current measurement results to generate a curve trend graph, calculate the trend, and predict the future health status of the generator stator.

[0104] This embodiment also provides a computer device applicable to the method for processing generator stator bar ALPHA test data, including a memory and a processor; the memory is used to store computer-executable instructions, and the processor is used to execute the computer-executable instructions to implement the generator stator bar ALPHA test data processing method proposed in the above embodiment.

[0105] The computer device can be a terminal, comprising a processor, memory, communication interface, display screen, and input devices connected via a system bus. The processor provides computing and control capabilities. The memory includes non-volatile storage media and internal memory. The non-volatile storage media stores the operating system and computer programs. The internal memory provides an environment for the operation of the operating system and computer programs stored in the non-volatile storage media. The communication interface is used for wired or wireless communication with external terminals; wireless communication can be achieved through Wi-Fi, carrier networks, NFC (Near Field Communication), or other technologies. The display screen can be an LCD screen or an e-ink screen. The input devices can be a touch layer covering the display screen, buttons, a trackball, or a touchpad on the computer device's casing, or an external keyboard, touchpad, or mouse.

[0106] This embodiment also provides a storage medium storing a computer program that, when executed by a processor, implements the method for processing generator stator bar ALPHA test data as proposed in the above embodiments.

[0107] The storage medium proposed in this embodiment and the data storage method proposed in the above embodiments belong to the same inventive concept. Technical details not described in detail in this embodiment can be found in the above embodiments, and this embodiment has the same beneficial effects as the above embodiments.

[0108] Example 3

[0109] Based on the previous two embodiments, this embodiment provides a method for processing ALPHA test data of generator stator bars. In order to verify the beneficial effects of the present invention, scientific demonstration is carried out through economic benefit calculation and simulation experiments.

[0110] Comparative Example 1: Using manual historical records, the future state of the generator stator bars is judged based on experience;

[0111] Comparative Example 2: Without introducing the identification of horizontal and vertical positions, the other structures are the same as in Example 1;

[0112] Comparative Example 3: No adaptive model is used; other structures are the same as in Example 1.

[0113] Table 1: Schematic diagram of generator stator bars under different conditions

[0114] Experimental method: Four identical datasets were set up. All data were calculated, and the calculation results were combined with the actual results. The accuracy of the prediction results was obtained by comparing whether they were consistent. It was also determined whether the calculated fault location was consistent with the actual location, and the calculation time was recorded.

[0115] As can be seen from Table 1, Comparative Example 1 is not advantageous in terms of prediction results, location judgment, and calculation time, and it requires a high level of technical skills from the staff. Comparative Example 2 cannot determine the fault location and has low practicality. The ALPHA coefficient calculation model of Comparative Example 3 cannot be updated, and it still relies on the old calculation method for new data, resulting in a gradual decrease in the accuracy of the prediction results. Example 1 can significantly solve the above problems.

[0116] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for processing ALPHA test data of generator stator bars, characterized in that: Includes the following steps, The generator stator bars were obtained from the ALPHA test unit, and calculations were performed on the obtained ALPHA test data. The health level of the generator stator is determined by the obtained calculation results; Historical data is obtained, and a trend curve is generated based on the assessed health level of the generator stator. The trend is then calculated based on the trend curve. Maintenance solutions are generated by following trends.

2. The method for processing ALPHA test data of generator stator bars as described in claim 1, characterized in that: Generator stator bar ALPHA test data includes measurement time, test number, slot number, horizontal position, vertical position, input voltage, input current, and contact resistance R. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3; Data from the ALPHA experiment is stored in a CSV file, and data obtained in the same batch is saved in the same slot.

3. The method for processing ALPHA test data of generator stator bars as described in claim 2, characterized in that: The calculation methods for the acquired ALPHA experimental data include: Identify the slot numbers in the acquired ALPHA experimental data, generate the corresponding number of table rows based on the number of slot numbers, and input the slot numbers into the corresponding table. Construct an ALPHA coefficient calculation model to incorporate the contact resistance R from the ALPHA experimental data. c The measured voltages U0, U1, U2, and U3 are input into the ALPHA coefficient calculation model to obtain three ALPHA coefficients. Enter the three ALPHA coefficients obtained into the corresponding tables according to the slot number; The mathematical expression for the ALPHA coefficient calculation model is as follows: In the formula, a1, a2, and a3 represent three ALPHA coefficients, and R c U0, U1, U2, and U3 represent contact resistance, while U0, U1, U2, and U3 represent measured voltages.

4. The method for processing ALPHA test data of generator stator bars as described in claim 3, characterized in that: Methods for determining the health level of a generator stator include: Based on historical data, the health level of the generator stator is set into high-risk, medium-risk, low-risk, and no-risk ranges. The system judges the input ALPHA coefficient. When the ALPHA coefficient is in the high-risk range, it obtains the judgment results of the other two ALPHA coefficients in the same batch. When the other two ALPHA coefficients are in the high-risk range, it activates the alarm program and outputs a damage warning. When the other two ALPHA coefficients are not in the high-risk range but are in the medium-risk range, it activates the alarm program and outputs a damage warning and the horizontal and vertical positions associated with the ALPHA coefficient. When the other two ALPHA coefficients are not in the high-risk or medium-risk range but are in the low-risk range, it outputs a damage warning and the horizontal and vertical positions associated with the ALPHA coefficient. When the other two ALPHA coefficients are in the no-risk range, it generates a manual verification option and uses the manual selection as the judgment result of the ALPHA coefficient. An adaptive model is constructed to update the high-risk, medium-risk, low-risk, and risk-free intervals based on the judgment results and operating status of the generator stator. Methods for outputting the horizontal and vertical positions associated with ALPHA coefficients include: Identify the measurement voltages U0, U1, U2, or U3 involved in the ALPHA coefficient, then obtain the detection position of the measurement voltage based on the involved measurement voltage, and finally obtain the horizontal and vertical positions corresponding to the measurement voltage.

5. The method for processing ALPHA test data of generator stator bars as described in claim 4, characterized in that: Methods for assessing the health level of a generator stator also include, When the ALPHA coefficient is determined to be in the high-risk range, the corresponding slot number L is retrieved from the CSV file, and CSV files corresponding to slot numbers L-1 and L+1 are output. The contact resistance R corresponding to slot numbers L-1 and L+1 is then obtained from the output CSV files. c , Measured voltage U0, Measured voltage U1, Measured voltage U2, and Measured voltage U3; Then, based on the ALPHA coefficient calculation model, the data corresponding to slot number L-1 and slot number L+1 are calculated. Generate ALPHA coefficient A corresponding to slot L-1 and ALPHA coefficient B corresponding to slot L+1, and finally judge ALPHA coefficient A and ALPHA coefficient B. When the ALPHA coefficient A is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L-2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient A-1 corresponding to slot L-2. This step is repeated until the ALPHA coefficient An corresponding to slot L-(n+1) is in the no-risk range. When the ALPHA coefficient B is in the high-risk, medium-risk, or low-risk range, the data corresponding to slot L+2 is calculated according to the ALPHA coefficient calculation model to generate the ALPHA coefficient B+1 corresponding to slot L+2. This step is repeated until the ALPHA coefficient B+n corresponding to slot L+(n+1) is in the risk-free range.

6. The method for processing ALPHA test data of generator stator bars as described in claim 5, characterized in that: The methods for creating the curve trend chart include: A security authentication and authorization protocol is set up, and historical ALPHA test data of the unit is read through the REST standard interface. The historical data is input into the cloud data platform, and an initial prediction model for the curve trend is trained through machine learning algorithms. Then, the error rate between the prediction result and the actual result is calculated until the error rate is less than the set value. The prediction model of the curve trend is output, and finally, the prediction health level result is calculated through the prediction model. The prediction health level result is displayed on the curve to obtain the curve trend.

7. The method for processing ALPHA test data of generator stator bars as described in claim 6, characterized in that: The method of using the adaptive model includes, The ALPHA coefficient calculation model is used to determine the health level of the generator stator. A time threshold T is set, and ALPHA test data of the generator stator bar at the same location before T hours are extracted. The generator stator bar ALPHA test data is input, and the trend is calculated using the ALPHA coefficient calculation model to obtain the predicted health level. The actual health level and the predicted health level are then compared. If the judgment results are the same, no change instruction is given; When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted downward according to the changes and fluctuations. When the judgment results are different and the actual health level is higher than the predicted health level, the threshold of the adaptive model expression is adjusted upward according to the fluctuation. The expression for the adaptive model is: IN new =In old -γL In the formula, γ represents the learning rate, and L represents the adjustment threshold.

8. A system for processing ALPHA test data of generator stator bars, based on the method for processing ALPHA test data of generator stator bars according to any one of claims 1 to 7, characterized in that: It includes a data acquisition and preprocessing module, a data analysis and calculation module, a risk assessment module, and a prediction module; The data acquisition and preprocessing module is responsible for collecting ALPHA test data of generator stator bars, including measurement time, test number, slot number, horizontal position, and vertical position, and performing preliminary data processing and storing the data in a CSV format file. The data analysis and calculation module is used to construct an ALPHA coefficient calculation model based on ALPHA test data and calculate the specific ALPHA coefficient. The risk assessment module analyzes and calculates the ALPHA coefficient, combines historical data and preset risk ranges to determine the health level of the generator stator; The prediction module uses historical ALPHA test data and current measurement results to generate a curve trend graph, calculate the trend, and predict the future health status of the generator stator.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that: When the processor executes the computer program, it implements the steps of the method for processing ALPHA test data of generator stator bars as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by the processor, it implements the steps of the method for processing ALPHA test data of generator stator bars as described in any one of claims 1 to 7.

Images