Water-turbine generator set stator winding temperature prediction method and device and storage medium

Through multivariate linear regression model and data preprocessing technology, the problem of rising stator winding temperature of the hydropower generator set is solved, and accurate prediction and early warning of stator winding temperature is realized, ensuring the safe operation of the equipment.

CN119090045AInactive Publication Date: 2024-12-06CHINA YANGTZE POWER

Patent Information

Application Number
CN202411014867.2
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-26
Publication Date
2024-12-06
Estimated Expiration
Not applicable · inactive patent

AI Technical Summary

Technical Problem

Increased stator winding temperature during long-term operation of the hydrowheel generator set may lead to aging of insulation materials and safety accidents, and the prior art is difficult to effectively predict and early warning.

Method used

The multivariate linear regression model is used to combine historical and real-time data to calculate the stator winding temperature, set the deviation warning threshold, and determine whether the stator winding temperature is abnormal through data cleaning and preprocessing, and provide real-time temperature prediction and early warning.

Benefits of technology

Accurate prediction and early warning of the stator winding temperature of the hydrowheel generator set is achieved, avoiding potential safety risks caused by excessive temperature.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119090045A_ABST
    Figure CN119090045A_ABST
Patent Text Reader

Abstract

The invention discloses a water-turbine generator set stator winding temperature prediction method and device and a storage medium, and the method comprises the steps: obtaining the historical operation condition data of a stator winding under the normal operation condition of a water-turbine generator, and calculating the standard temperature data of the stator winding under the historical operation condition through a multiple linear regression model; acquiring real-time operation data of a stator winding of the water turbine generator set at a certain moment, and calculating real-time temperature data of the stator winding under a real-time working condition by using the multiple linear regression model; under the same working condition, the deviation between the real-time temperature data and the standard temperature data is calculated; setting a temperature deviation early-warning threshold value of the stator winding of the water-turbine generator set; and comparing the deviation value of the real-time temperature data and the standard temperature data and the deviation early-warning threshold value, and judging whether the temperature of the generator stator winding is abnormal or not. And the prediction accuracy and efficiency are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The invention relates to a hydroelectric power generation equipment testing technology, and in particular to a method, a device and a storage medium for predicting the temperature of a stator winding of a hydroelectric generator set. Background Art

[0002] A hydro-turbine generator set is a device that converts water energy into electrical energy. It is an important device for hydroelectric power generation. Its operating status directly affects the stability and safety of the power system. During long-term operation, the temperature of the stator winding will gradually increase due to electromagnetic loss and heat loss. Excessive temperature may cause aging of insulation materials, reduce the electrical performance of the equipment, and even cause safety accidents. Therefore, predicting the stator winding temperature is crucial for the safe operation of the hydro-turbine generator. Summary of the invention

[0003] The invention provides a method, a device and a storage medium for predicting the temperature of a stator winding of a hydro-generator set.

[0004] In a first aspect, the present invention provides a method for predicting the temperature of a stator winding of a hydro-turbine generator set, the method comprising: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

[0005] Furthermore, the method uses a multivariate linear regression model to calculate the stator winding temperature data, specifically: The formula for calculating the stator winding temperature is: Y=β 0 +β 1 X 1 +β 2 X 2+β 3 X 3 +β 4 X 4 +β 5 X 5 +β 6 X 6 +β 7 X 7 +β 8 X 8 ; Where, Y is the stator winding temperature, is the stator voltage, is the stator current, is the stator core temperature, is the cooling water flow rate of the air cooler, is the air cooler inlet water pressure, is the outlet water pressure of the air cooler, is the air cooler inlet water temperature, is the air cooler outlet water temperature, It is a set of valid reference operating data corresponding to the same time under the normal operating condition of the generator; is a constant term, to is the regression coefficient of each parameter.

[0006] Furthermore, the method further includes: before calculating the real-time temperature data of the stator winding under the real-time working condition, performing data cleaning and preprocessing on the acquired real-time operation data, and processing abnormal data and missing data, specifically: For the processing of null values, if all variable values ​​at that moment are null values, the value at that moment will not be calculated or predicted; if a variable value is null, the variable will be filled with the average value of the first 50 sets of historical sampling data; For outliers and missing values, the median of the first 50 sets of historical data of the variable is used to fill them.

[0007] Furthermore, a temperature deviation warning threshold of the stator winding of the hydro-turbine generator set is set, specifically: A first warning threshold and a second warning threshold of the temperature deviation of the stator winding of the hydro-turbine generator set are set, wherein the second warning threshold is smaller than the first warning threshold.

[0008] Furthermore, the deviation value of the real-time temperature data and the standard temperature data, as well as the deviation warning threshold value, are compared to determine whether the stator winding temperature of the generator is abnormal. Specifically: If the deviation value between the real-time temperature data and the standard temperature data is less than the second warning threshold, it is judged that the generator stator is operating normally; if the deviation value is greater than the second warning threshold and less than the first warning threshold, it is judged that the temperature of the generator stator fluctuates; if the deviation value is greater than the first warning threshold, it is judged that the temperature of the generator stator is abnormal.

[0009] Furthermore, the historical operating condition data of the stator winding is the effective reference operating data of the stator winding under the normal operating condition of the generator, and the data acquisition cycle is one year.

[0010] Furthermore, a temperature deviation warning threshold of the stator winding of the hydro-turbine generator set is set, specifically: The second warning threshold is set to the difference between the maximum and minimum values ​​of the stator winding standard temperature data under the historical operating conditions calculated using the multivariate linear regression model; the first warning threshold is set to be 5°C higher than the second warning threshold.

[0011] In a second aspect, the present invention provides a device for predicting the temperature of a stator winding of a hydro-generator set, the device comprising: Module for calculating stator winding standard temperature data, used for: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Calculate the real-time temperature data module of stator winding, used for: Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Prediction and judgment module, used for: Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

[0012] In a third aspect, the present invention provides a device for predicting the temperature of a stator winding of a hydro-generator set, the device comprising: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0013] In a fourth aspect, the present invention provides a storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to execute the above method.

[0014] Compared with the prior art, the present invention has the following advantages: The present invention not only predicts the real-time temperature of the stator winding during the operation of the hydro-generator set, but also calculates its deviation by comparing it with the standard temperature data, so as to give an early warning when the real-time temperature of the stator winding has not yet reached its critical value. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 A schematic diagram of a method for predicting the stator winding temperature of a hydro-generator set provided by an embodiment of the present invention; Figure 2 A schematic diagram of the composition of a device for predicting the temperature of a stator winding of a hydro-generator set provided by an embodiment of the present invention; Figure 3 A schematic diagram of the composition of a device for predicting the stator winding temperature of a hydro-generator set provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0016] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0017] Figure 1 A schematic diagram of a method for predicting the stator winding temperature of a hydro-generator set provided by an embodiment of the present invention, the method comprising: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

[0018] When predicting the stator winding temperature of the generator, the embodiment of the present invention fully considers the influence of the stator current, stator voltage, stator core temperature, air cooler cooling water flow, air cooler water inlet pressure, air cooler water outlet pressure, air cooler water inlet temperature, and air cooler water outlet temperature on the stator winding temperature, making the prediction more accurate.

[0019] In one embodiment, the method uses a multivariate linear regression model to calculate the stator winding temperature data, specifically: The formula for calculating the stator winding temperature is: Y=β 0 +β 1 X 1 +β 2 X 2 +β 3 X 3 +β 4 X 4 +β 5 X 5 +β 6 X 6 +β 7 X 7 +β 8 X 8 ; Where Y is the stator winding temperature, is the stator voltage, is the stator current, is the stator core temperature, is the cooling water flow rate of the air cooler, is the air cooler inlet water pressure, is the outlet water pressure of the air cooler, is the air cooler inlet water temperature, is the air cooler outlet water temperature, It is a set of valid reference operating data corresponding to the same time under the normal operating condition of the generator; is a constant term, to is the regression coefficient of each parameter.

[0020] In one embodiment, the method further includes: before calculating the real-time temperature data of the stator winding under the real-time working condition, performing data cleaning and preprocessing on the acquired real-time operation data, and processing abnormal data and missing data, specifically: For the processing of null values, if all variable values ​​at that moment are null values, the value at that moment will not be calculated or predicted; if a variable value is null, the variable will be filled with the average value of the first 50 sets of historical sampling data; For outliers and missing values, the median of the first 50 sets of historical data of the variable is used to fill them.

[0021] In one embodiment, the temperature deviation warning threshold of the stator winding of the hydro-generator set is set, specifically: A first warning threshold and a second warning threshold of the temperature deviation of the stator winding of the hydro-turbine generator set are set, wherein the second warning threshold is smaller than the first warning threshold.

[0022] In one embodiment, the deviation value of the real-time temperature data and the standard temperature data and the deviation warning threshold are compared to determine whether the stator winding temperature of the generator is abnormal, specifically: If the deviation value between the real-time temperature data and the standard temperature data is less than the second warning threshold, it is judged that the generator stator is operating normally; if the deviation value is greater than the second warning threshold and less than the first warning threshold, it is judged that the temperature of the generator stator fluctuates; if the deviation value is greater than the first warning threshold, it is judged that the temperature of the generator stator is abnormal.

[0023] In one embodiment, the historical operating condition data of the stator winding is effective reference operating data of the stator winding under normal operating conditions of the generator, and the data acquisition cycle is one year.

[0024] In one embodiment, the temperature deviation warning threshold of the stator winding of the hydro-generator set is set, specifically: The second warning threshold is set to the difference between the maximum and minimum values ​​of the stator winding standard temperature data under the historical operating conditions calculated using the multivariate linear regression model; the first warning threshold is set to be 5°C higher than the second warning threshold.

[0025] Further explanation, in order to more accurately predict and evaluate the temperature of the generator stator winding, a first-level alarm threshold and a second-level alarm threshold are set, so that the deviation between the real-time temperature data and the standard temperature data can be more accurately evaluated. When applying, it is necessary to consider the comprehensive influence of the structure, capacity, working conditions and environmental factors of different generators, so as to formulate specific parameters of the first-level and second-level preset thresholds. In the specific evaluation process, if the deviation is small, that is, the deviation is less than the second-level preset threshold, it means that the generator stator is operating normally; if the deviation is general, that is, the deviation is greater than the second-level preset threshold and less than the first-level preset threshold, it means that the temperature of the generator stator fluctuates, and it is necessary to strengthen the operation monitoring and shorten the monitoring and evaluation cycle; if the deviation is large or even exceeds the first-level preset threshold, it is judged that the temperature of the generator stator is abnormal and needs to be repaired as soon as possible. It should be noted that this embodiment does not limit the specific value of the second-level preset threshold. If the second-level preset threshold is too high, it may miss the abnormal situation. If the second preset threshold is too low, a false alarm may occur.

[0026] Figure 2 A schematic diagram of a device for predicting the temperature of a stator winding of a hydro-turbine generator set provided by an embodiment of the present invention, the device comprising: Module for calculating stator winding standard temperature data, used for: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature, and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Calculate the real-time temperature data module of stator winding, used for: Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature, air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Prediction and judgment module, used for: Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

[0027] Figure 3A schematic diagram of a device for predicting the temperature of a stator winding of a hydro-generator set provided by an embodiment of the present invention; the device comprises: Memory, used to store programs; The processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the above method.

[0028] In addition, an embodiment of the present invention provides a storage medium storing computer-readable instructions. When the computer-readable instructions are executed by one or more processors, the one or more processors execute the above method.

[0029] Finally, it should be noted that the above are only preferred embodiments of the present invention and are not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art can still modify the technical solutions described in the aforementioned embodiments or replace some of the technical features therein by equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for predicting the stator winding temperature of a hydro-generator set, characterized in that: Methods include: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

2. The method for predicting the stator winding temperature of a hydro-generator set according to claim 1, characterized in that: The method uses a multivariate linear regression model to calculate the stator winding temperature data, specifically: The formula for calculating the stator winding temperature is: Y=β0+β1X1+β2X2+β3X3+β4X4+β5X5+β6X6+β7X7+β8X8; Where, Y is the stator winding temperature, is the stator voltage, is the stator current, is the stator core temperature, is the cooling water flow rate of the air cooler, is the air cooler inlet water pressure, is the outlet water pressure of the air cooler, is the air cooler inlet water temperature, is the air cooler outlet water temperature, It is a set of valid reference operating data corresponding to the same time under the normal operating condition of the generator; is a constant term, to is the regression coefficient of each parameter.

3. The method for predicting the stator winding temperature of a hydro-generator set according to claim 1, characterized in that: Also includes: Before calculating the real-time temperature data of the stator winding under real-time working conditions, the acquired real-time operation data is cleaned and preprocessed to handle abnormal data and missing data, specifically: For the processing of null values, if all variable values ​​at that moment are null values, the value at that moment will not be calculated or predicted; if a variable value is null, the variable will be filled with the average value of the first 50 sets of historical sampling data; For outliers and missing values, the median of the first 50 sets of historical data of the variable is used to fill them.

4. The method for predicting the stator winding temperature of a hydro-generator set according to claim 1, characterized in that: Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set, specifically: A first warning threshold and a second warning threshold of the temperature deviation of the stator winding of the hydro-turbine generator set are set, wherein the second warning threshold is smaller than the first warning threshold.

5. The method for predicting the stator winding temperature of a hydro-generator set according to claim 1, characterized in that: Compare the deviation value and deviation warning threshold between the real-time temperature data and the standard temperature data to determine whether the stator winding temperature of the generator is abnormal. Specifically: If the deviation value between the real-time temperature data and the standard temperature data is less than the second warning threshold, it is judged that the generator stator is operating normally; if the deviation value is greater than the second warning threshold and less than the first warning threshold, it is judged that the temperature of the generator stator fluctuates; if the deviation value is greater than the first warning threshold, it is judged that the temperature of the generator stator is abnormal.

6. The method for predicting the stator winding temperature of a hydro-generator set according to claim 1, characterized in that: The historical operating condition data of the stator winding is the effective reference operating data of the stator winding under normal operating conditions of the generator, and the data acquisition period is one year.

7. The method for predicting the stator winding temperature of a hydro-generator set according to claim 4, characterized in that: Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set, specifically: The second warning threshold is set to be the difference between the maximum value and the minimum value of the stator winding standard temperature data under the historical operating conditions calculated using the multivariate linear regression model; The first warning threshold is set to be 5°C higher than the second warning threshold.

8. A device for predicting the temperature of a stator winding of a hydro-generator set, characterized in that: The device includes: Module for calculating stator winding standard temperature data, used for: Obtain historical operating condition data of the stator winding under normal operating conditions of the hydro-generator, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The multivariate linear regression model is used to calculate the standard temperature data of the stator winding under historical operating conditions; Calculate the real-time temperature data module of the stator winding, used for: Obtain the real-time operating data of the stator winding of the hydro-generator set at a certain moment, including: stator voltage, stator current, stator core temperature, air cooler cooling water flow, air cooler inlet water pressure, air cooler outlet water pressure, air cooler inlet water temperature and air cooler outlet water temperature; The real-time temperature data of stator windings under real-time working conditions is calculated using a multivariate linear regression model; Prediction and judgment module, used for: Under the same working conditions, calculate the deviation between real-time temperature data and standard temperature data; Set the temperature deviation warning threshold of the stator winding of the hydro-turbine generator set; Compare the deviation value of real-time temperature data and standard temperature data, and the size of the deviation warning threshold to determine whether the temperature of the generator stator winding is abnormal.

9. The device for predicting the temperature of the stator winding of a hydro-generator set according to claim 8, characterized in that: The device also includes: Memory, used to store programs; A processor is used to execute the program stored in the memory. When the program stored in the memory is executed, the processor is used to execute the steps of the method as claimed in any one of claims 1 to 7.

10. A storage medium storing computer-readable instructions, which, when executed by one or more processors, causes the one or more processors to perform the steps of the method according to any one of claims 1 to 7.

Citation Information

Patent Citations

  • Nuclear power station diesel generating set coil temperature early warning method and system

    CN111046582A

  • Generator stator temperature monitoring method and device and medium

    CN112504511A

  • Stator winding temperature correction method and device based on temperature field simulation model

    CN113268886A

  • Generator winding temperature early warning method and device

    CN115719006A

  • Method for online evaluation of failure caused by rotoric eccentricity generators and synchronous motors

    WO2013024500A1

Cited By

  • Temperature early warning method and device for electrical connection point, storage medium and electronic equipment

    CN120277581A

  • Temperature early warning method and device of electrical connection point, storage medium and electronic equipment

    CN120277581B

  • Generator set operation maintenance data analysis system and method based on three-dimensional modeling

    CN120296636A