Hydropower station data analysis and scheduling method

Abstract

The invention relates to the field of hydropower station data processing, in particular to a hydropower station data analysis and scheduling method, which specifically comprises the following steps: S1, acquiring first working parameters of each group of water turbines in a hydropower station in real time, and storing the first working parameters in a database; s2, calculating a first health degree value of each group of water turbines according to the first working parameter of each time point; s3, optimizing the first health degree value Ht to generate a second health degree value; s4, whether the corresponding water turbine breaks down or not is judged according to the second health degree value; according to the method, when the health degree value of the water turbine is calculated, the influence of mutual influence of different parameters on the health degree value is considered, the influence of workers on the health degree of the water turbine is also considered, and the accuracy of evaluating the health degree of the water turbine can be effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of hydropower station data processing, and specifically to a method for hydropower station data analysis and scheduling. Background Art

[0002] The water turbine is one of the main equipment in a hydropower plant. When scheduling the working intensity of the water turbine, it is necessary to analyze the health degree of the water turbine and calculate the opening degree of the water turbine according to the health degree.

[0003] The common calculation method is to obtain information such as water flow rate, water flow pressure, and water turbine guide vane opening degree that affect the health degree of the water turbine, and calculate the health degree of the water turbine according to the above information. However, there may be mutual influences between these parameters, which ultimately affect the health degree of the water turbine. The above calculation method does not consider this problem, resulting in a large error in calculating the health degree of the water turbine, and it will also be affected when adjusting the working intensity of the water turbine according to the health degree in the later stage, leading to the phenomenon that the water turbine with a lower health degree continues to work and causes damage. Summary of the Invention

[0004] In view of the deficiencies of the prior art, the present invention provides a method for hydropower station data analysis and scheduling, which solves the technical problem that the mutual influence between the information affecting the health degree of the water turbine is not considered in the prior art, resulting in inaccurate calculation of the health degree of the water turbine and water turbine damage when scheduling the working intensity of the water turbine.

[0005] To achieve the above object, the present invention provides the following technical solutions:

[0006] A method for hydropower station data analysis and scheduling specifically includes the following steps:

[0007] S1. Real-time obtain the first working parameters of each group of water turbines in the hydropower station and store them in the database. The first working parameters include water flow rate, water flow pressure, water turbine guide vane opening degree, water turbine vibration amplitude, water turbine shaft displacement, water turbine temperature, water turbine noise, and water turbine efficiency η th ;

[0008] S2. Calculate the first health degree value H of each group of water turbines according to the first working parameters at each time point t ;

[0009] S3. Optimize the first health degree value H t to generate the second health degree value;

[0010] S4. Judge whether the corresponding water turbine is faulty according to the second health degree value;

[0011] If so, shut down the water turbine and end;

[0012] If not, go to step S5;

[0013] S5. Schedule the gate opening G corresponding to each group of turbines according to the second health value i for dispatching.

[0014] Furthermore, the formula for the efficiency η of the turbine is: th as follows:

[0015]

[0016] In the formula, T represents the torque borne by the turbine blades; N represents the rotational speed of the turbine; ρ represents the density of water; g represents the acceleration due to gravity; H 1 represents the liquid level height upstream of the pipeline; H 2 represents the liquid level height downstream of the pipeline; Q represents the water flow rate in the pipeline.

[0017] Furthermore, in step S2, it specifically includes the following steps:

[0018] S21. Obtain the first working parameters at each time point and construct a set of first working parameters respectively represent the water flow rate, water flow pressure, turbine guide vane opening, turbine vibration amplitude, turbine shaft displacement, turbine temperature, turbine noise, and turbine efficiency η th ;

[0019] S22. Standardize the set of first working parameters to generate a set of second working parameters whose expression is:

[0020]

[0021] In the formula, x min represents the historical minimum value of the i-th first working parameter; x max represents the historical maximum value of the i-th first working parameter;

[0022] S23. Calculate the first health value H at each time point according to the set of second working parameters ; t .

[0023] Furthermore, in step S23, it specifically includes the following steps:

[0024] S231. Construct a non-linear conversion function according to the mutual influence relationship between the first working parameters whose expression is:

[0025]

[0026] In the formula, a 0 represents the constant term with respect to ; a 1 and a 2 respectively represent the coefficients of the linear term and the quadratic term of

[0027] S232. Calculate the first health degree value H according to the non-linear conversion function t , and its calculation formula is:

[0028]

[0029] In the formula, n represents the total number of the first working parameters; w 0 represents the bias term; w i represents the weight coefficient of the i-th parameter; w ij represents the weight coefficient of the interaction between the i-th and the j-th parameters; represents the weight parameter with respect to .

[0030] Furthermore, in step S3, it specifically includes the following steps:

[0031] S31. Set a sliding window with a length of T and a step size of L in the first health degree value H t , and obtain a training sample every time the sliding window slides once;

[0032] S32. Optimize the last first health degree value H zt in each training sample to generate a sample label HY t , and its calculation formula is:

[0033]

[0034] In the formula, W i represents the weight parameter with respect to the i-th H t ; α represents the weight parameter with respect to H zt ;

[0035] S33. Construct a training set according to the training samples and the sample label HY t ;

[0036] S34. Use the training set to train the long short-term memory network to generate a target model;

[0037] S35. When the sliding window selects the first health degree value H t at the current time, generate an input parameter set;

[0038] S36. Input the input parameter set into the target model and output the second health value.

[0039] Further, in step S4, it specifically includes the following steps:

[0040] S41. Calculate the average health value H t of the first health values The calculation formula is:

[0041]

[0042] In the formula, represents the i-th first health value H t ; N represents the total number of the first health values H t ;

[0043] S42. Calculate the standard deviation σ based on the average health value H The calculation formula is:

[0044]

[0045] S43. Calculate the standard health value H std The calculation formula is:

[0046]

[0047] In the formula, β represents the safety margin coefficient;

[0048] S44. Determine whether the second health value is lower than the standard health value H std ;

[0049] If so, it indicates that the water turbine is faulty;

[0050] If not, it indicates that the water turbine is not faulty.

[0051] Further, in step S5, it specifically includes the following steps:

[0052] S51. Obtain the total generated power P total of the hydropower plant and the maximum generated power

[0053] of each group of working water turbines total S52. Calculate the total health value H

[0054]

[0055] In the formula, m represents the total number of working water turbines; L represents the maximum value; e represents the base of the natural logarithm; k represents the curve steepness; h iRepresents the second health degree value of the i-th group of turbines; x 0 Represents the center point of the curve;

[0056] S53. According to the total health degree value H total Calculate the allocated power generation P of each group of turbines i , and its calculation formula is:

[0057]

[0058] S54. According to the allocated power generation P i Calculate the gate opening G of each group of turbines i .

[0059] Furthermore, in step S54, the calculation formula of the gate opening G i is:

[0060]

[0061] In the formula, ln represents the logarithmic function; ω 1 , ω 2 , ω 3 and ω 4 respectively represent the first, second, third, and fourth weight parameters with respect to G i .

[0062] Compared with the prior art, the present invention provides a method for analyzing and scheduling data of a hydropower station, having the following beneficial effects:

[0063] 1. When calculating the health degree value of the turbine, the present invention not only considers the influence of the mutual influence between different parameters on the health degree value, but also considers the influence of the staff on the health degree of the turbine, which can effectively improve the accuracy of evaluating the health degree of the turbine. Moreover, when calculating the gate opening, considering the non-linear influence relationship between the power generation of the turbine and the health degree, the accuracy of calculating the gate opening can be further improved, and the average life of all gates can be increased.

[0064] 2. When calculating the allocated power generation of each group of turbines, the present invention considers the non-linear relationship between the power generation of the turbine and the second health degree value of the turbine. Therefore, compared with the common calculation methods, the accuracy of calculating the allocated power generation is higher, and further the accuracy of calculating the gate opening is improved.

[0065] 3. When optimizing the first health degree value, the present invention considers the influence of the staff on the health degree of the turbine. Compared with the common calculation methods, the accuracy of evaluating the health degree of the turbine is higher.

[0066] 4. The present invention evaluates the health condition of the water turbine in each period, so that when optimizing the first health degree value later, information such as the level and frequency of maintenance, repair, and component replacement by the staff can be added to further improve the more accurate evaluation of the health condition of the water turbine. BRIEF DESCRIPTION OF THE DRAWINGS

[0067] The drawings described herein are used to provide a further understanding of the present application, and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation of the present application. In the drawings:

[0068] Figure 1 is a flowchart of a method for data analysis and scheduling of a hydropower station according to the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0069] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the drawings and specific embodiments. Thereby, a full understanding of how the present application uses technical means to solve technical problems and achieve technical effects can be obtained and implemented accordingly.

[0070] The water turbine is one of the main equipment in the hydropower plant, and is responsible for driving the generator to rotate and thus generating electricity. During the operation of the water turbine, the guide vanes of the water turbine will be affected by factors such as water flow pressure and water flow impact force. In the case of long-term use, they will be damaged. Therefore, it is necessary to evaluate the health condition of each water turbine. Therefore, please refer to Figure 1 as shown, a method for data analysis and scheduling of a hydropower station is proposed, which specifically includes the following steps:

[0071] S1. Real-time obtain the first working parameters of each group of water turbines in the hydropower plant and store them in the database. The first working parameters include water flow rate, water flow pressure, water turbine guide vane opening, water turbine vibration amplitude, water turbine shaft displacement, water turbine temperature, water turbine noise, and water turbine efficiency η th ; Specifically, when evaluating the working conditions of the water turbine and the generator, it is necessary to more accurately analyze the health condition and aging degree of the water turbine and the generator according to their respective working parameters, and it is necessary to accurately obtain the above parameters. Therefore, the following equipment is set in the hydropower plant:

[0072] Ultrasonic flowmeter or electromagnetic flowmeter: directly measure the water flow velocity and volume in the pipeline to obtain the water flow rate;

[0073] Pressure sensor: real-time monitor the water pressure change to obtain the water flow pressure;

[0074] Position sensor or angular displacement sensor: monitor the angle change of the guide vane to directly reflect the opening of the guide vane;

[0075] Acceleration sensor or speed sensor: Monitor the vibration at the bearing positions of the water turbine and the generator to detect the vibration amplitude of the water turbine;

[0076] Linear displacement sensor or eddy current sensor: Measure the axial movement of the water turbine shaft;

[0077] Thermocouple or thermal resistance sensor: Monitor the temperature of the water turbine;

[0078] Sound level meter: Measure the ambient noise level and analyze the spectral characteristics to obtain the water turbine noise;

[0079] Rotational speed sensor or coding monitor: Monitor the rotational speed of the water turbine;

[0080] Strain type torque sensor: Monitor the torque borne by the blades of the water turbine;

[0081] Liquid level sensor: Monitor the liquid level heights upstream and downstream of the pipeline;

[0082] Water turbine efficiency η th The calculation formula is:

[0083]

[0084] In the formula, T represents the torque borne by the blades of the water turbine; N represents the rotational speed of the water turbine; ρ represents the density of water; g represents the acceleration due to gravity; H 1 represents the liquid level height upstream of the pipeline; H 2 represents the liquid level height downstream of the pipeline; Q represents the water flow rate in the pipeline;

[0085] After obtaining the above parameters in real time, the health status and aging condition of the water turbine can be analyzed.

[0086] S2. Calculate the first health degree value H of each group of water turbines according to the first working parameters at each time point t ; Specifically, the rotation of the water turbine will be directly transmitted to the generator, and then electricity is generated. Therefore, the water turbine is one of the important equipment for power generation in a hydropower plant. To ensure the normal operation of the hydropower plant, it is necessary to accurately evaluate the health status of the water turbine. During the daily use of the water turbine, the staff will perform operations such as maintenance, repair, and component replacement on the water turbine, which will cause fluctuations in the health degree of the water turbine. If the above situation is not considered, the calculation accuracy of the health degree of the water turbine will not be high. Therefore, in step S2, it specifically includes the following steps:

[0087] S21. Obtain the first working parameters at each time point and construct a first working parameter set respectively represent the water flow rate, water flow pressure, opening of the turbine guide vane, vibration amplitude of the turbine, axial displacement of the turbine, temperature of the turbine, noise of the turbine, and the efficiency η of the turbine th ;

[0088] S22. Standardize the first set of working parameters to generate a second set of working parameters The expression is as follows:

[0089]

[0090] In the formula, x min represents the historical minimum value of the i-th first working parameter; x max represents the historical maximum value of the i-th first working parameter;

[0091] S23. Calculate the first health degree value H for each time point; specifically, commonly used methods for evaluating the health degree of a turbine only consider the direct impact of the first working parameters on the turbine and do not take into account the mutual influence between different parameters on the health degree, so it will lead to a large error in the calculation result. Therefore, in step S23, it specifically includes the following steps: t ; specifically, commonly used methods for evaluating the health degree of a turbine only consider the direct impact of the first working parameters on the turbine and do not take into account the mutual influence between different parameters on the health degree, so it will lead to a large error in the calculation result. Therefore, in step S23, it specifically includes the following steps:

[0092] S231. Construct a non-linear conversion function based on the mutual influence relationship between the first working parameters The expression is as follows:

[0093]

[0094] In the formula, a 0 represents the constant term with respect to ; a 1 and a 2 respectively represent the coefficients of the first-order term and the second-order term of; in the present invention, a 0 , a 1 and a 2 are 0.2, 1, and 0.5 respectively; specifically, the mutual influence relationship represents the mutual influence between the first working parameters;

[0095] S232. Calculate the first health degree value H according to the non-linear conversion function t , and its calculation formula is:

[0096]

[0097] In the formula, n represents the total number of the first working parameters; w 0represents the bias term; w i represents the weight coefficient of the i-th parameter; w ij represents the weight coefficient of the interaction between the i-th and j-th parameters; represents with respect to the weight parameter; in the present invention, w 0 、w i 、w ij and are 0.1, 0.1, 0.05 and 0.2 respectively.

[0098] In step S23 of the present invention, since the influence relationship between the first operating parameters is not linear. For example, as the water flow rate or water flow pressure changes, the vibration, temperature or noise of the water turbine may not increase or decrease linearly. Therefore, a non-linear conversion function is constructed to simulate such complex dynamic behavior, and then when calculating the first health degree value H t , the mutual influence between different first operating parameters is also considered. In step S23 of the present invention, when calculating the health degree of the water turbine in each period, compared with common calculation methods, the mutual influence between different parameters is considered, so when calculating the health degree of the water turbine, the calculation accuracy is higher.

[0099] In step S3 of the present invention, the health degree of the water turbine in each period is evaluated, so that in the later stage when optimizing the first health degree value, information such as the level and frequency of maintenance, repair and component replacement of the staff can be added to further improve the more accurate evaluation of the health degree of the water turbine.

[0100] S3. Optimize the first health degree value H t to generate a second health degree value; specifically, since during the daily use of the water turbine, the staff will perform operations such as repairing, maintaining and replacing components on the water turbine, which will cause fluctuations in the health degree of the water turbine. Analyzing the health degree of the water turbine only based on the first operating parameters will result in a large error. Therefore, in step S3, it specifically includes the following steps:

[0101] S31. Set a sliding window with a length of T and a step size of L in the first health degree value H t , and obtain a training sample each time the sliding window slides once;

[0102] S32. Optimize the last first health degree value H zt in each training sample to generate a sample label HY t , and its calculation formula is:

[0103]

[0104] In the formula, W i represents the weight parameter for the i-th H t ; α represents the weight parameter for H zt ; in the present invention, when the replacement time of the water turbine does not exceed 3 months, both W i and α are 1; when the maintenance and repair time of the water turbine does not exceed 1 month, W i and α are 0.98 and 0.97 respectively; when the water turbine does not have the above situations, W i and α are 0.7 and 0.3 respectively;

[0105] S33. Construct a training set according to the training samples and the sample labels HY t ;

[0106] S34. Use the training set to train the long short-term memory network to generate a target model;

[0107] S35. When the sliding window selects the first health degree value H t at the current time, generate an input parameter set;

[0108] S36. Input the input parameter set into the target model and output the second health degree value.

[0109] In step S3 of the present invention, in order to improve the accuracy of calculating the health degree of the water turbine, considering the situation that the health degree of the water turbine fluctuates due to the operations of the staff such as maintenance, repair, and replacement of components of the water turbine, so when constructing the training label, according to the first health degree value H t in each period, the last first health degree value H zt is optimized. Therefore, the error of the first health degree value H t can be effectively reduced. In the present invention, when optimizing the first health degree value H t , considering the influence of the operations of the staff such as maintenance, repair, and replacement on the health degree of the water turbine, compared with the common calculation methods, the evaluation accuracy of the health degree of the water turbine is higher.

[0110] S4. Judge whether the corresponding water turbine is faulty according to the second health degree value;

[0111] If so, shut down the water turbine and end;

[0112] If not, enter step S5; As a further implementation manner of the present invention, when evaluating whether the water turbine is faulty according to the second health degree value, an evaluation criterion needs to be set. Therefore, in step S4, it specifically includes the following steps:

[0113] S41. Calculate the first health degree value H tAverage health value Its calculation formula is:

[0114]

[0115] In the formula, represents the i-th first health value H t ; N represents the total number of the first health values H t ;

[0116] S42. Calculate the standard deviation σ according to the average health value H , and its calculation formula is:

[0117]

[0118] S43. Calculate the standard health value H std , and its calculation formula is:

[0119]

[0120] In the formula, β represents the safety margin coefficient; in the present invention, β is 2;

[0121] S44. Judge whether the second health value is lower than the standard health value H std ;

[0122] If so, it means that the water turbine is faulty;

[0123] If not, it means that the water turbine is not faulty.

[0124] In step S4 of the present invention, the standard health value H H is calculated through the standard deviation σ and the average health value std , and this is used as the standard for judging whether the water turbine fails, so that it can quickly judge whether the water turbine fails.

[0125] S5. Schedule the gate opening G i corresponding to each group of water turbines according to the second health value; specifically, since the hydropower plant has a certain power generation task every day, and the health conditions of each group of water turbines are different, then when scheduling the task volume of each water turbine, it needs to be determined according to the specific situation of each group of water turbines. Moreover, the relationship between the second health value of the water turbine and the power generation of the water turbine is not linear. Adjusting the gate opening only according to the second health value will cause the damage speed of some water turbines to be unbalanced, which is not conducive to improving the average life of all water turbines. Therefore, in step S5, it specifically includes the following steps:

[0126] S51. Obtain the total task power generation P of the hydropower planttotal and the maximum power generation of each group of working turbines

[0127] S52. Calculate the total health value H of all turbines total , and its calculation formula is:

[0128]

[0129] In the formula, m represents the total number of working turbines; L represents the maximum value; e represents the base of the natural logarithm; k represents the curve steepness; h i represents the second health value of the i-th group of turbines; x 0 represents the center point of the curve; in the present invention, L, k, and x 0 are 0.5, 0.85, and 1 respectively;

[0130] S53. Calculate the allocated power generation P of each group of turbines according to the total health value H total , and its calculation formula is: i

[0131]

[0132]

[0132] S54. Calculate the gate opening G of each group of turbines according to the allocated power generation P i ; as a further implementation manner of the present invention, in step S54, the calculation formula of the gate opening G i is: i

[0133]

[0134]

[0134] In the formula, ln represents the logarithmic function; ω 1 , ω 2 , ω 3 and ω 4 respectively represent the first, second, third, and fourth weight parameters with respect to G i ; in the present invention, ω 1 , ω 2 , ω 3 and ω 4 are 0.2, 0.3, 0.2, and 0.3 respectively.

[0135] In step S5 of the present invention, in order to reasonably allocate the workload of each group of turbines, first calculate the total task power generation P total , and then calculate the allocated power generation P of each group of turbines according to the total health value H total , considering the non-linear relationship between the turbine power generation and the second health value of the turbine, so for the allocated power generation P of each group of turbines i , iThe accuracy of the calculation is higher, so for the gate opening G i The accuracy of the calculation is also higher. In the present invention, when calculating the allocated power generation amount P of each group of turbines i , the non-linear relationship between the turbine power generation amount and the second health degree value of the turbine is considered. Therefore, compared with the common calculation methods, the accuracy of calculating the allocated power generation amount P i is higher, and thus the accuracy of calculating the gate opening G i is improved.

[0136] In the present invention, when calculating the health degree value of the turbine, not only the influence of the mutual influence between different parameters on the health degree value is considered, but also the influence of the staff on the health degree of the turbine is considered, which can effectively improve the accuracy of evaluating the health degree of the turbine. Moreover, when calculating the gate opening, the non-linear influence relationship between the turbine power generation amount and the power generation amount on the health degree is considered, so the accuracy of calculating the gate opening can be further improved, and the average life of all gates can be increased.

[0137] Those of ordinary skill in the art can understand that all or part of the steps in the method of the above embodiments can be completed by instructing relevant hardware through a program. Therefore, the present application can adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware aspects. Moreover, the present application can adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk memories, CD-ROMs, optical memories, etc.) containing computer-usable program codes.

[0138] The above embodiments have introduced the present invention in detail. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those of ordinary skill in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present invention.

Claims

1. A hydropower station data analysis and dispatching method, characterized in that: The specific steps include: S1. Real-time acquisition of the first working parameters of each group of turbines in the hydropower plant and storage in the database. The first working parameters include water flow, water flow pressure, turbine guide vane opening, turbine vibration amplitude, turbine shaft displacement, turbine temperature, turbine noise and turbine efficiency η. th ; S2. Calculate the first health value H of each group of turbines according to the first working parameter at each time point. t ; S3. For the first health value H t Perform optimization to generate a second health value; S4. judging whether the corresponding turbine is faulty according to the second health value; If yes, shut down the turbine and end; If not, proceed to step S5; S5: the gate opening G corresponding to each group of turbines is adjusted according to the second health value. i Make a schedule.

2. The hydropower station data analysis and dispatching method according to claim 1, characterized in that: Turbine efficiency η th The calculation formula is: Where T represents the torque on the turbine blades; N represents the speed of the turbine; ρ represents the density of water; g represents the acceleration of gravity; h1 represents the liquid level upstream of the pipeline; h2 represents the liquid level downstream of the pipeline; and Q represents the water flow rate in the pipeline.

3. The hydropower station data analysis and dispatching method according to claim 1, characterized in that: In step S2, the following steps are specifically included: S21. Obtain the first working parameter at each time point and construct a first working parameter set They represent water flow, water flow pressure, turbine guide vane opening, turbine vibration amplitude, turbine shaft displacement, turbine temperature, turbine noise and turbine efficiency η respectively. th ; S22: first working parameter set Standardize and generate the second working parameter set Its expression is: In the formula, x min represents the historical minimum value of the i-th first working parameter; x max represents the historical maximum value of the i-th first operating parameter; S23, according to the second working parameter set Calculate the first health value H at each time point t .

4. The hydropower station data analysis and dispatching method according to claim 3, characterized in that: In step S23, the following steps are specifically included: S231: Construct a nonlinear conversion function according to the mutual influence relationship between the first working parameters Its expression is: In the formula, a0 represents the constant term; a1 and a2 represent The coefficients of the linear and quadratic terms of ; S232, according to the nonlinear conversion function Calculate the first health value H t , and its calculation formula is: Where n represents the total number of the first operating parameters; w0 represents the bias term; w i represents the weight coefficient of the i-th parameter; w ij Represents the weight coefficient of the interaction between the i-th and j-th parameters; Indicates about The weight parameter of .

5. The hydropower station data analysis and dispatching method according to claim 1, characterized in that: In step S3, the following steps are specifically included: S31, at the first health value H t In the example, a sliding window with a length of T and a step size of L is set, and a training sample is obtained each time the sliding window slides; S32, the last first health value H in each training sample zt Optimize and generate sample labels HY t , and its calculation formula is: Where W i Represents the i-th H t The weight parameter of H zt The weight parameter of S33, based on training samples and sample labels HY t Construct a training set; S34, training the long short-term memory network using the training set to generate a target model; S35, the sliding window selects the first health value H at the current time t When , an input parameter set is generated; S36. Input the input parameter set into the target model and output a second health value.

6. The hydropower station data analysis and dispatching method according to claim 1, characterized in that: In step S4, the following steps are specifically included: S41. Calculate the first health value H t The average health value The calculation formula is: In the formula, Indicates the first health value H of the i-th t ; N represents the first health value H t Total number of; S42. According to the average health value Calculate the standard deviation σ H , and its calculation formula is: S43. Calculate standard health value H std , and its calculation formula is: In the formula, β represents the safety margin factor; S44, determine whether the second health value is lower than the standard health value H std ; If so, it indicates turbine failure; If not, it means the turbine is not faulty.

7. The hydropower station data analysis and dispatching method according to claim 1, characterized in that: In step S5, the following steps are specifically included: S51. Obtain the total power generation capacity P of the hydropower plant total and the maximum power generation of each group of working turbines S52. Calculate the total health value H of all turbines total , and its calculation formula is: In the formula, m represents the total number of turbines in operation; L represents the maximum value; e represents the base of the natural logarithm; k represents the steepness of the curve; h represents the maximum value; i represents the second health value of the i-th group of turbines; x0 represents the center point of the curve; S53, according to the total health value H total Calculate the distributed power generation P of each group of turbines i , and its calculation formula is: S54, according to the distribution of power generation P i Calculate the gate opening G of each turbine group i .

8. The hydropower station data analysis and dispatching method according to claim 7, characterized in that: In step S54, the gate opening G i The calculation formula is: Where ln represents the logarithmic function; ω1, ω2, ω3 and ω4 represent the i The first, second, third and fourth weight parameters of .

Images