Wind energy conversion model construction and optimization method based on fan index analysis

Abstract

The invention relates to the technical field of wind energy conversion and system optimization, in particular to a wind energy conversion model construction and optimization method based on fan index analysis, which comprises the following steps of: 1, preprocessing fan data; 2, establishing a wind energy conversion model; 3, establishing a main shaft torque and tower thrust model; 4, establishing a material fatigue damage model; 5, optimizing parameters such as spindle torque, tower thrust and fatigue damage calculation by means of a genetic algorithm; and step 6, reference data comparison and error result analysis: analyzing the error of the model result through comparison with historical data and industrial standards. And the accuracy of the model and the reliability in practical application are evaluated by using a statistical method, so that the model can effectively reflect the dynamic characteristics of fan operation in practical engineering. Through systematic modeling steps, the wind energy conversion efficiency can be effectively improved, the accuracy of structural safety analysis is enhanced, and a scientific basis is provided for maintenance and optimization of the fan.

Description

Technical Field

[0001] The present invention relates to the technical field of wind energy conversion and system optimization, and in particular to a wind energy conversion model construction and optimization method based on wind turbine index analysis. Background Art

[0002] With the increasing use of renewable energy, wind energy, as an important green energy, has attracted more and more research and applications. However, wind turbines are affected by many factors during operation. How to effectively improve their conversion efficiency and optimize system performance has become an important research topic. Traditional wind energy conversion models often only focus on a single factor, such as wind speed or power generation, and lack a comprehensive analysis of various indicators. This leads to insufficient robustness and adaptability of the model in practical applications, especially when faced with environmental noise and communication delays, the performance of the model will be significantly affected.

[0003] To this end, the present invention proposes a wind energy conversion model construction and optimization method based on wind turbine index analysis, aiming to achieve comprehensive analysis and optimization of the wind turbine operation process through multi-step data processing and model construction. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings existing in the prior art, and proposes a wind energy conversion model construction and optimization method based on wind turbine index analysis. Through innovative data analysis and modeling strategies, this method can effectively improve the energy conversion efficiency and operation stability of the wind turbine, ensure the coordination between various indicators, thereby reducing system losses and enhancing the adaptability of the wind turbine in different working environments.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A wind energy conversion model construction and optimization method based on wind turbine index analysis includes the following steps:

[0007] Step 1: Preprocessing of wind turbine data: First, collect the operating data of the wind turbine under different wind speeds and load conditions, clean and normalize the data to eliminate noise and outliers, and thus provide accurate basic data for the construction of subsequent models;

[0008] Step 2: Establish a wind energy conversion model. Based on the preprocessed data, a wind energy conversion model is constructed. The model is based on the relationship between wind speed and energy conversion efficiency. It uses mathematical formulas to describe the process of converting wind energy into mechanical energy to ensure that the model can reflect the actual operating status.

[0009] Step 3: Establish a main shaft torque and tower thrust model. Model the main shaft torque and tower thrust of the wind turbine. By analyzing the mechanical characteristics of the wind turbine under different working conditions, establish the functional relationship between the main shaft torque and the wind speed and load. This model is used to calculate the force of the wind turbine and evaluate its structural safety.

[0010] Step 4: Establish a material fatigue damage model. Combined with the actual operating environment, establish a material fatigue damage model, use stress-strain relationship and rain flow counting method to analyze the fatigue life of the wind turbine structure, evaluate the possible damage and failure mode of the material during long-term operation, and provide a basis for maintenance decisions;

[0011] Step 5: Optimize the main shaft torque, tower thrust and fatigue damage calculation parameters with the help of genetic algorithm. The optimization search method based on natural selection and genetic principles can effectively optimize various parameters in the wind energy conversion model, such as main shaft torque, tower thrust and fatigue damage calculation;

[0012] Step 6: Comparison with reference data and analysis of error results. Analyze the errors of model results by comparing with historical data and industry standards.

[0013] Preferably, in step 1, the operation data of the fan under different wind speed and load conditions are collected, and the data are cleaned and normalized to eliminate noise and outliers. Through these processes, the accuracy and effectiveness of the data used are ensured, providing a reliable data basis for the construction of subsequent models. At the same time, by analyzing the data distribution characteristics, key parameters and influencing factors are identified, so as to conduct more in-depth analysis and modeling in subsequent steps.

[0014] Preferably, in step two, by collecting and preprocessing various operating data of the wind turbine, a wind energy conversion model is established to analyze the working status of the wind turbine, including wind speed, power generation and main shaft speed; using regression analysis methods, a mathematical relationship between wind speed and power generation is established, thereby providing a basis for the subsequent improvement of wind energy conversion efficiency.

[0015] Preferably, in step three, the sensor data and relevant physical models are combined, starting from the main shaft torque of the fan, and the torque change of the fan at different working angles is calculated using the dynamic equation; through numerical simulation, the operating parameters of the fan under specific working conditions are obtained, and its efficiency and stability are evaluated.

[0016] Preferably, in step four, a material fatigue damage model is established, taking into account the stress conditions of various components of the wind turbine during long-term operation; the fatigue life of the components is analyzed using material mechanics theory, and the fatigue accumulation process is simulated through software, so as to monitor the health status of the wind turbine components in real time during operation and effectively predict the risk of failure.

[0017] Preferably, in step five, first, define the fitness function, generate a new generation of parameter combinations through genetic operations such as selection, crossover and mutation, and then repeatedly evaluate its fitness and continue to iterate until the optimization criteria are met to improve the overall performance and reliability of the model. Finally, apply the optimization results to the wind energy conversion model for performance verification and result analysis to provide data support for practical applications.

[0018] Preferably, in step six, the errors of the model results are analyzed by comparison with historical data and industry standards, and statistical methods are used to evaluate the accuracy of the model and its reliability in practical applications, to ensure that the model can effectively reflect the dynamic characteristics of the fan operation in actual engineering.

[0019] Compared with the prior art, the present invention has the following beneficial effects:

[0020] 1. The present invention uses data mining and machine learning technology to effectively predict the nonlinear relationship between wind speed, rotation speed and power generation through in-depth analysis of various indicator data of the wind turbine. The model can dynamically adjust and optimize the operating parameters of the wind turbine to adapt to different wind speed conditions, thereby significantly improving the energy conversion efficiency of the wind turbine.

[0021] 2. The present invention accurately evaluates the stress of the fan under different working conditions by establishing a mechanical analysis model of main shaft torque and tower thrust. The model integrates various dynamic factors in the operation of the fan, uses numerical simulation technology, and provides a reliable basis for the operation of the fan in a complex environment through precise calculation, reducing the risk of system failure.

[0022] 3. The present invention also introduces a material fatigue damage assessment model, combined with the theory of material science, to analyze the life and reliability of wind turbine components under changing operating conditions. This method can not only monitor the health status of components in real time, but also provide data-based maintenance recommendations, thereby optimizing the maintenance strategy of the wind turbine and extending its service life.

[0023] 4. The present invention continuously improves the prediction accuracy of the model by implementing model error analysis and feedback optimization mechanism. Real-time data update and learning mechanism are used to ensure that the model can show good adaptability under different environmental conditions, so as to reduce uncertainty in operation and improve the economy and safety of the fan. BRIEF DESCRIPTION OF THE DRAWINGS

[0024] Figure 1 Schematic diagram of error distribution between calculated values ​​and reference values ​​of a fan in an embodiment of the present invention;

[0025] Figure 2 is a comparison chart of estimated values ​​and reference values ​​of 5 fans in an embodiment of the present invention;

[0026] Figure 3 Schematic diagram of error analysis of the sum of squares of differences between an estimated value and a reference value of a fan in an embodiment of the present invention;

[0027] Figure 4 Schematic diagram of stability test of the model in an embodiment of the present invention;

[0028] Figure 5 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0029] The technical solutions in the embodiments of the present invention will be described clearly and completely below in conjunction with the accompanying drawings, so that those skilled in the art can better understand the advantages and features of the present invention, thereby making a clearer definition of the protection scope of the present invention. The embodiments described in the present invention are only a part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of the present invention.

[0030] Example:

[0031] Reference Figure 5 , a wind energy conversion model construction and optimization method based on wind turbine index analysis, comprising the following steps:

[0032] Step 1: Preprocessing of wind turbine data. First, collect the operating data of the wind turbine under different wind speed and load conditions. Clean and normalize the data to eliminate noise and outliers, thereby providing accurate basic data for the construction of subsequent models.

[0033] Step 2: Establish a wind energy conversion model. Based on the preprocessed data, a wind energy conversion model is constructed. This model is mainly based on the relationship between wind speed and energy conversion efficiency, and uses mathematical formulas to describe the process of converting wind energy into mechanical energy to ensure that the model can reflect the actual operating status.

[0034] Step 3: Establish the main shaft torque and tower thrust model. Build a model for the main shaft torque and tower thrust of the wind turbine. By analyzing the mechanical characteristics of the wind turbine under different working conditions, establish the functional relationship between the main shaft torque and the wind speed and load. This model can be used to calculate the force of the wind turbine and evaluate its structural safety.

[0035] Step 4: Establish a material fatigue damage model. Establish a material fatigue damage model based on the actual operating environment. Use stress-strain relationship and rain flow counting method to analyze the fatigue life of the wind turbine structure, evaluate the possible damage and failure mode of the material during long-term operation, and provide a basis for maintenance decisions.

[0036] Step 5: Optimize the parameters such as main shaft torque, tower thrust and fatigue damage calculation with the help of genetic algorithm. The optimization search method based on natural selection and genetic principles can effectively optimize various parameters in the wind energy conversion model, such as main shaft torque, tower thrust and fatigue damage calculation.

[0037] Step 6: Analyze the errors of the model results by comparing with historical data and industry standards. Use statistical methods to evaluate the accuracy of the model and its reliability in practical applications to ensure that the model can effectively reflect the dynamic characteristics of wind turbine operation in actual projects.

[0038] In the process of wind power generation, there is a nonlinear relationship between wind speed and wind turbine output power. When the wind speed is low, the wind turbine is highly efficient and can efficiently convert wind energy into electrical energy; when the wind speed is too high, the wind turbine power reaches saturation, and the excess wind energy increases the main shaft torque and tower top thrust, which in turn affects the fatigue damage of the wind turbine mechanical components.

[0039] The working process of the fan is affected by many factors:

[0040] 1. Wind energy capture efficiency: power coefficient C p , which indicates the efficiency of the wind turbine in converting wind energy into mechanical power, depends on factors such as wind speed and rotor speed.

[0041] 2. Rated wind speed: The rated wind speed of the wind turbine is 11.2m / s. When the wind speed exceeds this value, the output power remains constant (5MW).

[0042] 3. Aerodynamic effect: When wind speed increases, tower top thrust and main shaft torque will also increase, especially when wind speed exceeds the rated value.

[0043] To this end, the present invention will establish a mathematical model to estimate the main shaft torque and tower top thrust of the wind turbine.

[0044] (1) Establishing a wind energy conversion model

[0045] Based on the Bell equation model and combined with the principles of fluid dynamics, the wind energy captured by the wind turbine is calculated:

[0046]

[0047] Among them, P w is wind power, ρ is air density, which is 1.225 kg / m 3 , A=πr 2 is the swept area of ​​the wind rotor, r is the radius of the wind rotor, V w is the wind speed.

[0048] Mechanical power output of the fan P ref The relationship between the captured wind energy and the power factor C pIt indicates the efficiency of wind turbine in capturing wind energy:

[0049]

[0050] Power coefficient C p It is a nonlinear coefficient, which is affected by factors such as wind speed and wind rotor speed. When the wind speed is low, C p As the wind speed increases; when the wind speed exceeds the rated wind speed, the fan power reaches saturation, C p Then it decreased.

[0051] Spindle torque: According to the law of conservation of energy, the output power of wind energy is related to the spindle torque and angular velocity as follows:

[0052] P ref =T s ·ω(3.)

[0053] Among them, T s is the main shaft torque, and ω is the angular velocity of the wind wheel. From this, the main shaft torque can be calculated:

[0054]

[0055] Tower thrust: Tower thrust F t Affected by wind speed and aerodynamic forces, proportional to the square of wind speed:

[0056]

[0057] Among them, C t It is the thrust coefficient, which indicates the force applied to the fan at different wind speeds.

[0058] (2) Establishing the main shaft torque and tower thrust model

[0059] The model is divided into three areas according to wind speed: low wind speed, rated wind speed, and high wind speed.

[0060] (a) Low wind speed range (V w <11.2m / s)

[0061] Spindle torque calculation:

[0062]

[0063] Tower thrust calculation:

[0064]

[0065] In this range, the wind speed output power is low, the mechanical components are subjected to less stress, and fatigue damage mainly comes from the high number of cycles.

[0066] (b) Rated wind speed range (Vw ≈11.2m / s)

[0067] Spindle torque calculation:

[0068]

[0069] Tower thrust calculation:

[0070]

[0071] At rated wind speed, the wind speed output power reaches the maximum and the fatigue damage accumulation is relatively uniform.

[0072] (c) High wind speed range (V w >11.2m / s)

[0073] Spindle torque calculation:

[0074]

[0075] Tower thrust calculation:

[0076]

[0077] At high wind speeds, the wind turbine performs power reduction, the main shaft torque decreases, but the tower thrust increases and fatigue damage accumulates faster.

[0078] In summary, the main shaft torque and tower thrust model can be expressed by a piecewise function:

[0079] Spindle torque calculation:

[0080]

[0081] Tower thrust calculation:

[0082]

[0083] (3) Establishing material fatigue damage model

[0084] Using the Palmgren-Miner linear cumulative damage theory:

[0085]

[0086] Where D is the cumulative fatigue damage, n i is the stress level F i The number of cycles under Fi is the material at stress level F i The maximum number of cycles under the condition is usually obtained through the SN curve.

[0087] (4) Using genetic algorithms to optimize parameters such as spindle torque, tower thrust, and fatigue damage calculation

[0088] In order to achieve the goals of minimizing the main shaft torque, reducing the tower thrust and reducing fatigue damage, the fitness function can be designed in the following form:

[0089] F=w1T s +w2F t +w3D(15.)

[0090] Among them, w1, w2, and w3 are weights that reflect the importance of different objectives.

[0091] Next, the model is solved and the reference data is compared and the error results are analyzed.

[0092] (1) The stress / torque results of the five wind turbines are shown in Table 1 and Table 2.

[0093] Table 1 Main shaft torque values ​​of the five fans at all times

[0094]

[0095]

[0096] Table 2 Tower thrust values ​​of the five wind turbines at all times

[0097]

[0098] (2) Comparison with reference data

[0099] Next, the comparison between the calculated results and the actual data will be presented from three aspects: error distribution, comparison between the estimated values ​​and reference values ​​of the five wind turbines, and the sum of squares of the differences between the estimated values ​​and the reference values.

[0100] (a) The error distribution of the fan is as follows Figure 1 Shown

[0101] Figure 1 The error distribution of the main shaft torque and tower thrust is shown, showing the difference between the estimated value and the reference value, respectively. Main shaft torque error distribution Figure 1 In the figure above, the X-axis is the error (Nm) and the Y-axis is the frequency. From the perspective of the error distribution, the errors are mainly concentrated between -2 and 0 Nm, showing a left-biased distribution. The peak area is between -1 and -0.5 Nm, with a high frequency, indicating that in this range, the estimated value of the spindle torque differs most from the reference value. From the perspective of deviation analysis, the left-biased phenomenon of the error distribution indicates that the estimated values ​​are generally lower than the reference values. This may be due to some parameters in the model (such as the power coefficient C P Or thrust coefficient C TThe error range is large, from -2 to 1Nm, which means that the estimation model has a large error in some cases. You can consider adjusting the power coefficient C P and thrust coefficient C T To optimize the model, the estimated value is closer to the reference value. The accuracy of wind speed and other input parameters is further analyzed to ensure the accuracy of input data.

[0102] Tower thrust error distribution Figure 1 In the figure below, from the perspective of error distribution, the errors are mainly concentrated between 6 and 10N, showing a relatively symmetrical distribution. The peak area is between 8 and 9N, with a high frequency, indicating that in this range, the estimated value of the tower thrust differs most from the reference value. From the perspective of deviation analysis, the error distribution is relatively symmetrical, but overall biased to the right, indicating that the estimated values ​​are generally higher than the reference values. This may be due to the thrust coefficient C t The high setting leads to systematically high estimates. The large error range, from 6 to 12N, means that the estimation model has large errors in some cases.

[0103] (b) Comparative analysis of the estimated values ​​of the first five wind turbines and the reference values. Figure 2 Shown

[0104] Figure 2 The estimated values ​​of the main shaft torque and tower thrust of the five wind turbines are compared with the reference values. The following is a detailed analysis of each sub-graph:

[0105] Figure 2 The left graph in shows the main shaft torque of fans 1-5, with the X-axis being the time step (from 0 to 100), the Y-axis being the main shaft torque (Nm), the solid line being the estimated value, and the dotted line being the reference value. From the overall trend, the estimated and reference values ​​of the main shaft torque of all fans show a trend of fluctuation over time. From the error analysis, the estimated value of fan 1 is significantly different from the reference value in most time steps, especially in the first 50 time steps, where the estimated value is low. The estimated value of fan 2 is closer to the reference value in some time steps, but there are still errors overall, especially in the high torque area. The difference between the estimated value of fan 3 and the reference value is large in the first 50 time steps, and it improves in the second half, but there are still errors. The difference between the estimated value of fan 4 and the reference value is relatively small, especially after time step 50, showing a good estimation effect. The estimated value of fan 5 is closer to the reference value in most time steps, but there are still errors in some peak areas.

[0106] Figure 2The right graph in the figure shows the tower thrust of wind turbines 1-5, with the Y axis being the tower thrust (N), and the rest being the same as the left graph. From the overall trend, the estimated and reference values ​​of the tower thrust of all wind turbines show a trend of fluctuation over time. From the error analysis, the estimated value of wind turbine 1 is significantly higher than the reference value in most time steps, especially in the first 30 time steps. The estimated value of wind turbine 2 is significantly higher than the reference value in most time steps, especially in the first 50 time steps. The estimated value of wind turbine 3 is significantly higher than the reference value in most time steps, showing a large systematic error. The estimated value of wind turbine 4 is significantly higher than the reference value in the first 50 time steps, and there is some improvement in the second half, but there is still an error. The estimated value of wind turbine 5 is significantly higher than the reference value in most time steps, especially in the first 50 time steps.

[0107] In summary, although the estimated values ​​are close to the reference values ​​in some time steps and wind turbines, there are still significant errors overall. The accuracy and stability of the estimates can be improved by further optimizing the model and calibration parameters.

[0108] (c) The sum of squares of the differences between the estimated value and the reference value is as follows: Figure 3 Shown

[0109] Figure 3 The figure shows the time trend of the error sum of the main shaft torque and tower thrust within 100 time steps. Figure 3 In the figure above, in the initial stage (0 to 10 time steps), from 6×10 13 It rises rapidly and stabilizes at 7.5×10 13 This means that the model quickly reduced the error by 25% in the initial stage. In the middle stage (10 to 50 time steps), the sum of squared errors is around 7×10 13 to 8×10 13 The fluctuation range is about 1×10 13 , accounting for 13.3% of the stable value, showing that the model has a certain performance in capturing the dynamic changes of wind speed and power. In the later stage (50 to 100 time steps), the error sum of squares remains at 7.5×10 13 There is no significant increase in the fluctuation amplitude near , which indicates that the model's estimation of the spindle torque remains stable throughout the period.

[0110] For the sum of squares of tower thrust errors, Figure 3 In the following figure, in the initial stage (0 to 10 time steps), from 1×10 13 It rises rapidly and stabilizes at 7×10 in about 10 time steps. 13 , which means that the model quickly reduced the error by 30% in the initial stage. In the mid-term stage (10 to 50 time steps), the fluctuation range of the sum of squared errors is 6.8×1013 to 7.2×10 13 The fluctuation range is about 4×10 12 , accounting for 5.7% of the stable value, indicating that the model has a certain stability in dealing with the relationship between wind speed and power. In the later stage (50 to 100 time steps), the error sum of squares continues to be around 7×10 13 It fluctuates around the area, showing a certain periodicity and stability.

[0111] Table 3 Sum of squares of differences between estimated values ​​and reference values

[0112]

[0113] The sum of squares of the differences between the estimated values ​​and the reference values ​​at all times is calculated to obtain Table 3. It can be seen that the sum of squares of the main shaft torque difference is high, but the model shows a certain stability when processing wind speed and power data. The stability of the mean sum of squares of errors shows that the performance of the model is relatively consistent in different time steps, and there is no significant error fluctuation, which provides a good basis for further optimization. The mean sum of squares of tower thrust errors is high, but the fluctuation amplitude is small, showing the stability of the model in dealing with the relationship between wind speed and power. Despite the large error, the model maintained a relatively stable error level throughout the time period, indicating that the model has a certain reliability in dealing with wind force distribution and tower forces.

[0114] Next, we test the stability of the model:

[0115] Figure 4 The stability test is performed by analyzing the sum of square errors of the main shaft torque and tower thrust. By analyzing the sum of square errors of the main shaft torque of 10 experiments, the following results can be observed:

[0116] (1) The range and fluctuation of the data of the sum of squares of the spindle torque error: The range is 7.62×10 15 to 7.626×10 15 , the maximum value is 7.625×10 15 (Experiment No. 8), the minimum value is 7.62×10 15 (Experiment No. 2). The fluctuation range is about 0.006×10 15 , showing that the overall fluctuation is small, indicating that the system maintains good stability in most cases. (2) Trend analysis of the sum of squares of the main shaft torque error: The data shows slight fluctuations between experimental numbers 1 to 10, but the overall trend is relatively stable. Although the peaks of experimental numbers 3 and 8 are significant, the remaining data points are relatively concentrated, showing the stability of the system in most cases. (3) For the statistical characteristics of the sum of squares of the shaft torque error: the mean is about 7.623×10 15. The standard deviation is small and the data is concentrated near the mean, indicating that the system is stable in terms of spindle torque. (4) Analysis of outliers in the sum of squared spindle torque errors: The values ​​of experimental numbers 3 and 8 are much higher than those of other experiments and may be outliers, but the remaining data points show that the system is stable in most cases. (5) Stability evaluation of the sum of squared spindle torque errors: Although there are a few peaks, the overall data fluctuations are small, showing the stability of the system in most cases. The system is able to maintain a low error under most experimental conditions, indicating that the model has a certain degree of robustness in handling spindle torque. (6) Analysis of the influence of experimental conditions on the sum of squared spindle torque errors: The peaks of experimental numbers 3 and 8 may be related to specific changes in experimental conditions. Further analysis of these conditions will help optimize the model. (7) Analysis of model robustness: Despite the presence of a few outliers, the model performs well in most cases, indicating a certain degree of robustness.

[0117] By analyzing the sum of squares of tower thrust errors of 10 experiments, the following results can be observed: (1) Data range and fluctuation of the sum of squares of tower thrust errors: The range is 7.006×10 15 to 7.009×10 15 , the maximum value is 7.009×10 15 (Experiment No. 4), the minimum value is 7.006×10 15 (Experiment No. 2). The fluctuation range of the sum of squares of the tower thrust error is about 0.003×10 15 , showing very little fluctuation, indicating that the system has high stability in terms of tower thrust. (2) Trend analysis of the sum of squares of tower thrust errors: The data remain basically stable between experiment numbers 1 to 10, with very little fluctuation. The values ​​of experiment numbers 4 and 7 are slightly higher, but the overall trend is stable, indicating that the system performs well in most cases. (3) Statistical characteristics analysis of the sum of squares of tower thrust errors: The mean of the sum of squares of tower thrust errors is about 7.0075×10 15 The smaller standard deviation and more concentrated data indicate that the system is very stable in terms of tower thrust. (4) Outlier analysis of the sum of squared tower thrust errors: The values ​​of experiment numbers 4 and 7 are slightly higher than those of other experiments, but the overall fluctuation range is extremely small, indicating the stability of the system. (5) Qualitative analysis of the sum of squared tower thrust errors: The data fluctuations are extremely small, indicating that the system is highly stable in terms of tower thrust. The system can maintain a low error under all experimental conditions, indicating that the model is very robust in handling tower thrust. (6) Analysis of the impact of experimental conditions on the sum of squared tower thrust errors: The peak values ​​of experiment numbers 4 and 7 also require further analysis to determine whether there are specific experimental conditions that cause the error to increase. (7) Model robustness analysis of the sum of squared tower thrust errors: The model is stable under all experimental conditions, showing extremely high robustness.

[0118] In summary, the following conclusions are drawn: (1) Stability: The sum of squared errors of the main shaft torque and tower thrust vary little in the 10 experiments, and both the mean and standard deviation are at a low level, indicating that the model has good stability under different experimental conditions. (2) Robustness: The overall trend of the sum of squared errors shows that the model is robust to random disturbances and can maintain relatively stable performance under different wind speed conditions.

[0119] In addition, the basic symbols in the embodiments of the present invention are explained as follows:

[0120]

[0121] In summary, the present invention can effectively improve wind energy conversion efficiency, enhance system operation stability, and provide strong support for the sustainable development of the wind energy industry through innovative modeling and optimization methods.

[0122] The description and practice disclosed in the present invention are easy to think and understand for ordinary technicians in the technical field, and several improvements and modifications can be made without departing from the principles of the present invention. Therefore, modifications or improvements made without departing from the spirit of the present invention should also be regarded as the protection scope of the present invention.

Claims

1. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis, characterized in that: The steps include: Step 1: Preprocessing of wind turbine data: First, collect the operating data of the wind turbine under different wind speeds and load conditions, clean and normalize the data to eliminate noise and outliers, and thus provide accurate basic data for the construction of subsequent models; Step 2: Establish a wind energy conversion model. Based on the preprocessed data, a wind energy conversion model is constructed. The model is based on the relationship between wind speed and energy conversion efficiency. It uses mathematical formulas to describe the process of converting wind energy into mechanical energy to ensure that the model can reflect the actual operating status. Step 3: Establish a main shaft torque and tower thrust model. Model the main shaft torque and tower thrust of the wind turbine. By analyzing the mechanical characteristics of the wind turbine under different working conditions, establish the functional relationship between the main shaft torque and the wind speed and load. This model is used to calculate the force of the wind turbine and evaluate its structural safety. Step 4: Establish a material fatigue damage model. Combined with the actual operating environment, establish a material fatigue damage model, use stress-strain relationship and rain flow counting method to analyze the fatigue life of the wind turbine structure, evaluate the possible damage and failure mode of the material during long-term operation, and provide a basis for maintenance decisions; Step 5: Optimize the main shaft torque, tower thrust and fatigue damage calculation parameters with the help of genetic algorithm. The optimization search method based on natural selection and genetic principles can effectively optimize various parameters in the wind energy conversion model, such as main shaft torque, tower thrust and fatigue damage calculation; Step 6: Comparison with reference data and analysis of error results. Analyze the errors of model results by comparing with historical data and industry standards.

2. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 1, characterized in that: In step 1, the operating data of the fan under different wind speed and load conditions are collected, and the data are cleaned and normalized to eliminate noise and outliers; Through these processes, the accuracy and validity of the data used are ensured, providing a reliable data foundation for the construction of subsequent models; by analyzing the data distribution characteristics, key parameters and influencing factors are identified to enable more in-depth analysis and modeling in subsequent steps.

3. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 2, characterized in that: In step two, by collecting and preprocessing various operating data of the wind turbine, a wind energy conversion model is established to analyze the working status of the wind turbine, including wind speed, power generation and main shaft speed; using regression analysis methods, a mathematical relationship between wind speed and power generation is established, thereby providing a basis for the subsequent improvement of wind energy conversion efficiency.

4. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 3, characterized in that: In step three, combining sensor data and physical models, starting from the main shaft torque of the fan, the dynamic equation is used to calculate the torque change of the fan at different working angles; through numerical simulation, the operating parameters of the fan under specific working conditions are obtained, and its efficiency and stability are evaluated.

5. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 4, characterized in that: In step four, a material fatigue damage model is established, taking into account the stress conditions of various wind turbine components during long-term operation; the fatigue life of the components is analyzed using material mechanics theory, and the fatigue accumulation process is simulated through software, so that the health status of the wind turbine components can be monitored in real time during operation and the risk of failure can be effectively predicted.

6. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 5, characterized in that: In step five, first, the fitness function is defined, and a new generation of parameter combinations is generated through selection, crossover and mutation genetic operations. Then, its fitness is repeatedly evaluated and iterated continuously until the optimization criteria are met to improve the overall performance and reliability of the model. Finally, the optimization results are applied to the wind energy conversion model for performance verification and result analysis to provide data support for practical applications.

7. A method for constructing and optimizing a wind energy conversion model based on wind turbine index analysis according to claim 6, characterized in that: In step six, by comparing with historical data and industry standards, the errors of the model results are analyzed, and statistical methods are used to evaluate the accuracy of the model and its reliability in practical applications, ensuring that the model can effectively reflect the dynamic characteristics of wind turbine operation in actual projects.

Images