A high-fidelity simulation platform, storage medium, and electronic device for wind turbine degradation-temperature coupling operation status

Abstract

The present invention discloses a high-fidelity simulation platform, storage medium, and electronic device for the operational state of a wind turbine with degradation-temperature coupling. The high-fidelity operational state simulation platform constructs a high-fidelity simulation environment for the operational state of a wind turbine throughout its life cycle by organically combining a wind speed simulation module, a degradation model module, a power conversion module, a coupling calculation module, a temperature dynamics module, and a state characterization module. The platform establishes a bidirectional coupling mechanism between the equipment degradation state and the operating temperature, simulating the positive feedback process between the two and resolving the modeling problem of multi-factor interactions in the prior art. It also employs a multi-stage nonlinear degradation model and Weibull-distributed wind speed simulation to characterize the dynamic characteristics of equipment operation. This platform provides a high-fidelity simulation platform for optimizing wind farm maintenance strategies and can be used for full-lifecycle simulation, fault prediction, predictive maintenance decision-making, and economic benefit evaluation of wind turbines.

Description

Technical Field

[0001] The present invention relates to the field of wind power generation technology, in particular to the field of technology related to wind turbine operating state simulation, and more specifically to a high-fidelity simulation platform, storage medium and electronic equipment for wind turbine degradation-temperature coupling operating state. Background Art

[0002] As the global energy transition strategy deepens, wind power, a key component of clean energy, has seen explosive growth in installed capacity. However, as the wind power industry expands, operational and maintenance (O&M) costs are becoming increasingly prominent. Currently, O&M accounts for approximately 25-30% of a wind farm's lifecycle costs, while unplanned downtime and emergency repairs caused by equipment failures account for another 20-30% of total maintenance costs. This significant financial burden severely impacts the market competitiveness and sustainable development of wind power.

[0003] The industry has conducted extensive research on optimizing wind turbine maintenance strategies, ranging from traditional time-based preventive maintenance to condition-based maintenance and, more recently, algorithm-based predictive maintenance. However, the effectiveness of maintenance strategies relies heavily on accurately understanding and simulating the operational characteristics of wind turbines. Currently, wind turbine maintenance decision-making faces a key challenge: the lack of high-fidelity simulation environments that can accurately simulate the long-term operational state of equipment.

[0004] The existing wind turbine simulation systems mainly have the following problems: First, traditional simulation models often simplify wind turbines into static systems, ignoring the dynamic evolution of equipment status over time, and cannot accurately simulate the degradation laws during long-term operation; second, most models only consider the impact of single factors such as wind speed and power on the equipment, ignoring the complex coupling between multiple factors, especially the mutual influence between temperature and degradation is seriously underestimated; third, existing models are usually based on simplified assumptions such as linear degradation and independent influencing factors, and there are significant differences from the nonlinear characteristics and interaction effects observed in actual systems; finally, there is a lack of an integrated simulation environment that has both physical fidelity and computational efficiency, which makes it difficult to support the training needs of modern optimization algorithms.

[0005] Existing methods for simulating the health of wind turbines consider changes in equipment health, but these employ simple linear degradation models that fail to reflect the phased nature and nonlinear variations of the actual degradation process. Wind turbine fault simulation systems also focus on simulating specific fault characteristics rather than the dynamic evolution of the overall system state, insufficiently capturing long-term cumulative degradation processes. Data generation methods for wind power fault diagnosis also focus primarily on generating fault signature data and lack in-depth simulation of the coupling between equipment degradation and environmental factors.

[0006] The aforementioned shortcomings of existing technologies for wind turbine simulation result in poor performance of maintenance strategies developed based on these models in real-world applications, making them incapable of meeting the demands of wind farm O&M optimization. With the development of predictive maintenance and deep reinforcement learning-based optimization and decision-making technologies, the need for high-fidelity, high-dimensional simulation environments has become increasingly urgent.

[0007] Therefore, how to provide a simulation environment that simulates the long-term operation status of wind turbines, considers the coupling of multiple factors, characterizes nonlinear characteristics, and has appropriate computational efficiency for optimizing wind farm maintenance strategies and improving operational efficiency is an urgent problem that needs to be solved by technical personnel in this field. Summary of the Invention

[0008] In view of the above problems, the present invention provides a high-fidelity simulation platform, storage medium and electronic device for the degradation-temperature coupled operation status of a wind turbine generator set, so as to at least solve some of the technical problems mentioned in the above background technology.

[0009] In order to achieve the above object, the present invention adopts the following technical solutions:

[0010] In one aspect, the present invention provides a high-fidelity simulation platform for wind turbine degradation-temperature coupled operating conditions, comprising:

[0011] Wind speed simulation module, used to generate complete wind speed time series with seasonal variation and intraday fluctuation characteristics based on Weibull distribution;

[0012] The degradation model module is used to divide the nonlinear degradation process of wind turbines into three stages: early degradation, mid-degradation and late degradation, and set the transition threshold between each stage;

[0013] A power conversion module, configured to obtain an actual output power of the wind turbine generator system based on the complete wind speed time series and the nonlinear degradation process;

[0014] A coupling calculation module is used to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine generator set based on the temperature sensitivity coefficient and the actual output power;

[0015] A temperature dynamic module is used to simulate the temperature variation characteristics of the wind turbine generator set based on the bidirectional coupling mechanism and obtain the operating temperature of the wind turbine generator set;

[0016] A state representation module, configured to construct an output state vector of a simulation environment based on the wind speed simulation module, the degradation model module, the power conversion module, the coupling calculation module, and the temperature dynamics module;

[0017] Maintenance effect simulation module is used to simulate the impact of different maintenance activities on system status.

[0018] Furthermore, the wind speed simulation module specifically includes:

[0019] The basic wind speed generation submodule is used to generate basic wind speed values ​​based on the shape parameters and scale parameters of the Weibull distribution;

[0020] A time correlation modeling submodule is used to construct a time correlation wind speed sequence based on the basic wind speed value by combining an autoregressive model with a random disturbance term, and to introduce a seasonal adjustment factor during the construction process to simulate seasonal changes in wind speed;

[0021] The intraday fluctuation superposition submodule is used to introduce the intraday fluctuation pattern on the basis of the time-correlated wind speed sequence to generate a complete wind speed time series.

[0022] Furthermore, the power conversion module includes:

[0023] a wind speed-power output modeling submodule for determining the operating range of the current wind speed based on the real-time wind speed data in the complete wind speed time series by comparing it with the preset cut-in wind speed, rated wind speed, and cut-out wind speed, and obtaining the ideal output power of the wind turbine based on the corresponding power curve model;

[0024] A degradation efficiency modeling submodule, configured to calculate a power generation efficiency coefficient of the wind turbine generator system according to a degradation degree obtained based on the nonlinear degradation process;

[0025] A real power output calculation submodule, configured to obtain the actual output power of the wind turbine generator set by combining the ideal output power and the power generation efficiency coefficient;

[0026] The economic benefit evaluation submodule is used to obtain the power generation benefit based on the actual output power and the current electricity price.

[0027] Furthermore, the coupling calculation module specifically includes:

[0028] The temperature-sensitive degradation rate submodule is used to construct the temperature impact factor based on the temperature sensitivity coefficient;

[0029] The degradation degree influences the temperature rise sub-model, which is used to simulate the actual output power of the current wind turbine and the impact of the degradation degree on the temperature rise of the wind turbine to obtain the target equilibrium temperature;

[0030] The temperature-degradation bidirectional coupling simulation submodule is used to integrate the two influencing mechanisms in the temperature-sensitive degradation rate submodule and the degradation degree affecting temperature rise submodel, and to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine.

[0031] Furthermore, the degradation model module also includes the following submodules:

[0032] The stage degradation function definition submodule is used to define the basic degradation function of the current degradation degree for the initial degradation stage, the middle degradation stage and the late degradation stage;

[0033] Load impact modeling submodule, used to quantify the load impact function that describes the degradation rate of wind turbines due to wind speed fluctuations and load changes;

[0034] The time cumulative effect modeling submodule is used to simulate the time impact function of the long-term use of wind turbines on the degradation rate;

[0035] The natural degradation evolution submodule is configured to update the degradation degree based on the temperature impact factor, the basic degradation function, the load impact function, and the time impact function.

[0036] Furthermore, the temperature dynamic module specifically includes:

[0037] The temperature evolution modeling submodule is used to construct a temperature evolution model of the wind turbine generator set based on thermodynamic principles, and calculate the operating temperature of the wind turbine generator set by combining the temperature adjustment coefficient and the target equilibrium temperature;

[0038] The temperature balance point and response characteristics analysis submodule is used to determine the temperature balance state and dynamic change law of the wind turbine under various operating conditions, and simulate the inertia and delay effects of temperature response;

[0039] The temperature random fluctuation simulation submodule is used to introduce temperature random fluctuation terms to simulate the temperature uncertainty caused by external factors and measurement errors in the actual environment.

[0040] Furthermore, the output state vector includes:

[0041] The health status subvector containing the degradation degree and wind turbine operating temperature;

[0042] The environmental condition subvector containing wind speed and ambient reference temperature;

[0043] A historical information subvector containing the accumulated operating time and maintenance records;

[0044] The economic state subvector contains the cumulative power generation, cumulative power generation revenue and maintenance cost.

[0045] Furthermore, the maintenance effect simulation module specifically includes:

[0046] The wind turbine status update submodule is used to update the degradation degree according to the maintenance activity type;

[0047] The temperature parameter update submodule is used to update the wind turbine operating temperature according to the type of maintenance activity;

[0048] The cost calculation and economic indicator update submodule is used to obtain the corresponding maintenance cost according to the maintenance activity type;

[0049] The maintenance cooling period management submodule is used to set a maintenance cooling period mechanism based on time intervals and system status.

[0050] On the other hand, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the computer program is executed by a processor, a high-fidelity simulation platform for the operating state of a wind turbine degradation-temperature coupling as described above is implemented.

[0051] On the other hand, the present invention also provides an electronic device, including a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and is characterized in that when the processor executes the computer program, it implements a high-fidelity simulation platform for the operating state of a wind turbine degradation-temperature coupling as described above.

[0052] As can be seen from the above technical solutions, compared with the prior art, the present invention provides a high-fidelity simulation platform, storage medium, and electronic device for the degradation-temperature coupled operation of a wind turbine generator set, which has the following beneficial effects:

[0053] 1. This invention introduces a bidirectional degradation-temperature coupling mechanism, establishing a positive feedback relationship between the wind turbine's degradation state and operating temperature, simulating the temperature changes and degradation process during wind turbine operation. This mechanism accurately captures the entire process of a wind turbine from normal state through accelerated degradation to failure, significantly improving the physical fidelity of the simulation environment and providing a reliable simulation foundation for fault precursor research and predictive maintenance strategy optimization.

[0054] 2. The multi-stage nonlinear degradation model employed in this invention differs from traditional linear degradation assumptions. It describes the changing characteristics of a wind turbine at different degradation stages through piecewise functions. Incorporating the influence of wind speed load and time effects, it achieves high-fidelity simulation of complex degradation processes. This model can be used to simulate the accelerated degradation of wind turbines in the later stages of aging, facilitating targeted maintenance decisions.

[0055] 3. The stochastic wind speed model based on the Weibull distribution used in this paper takes into account the statistical distribution characteristics of wind speed. Incorporating seasonal variations, intraday fluctuations, and temporal autocorrelation, the generated wind speed series can reflect the wind speed characteristics of actual wind farms. This high-fidelity environmental simulation provides important support for optimizing seasonal maintenance strategies for wind farms, enabling decisions to be more tailored to the actual operating environment.

[0056] 4. The power conversion model constructed in this invention takes into account the nonlinear impact of equipment degradation on power generation efficiency, describing the changes in power generation performance at different degradation stages. This model can be used for economic benefit analysis and maintenance decision evaluation, combining technical and economic indicators. This model can be applied to power output prediction of highly degraded equipment, providing a basis for maintenance timing decisions.

[0057] 5. This invention utilizes a modular design, and the simulation environment supports parallel training and long-term simulation, meeting the computational demands of modern maintenance strategy optimization. The system's interface design is compatible with industry standards and can be integrated with reinforcement learning algorithms and optimization methods, enhancing the practicality and versatility of the simulation environment.

[0058] The technical solution of the present invention is further described in detail below through the accompanying drawings and embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0059] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0060] Figure 1 Schematic diagram of the framework of a high-fidelity simulation platform for the degradation-temperature coupled operation status of a wind turbine generator system provided by an embodiment of the present invention.

[0061] Figure 2 Schematic diagram of a multi-stage nonlinear degradation model provided by an embodiment of the present invention.

[0062] Figure 3 Schematic diagram of the impact of wind speed power conversion and degradation on power generation efficiency provided by an embodiment of the present invention.

[0063] Figure 4 Schematic diagram of the degradation-temperature bidirectional coupling mechanism provided by an embodiment of the present invention.

[0064] Figure 5 A schematic diagram of maintenance effect simulation provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0066] Example 1:

[0067] The embodiment of the present invention discloses a high-fidelity simulation platform for the operation state of a wind turbine generator system with degradation and temperature coupling. Figure 1 As shown, it includes the following modules:

[0068] Wind speed simulation module, used to generate complete wind speed time series with seasonal variation and intraday fluctuation characteristics based on Weibull distribution;

[0069] The degradation model module is used to divide the nonlinear degradation process of wind turbines into three stages: early degradation, mid-degradation and late degradation, and set the transition threshold between each stage;

[0070] The power conversion module is used to obtain the actual output power of the wind turbine based on the complete wind speed time series and nonlinear degradation process;

[0071] A coupling calculation module is used to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine based on the temperature sensitivity coefficient and the actual output power;

[0072] The temperature dynamics module is used to simulate the temperature variation characteristics of wind turbines based on a bidirectional coupling mechanism and obtain the operating temperature of wind turbines;

[0073] A state representation module is used to construct the output state vector of the simulation environment based on the wind speed simulation module, degradation model module, power conversion module, coupling calculation module and temperature dynamic module;

[0074] Maintenance effect simulation module is used to simulate the impact of different maintenance activities on system status.

[0075] This invention provides a high-fidelity simulation platform for wind turbine degradation and temperature-coupled operational status. By accurately simulating the physical processes and state evolution of wind turbines, it overcomes the limitations of traditional simulation models and provides solid technical support for optimizing wind farm maintenance strategies and improving operational efficiency. The system's high fidelity, versatility, and computational efficiency make it a crucial tool for the wind power industry's digital transformation and intelligent operations, offering significant engineering application value and economic benefits.

[0076] Next, each of the above modules will be described in detail.

[0077] 1. Wind speed simulation module 10:

[0078] The wind speed simulation module 10 is used to generate a complete wind speed time series with seasonal variation and intraday fluctuation characteristics based on Weibull distribution; specifically, the wind speed simulation module 10 includes the following submodules:

[0079] (1) Basic wind speed generation submodule:

[0080] The basic wind speed generation submodule is used to generate basic wind speed values ​​based on the shape parameter and scale parameter of the Weibull distribution; wherein the Weibull distribution is expressed as:

[0081]

[0082] Where v represents wind speed; f(v) represents the probability density function of wind speed v; k represents the shape parameter; and c represents the scale parameter. In practice, different values ​​of k and c can be selected based on the wind conditions in different regions. For example, k = 2.0 and c = 7.0 m / s.

[0083] (2) Time correlation modeling submodule:

[0084] The time-correlation modeling submodule is used to construct a time-correlation wind speed sequence based on the basic wind speed value, combining the autoregressive model with the random disturbance term to ensure the continuity and reality of wind speed changes. A seasonal adjustment factor is introduced during the construction process to simulate the seasonal changes of wind speed. It is expressed as:

[0085]

[0086] Among them, v t represents the wind speed value at time t; v t-1 represents the wind speed value at time t-1; α w Represents the autoregressive coefficient, with a value range of [0,1], which is used to control the temporal autocorrelation strength of wind speed, usually α w =0.8; v base represents the basic wind speed value, which is generated by Weibull distribution; s(t) represents the seasonal adjustment factor, which is used to simulate the wind speed changes in different seasons; σ v Indicates the random fluctuation intensity, used to simulate the randomness of wind speed, usually taken as σ v =0.5;ε t represents a standard normally distributed random variable; by v With ε t Multiply to adjust the amplitude of random disturbance;

[0087] The above autoregressive coefficient α w The short-term correlation and time continuity characteristics of simulated wind speed are realized;

[0088] The seasonal adjustment factor s(t) characterizes the long-term climate change pattern, achieves a differentiated expression of wind speed characteristics in different seasons, reflects the periodic fluctuation of wind speed with seasonal changes, and also plays a role in correcting wind speed data. The seasonal adjustment factor s(t) is expressed as:

[0089]

[0090] Among them, A s Indicates the seasonal fluctuation range, usually A s =0.2; Indicates phase offset, which is used to adjust the season when peak wind speed occurs and can be adjusted according to specific regions.

[0091] (3) Intraday volatility superposition submodule:

[0092] The intraday fluctuation superposition submodule is used to introduce the intraday fluctuation pattern based on the time-correlated wind speed series to generate a complete wind speed time series; it is expressed as:

[0093]

[0094] Among them, v day (t) represents the complete wind speed time series; A d Indicates the intraday fluctuation range, usually A d =0.15; t hour Indicates the number of hours in a day; Indicates the phase offset, which is used to adjust the time when the peak wind speed occurs during the day. It is usually set so that the wind speed reaches its peak in the afternoon.

[0095] Based on the above seasonal adjustment factors and intraday fluctuation patterns, a complete wind speed time series with both long-period seasonal changes and short-period intraday fluctuation characteristics is generated, realizing a comprehensive simulation of wind speed variation characteristics at multiple time scales.

[0096] 2. Degradation model module 20:

[0097] The degradation model module 20 is used to divide the nonlinear degradation process of the wind turbine into three stages with different degradation laws based on the aging characteristics of the wind turbine, namely, the initial degradation stage, the middle degradation stage and the late degradation stage, and set the transition threshold between the stages to simulate the degradation process of the wind turbine. For details, see Figure 2 As shown in the figure, the three stages (initial, intermediate and late) of the degradation process of wind turbines are shown, showing the changing rules of degradation rates in different stages and the basic degradation function characteristic curves of each stage;

[0098] The degradation model module 20 also includes the following submodules:

[0099] (1) Stage degradation function definition submodule:

[0100] The degradation function definition submodule of this stage is used to define the basic degradation function of the current degradation degree for the early, middle and late stages of degradation, so as to characterize the degradation rate changes at different stages. The basic degradation function is expressed as:

[0101]

[0102] Among them, F base (d t ) represents the basic degradation function; d t Represents the degradation degree at time t, and its value range is , where 0 represents a brand new state and 1 represents a completely failed state; d th1 Indicates the transition threshold between the early stage of degradation and the middle stage of degradation, usually d th1 =0.3;d th2 Indicates the transition threshold between the middle and late stages of degeneration, usually d th2 =0.7;

[0103] Specifically, α1=0.0001h -1 is the basic degradation rate coefficient at the initial stage of degradation, α2=0.0002h -1 is the basic degradation rate coefficient in the middle stage of degradation, α3=0.0004h -1 is the basic degradation rate coefficient in the late stage of degradation, and its numerical relationship is α 1< α 2< α3 reflects the physical characteristics of the wind turbine foundation degradation intensity gradually increasing at different degradation stages; d th1 =0.3 is the transition threshold from the early stage to the middle stage of degradation, d th2 =0.7 is the transition threshold from the middle to the late stage of degradation, which accurately divides the different degradation stages of the entire life cycle of the equipment and realizes stage-by-stage degradation modeling.

[0104] (2) Load impact modeling submodule:

[0105] The load impact modeling submodule is used to quantify the dynamic load impact function that describes the wind speed fluctuation and load change on the degradation rate of the wind turbine, so as to characterize that high load operation will accelerate the degradation of the wind turbine. The load impact function is expressed as:

[0106]

[0107] Among them, f load (v t ) represents the load influence function, usually β l =0.4; P(v t ) represents the power output under wind speed at time t; P rated Indicates rated power.

[0108] (3) Time cumulative effect modeling submodule:

[0109] The time cumulative effect modeling submodule is used to simulate the cumulative effect of material fatigue and natural aging on the degradation rate caused by long-term use of wind turbines, which is represented by the time influence function:

[0110]

[0111] Among them, F t (T cum ) represents the time influence function; γ represents the time influence coefficient, usually γ=0.02; T cum Indicates the cumulative running time; T ref Indicates the reference time scale, usually taken as the number of hours in a year, 8760;

[0112] (4) Natural degradation evolution submodule:

[0113] The natural degradation evolution submodule is used to base (d t ), load impact function f load (v t ) and time influence function F t (T cum ) and temperature influence factor f temp (T t ), simulate the natural degradation evolution process of wind turbines under normal operating conditions and update the degradation degree; it is expressed as:

[0114] d t+1 =d t +F base (d t )·f load (v t )·F t (T cum )·f temp (T t )·Δt

[0115] Among them, d t+1 represents the degradation degree at time t+1; Δt is the time step in hours; f temp (T t ) represents the temperature influence factor, which is provided by the coupling calculation module.

[0116] 3. Power conversion module 30:

[0117] The power conversion module 30 is used to obtain the actual output power of the wind turbine based on the complete wind speed time series and the nonlinear degradation process. The power conversion module 30 specifically includes:

[0118] (1) Wind speed-power output modeling submodule:

[0119] The wind speed-power output modeling submodule is used to determine the working range of the current wind speed based on the real-time wind speed data in the complete wind speed time series by comparing it with the preset cut-in wind speed, rated wind speed, and cut-out wind speed, and obtain the ideal output power of the wind turbine based on the corresponding power curve model;

[0120] Specifically, a piecewise function model of wind speed and ideal power output is constructed to accurately reflect the working characteristics of the wind turbine; it is expressed as:

[0121]

[0122] Where P0(v) represents the ideal output power; v represents the wind speed; v cut-in Indicates the cut-in wind speed, usually 3m / s; v rated Indicates the rated wind speed, usually 12m / s; v cut-out Indicates the cut-out wind speed, usually 25m / s; P rated Indicates the rated power. For a typical 2MW wind turbine, it is 2000kW.

[0123] The above ideal output power follows the standard power curve characteristics of the wind turbine; the power output under this ideal state is defined by the basic power curve: below the cut-in wind speed, the power output is zero; between the cut-in wind speed and the rated wind speed, the power output increases with the cube of the wind speed; between the rated wind speed and the cut-out wind speed, the power output maintains a constant rated power value; above the cut-out wind speed, the power output is zero, and the equipment enters a safety protection state.

[0124] (2) Degradation efficiency modeling submodule:

[0125] The degradation efficiency modeling submodule is used to calculate the power generation efficiency coefficient of the wind turbine according to the degradation degree obtained based on the nonlinear degradation process;

[0126] Specifically, a relationship model between degradation degree and efficiency coefficient is established, and the attenuation effect of different degradation degrees on the power generation efficiency of wind turbines is quantified by combining linear and quadratic terms. The resulting power generation efficiency coefficient is expressed as:

[0127]

[0128] Among them, d t represents the degradation degree at time t; η(d t ) represents the degradation degree d t Corresponding power generation efficiency coefficient; α η and β η is the model parameter, usually α η =0.3,β η =0.5, indicating that as degradation intensifies, efficiency loss accelerates; specifically, α ηis the linear degradation coefficient, which indicates the linear effect of degradation on efficiency. A value of 0.3 means that when the degradation degree is 0.1, the efficiency loss caused by linear factors is 3%, which mainly reflects the influence of progressive degradation factors such as slight wear and surface contamination. η is the quadratic degradation coefficient, which indicates the nonlinear effect of degradation on efficiency. Its value of 0.5 reflects the accelerated efficiency loss during severe degradation, mainly reflecting the influence of accelerated degradation factors such as severe wear and component failure, ensuring that the efficiency decay curve conforms to the actual law of "slow decay in the early stage and accelerated decay in the later stage";

[0129] (3) Real power output calculation submodule:

[0130] The real power output calculation submodule is used to combine the ideal output power and the power generation efficiency coefficient to obtain the actual output power of the wind turbine; it is expressed as:

[0131] P(v,d t )=P0(v)·η(d t )

[0132] Among them, P(v,d t ) represents the actual output power;

[0133] The schematic diagram of the impact of wind speed power conversion and degradation on power generation efficiency is as follows: Figure 3 As shown in the figure, the power output curves under different degradation states (new unit, moderate degradation and severe degradation) are displayed, and the three key wind speed points of cut-in wind speed, rated wind speed and cut-out wind speed are marked; the figure clearly shows how the degree of degradation affects the actual power output capacity of the wind turbine in each wind speed range.

[0134] (4) Economic benefit evaluation submodule is used to obtain power generation benefits based on actual output power and current electricity prices, providing a quantitative basis for decision optimization; the power generation benefits are expressed as:

[0135] R t =P(v,d t )·Δt·price t

[0136] Among them, R t represents the power generation income; Δt is the time step, in hours; price t Represents the electricity price at time t, in yuan / kWh.

[0137] 4. Coupling calculation module 40:

[0138] The coupling calculation module 40 is used to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine generator system based on the temperature sensitivity coefficient and the actual output power. Specifically, the coupling calculation module 40 includes the following submodules:

[0139] (1) Temperature-sensitive degradation rate submodule:

[0140] The temperature-sensitive degradation rate submodule is used to construct a temperature impact factor based on the temperature sensitivity coefficient; it is expressed as:

[0141] f temp (T t )=exp(β T ·(T t -T normal ))

[0142] Among them, f temp (T t ) represents the temperature impact factor, which is used to quantify the influence of the wind turbine operating temperature on the degradation rate. When the operating temperature is higher than the reference temperature, the factor is greater than 1, resulting in an accelerated degradation rate. t represents the operating temperature of the wind turbine at time t, in °C; T normal Indicates the normal operating reference temperature, usually 40°C; β T Indicates the temperature sensitivity coefficient, the unit is 1 / °C, usually β T = 0.05, indicating that the degradation rate increases by about 64% for every 10°C increase in temperature;

[0143] In this formula, the degradation acceleration effect above the normal operating temperature is quantified by the temperature sensitivity coefficient, realizing the unidirectional influence mechanism of temperature on degradation.

[0144] (2) Degradation degree affects the temperature rise sub-model:

[0145] The degradation degree influence temperature rise sub-model is used to simulate the impact of the current wind turbine degradation degree and actual output power (i.e., operating load) on the wind turbine temperature rise and obtain the target equilibrium temperature; it is expressed as:

[0146] T target =T ambient +η p ×P(v,d t )+η d ×d t 2

[0147] Among them, T targetIndicates the target equilibrium temperature of the wind turbine under the current operating conditions, in °C. It represents the theoretical temperature equilibrium point of the wind turbine under the current operating conditions and is used as the input of the temperature dynamic module to calculate the actual operating temperature. ambient The ambient temperature of the environment where the wind turbine is located is in °C. It can be adjusted according to seasonal changes and is usually between -10°C and 40°C, reflecting the basic temperature conditions of the environment where the wind turbine is located. p Indicates the temperature rise coefficient caused by power, in °C / kW, usually η p =0.015°C / kW, reflecting the heating characteristics of wind turbines during normal operation, that is, each kW power output causes approximately °C temperature rise, quantifying the contribution of power output to the device temperature rise; P(v,d t ) represents the actual output power of the wind turbine at time t, in kW. This power value is converted by the power conversion module through P(v,d t )=P0(v)·η(d t ) is calculated, and the impact of degradation on power generation efficiency has been taken into account; η d It represents the additional temperature rise coefficient caused by degradation, in °C, usually η d =30°C, which means that in the fully degraded state (d t = 1), the additional temperature rise due to efficiency loss reaches 30°C; d t 2 The quadratic term represents the degree of degradation at time t, with a value range of [0,1], where 0 represents a brand new state and 1 represents a completely failed state. The quadratic function is used to simulate the rapid temperature rise in the later stage of degradation and reflect the acceleration effect of degradation.

[0148] (3) Temperature-degradation bidirectional coupling simulation submodule:

[0149] The temperature-degradation bidirectional coupling simulation submodule is used to integrate the two influencing mechanisms in the temperature-sensitive degradation rate submodule and the degradation degree-influenced temperature rise submodel, construct a bidirectional coupling mechanism between the nonlinear degradation process and the wind turbine operating temperature, form a degradation-temperature positive feedback loop system, and realize the interaction between degradation and temperature; specifically:

[0150] Step 1) The temperature sensitive degradation rate submodule receives the wind turbine operating temperature T output by the temperature dynamic module 50. t Then, the temperature influence factor f was constructed. temp (T t ), and the temperature influence factor f temp (T t ) is passed to the degradation model module 20;

[0151] Step 2) The natural degradation evolution submodule in the degradation model module 20 receives the temperature impact factor f temp (T t ), the degradation degree is updated and the updated degradation degree d is obtained t+1 ;

[0152] Step 3) The power conversion module 30 can be configured to generate a signal according to the updated degradation degree d t+1 Calculation, expressed as:

[0153] P(v,d t+1 )=P0(v)·η(d t+1 )

[0154] Among them, η(d t+1 ) represents the degradation degree d t+1 The corresponding power generation efficiency coefficient; P(v,d t+1 ) represents the degradation degree d t+1 The corresponding actual output power means the actual output power after considering the degradation effect;

[0155] Step 4) Degradation Degree Impact Temperature Rise Sub-model receives degradation degree d t+1 and the corresponding actual output power P(v,d t+1 ), calculate the degradation degree d t+1 The corresponding target equilibrium temperature T target , expressed as:

[0156] T target =T ambient +η p ×P(v,d t+1 )+η d ×d t+1 2

[0157] Step 5) Set the target equilibrium temperature T target The temperature dynamic module 50 can update the wind turbine operating temperature T according to the formula of the temperature evolution modeling submodule. t+1 ;

[0158] Based on the above content, it is possible to integrate the two influencing mechanisms in the temperature-sensitive degradation rate sub-module and the degradation degree-influenced temperature rise sub-model, and construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine. More specifically:

[0159] The input of the temperature-degradation bidirectional coupling simulation submodule is: the current wind turbine operating temperature T t (from the temperature dynamics module 50), the current degree of degradation (from the degradation model module 20);

[0160] The intermediate transfer of the temperature-degradation bidirectional coupling simulation submodule is: the temperature influence factor f temp (T t ), updated degradation degree d t+1 And the corresponding actual output power P(v,d t+1 );

[0161] The output of the temperature-degradation bidirectional coupling simulation submodule is: target equilibrium temperature T target (transmitted to the temperature dynamics module 50);

[0162] The feedback mechanism of the temperature-degradation bidirectional coupling simulation submodule is: the updated wind turbine operating temperature T t+1 Feedback to the temperature sensitive degradation rate submodule;

[0163] Based on this bidirectional coupling mechanism, the positive feedback loop implemented is as follows:

[0164] Temperature rising stage: Wind turbine operating temperature T t Increase → Temperature influence factor f temp (T t ) exponential growth;

[0165] Degradation acceleration stage: temperature influence factor f temp (T t ) increases → degradation rate increases → degradation degree d t+1 Rapid growth;

[0166] Efficiency reduction stage: Degradation degree increases → power generation efficiency η(d t+1 ) decreases → actual power P(v,d t+1 )decline;

[0167] Temperature rise increase stage: degradation term η d ×d t+1 2 Increase → target equilibrium temperature T target rise;

[0168] Cycle intensification stage: updated wind turbine operating temperature T t+1 If the temperature rises further, it re-enters step 1), forming a vicious cycle. The complete bidirectional coupling process is repeated in each simulation time step (10 minutes) to achieve a continuous interaction between temperature and degradation, accurately simulating the dynamic evolution of the degradation-temperature positive feedback loop during long-term operation of the equipment.

[0169] The schematic diagram of the degradation-temperature bidirectional coupling mechanism can be found in Figure 4As shown in the figure, the influence function of temperature on degradation rate and the influence relationship of degradation state on wind turbine operating temperature are displayed in the form of a flow chart, which intuitively shows the positive feedback loop formed between the two.

[0170] 5. Temperature dynamic module 50:

[0171] The temperature dynamics module 50 is used to simulate the temperature variation characteristics of the wind turbine generator system based on a bidirectional coupling mechanism and calculate the operating temperature of the wind turbine generator system. Specifically, the temperature dynamics module 50 includes the following submodules:

[0172] (1) Temperature evolution modeling submodule:

[0173] The temperature evolution modeling submodule is used to build a wind turbine temperature evolution model based on thermodynamic principles. It combines the temperature adjustment coefficient and the target equilibrium temperature to calculate the wind turbine operating temperature and obtain the temperature change trajectory under different conditions. The wind turbine operating temperature is expressed as:

[0174]

[0175] Among them, T t represents the operating temperature of the wind turbine at time t (e.g. current temperature); T t+1 Indicates the operating temperature of the wind turbine at time t+1 (for example, the temperature after 10 minutes); α T Indicates the temperature adjustment coefficient, usually α T =0.3, indicating the rate at which the system approaches the equilibrium temperature; T target Represents the target equilibrium temperature, which is determined by the coupled calculation module; represents the random temperature fluctuation term that obeys the standard normal distribution, with the standard deviation usually set to 2°C; the coefficient Used to convert the day scale to 10 minute scale.

[0176] (2) Temperature balance point and response characteristics analysis submodule:

[0177] The temperature balance point and response characteristic analysis submodule is used to determine the temperature balance point of the wind turbine under various operating conditions and the time characteristics required to reach balance, that is, to determine the temperature balance state and dynamic change law, and simulate the inertia and delay effects of temperature response.

[0178] (3) Temperature random fluctuation simulation submodule:

[0179] The temperature random fluctuation simulation submodule is used to introduce temperature random fluctuation terms with statistical characteristics to simulate the temperature uncertainty caused by external factors and measurement errors in the actual environment, thereby improving the authenticity of the simulation environment.

[0180] 6. State representation module 60:

[0181] The state representation module 60 is used to construct the output state vector of the simulation environment based on the output data of the wind speed simulation module 10, the degradation model module 20, the power conversion module 30, the coupling calculation module 40 and the temperature dynamic module 50, as well as the state update result of the maintenance effect simulation module 70. ;

[0182] The output state vector is the core output interface of the entire simulation system. It converts the complex operating state of the wind turbine into a standardized data format, including four dimensions: health status, environmental conditions, historical information, and economic status. Its main function is to provide environmental observation data for the reinforcement learning algorithm and support the formulation of intelligent maintenance decisions.

[0183] The output state vector includes:

[0184] (1) Contains the degradation degree d t and wind turbine operating temperature T t The health status sub-vector is used to reflect the core working condition of the wind turbine;

[0185] (2) Including wind speed v t and ambient reference temperature T ambient The environmental condition sub-vector is used to describe the characteristics of the external working environment;

[0186] (3) A historical information sub-vector containing the accumulated operating time and maintenance records, which is used to provide the time dimension characteristics of system operation;

[0187] (4) The economic state subvector containing the cumulative power generation, cumulative power generation income and maintenance cost, which is used to support economic benefit analysis;

[0188] The power generation income is expressed as:

[0189] R t =P(v,d t )·Δt·price t

[0190] At the same time, the cumulative power generation income is expressed as:

[0191]

[0192] Among them, R t Represents the power generation income at time t, in yuan; R total It represents the cumulative power generation revenue from the start of system operation to time t, in yuan; P(v,d t ) represents the actual output power at time t, in kW; Δt is the time step, in hours; λ t Represents the electricity price at time t, in yuan / kWh.

[0193] Data processing algorithms are applied to the above sub-vectors to reduce noise and extract features, improving the accuracy and robustness of state representation. All sub-vectors are then integrated to form a complete state vector, unifying state variables of different dimensions into a similar numerical range, providing a data basis for decision optimization. Finally, a state output interface suitable for subsequent decision algorithms and reinforcement learning models is generated to ensure the compatibility of the simulation environment and the optimization algorithm.

[0194] 7. Maintenance effect simulation module 70:

[0195] The maintenance effect simulation module 70 simulates the impact of different maintenance activities on the system state. It should be noted that the degradation degree update in the maintenance effect simulation module 70 is fundamentally different from the natural degradation evolution in the degradation model module 20. The degradation model module 20 simulates the natural aging process of the equipment, where the degradation degree can only increase and is executed continuously at each time step. In contrast, the maintenance effect simulation module 70 simulates the effects of manual maintenance interventions, where the degradation degree can be reduced through maintenance activities and is executed discretely only when maintenance decisions are made. Together, these two functions form a complete "natural degradation-manual maintenance" cycle, accurately reflecting the actual evolution of the wind turbine's operating state.

[0196] The maintenance effect simulation module 70 interacts closely with the aforementioned state vector in a closed-loop fashion: the state representation module outputs the current system state to the decision-making algorithm, which then selects a maintenance action (continue operation, minor repair, or major overhaul) based on the state. The maintenance effect simulation module 70 then executes the corresponding maintenance activity and updates system state parameters such as degradation and temperature. The updated state is then re-input into the state representation module, forming a complete "state observation-decision execution-state update" cycle. This two-way interaction enables automated optimization and learning of maintenance strategies, serving as a critical bridge connecting the entire simulation environment with the reinforcement learning algorithm. The ultimate goal is to discover the optimal maintenance strategy through continuous learning, thereby reducing operational costs and improving equipment availability.

[0197] Specifically, the maintenance effect simulation module 70 includes the following submodules:

[0198] (1) Wind turbine status update submodule:

[0199] The wind turbine status update submodule uses different degradation status update strategies based on the type of maintenance activity (continued operation, minor repair, or major repair) to accurately simulate the effect of different maintenance activities on the recovery of the equipment health status. Specifically:

[0200] The wind turbine status update submodule is used to update the degradation degree through manual maintenance intervention according to the maintenance activity type (continued operation, minor repair, or major repair). The degradation state naturally increases during continued operation, the degradation state is partially restored by minor repair, and the degradation state is basically restored to the state of the new equipment by major repair. The post-maintenance degradation degree update is expressed as:

[0201]

[0202] Among them, d before and d after Respectively represent the degradation degree before and after maintenance; Δd t is the natural degradation increment; Continue Operation, Minor Repair and Major Repair are all maintenance activity types, representing continued operation, minor repair and major repair respectively; a t is the maintenance decision variable, which is used to represent the type of maintenance activity selected at time t, a t = 0, select Continue Operation (continue running); a t = 1, select Minor Repair; a t = 2, select Major Repair; η repair (d before ) is the minor repair recovery efficiency function. It can be expressed as:

[0203] η repair (d before )=η0×(1-α×d before )

[0204] Among them, η repair (d before ) represents the minor repair recovery efficiency function, which is used to quantify the actual recovery effect of minor repairs performed under the current degraded state. Its value range is [0,1], reflecting the degree to which minor repairs improve the equipment status. η0 represents the basic recovery efficiency, which is usually set to 0.5, representing the theoretical maximum recovery efficiency of a wind turbine performing minor repairs in a brand new state, reflecting the upper limit constraint of the minor repair maintenance technology capability. Degradation influence coefficient, usually set to 0.3, is used to quantify the negative impact of equipment degradation on the recovery effect of minor repairs. It reflects the actual engineering law that "the older the equipment, the worse the recovery effect of minor repairs". That is, for every 0.1 increase in degradation degree, the recovery efficiency of minor repairs decreases by about 3%. beforerepresents the degree of degradation before maintenance, with a value range of [0, 1], where 0 represents a brand new state and 1 represents a completely failed state. This function, as an input variable, determines the actual recovery effect of a minor repair. This function accurately reflects the actual effectiveness of minor repairs for wind turbines through its linear attenuation characteristics. As the degree of equipment degradation increases, the effectiveness of minor repairs decreases linearly. This provides a scientific, quantitative basis for intelligent maintenance decision-making, ensuring that when equipment is severely degraded, a major repair strategy can be promptly implemented, avoiding the economic losses of ineffective maintenance activities.

[0205] (2) Temperature parameter update submodule:

[0206] The temperature parameter update submodule adopts the corresponding temperature update strategy according to the maintenance activity type to reflect the improvement effect of the maintenance activity on the operating temperature of the wind turbine; specifically:

[0207] The temperature parameter update submodule is used to update the wind turbine operating temperature according to the maintenance activity type (continued operation, minor repair, or major repair). During continued operation, the temperature evolves according to a dynamic model, while minor repairs partially reduce the temperature and major repairs restore the temperature to normal operating levels. The temperature update is expressed as:

[0208]

[0209] in, T represents the wind turbine operating temperature at the next moment predicted based on the temperature dynamic model; normal Indicates the normal operating reference temperature, usually 40°C; β minor Indicates the temperature recovery coefficient for minor repairs, usually taken as 0.6; Indicates that it obeys the normal distribution N(0,2 2 ) represents the random temperature fluctuation item after overhaul; Continue Operation, Minor Repair and Major Repair represent continued operation, minor repair and overhaul respectively.

[0210] (3) Cost calculation and economic indicator update submodule:

[0211] The cost calculation and economic indicator update submodule is used to obtain the corresponding maintenance cost based on the maintenance activity type. Specifically, the maintenance cost is calculated based on the maintenance activity type and equipment status, and the system economic indicators are updated to achieve the association between technical indicators and economic indicators. Among them, the cost of minor repairs is usually set at 5% of the equipment value, and the cost of major repairs is 30% of the equipment value. At the same time, the power generation loss during the maintenance period is calculated and the economic indicators are updated.

[0212] (4) Maintenance cooling period management submodule:

[0213] The maintenance cooldown management submodule is used to set a maintenance cooldown mechanism based on time intervals and system status to ensure the feasibility of maintenance activity arrangements and prevent excessively frequent, ineffective maintenance activities. For example, it is set to require the system to run for at least 48 hours after a minor repair before the next minor repair, and at least 168 hours after a major repair before the next maintenance.

[0214] The maintenance effect simulation diagram can be found in Figure 5 The figure shows the impact of different maintenance activities (continued operation, minor repairs, and major overhauls) on the degradation state and temperature of wind turbines, as well as the recovery process after the maintenance activities. The figure visually illustrates the changes in degradation degree and wind turbine operating temperature before and after maintenance, reflecting the effectiveness of implementing different maintenance strategies.

[0215] The simulation system adopts a modular design, allowing each functional module to be independently developed and tested. The system's time step is set to 10 minutes, consistent with the data acquisition frequency of actual wind farm SCADA systems. The system interface design adheres to the OpenAIGym standard, facilitating integration with various reinforcement learning algorithms.

[0216] The implementation can be developed in Python, leveraging scientific computing libraries such as NumPy and Pandas to improve computational efficiency. System status data can be stored in CSV or HDF5 format files for subsequent analysis and visualization. System parameters can be flexibly adjusted through configuration files to meet the needs of different wind farms and equipment types.

[0217] The simulation system of this invention can be applied to fields such as wind turbine lifecycle simulation, wind farm maintenance strategy optimization, equipment lifespan prediction, and fault warning algorithm development. In particular, by combining maintenance strategy optimization with reinforcement learning algorithms, it is possible to develop strategies that are more cost-effective than traditional time-based or condition-based maintenance strategies, significantly reducing wind farm O&M costs and increasing equipment availability.

[0218] In another embodiment, the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the high-fidelity simulation platform for the operating state of a wind turbine degradation-temperature coupling provided above is implemented.

[0219] In another embodiment, the present invention also provides an electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and when the processor executes the computer program, it implements the above-mentioned high-fidelity simulation platform for the operating state of the wind turbine degradation-temperature coupling.

[0220] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the various embodiments can be referenced to each other.

[0221] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status, characterized by: include: Wind speed simulation module, used to generate complete wind speed time series with seasonal variation and intraday fluctuation characteristics based on Weibull distribution; The degradation model module is used to divide the nonlinear degradation process of wind turbines into three stages: early degradation, mid-degradation and late degradation, and set the transition threshold between each stage; A power conversion module, configured to obtain an actual output power of the wind turbine generator system based on the complete wind speed time series and the nonlinear degradation process; A coupling calculation module is used to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine generator set based on the temperature sensitivity coefficient and the actual output power; A temperature dynamic module is used to simulate the temperature variation characteristics of the wind turbine generator set based on the bidirectional coupling mechanism and obtain the operating temperature of the wind turbine generator set; A state representation module, configured to construct an output state vector of a simulation environment based on the wind speed simulation module, the degradation model module, the power conversion module, the coupling calculation module, and the temperature dynamics module; Maintenance effect simulation module, used to simulate the impact of different maintenance activities on system status; The coupling calculation module specifically includes: The temperature-sensitive degradation rate submodule is used to construct the temperature impact factor based on the temperature sensitivity coefficient; The degradation degree influences the temperature rise sub-model, which is used to simulate the actual output power of the current wind turbine and the impact of the degradation degree on the temperature rise of the wind turbine to obtain the target equilibrium temperature; The temperature-degradation bidirectional coupling simulation submodule is used to integrate the two influencing mechanisms in the temperature-sensitive degradation rate submodule and the degradation degree affecting temperature rise submodel, and to construct a bidirectional coupling mechanism between the nonlinear degradation process and the operating temperature of the wind turbine.

2. A high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The wind speed simulation module specifically includes: The basic wind speed generation submodule is used to generate basic wind speed values ​​based on the shape parameters and scale parameters of the Weibull distribution; A time correlation modeling submodule is used to construct a time correlation wind speed sequence based on the basic wind speed value by combining an autoregressive model with a random disturbance term, and to introduce a seasonal adjustment factor during the construction process to simulate seasonal changes in wind speed; The intraday fluctuation superposition submodule is used to introduce the intraday fluctuation pattern on the basis of the time-correlated wind speed sequence to generate a complete wind speed time series.

3. The high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The power conversion module includes: a wind speed-power output modeling submodule for determining the operating range of the current wind speed based on the real-time wind speed data in the complete wind speed time series by comparing it with the preset cut-in wind speed, rated wind speed, and cut-out wind speed, and obtaining the ideal output power of the wind turbine based on the corresponding power curve model; A degradation efficiency modeling submodule, configured to calculate a power generation efficiency coefficient of the wind turbine generator system according to a degradation degree obtained based on the nonlinear degradation process; A real power output calculation submodule, configured to obtain the actual output power of the wind turbine generator set by combining the ideal output power and the power generation efficiency coefficient; The economic benefit evaluation submodule is used to obtain the power generation benefit based on the actual output power and the current electricity price.

4. The high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The degradation model module also includes the following submodules: The stage degradation function definition submodule is used to define the basic degradation function of the current degradation degree for the initial degradation stage, the middle degradation stage and the late degradation stage; Load impact modeling submodule, used to quantify the load impact function that describes the degradation rate of wind turbines due to wind speed fluctuations and load changes; The time cumulative effect modeling submodule is used to simulate the time impact function of the long-term use of wind turbines on the degradation rate; The natural degradation evolution submodule is configured to update the degradation degree based on the temperature impact factor, the basic degradation function, the load impact function, and the time impact function.

5. The high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The temperature dynamic module specifically includes: The temperature evolution modeling submodule is used to construct a temperature evolution model of the wind turbine generator set based on thermodynamic principles, and calculate the operating temperature of the wind turbine generator set by combining the temperature adjustment coefficient and the target equilibrium temperature; The temperature balance point and response characteristics analysis submodule is used to determine the temperature balance state and dynamic change law of the wind turbine under various operating conditions, and simulate the inertia and delay effects of temperature response; The temperature random fluctuation simulation submodule is used to introduce temperature random fluctuation terms to simulate the temperature uncertainty caused by external factors and measurement errors in the actual environment.

6. A high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The output state vector includes: The health status subvector containing the degradation degree and wind turbine operating temperature; The environmental condition subvector containing wind speed and ambient reference temperature; A historical information subvector containing the accumulated operating time and maintenance records; The economic state subvector contains the cumulative power generation, cumulative power generation revenue and maintenance cost.

7. The high-fidelity simulation platform for wind turbine degradation-temperature coupling operation status according to claim 1, characterized in that: The maintenance effect simulation module specifically includes: The wind turbine status update submodule is used to update the degradation degree according to the maintenance activity type; The temperature parameter update submodule is used to update the wind turbine operating temperature according to the type of maintenance activity; The cost calculation and economic indicator update submodule is used to obtain the corresponding maintenance cost according to the maintenance activity type; The maintenance cooling period management submodule is used to set a maintenance cooling period mechanism based on time intervals and system status.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, a high-fidelity simulation platform for the operation state of a wind turbine generator system with degradation and temperature coupling is realized as described in any one of claims 1 to 7.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that can be run on the processor, wherein: When the processor executes the computer program, a high-fidelity simulation platform for the operation state of a wind turbine generator set with degradation and temperature coupling as described in any one of claims 1 to 7 is implemented.

Images