Modelling Techniques to Improve Wind Turbine Performance

Real-time collaborative yaw control of wind farms that maximizes power generation by coordinating wind turbine yaw angles in response to changing wind conditions. The method involves predicting short-term wind variations using wavelet decomposition and machine learning models. This allows rapid and accurate prediction of wind direction and speed variations that can be used for real-time coordinated yaw control to mitigate wake effects between turbines.

Source

Intelligent control method and system for wind turbines that optimizes power generation efficiency by using digital twin modeling, data monitoring, and strategy matching to mitigate the effects of variable wind conditions. The method involves: monitoring wind speed with synchronized sensors, generating predicted wind speed, fitting turbine efficiency using digital twin models, matching optimization results with calibrated wind speeds, and stable optimization using averaged wind speeds.

Source

Optimizing wind turbine yield by adaptive curtailment to mitigate wake effects from nearby obstacles. The method involves using weather forecasts to estimate wind conditions and wake lengths. If forecasts indicate weaker wake impacts, turbine curtailment is reduced. This balances yield vs load protection. The curtailment is also adjusted based on terrain (flat vs mountainous) to account for flow dynamics. The turbine uses a local weather model trained on historical data to adapt curtailment to site-specific conditions. By leveraging forecasts and terrain, curtailment is tailored to reduce wake loads without excessive yield loss.

Source

Optimizing wind turbine performance using reinforcement learning to adjust blade angles and yaw based on predicted wind changes. The system analyzes environmental, equipment, and production factors to evaluate wind energy utilization. It predicts wind direction and speed changes and optimizes turbine adjustments to capture wind energy before actual changes. This improves power generation efficiency and reduces losses compared to just reacting to wind changes. The optimization is verified by comparing wind energy utilization before and after implementing the optimized control.

Source

Wind farm optimization method that quickly adjusts wind turbine parameters to maximize total power output. The method involves determining the dominant wind direction, key turbines in that direction, and correcting non-critical turbine data using a wake model based on the keys. It then optimizes the critical turbine parameters while monitoring total power sensitivity.

Source

Intelligent control of wind turbines using cloud-edge collaboration to improve power generation efficiency and reliability. The method involves real-time collection of wind data and turbine parameters at the edge using sensors and data collectors. It trains a short-term prediction channel using historical data to forecast wind energy accurately. If the forecast accuracy exceeds a threshold, it uses the forecast for intelligent control of the turbine. This leverages local edge processing for real-time monitoring and cloud-based training for accurate wind forecasting.

Source

A system to optimize power output of a wind turbine when operating at yaw misalignment. The system has a control device that calculates target pitch and torque setpoints based on the turbine's yaw misalignment to compensate for reduced efficiency. This allows operating turbines at yaw angles for wake steering without degrading performance. A farm-wide control can also adjust turbine yaw angles to optimize overall power.

Source

Wind farm power optimization by considering wake effects between wind turbines. The method involves a central controller that communicates with local controllers in each wind turbine. The central controller adjusts pitch angles to track the global optimum of total farm power by hill climbing. It calculates gradients based on wind farm power and uses them to guide pitch adjustments. This coordinated pitch optimization mitigates local optima caused by wake effects.

Source

Wind farm power control system that optimizes power allocation considering individual turbine output status to improve reliability and reduce fatigue. The system involves a wind power prediction module, a wind farm power distribution module, a database, SCADA, and turbine control systems. The power distribution module combines power prediction with turbine output analysis to optimize allocation of power commands to turbines based on their current output levels. This better tracks power commands and reduces fatigue compared to uniform or proportional allocation.

Source

Automatic identification of parameters for wind turbine generators to improve control performance, safety and reduce maintenance costs. The method involves controlling the generator to no-load start and shut down by adjusting blade pitch. During this transient, voltages and flux linkage can be measured to determine generator parameters like rotor angle, pole pairs, and flux linkage. Closing the circuit breaker at shutdown allows measuring stator resistance and inductance. This avoids manual parameter entry errors and reduces software versions compared to static tables.

Source

Optimizing wind farm active power regulation during grid frequency fluctuations using model predictive control to accurately allocate adjustment amounts to each wind turbine. This involves quantifying the active support capability of wind turbines using simulation when they only use rotor kinetic energy for short-term regulation. The turbine's maximum up and down power adjustments are calculated under different wind speeds. Then during frequency deviations, the total farm adjustment is computed and allocated per turbine via MPC to avoid exceeding their support limits and prevent rotor speed issues.

Source

Improving the adaptability and robustness of wind farm power generation control against changes in the environment or other factors. The method involves using a multi-agent system where each wind turbine has an independent intelligent agent. Communication connections are deployed between the agents. The inter-turbine wake impact relationship matrix is calculated for each wind turbine. Depth is determined for each turbine based on the matrix to decide if interaction is needed. Then, the yaw decision-making sequence is determined based on turbine depth to optimize efficiency and avoid redundant information.

Source

Wake steering optimization for wind farms that balances turbine efficiency and health. The method involves using a model to analyze factors like turbine waking, offline status, underperformance, and derating. This balances efficiency from wake steering against operational constraints. It generates recommended yaw controls for turbines based on both efficiency and health considerations. The method also uses a probabilistic network to determine turbine operational state. This allows selecting turbines that are feasible for wake steering based on their probability of being waked vs offline vs underperforming vs derated.

Source

Neural network based control of wind turbines to optimize power extraction and robustness. The control uses a trained neural network to estimate the optimal rotor speed and maximum power for a wind turbine given the wind speed. This is done by feeding wind speed and tip speed ratio into the network and outputting the optimal rotor speed and maximum power. The wind turbine is then operated at the estimated optimal speed determined by the neural network for any wind condition. This allows the turbine to track maximum power and efficiently adjust rotor speed in response to wind changes.

Source

Intelligent wind power prediction and dispatching method and system using deep learning and reinforcement learning to improve wind farm output and grid stability. The method involves using a ConvLSTM model to accurately predict wind speed and direction from historical data and meteorological inputs. This is followed by intelligent wind turbine control using reinforcement learning to maximize power and life. Finally, wind farm dispatching using reinforcement learning to balance output with grid needs, reducing impact and losses.

Source

Method to reduce misoperation of wind farm units by using short-term wind speed prediction. The method involves predicting wind speeds at each wind turbine in a wind farm for the next few dozen minutes or hours. This prediction is then used to optimize blade pitch and start/stop decisions to mitigate issues like frequent starts/stops and stall control at high wind speeds. By incorporating short-term wind forecasts into control algorithms, misoperation of wind farm units can be reduced compared to relying solely on real-time wind measurements.

Source

A wind farm control strategy that maximizes overall power generation by using a trained model to predict optimal operating conditions for a wind farm based on real-time wind data and current turbine conditions. The model takes incoming wind data, turbine restrictions, and current turbine settings to forecast the best settings for maximum power. This allows the wind farm to operate at the highest possible output by dynamically adjusting turbine settings in real-time based on the predicted optimal conditions.

Source

Power optimization method for wind farms to reduce wake losses and improve overall power generation by coordinated yaw control. The method involves using a wake model fitted from measured data, particle swarm optimization, and a wind farm power model to determine optimal yaw angles for each turbine. This reduces wake losses compared to individual turbine yawing.

Source

Optimizing power output of multi-rotor wind turbines by accurately determining the optimal yaw angle for the turbines. The method involves measuring wind power parameters over a range of relative wind directions for each rotor nacelle assembly. The maximum power points are determined for each nacelle. The average of these maximum points is used as the control wind direction for the common yaw system. This aligns the rotors with the wind for maximum power.

Source

Optimizing wind turbine power generation by predicting meteorological parameters and using machine learning to find the optimal operating parameters for maximum power. The method involves training a meteorological parameter prediction model and a wind turbine power generation model using support vector machines. It then solves for the optimal operating parameters in real time by combining predicted meteorological parameters and turbine parameters using an adaptive evolution strategy. This allows faster, more accurate wind turbine power optimization compared to using real-time meteorological data.

Source

Method for optimizing power production of wind farms by improving wake recovery between clusters of wind turbines. It involves quantifying the impact of a first cluster's wake on a second cluster, identifying triggers based on that impact, and then controlling the first cluster's turbines to improve wake recovery. This aims to mitigate the wake effect of upstream turbines on downstream turbines, increasing power generation potential of the latter.

Source

Predictive monitoring of wind turbine components like chopper resistors to prevent overheating and failures. It uses two separate thermal models, one to estimate internal temperatures based on external conditions and power loss, and another to predict future surface temperatures using the internal temperatures. By running these models in sequence, it allows detecting potential overheating issues before they become critical. If the predicted surface temperature exceeds limits, action can be taken to shut down the turbine before component failure or safety risks occur.

Source

A method and device to improve the stability and efficiency of wind farm power generation by dynamically adjusting output during ramp events. The method involves constructing a model to predict ramp duration based on historical ramp data. During real-time operation, if a ramp event is detected, the model is used to estimate the ramp duration. The wind farm output is then adjusted during the ramp to reduce power compared to normal operation. This leverages reserve power to mitigate ramp impacts and improve output stability.

Source

Neural network based control of wind turbines that efficiently tracks and adjusts maximum power as wind speed changes. A neural network model is trained using wind speed and tip speed ratio samples to output maximum power and optimum rotor speed. This model is used to control the wind turbine's reference angular speed instead of directly tracking maximum power. This allows the turbine to rapidly adapt to changing wind speeds and extract maximum power. The neural network is trained using a dataset of averaged wind speeds, which is then used to test the model's accuracy. The neural network output is used to control the wind turbine's rotor speed for optimal power extraction.

Source

Refinement energy management method and system for wind farms to improve coordinated control of active and reactive power. The method involves establishing a three-phase power model and wind-force network model for the wind farm using collected data. This allows accurate calculation of wind turbine generator system voltages for coordinated control. The system divides into data acquisition, situational awareness, and coordination control modules for independent functionality. It addresses issues of incompatible data and lack of coordination in existing wind farm energy management systems.

Source

Yaw control method for wind turbines that improves the power generation efficiency of multiple turbines in a wind farm by coordinating their yaw angles. The method involves establishing a reference relationship between turbines based on their locations, calculating wind interference angles between turbines, and adjusting downstream turbines' yaw angles to mitigate interference when upstream turbines face into the wind. This prevents missed opportunities for turbines to capture wind energy when yaw control takes too long. The strategy aims to maximize the frontal windward state duration of turbines in a wind farm.

Source

Vertical wind turbine with a blade pitch motor that allows optimal blade angle adjustment for maximum efficiency and longevity. The blade pitch motor is mounted between the upper and lower blade sections, allowing symmetric torque distribution along the blade span. The pitch motor also supports the blade weight. This avoids external actuators and guys for blade angle control. The pitch motor can have absolute and relative position sensors. The turbine also has a compact transmission with planetary stages. The control calculates optimal blade angles based on wind speed and direction. This enables continuous, smoothest blade pitch control compared to discrete steps.

Source

Yaw control method for wind turbines that improves efficiency by accurately predicting and responding to seasonal wind changes. The method involves using historical wind data to train a seasonal wind prediction model. The model captures seasonal patterns using an autoregressive neural network. Real-time wind data is compared with the predictions to generate optimized yaw control commands. This allows wind turbines to track seasonal wind directions for maximum power capture. Environmental impact factors are also considered in the optimization.

Source

Method and arrangement for determining pitch speeds of wind turbine blades to reduce bearing damage while allowing rapid and reliable blade pitching. The method involves calculating the pitch speed based on the blade bearing moment. If the moment is below a reference, the pitch speed exceeds it. This prevents high moments causing damage. If the moment increases, the pitch speed decreases. If the moment decreases, the pitch speed increases to catch up. This prevents overshooting. It balances speed to minimize damage while allowing quick pitching.

Source

Optimizing power generation in a wind farm by dynamically adjusting the operating parameters of individual wind turbines based on local wind shear conditions. The method involves measuring or predicting the vertical wind shear profile above the wind farm. This profile is then used to determine optimal adjustments to turbine settings like blade pitch, rotor speed, and yaw angle. These adjustments are made in real-time to optimize overall farm power production considering the non-standard wind shear profile and turbine interactions.

Source

A method for optimizing power generation in a wind farm by considering the condition of each turbine. Instead of uniformly reducing power when instructed to match a grid's capacity, each turbine's load factor is calculated based on its specific conditions. This allows turbines with higher faults, older components, or exposed to turbulence to continue operating while others are throttled back. The overall farm power is still adjusted to meet grid requirements.

Source

Yaw wake control method and equipment for wind turbines in wind farms to maximize power output by reducing wake effects between turbines. The method involves optimizing yaw angle and blade pitch/speed based on axial induction factors. It converts optimized axial induction factors into actual controllable pitch and speed for turbines. This reduces wake losses compared to optimizing just yaw or axial factors alone. It involves inputting wind farm data, building an optimization model, solving it, and setting turbine operations based on optimal yaw and converted axial factors.

Source

Real-time wind farm dispatching method using wind power prediction data to optimize power output from wind farms with complex terrain and wake effects. The method involves acquiring wind power prediction data, establishing dispatch indicators, and optimizing control methods to maximize overall farm power generation. It considers wake flow and turbulence factors between turbines to determine optimal output distribution and regulate individual turbine power to mitigate wake losses.

Source

Optimizing the operation of wind turbines to maximize lifetime or energy production by automatically determining the best combination of control features based on user-selected targets. The optimization involves estimating the optimization parameter (lifetime, energy, power demand satisfaction) for different combinations of activated control features, and selecting the combination that best meets the target while considering boundary conditions. The method considers the impact of all possible feature combinations to find the optimal strategy.

Source

Monitoring air flow over a wind turbine blade to improve blade design and control by placing a simple device on the blade surface. It has two air inlets facing opposite directions along an axis. A sensor module with two pressure sensors, one connected to each inlet, outputs signals. Processing determines flow direction based on pressure difference sign and speed based on magnitude. Additional inlets and sensors can provide additional flow data. The device is integrated in the blade and wirelessly communicates.

Source

Dynamic control method and system for optimizing service quality of wind farms. The method involves regulating wind turbine performance to maintain voltage, meet power demand, and optimize health. It uses a two-level control architecture. An upper level controller sets global optimal power references based on farm parameters and demand. A lower level controller adjusts turbine settings like pitch to track the references and improve service quality.

Source

Self-adaptive active power control for hybrid wind farms that optimizes the configuration and operation of the wind farm's sources (current and voltage) to improve grid stability. The method involves predicting source load and grid frequency fluctuations to dynamically allocate power between the sources and use energy storage to supplement power during frequency events. It also considers wind turbine differences to optimally distribute active load. By adapting source configurations based on forecasts, the hybrid wind farm can provide more effective grid frequency regulation.

Source

Power control method for wind farms to safely adjust wind turbine power without excessive speed jumps or shutdowns. The method involves calculating adjustable power ranges for each turbine based on current output levels. When the farm is asked to adjust total power, it allocates within the ranges. This prevents turbines from being over-asked and potentially going unstable during speed transitions. It also prevents the farm controller from commanding turbines to shutdown due to speed limits. By limiting adjustment within turbine capabilities, it reduces sudden speed changes and ensures safe operation.

Source

A stability evaluation method and system for direct-drive wind turbine generators that allows online assessment and parameter adjustment to improve stability of the system. The method involves calculating the energy gradient at the wind turbine terminal using voltage, current, and angle measurements. A negative energy gradient indicates instability. The gradient is influenced by factors like PLL parameters, wind turbine current levels, and transmission line resistance. By understanding these relationships, the method proposes adjustments to critical parameters like PLL gains and wind turbine current limits to improve stability.

Source

Method and control device for adjusting active power of a wind farm to effectively meet adjustment requirements like primary frequency modulation, secondary frequency modulation, and grid faults. The method involves determining an adjustable amount for each turbine based on its own adjustment capabilities. The turbine adjustable amounts are pitch increasable power, rotor kinetic energy increasable power, pitch diminishable power, and brake resistor diminishable power. This allows flexible, fast, and impact-minimized power adjustments by leveraging each turbine's unique capabilities.

Source

Intelligent wind farm power control system using deep learning for optimal economic dispatch of multiple wind turbines. It extracts multi-scale correlation features between turbine power and grid price using convolutional neural networks. The features are fused and decoded to obtain an economic index for each turbine. Turbines are prioritized based on indices and power is controlled accordingly for stable operation and economic benefits.

Source

Accurately determining the angular position of a wind turbine generator using an encoder sensor, even when the encoder has imperfections that distort the position signal. The method involves compensating for the distortions to improve position determination accuracy. The compensation signal is calculated based on the imperfection characteristics and applied to the raw position signal to correct for the distortions. This modified position signal is then used for tasks like wind turbine control.

Source

Predictive control method for wind turbines that improves efficiency by accurately predicting wind speeds and using that prediction to control turbine rotor speed. The method involves collecting wind speed data from the entire wind farm over a certain duration. This data is used to train a wind speed prediction model. The model is then applied to predict wind speeds at a turbine site for a shorter duration. This prediction is used to calculate the optimal turbine rotor speed for that time period.

Source

Operating wind turbines more efficiently by using real-time loading and travel data to estimate component damage accumulation and make adjustments to preventive maintenance and turbine operation. Instead of relying on simulated loading histories, the method involves generating actual cumulative loading histograms based on the measured or estimated loading and travel metrics during turbine operation. This allows accurate damage tracking and decision making based on the true fatigue experience of the components. The histograms are applied to life models to determine current damage levels and actions like shutdown, power reduction, or maintenance scheduling are implemented based on that.

Source

Active power control method for wind farms that balances load fatigue, production capacity, and power output. It aims to reduce wind turbine fatigue by optimizing power production while considering load distribution across the wind farm. The method involves constructing a mixed objective function that balances fatigue, capacity, and power. Constraints are added to ensure feasibility. The optimal active power set is then found using a solver.

Source

Method for scheduling active power generation in a wind farm using DFIG (Doubly Fed Induction Generator) wind turbines. The method involves coordinating active power and reactive power control within the wind farm to maximize reactive power generation capability. The scheduling algorithm selects turbines based on their active power output potential and reactive power limits. This allows utilizing the full reactive power capacity of the wind farm while meeting grid constraints. It improves coordinated control of active and reactive power inside the wind farm compared to traditional methods that separately optimize each power component.

Source

Neural network based control of wind turbines using permanent magnet synchronous generators (PMSG) that can efficiently and robustly track maximum power at varying wind speeds. The control involves training a neural network with wind speed and other parameters to output optimum rotor speed and maximum power. This network is then used to control the PMSG turbine based on real-time wind speed measurements, allowing the turbine to operate at maximum power in varying winds.

Source

Optimizing wind farm power output by dynamically allocating power among the wind turbines based on their operating states and wind conditions. The method involves dividing turbines into shutdown, running, and starting states, calculating power margins for running turbines, and adjusting power allocations to reach set targets. This improves wind farm power tracking accuracy and stability compared to uniform power distribution.

Source

Coordinating yaw control of multiple wind turbines to improve overall wind farm energy extraction. The method involves using data from multiple turbines and other sources to determine the overall wind direction across the turbine group or wind farm. This allows coordinated yaw control at farm level, collective yaw control across multiple turbines, and turbine level yaw control. It also involves regular yaw misalignment correction and wind direction prediction for advanced yaw control.

Source

Wind farm control and active power prediction method to improve wind farm stability and grid integration. The method involves predicting the active power variation of each wind turbine based on wind speed and calculation parameters. This allows determining the overall wind farm power limit. By predicting turbine power changes, it prevents over-limiting turbines with headroom. It removes anomalous data, short cycles, small changes, and excessive wind speed/speed change.

Source