In view of the fact that dynamic stall models in the wind energy industry such as ONERA model, Beddoes–Leishman model, and Snel model are mostly semi‐empirical models, and the determination of empirical time constants has a great influence on the model accuracy. To optimize the time constant in dynamic stall model and improve the prediction accuracy of unsteady aerodynamics, the influence of boundary layer and pressure lag on the unsteady performance of the S809 airfoil under 2D flow conditions is explored using a simple semi‐empirical dynamic stall engineering model. The proposed model consists of four first‐order differential equations accounting for attached flow and dynamic separation flow of trailing edge based on the Theodorsen theory. A validation is carried out by the wind tunnel experiment in the Key Laboratory of Wind and Solar Energy Utilization Technology of the Ministry of Education at Inner Mongolia University of Technology. The main conclusions are as follows. The time constants for lag in pressure and boundary layer both have a great influence on the unsteady lift coefficient. When the mean angle of attack is relatively small and the airflow is between the attached flow and the separated flow, appropriately reducing the time constant can make the prediction results closer to the experimental values. When the mean angle of attack is relatively large and the airflow is in condition of fully separated flow, the time constant value can be appropriately increased. The influence of pressure lag and boundary layer lag on the unsteady drag coefficient is not significant.
鉴于风能行业中的动失速模型如 ONERA 模型、Beddoes-Leishman 模型和 Snel 模型等多为半经验模型，而经验时间常数的确定对模型精度有很大影响。为了优化动失速模型中的时间常数，提高非稳态空气动力学的预测精度，利用简单的半经验动失速工程模型，探讨了边界层和压力滞后对 S809 机翼在二维流动条件下非稳态性能的影响。所提出的模型由四个一阶微分方程组成，根据 Theodorsen 理论计算后缘的附着流和动态分离流。在内蒙古工业大学风能和太阳能利用技术教育部重点实验室进行的风洞试验对该模型进行了验证。主要结论如下。压力滞后时间常数和边界层滞后时间常数对非稳态升力系数影响较大。当平均攻角相对较小，气流介于附着流和分离流之间时，适当减小时间常数可以使预测结果更接近实验值。当平均攻角相对较大，气流处于完全分离状态时，可适当增大时间常数值。压力滞后和边界层滞后对非稳定阻力系数的影响不大。
{"title":"Influence of boundary layer and pressure lag on unsteady aerodynamics of airfoil based on a simple semi‐empirical dynamic stall engineering model","authors":"Meng Chen, Zhiguo Li, Zhiying Gao, Jianwen Wang","doi":"10.1002/we.2931","DOIUrl":"https://doi.org/10.1002/we.2931","url":null,"abstract":"In view of the fact that dynamic stall models in the wind energy industry such as ONERA model, Beddoes–Leishman model, and Snel model are mostly semi‐empirical models, and the determination of empirical time constants has a great influence on the model accuracy. To optimize the time constant in dynamic stall model and improve the prediction accuracy of unsteady aerodynamics, the influence of boundary layer and pressure lag on the unsteady performance of the S809 airfoil under 2D flow conditions is explored using a simple semi‐empirical dynamic stall engineering model. The proposed model consists of four first‐order differential equations accounting for attached flow and dynamic separation flow of trailing edge based on the Theodorsen theory. A validation is carried out by the wind tunnel experiment in the Key Laboratory of Wind and Solar Energy Utilization Technology of the Ministry of Education at Inner Mongolia University of Technology. The main conclusions are as follows. The time constants for lag in pressure and boundary layer both have a great influence on the unsteady lift coefficient. When the mean angle of attack is relatively small and the airflow is between the attached flow and the separated flow, appropriately reducing the time constant can make the prediction results closer to the experimental values. When the mean angle of attack is relatively large and the airflow is in condition of fully separated flow, the time constant value can be appropriately increased. The influence of pressure lag and boundary layer lag on the unsteady drag coefficient is not significant.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-06-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141355950","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study introduces a constrained many‐objective optimization approach for the optimal design of 20 MW direct drive (DD) permanent magnet synchronous generators (PMSGs). Designing a high‐performance, competitive DD‐PMSG requires considering the generator's performance as well as its weight and material cost. Therefore, we focus on four main characteristics as our design objectives: (1) specific power (power per weight), (2) power‐per‐cost, (3) efficiency, and (4) power factor. To achieve this, we apply an advanced constrained nondominated sorting genetic algorithm III (NSGA‐III), a many‐objective optimization method utilizing evolutionary computation, capable of optimizing four or more objectives with constraints. Additionally, the electromagnetic finite element method is employed to evaluate the generator's characteristics. Through our proposed design process, we optimize three distinct 20 MW DD‐PMSG configurations: a 320‐pole/300‐slot, a 350‐pole/300‐slot, and a 350‐pole/336‐slot topology. Following this optimization, we perform additional multiphysics simulations (covering electromagnetic, structural, overload, and thermal aspects) and control response simulations on four selected models from the Pareto‐optimal solutions to validate their effectiveness as preliminary DD‐PMSG designs. Finally, we conduct a comprehensive analysis of all simulation results.
{"title":"Design of 20 MW direct‐drive permanent magnet synchronous generators for wind turbines based on constrained many‐objective optimization","authors":"Seok‐Won Jung, Dohyun Kang, Kumarasamy Palanimuthu, Young Hoon Joo, Sang‐Yong Jung","doi":"10.1002/we.2916","DOIUrl":"https://doi.org/10.1002/we.2916","url":null,"abstract":"This study introduces a constrained many‐objective optimization approach for the optimal design of 20 MW direct drive (DD) permanent magnet synchronous generators (PMSGs). Designing a high‐performance, competitive DD‐PMSG requires considering the generator's performance as well as its weight and material cost. Therefore, we focus on four main characteristics as our design objectives: (1) specific power (power per weight), (2) power‐per‐cost, (3) efficiency, and (4) power factor. To achieve this, we apply an advanced constrained nondominated sorting genetic algorithm III (NSGA‐III), a many‐objective optimization method utilizing evolutionary computation, capable of optimizing four or more objectives with constraints. Additionally, the electromagnetic finite element method is employed to evaluate the generator's characteristics. Through our proposed design process, we optimize three distinct 20 MW DD‐PMSG configurations: a 320‐pole/300‐slot, a 350‐pole/300‐slot, and a 350‐pole/336‐slot topology. Following this optimization, we perform additional multiphysics simulations (covering electromagnetic, structural, overload, and thermal aspects) and control response simulations on four selected models from the Pareto‐optimal solutions to validate their effectiveness as preliminary DD‐PMSG designs. Finally, we conduct a comprehensive analysis of all simulation results.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141115449","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ian Ammerman, Y. Alkarem, Richard W. Kimball, Kimberly Huguenard, Babak Hejrati
To enable real‐time monitoring and control strategies for floating offshore wind turbines, accurate information about the state of the system is needed. This paper details the application of a Kalman filter to the UMaine VolturnUS‐S floating wind platform to provide accurate state estimates in real time using minimal system measurements. The midfidelity nonlinear simulation tool OpenFAST was used to generate the underlying linear state‐space model for the Kalman filter. This linear model and its limitations are demonstrated through comparison with experimental data collected on a 1:70 froude‐scaled model of the floating platform and tower. Using a selection of five measurements from the real system, a Kalman filter was developed to provide estimates for the remaining system states and measurements. These estimates were then validated against the experimental values collected from testing of the scale model. Validation of the Kalman filter produced accurate estimates of surge, heave, and tower base bending moment, measurements of which were not available to the Kalman filter. Performance of the Kalman filter was tested and validated over a range of sea conditions from rated wind speed to storm events and demonstrated robustness in the Kalman filter to maintain accuracy across all operating conditions despite significant error in the underlying linear model for extreme conditions.
{"title":"Experimental validation of a Kalman observer using linearized OpenFAST and a fully instrumented 1:70 model","authors":"Ian Ammerman, Y. Alkarem, Richard W. Kimball, Kimberly Huguenard, Babak Hejrati","doi":"10.1002/we.2915","DOIUrl":"https://doi.org/10.1002/we.2915","url":null,"abstract":"To enable real‐time monitoring and control strategies for floating offshore wind turbines, accurate information about the state of the system is needed. This paper details the application of a Kalman filter to the UMaine VolturnUS‐S floating wind platform to provide accurate state estimates in real time using minimal system measurements. The midfidelity nonlinear simulation tool OpenFAST was used to generate the underlying linear state‐space model for the Kalman filter. This linear model and its limitations are demonstrated through comparison with experimental data collected on a 1:70 froude‐scaled model of the floating platform and tower. Using a selection of five measurements from the real system, a Kalman filter was developed to provide estimates for the remaining system states and measurements. These estimates were then validated against the experimental values collected from testing of the scale model. Validation of the Kalman filter produced accurate estimates of surge, heave, and tower base bending moment, measurements of which were not available to the Kalman filter. Performance of the Kalman filter was tested and validated over a range of sea conditions from rated wind speed to storm events and demonstrated robustness in the Kalman filter to maintain accuracy across all operating conditions despite significant error in the underlying linear model for extreme conditions.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140970822","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Remaining useful fatigue life monitoring of wind turbine drivetrains is important. However, the implementation of real‐time monitoring often faces efficiency and accuracy challenges. In order to resolve this, this paper proposes a vibration‐based damage monitoring digital twin (VBDM‐DT) that enables the online intelligent evaluation of wind turbine gearboxes, using gear tooth surface durability as an example fatigue mode. The VBDM‐DT integrates a random wind load model, a high‐fidelity dynamics model, and a fatigue damage model. The random wind load model takes the wind speed from the supervisory control and data acquisition (SCADA) as input to estimate the input torque of the drivetrain in real time. Simultaneously, VBDM‐DT uses the vibration signals from the condition monitoring system (CMS) to intelligently calibrate the dynamics model, allowing it to be continuously adjusted and optimized in response to actual vibrations. The fatigue damage model takes the real‐time dynamic loads estimated by the high‐fidelity dynamic model as input to achieve real‐time fatigue damage monitoring of key components in the wind turbine gearbox. Applying the VBDM‐DT model to a 2 MW wind turbine gearbox, the results indicate that the model provides satisfactory accuracy in estimating input loads and good adaptability in intelligent calibration of the dynamic model. Based on this model, the fatigue life estimation for gears and bearings is more credible and reliable.
{"title":"Digital twin‐driven online intelligent assessment of wind turbine gearbox","authors":"Yadong Zhou, Jianxing Zhou, Quanwei Cui, Jianmin Wen, Xiang Fei","doi":"10.1002/we.2912","DOIUrl":"https://doi.org/10.1002/we.2912","url":null,"abstract":"Remaining useful fatigue life monitoring of wind turbine drivetrains is important. However, the implementation of real‐time monitoring often faces efficiency and accuracy challenges. In order to resolve this, this paper proposes a vibration‐based damage monitoring digital twin (VBDM‐DT) that enables the online intelligent evaluation of wind turbine gearboxes, using gear tooth surface durability as an example fatigue mode. The VBDM‐DT integrates a random wind load model, a high‐fidelity dynamics model, and a fatigue damage model. The random wind load model takes the wind speed from the supervisory control and data acquisition (SCADA) as input to estimate the input torque of the drivetrain in real time. Simultaneously, VBDM‐DT uses the vibration signals from the condition monitoring system (CMS) to intelligently calibrate the dynamics model, allowing it to be continuously adjusted and optimized in response to actual vibrations. The fatigue damage model takes the real‐time dynamic loads estimated by the high‐fidelity dynamic model as input to achieve real‐time fatigue damage monitoring of key components in the wind turbine gearbox. Applying the VBDM‐DT model to a 2 MW wind turbine gearbox, the results indicate that the model provides satisfactory accuracy in estimating input loads and good adaptability in intelligent calibration of the dynamic model. Based on this model, the fatigue life estimation for gears and bearings is more credible and reliable.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141129288","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
L. Sethuraman, Andrew Glaws, Miles Skinner, M. Parans Paranthaman
Currently, many utility‐scale wind turbine generator original equipment manufacturers are dependent on imported rare earth permanent magnets, which are susceptible to market risks from cost instability. To lower the production costs of these generators and stay competitive in the market, several small wind manufacturers are pursuing continuous improvements to both generator design and manufacturing. However, traditional design and manufacturing methods have yielded marginal improvements in wind power performance. This work presents novel methods to redesign a baseline 15‐kW wind turbine generator with reduced rare‐earth permanent magnets by leveraging cutting‐edge three‐dimensional (3D) printed polymer‐bonded permanent magnets and steel. Symmetric, asymmetric, and multimaterial‐magnet parametrization methods are introduced for shape optimization. We extend the symmetric and asymmetric methods to the back iron in the stator to further investigate the impact and opportunities for performance improvements with lesser active materials. We employ a design‐of‐experiments approach with parametric computer‐aided design for shape generation and evaluate different designs by magneto‐thermal modeling and finite‐element analysis. We use adaptive sampling technique to identify better performing designs with lesser magnet mass, higher efficiency, and lower cogging torque when compared with the baseline generator. Asymmetric pole designs resulted in a magnet mass in the range of 4.77–5.37 kg, which was 27%–35% lighter than the baseline generator, suggesting that a new design freedom exists that can be enabled by advanced manufacturing, such as 3D printing. Shaping the back iron in the stator resulted in material savings in electrical steel of up to 14.62 kg, which was 20% lighter than the baseline stator. We conducted a structural analysis to evaluate an optimized asymmetric rotor design from the point of view of mechanical integrity and air‐gap stiffness. The magnetically optimal shape profile was shown as having a positive impact on the radial stiffness, and an optimal solution was discovered to reduce the structural mass by nearly 30 kg, which was 29% lighter than the baseline.
{"title":"Advanced multimaterial shape optimization methods as applied to advanced manufacturing of wind turbine generators","authors":"L. Sethuraman, Andrew Glaws, Miles Skinner, M. Parans Paranthaman","doi":"10.1002/we.2911","DOIUrl":"https://doi.org/10.1002/we.2911","url":null,"abstract":"Currently, many utility‐scale wind turbine generator original equipment manufacturers are dependent on imported rare earth permanent magnets, which are susceptible to market risks from cost instability. To lower the production costs of these generators and stay competitive in the market, several small wind manufacturers are pursuing continuous improvements to both generator design and manufacturing. However, traditional design and manufacturing methods have yielded marginal improvements in wind power performance. This work presents novel methods to redesign a baseline 15‐kW wind turbine generator with reduced rare‐earth permanent magnets by leveraging cutting‐edge three‐dimensional (3D) printed polymer‐bonded permanent magnets and steel. Symmetric, asymmetric, and multimaterial‐magnet parametrization methods are introduced for shape optimization. We extend the symmetric and asymmetric methods to the back iron in the stator to further investigate the impact and opportunities for performance improvements with lesser active materials. We employ a design‐of‐experiments approach with parametric computer‐aided design for shape generation and evaluate different designs by magneto‐thermal modeling and finite‐element analysis. We use adaptive sampling technique to identify better performing designs with lesser magnet mass, higher efficiency, and lower cogging torque when compared with the baseline generator. Asymmetric pole designs resulted in a magnet mass in the range of 4.77–5.37 kg, which was 27%–35% lighter than the baseline generator, suggesting that a new design freedom exists that can be enabled by advanced manufacturing, such as 3D printing. Shaping the back iron in the stator resulted in material savings in electrical steel of up to 14.62 kg, which was 20% lighter than the baseline stator. We conducted a structural analysis to evaluate an optimized asymmetric rotor design from the point of view of mechanical integrity and air‐gap stiffness. The magnetically optimal shape profile was shown as having a positive impact on the radial stiffness, and an optimal solution was discovered to reduce the structural mass by nearly 30 kg, which was 29% lighter than the baseline.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141011464","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Neglecting the velocity reduction in the induction zone of wind turbines can lead to overestimates of power production predictions, and, thus, of the annual energy production for a wind farm. An experimental study on the induction zone associated with wind turbine operations is performed in the boundary‐layer test section of the BLAST wind tunnel at UT Dallas using stereo particle image velocimetry. This experiment provides a detailed quantification of the wind speed decrease associated with the induction zone for two different incoming flows, namely, uniform flow and boundary layer flow. Operations of wind turbines in different regions of the power curve are modeled in the wind tunnel environment with two porous disks with a solidity of 50.4% and 32.3%, which correspond to thrust coefficients of 0.71 and 0.63, respectively. The porous disks are designed to approximate the wake velocity profiles previously measured for utility‐scale wind turbines through scanning wind LiDARs. The results show that the streamwise velocity at one rotor diameter upwind of both disks decreases 1% more for the boundary layer flow than for the uniform flow. Further, the effect of shear in front of the disk with a higher thrust coefficient can be observed until 1.75 rotor diameter upwind of the disk, whereas for the disk with a lower thrust coefficient, the effect of shear becomes negligible at 1.25 rotor diameter upwind. It is found that at one rotor diameter upwind, for both incoming flows, the disk having a higher thrust coefficient has 2% more velocity reduction than the lower‐thrust‐coefficient disk. The results suggest that the variability in wind shear and rotor thrust coefficient, which is encountered during typical operations of wind turbines, should be considered for the development of improved models for predictions of the rotor induction zone, the respective cumulative effects in the presence of multiple turbines, namely, wind farm blockage, and more accurate predictions of wind farm power capture.
{"title":"Effects of wind shear and thrust coefficient on the induction zone of a porous disk: A wind tunnel study","authors":"Wasi Uddin Ahmed, G. Iungo","doi":"10.1002/we.2910","DOIUrl":"https://doi.org/10.1002/we.2910","url":null,"abstract":"Neglecting the velocity reduction in the induction zone of wind turbines can lead to overestimates of power production predictions, and, thus, of the annual energy production for a wind farm. An experimental study on the induction zone associated with wind turbine operations is performed in the boundary‐layer test section of the BLAST wind tunnel at UT Dallas using stereo particle image velocimetry. This experiment provides a detailed quantification of the wind speed decrease associated with the induction zone for two different incoming flows, namely, uniform flow and boundary layer flow. Operations of wind turbines in different regions of the power curve are modeled in the wind tunnel environment with two porous disks with a solidity of 50.4% and 32.3%, which correspond to thrust coefficients of 0.71 and 0.63, respectively. The porous disks are designed to approximate the wake velocity profiles previously measured for utility‐scale wind turbines through scanning wind LiDARs. The results show that the streamwise velocity at one rotor diameter upwind of both disks decreases 1% more for the boundary layer flow than for the uniform flow. Further, the effect of shear in front of the disk with a higher thrust coefficient can be observed until 1.75 rotor diameter upwind of the disk, whereas for the disk with a lower thrust coefficient, the effect of shear becomes negligible at 1.25 rotor diameter upwind. It is found that at one rotor diameter upwind, for both incoming flows, the disk having a higher thrust coefficient has 2% more velocity reduction than the lower‐thrust‐coefficient disk. The results suggest that the variability in wind shear and rotor thrust coefficient, which is encountered during typical operations of wind turbines, should be considered for the development of improved models for predictions of the rotor induction zone, the respective cumulative effects in the presence of multiple turbines, namely, wind farm blockage, and more accurate predictions of wind farm power capture.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141013092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Offshore wind turbines have rapidly scaled up in recent years, with plans to construct turbines up to 22 MW in the next decade. However, the operations and maintenance (O&M) requirements for these ‘next‐generation turbines’ remain largely unknown. In this study, the total O&M costs are calculated, using a bench‐marked O&M model, for a hypothetical 10 MW turbine scenario using two drive train configurations, based on known failure rates of smaller turbines. The O&M costs of the 10 MW turbines are compared with those of existing 3 MW turbines in two case studies: a North Sea wind farm and an East Coast US wind farm. Overall, direct drive 10 MW turbines performed better depending on the site's climate conditions. The study indicated that the two‐stage drive train configuration may be more suitable for the US site than the North Sea, depending on the turbine's failure rate. The US site benefited from increased availability due to more favourable weather windows, resulting in lower lost revenue for the two‐stage configuration despite high transport costs. The study found that the failure rate of 10 MW offshore wind turbines in the North Sea with a two‐stage gearbox can increase by as much as 30% compared to the 3 MW failure rates without increasing direct O&M costs. These findings are crucial for the offshore wind energy industry, particularly for OEMs, developers and maintenance providers, as they provide insights into the required reliability for next generation turbines to reduce O&M costs compared to existing 3 MW turbines.
{"title":"Analysing the cost impact of failure rates for the next generation of offshore wind turbines","authors":"Orla Donnelly, James Carroll, Michael Howland","doi":"10.1002/we.2907","DOIUrl":"https://doi.org/10.1002/we.2907","url":null,"abstract":"Offshore wind turbines have rapidly scaled up in recent years, with plans to construct turbines up to 22 MW in the next decade. However, the operations and maintenance (O&M) requirements for these ‘next‐generation turbines’ remain largely unknown. In this study, the total O&M costs are calculated, using a bench‐marked O&M model, for a hypothetical 10 MW turbine scenario using two drive train configurations, based on known failure rates of smaller turbines. The O&M costs of the 10 MW turbines are compared with those of existing 3 MW turbines in two case studies: a North Sea wind farm and an East Coast US wind farm. Overall, direct drive 10 MW turbines performed better depending on the site's climate conditions. The study indicated that the two‐stage drive train configuration may be more suitable for the US site than the North Sea, depending on the turbine's failure rate. The US site benefited from increased availability due to more favourable weather windows, resulting in lower lost revenue for the two‐stage configuration despite high transport costs. The study found that the failure rate of 10 MW offshore wind turbines in the North Sea with a two‐stage gearbox can increase by as much as 30% compared to the 3 MW failure rates without increasing direct O&M costs. These findings are crucial for the offshore wind energy industry, particularly for OEMs, developers and maintenance providers, as they provide insights into the required reliability for next generation turbines to reduce O&M costs compared to existing 3 MW turbines.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-05","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141011733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jifeng Song, Xiaosheng Peng, Jiajiong Song, Zimin Yang, Bo Wang, Jianfeng Che
Wind power prediction for newly built wind farms is usually faced with the problem of no sufficient historical data. To efficiently extract the useful features from related wind farms, a novel transfer learning method based on temporal convolutional network (TCN)‐Bi‐long short‐term memory (LSTM) with dynamic loss weights is proposed. Firstly, a novel multi‐task TCN‐Bi‐LSTM model is designed to extract common features. The separate TCNs, and common Bi‐LSTM layers of the proposed model are designed to extract the temporal features from related wind farms. Secondly, in the pre‐training stage, to optimize the training process of the neural networks, a dynamic loss‐weighting strategy is proposed for multi‐task learning (MTL) to select the most related features, which increase the prediction accuracy by providing a suitable optimization object. Thirdly, the multi‐task TCN‐Bi‐LSTM model is re‐trained based on the samples from the target wind farm. Finally, a dataset of seven wind farms was employed to evaluate the efficiency of the proposed MTL structure and the dynamic loss‐weighting strategy. The result shows that the root mean squared error of the 12‐h short‐term prediction can be decreased by 4.19% compared with the traditional single‐task learning model, which verifies the validity of the proposed multi‐task transfer learning method.
{"title":"MTTLA‐DLW: Multi‐task TCN‐Bi‐LSTM transfer learning approach with dynamic loss weights based on feature correlations of the training samples for short‐term wind power prediction","authors":"Jifeng Song, Xiaosheng Peng, Jiajiong Song, Zimin Yang, Bo Wang, Jianfeng Che","doi":"10.1002/we.2909","DOIUrl":"https://doi.org/10.1002/we.2909","url":null,"abstract":"Wind power prediction for newly built wind farms is usually faced with the problem of no sufficient historical data. To efficiently extract the useful features from related wind farms, a novel transfer learning method based on temporal convolutional network (TCN)‐Bi‐long short‐term memory (LSTM) with dynamic loss weights is proposed. Firstly, a novel multi‐task TCN‐Bi‐LSTM model is designed to extract common features. The separate TCNs, and common Bi‐LSTM layers of the proposed model are designed to extract the temporal features from related wind farms. Secondly, in the pre‐training stage, to optimize the training process of the neural networks, a dynamic loss‐weighting strategy is proposed for multi‐task learning (MTL) to select the most related features, which increase the prediction accuracy by providing a suitable optimization object. Thirdly, the multi‐task TCN‐Bi‐LSTM model is re‐trained based on the samples from the target wind farm. Finally, a dataset of seven wind farms was employed to evaluate the efficiency of the proposed MTL structure and the dynamic loss‐weighting strategy. The result shows that the root mean squared error of the 12‐h short‐term prediction can be decreased by 4.19% compared with the traditional single‐task learning model, which verifies the validity of the proposed multi‐task transfer learning method.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-05-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141015537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Based on SCADA data, this study aims at fitting three performance curves (PCs), power curve, pitch angle curve, and rotor speed curve, to accurately describe the normal behaviour of a wind turbine (WT) for performance monitoring and identification of anomalous signals. The fitting accuracy can be undesirably affected by erroneous SCADA data. Hence, outliers generated from raw SCADA data should be removed to mitigate the prediction inaccuracy, so various outlier detection (OD) approaches are compared in terms of area under the curve (AUC) and mean average precision (mAP). Among them, a novel unsupervised SVM‐KNN model, integrated by support vector machine (SVM) and k nearest neighbour (KNN), is the optimum detector for PC refinements. Based on the refined data by the SVM‐KNN detector, several common nonparametric regressors have largely improved their prediction accuracies on pitch angle and rotor speed curves from roughly 86% and 90.6%, respectively, (raw data) to both 99% (refined data). Noticeably, under the SVM‐KNN refinement, the errors have been reduced by roughly five times and 10 times for pitch angle and rotor speed predictions, respectively. Ultimately, bootstrapped prediction interval is applied to conduct the uncertainty analysis of the optimal predictive regression model, reinforcing the performance monitoring and anomaly detection.
{"title":"Wind turbine condition monitoring based on three fitted performance curves","authors":"Shuo Zhang, Emma Robinson, Malabika Basu","doi":"10.1002/we.2859","DOIUrl":"https://doi.org/10.1002/we.2859","url":null,"abstract":"Based on SCADA data, this study aims at fitting three performance curves (PCs), power curve, pitch angle curve, and rotor speed curve, to accurately describe the normal behaviour of a wind turbine (WT) for performance monitoring and identification of anomalous signals. The fitting accuracy can be undesirably affected by erroneous SCADA data. Hence, outliers generated from raw SCADA data should be removed to mitigate the prediction inaccuracy, so various outlier detection (OD) approaches are compared in terms of area under the curve (AUC) and mean average precision (mAP). Among them, a novel unsupervised SVM‐KNN model, integrated by support vector machine (SVM) and k nearest neighbour (KNN), is the optimum detector for PC refinements. Based on the refined data by the SVM‐KNN detector, several common nonparametric regressors have largely improved their prediction accuracies on pitch angle and rotor speed curves from roughly 86% and 90.6%, respectively, (raw data) to both 99% (refined data). Noticeably, under the SVM‐KNN refinement, the errors have been reduced by roughly five times and 10 times for pitch angle and rotor speed predictions, respectively. Ultimately, bootstrapped prediction interval is applied to conduct the uncertainty analysis of the optimal predictive regression model, reinforcing the performance monitoring and anomaly detection.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140377718","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jingna Pan, C. Ferreira, Alexander van van Zuijlen
To investigate the effect of force distributions of each turbine component on the power performance of the Darrieus–Savonius combined vertical axis wind turbine (hybrid VAWT), the hybrid VAWT is modeled as idealized turbine under various force distributions. The goal of idealization is to simplify the intricate interactions between the Savonius and Darrieus components. The simulation actuator surfaces with uniform force distributions lead to a cost‐effective way to identify the optimal force distribution of each turbine component. The numerical model was validated against momentum theory. The results demonstrated that the numerical and theoretical results yield similar predictions in the low‐thrust cases but show differences in the high‐thrust cases. The maximum power coefficient of an idealized hybrid VAWT with given thrust coefficient is lower than that of a single actuator. This is a consequence of the nonoptimal loading on the actuator. The results indicate that an idealized hybrid VAWT does not show a significant power increase compared with an optimal single Darrieus rotor. Therefore, the presence of a Savonius rotor inside a Darrieus rotor leads to a lower power output in any circumstance. The hybrid configuration is primarily advantageous for the start‐up performance of the combined rotor, which is not explored in this study.
{"title":"Performance analysis of an idealized Darrieus–Savonius combined vertical axis wind turbine","authors":"Jingna Pan, C. Ferreira, Alexander van van Zuijlen","doi":"10.1002/we.2904","DOIUrl":"https://doi.org/10.1002/we.2904","url":null,"abstract":"To investigate the effect of force distributions of each turbine component on the power performance of the Darrieus–Savonius combined vertical axis wind turbine (hybrid VAWT), the hybrid VAWT is modeled as idealized turbine under various force distributions. The goal of idealization is to simplify the intricate interactions between the Savonius and Darrieus components. The simulation actuator surfaces with uniform force distributions lead to a cost‐effective way to identify the optimal force distribution of each turbine component. The numerical model was validated against momentum theory. The results demonstrated that the numerical and theoretical results yield similar predictions in the low‐thrust cases but show differences in the high‐thrust cases. The maximum power coefficient of an idealized hybrid VAWT with given thrust coefficient is lower than that of a single actuator. This is a consequence of the nonoptimal loading on the actuator. The results indicate that an idealized hybrid VAWT does not show a significant power increase compared with an optimal single Darrieus rotor. Therefore, the presence of a Savonius rotor inside a Darrieus rotor leads to a lower power output in any circumstance. The hybrid configuration is primarily advantageous for the start‐up performance of the combined rotor, which is not explored in this study.","PeriodicalId":23689,"journal":{"name":"Wind Energy","volume":null,"pages":null},"PeriodicalIF":4.1,"publicationDate":"2024-03-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140385348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：