首页 > 最新文献

Sustainable Energy Technologies and Assessments最新文献

英文 中文
Dust-induced transmission attenuation in solar photovoltaic modules: A simplified theoretical model 太阳能光伏组件中粉尘引起的传输衰减:一个简化的理论模型
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-24 DOI: 10.1016/j.seta.2025.104777
Weiping Zhao, Shuai Hu, Zhiguang Dong, Fang Zhao
Dust deposition on photovoltaic (PV) module surfaces reduces transmittance. This results in a decrease in incident solar radiation and, consequently, a reduction in power generation. Investigating transmittance attenuation caused by dust deposition is, therefore, crucial for accurate power forecasting and the development of optimized cleaning strategies. The main contribution of this paper is the proposal of several transmittance calculation models for soiled PV modules. These models clarify the relationships between transmittance and dust accumulation, particle size, and solar incidence angle. The models closely match experimental results, with relative errors of less than 7 % under identical conditions. This confirms their validity and enables reliable predictions. After validation, the models were used to examine how the dust accumulation amount, particle size, and solar incidence angle affect transmittance. The key results show that transmittance decreases as dust accumulation increases. Specifically, for 30 µm particles, increasing dust from 1 g/m2 to 20 g/m2 yields transmittance attenuation rates of 35.1 %, 44.2 %, 45.7 %, and 63.1 %, as predicted by models I, III, V, and VII, respectively. Additionally, the transmittance increases with increasing particle size, but at a diminishing rate. Increasing the solar incidence angle causes the transmittance to decrease gradually at first, then sharply after 60°. For a dust accumulation of 5 g/m2 and a particle size of 30 µm, the module transmittance decreases from 0.869 to 0.849 and then to 0 as the incidence angle moves from 0° to 45° and finally to 90°. This demonstrates the importance of module orientation for maximizing energy capture and sustainable performance.
灰尘沉积在光伏(PV)组件表面降低透光率。这导致入射太阳辐射的减少,从而减少了发电量。因此,研究粉尘沉积引起的透光率衰减对于准确预测功率和制定优化的清洁策略至关重要。本文的主要贡献是提出了几种污染光伏组件的透光率计算模型。这些模型阐明了透光率与尘埃堆积、颗粒大小和太阳入射角之间的关系。模型与实验结果吻合较好,在相同条件下的相对误差小于7%。这证实了它们的有效性,并使预测变得可靠。验证后,利用该模型考察了尘埃堆积量、粒径和太阳入射角对透光率的影响。关键结果表明,透光率随积尘量的增加而降低。具体来说,对于30µm颗粒,从1 g/m2增加到20 g/m2,透过率衰减率分别为35.1%、44.2%、45.7%和63.1%,与模型I、III、V和VII预测的一致。透光率随粒径的增大而增大,但呈递减趋势。增大太阳入射角时,透光率先逐渐减小,60°后急剧减小。当粉尘堆积量为5 g/m2,粒径为30µm时,随着入射角从0°→45°→90°,模块透过率从0.869→0.849→0。这证明了模块定向对于最大限度地获取能量和可持续性能的重要性。
{"title":"Dust-induced transmission attenuation in solar photovoltaic modules: A simplified theoretical model","authors":"Weiping Zhao,&nbsp;Shuai Hu,&nbsp;Zhiguang Dong,&nbsp;Fang Zhao","doi":"10.1016/j.seta.2025.104777","DOIUrl":"10.1016/j.seta.2025.104777","url":null,"abstract":"<div><div>Dust deposition on photovoltaic (PV) module surfaces reduces transmittance. This results in a decrease in incident solar radiation and, consequently, a reduction in power generation. Investigating transmittance attenuation caused by dust deposition is, therefore, crucial for accurate power forecasting and the development of optimized cleaning strategies. The main contribution of this paper is the proposal of several transmittance calculation models for soiled PV modules. These models clarify the relationships between transmittance and dust accumulation, particle size, and solar incidence angle. The models closely match experimental results, with relative errors of less than 7 % under identical conditions. This confirms their validity and enables reliable predictions. After validation, the models were used to examine how the dust accumulation amount, particle size, and solar incidence angle affect transmittance. The key results show that transmittance decreases as dust accumulation increases. Specifically, for 30 µm particles, increasing dust from 1 g/m<sup>2</sup> to 20 g/m<sup>2</sup> yields transmittance attenuation rates of 35.1 %, 44.2 %, 45.7 %, and 63.1 %, as predicted by models I, III, V, and VII, respectively. Additionally, the transmittance increases with increasing particle size, but at a diminishing rate. Increasing the solar incidence angle causes the transmittance to decrease gradually at first, then sharply after 60°. For a dust accumulation of 5 g/m<sup>2</sup> and a particle size of 30 µm, the module transmittance decreases from 0.869 to 0.849 and then to 0 as the incidence angle moves from 0° to 45° and finally to 90°. This demonstrates the importance of module orientation for maximizing energy capture and sustainable performance.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104777"},"PeriodicalIF":7.0,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Effect of water level variation in canal on energy Harvesting capacity of the Savonius turbine 渠内水位变化对水轮机蓄能能力的影响
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-24 DOI: 10.1016/j.seta.2025.104788
Jaykumar S. Patel, Vikram Rathod, Vimal Patel
Most studies on Savonius turbines have been conducted under constant water level conditions, assuming complete submergence of the rotor. However, in a real-world canal, the water level varies significantly throughout the year, which can influence turbine performance. To address this gap, this experimental investigation is conducted for the submerge ratio (SR) ranges from 0.076 to −0.199. The effect of water level variation is generated by lifting the turbine from the 67 mm depth of the water (0.076 SR) to the −17.5 cm height from the free surface of the water (−0.199 SR), while the flow depth of 88 cm and flow velocity of 0.37 m/s maintain constant throughout the study. According to the ANOVA study, SR has a significant impact on performance, and the rotor kept at 100 % submersion with an SR of 0.076 yields the optimal Cp of 0.1925. Additionally, the maximum Cp remains almost constant for all positive SR, but it profoundly affects Cp at higher TSR. The findings clearly indicate that the positive SR should be maintained above 0.028 to ensure a uniform velocity and to eliminate the effect of water level fluctuations across the rotor. The Cp of the rotor decreases with a rise in the negative SR, and for the −0.199 SR, the rotor stops rotating even under no load conditions.
大多数萨沃纽斯水轮机的研究都是在恒定水位条件下进行的,假设转子完全浸入水中。然而,在现实世界的运河中,水位全年变化很大,这可能会影响涡轮机的性能。为了解决这一差距,本实验研究的淹没比(SR)范围为0.076至- 0.199。水位变化效应是通过将水轮机从水深67 mm处(0.076 SR)提升到距离自由水面- 17.5 cm处(- 0.199 SR)产生的,在整个研究过程中,流深为88 cm,流速为0.37 m/s保持不变。根据方差分析研究,SR对性能有显著影响,转子保持在100%浸没时,SR为0.076,最佳Cp为0.1925。此外,在所有正SR下,最大Cp几乎保持不变,但在较高的TSR下,它会深刻影响Cp。研究结果清楚地表明,正SR应保持在0.028以上,以确保匀速,并消除转子上水位波动的影响。转子的Cp值随着负SR值的增大而减小,当SR值为- 0.199时,转子即使在空载情况下也会停止转动。
{"title":"Effect of water level variation in canal on energy Harvesting capacity of the Savonius turbine","authors":"Jaykumar S. Patel,&nbsp;Vikram Rathod,&nbsp;Vimal Patel","doi":"10.1016/j.seta.2025.104788","DOIUrl":"10.1016/j.seta.2025.104788","url":null,"abstract":"<div><div>Most studies on Savonius turbines have been conducted under constant water level conditions, assuming complete submergence of the rotor. However, in a real-world canal, the water level varies significantly throughout the year, which can influence turbine performance. To address this gap, this experimental investigation is conducted for the submerge ratio (SR) ranges from 0.076 to −0.199. The effect of water level variation is generated by lifting the turbine from the 67 mm depth of the water (0.076 SR) to the −17.5 cm height from the free surface of the water (−0.199 SR), while the flow depth of 88 cm and flow velocity of 0.37 m/s maintain constant throughout the study. According to the ANOVA study, SR has a significant impact on performance<u>,</u> and the rotor kept at 100 % submersion with an SR of 0.076 yields the optimal C<sub>p</sub> of 0.1925. Additionally, the maximum Cp remains almost constant for all positive SR, but it profoundly affects Cp at higher TSR. The findings clearly indicate that the positive SR should be maintained above 0.028 to ensure a uniform velocity and to eliminate the effect of water level fluctuations across the rotor. The Cp of the rotor decreases with a rise in the negative SR, and for the −0.199 SR, the rotor stops rotating even under no load conditions.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104788"},"PeriodicalIF":7.0,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A comprehensive evaluation of contemporary research on photosynthetic microalgal–microbial fuel cells (PM–MFCs) concerning wastewater and pollution remediation, bioelectricity generation, and bioproduct synthesis 综合评价光合微藻-微生物燃料电池(pm - mfc)在废水和污染修复、生物发电和生物产品合成方面的当代研究
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-24 DOI: 10.1016/j.seta.2025.104807
Chi-Wen Lin , Baala H. Anandapadmanaban , Shu-Hui Liu , Yu-Shen Cheng
Rising CO2 emissions and wastewater discharge threaten ecosystems and human health. Conventional physicochemical treatments are costly and may yield toxic byproducts, whereas biological methods offer safer, sustainable alternatives. Photosynthetic microalgal–microbial fuel cells (PM-MFCs) integrate electrogenic bacteria and microalgae to achieve simultaneous pollutant removal, oxygen generation, and electricity production. The resulting algal biomass also serves as a source of value-added bioproducts. Electrodes, exchange membranes, and microbial fuel cell setups are observed to play a major role in pollutant removal, with CO2 fixation rate, thus supporting the reuse of water, bioelectricity generation, and bioproduct production. Despite their multifunctional advantages, PM-MFCs encounter challenges in maintaining operational stability under fluctuating environmental conditions, particularly diurnal light–dark cycles and nutrient deficiencies. Sustained redox activity and power generation demand innovative system designs, such as employing microalgae in both anodic and cathodic chambers to enable adaptive responses to variable photoperiods. This strategy enables resilient, self-sustaining PM-MFCs capable of continuous power generation without external nutrients, while supporting scalable production of electricity and value-added bioproducts. The recovered biomass can further supplement nutrients for living microalgae, promoting carbon–neutral, sustainable development and advancing real-world applicability.
不断上升的二氧化碳排放和废水排放威胁着生态系统和人类健康。传统的物理化学处理成本高昂,可能产生有毒的副产品,而生物方法提供了更安全、可持续的替代方法。光合微藻-微生物燃料电池(PM-MFCs)将电生细菌和微藻结合在一起,同时实现污染物去除、氧气生成和发电。由此产生的藻类生物量也可作为增值生物产品的来源。电极、交换膜和微生物燃料电池装置在污染物去除和二氧化碳固定率方面发挥着重要作用,从而支持水的再利用、生物发电和生物产品生产。尽管具有多功能优势,但pm - mfc在波动的环境条件下保持运行稳定性方面面临挑战,特别是昼夜光暗循环和营养缺乏。持续的氧化还原活性和发电需要创新的系统设计,例如在阳极和阴极腔中使用微藻来实现对可变光周期的自适应响应。这一战略使弹性、自我维持的pm - mfc能够在没有外部营养的情况下持续发电,同时支持可扩展的电力生产和增值生物产品。回收的生物质可以进一步补充微藻的营养物质,促进碳中和、可持续发展,提高实际应用能力。
{"title":"A comprehensive evaluation of contemporary research on photosynthetic microalgal–microbial fuel cells (PM–MFCs) concerning wastewater and pollution remediation, bioelectricity generation, and bioproduct synthesis","authors":"Chi-Wen Lin ,&nbsp;Baala H. Anandapadmanaban ,&nbsp;Shu-Hui Liu ,&nbsp;Yu-Shen Cheng","doi":"10.1016/j.seta.2025.104807","DOIUrl":"10.1016/j.seta.2025.104807","url":null,"abstract":"<div><div>Rising CO<sub>2</sub> emissions and wastewater discharge threaten ecosystems and human health. Conventional physicochemical treatments are costly and may yield toxic byproducts, whereas biological methods offer safer, sustainable alternatives. Photosynthetic microalgal–microbial fuel cells (PM-MFCs) integrate electrogenic bacteria and microalgae to achieve simultaneous pollutant removal, oxygen generation, and electricity production. The resulting algal biomass also serves as a source of value-added bioproducts. Electrodes, exchange membranes, and microbial fuel cell setups are observed to play a major role in pollutant removal, with CO<sub>2</sub> fixation rate, thus supporting the reuse of water, bioelectricity generation, and bioproduct production. Despite their multifunctional advantages, PM-MFCs encounter challenges in maintaining operational stability under fluctuating environmental conditions, particularly diurnal light–dark cycles and nutrient deficiencies. Sustained redox activity and power generation demand innovative system designs, such as employing microalgae in both anodic and cathodic chambers to enable adaptive responses to variable photoperiods. This strategy enables resilient, self-sustaining PM-MFCs capable of continuous power generation without external nutrients, while supporting scalable production of electricity and value-added bioproducts. The recovered biomass can further supplement nutrients for living microalgae, promoting carbon–neutral, sustainable development and advancing real-world applicability.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104807"},"PeriodicalIF":7.0,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Towards zero-carbon power supply: development of a multi-energy coupled offshore green energy production island 迈向零碳供电:多能耦合的海上绿色能源生产岛建设
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-24 DOI: 10.1016/j.seta.2025.104791
Kehan Su , Lijie Wang , Dalin Jiang , Junguang Lin , Chao Yang , Fan Wu , Dazheng Liu , Fan Wu , Chenghang Zheng , Xiang Gao
Offshore islands, with their abundant renewable energy resources and geographic advantages, present significant potential for the development of low-carbon, multi-energy systems. This study develops an innovative framework for the configuration optimization and operational analysis of multi-energy coupled offshore green energy production islands, aiming to achieve zero-carbon energy supply. A multi-objective model is developed to optimize system configuration, incorporating techno-economic analysis and environmental performance and efficiency evaluation. Key performance metrics including levelized cost of energy (LCOE), energy storage efficiency and curtailment ratio, are employed to evaluate system forms and configurations. The proposed optimized system integrates renewable energy sources including photovoltaic (PV) and wind power, with hydrogen production, ammonia storage and methanol synthesis as multi-scale energy storage and transfer pathways. The system fosters collaborative operation between offshore islands and mainland energy networks, enhancing energy efficiency and flexibility. Case studies demonstrate that coupling renewable energy with green fuel production provides a sustainable pathway for offshore islands to achieve zero-carbon energy supply with a LCOE of 0.128 USD/kWh, a load satisfaction rate exceeding 99.8% and a curtailment ratio below 6%. This research offers valuable insights into the design and operation of zero-carbon island energy systems, advancing the transition to a sustainable, low-carbon energy future.
近海岛屿拥有丰富的可再生能源资源和地理优势,具有发展低碳、多能源系统的巨大潜力。本研究以实现零碳能源供应为目标,构建了多能耦合海上绿色能源生产岛配置优化与运行分析的创新框架。结合技术经济分析、环境绩效和效率评价,建立了优化系统配置的多目标模型。主要性能指标包括平准化能源成本(LCOE)、储能效率和弃风比,用于评估系统的形式和配置。优化后的系统集成了包括光伏和风能在内的可再生能源,以制氢、储氨和甲醇合成为多尺度的储能和转移途径。该系统促进了近海岛屿和大陆能源网络之间的合作运作,提高了能源效率和灵活性。案例研究表明,将可再生能源与绿色燃料生产相结合,为近海岛屿实现LCOE为0.128美元/千瓦时、负荷满意率超过99.8%、弃风率低于6%的零碳能源供应提供了一条可持续的途径。这项研究为零碳岛能源系统的设计和运行提供了宝贵的见解,推动了向可持续低碳能源未来的过渡。
{"title":"Towards zero-carbon power supply: development of a multi-energy coupled offshore green energy production island","authors":"Kehan Su ,&nbsp;Lijie Wang ,&nbsp;Dalin Jiang ,&nbsp;Junguang Lin ,&nbsp;Chao Yang ,&nbsp;Fan Wu ,&nbsp;Dazheng Liu ,&nbsp;Fan Wu ,&nbsp;Chenghang Zheng ,&nbsp;Xiang Gao","doi":"10.1016/j.seta.2025.104791","DOIUrl":"10.1016/j.seta.2025.104791","url":null,"abstract":"<div><div>Offshore islands, with their abundant renewable energy resources and geographic advantages, present significant potential for the development of low-carbon, multi-energy systems. This study develops an innovative framework for the configuration optimization and operational analysis of multi-energy coupled offshore green energy production islands, aiming to achieve zero-carbon energy supply. A multi-objective model is developed to optimize system configuration, incorporating techno-economic analysis and environmental performance and efficiency evaluation. Key performance metrics including levelized cost of energy (LCOE), energy storage efficiency and curtailment ratio, are employed to evaluate system forms and configurations. The proposed optimized system integrates renewable energy sources including photovoltaic (PV) and wind power, with hydrogen production, ammonia storage and methanol synthesis as multi-scale energy storage and transfer pathways. The system fosters collaborative operation between offshore islands and mainland energy networks, enhancing energy efficiency and flexibility. Case studies demonstrate that coupling renewable energy with green fuel production provides a sustainable pathway for offshore islands to achieve zero-carbon energy supply with a LCOE of 0.128 USD/kWh, a load satisfaction rate exceeding 99.8% and a curtailment ratio below 6%. This research offers valuable insights into the design and operation of zero-carbon island energy systems, advancing the transition to a sustainable, low-carbon energy future.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104791"},"PeriodicalIF":7.0,"publicationDate":"2025-12-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Efficiency optimization model for coal-fired power plants with CCS in emissions trading markets 碳捕集与封存燃煤电厂排放交易市场效率优化模型
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-23 DOI: 10.1016/j.seta.2025.104803
Jingjie Huang , Zhiyao Zhang , Liang Yuan , Hongming Yang , Zhaoyang Dong , Renjun Zhou , Yan Xu
To address the challenge of minimizing emission allowance purchasing costs and carbon capture system (CCS) energy consumption in coal-fired power plants (CFPPs) participating in emission trading schemes (ETS), this study develops a novel stochastic optimization framework for dynamic carbon capture efficiency (CCE) adjustment. First, a deterministic optimization model is established to quantify the price-sensitive range (PSR) of emission allowance prices (EAP), which is required to incentivize active CFPP participation in ETS while balancing CCS operational costs. Due to the inherent EAP uncertainty in real markets, a superquantile-based risk characterization of emission allowance purchasing costs is developed using Monte Carlo discretization. This leads to the creation of confidence-level-dependent operational strategies that maximize plant profitability under fluctuating electricity prices, net output requirements, and carbon market volatility. Simulation analyses demonstrate that the proposed approach provides conservative, adaptive operating modes, which reduce costs compared to deterministic methods while enhancing capture efficiency flexibility and delivering economically viable decarbonization pathways for CCS-equipped power infrastructure.
为解决参与碳排放交易机制(ETS)的燃煤电厂(CFPPs)碳捕集系统(CCS)能耗最小化的挑战,本研究开发了一种新的动态碳捕集效率(CCE)随机优化框架。首先,建立了一个确定性优化模型,量化排放限额价格(EAP)的价格敏感范围(PSR),以激励CFPP积极参与ETS,同时平衡CCS的运营成本。考虑到实际市场中排放配额购买成本固有的不确定性,采用蒙特卡罗离散方法建立了基于超分位数的排放配额购买成本风险表征。这就产生了依赖于信心水平的运营策略,在电价波动、净输出要求和碳市场波动的情况下,使工厂的盈利能力最大化。仿真分析表明,与确定性方法相比,该方法提供了保守的、自适应的运行模式,降低了成本,同时提高了捕集效率的灵活性,并为配备ccs的电力基础设施提供了经济上可行的脱碳途径。
{"title":"Efficiency optimization model for coal-fired power plants with CCS in emissions trading markets","authors":"Jingjie Huang ,&nbsp;Zhiyao Zhang ,&nbsp;Liang Yuan ,&nbsp;Hongming Yang ,&nbsp;Zhaoyang Dong ,&nbsp;Renjun Zhou ,&nbsp;Yan Xu","doi":"10.1016/j.seta.2025.104803","DOIUrl":"10.1016/j.seta.2025.104803","url":null,"abstract":"<div><div>To address the challenge of minimizing emission allowance purchasing costs and carbon capture system (CCS) energy consumption in coal-fired power plants (CFPPs) participating in emission trading schemes (ETS), this study develops a novel stochastic optimization framework for dynamic carbon capture efficiency (CCE) adjustment. First, a deterministic optimization model is established to quantify the price-sensitive range (PSR) of emission allowance prices (EAP), which is required to incentivize active CFPP participation in ETS while balancing CCS operational costs. Due to the inherent EAP uncertainty in real markets, a superquantile-based risk characterization of emission allowance purchasing costs is developed using Monte Carlo discretization. This leads to the creation of confidence-level-dependent operational strategies that maximize plant profitability under fluctuating electricity prices, net output requirements, and carbon market volatility. Simulation analyses demonstrate that the proposed approach provides conservative, adaptive operating modes, which reduce costs compared to deterministic methods while enhancing capture efficiency flexibility and delivering economically viable decarbonization pathways for CCS-equipped power infrastructure.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104803"},"PeriodicalIF":7.0,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841235","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
CNN-BiLSTM-Autoencoder hybrid for prognostics of gearbox Over-Temperature faults in offshore wind turbines cnn - bilstm -自编码器混合预测海上风力发电机齿轮箱过温故障
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-23 DOI: 10.1016/j.seta.2025.104806
Renshen Tan , Zhihao Wang , Yidian Chen , Xiaowei Zhou , Peiyi Zhu , Khalil AL-Bukhaiti , Anping Wan
The escalating adoption of offshore wind energy underscores the need for robust fault detection systems, particularly for gearbox failures that account for 30–40 % of turbine downtime, incurring significant economic losses. Traditional threshold-based methods for monitoring gearbox oil temperature suffer from delayed warnings and limited generalization, prompting the development of a novel fault early warning method based on the CNN-BiLSTM-AE model (CBL-AE-FEW). This approach integrates convolutional neural networks (CNN) for spatial feature extraction, bidirectional long short-term memory (BiLSTM) networks for temporal dependency modeling, and autoencoders (AE) for adaptive reconstruction error analysis. Utilizing SCADA data from six offshore wind turbines, feature importance is assessed via Random Forest and Pearson correlation coefficient, selecting key predictors such as hydraulic oil temperature. The method dynamically captures temperature trends, triggering early warnings when reconstruction errors escalate. Validation demonstrates superior performance, with a mean squared error of 0.06513, root mean squared error of 0.25564, and an average lead time of 930 min across turbines, surpassing traditional models like XGBoost and SVM. This study offers a reliable, generalizable solution for predictive maintenance, enhancing the operational stability and economic viability of offshore wind farms.
海上风能的不断发展凸显了对强大的故障检测系统的需求,特别是变速箱故障,变速箱故障占涡轮机停机时间的30 - 40%,会造成重大的经济损失。传统的基于阈值的齿轮箱油温监测方法存在预警滞后和泛化有限的问题,提出了一种基于CNN-BiLSTM-AE模型(CBL-AE-FEW)的齿轮箱油温故障预警方法。该方法集成了卷积神经网络(CNN)用于空间特征提取,双向长短期记忆(BiLSTM)网络用于时间依赖性建模,以及自适应重构误差分析的自编码器(AE)。利用来自六个海上风力涡轮机的SCADA数据,通过随机森林和Pearson相关系数评估特征重要性,选择关键预测因子,如液压油温度。该方法动态捕获温度趋势,在重建错误升级时触发早期预警。验证结果表明,该模型性能优越,均方误差为0.06513,均方根误差为0.25564,各涡轮机平均提前期为930 min,优于传统模型如XGBoost和SVM。该研究为预测性维护提供了一个可靠的、通用的解决方案,提高了海上风电场的运行稳定性和经济可行性。
{"title":"CNN-BiLSTM-Autoencoder hybrid for prognostics of gearbox Over-Temperature faults in offshore wind turbines","authors":"Renshen Tan ,&nbsp;Zhihao Wang ,&nbsp;Yidian Chen ,&nbsp;Xiaowei Zhou ,&nbsp;Peiyi Zhu ,&nbsp;Khalil AL-Bukhaiti ,&nbsp;Anping Wan","doi":"10.1016/j.seta.2025.104806","DOIUrl":"10.1016/j.seta.2025.104806","url":null,"abstract":"<div><div>The escalating adoption of offshore wind energy underscores the need for robust fault detection systems, particularly for gearbox failures that account for 30–40 % of turbine downtime, incurring significant economic losses. Traditional threshold-based methods for monitoring gearbox oil temperature suffer from delayed warnings and limited generalization, prompting the development of a novel fault early warning method based on the CNN-BiLSTM-AE model (CBL-AE-FEW). This approach integrates convolutional neural networks (CNN) for spatial feature extraction, bidirectional long short-term memory (BiLSTM) networks for temporal dependency modeling, and autoencoders (AE) for adaptive reconstruction error analysis. Utilizing SCADA data from six offshore wind turbines, feature importance is assessed via Random Forest and Pearson correlation coefficient, selecting key predictors such as hydraulic oil temperature. The method dynamically captures temperature trends, triggering early warnings when reconstruction errors escalate. Validation demonstrates superior performance, with a mean squared error of 0.06513, root mean squared error of 0.25564, and an average lead time of 930 min across turbines, surpassing traditional models like XGBoost and SVM. This study offers a reliable, generalizable solution for predictive maintenance, enhancing the operational stability and economic viability of offshore wind farms.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104806"},"PeriodicalIF":7.0,"publicationDate":"2025-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841232","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Optimization design of low-head reversible pumped storage units in pump mode based on linear circulation distribution 基于线性循环分布的泵式低水头可逆抽水蓄能机组优化设计
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-22 DOI: 10.1016/j.seta.2025.104795
Yifan Zhang , Kan Kan , Yanxin Hu , Zhaodan Fei , Huixiang Chen , Changliang Ye , Jinbo Chen , Jichang Chen , Weidong Liu
Improving hydraulic efficiency of low-head pumped hydroelectric energy storage systems enables energy savings, shortens charging times, and enhanced round-trip efficiency. This study employs a linear distribution strategy for circulation at the impeller outlet and guide vane inlet of a low-head reversible pumped storage unit in pump mode. To determine the optimal design based on numerical simulations, a combined approach of parametric design and orthogonal experiments was used. Linearizing circulation distribution significantly improved hydraulic efficiency of the low-head reversible pumped storage unit under both low-flow and rated conditions in pump mode, with rated efficiency increasing by 1.03% to 85.48%. The circumferential uniformity of absolute velocity at the impeller outlet and guide vane inlet was improved, resulting in a more uniform flow field. High-pressure zones at impeller leading edges decreased, suction-side pressure became more uniform, and flow separation was restrained. Vortex intensity and extent at trailing edges diminished, lowering turbulent entropy production. Flow at the guide vane inlet and inter-vane channels became more consistent. These coupled improvements reveal the intrinsic mechanism by which the optimized circulation enhances hydraulic performance. This study provides theoretical guidance for efficiency enhancement of low-head reversible pumped storage units in pump mode.
提高低水头抽水蓄能系统的水力效率,可以节约能源,缩短充电时间,提高往返效率。本文对低扬程可逆抽水蓄能机组在泵态下叶轮出口和导叶进口的循环采用线性分布策略。为了在数值模拟的基础上确定最优设计,采用了参数化设计和正交试验相结合的方法。线性化循环分布显著提高了低水头可逆式抽水蓄能机组在低流量和额定工况下的水力效率,额定效率提高了1.03%,达到85.48%。叶轮出口和导叶进口绝对速度的周向均匀性得到改善,流场更加均匀。叶轮前缘高压区减小,吸侧压力更加均匀,流动分离得到抑制。尾缘涡强度和范围减小,降低了湍流熵产。导叶入口和叶片间通道的流动变得更加一致。这些耦合的改进揭示了优化循环提高水力性能的内在机制。该研究为提高低水头可逆抽水蓄能机组在抽水模式下的效率提供了理论指导。
{"title":"Optimization design of low-head reversible pumped storage units in pump mode based on linear circulation distribution","authors":"Yifan Zhang ,&nbsp;Kan Kan ,&nbsp;Yanxin Hu ,&nbsp;Zhaodan Fei ,&nbsp;Huixiang Chen ,&nbsp;Changliang Ye ,&nbsp;Jinbo Chen ,&nbsp;Jichang Chen ,&nbsp;Weidong Liu","doi":"10.1016/j.seta.2025.104795","DOIUrl":"10.1016/j.seta.2025.104795","url":null,"abstract":"<div><div>Improving hydraulic efficiency of low-head pumped hydroelectric energy storage systems enables energy savings, shortens charging times, and enhanced round-trip efficiency. This study employs a linear distribution strategy for circulation at the impeller outlet and guide vane inlet of a low-head reversible pumped storage unit in pump mode. To determine the optimal design based on numerical simulations, a combined approach of parametric design and orthogonal experiments was used. Linearizing circulation distribution significantly improved hydraulic efficiency of the low-head reversible pumped storage unit under both low-flow and rated conditions in pump mode, with rated efficiency increasing by 1.03% to 85.48%. The circumferential uniformity of absolute velocity at the impeller outlet and guide vane inlet was improved, resulting in a more uniform flow field. High-pressure zones at impeller leading edges decreased, suction-side pressure became more uniform, and flow separation was restrained. Vortex intensity and extent at trailing edges diminished, lowering turbulent entropy production. Flow at the guide vane inlet and inter-vane channels became more consistent. These coupled improvements reveal the intrinsic mechanism by which the optimized circulation enhances hydraulic performance. This study provides theoretical guidance for efficiency enhancement of low-head reversible pumped storage units in pump mode.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104795"},"PeriodicalIF":7.0,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841233","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Dual frequency-up conversion for enhanced low-frequency swing energy harvesting in a hybrid piezoelectric-electromagnetic harvester 压电-电磁混合收割机中增强低频摆振能量收集的双频上升转换
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-22 DOI: 10.1016/j.seta.2025.104789
Zhenheng Li, Yifan Li, Guanghong Han, Juan Zhu, Ziming Zhou, Lipeng He
Although ambient mechanical energy is ubiquitously accessible, its practical utilization for powering electronic devices is constrained due to the low-frequency characteristics and low displacement amplitude of ambient mechanical energy. This work proposed dual frequency-up conversion (D-FUC) for enhanced low-frequency swing energy harvesting in a hybrid piezoelectric-electromagnetic harvester (HPEH). The D-FUC is composed of FUC1 and FUC2. FUC1 implemented with a swing structure, an inextensible rope, and a static pulley, and FUC2, enabled by a gear system. The D-FUC can convert low-frequency swing motion into high-frequency oscillations while addressing the low displacement amplitude of mechanical motion, demonstrating advantages in harvesting ambient mechanical energy. Furthermore, a dual-spiral spring configuration is implemented to enhance operational continuity in the energy harvesting system. The output voltage of the prototype at an 18° swing angle is comparable to that at a 90° swing angle. Additionally, benefiting from the non-contact excitation enabled by magnetic coupling, the risk of damage to the piezoelectric component is significantly reduced. The swing angle enhancement ratio (the ratio of output to input swing angles) reaches 9.72–10.64. Validation results show that the prototype, with optimized structural parameters, delivers an RMS output power of 3.52 mW. The D-FUC provides a novel frequency up-conversion mechanism.
虽然环境机械能无处不在,但由于环境机械能的低频特性和低位移幅值,限制了其在电子设备供电中的实际应用。本文提出了一种双频上转换(D-FUC)技术,用于增强混合压电-电磁收割机(HPEH)的低频摆动能量收集。D-FUC由FUC1和FUC2组成。FUC1采用摆动结构、不可伸缩绳索和静态滑轮,FUC2采用齿轮系统。D-FUC可以将低频摆动运动转换为高频振荡,同时解决机械运动的低位移幅值问题,在收集环境机械能方面具有优势。此外,采用了双螺旋弹簧结构,以提高能量收集系统的操作连续性。样机在18°摆角时的输出电压与90°摆角时的输出电压相当。此外,得益于磁耦合的非接触激励,压电元件的损坏风险大大降低。摆角增强比(输出与输入摆角之比)达到9.72 ~ 10.64。验证结果表明,在优化结构参数的情况下,样机的RMS输出功率为3.52 mW。D-FUC提供了一种新颖的频率上转换机制。
{"title":"Dual frequency-up conversion for enhanced low-frequency swing energy harvesting in a hybrid piezoelectric-electromagnetic harvester","authors":"Zhenheng Li,&nbsp;Yifan Li,&nbsp;Guanghong Han,&nbsp;Juan Zhu,&nbsp;Ziming Zhou,&nbsp;Lipeng He","doi":"10.1016/j.seta.2025.104789","DOIUrl":"10.1016/j.seta.2025.104789","url":null,"abstract":"<div><div>Although ambient mechanical energy is ubiquitously accessible, its practical utilization for powering electronic devices is constrained due to the low-frequency characteristics and low displacement amplitude of ambient mechanical energy. This work proposed dual frequency-up conversion (D-FUC) for enhanced low-frequency swing energy harvesting in a hybrid piezoelectric-electromagnetic harvester (HPEH). The D-FUC is composed of FUC<sub>1</sub> and FUC<sub>2</sub>. FUC<sub>1</sub> implemented with a swing structure, an inextensible rope, and a static pulley, and FUC<sub>2</sub>, enabled by a gear system. The D-FUC can convert low-frequency swing motion into high-frequency oscillations while addressing the low displacement amplitude of mechanical motion, demonstrating advantages in harvesting ambient mechanical energy. Furthermore, a dual-spiral spring configuration is implemented to enhance operational continuity in the energy harvesting system. The output voltage of the prototype at an 18° swing angle is comparable to that at a 90° swing angle. Additionally, benefiting from the non-contact excitation enabled by magnetic coupling, the risk of damage to the piezoelectric component is significantly reduced. The swing angle enhancement ratio (the ratio of output to input swing angles) reaches 9.72–10.64. Validation results show that the prototype, with optimized structural parameters, delivers an RMS output power of 3.52 mW. The D-FUC provides a novel frequency up-conversion mechanism.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104789"},"PeriodicalIF":7.0,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
AI technologies towards achieving net-zero energy building: Potential framework, implementation factors, challenges and future directions 实现净零能耗建筑的人工智能技术:潜在框架、实施因素、挑战和未来方向
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-22 DOI: 10.1016/j.seta.2025.104804
M.A. Hannan , S. Ansari , S.R. Arsad , A.Z. Arsad , Pin Jern Ker , R.A. Begum , G. Jang
To achieve Net-Zero Energy Buildings (NZEBs), intelligent, flexible systems that can handle intricate energy dynamics in real time are needed. Artificial Intelligence (AI) is crucial for accomplishing NZEB objectives because it optimizes energy use, forecasts demand and increases control accuracy. This review synthesizes findings from 350 peer-reviewed studies published between 2016 and 2025 to examine the role of AI in building energy consumption, HVAC control, and smart building operation. A structured selection and thematic analysis approach is employed to classify AI applications, identify dominant research directions, and evaluate implementation readiness. The review highlights that data-driven models, hybrid AI frameworks, and reinforcement learning-based controllers consistently outperform conventional rule-based strategies in terms of flexibility, responsiveness, and automation capability. The review also identifies key implementation factors for AI in NZEBs, including interpretability, hybrid architectures, computational effectiveness, system integration, model selection, data quality and preprocessing, and interpretation. The latest developments in AI-based NZEB research are also covered, including digital twins, explainable AI, federated and transfer learning, AI for retrofit and design optimization, and interpretable models. Furthermore, important issues and challenges are listed to denote areas that lack research on AI-enabled NZEB systems. Lastly, this review offers useful suggestions, prospects for the future, and strategic directions to help researchers create strong, context-aware AI solutions for the intelligent management and sustainable operation of next-generation energy-efficient buildings.
为了实现净零能耗建筑(nzeb),需要能够实时处理复杂能源动态的智能、灵活的系统。人工智能(AI)对于实现NZEB目标至关重要,因为它可以优化能源使用,预测需求并提高控制精度。本综述综合了2016年至2025年间发表的350项同行评审研究的结果,研究了人工智能在建筑能耗、暖通空调控制和智能建筑运营中的作用。采用结构化选择和专题分析方法对人工智能应用进行分类,确定主导研究方向,并评估实施准备情况。该综述强调,数据驱动模型、混合人工智能框架和基于强化学习的控制器在灵活性、响应能力和自动化能力方面始终优于传统的基于规则的策略。该审查还确定了nzeb中人工智能的关键实施因素,包括可解释性、混合架构、计算效率、系统集成、模型选择、数据质量和预处理以及解释。本文还介绍了基于人工智能的NZEB研究的最新进展,包括数字双胞胎、可解释的人工智能、联合和迁移学习、用于改造和设计优化的人工智能以及可解释的模型。此外,列出了重要的问题和挑战,以指出缺乏对人工智能支持的NZEB系统研究的领域。最后,本文提供了有用的建议、对未来的展望和战略方向,以帮助研究人员为下一代节能建筑的智能管理和可持续运营创造强大的、情境感知的人工智能解决方案。
{"title":"AI technologies towards achieving net-zero energy building: Potential framework, implementation factors, challenges and future directions","authors":"M.A. Hannan ,&nbsp;S. Ansari ,&nbsp;S.R. Arsad ,&nbsp;A.Z. Arsad ,&nbsp;Pin Jern Ker ,&nbsp;R.A. Begum ,&nbsp;G. Jang","doi":"10.1016/j.seta.2025.104804","DOIUrl":"10.1016/j.seta.2025.104804","url":null,"abstract":"<div><div>To achieve Net-Zero Energy Buildings (NZEBs), intelligent, flexible systems that can handle intricate energy dynamics in real time are needed. Artificial Intelligence (AI) is crucial for accomplishing NZEB objectives because it optimizes energy use, forecasts demand and increases control accuracy. This review synthesizes findings from 350 peer-reviewed studies published between 2016 and 2025 to examine the role of AI in building energy consumption, HVAC control, and smart building operation. A structured selection and thematic analysis approach is employed to classify AI applications, identify dominant research directions, and evaluate implementation readiness. The review highlights that data-driven models, hybrid AI frameworks, and reinforcement learning-based controllers consistently outperform conventional rule-based strategies in terms of flexibility, responsiveness, and automation capability. The review also identifies key implementation factors for AI in NZEBs, including interpretability, hybrid architectures, computational effectiveness, system integration, model selection, data quality and preprocessing, and interpretation. The latest developments in AI-based NZEB research are also covered, including digital twins, explainable AI, federated and transfer learning, AI for retrofit and design optimization, and interpretable models. Furthermore, important issues and challenges are listed to denote areas that lack research on AI-enabled NZEB systems. Lastly, this review offers useful suggestions, prospects for the future, and strategic directions to help researchers create strong, context-aware AI solutions for the intelligent management and sustainable operation of next-generation energy-efficient buildings.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104804"},"PeriodicalIF":7.0,"publicationDate":"2025-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
An explainable (interpretable) stacking ensemble machine learning model for real-time and short-term significant sea wave height prediction 用于实时和短期显著海浪高度预测的可解释(可解释)叠加集成机器学习模型
IF 7 2区 工程技术 Q1 ENERGY & FUELS Pub Date : 2025-12-21 DOI: 10.1016/j.seta.2025.104794
Mie Wang , Feixiang Ying , Jianing Yang , Dongming Zhu
Accurate and interpretable wave height prediction is essential for advancing wave energy and marine renewable energy. This study proposes an explainable stacking ensemble machine learning framework for real-time and short-term significant wave height prediction. The framework constructs a diverse pool of nine candidate base learners from different algorithm families. Based on performance and correlation analysis, a representative subset is selected and aggregated using a linear regression meta-learner to enhance robustness. The framework is validated using 2016 observational data from NDBC buoys 41002 (North Atlantic) and 42055 (Gulf of Mexico). For real-time forecasting, the stacking ensemble consistently outperforms baseline models at both buoy sites, achieving the highest R2 (0.9148 / 0.9391) and the lowest RMSE, MAE, and MSE values. It also maintains superior accuracy in short-term multi-step forecasting (1 h, 3 h, 6 h) compared to LSTM and TCN-LSTM, demonstrating strong robustness and generalization across varying time horizons. To ensure model transparency and practical trustworthiness, Shapley Additive Explanations (SHAP) are employed, enabling comprehensive interpretation of feature contributions and the relative influence of each base learner. By integrating SHAP with stacking ensemble learning, this study improves both the accuracy and interpretability of wave height prediction, supporting safer and more efficient use of marine resources.
准确和可解释的波高预测对于推进波浪能和海洋可再生能源至关重要。本研究提出了一种可解释的叠加集成机器学习框架,用于实时和短期有效波高预测。该框架构建了一个由来自不同算法族的9个候选基学习者组成的多样化库。基于性能和相关性分析,选择一个具有代表性的子集,并使用线性回归元学习器进行聚合,以增强鲁棒性。利用2016年NDBC浮标41002(北大西洋)和42055(墨西哥湾)的观测数据对该框架进行了验证。在实时预报方面,两个浮标点的叠加集合均优于基线模型,R2最高(0.9148 / 0.9391),RMSE、MAE和MSE值最低。与LSTM和TCN-LSTM相比,它在短期多步预测(1小时、3小时、6小时)中也保持了更高的准确性,在不同的时间范围内表现出很强的稳健性和泛化性。为了保证模型的透明度和实际可信度,采用Shapley加性解释(SHAP),可以全面解释特征贡献和每个基础学习器的相对影响。本研究通过将SHAP与叠加集成学习相结合,提高了波高预测的精度和可解释性,支持更安全、更有效地利用海洋资源。
{"title":"An explainable (interpretable) stacking ensemble machine learning model for real-time and short-term significant sea wave height prediction","authors":"Mie Wang ,&nbsp;Feixiang Ying ,&nbsp;Jianing Yang ,&nbsp;Dongming Zhu","doi":"10.1016/j.seta.2025.104794","DOIUrl":"10.1016/j.seta.2025.104794","url":null,"abstract":"<div><div>Accurate and interpretable wave height prediction is essential for advancing wave energy and marine renewable energy. This study proposes an explainable stacking ensemble machine learning framework for real-time and short-term significant wave height prediction. The framework constructs a diverse pool of nine candidate base learners from different algorithm families. Based on performance and correlation analysis, a representative subset is selected and aggregated using a linear regression meta-learner to enhance robustness. The framework is validated using 2016 observational data from NDBC buoys 41002 (North Atlantic) and 42055 (Gulf of Mexico). For real-time forecasting, the stacking ensemble consistently outperforms baseline models at both buoy sites, achieving the highest R<sup>2</sup> (0.9148 / 0.9391) and the lowest RMSE, MAE, and MSE values. It also maintains superior accuracy in short-term multi-step forecasting (1 h, 3 h, 6 h) compared to LSTM and TCN-LSTM, demonstrating strong robustness and generalization across varying time horizons. To ensure model transparency and practical trustworthiness, Shapley Additive Explanations (SHAP) are employed, enabling comprehensive interpretation of feature contributions and the relative influence of each base learner. By integrating SHAP with stacking ensemble learning, this study improves both the accuracy and interpretability of wave height prediction, supporting safer and more efficient use of marine resources.</div></div>","PeriodicalId":56019,"journal":{"name":"Sustainable Energy Technologies and Assessments","volume":"85 ","pages":"Article 104794"},"PeriodicalIF":7.0,"publicationDate":"2025-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145841231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Sustainable Energy Technologies and Assessments
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1