首页 > 最新文献

Energy and AI最新文献

英文 中文
Modelling Anti-Corrosion Coating Performance of Metallic Bipolar Plates for PEM Fuel Cells: A Machine Learning Approach PEM 燃料电池金属双极板防腐蚀涂层性能建模:机器学习方法
IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-26 DOI: 10.1016/j.egyai.2024.100391
Pramoth Varsan Madhavan , Samaneh Shahgaldi , Xianguo Li

Proton exchange membrane (PEM) fuel cells have significant potential for clean power generation, yet challenges remain in enhancing their performance, durability, and cost-effectiveness, particularly concerning metallic bipolar plates, which are pivotal for lightweight compact fuel cell stacks. Protective coatings are commonly employed to combat metallic bipolar plate corrosion and enhance water management within stacks. Conventional methods for predicting coating performance in terms of corrosion resistance involve complex physical-electrochemical modelling and extensive experimentation, with significant time and cost. In this study machine learning techniques are employed to model metallic bipolar plate coating performance, diamond-like-carbon coatings of varying thicknesses deposited on SS316L are considered, and coating performance is evaluated using potentiodynamic polarization and electrochemical impedance spectroscopy. The obtained experimental data is split into two datasets for machine learning modelling: one predicting corrosion current density and another predicting impedance parameters. Machine learning models, including extreme gradient boosting (XGB) and artificial neural networks (ANN), are developed, and optimized to predict coating performance attributes. Data preprocessing and hyperparameter tuning are carried out to enhance model accuracy. Results show that ANN outperforms XGB in predicting corrosion current density, achieving an R2 > 0.98, and accurately predicting impedance parameters with an R2 > 0.99, indicating that the models developed are very promising for accurate prediction of the corrosion performance of coated metallic bipolar plates for PEM fuel cells.

质子交换膜(PEM)燃料电池在清洁发电方面具有巨大潜力,但在提高其性能、耐用性和成本效益方面仍面临挑战,尤其是对轻质紧凑型燃料电池堆至关重要的金属双极板。通常采用保护涂层来防止金属双极板腐蚀并加强堆内的水管理。预测涂层耐腐蚀性能的传统方法涉及复杂的物理-电化学建模和大量实验,耗费大量时间和成本。本研究采用机器学习技术建立金属双极板涂层性能模型,考虑在 SS316L 上沉积不同厚度的类金刚石碳涂层,并使用电位极化和电化学阻抗光谱评估涂层性能。获得的实验数据被分成两个数据集用于机器学习建模:一个数据集预测腐蚀电流密度,另一个数据集预测阻抗参数。开发并优化了机器学习模型,包括极端梯度提升(XGB)和人工神经网络(ANN),以预测涂层性能属性。通过数据预处理和超参数调整来提高模型的准确性。结果表明,人工神经网络在预测腐蚀电流密度方面优于 XGB,R2 为 0.98,并能准确预测阻抗参数,R2 为 0.99,这表明所开发的模型在准确预测 PEM 燃料电池涂层金属双极板的腐蚀性能方面大有可为。
{"title":"Modelling Anti-Corrosion Coating Performance of Metallic Bipolar Plates for PEM Fuel Cells: A Machine Learning Approach","authors":"Pramoth Varsan Madhavan ,&nbsp;Samaneh Shahgaldi ,&nbsp;Xianguo Li","doi":"10.1016/j.egyai.2024.100391","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100391","url":null,"abstract":"<div><p>Proton exchange membrane (PEM) fuel cells have significant potential for clean power generation, yet challenges remain in enhancing their performance, durability, and cost-effectiveness, particularly concerning metallic bipolar plates, which are pivotal for lightweight compact fuel cell stacks. Protective coatings are commonly employed to combat metallic bipolar plate corrosion and enhance water management within stacks. Conventional methods for predicting coating performance in terms of corrosion resistance involve complex physical-electrochemical modelling and extensive experimentation, with significant time and cost. In this study machine learning techniques are employed to model metallic bipolar plate coating performance, diamond-like-carbon coatings of varying thicknesses deposited on SS316L are considered, and coating performance is evaluated using potentiodynamic polarization and electrochemical impedance spectroscopy. The obtained experimental data is split into two datasets for machine learning modelling: one predicting corrosion current density and another predicting impedance parameters. Machine learning models, including extreme gradient boosting (XGB) and artificial neural networks (ANN), are developed, and optimized to predict coating performance attributes. Data preprocessing and hyperparameter tuning are carried out to enhance model accuracy. Results show that ANN outperforms XGB in predicting corrosion current density, achieving an R<sup>2</sup> &gt; 0.98, and accurately predicting impedance parameters with an R<sup>2</sup> &gt; 0.99, indicating that the models developed are very promising for accurate prediction of the corrosion performance of coated metallic bipolar plates for PEM fuel cells.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100391"},"PeriodicalIF":9.6,"publicationDate":"2024-06-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000570/pdfft?md5=e9602a2d4bdcbf9edd1ed121d42ef9f7&pid=1-s2.0-S2666546824000570-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141542907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Comparing four machine learning algorithms for household non-intrusive load monitoring 比较用于家庭非侵入式负荷监测的四种机器学习算法
IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-24 DOI: 10.1016/j.egyai.2024.100384
Thomas Lee Young, James Gopsill, Maria Valero, Sindre Eikevåg, Ben Hicks

The combination of Machine Learning (ML), smart energy meters, and availability of household appliance energy profile data has opened new opportunities for Non-Intrusive Load Monitoring (NILM). However, the number of options makes it challenging in selecting optimal combinations for different energy applications, which requires studies to examine their trade-offs.

This paper contributes one such study that investigated four established ML approaches – K Nearest Neighbour (KNN), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN) – and their performance in classifying appliance events from Alternating Current (AC) and Root Mean Square (RMS) energy data where the sampling frequency and training dataset set size was varied (10 Hz–1 kHz and 50–2000 examples per class, respectively). The computational expense during training, testing and storage was also assessed and evaluated with reference to real-world applications.

The CNN classifier trained on AC data at 500 Hz and 11,000 examples gave the best F1-score 0.989 followed by the KNN classifier 0.940. The storage size required by the CNN models was 3̃MB, which is very close to fitting on cost-effective embedded system microcontrollers. This would prevent high-rate data needing to be sent to the cloud as analysis could be performed on edge computing Internet-of-Things (IoT) devices.

机器学习(ML)、智能能源计量表和家用电器能源概况数据的结合为非侵入式负荷监测(NILM)带来了新的机遇。然而,由于选项众多,要为不同的能源应用选择最佳组合极具挑战性,这就需要对其权衡利弊进行研究。本文就是这样一项研究,研究了四种成熟的 ML 方法--K 最近邻 (KNN)、支持向量机 (SVM)、极梯度提升 (XGBoost) 和卷积神经网络 (CNN)--以及它们在对交流 (AC) 和均方根 (RMS) 能源数据中的家电事件进行分类时的性能,其中采样频率和训练数据集大小各不相同(分别为 10 Hz-1 kHz 和每类 50-2000 个实例)。在实际应用中,还对训练、测试和存储过程中的计算费用进行了评估和评价。在 500 Hz 和 11,000 个示例的交流电数据上训练的 CNN 分类器给出了最佳 F1 分数 0.989,其次是 KNN 分类器的 0.940。CNN 模型所需的存储容量为 3̃MB,非常接近成本效益型嵌入式系统微控制器的容量。这可以避免将高速数据发送到云端,因为分析可以在边缘计算的物联网(IoT)设备上进行。
{"title":"Comparing four machine learning algorithms for household non-intrusive load monitoring","authors":"Thomas Lee Young,&nbsp;James Gopsill,&nbsp;Maria Valero,&nbsp;Sindre Eikevåg,&nbsp;Ben Hicks","doi":"10.1016/j.egyai.2024.100384","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100384","url":null,"abstract":"<div><p>The combination of Machine Learning (ML), smart energy meters, and availability of household appliance energy profile data has opened new opportunities for Non-Intrusive Load Monitoring (NILM). However, the number of options makes it challenging in selecting optimal combinations for different energy applications, which requires studies to examine their trade-offs.</p><p>This paper contributes one such study that investigated four established ML approaches – K Nearest Neighbour (KNN), Support Vector Machine (SVM), eXtreme Gradient Boosting (XGBoost) and Convolutional Neural Network (CNN) – and their performance in classifying appliance events from Alternating Current (AC) and Root Mean Square (RMS) energy data where the sampling frequency and training dataset set size was varied (10 Hz–1 kHz and 50–2000 examples per class, respectively). The computational expense during training, testing and storage was also assessed and evaluated with reference to real-world applications.</p><p>The CNN classifier trained on AC data at 500 Hz and 11,000 examples gave the best F1-score <span><math><mfenced><mrow><mn>0</mn><mo>.</mo><mn>989</mn></mrow></mfenced></math></span> followed by the KNN classifier <span><math><mfenced><mrow><mn>0</mn><mo>.</mo><mn>940</mn></mrow></mfenced></math></span>. The storage size required by the CNN models was 3̃MB, which is very close to fitting on cost-effective embedded system microcontrollers. This would prevent high-rate data needing to be sent to the cloud as analysis could be performed on edge computing Internet-of-Things (IoT) devices.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100384"},"PeriodicalIF":9.6,"publicationDate":"2024-06-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000508/pdfft?md5=240b289da6cfc06f2620e646326a2a01&pid=1-s2.0-S2666546824000508-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141481313","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A systematic review of spatial disaggregation methods for climate action planning 对气候行动规划空间分类方法的系统审查
IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-17 DOI: 10.1016/j.egyai.2024.100386
Shruthi Patil , Noah Pflugradt , Jann M. Weinand , Detlef Stolten , Jürgen Kropp

National-level climate action plans are often formulated broadly. Spatially disaggregating these plans to individual municipalities can offer substantial benefits, such as enabling regional climate action strategies and for assessing the feasibility of national objectives. Numerous spatial disaggregation approaches can be found in the literature. This study reviews and categorizes these. The review is followed by a discussion of the relevant methods for the disaggregation of climate action plans. It is seen that methods employing proxy data, machine learning models, and geostatistical ones are the most relevant methods for the spatial disaggregation of national energy and climate plans. The analysis offers guidance for selecting appropriate methods based on factors such as data availability at the municipal level and the presence of spatial autocorrelation in the data.

As the urgency of addressing climate change escalates, understanding the spatial aspects of national energy and climate strategies becomes increasingly important. This review will serve as a valuable guide for researchers and practitioners applying spatial disaggregation in this crucial field.

国家级气候行动计划的制定通常比较宽泛。将这些计划在空间上细分到各个城市,可以带来很大的好处,例如可以制定区域气候行动战略,评估国家目标的可行性。文献中有许多空间分解方法。本研究对这些方法进行了回顾和分类。回顾之后,讨论了气候行动计划的相关分解方法。可以看出,采用代用数据、机器学习模型和地质统计模型的方法是与国家能源和气候计划的空间分解最相关的方法。随着应对气候变化的紧迫性不断升级,了解国家能源和气候战略的空间方面变得越来越重要。本综述将为在这一关键领域应用空间分类的研究人员和从业人员提供有价值的指导。
{"title":"A systematic review of spatial disaggregation methods for climate action planning","authors":"Shruthi Patil ,&nbsp;Noah Pflugradt ,&nbsp;Jann M. Weinand ,&nbsp;Detlef Stolten ,&nbsp;Jürgen Kropp","doi":"10.1016/j.egyai.2024.100386","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100386","url":null,"abstract":"<div><p>National-level climate action plans are often formulated broadly. Spatially disaggregating these plans to individual municipalities can offer substantial benefits, such as enabling regional climate action strategies and for assessing the feasibility of national objectives. Numerous spatial disaggregation approaches can be found in the literature. This study reviews and categorizes these. The review is followed by a discussion of the relevant methods for the disaggregation of climate action plans. It is seen that methods employing proxy data, machine learning models, and geostatistical ones are the most relevant methods for the spatial disaggregation of national energy and climate plans. The analysis offers guidance for selecting appropriate methods based on factors such as data availability at the municipal level and the presence of spatial autocorrelation in the data.</p><p>As the urgency of addressing climate change escalates, understanding the spatial aspects of national energy and climate strategies becomes increasingly important. This review will serve as a valuable guide for researchers and practitioners applying spatial disaggregation in this crucial field.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100386"},"PeriodicalIF":9.6,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000521/pdfft?md5=b85d13c3337101d8dea3c12c85754bdd&pid=1-s2.0-S2666546824000521-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141438719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Discriminative features based comprehensive detector for defective insulators 基于判别特征的缺陷绝缘体综合检测器
IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-17 DOI: 10.1016/j.egyai.2024.100387
Yalin Li, Xinshan Zhu, Bin Li, Junting Zeng, Shuai Wang

Insulators are essential equipment to ensure the safety and reliability of power transmission systems. Defective insulators may cause partial discharge and even lead to serious safety accidents. Hence it is necessary to accurately identify the defective insulator from a string of insulators. However, small defect poses significant challenges for recognizing the defective insulator from a large number of insulators. To address these issues, we collect and annotate the randomly generated defect dataset (RGDD). Further, the discriminative feature learning-based detector (DFLD) is constructed based on the pattern of backbone-neck-head. Specifically, considering the simultaneous existence of many insulators, attention-based bidirectional feature pyramid (ABFP) is designed to capture the discriminative information. Considering the small size of defective part, the efficient receptive field adaptation (ERFA) module is constructed to enhance the perception of contextual information related to defective insulators. Meanwhile, the two-stage detection head is designed to correct the location of defective insulators. It also adapts to the shape variation of insulators by the deformable convolution. On this basis, the keypoints method is introduced to more accurately represent the location of defective insulators. Due to the imbalance between positive and negative samples, the Adaptive Threshold Sample Assignment (ATSA) Strategy is proposed for selecting the best positive samples. DFLD has achieved good detection performance compared with classical object detection networks on the RGDD dataset and CPLID dataset. The ablation experiments are conducted on the RGDD dataset. It is verified that the discriminative features from DFLD can effectively recognize the small defect from insulators.

绝缘子是确保输电系统安全性和可靠性的重要设备。有缺陷的绝缘子可能会导致局部放电,甚至引发严重的安全事故。因此,有必要从一串绝缘子中准确识别出有缺陷的绝缘子。然而,要从大量绝缘子中识别出有缺陷的绝缘子,微小的缺陷带来了巨大的挑战。为了解决这些问题,我们收集并注释了随机生成的缺陷数据集(RGDD)。此外,我们还根据骨干-颈部-头部模式构建了基于判别特征学习的检测器(DFLD)。具体来说,考虑到同时存在多个绝缘体,设计了基于注意力的双向特征金字塔(ABFP)来捕捉判别信息。考虑到缺陷部分的尺寸较小,构建了高效感受野适应(ERFA)模块,以增强对缺陷绝缘体相关上下文信息的感知。同时,设计了两级检测头来校正缺陷绝缘体的位置。它还通过可变形卷积来适应绝缘子的形状变化。在此基础上,引入了关键点方法,以更准确地表示缺陷绝缘子的位置。由于正负样本之间的不平衡,提出了自适应阈值样本分配(ATSA)策略来选择最佳的正样本。在 RGDD 数据集和 CPLID 数据集上,DFLD 与经典物体检测网络相比取得了良好的检测性能。在 RGDD 数据集上进行了消融实验。实验验证了 DFLD 的判别特征能有效识别绝缘体的小缺陷。
{"title":"Discriminative features based comprehensive detector for defective insulators","authors":"Yalin Li,&nbsp;Xinshan Zhu,&nbsp;Bin Li,&nbsp;Junting Zeng,&nbsp;Shuai Wang","doi":"10.1016/j.egyai.2024.100387","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100387","url":null,"abstract":"<div><p>Insulators are essential equipment to ensure the safety and reliability of power transmission systems. Defective insulators may cause partial discharge and even lead to serious safety accidents. Hence it is necessary to accurately identify the defective insulator from a string of insulators. However, small defect poses significant challenges for recognizing the defective insulator from a large number of insulators. To address these issues, we collect and annotate the randomly generated defect dataset (RGDD). Further, the discriminative feature learning-based detector (DFLD) is constructed based on the pattern of backbone-neck-head. Specifically, considering the simultaneous existence of many insulators, attention-based bidirectional feature pyramid (ABFP) is designed to capture the discriminative information. Considering the small size of defective part, the efficient receptive field adaptation (ERFA) module is constructed to enhance the perception of contextual information related to defective insulators. Meanwhile, the two-stage detection head is designed to correct the location of defective insulators. It also adapts to the shape variation of insulators by the deformable convolution. On this basis, the keypoints method is introduced to more accurately represent the location of defective insulators. Due to the imbalance between positive and negative samples, the Adaptive Threshold Sample Assignment (ATSA) Strategy is proposed for selecting the best positive samples. DFLD has achieved good detection performance compared with classical object detection networks on the RGDD dataset and CPLID dataset. The ablation experiments are conducted on the RGDD dataset. It is verified that the discriminative features from DFLD can effectively recognize the small defect from insulators.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100387"},"PeriodicalIF":9.6,"publicationDate":"2024-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000533/pdfft?md5=ee18da9af0fcff760d49779875c4d300&pid=1-s2.0-S2666546824000533-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141481292","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Multi-criteria decision-making method for evaluation of investment in enhanced geothermal systems projects 评估强化地热系统项目投资的多标准决策方法
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-13 DOI: 10.1016/j.egyai.2024.100390
Sara Raos , Josipa Hranić , Ivan Rajšl

Deep geothermal energy presents large untapped renewable energy potential could significantly contribute to global energy needs. However, developing geothermal projects involves uncertainties regarding adequate geothermal brine extraction and huge costs related to preparation phases and consequently drilling and stimulation activities. Therefore, evaluating utilization alternatives of such projects is a complex decision-making problem effectively addressed using multi-criteria decision-making (MCDM) methods. This study introduces the MCDM method utilizing analytic hierarchy process (AHP) and weighted decision matrix (WDM) to assess different utilization alternatives (electricity generation, direct heat use and cogeneration). The AHP method determines the weight of each criterion and sub-criterion, while the WDM calculates the final project grade. Five criteria groups - technological, geological, economic, societal and environmental – comprising twenty-eight influencing factors were selected and used for the assessment of investment in Enhanced Geothermal Systems (EGS) projects. The AHP-WDM method was used by 38 experts from six categories: industry, educational institution, research and technology organization (RTO), small- and medium-sized enterprises (SME), local community and other. These diverse expert inputs aimed to capture varying perspectives and knowledge influence investment decisions in geothermal energy. The results were analysed accordingly. The results underscore the importance of incorporating different viewpoints to develop robust, credible, and effective investment strategies for EGS projects. Therefore, this method will contribute to more efficient EGS project development, enabling thus a greater penetration of the EGS into the market. Additionally, the proposed AHP-WDM method was implemented for a case study examining two locations. Locations were assessed and compared on scenario-based evaluation. The results confirmed the method's adequacy for assessing various end uses and comparing project feasibility across different locations.

深层地热能源具有巨大的未开发可再生能源潜力,可极大地满足全球能源需求。然而,开发地热项目涉及到地热卤水提取是否充足的不确定性,以及与准备阶段和随后的钻探和刺激活动相关的巨额成本。因此,评估此类项目的可选利用方案是一个复杂的决策问题,可通过多标准决策(MCDM)方法有效解决。本研究介绍了利用层次分析法(AHP)和加权决策矩阵(WDM)评估不同利用替代方案(发电、直接供热和热电联产)的 MCDM 方法。AHP 方法确定每个标准和次级标准的权重,而 WDM 则计算项目的最终等级。在对强化地热系统(EGS)项目进行投资评估时,选择并使用了五个标准组(技术、地质、经济、社会和环境),包括 28 个影响因素。来自工业、教育机构、研究和技术组织 (RTO)、中小型企业 (SME)、当地社区和其他六类的 38 位专家使用了 AHP-WDM 方法。这些不同的专家意见旨在捕捉影响地热能源投资决策的不同观点和知识。对结果进行了相应的分析。研究结果强调了纳入不同观点的重要性,以便为 EGS 项目制定稳健、可信和有效的投资战略。因此,该方法将有助于提高 EGS 项目开发的效率,从而使 EGS 更广泛地进入市场。此外,建议的 AHP-WDM 方法还用于对两个地点的案例研究。通过基于情景的评估对两个地点进行了评估和比较。结果证实,该方法适用于评估各种最终用途和比较不同地点的项目可行性。
{"title":"Multi-criteria decision-making method for evaluation of investment in enhanced geothermal systems projects","authors":"Sara Raos ,&nbsp;Josipa Hranić ,&nbsp;Ivan Rajšl","doi":"10.1016/j.egyai.2024.100390","DOIUrl":"10.1016/j.egyai.2024.100390","url":null,"abstract":"<div><p>Deep geothermal energy presents large untapped renewable energy potential could significantly contribute to global energy needs. However, developing geothermal projects involves uncertainties regarding adequate geothermal brine extraction and huge costs related to preparation phases and consequently drilling and stimulation activities. Therefore, evaluating utilization alternatives of such projects is a complex decision-making problem effectively addressed using multi-criteria decision-making (MCDM) methods. This study introduces the MCDM method utilizing analytic hierarchy process (AHP) and weighted decision matrix (WDM) to assess different utilization alternatives (electricity generation, direct heat use and cogeneration). The AHP method determines the weight of each criterion and sub-criterion, while the WDM calculates the final project grade. Five criteria groups - technological, geological, economic, societal and environmental – comprising twenty-eight influencing factors were selected and used for the assessment of investment in Enhanced Geothermal Systems (EGS) projects. The AHP-WDM method was used by 38 experts from six categories: industry, educational institution, research and technology organization (RTO), small- and medium-sized enterprises (SME), local community and other. These diverse expert inputs aimed to capture varying perspectives and knowledge influence investment decisions in geothermal energy. The results were analysed accordingly. The results underscore the importance of incorporating different viewpoints to develop robust, credible, and effective investment strategies for EGS projects. Therefore, this method will contribute to more efficient EGS project development, enabling thus a greater penetration of the EGS into the market. Additionally, the proposed AHP-WDM method was implemented for a case study examining two locations. Locations were assessed and compared on scenario-based evaluation. The results confirmed the method's adequacy for assessing various end uses and comparing project feasibility across different locations.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100390"},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000569/pdfft?md5=8bd57e3e6f065bf06bc16f61d5e85db4&pid=1-s2.0-S2666546824000569-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141413108","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
STATNet: One-stage coal-gangue detector based on deep learning algorithm for real industrial application STATNet:基于深度学习算法的单级煤矸石检测器在实际工业中的应用
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-13 DOI: 10.1016/j.egyai.2024.100388
Kefei Zhang , Teng Wang , Xiaolin Yang , Liang Xu , Jesse Thé , Zhongchao Tan , Hesheng Yu

Coal-gangue object detection has attracted substantial attention because it is the core of realizing vision-based intelligent and green coal separation. However, most existing studies have been focused on laboratory datasets and prioritized model lightweight. This makes the coal-gangue object detection challenging to adapt to the complex and harsh scenes of real production environments. Therefore, our project collected and labeled image datasets of coal and gangue under real production conditions from a coal preparation plant. We then designed a one-stage object model, named STATNet, following the “backbone-neck-head” architecture with the aim of enhancing the detection accuracy under industrial coal preparation scenarios. The proposed model utilizes Swin Transformer as backbone module to extract multi-scale features, improved path augmentation feature pyramid network (iPAFPN) as neck module to enrich feature fusion, and task-aligned head (TAH) as head module to mitigate conflicts and misalignments between classification and localization tasks. Experimental results on a real-world industrial dataset demonstrate that the proposed STATNet model achieves an impressive AP50 of 89.27 %, significantly surpassing several state-of-the-art baseline models by 2.02 % to 5.58 %. Additionally, it exhibits stronger robustness in resisting image corruption and perturbation. These findings demonstrate its promising prospects in practical coal and gangue separation applications.

煤矸石物体检测是实现基于视觉的智能绿色选煤的核心,因此备受关注。然而,现有研究大多集中于实验室数据集,并优先考虑模型轻量化。这使得煤矸石物体检测难以适应实际生产环境中复杂恶劣的场景。因此,我们的项目从选煤厂收集并标注了真实生产条件下的煤炭和煤矸石图像数据集。然后,我们按照 "骨干-颈部-头部 "架构设计了一个单级对象模型,命名为 STATNet,旨在提高工业选煤场景下的检测精度。该模型利用 Swin Transformer 作为骨干模块来提取多尺度特征,利用改进路径增强特征金字塔网络(iPAFPN)作为颈部模块来丰富特征融合,利用任务对齐头(TAH)作为头部模块来缓解分类和定位任务之间的冲突和错位。在实际工业数据集上的实验结果表明,所提出的 STATNet 模型实现了 89.27 % 的惊人 AP50,大大超过了几个最先进的基线模型 2.02 % 到 5.58 %。此外,它在抵御图像损坏和扰动方面表现出更强的鲁棒性。这些研究结果表明,它在实际煤炭和矸石分离应用中大有可为。
{"title":"STATNet: One-stage coal-gangue detector based on deep learning algorithm for real industrial application","authors":"Kefei Zhang ,&nbsp;Teng Wang ,&nbsp;Xiaolin Yang ,&nbsp;Liang Xu ,&nbsp;Jesse Thé ,&nbsp;Zhongchao Tan ,&nbsp;Hesheng Yu","doi":"10.1016/j.egyai.2024.100388","DOIUrl":"10.1016/j.egyai.2024.100388","url":null,"abstract":"<div><p>Coal-gangue object detection has attracted substantial attention because it is the core of realizing vision-based intelligent and green coal separation. However, most existing studies have been focused on laboratory datasets and prioritized model lightweight. This makes the coal-gangue object detection challenging to adapt to the complex and harsh scenes of real production environments. Therefore, our project collected and labeled image datasets of coal and gangue under real production conditions from a coal preparation plant. We then designed a one-stage object model, named STATNet, following the “backbone-neck-head” architecture with the aim of enhancing the detection accuracy under industrial coal preparation scenarios. The proposed model utilizes Swin Transformer as backbone module to extract multi-scale features, improved path augmentation feature pyramid network (iPAFPN) as neck module to enrich feature fusion, and task-aligned head (TAH) as head module to mitigate conflicts and misalignments between classification and localization tasks. Experimental results on a real-world industrial dataset demonstrate that the proposed STATNet model achieves an impressive AP<sub>50</sub> of 89.27 %, significantly surpassing several state-of-the-art baseline models by 2.02 % to 5.58 %. Additionally, it exhibits stronger robustness in resisting image corruption and perturbation. These findings demonstrate its promising prospects in practical coal and gangue separation applications.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100388"},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000545/pdfft?md5=59c53a1ec82a8c06886114b0bc76cebc&pid=1-s2.0-S2666546824000545-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141397737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Descriptors-based machine-learning prediction of cetane number using quantitative structure–property relationship 基于描述符的机器学习利用定量结构-性质关系预测十六烷值
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-13 DOI: 10.1016/j.egyai.2024.100385
Rodolfo S.M. Freitas, Xi Jiang

The physicochemical properties of liquid alternative fuels are important but difficult to measure/predict, especially when complex surrogate fuels are concerned. In the present work, machine learning is used to develop quantitative structure–property relationship models. The fuel chemical structure is represented by molecular descriptors, allowing the linking of important features of the fuel composition and key properties of fuel utilization. Feature selection is employed to select the most relevant features that describe the chemical structure of the fuel and several machine learning algorithms are tested to construct interpretable models. The effectiveness of the methodology is demonstrated through the development of accurate and interpretable predictive models for cetane numbers, with a focus on understanding the link between molecular structure and fuel properties. In this context, matrix-based descriptors and descriptors related to the number of atoms in the molecule are directly linked with the cetane number of hydrocarbons. Furthermore, the results showed that molecular connectivity indices play a role in the cetane number for aromatic molecules. Also, the methodology is extended to predict the cetane number of ester and ether molecules, leveraging the design of alternative fuels towards fully sustainable fuel utilization.

液体替代燃料的物理化学特性非常重要,但却很难测量/预测,尤其是在涉及复杂的代用燃料时。在本研究中,机器学习被用来开发定量的结构-性能关系模型。燃料化学结构由分子描述符表示,从而将燃料成分的重要特征与燃料利用的关键属性联系起来。特征选择用于选择描述燃料化学结构的最相关特征,并对几种机器学习算法进行了测试,以构建可解释的模型。通过开发准确且可解释的十六烷值预测模型,展示了该方法的有效性,重点是了解分子结构与燃料特性之间的联系。在这种情况下,基于矩阵的描述符和与分子中原子数有关的描述符与碳氢化合物的十六烷值直接相关。此外,研究结果表明,分子连通性指数对芳香族分子的十六烷值也有影响。此外,该方法还可用于预测酯类和醚类分子的十六烷值,从而有助于替代燃料的设计,实现完全可持续的燃料利用。
{"title":"Descriptors-based machine-learning prediction of cetane number using quantitative structure–property relationship","authors":"Rodolfo S.M. Freitas,&nbsp;Xi Jiang","doi":"10.1016/j.egyai.2024.100385","DOIUrl":"10.1016/j.egyai.2024.100385","url":null,"abstract":"<div><p>The physicochemical properties of liquid alternative fuels are important but difficult to measure/predict, especially when complex surrogate fuels are concerned. In the present work, machine learning is used to develop quantitative structure–property relationship models. The fuel chemical structure is represented by molecular descriptors, allowing the linking of important features of the fuel composition and key properties of fuel utilization. Feature selection is employed to select the most relevant features that describe the chemical structure of the fuel and several machine learning algorithms are tested to construct interpretable models. The effectiveness of the methodology is demonstrated through the development of accurate and interpretable predictive models for cetane numbers, with a focus on understanding the link between molecular structure and fuel properties. In this context, matrix-based descriptors and descriptors related to the number of atoms in the molecule are directly linked with the cetane number of hydrocarbons. Furthermore, the results showed that molecular connectivity indices play a role in the cetane number for aromatic molecules. Also, the methodology is extended to predict the cetane number of ester and ether molecules, leveraging the design of alternative fuels towards fully sustainable fuel utilization.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100385"},"PeriodicalIF":0.0,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266654682400051X/pdfft?md5=11622043c70586930c8e405147983d28&pid=1-s2.0-S266654682400051X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141402689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Distributionally robust optimization configuration method for island microgrid considering extreme scenarios 考虑极端情况的岛屿微电网分布式鲁棒优化配置方法
IF 9.6 Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-13 DOI: 10.1016/j.egyai.2024.100389
Qingzhu Zhang, Yunfei Mu, Hongjie Jia, Xiaodan Yu, Kai Hou

The marine climate conditions are intricate and variable. In scenarios characterized by high proportions of wind and solar energy access, the uncertainty regarding the energy sources for island microgrid is significantly exacerbated, presenting challenges to both the economic viability and reliability of the capacity configuration for island microgrids. To address this issue, this paper proposes a distributionally robust optimization (DRO) method for island microgrids, considering extreme scenarios of wind and solar conditions. Firstly, to address the challenge of determining the probability distribution functions of wind and solar in complex island climates, a conditional generative adversarial network (CGAN) is employed to generate a scenario set for wind and solar conditions. Then, by combining k-means clustering with an extreme scenario selection method, typical scenarios and extreme scenarios are selected from the generated scenario set, forming the scenario set for the DRO model of island microgrids. On this basis, a DRO model based on multiple discrete scenarios is constructed with the objective of minimizing the sum of investment costs, operation and maintenance costs, fuel purchase costs, penalty costs of wind and solar curtailment, and penalty costs of load loss. The model is subjected to equipment operation and power balance constraints, and solved using the columns and constraints generation (CCG) algorithm. Finally, through typical examples, the effectiveness of this paper’s method in balancing the economic viability and robustness of the configuration scheme for the island microgrid, as well as reducing wind and solar curtailment and load loss, is verified.

海洋气候条件复杂多变。在风能和太阳能接入比例较高的情况下,岛屿微电网能源来源的不确定性大大增加,这对岛屿微电网容量配置的经济可行性和可靠性都提出了挑战。针对这一问题,本文提出了一种考虑风能和太阳能极端情况的岛屿微电网分布式鲁棒优化(DRO)方法。首先,为了解决在复杂的海岛气候条件下确定风能和太阳能概率分布函数的难题,本文采用了条件生成对抗网络(CGAN)来生成风能和太阳能条件的情景集。然后,通过将 k-means 聚类与极端情景选择方法相结合,从生成的情景集中选择典型情景和极端情景,形成海岛微电网 DRO 模型的情景集。在此基础上,以投资成本、运行和维护成本、燃料采购成本、风能和太阳能削减惩罚成本以及负荷损失惩罚成本之和最小化为目标,构建了基于多个离散情景的 DRO 模型。该模型受到设备运行和电力平衡约束,并使用列和约束生成(CCG)算法求解。最后,通过典型实例验证了本文方法在平衡岛屿微电网配置方案的经济可行性和鲁棒性,以及减少风能和太阳能削减和负荷损失方面的有效性。
{"title":"Distributionally robust optimization configuration method for island microgrid considering extreme scenarios","authors":"Qingzhu Zhang,&nbsp;Yunfei Mu,&nbsp;Hongjie Jia,&nbsp;Xiaodan Yu,&nbsp;Kai Hou","doi":"10.1016/j.egyai.2024.100389","DOIUrl":"10.1016/j.egyai.2024.100389","url":null,"abstract":"<div><p>The marine climate conditions are intricate and variable. In scenarios characterized by high proportions of wind and solar energy access, the uncertainty regarding the energy sources for island microgrid is significantly exacerbated, presenting challenges to both the economic viability and reliability of the capacity configuration for island microgrids. To address this issue, this paper proposes a distributionally robust optimization (DRO) method for island microgrids, considering extreme scenarios of wind and solar conditions. Firstly, to address the challenge of determining the probability distribution functions of wind and solar in complex island climates, a conditional generative adversarial network (CGAN) is employed to generate a scenario set for wind and solar conditions. Then, by combining k-means clustering with an extreme scenario selection method, typical scenarios and extreme scenarios are selected from the generated scenario set, forming the scenario set for the DRO model of island microgrids. On this basis, a DRO model based on multiple discrete scenarios is constructed with the objective of minimizing the sum of investment costs, operation and maintenance costs, fuel purchase costs, penalty costs of wind and solar curtailment, and penalty costs of load loss. The model is subjected to equipment operation and power balance constraints, and solved using the columns and constraints generation (CCG) algorithm. Finally, through typical examples, the effectiveness of this paper’s method in balancing the economic viability and robustness of the configuration scheme for the island microgrid, as well as reducing wind and solar curtailment and load loss, is verified.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100389"},"PeriodicalIF":9.6,"publicationDate":"2024-06-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000557/pdfft?md5=4deedfabeeaa261dac258a4e27cbf257&pid=1-s2.0-S2666546824000557-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141391621","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Machine learning and Bayesian optimization for performance prediction of proton-exchange membrane fuel cells 用于质子交换膜燃料电池性能预测的机器学习和贝叶斯优化技术
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-08 DOI: 10.1016/j.egyai.2024.100380
Soufian Echabarri , Phuc Do , Hai-Canh Vu , Bastien Bornand

Proton-exchange membrane fuel cells (PEMFCs) are critical components of zero-emission electro-hydrogen generators. Accurate performance prediction is vital to the optimal operation management and preventive maintenance of these generators. Polarization curve remains one of the most important features representing the performance of PEMFCs in terms of efficiency and durability. However, predicting the polarization curve is not trivial as PEMFCs involve complex electrochemical reactions that feature multiple nonlinear relationships between the operating variables as inputs and the voltage as outputs. Herein, we present an artificial-intelligence-based approach for predicting the PEMFCs’ performance. In that way, we propose first an explainable solution for selecting the relevant features based on kernel principal component analysis and mutual information. Then, we develop a machine learning approach based on XGBRegressor and Bayesian optimization to explore the complex features and predict the PEMFCs’ performance. The performance and the robustness of the proposed machine learning based prediction approach is tested and validated through a real industrial dataset including 10 PEMFCs. Furthermore, several comparison studies with XGBRegressor and the two popular machine learning-based methods in predicting PEMFC performance, such as artificial neural network (ANN) and support vector machine regressor (SVR) are also conducted. The obtained results show that the proposed approach is more robust and outperforms the two conventional methods and the XGBRegressor for all the considered PEMFCs. Indeed, according to the coefficient of determination criterion, the proposed model gains an improvement of 6.35%, 6.8%, and 4.8% compared with ANN, SVR, and XGBRegressor respectively.

质子交换膜燃料电池(PEMFC)是零排放电氢发电机的关键部件。准确的性能预测对于这些发电机的优化运行管理和预防性维护至关重要。极化曲线仍然是代表 PEMFC 在效率和耐用性方面性能的最重要特征之一。然而,预测极化曲线并非易事,因为 PEMFCs 涉及复杂的电化学反应,在作为输入的操作变量和作为输出的电压之间存在多种非线性关系。在此,我们提出了一种基于人工智能的 PEMFC 性能预测方法。为此,我们首先提出了一种基于内核主成分分析和互信息选择相关特征的可解释解决方案。然后,我们开发了一种基于 XGBRegressor 和贝叶斯优化的机器学习方法,以探索复杂特征并预测 PEMFC 的性能。我们通过一个包括 10 个 PEMFC 的真实工业数据集测试和验证了所提出的基于机器学习的预测方法的性能和稳健性。此外,还与 XGBRegressor 以及人工神经网络(ANN)和支持向量机回归器(SVR)等两种常用的基于机器学习的 PEMFC 性能预测方法进行了比较研究。结果表明,就所有考虑的 PEMFC 而言,所提出的方法更加稳健,性能优于两种传统方法和 XGBRegressor。事实上,根据判定系数标准,与 ANN、SVR 和 XGBRegressor 相比,所提出的模型分别提高了 6.35%、6.8% 和 4.8%。
{"title":"Machine learning and Bayesian optimization for performance prediction of proton-exchange membrane fuel cells","authors":"Soufian Echabarri ,&nbsp;Phuc Do ,&nbsp;Hai-Canh Vu ,&nbsp;Bastien Bornand","doi":"10.1016/j.egyai.2024.100380","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100380","url":null,"abstract":"<div><p>Proton-exchange membrane fuel cells (PEMFCs) are critical components of zero-emission electro-hydrogen generators. Accurate performance prediction is vital to the optimal operation management and preventive maintenance of these generators. Polarization curve remains one of the most important features representing the performance of PEMFCs in terms of efficiency and durability. However, predicting the polarization curve is not trivial as PEMFCs involve complex electrochemical reactions that feature multiple nonlinear relationships between the operating variables as inputs and the voltage as outputs. Herein, we present an artificial-intelligence-based approach for predicting the PEMFCs’ performance. In that way, we propose first an explainable solution for selecting the relevant features based on kernel principal component analysis and mutual information. Then, we develop a machine learning approach based on XGBRegressor and Bayesian optimization to explore the complex features and predict the PEMFCs’ performance. The performance and the robustness of the proposed machine learning based prediction approach is tested and validated through a real industrial dataset including 10 PEMFCs. Furthermore, several comparison studies with XGBRegressor and the two popular machine learning-based methods in predicting PEMFC performance, such as artificial neural network (ANN) and support vector machine regressor (SVR) are also conducted. The obtained results show that the proposed approach is more robust and outperforms the two conventional methods and the XGBRegressor for all the considered PEMFCs. Indeed, according to the coefficient of determination criterion, the proposed model gains an improvement of 6.35%, 6.8%, and 4.8% compared with ANN, SVR, and XGBRegressor respectively.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100380"},"PeriodicalIF":0.0,"publicationDate":"2024-06-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S2666546824000466/pdfft?md5=84951ddfd79fda43e2f7ebe4da185d3f&pid=1-s2.0-S2666546824000466-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141323042","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments 利用合成数据进行转移学习,从部分充电片段重建开路电压曲线并评估锂离子电池的健康状况
Q1 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE Pub Date : 2024-06-06 DOI: 10.1016/j.egyai.2024.100382
Tobias Hofmann , Jacob Hamar , Bastian Mager , Simon Erhard , Jan Philipp Schmidt

Data-driven models for battery state estimation require extensive experimental training data, which may not be available or suitable for specific tasks like open-circuit voltage (OCV) reconstruction and subsequent state of health (SOH) estimation. This study addresses this issue by developing a transfer-learning-based OCV reconstruction model using a temporal convolutional long short-term memory (TCN-LSTM) network trained on synthetic data from an automotive nickel cobalt aluminium oxide (NCA) cell generated through a mechanistic model approach. The data consists of voltage curves at constant temperature, C-rates between C/30 to 1C, and a SOH-range from 70 % to 100 %. The model is refined via Bayesian optimization and then applied to four use cases with reduced experimental nickel manganese cobalt oxide (NMC) cell training data for higher use cases. The TL models’ performances are compared with models trained solely on experimental data, focusing on different C-rates and voltage windows. The results demonstrate that the OCV reconstruction mean absolute error (MAE) within the average battery electric vehicle (BEV) home charging window (30 % to 85 % state of charge (SOC)) is less than 22 mV for the first three use cases across all C-rates. The SOH estimated from the reconstructed OCV exhibits an mean absolute percentage error (MAPE) below 2.2 % for these cases. The study further investigates the impact of the source domain on TL by incorporating two additional synthetic datasets, a lithium iron phosphate (LFP) cell and an entirely artificial, non-existing, cell, showing that solely the shifting and scaling of gradient changes in the charging curve suffice to transfer knowledge, even between different cell chemistries. A key limitation with respect to extrapolation capability is identified and evidenced in our fourth use case, where the absence of such comprehensive data hindered the TL process.

用于电池状态估计的数据驱动模型需要大量实验训练数据,而这些数据可能无法获得或不适合开路电压(OCV)重建和后续健康状态(SOH)估计等特定任务。为解决这一问题,本研究开发了基于迁移学习的开路电压重构模型,该模型采用时序卷积长短期记忆(TCN-LSTM)网络,通过机理模型方法生成的汽车镍钴铝氧化物(NCA)电池合成数据对其进行训练。数据包括恒温下的电压曲线、C/30 到 1C 之间的 C 率以及 70% 到 100% 的 SOH 范围。通过贝叶斯优化法对该模型进行了改进,然后将其应用于四种使用情况,并在较高使用情况下减少了镍锰钴氧化物(NMC)电池的实验训练数据。将 TL 模型的性能与仅根据实验数据训练的模型进行了比较,重点关注不同的 C 速率和电压窗口。结果表明,在所有 C 速率的前三种使用情况下,平均电池电动汽车 (BEV) 家庭充电窗口(30 % 至 85 % 充电状态 (SOC))内的 OCV 重建平均绝对误差 (MAE) 小于 22 mV。在这些情况下,根据重建的 OCV 估算的 SOH 平均绝对百分比误差 (MAPE) 低于 2.2%。该研究通过纳入两个额外的合成数据集(磷酸铁锂(LFP)电池和完全人造的不存在的电池),进一步研究了源域对 TL 的影响,结果表明,即使在不同的电池化学成分之间,仅靠充电曲线梯度变化的移动和缩放就足以实现知识转移。在我们的第四个使用案例中,我们发现并证明了外推能力方面的一个关键限制,即缺乏此类全面的数据阻碍了 TL 过程。
{"title":"Transfer learning from synthetic data for open-circuit voltage curve reconstruction and state of health estimation of lithium-ion batteries from partial charging segments","authors":"Tobias Hofmann ,&nbsp;Jacob Hamar ,&nbsp;Bastian Mager ,&nbsp;Simon Erhard ,&nbsp;Jan Philipp Schmidt","doi":"10.1016/j.egyai.2024.100382","DOIUrl":"https://doi.org/10.1016/j.egyai.2024.100382","url":null,"abstract":"<div><p>Data-driven models for battery state estimation require extensive experimental training data, which may not be available or suitable for specific tasks like open-circuit voltage (OCV) reconstruction and subsequent state of health (SOH) estimation. This study addresses this issue by developing a transfer-learning-based OCV reconstruction model using a temporal convolutional long short-term memory (TCN-LSTM) network trained on synthetic data from an automotive nickel cobalt aluminium oxide (NCA) cell generated through a mechanistic model approach. The data consists of voltage curves at constant temperature, C-rates between <span><math><mrow><mtext>C</mtext><mo>/</mo><mn>30</mn></mrow></math></span> to <span><math><mrow><mn>1</mn><mtext>C</mtext></mrow></math></span>, and a SOH-range from 70<!--> <!-->% to 100<!--> <!-->%. The model is refined via Bayesian optimization and then applied to four use cases with reduced experimental nickel manganese cobalt oxide (NMC) cell training data for higher use cases. The TL models’ performances are compared with models trained solely on experimental data, focusing on different C-rates and voltage windows. The results demonstrate that the OCV reconstruction mean absolute error (MAE) within the average battery electric vehicle (BEV) home charging window (30<!--> <!-->% to 85<!--> <!-->% state of charge (SOC)) is less than 22<!--> <!-->mV for the first three use cases across all C-rates. The SOH estimated from the reconstructed OCV exhibits an mean absolute percentage error (MAPE) below 2.2<!--> <!-->% for these cases. The study further investigates the impact of the source domain on TL by incorporating two additional synthetic datasets, a lithium iron phosphate (LFP) cell and an entirely artificial, non-existing, cell, showing that solely the shifting and scaling of gradient changes in the charging curve suffice to transfer knowledge, even between different cell chemistries. A key limitation with respect to extrapolation capability is identified and evidenced in our fourth use case, where the absence of such comprehensive data hindered the TL process.</p></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"17 ","pages":"Article 100382"},"PeriodicalIF":0.0,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S266654682400048X/pdfft?md5=ea2f1d52a5cbfefe64bb5081c632c13d&pid=1-s2.0-S266654682400048X-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141314062","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
期刊
Energy and AI
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:481959085
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