Pub Date : 2025-12-01Epub Date: 2025-11-29DOI: 10.1016/j.egyai.2025.100661
Mo'ath El-Dalahmeh, Om Siddhapura, Geanina Apachitei, Matthew Capener, James Marco, Adam Todd, Keri Goodwin, Mona Faraji Niri
Reliable prediction of slurry viscosity is essential for consistent electrode coating in lithium-ion battery manufacturing. This study investigates transfer learning to address deployment-phase uncertainty arising from batch-to-batch variability under pilot-scale conditions. Experimental data from two batches are used to model viscosity at 1, 10, and 100 1/s using four inputs: formulation, dispersant type, solid content percent, and solid dispersant percent. Linear baselines (ordinary least squares and ridge) are evaluated alongside tree ensembles and neural architectures, under identical splits and preprocessing. Results show consistent performance gains from transfer learning across all shear rates, with higher R2 and lower MAE and RMSE relative to no-transfer training. Across models, differences in backbone choice are secondary; the transfer step is the principal driver of improvement under the present data regime. Uncertainty is quantified using split-conformal prediction intervals, yielding nominal 90 percent coverage with narrower intervals after transfer learning. Small-data design choices are reported, including balanced splits and sensitivity checks with conservative augmentation used only for analysis. The findings indicate a practical and data-efficient route to viscosity prediction under sequential batches, supporting more robust model deployment in pilot-scale manufacturing.
{"title":"Predictive modelling of slurry viscosity using transfer learning to mitigate uncertainties in pilot-scale lithium-ion battery manufacturing process","authors":"Mo'ath El-Dalahmeh, Om Siddhapura, Geanina Apachitei, Matthew Capener, James Marco, Adam Todd, Keri Goodwin, Mona Faraji Niri","doi":"10.1016/j.egyai.2025.100661","DOIUrl":"10.1016/j.egyai.2025.100661","url":null,"abstract":"<div><div>Reliable prediction of slurry viscosity is essential for consistent electrode coating in lithium-ion battery manufacturing. This study investigates transfer learning to address deployment-phase uncertainty arising from batch-to-batch variability under pilot-scale conditions. Experimental data from two batches are used to model viscosity at 1, 10, and 100 1/s using four inputs: formulation, dispersant type, solid content percent, and solid dispersant percent. Linear baselines (ordinary least squares and ridge) are evaluated alongside tree ensembles and neural architectures, under identical splits and preprocessing. Results show consistent performance gains from transfer learning across all shear rates, with higher R2 and lower MAE and RMSE relative to no-transfer training. Across models, differences in backbone choice are secondary; the transfer step is the principal driver of improvement under the present data regime. Uncertainty is quantified using split-conformal prediction intervals, yielding nominal 90 percent coverage with narrower intervals after transfer learning. Small-data design choices are reported, including balanced splits and sensitivity checks with conservative augmentation used only for analysis. The findings indicate a practical and data-efficient route to viscosity prediction under sequential batches, supporting more robust model deployment in pilot-scale manufacturing.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100661"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680992","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-10-01DOI: 10.1016/j.egyai.2025.100627
Yuxuan Chen, Shuo Dai, Ruoyi Xu, Haipeng Xie, Yao Zhang
Anomaly detection is crucial for data-driven applications in integrated energy systems. Traditional anomaly detection methods primarily focus on one single energy load, often neglecting potential spatial correlations between multivariate energy time series. Meanwhile, addressing the imbalanced nature of user-level multi-energy load data remains a significant challenge. In this paper, we propose EGBAD, an Ensemble Graph-Boosted Anomaly Detection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning. First, a dynamic graph construction method based on multidimensional scaling (MDS) is proposed to transform multi-energy load data into graph representations. These graphs are subsequently processed using graph convolutional network (GCN) to capture the spatiotemporal correlations between multi-energy load time series. In addition, to improve detection robustness under class imbalance, the entire training process is embedded within a Boosting ensemble learning framework, where the weight assigned to the minority class is progressively increased at each boosting stage. Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods. Notably, it performs especially well in scenarios characterized by extreme data imbalance, achieving the highest recall and F1-score for anomaly detection.
{"title":"EGBAD: Ensemble graph-boosted anomaly detection for user-level multi-energy load data","authors":"Yuxuan Chen, Shuo Dai, Ruoyi Xu, Haipeng Xie, Yao Zhang","doi":"10.1016/j.egyai.2025.100627","DOIUrl":"10.1016/j.egyai.2025.100627","url":null,"abstract":"<div><div>Anomaly detection is crucial for data-driven applications in integrated energy systems. Traditional anomaly detection methods primarily focus on one single energy load, often neglecting potential spatial correlations between multivariate energy time series. Meanwhile, addressing the imbalanced nature of user-level multi-energy load data remains a significant challenge. In this paper, we propose EGBAD, an <strong>E</strong>nsemble <strong>G</strong>raph-<strong>B</strong>oosted <strong>A</strong>nomaly <strong>D</strong>etection framework for user-level multi-energy load that leverages the advantages of graph relational analysis and ensemble learning. First, a dynamic graph construction method based on multidimensional scaling (MDS) is proposed to transform multi-energy load data into graph representations. These graphs are subsequently processed using graph convolutional network (GCN) to capture the spatiotemporal correlations between multi-energy load time series. In addition, to improve detection robustness under class imbalance, the entire training process is embedded within a Boosting ensemble learning framework, where the weight assigned to the minority class is progressively increased at each boosting stage. Experimental results on publicly real-world datasets demonstrate that the proposed model achieves superior anomaly detection accuracy compared to most baseline methods. Notably, it performs especially well in scenarios characterized by extreme data imbalance, achieving the highest recall and F1-score for anomaly detection.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100627"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219587","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-11-28DOI: 10.1016/j.egyai.2025.100654
Keqi Chen , Tianshuai Pei , Lina Yang , Thomas Wu , Yunxuan Dong
Short-term offshore wind power forecasting is crucial for stable power system operations. However, accurate forecasting is hindered by multivariate interactions that generate multi-scale repetitive patterns and obscure cross-variate correlations. In this paper, we propose a hierarchical framework, the Time–Frequency Clustering Inverted Transformer, for multivariate offshore wind power forecasting. First, a Time–Frequency Clustering component applies Wavelet Packet Decomposition to each series and quantifies sub-series similarity by overall activity and evolutionary trend, grouping repetitive patterns into structured clusters. Second, an inverted Transformer captures multivariate correlations within clusters by treating time points of individual sub-series as variate tokens, enabling self-attention to focus on multivariate correlations rather than temporal dependencies. On two real-world offshore wind datasets (horizons 8–48 h), our proposed framework reduces MSE/MAE by 14.11% and outperforms 12 recognised baselines (e.g., PatchTST, TimesNet), with the advantage persisting even when the TFC component is applied to the baselines. Moreover, our method demonstrates remarkable generalisability on three public datasets (Solar-Energy, Traffic, and ECL), reducing MSE/MAE by 7.36%. These results indicate that associating repetitive patterns with attention to cross-variate structure materially improves multivariate offshore wind power forecasting.
{"title":"A novel method for multivariate short-term offshore wind forecasting via time–frequency clustering and inverted attention","authors":"Keqi Chen , Tianshuai Pei , Lina Yang , Thomas Wu , Yunxuan Dong","doi":"10.1016/j.egyai.2025.100654","DOIUrl":"10.1016/j.egyai.2025.100654","url":null,"abstract":"<div><div>Short-term offshore wind power forecasting is crucial for stable power system operations. However, accurate forecasting is hindered by multivariate interactions that generate multi-scale repetitive patterns and obscure cross-variate correlations. In this paper, we propose a hierarchical framework, the Time–Frequency Clustering Inverted Transformer, for multivariate offshore wind power forecasting. First, a Time–Frequency Clustering component applies Wavelet Packet Decomposition to each series and quantifies sub-series similarity by overall activity and evolutionary trend, grouping repetitive patterns into structured clusters. Second, an inverted Transformer captures multivariate correlations within clusters by treating time points of individual sub-series as variate tokens, enabling self-attention to focus on multivariate correlations rather than temporal dependencies. On two real-world offshore wind datasets (horizons 8–48 h), our proposed framework reduces MSE/MAE by 14.11% and outperforms 12 recognised baselines (e.g., PatchTST, TimesNet), with the advantage persisting even when the TFC component is applied to the baselines. Moreover, our method demonstrates remarkable generalisability on three public datasets (Solar-Energy, Traffic, and ECL), reducing MSE/MAE by 7.36%. These results indicate that associating repetitive patterns with attention to cross-variate structure materially improves multivariate offshore wind power forecasting.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100654"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680875","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-12-02DOI: 10.1016/j.egyai.2025.100647
Amir Ali Panahi , Daniel Luder , Billy Wu , Gregory Offer , Dirk Uwe Sauer , Weihan Li
Digital twins of lithium-ion batteries are increasingly used to enable predictive monitoring, control, and design at system scale. Increasing their capabilities involves improving their physical fidelity while maintaining sub-millisecond computational speed. In this work, we introduce machine learning surrogates that learn physical dynamics. Specifically, we benchmark three operator-learning surrogates for the Single Particle Model (SPM): Deep Operator Networks (DeepONets), Fourier Neural Operators (FNOs) and a newly proposed parameter-embedded Fourier Neural Operator (PE-FNO), which conditions each spectral layer on particle radius and solid-phase diffusivity. We extend the comparison to classical machine-learning baselines by including U-Nets. Models are trained on simulated trajectories spanning four current families (constant, triangular, pulse-train, and Gaussian-random-field) and a full range of State-of-Charge (SOC) (0 % to 100 %). DeepONet accurately replicates constant-current behaviour but struggles with more dynamic loads. The basic FNO maintains mesh invariance and keeps concentration errors below 1 %, with voltage mean-absolute errors under 1.7 mV across all load types. Introducing parameter embedding marginally increases error but enables generalisation to varying radii and diffusivities. PE-FNO executes approximately 200 times faster than a 16-thread SPM solver. Consequently, PE-FNO’s capabilities in inverse tasks are explored in a parameter estimation task with Bayesian optimisation, recovering anode and cathode diffusivities with 1.14 % and 8.4 % mean absolute percentage error, respectively, and 0.5918 percentage points higher error in comparison with classical methods. These results pave the way for neural operators to meet the accuracy, speed and parametric flexibility demands of real-time battery management, design-of-experiments and large-scale inference. PE-FNO outperforms conventional neural surrogates, offering a practical path towards high-speed and high-fidelity electrochemical digital twins.
{"title":"Fast and generalisable parameter-embedded neural operators for lithium-ion battery simulation","authors":"Amir Ali Panahi , Daniel Luder , Billy Wu , Gregory Offer , Dirk Uwe Sauer , Weihan Li","doi":"10.1016/j.egyai.2025.100647","DOIUrl":"10.1016/j.egyai.2025.100647","url":null,"abstract":"<div><div>Digital twins of lithium-ion batteries are increasingly used to enable predictive monitoring, control, and design at system scale. Increasing their capabilities involves improving their physical fidelity while maintaining sub-millisecond computational speed. In this work, we introduce machine learning surrogates that learn physical dynamics. Specifically, we benchmark three operator-learning surrogates for the Single Particle Model (SPM): Deep Operator Networks (DeepONets), Fourier Neural Operators (FNOs) and a newly proposed parameter-embedded Fourier Neural Operator (PE-FNO), which conditions each spectral layer on particle radius and solid-phase diffusivity. We extend the comparison to classical machine-learning baselines by including U-Nets. Models are trained on simulated trajectories spanning four current families (constant, triangular, pulse-train, and Gaussian-random-field) and a full range of State-of-Charge (SOC) (0<!--> <!-->% to 100<!--> <!-->%). DeepONet accurately replicates constant-current behaviour but struggles with more dynamic loads. The basic FNO maintains mesh invariance and keeps concentration errors below 1<!--> <!-->%, with voltage mean-absolute errors under 1.7<!--> <!-->mV across all load types. Introducing parameter embedding marginally increases error but enables generalisation to varying radii and diffusivities. PE-FNO executes approximately 200 times faster than a 16-thread SPM solver. Consequently, PE-FNO’s capabilities in inverse tasks are explored in a parameter estimation task with Bayesian optimisation, recovering anode and cathode diffusivities with 1.14<!--> <!-->% and 8.4<!--> <!-->% mean absolute percentage error, respectively, and 0.5918 percentage points higher error in comparison with classical methods. These results pave the way for neural operators to meet the accuracy, speed and parametric flexibility demands of real-time battery management, design-of-experiments and large-scale inference. PE-FNO outperforms conventional neural surrogates, offering a practical path towards high-speed and high-fidelity electrochemical digital twins.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100647"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-09-02DOI: 10.1016/j.egyai.2025.100611
Wenjun Guo , Renkang Wang , Yu Qiu , Linhong Wu , Kai Li , Hao Tang
The anode pressure control in proton exchange membrane fuel cells (PEMFCs) significantly influences the stable operation of the hydrogen supply system and the internal gas circulation within the fuel cell. An efficient anode pressure control strategy is imperative for enhancing the overall system efficiency and mitigating lifespan degradation. Effective anode pressure control can prevent hydrogen starvation and instability in output performance under rapid load changes and purge disturbances. Fuzzy control has been extensively employed in anode pressure control studies. However, creating fuzzy rules in the control parameter’s tuning process in existing studies is predominantly dependent on expert knowledge, resulting in concerns about control accuracy. This study investigates the potential of employing the whale optimization algorithm to optimize the selection of fuzzy parameters. We first developed a control-oriented model to address the nonlinearity, coupling, and uncertainty in the hydrogen supply system. Then, based on the model and considering load variations and purge disturbances, we integrated feedforward compensation and fuzzy control into the conventional Proportional-Integral (PI) controller to suppress input disturbances, enhance control accuracy, and reduce the pressure response lag. Finally, an innovative fuzzy PI controller with the whale optimization algorithm is proposed to optimize the fuzzy parameter selection, thereby achieving precise anode pressure control. Simulation tests demonstrate that the whale-optimization-based fuzzy PI control (WFLPIF) reduces a root mean square error by 14.3 % (0.636 vs. 0.742) and a mean absolute percentage error by 28.8 % (0.037 vs. 0.052) compared to conventional PI control, while also outperforming feedforward-compensated fuzzy PI control (FLPIF) by 9.5 % in RMSE and 17.8 % in MAPE. This study substantiates the efficacy of the whale optimization algorithm in addressing the anode pressure stability control challenge of fuel cell hydrogen supply systems.
质子交换膜燃料电池（pemfc）的阳极压力控制对供氢系统的稳定运行和燃料电池内部气体循环有着重要的影响。有效的阳极压力控制策略对于提高系统整体效率和减少寿命退化是必不可少的。有效的阳极压力控制可以防止在负载快速变化和吹扫干扰下的氢饥饿和输出性能不稳定。模糊控制在阳极压力控制研究中得到了广泛应用。然而，在现有的研究中，在控制参数整定过程中模糊规则的创建主要依赖于专家知识，导致对控制精度的担忧。本研究探讨了采用鲸鱼优化算法优化模糊参数选择的潜力。我们首先开发了一个面向控制的模型来解决氢供应系统中的非线性、耦合和不确定性。然后，在此基础上，考虑负载变化和吹扫干扰，将前馈补偿和模糊控制集成到传统的比例积分（PI）控制器中，以抑制输入干扰，提高控制精度，减小压力响应滞后。最后，提出了一种创新的模糊PI控制器，采用鲸鱼优化算法对模糊参数选择进行优化，从而实现精确的阳极压力控制。仿真测试表明，与传统PI控制相比，基于鲸鱼优化的模糊PI控制（WFLPIF）的均方根误差降低了14.3% (0.636 vs. 0.742)，平均绝对百分比误差降低了28.8% (0.037 vs. 0.052)，同时在RMSE和MAPE方面也优于前馈补偿模糊PI控制（FLPIF） 9.5%和17.8%。本研究证实了鲸鱼优化算法在解决燃料电池供氢系统阳极压力稳定性控制挑战方面的有效性。
{"title":"Whale algorithm optimized anode pressure controller for fuel cell systems in ejector recirculation mode","authors":"Wenjun Guo , Renkang Wang , Yu Qiu , Linhong Wu , Kai Li , Hao Tang","doi":"10.1016/j.egyai.2025.100611","DOIUrl":"10.1016/j.egyai.2025.100611","url":null,"abstract":"<div><div>The anode pressure control in proton exchange membrane fuel cells (PEMFCs) significantly influences the stable operation of the hydrogen supply system and the internal gas circulation within the fuel cell. An efficient anode pressure control strategy is imperative for enhancing the overall system efficiency and mitigating lifespan degradation. Effective anode pressure control can prevent hydrogen starvation and instability in output performance under rapid load changes and purge disturbances. Fuzzy control has been extensively employed in anode pressure control studies. However, creating fuzzy rules in the control parameter’s tuning process in existing studies is predominantly dependent on expert knowledge, resulting in concerns about control accuracy. This study investigates the potential of employing the whale optimization algorithm to optimize the selection of fuzzy parameters. We first developed a control-oriented model to address the nonlinearity, coupling, and uncertainty in the hydrogen supply system. Then, based on the model and considering load variations and purge disturbances, we integrated feedforward compensation and fuzzy control into the conventional Proportional-Integral (PI) controller to suppress input disturbances, enhance control accuracy, and reduce the pressure response lag. Finally, an innovative fuzzy PI controller with the whale optimization algorithm is proposed to optimize the fuzzy parameter selection, thereby achieving precise anode pressure control. Simulation tests demonstrate that the whale-optimization-based fuzzy PI control (WFLPIF) reduces a root mean square error by 14.3 % (0.636 vs. 0.742) and a mean absolute percentage error by 28.8 % (0.037 vs. 0.052) compared to conventional PI control, while also outperforming feedforward-compensated fuzzy PI control (FLPIF) by 9.5 % in RMSE and 17.8 % in MAPE. This study substantiates the efficacy of the whale optimization algorithm in addressing the anode pressure stability control challenge of fuel cell hydrogen supply systems.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100611"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007631","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-08-26DOI: 10.1016/j.egyai.2025.100591
Binye Ni , Xinlei Cai , Zhijun Shen , Zijie Meng , Junhua Zhao , Yuheng Cheng , Xuanang Gui
The increasing complexity of modern power systems, driven by factors such as the large-scale integration of renewable energy and the proliferation of distributed generation, has placed unprecedented demands on power dispatching operations. Ensuring grid stability and safety in this new environment requires real-time monitoring and swift, data-driven decision-making. Consequently, efficient and accurate data querying capabilities have become paramount. This study introduces Intelli-Dispatch-SQL, a novel agent-based Text-to-SQL framework that leverages the Large Language Model (LLM) to enhance the accuracy and reliability of generated SQL queries in the context of power dispatching. By integrating intent recognition and SQL validation modules, Intelli-Dispatch-SQL ensures that generated queries are not only syntactically correct but also semantically aligned with user intent and executable within the operational context. Through comprehensive experiments, including ablation studies and cross-model evaluations, we demonstrate that Intelli-Dispatch-SQL significantly outperforms existing Text-to-SQL models, achieving substantial improvements in both Exact Match (EM) and Execution Accuracy (EX). Notably, the incorporation of intent recognition and SQL validation modules is shown to be critical for performance enhancement. The framework’s effectiveness was further validated across various LLMs, confirming its robustness and applicability across diverse scenarios. Intelli-Dispatch-SQL offers a high-performance and generalizable solution for Text-to-SQL in power dispatching, paving the way for more efficient and intelligent power system management.
{"title":"Intelli-Dispatch-SQL: An LLM-based agent for reliable Text-to-SQL in power dispatching","authors":"Binye Ni , Xinlei Cai , Zhijun Shen , Zijie Meng , Junhua Zhao , Yuheng Cheng , Xuanang Gui","doi":"10.1016/j.egyai.2025.100591","DOIUrl":"10.1016/j.egyai.2025.100591","url":null,"abstract":"<div><div>The increasing complexity of modern power systems, driven by factors such as the large-scale integration of renewable energy and the proliferation of distributed generation, has placed unprecedented demands on power dispatching operations. Ensuring grid stability and safety in this new environment requires real-time monitoring and swift, data-driven decision-making. Consequently, efficient and accurate data querying capabilities have become paramount. This study introduces Intelli-Dispatch-SQL, a novel agent-based Text-to-SQL framework that leverages the Large Language Model (LLM) to enhance the accuracy and reliability of generated SQL queries in the context of power dispatching. By integrating intent recognition and SQL validation modules, Intelli-Dispatch-SQL ensures that generated queries are not only syntactically correct but also semantically aligned with user intent and executable within the operational context. Through comprehensive experiments, including ablation studies and cross-model evaluations, we demonstrate that Intelli-Dispatch-SQL significantly outperforms existing Text-to-SQL models, achieving substantial improvements in both Exact Match (EM) and Execution Accuracy (EX). Notably, the incorporation of intent recognition and SQL validation modules is shown to be critical for performance enhancement. The framework’s effectiveness was further validated across various LLMs, confirming its robustness and applicability across diverse scenarios. Intelli-Dispatch-SQL offers a high-performance and generalizable solution for Text-to-SQL in power dispatching, paving the way for more efficient and intelligent power system management.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100591"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144908072","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-10-17DOI: 10.1016/j.egyai.2025.100632
Yang Bai , Chen Yang , Mao Li , Pingya Luo , Haochen Han
Accurate identification and prediction of lost circulation (LC) are critical for ensuring drilling safety and reducing production costs. Traditional LC detection methods rely heavily on expert knowledge, which inherently suffers from limitations such as subjective bias, low operational efficiency, and insufficient precision. In this context, data-driven prediction approaches have shown promising potential. This study develops a novel LC risk prediction framework that integrates transfer learning with deep learning. By leveraging the mud pit volume from acquired drilling parameters and defining three distinct step intervals, LC risk categories were efficiently labeled. An optimized LSTM-based predictive architecture was constructed using three distribution-alignment transfer learning techniques. Comparative experiments under varying numbers of input features confirmed the effectiveness of transfer learning in improving LC prediction performance. To address the class imbalance issue commonly observed in LC risk prediction, a delayed matching verification (DMV) strategy—customized for drilling operations—was introduced. This method mitigates the impact of class imbalance and enhances the evaluation of LC risk recognition capabilities. Experimental results from five test wells demonstrate that the proposed method can effectively label LC risk categories and promptly identify risk types, thereby offering valuable insights to support safe and efficient drilling operations.
{"title":"A method for lost circulation risk identification: Labeling, LSTM transfer learning recognition, and delayed matching verification","authors":"Yang Bai , Chen Yang , Mao Li , Pingya Luo , Haochen Han","doi":"10.1016/j.egyai.2025.100632","DOIUrl":"10.1016/j.egyai.2025.100632","url":null,"abstract":"<div><div>Accurate identification and prediction of lost circulation (LC) are critical for ensuring drilling safety and reducing production costs. Traditional LC detection methods rely heavily on expert knowledge, which inherently suffers from limitations such as subjective bias, low operational efficiency, and insufficient precision. In this context, data-driven prediction approaches have shown promising potential. This study develops a novel LC risk prediction framework that integrates transfer learning with deep learning. By leveraging the mud pit volume from acquired drilling parameters and defining three distinct step intervals, LC risk categories were efficiently labeled. An optimized LSTM-based predictive architecture was constructed using three distribution-alignment transfer learning techniques. Comparative experiments under varying numbers of input features confirmed the effectiveness of transfer learning in improving LC prediction performance. To address the class imbalance issue commonly observed in LC risk prediction, a delayed matching verification (DMV) strategy—customized for drilling operations—was introduced. This method mitigates the impact of class imbalance and enhances the evaluation of LC risk recognition capabilities. Experimental results from five test wells demonstrate that the proposed method can effectively label LC risk categories and promptly identify risk types, thereby offering valuable insights to support safe and efficient drilling operations.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100632"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145362269","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-09-10DOI: 10.1016/j.egyai.2025.100608
Andrea Gayon-Lombardo , Ehecatl A. del Rio-Chanona , Catalina A. Pino-Muñoz , Nigel P. Brandon
The generation of multiphase porous electrode microstructures with optimum morphological and transport properties is essential in the design of improved electrochemical energy storage devices, such as lithium-ion batteries. Electrode characteristics directly influence battery performance by acting as the main sites where the electrochemical reactions coupled with transport processes occur. This work presents a generation-optimisation closed-loop algorithm for the design of microstructures with tailored properties. A deep convolutional Generative Adversarial Network is used as a deep kernel and employed to generate synthetic three-phase three-dimensional images of a porous lithium-ion battery cathode material. A Gaussian Process Regression uses the latent space of the generator and serves as a surrogate model to correlate the morphological and transport properties of the synthetic microstructures. This surrogate model is integrated into a deep kernel Bayesian optimisation framework, which optimises cathode properties as a function of the latent space of the generator. A set of objective functions were defined to perform the maximisation of morphological properties (e.g., volume fraction, specific surface area) and transport properties (relative diffusivity). We demonstrate the ability to perform simultaneous maximisation of correlated properties (specific surface area and relative diffusivity), as well as constrained optimisation of these properties. This is the maximisation of morphological or transport properties constrained by constant values of the volume fraction of the phase of interest. Visualising the optimised latent space reveals its correlation with morphological properties, enabling the fast generation of visually realistic microstructures with customised properties.
{"title":"Deep kernel Bayesian optimisation for closed-loop electrode microstructure design with user-defined properties","authors":"Andrea Gayon-Lombardo , Ehecatl A. del Rio-Chanona , Catalina A. Pino-Muñoz , Nigel P. Brandon","doi":"10.1016/j.egyai.2025.100608","DOIUrl":"10.1016/j.egyai.2025.100608","url":null,"abstract":"<div><div>The generation of multiphase porous electrode microstructures with optimum morphological and transport properties is essential in the design of improved electrochemical energy storage devices, such as lithium-ion batteries. Electrode characteristics directly influence battery performance by acting as the main sites where the electrochemical reactions coupled with transport processes occur. This work presents a generation-optimisation closed-loop algorithm for the design of microstructures with tailored properties. A deep convolutional Generative Adversarial Network is used as a deep kernel and employed to generate synthetic three-phase three-dimensional images of a porous lithium-ion battery cathode material. A Gaussian Process Regression uses the latent space of the generator and serves as a surrogate model to correlate the morphological and transport properties of the synthetic microstructures. This surrogate model is integrated into a deep kernel Bayesian optimisation framework, which optimises cathode properties as a function of the latent space of the generator. A set of objective functions were defined to perform the maximisation of morphological properties (e.g., volume fraction, specific surface area) and transport properties (relative diffusivity). We demonstrate the ability to perform simultaneous maximisation of correlated properties (specific surface area and relative diffusivity), as well as constrained optimisation of these properties. This is the maximisation of morphological or transport properties constrained by constant values of the volume fraction of the phase of interest. Visualising the optimised latent space reveals its correlation with morphological properties, enabling the fast generation of visually realistic microstructures with customised properties.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100608"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145096068","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Federated learning (FL) is essential to energy transition as it leverages decentralized energy data and machine learning to collaborative train global energy predictive models across distributed energy resources while preserving data privacy. This paper introduces one of the first FL frameworks that efficiently integrates swarm intelligence-based aggregation methods to large-scale energy consumption forecasting, by extending the TensorFlow Federated Core framework with specialized functional enhancements. The primary objective is to enhance forecasting accuracy in decentralized learning settings. We investigated the effectiveness of various nature-inspired metaheuristics for optimizing the aggregation of local model updates from distributed energy resource nodes into a global model for load forecasting tasks, including Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Firefly Algorithm (FFA) against the standard Federated Averaging (FedAvg) algorithm. Using a real-world dataset comprising of 4,438 distinct energy consumers, we demonstrate that metaheuristic aggregators consistently outperform the most well-known method, Federated Averaging in predictive accuracy. Among these approaches, GWO emerges as the superior performer achieving up to 23.6% error reduction. Our findings underscore the significant potential of metaheuristic-based aggregation mechanisms in improving FL outcomes, particularly in energy forecasting applications involving large-scale distributed data scenarios.
{"title":"Meta-heuristic federated learning aggregation methods for load forecasting","authors":"Efstathios Sarantinopoulos , Vasilis Michalakopoulos , Elissaios Sarmas , Vangelis Marinakis , Liana Toderean , Tudor Cioara","doi":"10.1016/j.egyai.2025.100594","DOIUrl":"10.1016/j.egyai.2025.100594","url":null,"abstract":"<div><div>Federated learning (FL) is essential to energy transition as it leverages decentralized energy data and machine learning to collaborative train global energy predictive models across distributed energy resources while preserving data privacy. This paper introduces one of the first FL frameworks that efficiently integrates swarm intelligence-based aggregation methods to large-scale energy consumption forecasting, by extending the TensorFlow Federated Core framework with specialized functional enhancements. The primary objective is to enhance forecasting accuracy in decentralized learning settings. We investigated the effectiveness of various nature-inspired metaheuristics for optimizing the aggregation of local model updates from distributed energy resource nodes into a global model for load forecasting tasks, including Grey Wolf Optimization (GWO), Particle Swarm Optimization (PSO), and Firefly Algorithm (FFA) against the standard Federated Averaging (FedAvg) algorithm. Using a real-world dataset comprising of 4,438 distinct energy consumers, we demonstrate that metaheuristic aggregators consistently outperform the most well-known method, Federated Averaging in predictive accuracy. Among these approaches, GWO emerges as the superior performer achieving up to 23.6% error reduction. Our findings underscore the significant potential of metaheuristic-based aggregation mechanisms in improving FL outcomes, particularly in energy forecasting applications involving large-scale distributed data scenarios.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100594"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145007633","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-12-01Epub Date: 2025-11-29DOI: 10.1016/j.egyai.2025.100653
Manuel Sage , Khalil Al Handawi , Yaoyao Fiona Zhao
This study introduces a novel deep reinforcement learning (DRL) framework for the joint dispatch of Gas Turbines (GTs) and Battery Energy Storage Systems (BESs) in microgrids that face the variability of renewable energy sources and demands. BESs can store surplus renewable energy for nearly instantaneous use, while GTs offer sustained energy output over longer periods, offering complementary benefits. Previous studies often oversimplified GT operations, neglecting critical factors such as ramp-up times and increased degradation from frequent starts. This research addresses these gaps by proposing an advanced modeling framework that accurately captures the dynamic interaction between GTs and BESs, including GT ramp-up times and maintenance costs associated with operational cycles. Through extensive case studies involving diverse microgrid configurations, we demonstrate that DRL effectively learns dispatch policies directly from historical data, outperforming traditional optimization techniques. Deploying DRL to our framework yields more realistic dispatch policies, reducing GT maintenance costs by avoiding frequent starts. The proposed framework has significant potential to improve energy management strategies and to streamline the planning of hybrid energy systems. To encourage further research, we have released our codebase to the public, enabling the scientific community to build upon our findings.
{"title":"Deep reinforcement learning for joint dispatch of battery storage and gas turbines in renewable-powered microgrids","authors":"Manuel Sage , Khalil Al Handawi , Yaoyao Fiona Zhao","doi":"10.1016/j.egyai.2025.100653","DOIUrl":"10.1016/j.egyai.2025.100653","url":null,"abstract":"<div><div>This study introduces a novel deep reinforcement learning (DRL) framework for the joint dispatch of Gas Turbines (GTs) and Battery Energy Storage Systems (BESs) in microgrids that face the variability of renewable energy sources and demands. BESs can store surplus renewable energy for nearly instantaneous use, while GTs offer sustained energy output over longer periods, offering complementary benefits. Previous studies often oversimplified GT operations, neglecting critical factors such as ramp-up times and increased degradation from frequent starts. This research addresses these gaps by proposing an advanced modeling framework that accurately captures the dynamic interaction between GTs and BESs, including GT ramp-up times and maintenance costs associated with operational cycles. Through extensive case studies involving diverse microgrid configurations, we demonstrate that DRL effectively learns dispatch policies directly from historical data, outperforming traditional optimization techniques. Deploying DRL to our framework yields more realistic dispatch policies, reducing GT maintenance costs by avoiding frequent starts. The proposed framework has significant potential to improve energy management strategies and to streamline the planning of hybrid energy systems. To encourage further research, we have released our codebase to the public, enabling the scientific community to build upon our findings.</div></div>","PeriodicalId":34138,"journal":{"name":"Energy and AI","volume":"22 ","pages":"Article 100653"},"PeriodicalIF":9.6,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145680874","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号