Pub Date : 2025-03-28DOI: 10.1016/j.geits.2025.100308
Vijay Muniyandi , V Kumar Reddy Majji , Manam Ravindra , Ramesh Adireddy , Ashok Kumar Balasubramanian
Solar irradiance (SI) forecasting and determination of optimum tilt angle (OTA) of photovoltaic (PV) panels are the key strategies for improving the power output of PV systems. Precise SI forecasting offer valuable information regarding the predictable accessibility of solar energy, empowering PV system operators to make informed decisions for PV system optimization. This research uses a bi-directional long short-term memory (Bi-LSTM) hybrid network to forecast SI. Then, the OTA of the PV module is estimated by applying the forecasted SI data to the ASHRAE (American Society of Heating, Refrigerating and Air-conditioning Engineers) SI model. The performance of the Bi-LSTM hybrid network to estimate SI is compared with the observed data and the other existing forecasting models in the literature. The impact of OTA in improving PV power output is evaluated by comparing the solar irradiance received on both tilted and horizontal surfaces. This work has been experimentally implemented using the PV module setup at Thiagarajar College of Engineering, Madurai, Tamil Nadu, India. The OTA obtained by the proposed method yielded an increased output PV power compared to all other tilt angle approaches in the literature.
{"title":"Feature selection-based irradiance forecast for efficient operation of a stand-alone PV system","authors":"Vijay Muniyandi , V Kumar Reddy Majji , Manam Ravindra , Ramesh Adireddy , Ashok Kumar Balasubramanian","doi":"10.1016/j.geits.2025.100308","DOIUrl":"10.1016/j.geits.2025.100308","url":null,"abstract":"<div><div>Solar irradiance (SI) forecasting and determination of optimum tilt angle (OTA) of photovoltaic (PV) panels are the key strategies for improving the power output of PV systems. Precise SI forecasting offer valuable information regarding the predictable accessibility of solar energy, empowering PV system operators to make informed decisions for PV system optimization. This research uses a bi-directional long short-term memory (Bi-LSTM) hybrid network to forecast SI. Then, the OTA of the PV module is estimated by applying the forecasted SI data to the ASHRAE (American Society of Heating, Refrigerating and Air-conditioning Engineers) SI model. The performance of the Bi-LSTM hybrid network to estimate SI is compared with the observed data and the other existing forecasting models in the literature. The impact of OTA in improving PV power output is evaluated by comparing the solar irradiance received on both tilted and horizontal surfaces. This work has been experimentally implemented using the PV module setup at Thiagarajar College of Engineering, Madurai, Tamil Nadu, India. The OTA obtained by the proposed method yielded an increased output PV power compared to all other tilt angle approaches in the literature.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 2","pages":"Article 100308"},"PeriodicalIF":16.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145979166","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 : 2025-03-28DOI: 10.1016/j.geits.2025.100295
Hao Yu , Amit Adhikari , Xu Sun , Wei Deng Solvang , Mi Gan , Nezir Aydin
As one of the most substantial contributors to the rapidly increasing carbon emissions, the greening and decarbonization of the transportation and logistics sectors are essential. In this context, electric trucks (E-trucks) have garnered global interest due to their potential to significantly reduce tailpipe emissions in the freight transport sector. However, inadequate charging infrastructure is a substantial barrier to the widespread adoption of E-trucks. This paper investigates a charging infrastructure development model led by an industry cluster in order to better meet the emission target. To this end, a new optimization model is formulated for a joint logistics-and-charging-infrastructure network design problem. The model aims to minimize the total cost of operating the logistics system and charging infrastructure network while simultaneously ensuring accessibility to charging stations. Numerical experiments based on a case study in Nepal were conducted to validate the proposed optimization model. The results demonstrate potential reductions of up to 33.3% in total logistics costs and 55.9% in emissions related to transportation through the transition to electric power. This analysis highlights the economic viability and environmental benefits of adopting E-trucks in green logistics and transportation, supported by an industry-spearheaded business model for developing charging infrastructure.
{"title":"Can electric trucks be a viable green logistics and transportation solution? Modeling a joint logistics-and-charging-infrastructure network design problem","authors":"Hao Yu , Amit Adhikari , Xu Sun , Wei Deng Solvang , Mi Gan , Nezir Aydin","doi":"10.1016/j.geits.2025.100295","DOIUrl":"10.1016/j.geits.2025.100295","url":null,"abstract":"<div><div>As one of the most substantial contributors to the rapidly increasing carbon emissions, the greening and decarbonization of the transportation and logistics sectors are essential. In this context, electric trucks (E-trucks) have garnered global interest due to their potential to significantly reduce tailpipe emissions in the freight transport sector. However, inadequate charging infrastructure is a substantial barrier to the widespread adoption of E-trucks. This paper investigates a charging infrastructure development model led by an industry cluster in order to better meet the emission target. To this end, a new optimization model is formulated for a joint logistics-and-charging-infrastructure network design problem. The model aims to minimize the total cost of operating the logistics system and charging infrastructure network while simultaneously ensuring accessibility to charging stations. Numerical experiments based on a case study in Nepal were conducted to validate the proposed optimization model. The results demonstrate potential reductions of up to 33.3% in total logistics costs and 55.9% in emissions related to transportation through the transition to electric power. This analysis highlights the economic viability and environmental benefits of adopting E-trucks in green logistics and transportation, supported by an industry-spearheaded business model for developing charging infrastructure.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100295"},"PeriodicalIF":16.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685435","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 : 2025-03-28DOI: 10.1016/j.geits.2025.100307
Baokun Zhang , Junjun Deng , Mengchen Duan , Chang Li , Yi Zheng , Shuo Wang , David Dorrell
The rapid growth of electric vehicle ownership and advancements in vehicle-to-grid (V2G) technologies have created an urgent demand for bidirectional charging–discharging interfaces. Wireless power transfer (WPT) technology, known for its convenience, safety, and flexibility, is a promising solution for energy transfer between vehicles and the grid. This paper presents the design and demonstration of a highly interoperable and high-efficiency bidirectional WPT system, addressing key challenges such as wide voltage output adaptation, multi-power level compatibility, and efficient operation over a broad power range. The front-end converter uses a power module combining a three-phase fully controlled rectifier and a cascaded buck converter to provide a wide DC voltage range. Modular activation technology ensures the grid interface operates efficiently under varying power demands. For the bidirectional inductive power transfer (BIPT) link, an integrated scheme for the resonant networks in the ground assembly (GA) with cross-frequency compatibility is proposed, and its performance is validated through calculations and simulations. A bidirectional power flow control strategy is implemented, with voltage regulation and operation mode switching as the main method. Experimental results demonstrate interoperability between the same grid-side equipment and different vehicle-side equipment rated at 6, 11, and 30 kW. Under specified operating conditions at the aligned position, the system achieves a grid-to-battery efficiency from 91.7% to 94.3%, and a battery-to-grid efficiency ranging from 89.5% to 93.5%.
{"title":"Design and implementation of interoperable high-efficiency bidirectional wireless power transfer systems for multiple vehicles","authors":"Baokun Zhang , Junjun Deng , Mengchen Duan , Chang Li , Yi Zheng , Shuo Wang , David Dorrell","doi":"10.1016/j.geits.2025.100307","DOIUrl":"10.1016/j.geits.2025.100307","url":null,"abstract":"<div><div>The rapid growth of electric vehicle ownership and advancements in vehicle-to-grid (V2G) technologies have created an urgent demand for bidirectional charging–discharging interfaces. Wireless power transfer (WPT) technology, known for its convenience, safety, and flexibility, is a promising solution for energy transfer between vehicles and the grid. This paper presents the design and demonstration of a highly interoperable and high-efficiency bidirectional WPT system, addressing key challenges such as wide voltage output adaptation, multi-power level compatibility, and efficient operation over a broad power range. The front-end converter uses a power module combining a three-phase fully controlled rectifier and a cascaded buck converter to provide a wide DC voltage range. Modular activation technology ensures the grid interface operates efficiently under varying power demands. For the bidirectional inductive power transfer (BIPT) link, an integrated scheme for the resonant networks in the ground assembly (GA) with cross-frequency compatibility is proposed, and its performance is validated through calculations and simulations. A bidirectional power flow control strategy is implemented, with voltage regulation and operation mode switching as the main method. Experimental results demonstrate interoperability between the same grid-side equipment and different vehicle-side equipment rated at 6, 11, and 30 kW. Under specified operating conditions at the aligned position, the system achieves a grid-to-battery efficiency from 91.7% to 94.3%, and a battery-to-grid efficiency ranging from 89.5% to 93.5%.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 2","pages":"Article 100307"},"PeriodicalIF":16.4,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886235","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 : 2025-03-27DOI: 10.1016/j.geits.2025.100304
Marcelo Forte , Cindy P. Guzman , Alexios Lekidis , Hugo Morais
The continuous growth of electric vehicles (EVs) poses new challenges to power systems planning and operation due to the need to meet society's decarbonization goals. In this context, clustering has emerged as a powerful tool to help understand and categorize the uncertain behavior of EV users and the electric vehicle supply equipment (EVSE) needs. However, previous studies lack empirical European EV charging data and relevance for practical applications.Therefore, to address such issues, this study evaluates different clustering techniques to identify typical EV charging profiles and, mainly, usage flexibility. The defined methodology comprises three major stages: data preprocessing, clustering application, and validation of results. We conduct benchmarking based on EV energy consumption, arrival, and sojourn times, using K-means, Gaussian mixture model, and Hierarchical clustering. This method allows greater applicability to various datasets from different regions, producing more comprehensive profiles that can provide empirical flexibility data in a visual, intuitive, and relevant approach.A use case considering EV charging data from Caltech University and Greece is utilized to test the proposed methods, demonstrating the versatility of our methodology.Specifically, Caltech features highly flexible prolonged charging sessions, while Greece exhibits quick-stay sessions with less flexibility potential. Both contexts offer opportunities to use the available flexibility for coordination with renewable energy sources and help balance the grid. This information unlocks the potential for future studies, enabling distribution system operators and charge point operators to intelligently and successfully integrate EVs into the energy system.
{"title":"Clustering methodologies for flexibility characterization of electric vehicles supply equipment","authors":"Marcelo Forte , Cindy P. Guzman , Alexios Lekidis , Hugo Morais","doi":"10.1016/j.geits.2025.100304","DOIUrl":"10.1016/j.geits.2025.100304","url":null,"abstract":"<div><div>The continuous growth of electric vehicles (EVs) poses new challenges to power systems planning and operation due to the need to meet society's decarbonization goals. In this context, clustering has emerged as a powerful tool to help understand and categorize the uncertain behavior of EV users and the electric vehicle supply equipment (EVSE) needs. However, previous studies lack empirical European EV charging data and relevance for practical applications.Therefore, to address such issues, this study evaluates different clustering techniques to identify typical EV charging profiles and, mainly, usage flexibility. The defined methodology comprises three major stages: data preprocessing, clustering application, and validation of results. We conduct benchmarking based on EV energy consumption, arrival, and sojourn times, using K-means, Gaussian mixture model, and Hierarchical clustering. This method allows greater applicability to various datasets from different regions, producing more comprehensive profiles that can provide empirical flexibility data in a visual, intuitive, and relevant approach.A use case considering EV charging data from Caltech University and Greece is utilized to test the proposed methods, demonstrating the versatility of our methodology.Specifically, Caltech features highly flexible prolonged charging sessions, while Greece exhibits quick-stay sessions with less flexibility potential. Both contexts offer opportunities to use the available flexibility for coordination with renewable energy sources and help balance the grid. This information unlocks the potential for future studies, enabling distribution system operators and charge point operators to intelligently and successfully integrate EVs into the energy system.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100304"},"PeriodicalIF":16.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145584455","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 : 2025-03-27DOI: 10.1016/j.geits.2025.100297
Bingxin Guo , Changjun Xie , Wenchao Zhu , Yang Yang , Hao Li , Yang Li , Hangyu Wu
Accurately predicting the degradation trends of proton exchange membrane fuel cells (PEMFCs) can provide a solid basis for optimizing the control of vehicles and stations based on PEMFCs. However, most prediction methods do not consider factors such as measurement errors from experimental environments and the inherent cognitive uncertainty of the model. These methods can only offer point estimates, lacking credibility. This paper introduces a deep learning prediction framework that combines a bidirectional gated recurrent unit (BiGRU) model with a truncated Bayes by backpropagation through time (TB) algorithm. The TB algorithm reconstructs fixed parameters in the model into probability density distributions, transforming the output from point estimation to interval estimation with probability density distributions. Under dynamic conditions, the TB-BiGRU (truncated Bayes-based bidirectional gated recurrent unit) improves the mean absolute error (MAE) and root mean square error (RMSE) by 37.28% and 36.09%, respectively, compared to the TB-GRU (truncated Bayes-based gated recurrent unit). Compared with TB-GRU and B-GRU (Bayesian gated recurrent unit), TB-BiGRU has significantly improved uncertainty quantification ability. Under different working conditions and noise levels, the prediction accuracy of TB-BiGRU is superior to that of the other seven models, and it exhibits better noise resistance and stability. This method holds greater practical significance compared to other prediction approaches. Additionally, the paper proposes four effective evaluation metrics for uncertainty quantification, providing higher reference value in effectively characterizing the model's prediction accuracy and uncertainty quantification capability.
{"title":"Uncertainty quantification-based framework for predicting degradation trends of proton exchange membrane fuel cell","authors":"Bingxin Guo , Changjun Xie , Wenchao Zhu , Yang Yang , Hao Li , Yang Li , Hangyu Wu","doi":"10.1016/j.geits.2025.100297","DOIUrl":"10.1016/j.geits.2025.100297","url":null,"abstract":"<div><div>Accurately predicting the degradation trends of proton exchange membrane fuel cells (PEMFCs) can provide a solid basis for optimizing the control of vehicles and stations based on PEMFCs. However, most prediction methods do not consider factors such as measurement errors from experimental environments and the inherent cognitive uncertainty of the model. These methods can only offer point estimates, lacking credibility. This paper introduces a deep learning prediction framework that combines a bidirectional gated recurrent unit (BiGRU) model with a truncated Bayes by backpropagation through time (TB) algorithm. The TB algorithm reconstructs fixed parameters in the model into probability density distributions, transforming the output from point estimation to interval estimation with probability density distributions. Under dynamic conditions, the TB-BiGRU (truncated Bayes-based bidirectional gated recurrent unit) improves the mean absolute error (MAE) and root mean square error (RMSE) by 37.28% and 36.09%, respectively, compared to the TB-GRU (truncated Bayes-based gated recurrent unit). Compared with TB-GRU and B-GRU (Bayesian gated recurrent unit), TB-BiGRU has significantly improved uncertainty quantification ability. Under different working conditions and noise levels, the prediction accuracy of TB-BiGRU is superior to that of the other seven models, and it exhibits better noise resistance and stability. This method holds greater practical significance compared to other prediction approaches. Additionally, the paper proposes four effective evaluation metrics for uncertainty quantification, providing higher reference value in effectively characterizing the model's prediction accuracy and uncertainty quantification capability.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 3","pages":"Article 100297"},"PeriodicalIF":16.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145948039","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 : 2025-03-27DOI: 10.1016/j.geits.2025.100299
Meiwen Liu , Junfu Li , Yaxuan Wang , Shilong Guo , Lei Zhao , Zhenbo Wang
Sodium-ion batteries have gained increasing attention due to their advantages, such as abundant raw material reserves and low costs. As a new battery system, the electrochemical and thermal properties of its electrodes and the entire cell, as well as their variations over both short and long periods, still contain many unknowns. Similar to lithium-ion batteries, sodium-ion batteries also experience performance degradation over time. To ensure the long-term, safe, and stable operation of batteries in service, health and safety management are necessary. Modeling and simulation can accurately predict the multi-scale behavior of battery characteristics, and thus, serve as an important theoretical foundation for battery management. Therefore, modeling and simulation of sodium-ion batteries are crucial.
This paper first considers the temperature changes during battery operation and, based on the fundamental working principles of the battery, develops an electrochemical-thermal coupling model by retaining the main physical processes while ignoring secondary processes. Then, to identify and optimize the highly sensitive model parameters, a weighted particle swarm optimization algorithm is used, ensuring that the parameters are valid and reasonable. Finally, to address the differences among individual cells and the uncertainties in the measured data, machine learning algorithms are introduced into battery mechanism modeling. Specifically, a dynamic residual forest model (DRF) for sodium-ion batteries is constructed using random forest and incremental learning algorithms, which iteratively learns from errors to reduce simulation errors in voltage and temperature.
In the DRF model, the random forest algorithm initially performs a preliminary prediction, followed by the use of incremental learning algorithms to correct prediction errors, thereby continuously optimizing the prediction accuracy of battery terminal voltage and temperature. The key feature of this model is its ability to handle real-time data streams, adapt to dynamic changes in data distribution, and reduce the need for retraining on new data, all while maintaining high prediction accuracy. This allows the model to simulate the complex operating conditions during the actual use of the battery. By using the DRF model to correct the outputs of the electrochemical-thermal coupling model, the final predictions of terminal voltage and temperature are obtained. Validation results show that the hybrid model provides better predictions of terminal voltage and temperature for different individual cells with higher accuracy.
{"title":"Modeling and simulation of sodium-ion batteries based on the combination of electrochemical mechanism and machine learning","authors":"Meiwen Liu , Junfu Li , Yaxuan Wang , Shilong Guo , Lei Zhao , Zhenbo Wang","doi":"10.1016/j.geits.2025.100299","DOIUrl":"10.1016/j.geits.2025.100299","url":null,"abstract":"<div><div>Sodium-ion batteries have gained increasing attention due to their advantages, such as abundant raw material reserves and low costs. As a new battery system, the electrochemical and thermal properties of its electrodes and the entire cell, as well as their variations over both short and long periods, still contain many unknowns. Similar to lithium-ion batteries, sodium-ion batteries also experience performance degradation over time. To ensure the long-term, safe, and stable operation of batteries in service, health and safety management are necessary. Modeling and simulation can accurately predict the multi-scale behavior of battery characteristics, and thus, serve as an important theoretical foundation for battery management. Therefore, modeling and simulation of sodium-ion batteries are crucial.</div><div>This paper first considers the temperature changes during battery operation and, based on the fundamental working principles of the battery, develops an electrochemical-thermal coupling model by retaining the main physical processes while ignoring secondary processes. Then, to identify and optimize the highly sensitive model parameters, a weighted particle swarm optimization algorithm is used, ensuring that the parameters are valid and reasonable. Finally, to address the differences among individual cells and the uncertainties in the measured data, machine learning algorithms are introduced into battery mechanism modeling. Specifically, a dynamic residual forest model (DRF) for sodium-ion batteries is constructed using random forest and incremental learning algorithms, which iteratively learns from errors to reduce simulation errors in voltage and temperature.</div><div>In the DRF model, the random forest algorithm initially performs a preliminary prediction, followed by the use of incremental learning algorithms to correct prediction errors, thereby continuously optimizing the prediction accuracy of battery terminal voltage and temperature. The key feature of this model is its ability to handle real-time data streams, adapt to dynamic changes in data distribution, and reduce the need for retraining on new data, all while maintaining high prediction accuracy. This allows the model to simulate the complex operating conditions during the actual use of the battery. By using the DRF model to correct the outputs of the electrochemical-thermal coupling model, the final predictions of terminal voltage and temperature are obtained. Validation results show that the hybrid model provides better predictions of terminal voltage and temperature for different individual cells with higher accuracy.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100299"},"PeriodicalIF":16.4,"publicationDate":"2025-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145618583","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 : 2025-03-26DOI: 10.1016/j.geits.2025.100303
Muhammad Sohaib Zahid , Umar Jamil
Sustainable transportation aims to reduce greenhouse gas emissions and improve air quality. While developed countries focus on transitioning to electric vehicles, undeveloped and some developing countries face challenges due to energy crises and high costs, making immediate adoption difficult. In response to the growing demand for vehicles, automotive industries are encountering diverse challenges, including high initial costs due to the integration of intelligent technologies for enhanced vehicle performance. Concurrently, consumers prioritize vehicles with improved fuel economy, aiming to minimize fuel expenses and mitigate environmental impacts like air pollution. The fuel economy of vehicles depends on different features such as their vehicle class, engine size, cylinders, fuel type and city fuel consumption. In this research work, various Machine Learning (ML) techniques such as Linear Regression (LR), Random Forest Regression (RFR), and Support Vector Regression (SVR) are used to predict the fuel economy of vehicles based on the factors mentioned above. After a comparative study, the RFR demonstrated superior performance compared to other machine learning models, such as LR and SVR, using most of the input features. Specifically, with city fuel consumption (L/(100 km)) as the input, RFR achieved a Mean Squared Error (MSE) of 0.839,4, a Mean Absolute Error (MAE) of 0.66, and an R-Squared (R2) score of 0.984,3 on the 2000–2022 dataset. In comparison, LR resulted in an MSE of 7.375,4, an MAE of 1.754,9, and an R2 score of 0.856,7, while SVR yielded an MSE of 0.976,1, an MAE of 0.69, and an R2 score of 0.981,9. On the validated 2023–2024 dataset, RFR maintained superior performance with an MSE of 0.848,6, an MAE of 0.66, and an R2 score of 0.984,9. In contrast, LR achieved an MSE of 10.504,5, an MAE of 1.950,7, and an R2 score of 0.827,3, whereas SVR obtained an MSE of 1.104,7, an MAE of 0.75, and an R2 score of 0.980,9.
{"title":"Data-driven machine learning techniques for fuel economy prediction in sustainable transportation systems","authors":"Muhammad Sohaib Zahid , Umar Jamil","doi":"10.1016/j.geits.2025.100303","DOIUrl":"10.1016/j.geits.2025.100303","url":null,"abstract":"<div><div>Sustainable transportation aims to reduce greenhouse gas emissions and improve air quality. While developed countries focus on transitioning to electric vehicles, undeveloped and some developing countries face challenges due to energy crises and high costs, making immediate adoption difficult. In response to the growing demand for vehicles, automotive industries are encountering diverse challenges, including high initial costs due to the integration of intelligent technologies for enhanced vehicle performance. Concurrently, consumers prioritize vehicles with improved fuel economy, aiming to minimize fuel expenses and mitigate environmental impacts like air pollution. The fuel economy of vehicles depends on different features such as their vehicle class, engine size, cylinders, fuel type and city fuel consumption. In this research work, various Machine Learning (ML) techniques such as Linear Regression (LR), Random Forest Regression (RFR), and Support Vector Regression (SVR) are used to predict the fuel economy of vehicles based on the factors mentioned above. After a comparative study, the RFR demonstrated superior performance compared to other machine learning models, such as LR and SVR, using most of the input features. Specifically, with city fuel consumption (L/(100 km)) as the input, RFR achieved a Mean Squared Error (MSE) of 0.839,4, a Mean Absolute Error (MAE) of 0.66, and an R-Squared (<em>R</em><sup>2</sup>) score of 0.984,3 on the 2000–2022 dataset. In comparison, LR resulted in an MSE of 7.375,4, an MAE of 1.754,9, and an <em>R</em><sup>2</sup> score of 0.856,7, while SVR yielded an MSE of 0.976,1, an MAE of 0.69, and an <em>R</em><sup>2</sup> score of 0.981,9. On the validated 2023–2024 dataset, RFR maintained superior performance with an MSE of 0.848,6, an MAE of 0.66, and an <em>R</em><sup>2</sup> score of 0.984,9. In contrast, LR achieved an MSE of 10.504,5, an MAE of 1.950,7, and an <em>R</em><sup>2</sup> score of 0.827,3, whereas SVR obtained an MSE of 1.104,7, an MAE of 0.75, and an <em>R</em><sup>2</sup> score of 0.980,9.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100303"},"PeriodicalIF":16.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145584456","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}
Accurate and robust estimation of the State of Charge (SOC) in complex environments is vital to achieving high battery performance, extended lifespan, enhanced safety, and improved user experience. Conventional estimation methods often neglect the impact of temperature on battery during the modeling process. To address this, this paper presents a battery modeling method applicable across a comprehensive temperature range that encompasses all potential operating temperatures. A second-order equivalent circuit model (ECM) is developed for the battery, with parameters defined within a specified temperature range. Furthermore, an adaptive cubature Kalman filter based on an improved minimum error entropy criterion (IMEF-ACKF) is introduced to address the significant accuracy degradation of traditional methods under non-Gaussian noise and substantial outlier interference. The generalized minimum error entropy criterion is combined with the generalized maximum correntropy criterion to replace the traditional minimum mean-square error (MMSE) criterion, addressing the influence of non-Gaussian noise. Then, exponential transformation of system residual is used to mitigate the impact of large outliers, and adaptive filter is incorporated to improve the stability of the calculation process. Predictions at various cycle tests and temperatures show that RMSE values below 0.3% and MAX values below 0.6% could be achieved by the proposed method in environments without additional noises. Even under non-Gaussian and impulsive noise conditions, the RMSE value of the optimized method remains below 0.9%. The results indicate that this method consistently maintains excellent estimation accuracy and robustness across all application scenarios.
{"title":"State of charge estimation for lithium-ion batteries using an adaptive cubature Kalman filter based on improved generalized minimum error entropy criterion","authors":"Chen Chen , Qiang Zhang , Wei Liao , Feng Zhu , Menghan Li , Hanming Wu","doi":"10.1016/j.geits.2025.100292","DOIUrl":"10.1016/j.geits.2025.100292","url":null,"abstract":"<div><div>Accurate and robust estimation of the State of Charge (SOC) in complex environments is vital to achieving high battery performance, extended lifespan, enhanced safety, and improved user experience. Conventional estimation methods often neglect the impact of temperature on battery during the modeling process. To address this, this paper presents a battery modeling method applicable across a comprehensive temperature range that encompasses all potential operating temperatures. A second-order equivalent circuit model (ECM) is developed for the battery, with parameters defined within a specified temperature range. Furthermore, an adaptive cubature Kalman filter based on an improved minimum error entropy criterion (IMEF-ACKF) is introduced to address the significant accuracy degradation of traditional methods under non-Gaussian noise and substantial outlier interference. The generalized minimum error entropy criterion is combined with the generalized maximum correntropy criterion to replace the traditional minimum mean-square error (MMSE) criterion, addressing the influence of non-Gaussian noise. Then, exponential transformation of system residual is used to mitigate the impact of large outliers, and adaptive filter is incorporated to improve the stability of the calculation process. Predictions at various cycle tests and temperatures show that RMSE values below 0.3% and MAX values below 0.6% could be achieved by the proposed method in environments without additional noises. Even under non-Gaussian and impulsive noise conditions, the RMSE value of the optimized method remains below 0.9%. The results indicate that this method consistently maintains excellent estimation accuracy and robustness across all application scenarios.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100292"},"PeriodicalIF":16.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145685437","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 : 2025-03-26DOI: 10.1016/j.geits.2025.100298
Xudong Qu , Jingyuan Zhao , Hui Pang , Michael Fowler , Andrew F. Burke
The performance of lithium-ion batteries is critical across a range of applications, including portable devices, electric vehicles, and energy storage systems. Effective diagnostics of these battery systems require evaluating multiple factors such as charge, health, lifespan, and safety. Diagnosing batteries under real-world conditions presents notable challenges, particularly due to dynamic operating environments, inconsistent data quality, and cell-to-cell variations. These challenges complicate diagnostics further when considering the need for model integration, scalability, and managing computational costs. Industry 4.0 introduces new opportunities for intelligent, real-time battery performance evaluation, but also brings its own complexities. This review examines several real-world battery diagnostic scenarios, identifying key obstacles. We provide an in-depth analysis of the integration of intelligent diagnostic technologies in Industry 4.0, with a focus on IoT connectivity, machine learning techniques, and big data analytics. Moreover, we outline promising research directions, such as fostering interdisciplinary collaboration, improving data and model integration, utilizing diverse data patterns, and strengthening partnerships between academia and industry. Cloud-based AI solutions not only enhance diagnostics related to battery lifespan and safety but also align with the Industry 4.0 framework by facilitating automated decision-making and resource management. This review highlights recent advancements and identifies critical challenges that require further exploration. It aims to support sustainable industrial practices and drive the adoption of green technologies within smart, digital and sustainable environments. It aims to promote intelligent industrial practices and accelerate the adoption of battery technologies within smart, digital, and eco-friendly environments.
{"title":"Challenges and prospects in real-world battery status prediction within Industry 4.0","authors":"Xudong Qu , Jingyuan Zhao , Hui Pang , Michael Fowler , Andrew F. Burke","doi":"10.1016/j.geits.2025.100298","DOIUrl":"10.1016/j.geits.2025.100298","url":null,"abstract":"<div><div>The performance of lithium-ion batteries is critical across a range of applications, including portable devices, electric vehicles, and energy storage systems. Effective diagnostics of these battery systems require evaluating multiple factors such as charge, health, lifespan, and safety. Diagnosing batteries under real-world conditions presents notable challenges, particularly due to dynamic operating environments, inconsistent data quality, and cell-to-cell variations. These challenges complicate diagnostics further when considering the need for model integration, scalability, and managing computational costs. Industry 4.0 introduces new opportunities for intelligent, real-time battery performance evaluation, but also brings its own complexities. This review examines several real-world battery diagnostic scenarios, identifying key obstacles. We provide an in-depth analysis of the integration of intelligent diagnostic technologies in Industry 4.0, with a focus on IoT connectivity, machine learning techniques, and big data analytics. Moreover, we outline promising research directions, such as fostering interdisciplinary collaboration, improving data and model integration, utilizing diverse data patterns, and strengthening partnerships between academia and industry. Cloud-based AI solutions not only enhance diagnostics related to battery lifespan and safety but also align with the Industry 4.0 framework by facilitating automated decision-making and resource management. This review highlights recent advancements and identifies critical challenges that require further exploration. It aims to support sustainable industrial practices and drive the adoption of green technologies within smart, digital and sustainable environments. It aims to promote intelligent industrial practices and accelerate the adoption of battery technologies within smart, digital, and eco-friendly environments.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 2","pages":"Article 100298"},"PeriodicalIF":16.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145886232","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 : 2025-03-26DOI: 10.1016/j.geits.2025.100294
Tianxin Chen , Xin Lai , Fei Chen , Zhouyang Xu , Xuebing Han , Languang Lu , Yuejiu Zheng , Minggao Ouyang
Lithium-ion batteries (LIBs) are widespread with the fast development of new energy vehicles. The characteristics of LIB electrodes, including mass load, thickness, and porosity, are critical for battery performance such as energy density and lifespan. These characteristics are greatly influenced by the manufacturing methods and should be carefully considered during the production process development. However, the manufacturing process of electrodes is highly complex, involving a multitude of parameters. The traditional trial-and-error method has proven to be ineffective in improving manufacturing efficiency. In this study, we propose an artificial intelligence-based prediction method for estimating the key characteristics of electrodes. Specifically, it utilizes active material mass content, viscosity, solid-to-liquid ratio, and comma gap as input parameters. Compared to the traditional multiple linear regression method, the proposed method exhibits a significant improvement in accuracy. In certain cases, the root-mean-square error is reduced by an average of 35.5%, highlighting the superior prediction accuracy achieved by our method. Furthermore, we conduct a comparative analysis of different deep neural networks in predicting electrode characteristics. Finally, the importance of input features using the permutation feature importance analysis method is analyzed. By harnessing the powerful generalization ability of artificial intelligence, our method can be effectively applied to the manufacturing process of LIBs, resulting in a significant enhancement of battery production efficiency.
{"title":"Intelligent prediction of electrode characteristics based on neural networks in the lithium-ion battery production chain","authors":"Tianxin Chen , Xin Lai , Fei Chen , Zhouyang Xu , Xuebing Han , Languang Lu , Yuejiu Zheng , Minggao Ouyang","doi":"10.1016/j.geits.2025.100294","DOIUrl":"10.1016/j.geits.2025.100294","url":null,"abstract":"<div><div>Lithium-ion batteries (LIBs) are widespread with the fast development of new energy vehicles. The characteristics of LIB electrodes, including mass load, thickness, and porosity, are critical for battery performance such as energy density and lifespan. These characteristics are greatly influenced by the manufacturing methods and should be carefully considered during the production process development. However, the manufacturing process of electrodes is highly complex, involving a multitude of parameters. The traditional trial-and-error method has proven to be ineffective in improving manufacturing efficiency. In this study, we propose an artificial intelligence-based prediction method for estimating the key characteristics of electrodes. Specifically, it utilizes active material mass content, viscosity, solid-to-liquid ratio, and comma gap as input parameters. Compared to the traditional multiple linear regression method, the proposed method exhibits a significant improvement in accuracy. In certain cases, the root-mean-square error is reduced by an average of 35.5%, highlighting the superior prediction accuracy achieved by our method. Furthermore, we conduct a comparative analysis of different deep neural networks in predicting electrode characteristics. Finally, the importance of input features using the permutation feature importance analysis method is analyzed. By harnessing the powerful generalization ability of artificial intelligence, our method can be effectively applied to the manufacturing process of LIBs, resulting in a significant enhancement of battery production efficiency.</div></div>","PeriodicalId":100596,"journal":{"name":"Green Energy and Intelligent Transportation","volume":"5 1","pages":"Article 100294"},"PeriodicalIF":16.4,"publicationDate":"2025-03-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145584458","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