In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train ...In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train control equipment.A virtual sample generation solution based on Generative Adversarial Network(GAN)is proposed to overcome this shortcoming.Aiming at augmenting the sample classes with the imbalanced data problem,the GAN-based virtual sample generation strategy is embedded into the establishment of fault prediction models.Under the PHM framework of the on-board train control system,the virtual sample generation principle and the detailed procedures are presented.With the enhanced class-balancing mechanism and the designed sample augmentation logic,the PHM scheme of the on-board train control equipment has powerful data condition adaptability and can effectively predict the fault probability and life cycle status.Practical data from a specific type of on-board train control system is employed for the validation of the presented solution.The comparative results indicate that GAN-based sample augmentation is capable of achieving a desirable sample balancing level and enhancing the performance of correspondingly derived fault prediction models for the Condition-based Maintenance(CBM)operations.展开更多
Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead b...Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead before EVs can establish themselves as the dominant force in the global automotive market. Concerns such as range anxiety, battery aging, and safety issues remain significant challenges.展开更多
State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to ac...State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.展开更多
Mining safety and health improvements over the past decades are remarkable by many metrics, and yet the expectation of society, and the goal of the mining industry, is zero harm. If we examine the underlying enablers ...Mining safety and health improvements over the past decades are remarkable by many metrics, and yet the expectation of society, and the goal of the mining industry, is zero harm. If we examine the underlying enablers for the significant gains that have been achieved, the key role that research to help understand the causes of problems and to develop lasting solutions is clear. Many of the remaining challenges have been resistant to solutions by various approaches. Some, such as fatalities and injuries from ground control or powered haulage are prominent year after year. Different approaches are indicated and new solutions will be required if we are to achieve a goal of zero harm. These will originate with research, but into which topics, and what are some of these different approaches? This paper examines the current state of mine safety in the United States and highlights areas of significant opportunity for research that will lead to solutions. The likely direction of research that will enable realization of the ‘‘zero harm'' goal is described in terms of evolutionary and revolutionary approaches. Both are important, but the author's view is that some of the largest gains will be made with trans-disciplinary approaches that break from the past. Topical areas of research are suggested and several research questions are given to illustrate the direction of future research in mining safety and health.展开更多
基金supported by National Natural Science Foundation of China(U2268206,T2222015)Beijing Natural Science Foundation(4232031)+1 种基金Key Fields Project of DEGP(2021ZDZX1110)Shenzhen Science and Technology Program(CJGJZD20220517141801004).
文摘In view of class imbalance in data-driven modeling for Prognostics and Health Management(PHM),existing classification methods may fail in generating effective fault prediction models for the on-board high-speed train control equipment.A virtual sample generation solution based on Generative Adversarial Network(GAN)is proposed to overcome this shortcoming.Aiming at augmenting the sample classes with the imbalanced data problem,the GAN-based virtual sample generation strategy is embedded into the establishment of fault prediction models.Under the PHM framework of the on-board train control system,the virtual sample generation principle and the detailed procedures are presented.With the enhanced class-balancing mechanism and the designed sample augmentation logic,the PHM scheme of the on-board train control equipment has powerful data condition adaptability and can effectively predict the fault probability and life cycle status.Practical data from a specific type of on-board train control system is employed for the validation of the presented solution.The comparative results indicate that GAN-based sample augmentation is capable of achieving a desirable sample balancing level and enhancing the performance of correspondingly derived fault prediction models for the Condition-based Maintenance(CBM)operations.
文摘Transportation electrification is essential for decarbonizing transport. Currently, lithium-ion batteries are the primary power source for electric vehicles (EVs). However, there is still a significant journey ahead before EVs can establish themselves as the dominant force in the global automotive market. Concerns such as range anxiety, battery aging, and safety issues remain significant challenges.
基金funded by the “SMART BATTERY” project, granted by Villum Foundation in 2021 (project number 222860)。
文摘State of health(SoH) estimation plays a key role in smart battery health prognostic and management.However,poor generalization,lack of labeled data,and unused measurements during aging are still major challenges to accurate SoH estimation.Toward this end,this paper proposes a self-supervised learning framework to boost the performance of battery SoH estimation.Different from traditional data-driven methods which rely on a considerable training dataset obtained from numerous battery cells,the proposed method achieves accurate and robust estimations using limited labeled data.A filter-based data preprocessing technique,which enables the extraction of partial capacity-voltage curves under dynamic charging profiles,is applied at first.Unsupervised learning is then used to learn the aging characteristics from the unlabeled data through an auto-encoder-decoder.The learned network parameters are transferred to the downstream SoH estimation task and are fine-tuned with very few sparsely labeled data,which boosts the performance of the estimation framework.The proposed method has been validated under different battery chemistries,formats,operating conditions,and ambient.The estimation accuracy can be guaranteed by using only three labeled data from the initial 20% life cycles,with overall errors less than 1.14% and error distribution of all testing scenarios maintaining less than 4%,and robustness increases with aging.Comparisons with other pure supervised machine learning methods demonstrate the superiority of the proposed method.This simple and data-efficient estimation framework is promising in real-world applications under a variety of scenarios.
文摘Mining safety and health improvements over the past decades are remarkable by many metrics, and yet the expectation of society, and the goal of the mining industry, is zero harm. If we examine the underlying enablers for the significant gains that have been achieved, the key role that research to help understand the causes of problems and to develop lasting solutions is clear. Many of the remaining challenges have been resistant to solutions by various approaches. Some, such as fatalities and injuries from ground control or powered haulage are prominent year after year. Different approaches are indicated and new solutions will be required if we are to achieve a goal of zero harm. These will originate with research, but into which topics, and what are some of these different approaches? This paper examines the current state of mine safety in the United States and highlights areas of significant opportunity for research that will lead to solutions. The likely direction of research that will enable realization of the ‘‘zero harm'' goal is described in terms of evolutionary and revolutionary approaches. Both are important, but the author's view is that some of the largest gains will be made with trans-disciplinary approaches that break from the past. Topical areas of research are suggested and several research questions are given to illustrate the direction of future research in mining safety and health.
