Decentralization and strengthening supervision are the two wings of the reform of administrative examination and approval system. At present, in the supervision process of Chinese government, the phenomenon of strict ...Decentralization and strengthening supervision are the two wings of the reform of administrative examination and approval system. At present, in the supervision process of Chinese government, the phenomenon of strict approval and slack supervision still exists in some local governments. And the dynamic supervision mechanism and supervision restriction mechanism of some local governments are still not perfect. These problems directly lead to"regulatory vacuum"and service absence and other circumstances. The existence of these circumstances will block the process of China's administrative examination and approval system reform. As a result to explore how to promote government supervision innovation and optimize government services is the first important thing, and then to create conditions for the rapid, stable and orderly progress of the administrative examination,what's more to approval system reform.Based on this thesis, the author realizes legal supervision, implement informatization supervision.It not only has increased normalized supervision, improve the administrative examination and approval all-round supervision mechanism, but also established the third party assessment normalization mechanism, and optimize the administrative examination and approval policy advocacy mechanism as well.展开更多
The state of health(SOH)and remaining useful life(RUL)of lithium-ion batteries are crucial for health management and diagnosis.However,most data-driven estimation methods heavily rely on scarce labeled data,while trad...The state of health(SOH)and remaining useful life(RUL)of lithium-ion batteries are crucial for health management and diagnosis.However,most data-driven estimation methods heavily rely on scarce labeled data,while traditional transfer learning faces challenges in handling domain shifts across various battery types.This paper proposes an enhanced vision-transformer integrating with semi-supervised transfer learning for SOH and RUL estimation of lithium-ion batteries.A depth-wise separable convolutional vision-transformer is developed to extract local aging details with depth-wise convolutions and establishes global dependencies between aging information using multi-head attention.Maximum mean discrepancy is employed to initially reduce the distribution difference between the source and target domains,providing a superior starting point for fine-tuning the target domain model.Subsequently,the abundant aging data of the same type as the target battery are labeled through semi-supervised learning,compensating for the source model's limitations in capturing target battery aging characteristics.Consistency regularization incorporates the cross-entropy between predictions with and without adversarial perturbations into the gradient backpropagation of the overall model.In particular,across the experimental groups 13–15 for different types of batteries,the root mean square error of SOH estimation was less than 0.66%,and the mean relative error of RUL estimation was 3.86%.Leveraging extensive unlabeled aging data,the proposed method could achieve accurate estimation of SOH and RUL.展开更多
基金the Research on Government Responsibility in the Process of Purchasing Public Service and the project of social science in Anhui Province(AHSKY 2014018)It is also a cooperation fund of the national administrative institute and one of the results of A Study on the Construction of the Responsibility List and the Government of the Rule of Law
文摘Decentralization and strengthening supervision are the two wings of the reform of administrative examination and approval system. At present, in the supervision process of Chinese government, the phenomenon of strict approval and slack supervision still exists in some local governments. And the dynamic supervision mechanism and supervision restriction mechanism of some local governments are still not perfect. These problems directly lead to"regulatory vacuum"and service absence and other circumstances. The existence of these circumstances will block the process of China's administrative examination and approval system reform. As a result to explore how to promote government supervision innovation and optimize government services is the first important thing, and then to create conditions for the rapid, stable and orderly progress of the administrative examination,what's more to approval system reform.Based on this thesis, the author realizes legal supervision, implement informatization supervision.It not only has increased normalized supervision, improve the administrative examination and approval all-round supervision mechanism, but also established the third party assessment normalization mechanism, and optimize the administrative examination and approval policy advocacy mechanism as well.
基金supported by the Science and Technology Major Project of Fujian Province of China(Grant No.2022HZ028018)the National Natural Science Foundation of China(Grant No.51907030).
文摘The state of health(SOH)and remaining useful life(RUL)of lithium-ion batteries are crucial for health management and diagnosis.However,most data-driven estimation methods heavily rely on scarce labeled data,while traditional transfer learning faces challenges in handling domain shifts across various battery types.This paper proposes an enhanced vision-transformer integrating with semi-supervised transfer learning for SOH and RUL estimation of lithium-ion batteries.A depth-wise separable convolutional vision-transformer is developed to extract local aging details with depth-wise convolutions and establishes global dependencies between aging information using multi-head attention.Maximum mean discrepancy is employed to initially reduce the distribution difference between the source and target domains,providing a superior starting point for fine-tuning the target domain model.Subsequently,the abundant aging data of the same type as the target battery are labeled through semi-supervised learning,compensating for the source model's limitations in capturing target battery aging characteristics.Consistency regularization incorporates the cross-entropy between predictions with and without adversarial perturbations into the gradient backpropagation of the overall model.In particular,across the experimental groups 13–15 for different types of batteries,the root mean square error of SOH estimation was less than 0.66%,and the mean relative error of RUL estimation was 3.86%.Leveraging extensive unlabeled aging data,the proposed method could achieve accurate estimation of SOH and RUL.
