http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Jiahui Xu,Jingcheng Wang,Jun Rao,Yanjiu Zhong,Shangwei Zhao 제어·로봇·시스템학회 2022 International Journal of Control, Automation, and Vol.20 No.9
Recent achievements in the field of adaptive dynamic programming (ADP), as well as the data resources and computational capabilities in modern control systems, have led to a growing interest in learning and data-driven control technologies. This paper proposes a twin deterministic policy gradient adaptive dynamic programming (TDPGADP) algorithm to solve the optimal control problem for a discrete-time affine nonlinear system in a modelfree scenario. To solve the overestimation problem resulted from function approximation errors, the minimum value between the double Q network is taken to update the control policy. The convergence of the proposed algorithm in which the value function is served as the Lyapunov function is verified. By designing a twin actor-critic network structure, combining the target network and a specially designed adaptive experience replay mechanism, the algorithm is convenient to implement and the sample efficiency of the learning process can be improved. Two simulation examples are conducted to verify the efficacy of the proposed method.
Disassembly Line Balancing Optimization Method for High Efficiency and Low Carbon Emission
Lei Zhang,Xikun Zhao,Qingdi Ke,Wanfu Dong,Yanjiu Zhong 한국정밀공학회 2021 International Journal of Precision Engineering and Vol.8 No.1
Disassembly is the first step in product recycling and remanufacturing. When disassembling large quantities of products, the disassembly efficiency is crucial for enterprises. Thus, disassembly line is the best choice for automated disassembly of disposal products. Disassembling products, especially complex structure of products, consume a lot of resources and energy and produce large amounts of carbon emissions. So, it is essential for disassembly line to work efficiently and environmentally. In this paper, the hybrid graph is proposed to express the direct and indirect constraint relationship among components. Then, the mathematical model of carbon emission is built by quantifying the carbon emissions in the process of product disassembly. Taking into account the basic disassembly time, direction change time and tool change time, the mathematical model of high efficiency is presented for optimizing disassembly time. Additionally, based on the traditional multi-objective disassembly line balancing problem (DLBP), a novel multi-objective optimization model of the DLBP with shortest disassembly time and minimum carbon emissions is proposed for improving disassembly efficiency and reducing the carbon emissions in the process of disassembly. Furthermore, genetic algorithm is presented for optimizing the disassembly sequence. Finally, an automobile engine is given as an example to confirm the practicality of the proposed model in solving the DLBP.