Search

Your search keyword '"Wu, Xuzhong"' showing total 13 results
Start Over Author "Wu, Xuzhong"
13 results on '"Wu, Xuzhong"'

2. A novel carbon reduction engineering method-based deep Q-learning algorithm for energy-efficient scheduling on a single batch-processing machine in semiconductor manufacturing.

Author

Kong, Min, Wang, Weizhong, Deveci, Muhammet, Zhang, Yajing, Wu, Xuzhong, and Coffman, D'Maris

Subjects
DEEP reinforcement learning, REINFORCEMENT learning, SEMICONDUCTOR manufacturing, ION implantation, GROUP decision making
Abstract

The semiconductor industry is a resource-intensive sector that heavily relies on energy, water, chemicals, and raw materials. Within the semiconductor manufacturing process, the diffusion furnace, ion implantation machine, and plasma etching machine exhibit high energy demands or operate at extremely high temperatures, resulting in significant electricity consumption, which is usually carbon-intensive. To address energy conservation concerns, the industry adopts batch production technology, which allows for the simultaneous processing of multiple products. The energy-efficient parallel batch scheduling problem arises from the need to optimise product grouping and sequencing. In contrast to existing heuristics, meta-heuristics, and exact algorithms, this paper introduces the Deep Q-Network (DQN) algorithm as a novel approach to address the proposed problem. The DQN algorithm is built upon the agent's systematic learning of scheduling rules, thereby enabling it to offer guidance for online decision-making regarding the grouping and sequencing of products. The efficacy of the algorithm is substantiated through extensive computational experiments. [ABSTRACT FROM AUTHOR]

Published
2024
Full Text
View/download PDF

11. Three-Dimensional Autonomous Reentry Guidance for Hypersonic Glide Vehicle.

Author

Wu Xuzhong, Tang Shengjing, and Guo Jie

Subjects
*HEAT flux measurement, *HEAT flux, *SIMULATION methods & models, *ANGLE of attack (Aerodynamics), *BOUNDARY layer (Aerodynamics)
Abstract

A novel three-dimensional autonomous reentry guidance method satisfying heat flux, overload, dynamic pressure, waypoints and other path and terminal constraints is proposed. The reentry trajectory is divided into the initial and glide phases. In the initial phase, a nominal angle of attack and a constant bank angle are used to generate the trajectory. And the glide phase is designed based on drag acceleration versus energy profile which is obtained by using the interpolation between the upper boundary and the lower boundary of the reentry corridor. The magnitude of the bank angle can be decided through the profile, and the sign of bank angle is determined by lateral planner satisfying the waypoints constraints. Simulation results show that the proposed reentry guidance method can generate trajectories satisfying path and terminal constraints. [ABSTRACT FROM AUTHOR]

Published
2014

12. Autonomous gliding entry guidance withgeographic constraints

Author

Guo, Jie, Wu, Xuzhong, and Tang, Shengjing

Abstract

This paper presents a novel three-dimensional autonomous entry guidance for relatively high lift-to-drag ratio vehicles satisfying geographic constraints and other path constraints. The guidance is composed of onboard trajectory planning and robust trajectory tracking. For trajectory planning, a longitudinal sub-planner is introduced to generate a feasible drag-versus-energy profile by using the interpolation between upper boundary and lower boundary of entry corridor to get the desired trajectory length. The associated magnitude of the bank angle can be specified by drag profile, while the sign of bank angle is determined by lateral sub-planner. Two-reverse mode is utilized to satisfy waypoint constraints and dynamic heading error corridor is utilized to satisfy no-fly zone constraints. The longitudinal and lateral sub-planners are iteratively employed until all of the path constraints are satisfied. For trajectory tracking, a novel tracking law based on the active disturbance rejection control is introduced. Finally, adaptability tests and Monte Carlo simulations of the entry guidance approach are performed. Results show that the proposed entry guidance approach can adapt to different entry missions and is able to make the vehicle reach the prescribed target point precisely in spite of geographic constraints.

Published
2015
Full Text
View/download PDF

13. Cooperative multiple target assignment of submunitions based on Chaos-PSO algorithm

Author

Wu, Xuzhong, Tang, Shengjing, and Shi, Jiao

Abstract

In this paper Multi-Objective particle swarm optimization (MOPSO) algorithm is utilized to solve the problem for cooperative multiple target assignment, which is the optimization problem in the discrete search space. At first a model of multi-objective optimization for Cooperative Multiple Target Assignment is established. Aiming to solve out the local convergence phenomenon, the chaos mutation is introduced into PSO for improving global optimal ability. Another underlying problem is that computing speed of the algorithm must meet the operational requirement, so a new kind of Chaos-MOPSO Algorithm is developed to solve the target assignment problem with less population and iterations. At last an authentication example is given in this paper, compared with basic MOPSO and NSGA-II, the Chaos-MOPSO algorithm obtained a better Pareto solution set with smaller computational burden.

Published
2011
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results