Distributed scheduling problems in intelligent manufacturing systems

Fu, Yaping; Hou, Yuhan; Wang, Zifan; Wu, Xinwei; Gao, Kaizhou; Wang, Ling

doi:10.26599/tst.2021.9010009

Cited by 122 publications

(31 citation statements)

References 134 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Distributed scheduling integrates discrete units or factories and enables them to operate independently, which improves the operating efficiency of the whole manufacturing system. 32 However, the distributed manufacturing manner may cause environmental fluctuation and local optimum.…”

Section: Literature Reviewmentioning

confidence: 99%

Reinforcement learning for online optimization of job-shop scheduling in a smart manufacturing factory

Zhou

Zhu

Tang

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

The job-shop scheduling problem (JSSP) is a complex combinatorial problem, especially in dynamic environments. Low-volume-high-mix orders contain various design specifications that bring a large number of uncertainties to manufacturing systems. Traditional scheduling methods are limited in handling diverse manufacturing resources in a dynamic environment. In recent years, artificial intelligence (AI) arouses the interests of researchers in solving dynamic scheduling problems. However, it is difficult to optimize the scheduling policies for online decision making while considering multiple objectives. Therefore, this paper proposes a smart scheduler to handle real-time jobs and unexpected events in smart manufacturing factories. New composite reward functions are formulated to improve the decision-making abilities and learning efficiency of the smart scheduler. Based on deep reinforcement learning (RL), the smart scheduler autonomously learns to schedule manufacturing resources in real time and improve its decision-making abilities dynamically. We evaluate and validate the proposed scheduling model with a series of experiments on a smart factory testbed. Experimental results show that the smart scheduler not only achieves good learning and scheduling performances by optimizing the composite reward functions, but also copes with unexpected events (e.g. urgent or simultaneous orders, machine failures) and balances between efficiency and profits.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Reinforcement learning for online optimization of job-shop scheduling in a smart manufacturing factory

Zhou

Zhu

Tang

et al. 2022

Advances in Mechanical Engineering

View full text Add to dashboard Cite

show abstract

“…3 Shandong Computer Science Center (National Supercomputer Center in Jinan), Jinan, China. 4 Shandong Provincial Key Laboratory of Computer Networks, Jinan, China.…”

Section: Abbreviationsmentioning

confidence: 99%

Shortest link scheduling in wireless networks under the Rayleigh fading model

Huang

et al. 2021

J Wireless Com Network

View full text Add to dashboard Cite

Many shortest link scheduling algorithms adopt non-fading SINR interference model, which assumes that the received signal power will always remain determinate as long as the transmission power of the corresponding sender is fixed. In fact, because environment always influences the propagation of radio signals, the received signal power is by no means a certain value. Rayleigh fading is a statistical model for radio signals propagation. It assumes that the strength of a signal on a receiver is a random variable, varying with the Rayleigh distribution. This paper proposes a shortest link scheduling algorithm under the Rayleigh fading model (SLSRF). The SLSRF partitions the wireless network area into hexagons and colors the hexagons with three different colors such that two neighboring hexagons have different colors. The senders of the links scheduled simultaneously are arranged in hexagons with the same color. The correctness of the SLSRF is proved through theoretical analysis, and the efficiency is illustrated by elaborate simulations. Our simulation results demonstrate that the schedule delay of SLSRF is less than that of some results under the non-fading SINR interference model. Furthermore, we extend the SLSRF to a distributed version, which is suitable for large wireless networks.

show abstract

“…They include those resulting from electrical “abuse” (over‐charging, fast charging, over‐discharging, and external short‐circuit) and mechanical abuse (compression and container breaching). In recent years, due to the mechanical misuse of lithium batteries, fire accidents caused by battery thermal runaway of electric vehicles have occurred from time to time 12–15 . Binghe Liu et al studied that under the condition of mechanical abuse, LIBs would successively undergo mechanical deformation, internal short‐circuit, thermal runaway, and explosion/fire 16 …”

Section: Introductionmentioning

confidence: 99%

“…In recent years, due to the mechanical misuse of lithium batteries, fire accidents caused by battery thermal runaway of electric vehicles have occurred from time to time. [12][13][14][15] Binghe Liu et al studied that under the condition of mechanical abuse, LIBs would successively undergo mechanical deformation, internal short-circuit, thermal runaway, and explosion/fire. 16 Therefore, it has become an urgent problem to give early warning and improve battery safety to prevent battery thermal runaway in advance.…”

Section: Introductionmentioning

confidence: 99%

Temperature prediction of lithium‐ion batteries based on electrochemical impedance spectrum: A review

Wang

Duan

et al. 2022

Intl J of Energy Research

View full text Add to dashboard Cite

Summary With the rapid development of global electric vehicles, artificial intelligence, and aerospace, lithium‐ion batteries (LIBs) have become more and more widely used due to their high property. More and more disasters are caused by battery combustion. Among them, the temperature prediction of LIBs is the key to prevent the occurrence of fire. At present, using surface temperature sensor to measure the temperature of LIBs is the main method. High‐capacity LIB packs used in electric vehicles and grid‐tied stationary energy storage system essentially consist of thousands of individual LIB cells. Therefore, installing a physical sensor at each cell, especially at the cell core, is not practically feasible from the solution cost, space, and weight point of view. So developing a new method for battery temperature prediction has become an urgent problem to be solved. Electrochemical impedance spectroscopy (EIS) is a widely applied non‐destructive method of characterization of LIBs. In recent years, methods of predicting LIBs temperature by EIS have been developed. The prediction of LIBs temperature based on EIS has the advantages of high real‐time performance and prediction accuracy, and the device is simple and practical. The proposed method has a good development prospect in electric vehicles and other fields and can effectively solve the current problems of LIBs temperature prediction. Therefore, it is urgent to summarize these works to promote the next development. This review summarizes the main methods of using EIS to predict the temperature of LIBs in recent years, including the methods based on the impedance, phase shift, and intercept frequency. The principle and application of various methods are reviewed. The advantages and disadvantages of different methods and the future development direction are discussed. Highlights Use EIS to quickly and effectively predict the internal temperature changes of LIBs. No hardware temperature sensors and thermal model are required. The methods to predict battery temperature based on impedance, phase shift, and intercept frequency are reviewed.

show abstract

Distributed scheduling problems in intelligent manufacturing systems

Cited by 122 publications

References 134 publications

Reinforcement learning for online optimization of job-shop scheduling in a smart manufacturing factory

Reinforcement learning for online optimization of job-shop scheduling in a smart manufacturing factory

Shortest link scheduling in wireless networks under the Rayleigh fading model

Temperature prediction of lithium‐ion batteries based on electrochemical impedance spectrum: A review

Contact Info

Product

Resources

About