Deep reinforcement learning for a color-batching resequencing problem

Leng, Jinling; Jin, Chun; Vogl, Alexander; Liu, Huiyu

doi:10.1016/j.jmsy.2020.06.001

Cited by 35 publications

(9 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…e experiments demonstrate the correctness of the proposed algorithm, and its performance surpasses the conventional DQN algorithm. Leng et al [20] propose a Color-Histogram (CH) model, which combines the Markov decision process with a DQN algorithm, to solve the problem of color reordering in automotive spray painting workshops.…”

Section: Reinforcement Learningmentioning

confidence: 99%

A Reinforcement Learning-Based Basketball Player Activity Recognition Method Using Multisensors

Yang

2022

Mobile Information Systems

View full text Add to dashboard Cite

It is an effective means to use a computer auxiliary system to assist athletes in training. In this paper, we design a technical activity recognition system for basketball players. The system uses the sensing module bound to the basketball player to collect the activity data and uses the proposed Multilayer Parallel Long Short Term Memory (MP-LSTM) algorithm to recognize the activity. Moreover, in order to extend the working time of the system and reduce the energy consumption of the sensing module, we also utilize the classical reinforcement learning algorithm DQN to adaptively control the sampling frequency of the sensing module for making a trade-off between recognition accuracy and energy consumption. Experiment results show that the recognition accuracy of the proposed MP-LSTM algorithm reaches 94%, while the recognition accuracy of the system remains at about 90% after applying the DQN algorithm, and the energy consumption is reduced by 76%.

show abstract

Section: Reinforcement Learningmentioning

confidence: 99%

A Reinforcement Learning-Based Basketball Player Activity Recognition Method Using Multisensors

Yang

2022

Mobile Information Systems

View full text Add to dashboard Cite

show abstract

“…The deep RL approach reduced CPU times remarkably for the high volatile medical mask production in times of Covid-19. Besides mask production, deep RL demonstrated superior performances in batch processing which reduced tardiness for repair scheduling operations (Palombarini and Martinez 2018;Palombarini and Martínez 2019), in chemical scheduling to increase profitability and deal with fluctuating prices, shifting demands, and stoppages (Hubbs et al 2020), and in paint job scheduling to minimise costs of colour changeovers within the automotive industry (Leng et al 2020). Discipline-specific scheduling objectives were addressed by Lee, Cho, and Lee (2020), who increased sustainability and minimised tardiness in injection mold scheduling, or by Xie, Zhang, and Rose (2019) who reduced total throughput time and lateness in singlemachine processes.…”

Section: Production Schedulingmentioning

confidence: 99%

Deep reinforcement learning in production systems: a systematic literature review

Panzer

Bender

2021

International Journal of Production Research

128

View full text Add to dashboard Cite

Shortening product development cycles and fully customisable products pose major challenges for production systems. These not only have to cope with an increased product diversity but also enable high throughputs and provide a high adaptability and robustness to process variations and unforeseen incidents. To overcome these challenges, deep Reinforcement Learning (RL) has been increasingly applied for the optimisation of production systems. Unlike other machine learning methods, deep RL operates on recently collected sensor-data in direct interaction with its environment and enables real-time responses to system changes. Although deep RL is already being deployed in production systems, a systematic review of the results has not yet been established. The main contribution of this paper is to provide researchers and practitioners an overview of applications and to motivate further implementations and research of deep RL supported production systems. Findings reveal that deep RL is applied in a variety of production domains, contributing to data-driven and flexible processes. In most applications, conventional methods were outperformed and implementation efforts or dependence on human experience were reduced. Nevertheless, future research must focus more on transferring the findings to real-world systems to analyse safety aspects and demonstrate reliability under prevailing conditions.

show abstract

“…Leng et. al. propose the usage of the Deep Q-Network algorithm to solve this Colour-batching Re-sequencing Problem [9]. Huang et al proved, through a simulation study, the effectiveness of the usage of Q-Learning in a maintenance problem where random failures of machines are highly disruptive [10].…”

Section: Reinforcement Learning Applicationsmentioning

confidence: 99%

“…Lastly, with all the other parameters decided, the reward multiplier's impact was studied with various values (1,5,9,11,13,15,19,25,30) and the experiments results are visible in the Fig. 16.…”

Section: Q-learning Algorithm -Scenario Ii: Learning An Assembly Sequ...mentioning

confidence: 99%

A study on a Q-Learning algorithm application to a manufacturing assembly problem

Neves

Vieira

Neto

2021

Journal of Manufacturing Systems

View full text Add to dashboard Cite

Deep reinforcement learning for a color-batching resequencing problem

Cited by 35 publications

References 23 publications

A Reinforcement Learning-Based Basketball Player Activity Recognition Method Using Multisensors

A Reinforcement Learning-Based Basketball Player Activity Recognition Method Using Multisensors

Deep reinforcement learning in production systems: a systematic literature review

A study on a Q-Learning algorithm application to a manufacturing assembly problem

Contact Info

Product

Resources

About