Deep reinforcement learning for selecting demand forecast models to empower Industry 3.5 and an empirical study for a semiconductor component distributor

Chien, Chen–Fu; Lin, Yun-Siang; Lin, Sheng

doi:10.1080/00207543.2020.1733125

Cited by 89 publications

(44 citation statements)

References 82 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The employment of Industrial AI towards process optimization in manufacturing is gaining rapid traction, enabling smarter, more efficient data-driven decision-making by leveraging both historical and real-time data. In this regard, the main emphasis has been put into energy consumption prediction and optimization problems [41], production efficiency [71] and demand forecasting [24]. Thus, the application of Industrial AI for process optimization can contribute to make For data-driven applications, real-time capability is crucial to turn new AI predictions and insights into actionable knowledge at both the level of the processes and of the overall smart factory operations in a timely manner, adequate for the increasingly real-time economy.…”

Section: ) Process Optimizationmentioning

confidence: 99%

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

et al. 2020

View full text Add to dashboard Cite

Section: ) Process Optimizationmentioning

confidence: 99%

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

et al. 2020

View full text Add to dashboard Cite

“…Further categories with single publications are listed in Table 7. These include specific topics such as building an agent swapping framework to allow learning in a nonreal-time environment and execution in a real-time environment (Schmidt, Schellroth, and Riedel 2020) or the deep RL based selection of optimal prediction models in the semiconductor manufacturing domain to cope with demand fluctuations and avoid shortages and overstock (Chien, Lin, and Lin 2020).…”

Section: Further Applicationsmentioning

confidence: 99%

Deep reinforcement learning in production systems: a systematic literature review

Panzer

Bender

2021

International Journal of Production Research

103

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

“…For example, machine learning can support data-driven decisionmaking in pre-production, production, processing, and distribution stages of agricultural SCs (Sharma et al 2020). Prior research has examined the role of AI for effective and efficient SCM, including forecasting (Chien, Lin, and Lin 2020), configuration and optimisation (Abbasi et al 2020;Fragapane et al 2020), forecasting (Chien, Lin, and Lin 2020), risk management (Baryannis et al 2020;Soleymani and Nejad 2018), col-laboration between human operators and AI-based systems (Klumpp 2018), increased operational efficiency in replenishment policies (Priore et al 2019), and supplier selection (Zhao and Yu 2011;Choy et al 2004). While such studies have made valuable contributions, knowledge about the influential and mediating role of culture is limited.…”

Section: Evolution Of Ai In Modern Operations and Supply Chain Managementmentioning

confidence: 99%

Understanding the influential and mediating role of cultural enablers of AI integration to supply chain

Cadden

Dennehy

Mäntymäki

et al. 2021

International Journal of Production Research

View full text Add to dashboard Cite

Artificial Intelligence (AI) has been claimed to offer transformational power across industries and sectors. To date, research has largely focused on the technical characteristics of AI and its influence on organisational capabilities. Despite the hype surrounding AI, there is a scarcity of rigorous research that examines the organisational and behavioural factors that foster AI integration in supply chains is lacking. This quantitative study addresses this gap in knowledge by developing a research hypothesis that examines the relationships between supply chain culture and AI. We extend the generalisability of culture to provide novel insights about AI-driven supply chains that have not been reported in previous studies. The findings demonstrate the influential role that cultural enablers have on the successful integration of AI technologies in supply chains, which has implications for operations and supply chain management.

show abstract

Deep reinforcement learning for selecting demand forecast models to empower Industry 3.5 and an empirical study for a semiconductor component distributor

Cited by 89 publications

References 82 publications

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

Industrial Artificial Intelligence in Industry 4.0 - Systematic Review, Challenges and Outlook

Deep reinforcement learning in production systems: a systematic literature review

Understanding the influential and mediating role of cultural enablers of AI integration to supply chain

Contact Info

Product

Resources

About