A vast amount of data is constantly being generated by people, machines and products through sensors and smart devices within powerful and ubiquitous computing networks. These data are being analyzed far faster and at broader and deeper levels than ever before. Increasing computational power and the availability of Big Data have redefined the value of Artificial Intelligence (AI) technologies. The advancement of these technologies has recently supported a new age of manufacturing, known as Industry 4.0 or the Smart Factory.
Advanced cognitive computing and deep learning are already being applied in manufacturing in the areas of automated visual inspections, fault detection, and preventive maintenance. Production scheduling and material handling systems based on reinforcement learning are being actively investigated. Industries are seeking opportunities to integrate AI approaches, the concepts and technologies of the Internet of Things (IoT), and cyber-physical systems (CPSs), into their manufacturing systems to convert real-time data into actionable operational decisions.
The primary goal of the special issue is to answer the following questions:
- What are the state-of-the-art AI-based approaches in academic research and industry practice?
- How are the new AI-based approaches being or can be applied in manufacturing and logistics systems?
- When are the AI-based algorithms used in manufacturing and logistics systems better than conventional rule-based or analytical approaches? Why are they better in those cases?
- How are advanced computing platforms, concepts, and technologies such as IoT, CPS, cloud computing and Big Data used in conjunction with AI approaches in manufacturing and logistics systems?
- What approaches and methods can compensate for the disadvantages of using AI in industry, such as unexplainable black box logic?
- How can domain knowledge in manufacturing be effectively used in the design and development of AI-based approaches?
- How can AI be combined with more conventional Industrial Engineering or Operational Research approaches, when and why is it relevant?
As the wave of AI is transforming every industry, it is time for the production research community to seek answers to the above questions from academic perspectives. The aim of this special issue is to bring academic researchers and industry professionals together to review the latest advances and explore future directions in this field.
Specific topics of interest include, but are not limited to, the following:
- Machine learning approaches in manufacturing system operations
- AI-based control of production lines
- AI-based dispatching algorithms and control of automated material handling systems (AMHS)
- Inventory control and management using AI approaches
- Machine learning platforms and architecture for manufacturing
- Data analytics for real-time production planning and management
- Smart sensing for manufacturing processes
- Energy control and management in manufacturing systems
- CPS in manufacturing
- Using learning-based approaches such as reinforcement learning, Bayesian learning, and deep learning for decision-making in manufacturing
- Any connection or combination of AI with more conventional Industrial Engineering or Operational Research approaches
September 30th, 2018
- Principal Guest Editor: Young Jae Jang , 291 Daehak-ro, Industrial and Systems Engineering KAIST, Daejeon (email@example.com )
- Guest Editor: Chen-Fu Chien, National Tsing Hua University (firstname.lastname@example.org)
- Guest Editor: Stéphane Dauzère-Pérès, Ecole des Mines de Saint-Etienne (Dauzere-Peres@emse.fr)
- Guest Editor: Tim Huh, University of British Columbia (email@example.com)
- Guest Editor: Young Jae Jang, KAIST (firstname.lastname@example.org)
- Guest Editor: James Morrison, KAIST (email@example.com)