Learning to Optimize in Intelligent Systems Processes

Dear Colleagues,

Intelligent system can be defined as the system that incorporates intelligence into applications being handled by machines. Many intelligent systems perform search and optimization along with learning capabilities. The techniques are in general based on biologically inspired and artificial intelligence algorithms for solving problems. In tradition, the design of algorithms is primarily based on expert knowledge or handcrafted heuristics. Recently, Learning-to-Optimize (L2O), as a powerful framework for various optimization and machine learning tasks, becomes one of the most active research areas. The goal of L2O is to make use of data driven ability to improve algorithms’ accuracy and efficiency. It provides a new optimization paradigm that uses data to learn a model offline and then makes decisions online. L2O can be widely applied in intelligent systems such as production planning, job scheduling, traffic control, vehicle routing, crew rostering, port operation, supply chain management, etc. Recent studies also suggest that L2O has a great potential to improve the performance of intelligent systems. This special session provides a platform to exchange research works, technical trends and practical experience related to computer science, transportation research, operation research, applied mathematics and management science. This session is expected to broaden the L2O research community and promote the L2O research in intelligent systems as follows:

• Design, control and optimization of assembly systems
• Design, control and optimization of disassembly systems
• Digital twin techniques in manufacturing
• Emission control and energy saving in manufacturing
• End-of-life product recycling
• Formal methods in the modeling, verification and analysis of manufacturing systems, such as Petri nets, finite automata, UML, queuing theory, model checking techniques, etc.
• Heuristic search algorithms
• Intelligent factory
• Real-time operation management
• Real-time task allocation
• Real-time task scheduling
• Machine learning and reinforcement learning in manufacturing
• Smart sensing and control
• Smart logistics management
• System simulation and performance evaluation
• Sustainability manufacturing
• Workstation load balancing in manufacturing, assembly and disassembly

Dr. Bin Hu
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.