Toyoo Fukuda

Adaptive scheduling system inspired by immune system

An immune system has powerful abilities such as memory, recognition and learning to respond to invading antigens, and artificial immunity-based systems are expected to be applicable to many engineering applications. This paper proposes an optimization algorithm imitating the immune system to solve the scheduling problem. The proposed algorithm is shown to be effective for multi-optimization such as a scheduling problem with variable batch sizes.

Immune Networks Using Genetic Algorithm for Adaptive Production Scheduling

Abstract Immune system has powerful abilities such as memory, recognition and learning to respond to invading antigens, and is expected to be applicable to many industrial applications as well as neural networks. This paper proposes an algorithm imitating the immune system to solve the optimization problem partly with genetic algorithm. The proposed algorithm is shown to be capable of searching for a global solution not but local solutions through an illustrative example of a resource allocation problem.

ESTRAC-III: An Expert System for Train Traffic Control in Disturbed Situations

Abstract This paper describes a rule-based decision support system for train traffic control in disturbed situations, which is called ESTRAC-III. ESTRAC-III can automatically generate a rescheduling plan for traffic disturbances which comprises many kinds of schedule adjustments, as human experts work manually. We have applied knowledge engineering technology to develop ESTRAC-III. We also have applied a newly developed simulation method, which is called a partial simulation, to combine a basic simulation unit which predicts local operation of interacting trains and “If-Then” rules which govern local rescheduling decisions. Using this method, we can duplicate on a computer the problem solving process of human experts who regularly make rescheduling plans. Through the experience of applying ESTRAC-III to a large and complicated railway network operated in real life, we have confirmed that this system can support human experts efficiently and effectively.

Scheduling Editor for Production Management with Human-Computer Cooperative Systems

Abstract The computer-aided scheduling environment of manufacturing system is described. The cooperation of the human and the computer is proposed, in which the complex simulation and data handling are executed by computer and the evaluation of schedule and the editing of schedule is indicated by the human planner. The cooperation of human and computer is essential in the system to edit the schedule as a planner desires. The simulation and the modelling of manufacturing systems as discrete event systems is based on the timed Petri net.

Artificial immunity based management system for a semiconductor production line

A semiconductor production line is a large scale and complex system. It is considered to be difficult to control because there exist lots of malfunctions such as maintenance of equipment, equipment break-down and imbalance of WIP to disturb production of wafers in the semiconductor production system. Methods and systems using simulations or expert systems have been used to solve these disturbances, the but semiconductor production environments change dynamically and therefore these methods alone do not yield a perfect control system. This paper presents a method applying an artificial immunity based system described by multi-agent nets, that adapts itself to a dynamical environment.

Optimum Planning of Sewage Treatment Systems for Preserving Stream Quality

Abstract An optimum planning and control of a regional sewage treatment system is investigated. To minimize total construction and operation cost, an optimum allocation of plants and their sizes are first decided. After allocating the plants along a river based on the result obtained, a control policy of each treatment process which can preserve stream quality is developed employing the principles of dynamic programming.

Engineering design support framework by case-based reasoning

Abstract In engineering design, the customers order-bandling process normally requires the designers previous experiences. The designer may be required to modify basic product units as well as install new functions. We propose a case-based design support framework to support this process. Our framework is implemented as a system SUPPORT, which interactively supports the design process involving the specification analysis, the functional design, and the parts selection and layout. The designer can analogically reuse past designs and/or their pieces from various viewpoints. After a new design is completed, the functional design is organized into an existing function abstraction hierarchy and can be used as a framework for a new design in the future.

Case organization in a case-based engineering design support system

The authors propose a case algorithm method in a case-based engineering design support system based on a psychological memory model. The objective is to support the conceptual design process interactively as much as possible, using the SUPPORT tool as an intelligent assistant. The work is characteristic in: (1) supporting the functional design with the value analysis methodology; (2) analogical case retrieval based on the semantic memory which defines the relations among concepts from multi-viewpoints; and (3) organization of cases based on a model of dynamic and hierarchical human episodic memory in cognitive science. SUPPORT and the memory organization method are discussed.<<ETX>>

A Real-Time Scheduling Method Using Hierarchical Decentralized Decision Makers for Flexible Manufacturing Systems

This paper presents a hierarchical decentralized scheduling method for a real-time production line control, which consists of a strategic level scheduler(SLS) and operational level schedulers(OLS). The SLS aims at making a schedule referenced by the OLS. The schedule solved by the SLS satisfies some constraints, and is generated by a schedule editor on the Flexible Planning System(FPS). The OLS aims at the real-time control of the production line and is based on the know-how of the supervisor.

DYNAMIC SCHEDULING BY USING SCHEDULING EDITOR AND DISTRIBUTED DECISION MAKER

Abstract In this paper, we propose a hierarchical dynamic scheduling procedure with a schedule editor as a strategic level scheduler, and distributed operational level schedulers. In the proposed system Petri-net is used to represent constraints of a complex manufacturing system. With the schedule editor, it becomes possible to freely generate and modify a schedule. With the operational level scheduler, dynamic dispatching decisions can be made.