Autonomous Distributed Manufacturing Systems Research Articles

総納期ずれ最小化のためのマルチエージェント強化学習を用いた自律分散型スケジューリング

Multi-agent reinforcement learning have been applied to scheduling method based on utility values for autonomous distributed manufacturing systems in order to improve the objective functions of individual job agents and resource agents, in the previous researches. New distributed scheduling method based on utility values is proposed to improve the sum of earliness and tardiness of all the job agents by applying the multi-agent reinforcement learning to the resource agents, in this research. The resource agents learn the suitable criteria to determine the utility values of the candidate job agents for next machining operation based on the status of manufacturing systems. Some case studies have been carried out to verify the effectiveness of the proposed method.

Real-Time Scheduling Procedures Based on Autonomous Distributed Manufacturing System (ADiMS) Concept

This paper deals with the implementation of Autonomous Distributed Manufacturing System (ADiMS) concept in real-time scheduling in order to solve scheduling problems. Basically production scheduling is an important thing and has significant role in manufacturing system. Generally unpredictable conditions such as machine breakdown, absenteeism, or material shortages, in manufacturing system are a problem. These conditions will make the production schedule could not be implemented as planned. However, these conditions are difficult to be avoided and almost always occur in manufacturing systems. A real-time scheduling based on ADiMS concept that provide flexibility, adaptability, and capable could be use to face this problem. In this paper, the problem is limited to real-time scheduling procedures. The result of the case study is every process has been scheduled real-time manually in certain order by the real-time scheduling procedures based on ADiMS. This is showed that ADiMS concept could be implemented in a real-time scheduling and provides flexibility, adaptability, and capable to solve the scheduling problems.

205 自律分散型生産システムにおける作業者の希望を考慮したリアルタイムスケジューリング(OS-1・GS-13・14 生産システム)

205 自律分散型生産システムにおける作業者の希望を考慮したリアルタイムスケジューリング(OS-1・GS-13・14 生産システム)

206 自律分散型生産システムにおける作業者の希望を考慮した勤務スケジューリング(OS-1・GS-13・14 生産システム)

206 自律分散型生産システムにおける作業者の希望を考慮した勤務スケジューリング(OS-1・GS-13・14 生産システム)

A study on integration of process planning and scheduling system for holonic manufacturing with modification of process plans

The purpose of the present research is to develop an integrated process planning and scheduling system applicable to Holonic Manufacturing System (HMS), which is one of the autonomous distributed manufacturing systems which can cope with dynamic changes in volume and variety of products. A systematic method is firstly proposed to generate a suitable schedule using the methods of Genetic Algorithm (GA) and Dispatching Rule (DR) for the multi products. A Dynamic Programming (DP) method is then proposed to modify the process plans, taking into consideration of the load balance of the machining equipments, which are obtained from the scheduling results.

A Robust Dispatching Algorithm for Autonomous Distributed Manufacturing of Mixed VLSI Products

This paper describes a new dispatching algorithm for dynamic allocation of work-in-process (WIP), named pseudo periodical priority dispatching (P3D). The algorithm is developed to manage a processing station in an autonomous distributed manufacturing system. The priority of dispatching is examined when each quantum starts, by considering both the amount of WIP in the input buffer of the processing station and the arrival rate of WIP. Here, a quantum is defined as a period, during which a single type of WIP is processed in a machine, and the machine for each type of WIP is fixed during the quantum. Performance parameters, i.e., adjustment rate, throughput, response time, and tardiness, when applying P3D are compared with the results of the first-come first-serve (FCFS) and the shortest processing time (SPT) in simulations assuming Poisson arrival. A fluctuation in arrival rate causes large inventories at the processing station. The adjustment rate is the lowest and the availability of machines is the highest with P3D; therefore, P3D can quickly dissolve a bottleneck. Both P3D and SPT produced shorter response times than FCFS in average, and both P3D and FCFS produced shorter tardiness than SPT. The small quantum size helps to shorten the response time in P3D. P3D with the minimized quantum size gives a good estimation when setting the due date. P3D achieves very fair dispatching even though the arrival rate differs by 40 times among mixed WIPs. The author concludes from the above results that P3D is a robust dispatching algorithm for manufacturing a broad mix of VLSI products.

3706 自律分散型生産システムにおける作業者に関する検討 : リアルタイムスケジューリングのための作業者のインターフェース(S67 生産システムの新展開(産業応用),S67 生産システムの新展開(産業応用))

3706 自律分散型生産システムにおける作業者に関する検討 : リアルタイムスケジューリングのための作業者のインターフェース(S67 生産システムの新展開(産業応用),S67 生産システムの新展開(産業応用))

A Cooperative Algorithm for Autonomous Distributed Vehicle Systems with Finite Buffer Capacity

Recently, there are so many researches on Autonomous Distributed Manufacturing Systems (ADMSs), where cooperation among agents is used to solve problems, such as the scheduling problem and the vehicle routing problem. We target ADMSs where an ADMS consists of two sub-systems: a Production System (PS) and an Autonomous Transportation System (ATS). This paper discusses an on-line Tasks Assignment and Routing Problem (TARP) for ATSs under conditions of given production schedule and finite buffer capacity. The TARP results in a constrained version of the Pickup and Delivery Problem with Time Windows (PDPTW), and this paper gives a mathematical formulation of the problem. This paper, also, proposes a cooperative algorithm to obtain suboptimal solutions in which no deadlocks and buffer overflows occur. By computational experiments, we will examine the effectiveness of the proposed algorithm. Computational experiments show that the proposed algorithm is able to obtain efficient and deadlock-free routes even though the buffer capacity is less.

Study on Process Planning System for Holonic Manufacturing (3rd Report, Process Planning Considering Machining Schedules)

New architectures of manufacturing systems have been proposed aiming at realizing more flexible control structures of manufacturing systems which can cope with dynamic changes in volume and variety of products. They are so called as holonic manufacturing systems, autonomous distributed manufacturing systems, random manufacturing systems and biological manufacturing systems. The objective of the present research is to develop an integrated process planning and scheduling system which is applicable to the holonic manufacturing systems. In the previous paper, a systematic method is proposed to select suitable sequences of machining equipment, by applying the genetic algorithm (GA) and the dynamic programming (DP) methods. The method is extended, in the present paper, to consider the production schedules of the machining equipment.

613 ホロニック生産システムにおける工程設計とスケジューリングの統合化

New architectures of manufacturing systems have been proposed aiming at realizing more flexible control structures of manufacturing systems which can cope with dynamic changes in volume and variety of products. They are so called as holonic manufacturing systems, autonomous distributed manufacturing systems, random manufacturing systems and bionic manufacturing systems. The objective of the present research is to develop an integrated process planning and scheduling system which is applicable to the holonic manufacturing systems. In the research, to select suitable machining sequences and sequences of machining equipment, by applying the genetic algorithm (GA) and the dynamic programming (DP) methods

CONTEXT-DEPENDENT AGENTS FOR REAL-TIME SCHEDULING IN MANUFACTURING SYSTEMS

Autonomous distributed manufacturing systems(ADMS) consist of multiple intelligent components with each component acting according to its own judgments. The ADMS objective is to realize more agile and adaptive manufacturing systems. This paper presents the introduction of context-dependent agents (CDAs) in ADMS that switch strategies depending on system conditions to achieve better performance than can be realized by agents that use the same strategies under all system conditions. For the real-time job scheduling problem, the paper presents a basic CDA architecture and the results of an extensive empirical evaluation its performance relative to other rule-based schemes based on several common indices for real-time dispatch.

Study on Process Planning System for Holonic Manufacturing

New architectures of manufacturing systems have been proposed aiming at realizing more flexible control structures of manufacturing systems which can cope with dynamic changes in volume and variety of products. They are so called as holonic manufacturing systems, autonomous distributed manufacturing systems, random manufacturing systems and biological manufacturing systems. The objective of the present research is to develop an integrated process planning and scheduling system which is applicable to the holonic manufacturing systems. In the previous paper, procedures were proposed to recognize the machining features from the product model. A systematic method is proposed, in this paper, to select suitable machining sequences and sequences of machining equipment, by applying the genetic algorithm (GA) and the dynamic programming (DP) methods.

Study on Process Planning System for Holonic Manufacturing. 2nd Report. Selection of Machining Sequences and Sequences of Machining Equipment.

New architectures of manufacturing systems have been proposed aiming at realizing more flexible control structures of manufacturing systems which can cope with dynamic changes in volume and variety of products. They are so called as holonic manufacturing systems, autonomous distributed manufacturing systems, random manufacturing systems and bionic manufacturing systems. The objective of the present research is to develop an integrated process planning and scheduling system which is applicable to the holonic manufacturing systems. In the previous paper, procedures were proposed to recognize the machining features from the product model. A systematic method is proposed, in this paper, to select suitable machining sequences and sequences of machining equipment, by applying the genetic algorithm(GA)and the dynamic programming(DP)methods.

Study on Process Planning System for Holonic Manufacturing : 1st Report, System Architecture and Recognition of Machining Feature

New architectures of the manufacturing systems have been proposed aiming at realizing more flexible control structures of the manufacturing systems which can cope with the dynamic changes in the volume and the variety of the products. They are so called as holonic manufacturing systems, autonomous distributed manufacturing systems, random manufacturing systems and bionic manufacturing systems. The objective of the present research is to develop an integrated process planning and scheduling system which is applicable to the holonic manufacturing systems. A basic architecture is proposed in the paper to realize a process planning system for the holonic manufacturing systems. The system consists of three types of holons; they are, order holons, workpiece holons and machining equipment holons. The workpiece holons carry out process planning tasks referring to the schedules and the availability of the machining equipment. A procedure is proposed to extract the machining features from the product model based on the shape generation functions of the machining equipment.

Advanced Autonomous Distributed Manufacturing System Using Active Database.

The architecture of dynamic scheduling using active database is proposed to realize an autonomous distributed manufacturing system which is expected to be a next generation manufacturing system. The proposed system employ both of the centralized scheduling algorism and the distributed information processing concept to achieve efficiency and flexibility of manufacturing systems, respectively. In the system, the active database is a core module acting as a data manager. Autonomous machining cells organized by self judging and self evaluating NC machine tools receive machining orders from the active database, and send machining status as well. Dynamic sheduling is performed to send machining orders to the active database when the events such as a machine trouble and an job addition happened. The system simulator is developed to verify the performance of the proposed system. Both of efficiency and flexibility of this system is clearly shown under several case studies.

A Modeling Method for Autonomous Distributed Real Time Scheduling by Using Colored Petri Net.

In modeling autonomous distributed manufacturing systems, a basic module of the net structure in the colored Petri net is introduced to describe the configuration of a machining cell and its autonomous decision making for real time scheduling. The arc expressions and transition guards are used to express the local decision making activities and the progress of the part process in each module. Three types of colored tokens which are the part token, the machine token and the AGV-token are introduced to record their own current states. The local decision making and information processing are made on the local computer attached to each machine. The whole system which consists of several machining cells can be represented by connecting the corresponding modules in which the transporting transitions between machining cells play the role of the interface between modules. The central computer makes the transporting schedule of the AGV by coordinating the transporting orders from various machines.

生産システムにおける最近の動向 エージェントネットによる自律分散型生産システムのモデル化と制御

生産システムにおける最近の動向 エージェントネットによる自律分散型生産システムのモデル化と制御

Design and Management of Autonomous Distributed Manufacturing Systems. 2nd Report. Application to Scheduling Problems Considering Unscheduled Disruptions.

This paper deals with object-oriented modeling of an autonomous distributed manufacturing system and its application to real-time production scheduling considering unscheduled disruptions. The autonomous activities of the components of the manufacturing systems are analyzed in order to realize a distributed autonomous real-time scheduling system which can cope with such disruptions as breakdown of equipment and interruption of high priority lots. An object-oriented model is developed to represent the activities of the individual components and communication among the components. Decision-making criteria of the individual components are established in order to carry out real time scheduling. A prototype of a distributed autonomous scheduling system has been implemented in smalltalk, and applied to the real-time production scheduling problem considering unscheduled disruptions. It is shown, through case studies, that the method proposed here is effective for realizing a scheduling system to cope with unscheduled disruptions.

Design and Management of Autonomous Distributed Manufacturing System. Modeling and Application to Production Scheduling.

This paper deals with an object-oriented modeling of an autonomous distributed manufacturing system and its application to the production scheduling. The architecture of the autonomous distributed manufacturing systems is discussed from the viewpoint of information processing in the manufacturing system. An object-oriented modeling method is applied to describe the decision-making activities and the communication activities of the components, such as the manufacturing devices and the workpieces. The activities of the objects are discussed in detail from the viewpoint of the production scheduling. The contents of the objects are clarified, and the part-of relations and the is-a relations between the objects are also established. A distributed production scheduling method is proposed on the basis of the autonomous decision making of the individual components and their coordinations.