Autonomous Manufacturing Systems Research Articles

An autonomous manufacturing system based on swarm of cognitive agents

Disruptions of the manufacturing systems caused by the disturbances such as the tool wear, machine breakdown, malfunction of robot or transporter, and so on reduce the productivity as well as increase the cost of product. The conventional manufacturing systems are unable to face with the disturbances by their rigid structure. These systems should be stopped when the disturbances occur. The paper presents an Autonomous Manufacturing System based on Swarm of Cognitive Agents (AMS-SCA) in order to adapt to the disturbances. In the AMS-SCA, the manufacturing system is considered as a swarm of cognitive agents where work-pieces, machines, robots, and transporters are controlled by the corresponding cognitive agents. The system reacts to disturbances autonomously based on the reaction of each agent or the cooperation among them. To develop the AMS-SCA, the disturbances happened in the machining shop were analyzed to find out the corresponding management methods. A test-bed was implemented to prove the functionality of the proposed AMS-SCA.

자율적 제조 공정 관리를 위한 인지 에이전트의 개미 군집 지능

The flexibility and evolvability are critical characteristics of modern manufacturing to adapt to changes from products and disturbances in the shop floor. The technologies inspired from biology and nature enable to equip the manufacturing systems with these characteristics. This paper proposes an ant colony inspired autonomous manufacturing system in which the resources on the shop floor are considered as the autonomous entities. Each entity overcomes the disturbance by itself or negotiates with the others. The swarm of cognitive agents with the ant-like pheromone based negotiation mechanism is proposed for controlling the shop floor. The functionality of the developed system is proven on the test bed.

An autonomous manufacturing system for adapting to disturbances

Disruptions in manufacturing systems caused by system changes and disturbances reduce the productivity, and increase the downtime as well as the cost of products. To cope with these challenges, new strategies and technologies have been applied to build an adaptive manufacturing system, namely autonomous manufacturing system (AMS). In the AMS, workpieces, machines, robots, and transporters are the autonomous entities. They have an ability to identify their status and capability autonomously, to collect data, and to take decisions according to the changes of the manufacturing system. In order to implement the AMS, the agent and cognitive technologies were chosen. The AMS needs autonomy and cooperation for solving problems of agents from agent technology. The AMS also needs cognitive capabilities for agents based on cognitive technology. As a result, smarter agents with the cognitive abilities were applied. This paper presents a synthetic method of the two proposed technologies for building autonomous control entities, namely cognitive agents, which control the manufacturing system for adapting to disturbances. The cognitive agents with characteristics of intelligence, autonomy, and communication were proposed to develop the AMS.

Artificial Cognition in Production Systems

Today's manufacturing and assembly systems have to be flexible to adapt quickly to an increasing number and variety of products, and changing market volumes. To manage these dynamics, several production concepts (e.g., flexible, reconfigurable, changeable or autonomous manufacturing and assembly systems) were proposed and partly realized in the past years. This paper presents the general principles of autonomy and the proposed concepts, methods and technologies to realize cognitive planning, cognitive control and cognitive operation of production systems. Starting with an introduction on the historical context of different paradigms of production (e.g., evolution of production and planning systems), different approaches for the design, planning, and operation of production systems are lined out and future trends towards fully autonomous components of an production system as well as autonomous parts and products are discussed. In flexible production systems with manual and automatic assembly tasks, human-robot cooperation is an opportunity for an ergonomic and economic manufacturing system especially for low lot sizes. The state-of-the-art and a cognitive approach in this area are outlined. Furthermore, introducing self-optimizing and self-learning control systems is a crucial factor for cognitive systems. This principles are demonstrated by a quality assurance and process control in laser welding that is used to perform improved quality monitoring. Finally, as the integration of human workers into the workflow of a production system is of the highest priority for an efficient production, worker guidance systems for manual assembly with environmentally and situationally dependent triggered paths on state-based graphs are described in this paper.

Robot workspace estimation and base placement optimisation techniques for the conversion of conventional work cells into autonomous flexible manufacturing systems

Robot arms are used in modern work cells and flexible manufacturing systems (FMS) in handling work pieces and loading/unloading processes. The robot arm links may interfere with the bodies of the system components, which are considered as obstacles in the robot workspace. In order that the robot works in safe conditions, study of robot workspace in a free space and in the presence of obstacles should be investigated. The inverse problem of having an existing working space occupied with a number of CNC machines to which it is supposed to introduce a robot to serve is an interesting problem. This is a very common problem when trying to convert conventional work cells into autonomous systems. There are two main questions when studying this kind of problem: what type of robots is suitable to satisfy the existing working space? And where to place the base of this robot to efficiently serve the existing machines? The main objective of this article is trying to answer these two questions. A computational algorithm is developed to estimate the robot workspace. The optimisation of robot base placement is achieved using genetic algorithms. A comparative study of the suitability of different robots for a specified working area is also included. Finally, robot movement visualisation within a pre-defined FMS using solid edge modelling is presented to verify the proposed algorithm and simulate the robot path within the work cell.

The Research of Distributed Manufacturing System Based on Agent

The intelligence of manufacturing system by using the Agent technology has become a trend. The paper describes the current studies, analyzes the characteristics and problems of the distributed manufacturing system, and combines the advanced theoretical results in distributed artificial intelligence and behavior intelligence; finally it studies the theory and methods of global coordination and control for distributed autonomous manufacturing system based on behavior under modern manufacturing environment.

3304 自律型生産システムのためのエージェントの制御方法(OS3-3 先進生産システム)

3304 自律型生産システムのためのエージェントの制御方法(OS3-3 先進生産システム)

Manufacturing perspective of enterprise application integration: the state of the art review

Manufacturing enterprise today has become a matter of effective and efficient application of information technology and knowledge-based engineering. Several new manufacturing paradigms such as virtual enterprise (or extended enterprise) and mass customization have resulted in a highly distributed and autonomous manufacturing system. On the one hand, this will increase the competitiveness of a firm in terms of quickly meeting dynamic changes in the market; on the other hand, this will also increase the difficulty of integrating different information and knowledge systems residing in each member firm. This integration is also called enterprise application integration (EAI) (here the term application means information systems or software systems for supporting manufacturing or service activities). The methodology for EAI has been studied for at least a decade; but no satisfactory solution has been found from a practical viewpoint. EAI is becoming even more difficult due to the boom in various enterprise information and knowledge systems (and also to ever increasing competition in the technical software market). The study presented in this paper conducted a critical analysis of existing solutions to EAI. We consider EAI as having two generic issues: semantic integration and syntactic integration. The main problem of semantic integration reduces to the general problem of enterprise or business modelling. The main problem of syntactic integration reduces to the general problem of software architecture of enterprise applications which enables interoperability between any two EAs. While the first issue is studied in the manufacturing field, the second issue is studied in the computing engineering field. In this paper, both issues are put together under the context of EAI and studied. The result of the study, together with our experience with one Canadian manufacturing firm, has led to the identification of several issues to be addressed in the future. We also outline possible ways to approach these issues.

Metamodeling Techniques Applied to the Design of Reconfigurable Control Applications

In order to realize autonomous manufacturing systems in environments characterized by high dynamics and high complexity of task, it is necessary to improve the control system modelling and performance. This requires the use of better and reusable abstractions. In this paper, we explore the metamodel techniques as a foundation to the solution of this problem. The increasing popularity of model-driven approaches and a new generation of tools to support metamodel techniques are changing software engineering landscape, boosting the adoption of new methodologies for control application development.

NEXT GENERATION OF INTELLIGENT MANUFACTURING SYSTEMS: A SURVEY

The American Institute of Industrial Engineering formulated in 1955 the following paradigm for Manufacturing Systems: conceptual and detailed design, as well as socio- technologic- economic systems including heterogeneous resources (human, financial, technologies, capital, energy resources). During the last five decades many paradigm shifts have been identified. The paper is focused on the current achievements sustaining the time of convergence for different recent paradigm shifts. The authors do believe that Intelligent Autonomous Manufacturing Systems should be an appropriate purpose within global digital eve.

Real-time control of decentralised autonomous flexible manufacturing systems by using memory and oblivion

This paper describes a method that uses memory to determine a priority ranking for competing hypotheses. The aim is to increase the reasoning efficiency of a system which controls Automatic Guided Vehicles (AGVs) in Autonomous Decentralised Flexible Manufacturing Systems (AD-FMSs). The system includes memory data of past production conditions and AGV actions. Using these memory data, the system reorders hypotheses by giving the highest priority ranking to the hypothesis that is most likely to be true. The system was applied to an AD-FMS constructed on a computer. The results showed that this reasoning system reduced the number of hypothesis replacements.

Flexible integrated manufacturing - future challenges towards socially responsible manufacturing

This paper aims to develop Flexible Integrated Manufacturing (FIM) as an ultimate manufacturing system for future manufacturing perspectives. In the long term, it can ensure the fulfilment of social requirements while providing superior performance and thriving in an integrated autonomous cellular manufacturing system. Socially responsible manufacturing guarantees better productivity and competitiveness via the self-directed efforts of shop floor workers, as well as environmentally safe manufacturing processes by taking resource-saving and recycling-conscious manufacturing into account. A global view of manufacturing can be gained via alliances which can be initiated quickly and with minimal resources. Moreover, human-enriching cooperative manufacturing will be capable of being developed through team-based cooperative planning between production and marketing activities.

A Behavior-Based Approach to Scheduling in Distributed Manufacturing Systems

This article proposes a behavior-based approach to scheduling a distributed autonomous manufacturing system. A behavior-based approach advances self-control of the autonomous entities as an alternative to purely reactive control through negotiations.

Neural Networks in Manufacturing

Neural networks can be used to build autonomous manufacturing systems that can adapt to the changes in their environments. This paper provides some general discussion of the applications of neural network techniques in manufacturing and engineering. In particular, a new neural controller for process control and a novel network suitable for engineering classification and prediction tasks such as quality control and production monitoring are described.

Information system architecture for heterarchial control of large FMSs

In this paper we investigate the design of a distributed information management system for heterarchical (decentralized) shopfloor control in large Flexible Manufacturing Systems (FMS). We characterize the complexity of information management in automated manufacturing, and study the interaction between the shopfloor control system and the information management system. We describe protocols for a heterarchical control scheme, and identify the information content of messages that are transmitted between autonomous manufacturing system entities under this control paradigm. On the basis of the proposed shopfloor control protocols and the information requirements at each type of manufacturing system entity, we develop an information system architecture that is capable of supporting heterarchical shopfloor control in large FMSs.

An adaptive approach to tool wear sensing and decay rate control in autonomous manufacturing

This paper is concerned with tool management in autonomous manufacturing systems. On-line wear sensing, automatic decision making for tool replacement, and real-time optimization of cutting processes are focused on the turning problem. An adaptive control system designed to cope with this problem is described and discussed with application on the shop floor.

Artificial intelligence: Can it be economically applied?

Artificial intelligence (AI) is an emerging technology with great potential, particularly in manufacturing. But, has this technology matured to the point where its application can have a favorable financial impact? To answer this, existing AI technology is examined and evaluated for how well it can be applied to computer-aided manufacturing (CAM). Areas well suited to current AI CAM tools are identified. Following this analysis is a proposed autonomous manufacturing system that employs AI technology. A methodology for evaluating the fiscal soundness of this system is proposed and demonstrated.