István Mezgár

Co-operative production planning for small- and medium-sized enterprises

Abstract Minimising manufacturing cost and production time parallel to raising the quality and the shipment reliability are important challenges in every production system. In case of distributed production systems the management of the above-mentioned criteria has great significance and needs a complex, co-operative handling of the problems. A new, co-operative manufacturing network model is proposed for co-ordinating the production of Small- and Medium-sized Enterprises (SMEs), based on the holonic paradigm. The paper introduces the main modules of the model succinctly and describes an application under realisation in Hungary, in an agricultural SME network, pointing its economic benefits as well.

The challenge of networked enterprises for cloud computing interoperability

Abstract Manufacturing enterprises have to organize themselves into effective system architectures forming different types of Networked Enterprises (NE) to match fast changing market demands. Cloud Computing (CC) is an important up to date computing concept for NE, as it offers significant financial and technical advantages beside high-level collaboration possibilities. As cloud computing is a new concept the solutions for handling interoperability, portability, security, privacy and standardization challenges have not been solved fully yet. The paper introduces the main characteristics of future Internet-based enterprises and the different CC models. An overview is given on interoperability and actual standardization issues in CC environments. A taxonomy on possible connecting forms of networked enterprises and cloud-based IT systems with reference on interoperability is introduced, parallel presenting four use cases as well. Finally, an example of connecting cloud and NE is presented as an effective application of cloud computing in manufacturing industry.

New perspectives for the future interoperable enterprise systems

The paper describes the information system and interoperability related challenges, trends and issues that must be addressed to support a new generation of scientific-based and technological solutions for facilitating the collaboration of existing enterprise systems.This paper presents general research priorities and directions of related to context-aware systems, semantic interoperability, cyber-physical systems, cloud-based systems and interoperability assessment.The listed properties are used to propose the generic abstract architecture of the Next Generation Enterprise Information Systems. The rapid changes in todays socio-economic and technological environment in which the enterprises operate necessitate the identification of new requirements that address both theoretical and practical aspects of the Enterprise Information Systems (EIS). Such an evolving environment contributes to both the process and the system complexity which cannot be handled by the traditional architectures. The constant pressure of requirements for more data, more collaboration and more flexibility motivates us to discuss about the concept of Next Generation EIS (NG EIS) which is federated, omnipresent, model-driven, open, reconfigurable and aware. All these properties imply that the future enterprise system is inherently interoperable. This position paper presents the discussion that spans several research challenges of future interoperable enterprise systems, specialized from the existing general research priorities and directions of IFAC Technical Committee 5.3,11IFAC Technical Committee 5.3 ??Enterprise Integration and Networking??, http://www.ifac-tc53.org namely: context-aware systems, semantic interoperability, cyber-physical systems, cloud-based systems and interoperability assessment.

Design and real-time reconfiguration of robust manufacturing systems by using design of experiments and artificial neural networks

Abstract A methodology for design and real-time reconfiguration of robust manufacturing systems is described which combines design of experimental technology, Taguchi method and knowledge-based simulation techniques. Artificial neural networks are proposed for mapping between design factors and system performance. The applicability of the approach is analysed through experiments for the estimation of the throughput time, and the determination of Automated Guided Vehicle (AGV) speed in a given system. In contrast to the simulation-based approach, the solution using artificial neural networks can also be used in real-time circumstances.

Application of artificial intelligence to problems in advanced manufacturing systems

Abstract Flexible manufacturing systems (FMS) are used worldwide for the production of parts in CIM systems. The design and operation of an FMS can be achieved only by the teamwork of several experts using different computer programs. Because of the complexity and diversity of the problems to be solved, traditional programming can be used only if combined with artificial intelligence techniques, such as expert and knowledge-based systems. This paper deals with the application of expert systems to assist in quality control and the simulation and control of FMSs. Well known traditional simulation (Cinema/SIMAN) and networking (MAP) packages are combined with high performance expert systems (ALL-EX, G2) to provide acceptable solutions. This paper reports on recent work where rapid prototype rograms are under test, with the ultimate goal of providing industrially applicable programs.

Concurrent design of automated manufacturing systems using knowledge processing technology

Abstract Flexible manufacturing systems (FMS) built up from smaller, complex units, i.e. from cells (FMC) are becoming typical examples of flexible systems. The design and the operation (control) of these cells need new methods to utilize all the embedded benefits of the sophisticated and expensive elements installed for production purposes. In the case of such systems the life-cycle engineering approach has an important role. This means that during the design of automated manufacturing systems the technological plans of the future products strongly have to be taken into consideration. New technologies and methods like knowledge processing technology and cooperative problem solving techniques offer wide possibilities to design more reasonable systems. The paper describes a prototype design system that makes use of different knowledge based tools and techniques to configure, or reconfigure manufacturing cells taking into consideration technological plans. There is also a possibility for analyzing the cells by simulating and animating their operation.

Integrated application of real-time expert systems for FMS evaluation and control

The paper describes some applications of expert systems (ES) for flexible manufacturing systems (FMS). A complex FMS simulation tool is shown with different connection possibilities to expert systems to have a good evaluation performance and the make steps toward automatic control. The interfacing problems of the software modules are also discussed. In the recent stage of the research rapid prototype programs are under test, and the future goal of CIM Research Laboratory (CIMLab) is to solve industrial problems with these tools and softwares.

Trust Building for Enhancing Collaboration in Virtual Organizations

Virtual organizations play an important role in today’s economy, as they are able to adapt themselves to the turbulent market environments. Team work and collaboration are main characteristics of virtual organizations, so the contacts among human beings have outstanding importance. A very important element of this human contact is trust. Trust building in virtual organizations has special characteristics, it is influenced among others by the type of media and communication device, and also by the duration of cooperation. The paper discusses the role of trust and trust building in the operation of virtual organizations from these aspects.

Knowledge-Based Hybrid Techniques Combined with Simulation: Application to Robust Manufacturing Systems

Publisher Summary Knowledge-based hybrid systems (KBHSs) play an increasing role in industrial applications. New techniques of artificial intelligence (AI) such artificial neural networks (ANNs), genetic algorithms (GEs), machine learning (ML), or the fuzzy set theory have created new ways of solving problems. Most of these new techniques, however, are not appropriate for handling complex tasks alone; therefore, their integration with or connection to other systems is obligatory. The different types of KBHSs are the result of this development trend, as in their case the goal is to solve complex problems of a well-defined limited area. This chapter defines and classifies KBHSs, including the integration possibilities with simulation. Several examples of industrial applications of various types of KBHSs are described. KBHSs will have an increasing role in industry in future, as they are a significant source of support for users in a variety of applications. The representation, design, and control of dynamic, stochastic, and complex systems (like manufacturing systems) can be intensively supported by KBHSs.

COMBINED USE OF SIMULATION AND AI/MACHINE LEARNING TECHNIQUES IN DESIGNING MANUFACTURING PROCESSES AND SYSTEMS

In the paper different architectures with partly self-developed simulation packages are described illustrating the benefits of combining simulation and machine learning (ML) techniques in manufacturing. From the artificial intelligence (AI) and ML side, artificial neural networks, heuristic search, simulated annealing, and agent-based techniques are put into action. The applicability of the proposed solutions is illustrated by the results of experimental runs.