Lada Alexander and Smirnov Sergey. The Multi-Agent method for real time production resource-scheduling problem // J. Kacprzyk (Ed.). Proceedings of the International Conference on Information Technologies: Information and Communication Technologies for Industry and Research (ICIT-2019), Yuri Gagarin State Technical University of Saratov, Saratov, February 7-8, 2019. – Recent Research in Control Engineering and Decision Making / Studies in Systems, Decision and Control (SSDC), Vol. 199. – Springer. – P. 103-111. – ISBN 978-3-030-12071-9. ISSN 2198-4182. DOI:https://doi.org/10.1007/978-3-030-12072-6.
An operational scheduling method of production resources for enterprises has been analyzed and is being proposed. In order to assemble a client’s order, it is necessary to produce each detail by making the number of technological operations via an appropriate production resource. For scheduling and managing the production process, it is necessary to define the whole structure of the final assembly with a technology map. This representation is proposed by using a special ontological definition, and give the example for an enterprise producing electrical products. The process of scheduling has a high level of complexity due to the variety of types of resources used, and the dependence of production processes on many factors and conditions. Also considered real time events and each time getting information about a new fact of processing of each detail on each resource, the current production plan has to be rescheduled. Traditional methods for solving the problem are not possible using in real time scheduling, which is why it is proposed the multi-agent approach for that task. The developed system based on the proposed method is used by the real enterprise produces electrical products in Samara city, where, as a result, the number of delays in the execution of production orders was reduced by 10%.
George Rzevski, Petr Skobelev, Alexey Zhilyaev, Oleg Lakhin, Igor Mayorov and Elena Simonova. Customization of Multi-Agent Systems for Adaptive Resource Management with the Use of Domain Ontologies // International Journal of Economics and Statistics. – 2018, vol. 6. – P. 112-124.
Nowadays, the demand for increasing business efficiency is constantly growing, calling for development of resource management systems that can be applied to solve a wide range of complex tasks with minimum costs and within a limited time period. Unfortunately, traditional combinatorial or heuristic methods and tools cannot reach good enough solutions for complex tasks of real-time resource management. For this reason, the paper considers multi-agent technology as the key element of the required solutions. It can help find the balance of interests of all parties involved and flexibly adapt it to unpredictable events, such as, for example, a new order, inaccessible resources, delay of operations, etc. This paper presents the use of ontology for planning, giving the opportunity to develop an ontological enterprise model and a generic multi-agent scheduler, as well as to customize the appropriate requirements for each operation in business processes or technological processes in production applications, project management, supply chains and so on. At the top of the ontology editor is the Semantic Wikipedia, supporting the enterprise knowledge base for the tasks of resource management. The paper also provides examples of applications for supply chain in insurance business and management of maintenance of complex technical objects.
Petr Skobelev, Valery Eliseev, Igor Mayorov, Vitaly Travin, Alexey Zhilyaev, Elena Simonova. Designing distributed multi-agent system for aggregate and final assembly of complex technical objects on ramp-up stage // Proceedings of the 10th International Conference on Agents and Artificial Intelligence (ICAART 2018), Funchal, Madeira, Portugal, 16-18 January, 2018, vol.1. – SCITEPRESS. – P. 250-257. DOI:10.5220/0006636202500257
The paper covers the problem of aggregate and final assembly of complex technical objects at the ramp-up stage. New models, methods and tools for distributed scheduling are proposed, including modified version of virtual market with new classes of agents. The new feature of multi-agent scheduler considers knowledge base technology which helps to specify each operation in more detailed and individual way. The paper describes first system prototype for adaptive planning at the ramp-up stage and the main directions of future system development.
Damien Trentesaux, Adriana Giret, Flavio Tonelli, Petr Skobelev. Emerging key requirements for future energy-aware production scheduling systems: a multi-agent and holonic perspective // Borangiu, T., Trentesaux, D., Thomas, A., Leitao, P., Barata Oliveira, J.A. (Eds.): Proceedings of the 6th Workshop on Service Orientation in Holonic and Multi-Agent Manufacturing (SOHOMA16), October 6-7, 2016, Lisbon, Portugal. – «Service Orientation in Holonic and Multi-agent Manufacturing», series «Studies in Computational Intelligence», Vol. 694 – P. 127-141. – Springer International Publishing, Switzerland, 2016. DOI: 10.1007/978-3-319-51100-9.
The aim of this paper is to study a set of emerging key-enabling requirements for the design of multi-agent or holonic manufacturing systems
dealing with the energy aware scheduling of future production systems. These requirements are organized according to three different views, namely informational, organizational and lifecycle views. It is shown that these emerging key-enabling requirements are not sufficiently addressed by the literature. An illustrative futuristic example of a system complying with these requirements is provided. From this example, new research opportunities and issues can be easily found.
Yaroslav Shepilov, Daria Pavlova, Daria Kazanskaia, Valerii Novikov. Multithreading MAS for real time scheduling // Proceedings of the 16th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (IEEE/ACIS SNPD 2015), 1-3 June, 2015, Takamatsu, Japan. – IEEE, 2015. – P. 1-6.
The scheduling is widely used for organizing the processes in time in different spheres ranging from the simple school timetables to production plans of the biggest factories with
thousands of employees. In the most of cases this process has to be supported and managed by the complex tools, sometimes based on mathematical principles. In the paper the description of scheduling problem is given, the existing methods and tools for solving this problem are described, the approach based on multiagent multithreading application is considered. Nowadays there exist numerous approaches to solving of the scheduling problem. The suggested method of multithreading multi-agent scheduling allows efficient and fast solution of complex problems featuring rapid dynamic changes and uncertainty that cannot be handled by the other methods and tools.
Daria Kazanskaia, Yaroslav Shepilov, Bjorn Madsen. Adaptive production management for small-lot enterprise // V. Marik, et al. (Eds.): Proceedings of the 7th International Conference on Industrial Applications of Holonic and Multi-Agent Systems (HoloMAS’2015), September 2-4, 2015, Valencia, Spain. – HoloMas 2015, LNAI 9266. – P. 157-168, 2015. Springer International Publishing, Switzerland, 2015
Currently the methodology of eliminating the negative effects of the issues in ramp-up stage mostly involves the increase in investment and updating the design data. In the paper the authors consider an approach that can be applied on every level of ramp-up production: from suppliers to shopfloor operators. The architecture of the system is described and the first implementation results are given.
Alexander Tsarev, Daria Kazanskaia, Petr Skobelev, Sergey Kozhevnikov, Vladimir Larukhin, Yaroslav Shepilov. Knowledge-driven adaptive production management based on real-time user feedback and ontology updates // Proceedings of the EEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2013), October 13-16, 2013, Manchester, UK. – 2013. – P. 4755-4759.
This paper presents the principles of the knowledgedriven adaptive management in manufacturing. The problems of real-time resource allocation, reaction to the unexpected events, on-the-fly update of the knowledge stored in ontology are considered. The possibilities of simultaneous change of the existing factory or workshop processes and schedules according to the information provided by the users are described. Finally, the possible ways of development of the presented approach and its application in production resource management are considered.
Cesar Marin, Lars Moench, Paulo Leitao, Pavel Vrba, Daria Kazanskaia, Vadim Chepegin, Liwei Liu, Nikolay Mehandjiev. A Conceptual Architecture Based on Intelligent Services for Manufacturing Support Systems // Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2013), October 13-16, 2013, Manchester, UK. –2013. – P. 4749-4754.
The contribution of this paper is a conceptual architecture based on intelligent services for manufacturing support systems. Current approaches cannot cope with the dynamism inherent in the manufacturing domain, where unexpected and drastic changes occur at any time and affect cross-boundary systems. Our approach alleviates these issues and focuses on the need for supporting real-time automatic negotiation, planning, scheduling and optimisation, intra and across factories. We present an execution example of our approach in the aerospace industry, instantiating the conceptual architecture using different technologies. With this we push forward a new definition of Intelligent Services and indicate future work in the area.
Paulo Leitão, José Barbosa, Pavel Vrba, Petr Skobelev, Alexander Alexander, Daria Kazanskaia. Multi-agent System Approach for the Strategic Planning in Ramp-up Production of Small Lots // Proceedings of the IEEE International Conference on Systems, Man, and Cybernetics (IEEE SMC 2013), October 13-16, 2013, Manchester, UK. – 2013. – P. 4743-4748.
This paper discusses the methodology for the development of a strategic planning tool, and particularly the architectural solution to be adopted, within an integrated ICT solution for the improvement of planning and scheduling systems for the manufacturing of small production lots of complex products. After the analysis of different possible architectural solutions, the paper proposes a hybrid solution that combines existing solvers with the multi-agent system principles. The proposed approach introduces several benefits, namely in terms of flexibility, robustness, and achievement of exploratory alternative solutions, playing interactive what-if simulation supporting decision-makers to take strategic decisions.
V. Shpilevoy, A. Shishov, P. Skobelev, E. Kolbova, D. Kazanskaia, Ya. Shepilov, А. Tsarev. Multi-agent system “Smart Factory” for real-time workshop management in aircraft jet engines production // Proceedings of the 11th IFAC Workshop on Intelligent Manufacturing Systems (IMS’13), May 22-24, 2013, São Paulo, Brazil. 2013. №2. – P. 204-209.
The paper presents design principles of multi-agent system “Smart Factory” for real time resource management in manufacturing workshops. This objective is achieved by flexible event-driven reaction on changes in factory environment, resource allocation, scheduling, optimization and controlling in real time. The developed method of adaptive resource scheduling based on multi-agent technology, main functionality and architecture of the system are discussed. The results of application and measured benefits for aircraft jet engines manufacturer are presented.
Ivan Tyrin, Andrey Vylegzhanin, Elina Kolbova, Oleg Kuznetzov, Petr Skobelev, Alexander Tsarev, Yaroslav Shepilov. Multi-Agent System “Smart Factory” for Real-time Workshop Management: Results of Design & Implementation for Izhevsk Axion-Holding Factory. – Proceedings of the 2012 IEEE 17th International Conference on Emerging Technologies & Factory Automation (ETFA 2012), September 17-22, 2012, Krakow, Poland. – 4 pp.
This paper describes the results of design and implementation of a multi-agent system for real time scheduling and controlling in the Izhevsk Axion-Holding Factory. Lessons learned, key measured benefits of solution and perspectives are presented.
Alexey Goryachev, Sergey Kozhevnikov, Elina Kolbova, Oleg Kuznetsov, Elena Simonova, Petr Skobelev, Alexander Tsarev, Yaroslav Shepilov. «Smart Factory»: Intelligent System for Workshop Resource Allocation, Scheduling, Optimization and Controlling in Real Time. – Proceedings of the 2012 International Conference on Manufacturing (Manufacturing 2012), November 14-15, 2012, Macau, China. – Advanced Materials Research, Vol. 630 (2013), pp. 508-513, Trans Tech Publications, Switzerland.
The paper describes intelligent system “Smart Factory” which is designed to increase factory productivity and efficiency of resources utilization in real time (including equipment, manpower, materials, etc.).
The objectives and key areas of application are considered and it is shown that system provides flexible event-driven reaction on changes in factory environment, resource allocation, scheduling, optimization and controlling in real time. The developed method of adaptive resource scheduling, main functionality of system and examples of screens are discussed.
The results of implementation and measured benefits for Izhevsk Axion Holding are presented.