Aleksandra Dvoryanchikova

Ontology‐based context‐sensitive computing for FMS optimization

Purpose – The purpose of this paper is to present an ontology‐based approach of context‐sensitive computing for the optimization of flexible manufacturing systems (FMS).Design/methodology/approach – A context‐sensitive computing approach is presented, integrated on top of FMS control platform. The approach addresses how to extract manufacturing contexts at source, how to process contextual entities by developing an ontology‐based context model and how to utilize this approach for real time decision making to optimize the key performance indicators (KPIs). A framework for such an optimization support system is proposed. A practical FMS use case within SOA‐based control architecture is considered as an illustrative example and the implementation of the core functionalities to the use case is reported.Findings – Continuous improvement of the factory can be enhanced utilizing context‐sensitive support applications, which provides an intelligent interface for knowledge acquisition and elicitation. This can be ...

Modeling system of systems: A generic method based on system characteristics and interface

In the 90s there was introduced concept of system of systems (SoS) in order to deal with growing complexity, geographical distribution, and heterogeneity of the various technological systems such as, for instance, modern factories. Methods of the traditional system engineering have been challenged in capturing of SoS specific nature like evolving requirements, ambulatory boundaries, decentralization, and other. In order to analyze, simulate and modify such kind of systems, there should be developed modeling methods and tools which would be capable to encompass the SoS specific properties. The aim of this work was to propose a computational method to model SoS, which could be further applied to the description and simulation of the highly distributed, heterogeneous, and networked production systems of the future. It was concluded that the proposed approach is able to provide the static and dynamic descriptions of the SoS-components and the communication between them in detailed yet relatively simple mode. For further maturing of the approach and with order to prove the applicability of the method proposed, next steps will be implemented: the method will be tested on a tesbed of a production line, and then a modeling of a real use case from the domain of manufacturing is preplanned.

Ontological framework of context-aware and reasoning middleware for smart homes with health and social services

Modern buildings are equipped with multiple systems, which are dedicated to improve quality of living for inhabitants and to facilitate performance of daily duties for maintenance personnel. Yet the variety of the systems causes the bulky informational flow, which may result informational tense to the user, time lost and increase of errors. To make life comfortable in a smart house, the inhabitants of the building should have an access to the simple and intuitive control and monitoring of the apartment, and the maintenance personnel should have a handily informational support for the prioritizing and efficient performance of the maintenance tasks. Thus, there is a need in intelligent management of information flow to provide data to the users with regards to the context like for instance on-going situation and goals, users intentions, state and role in the system. This paper proposes framework of context-aware middleware as a solution for information management in the system. Context-awareness is achieved with ontological knowledge models of the system and two-level reasoning upon the ontologies. The enabled technologies are discussed with relation to the use case, which is a combination of smart home and elderly care services. Future steps towards framework realization end the paper.

An ontology-based semantic foundation for flexible manufacturing systems

The aim of this manuscript is to present an ontology-based knowledge representation for flexible manufacturing systems (FMS), providing a comprehensive semantic foundation of the facility. Domain ontology model is addressed that captures and formally represents the manufacturing semantics from heterogeneous data sources allowing knowledge sharing, re-use and update. Reported semantic foundation enables the plant operations to become knowledge intensive, distributed and collaborative in nature. It enables knowledge management among various design tools and knowledge exchange in an adaptive operation environment through decision support applications. A framework for such a knowledge-based optimization support system is also proposed. A practical FMS use case is considered as an illustrative example in this work.

Service oriented computing to Self-Learning production system

The aim of this manuscript is to present what is Self-Learning production system and how service oriented architecture (SOA) and supporting technologies are bridged together to implement this new concept in the ongoing EU Self-Learning production system project. A brief review of the most recent EU projects that have reported results relevant to the main discussed investigation problems is presented. Reference architecture and functionalities of Self-Learning production system is introduced aiming for improved control and maintenance in production plants. Service oriented computing to Self-Learning production system is proposed to meet the required level of flexibility, interoperability and communications needs for reusable Self-Learning services. A roadmap for future research is defined.

Context-aware knowledge-based middleware for selective information delivery in data-intensive monitoring systems

Multiple embedded devices in modern control and monitoring systems are able to sense different aspects of the current context such as environmental conditions, current processes in the system and user state. The number of captured situations in the environment and quantity and variety of devices in the system produce considerable amounts of data, which should be processed, understood and followed by corresponding actions. However, fully delivered to the user regardless of their role in the system and needs, data flows cause cognitive overload and thus may compromise the safety of the system depending on the timely response of the operators. This paper addresses the problem of selective information delivery with respect to the user?s role in the system, his needs and responsibilities, by proposing context-aware information management middleware. The system utilizes Semantic Web technologies by capturing relevant information in the knowledge model of the system, which decouples data from the application logics. A clear division of data and application logics enables context-awareness and facilitates the reconfiguration process, when new information should be added into the system. The chosen approach is justified with an analysis of main trends in context-aware solutions. The engineering principles of the knowledge model are described and illustrated with simple scenarios from the building automation domain. The prototype developed proves the feasibility of the approach via performance evaluation and demonstrates the reconfiguration capabilities of information flows in the system. Further work assumes the extension of the knowledge model and integration of the system with adaptive human-machine interfaces for multi-role and multi-user environments.

Pro-active content managing system for efficient human machine interaction in data intensive environments

The informational flow in modern technological systems is intensive due to multiple embedded devices, which leads to informational overload for users, causes time lost and decreases the reliability of the performance of a human-machine system. There is a need for efficient managing of information in order to display it to a particular user accordingly to his/her current needs. This paper presents the concept of a Virtual Control Room (VCR) which is a proactive content-managing context-aware system aiming to facilitate human-machine interaction and the process of human decision/making in data intensive environments. The system collects, models, and reasons the context information and displays it in a personalized way via pro-active and adaptive multimodal Human Machine Interfaces (HMIs) on mobile devices. As a result, users can monitor and control the system from any location in a comfortable manner. The breakthrough is seen in a semantic Web based solution, which considers ontological dynamic context models with two level reasoning on top, and adaptive HMIs which support functionality on different mobile devices with introduction of modern technologies like 3D and augmented reality. The VCR concept is illustrated using two possible application domains, which are seen as important and challenging both from a socio-economic and from a technical perspective: building and manufacturing domains.

Application of the generic modelling method for system of systems to manufacturing domain

Meeting challenges of the competitive market, modern manufacturing systems are evolving to heterogeneous and distributed network of systems which can be seen as an application of systems of systems (SoS). There is a challenge to develop adequate modelling techniques and tools which would be able to capture paradoxical nature of SoS with its evolving boundaries and requirements, network centricity, heterogeneous composition, and distributed facilities in order to visualise, to design and to analyse modern manufacturing systems. The paper describes results of the first stage of an on-going research. The stage is dedicated to an application of the method based on modelling of SoS characteristics and interfaces between component systems to a conveyor-based pallet transferring system. With control of decentralization, each module of such a system can be seen as a subsystem for a SoS. The results of the application show that the method applied allows to provide description of the production system, and the model can automatically evolve with modifications in the system like for instance increase of the components. In the next stage of the research, the method will be applied to a more complex use case from the domain of composite materials manufacturing which can be considered as a SoS application, the development of a software environment for modelling and simulation is planned.

A device configuration management tool for context-aware system

Automation industry is moving towards more complex systems which are posing new challenges for operation from both machine and human perspectives. A group of challenges is related to management of the overwhelming information flow and to usability of the systems, and context-aware solutions have been recently introduced to the automation field in order to cope with challenges of this kind. The context awareness is seen as a solution which would allow to both the technological system and the human operator to infer the optimal decisions and to behave in the most effective way. In order to reach this capability, the external physical world and the system must be described in a way both interprétable for humans and machines. Ambition of this paper is to contribute to the context-aware (re)configuration of the system with a tool, which is designed to improve the efficiency of the configuration phase of a context-aware system. The tool provides a solution to configure and model the field devices of a system via automatically generated ontologies. This research is a part of a device management framework for a building automation use case, which is targeting to support controlling decisions of dwellers, technical support and social services.

Connectionism-inspired knowledge modeling for industrial systems

This paper introduces connectionistic concept grid (CCG), which is used for representation and reasoning of engineering knowledge applied for the industrial systems. The paper also presents the Crossword tool which was used for computer aided modelling and execution of CCG. CCG is able to provide semantic descriptions of objects and processes and was developed to overcome limitations of earlier knowledge approaches in expression of temporal relations between objects. The scope of this article includes an explanation of the principles for the proposed approach. The execution principles of the model, description of the tool and simple illustrative scenario of industrial equipment used in automated assembly line are discussed. It is assumed that the equipment interfaces are implemented as web services.