Objective Better automation is a key aspect for improving industrial competitiveness. Intelligent automation can play a major role in this. However, intelligent control systems are very expensive to build and don't usually cover all control layers. These costs can be reduced by building generic software components aimed at addressing different types of problems at different control layers, supported and integrated by a flexible architecture, and the definition of a methodology. This is the commitment of the DIXIT project partners.The structure of most distributed control systems is hierarchical and multilayered, similar to a pyramid, where abstraction as well as control mechanisms complexity increases in higher layers. DIXIT deals with problems and situations included in the intelligent control layers; operational, tactical and strategic. In particular, it focuses on the strategic level, especially on environmental, safety and maintenance aspects considering them together with other global objectives of the plant, such as production, quality, etc. All these objectives constitute a constraint network where priorities and weights have to be assigned depending on the situation.From the user point of view, a DIXIT application helps the plant staff in deciding and acting promptly and uniquely when an emergency is detected. This increases plant safety. In addition, it facilitates the access and integration of large amounts of information and complex data. Finally, the prevention of these emergencies is also an important benefit from the use of a DIXIT application.From the technical point of view, the DIXIT final product is composed of different software modules: user interface components, problem solving components and architectural components. The problem solving modules perform tasks such as failure detection, diagnosis, monitoring, tactic creation and recommendation, sensor validation, forecasting, alarm and emergencies handling, prevention, optimisation, etc. The technologies used are rule-based systems, neural networks, fuzzy logic, optimisation techniques, etc. In order to support the other modules and the distribution features, the DIXIT architectural components combines the blackboard paradigm (already proven as a successful approach for intelligent applications) with other paradigms related to distribution, such as agent architecture. A summarised overview of the DIXIT project is given below:The project aims at producing a software and methodological environment aimed at preventing and solving control problems at different intelligent control layers (operational, tactical and strategic). The strategic situations to deal with focus on safety, environmental and maintenance issues. The software environment consists of AI problem solving components integrated by means of a flexible and distributed architecture.Knowledge engineering techniques and software engineering methods, including object oriented technologies will be used and combined with distributed architecture paradigms in order to produce cheaper and more efficient software.The consortium is formed by five technical developer organisations (IIC, acting as co-ordinator, RH&H, DaCapo and UPM-DISAM and Euristic Systemes) and two users (Repsol Quimica and Lafarge Ciments). Four European countries are represented in the consortium. Fields of science natural sciencescomputer and information sciencessoftwareengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringcontrol systemsnatural sciencescomputer and information sciencesknowledge engineeringengineering and technologyelectrical engineering, electronic engineering, information engineeringelectronic engineeringsensorsnatural sciencescomputer and information sciencesartificial intelligencecomputational intelligence Programme(s) FP4-ESPRIT 4 - Specific research and technological development programme in the field of information technologies, 1994-1998 Topic(s) 1.7 - Emerging Software Technologies Call for proposal Data not available Funding Scheme CSC - Cost-sharing contracts Coordinator Asociacion Para El Desarrollo de la Ingenieria del Conocimiento - Instituto de Ingenieria del Conocimiento EU contribution No data Address Uam-Cantoblanco Modulo C-vi Planta 2 28049 Madrid Spain See on map Total cost No data Participants (4) Sort alphabetically Sort by EU Contribution Expand all Collapse all Dacapo Infix Sweden EU contribution No data Address Torggatan 8 41105 Goteborg See on map Total cost No data Lafarge Ciments France EU contribution No data Address Boulevard Louis Loucheur 5 92214 Saint-Claude See on map Total cost No data Ramboll, Hannemann & Hojlund A/S Denmark EU contribution No data Address Teknikerbyen 19 2830 Virum See on map Total cost No data Repsol Quimica Spain EU contribution No data Address El Morell, Ap.Do 398 43080 Tarragona See on map Total cost No data
