Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models
Learning and Soft Computing: Support Vector Machines, Neural Networks, and Fuzzy Logic Models
Stochastic modeling as a means of automatic speech recognition.
Stochastic modeling as a means of automatic speech recognition.
Ecological predictive maintenance in urban fleets
EE'10 Proceedings of the 5th IASME/WSEAS international conference on Energy & environment
| Hi-index | 0.00 |
Terology is defined as the combined use of techniques of operational research, information systems and engineering, with the objective of accompanying the life cycle of facilities and equipments; it includes the definition of specifications referred to its purchase, installation and reception, as well as the management and control of its maintenance, modification and substitution and, still, its accompaniment in service. Under this perspective, maintenance is the core of terology and it correspond a subject that, instead of reducing importance of maintenance with the increasing of equipment reliability, it increases its role in the companies and obliges the increasing of the level of demand of professionals involved because of the new technical and environmental demands. This reveals the importance of this scientific area and the necessity to concentrate and to increase the research around it. The maintenance area is an example that offers challenges to both science and companies in order to optimize the performance of equipment and facilities. But, the scientific developments, namely in this area, must be more and more environmentally friendly or, in other words, must close the technology to nature, guarantying its life through an adequate maintenance management. It is because of this kind of challenge that the authors are developing new methodologies, almost antagonistic, because of the areas under development, namely diesel engines and wind generators, but as we will demonstrate, areas which are compatible and can contribute for a better environment. In the case of wind generators, the methodology aims to optimize the cycles of production and, consequently, reduce the other kinds of energy production. On the other hand, the methodologies for maintenance of diesel engines are based on environmental indicators that can predict the "health state" taking into account restrictions including health human factors among others. The new methodologies will later be incorporated through new predictive maintenance modules in an integrated maintenance management system called SMIT (Terology Integrated Modular System). The SMIT was developed as a traditional system, but it includes several innovations, like a fault diagnosis module, a non-periodic maintenance planning module and a generic on-condition maintenance module, among others. The new features will include, in the case of wind generators, on-line measures and the corresponding on-time treatment, using algorithms based on time-series forecasting and TCP/IP technology to transmit the signals. In the case of diesel engines, the algorithms are based on Markov chains and hidden Markov chains. It is based on these developments and the new researches mentioned so far, that this paper is built upon, and we believe that it will be a contribution to the maintenance management area.