Abstract
A fuzzy identification model and fuzzy logic controller was developed aiming the environmental control of an agriculture greenhouse. The fuzzy identification of the process was performed by the analysis of the data collected either during normal operation, as well in reaction to random generated actuating signals on the heating, ventilation and CO2 injection systems. A comparative study has been realized between fuzzy and physical models. Using the fuzzy model it was possible to implement an accurate Generalized Predictive Control (GPC) strategy in order to regulate the environment and to minimize energy consumption. The optimal setpoints were computed by means of balancing the benefits associated with the marketable produce against the costs associated with its production. The calculations use growth, photosynthesis and climate models. This work describes the practical development of an fuzzy controller that memorize the optimal strategy, executed by the GPC, to regulate the temperature and the CO2 concentration of the greenhouse inside air.

Abstract
The recent new developments in hardware and software tools, and in particular of the microprocessors and microcontrollers, are leading to more complex control and management potentialities in the agriculture applications. For the quality and productivity improvement of greenhouse crops it is necessary to measure and control several interacting physical variables. Also, to achieve competitiveness in the market, the production costs must be kept as low as possible. These tasks can only be accomplished using control and management systems with adequate built in software. At the University of Tras-os-Montes and Alto Douro, Vila Real, a data acquisition and control network was implemented with the aim of being applied to agricultural processes. This network has three main operating levels. At the lower level, a set of remote microcontroller stations performs the data acquisition and transmission by radio frequency to a collecting and control station. The control station generates the actuating signals for the agricultural process and communicates with a higher level network, based on PC's. This higher level network is responsible for the system management and supervision. In this paper it will be described the implemented network and the results achieved in its application to the greenhouse environmental and control.

Abstract
A major transport company working in a urban environment, in Portugal, has been developing an automatic vehicle location (AVL) system, based on a telemetric system to assist the optimisation of vehicle use, time-tabling and scheduling. The data is used in real time and stored on disk for later statistical analysis. Several factors can corrupt data during acquisition and transmission, and make it impossible to automatically extract useful information. A pre-processing stage is needed to extract inconsistent data. The paper describes a strategy, based on simulation, to pre-process the data in order to analyse data consistency and classify the messages as correct or incorrect. Copyright (C) 1998 IFAC.

Abstract
Fuzzy Logic is a part of Artificial Intelligence science and provides for control of complex processes, where exact models are not applicable. Such a controller is necessary for the process of drying oil filled transformers. Indeed, this controller needs to tackle with a highly non-linear and time variant process. The development of the controller was fast and the implementation size very small. Its performance proved very robust whilst providing both good dynamical and steady-state behaviour.

Abstract
The control of fermentation is very important in order to ensure a sustained level of wine quality year after year. Usually wine fermentation is carried out at a constant temperature. This fact is due mainly to traditional reasons. Nevertheless the results year after year and from region to region may be very different due to large variations in must characteristics. A more complex control is needed to overcome this fluctuations. Recent works have introduced some innovation but still have some empirical characteristics and can not control the duration of fermentation. In order to predict the behaviour of the fermentation, a reasonably accurate mathematical model is required. Unfortunately mathematical models for wine fermentation are scarce, particularly for wine batch fermentation. In this work we develop a mathematical fermentation model and an industrial tank thermal model. A new control strategy is proposed: Relative density control instead of temperature control. A reference model is developed and we try to tune a PID controller to the process. The need of more complex controllers such as predictive controllers is addressed.

Abstract
In this article we present two methods for the real time automatic measurement of the relative density. The first one relies on the heat generated during the fermentation which requires no additional sensors in the tanks. It is based on the thermal model of the tank and the only additional requirements are the measurement of the temperature of the surrounding air. The other method is based on two low-cost pressure sensors with an algorithm for autocalibration and compensation of temperature perturbation. The autocalibration is done during fermenter feeding and with only one manual measurement of the relative density.