Supervision of an industrial steam generator. Part I: Bond graph modelling

Model based supervision of most process engineering plants is difficult due to the complexities arising out of the energetic couplings in the model. Bond graph modelling is a suitable tool to represent the model structures of such processes along with their control system instrumentation. In this paper, bond graph model of a steam generator installation consisting of complex industrial components such as a boiler, a condenser, etc. is developed and validated through experimental observations. It is further shown that the causal properties of bond graphs not only allow validating the model, but they also provide the computational algorithms to eliminate the unknown variables from coupled thermo-fluid models and thus generate analytical redundancy relations (ARR) in terms of measurements and parameters. Structural analysis of the model is used to obtain the fault signatures and also to identify the hardware redundancies in the sensor placement. Thereafter, quantitative evaluations of ARR are used to yield residuals, which are subsequently implemented in an online integrated supervision system described in the sequel to this paper. The fault tolerant control and reconfiguration strategies implemented in that supervision platform are based on the available hardware redundancies in the process, which have been deduced directly from bond graph model using the methodology presented in this paper.