Probabilistic Model-Based Degradation Diagnosing of Thermal System and Simulation Test

This paper proposed a probabilistic model-based approach to diagnose the possible parameters deviations that cause energy system degradation. It is competent for differentiating the deviations that is usually indiscernible in conventional physical model-based analysis. Probabilistic model combines domain knowledge and statistical data. Its diagnostic output provides a probabilistic confidence level for optimum operation. Operator´s own experience can also contrast with the model output to improve operation availability. A prototype model is tested on a full-scope simulator to verify its practical availability