A Hybrid Knowledge Structure for Process Plant Fault Diagnosis

A method of capturing the complete knowledge of a process plant, for making system is proposed. Provisions have been made to acquire the knowledge of the plant in a hybrid way, which describes the domain-specific, heuristic and the control knowledge. The domain knowledge includes structural and behavioral information about a plant. The heuristic knowledge includes hypotheses regarding fault-location and fault-cause about its structure, behaviour and function. The control knowledge not only contains the procedures for diagnosis, but also comprises of the information regarding the control mechanism about now to access different parts of the Knowledge Base (KB). In the proposed method, the KB for the entire plant is partitioned into a set of Functional Blocks (FBs) which reduces the problem of locating any malfunction to a manageable propotion. The method of knowledge representation is structured and hybrid. The structured organization of KB makes a diagnostic procedure easy, while the hybrid representation makes the KB general and flexible.