Qualitative reasoning: modeling and simulation with incomplete knowledge
Qualitative reasoning: modeling and simulation with incomplete knowledge
Foundations of Fuzzy Systems
Human-like fault diagnosis using a neural network implementation of plausibility and relevance
Neural Computing and Applications
| Hi-index | 0.00 |
A complex system in industry is often a conductive flow system. Its abnormal behaviour is difficult to manage due to incomplete and imprecise knowledge on it, also due to propagated effects that appear at faults. Human experts use knowledge from practice to represent abnormal ranges as interval values but they have poor knowledge on variables with no direct link to target system’s goals. The paper proposes a new fuzzy arithmetic, suited to calculate abnormal ranges at test points located far deep in the conductive flow structure of the target system. It uses a semiqualitative encoding of manifestations at faults, and exploits the negative correlation of the power variables (pressure like and flow-rate like) in faulty cases. The method is compared to other approaches and it is tested on a practical case.