Bayesian Uncertainty Inferencing for Fault Diagnosis of Intelligent Instruments in IoT Systems

Intelligent instruments are common components in industrial machinery, and fault diagnosis IoT systems requires the handling of real-time sensor data expert knowledge. sensors cannot collect for all types a specific instrument, long-distance transfer introduces additional uncertainties. However, because equipment has complex causes performances, it is typically difficult or expensive to obtain exact probabilities. Therefore, this study, we proposed an innovative failure detection model intelligent system using Bayesian network, with focus on uncertainties knowledge monitoring information. The addresses challenge performances equipment, which make obtainment probabilities expensive. trapezoidal intuitionistic fuzzy number (TrIFN)-based entropy method was applied order aggregate generate priority probability, Leaky-OR gate used calculate CPT. effectiveness strategy demonstrated through its application pressure transmitter (IPT) GeNIe software.