A Data-Driven Process Monitoring Approach Based on Evidence Reasoning Rule Considering Interval-Valued Reliability

In the process industry, an alarm system is one of important ways condition monitoring. Due to complexity and irregularity information in monitoring, there are too many false alarms current system. order solve problem designing system, this paper proposes a multivariate design method based on evidence reasoning (ER) rule, considering interval-valued reliability, which can make full use accurate decisions. Firstly, referential matrixes (REMs) constructed training samples variables, real-time variables converted into by activating REMs. Alarm then fused ER rule. fusion process, better describe uncertainty information, reliability characterized random with certain probability distributions, it be adjusted dynamic intervals according change evidence. Finally, reactor fault case implemented Tennessee Eastman (TE) shows that adjustment adapt irregular obtains consistent results further improve accuracy