Evaluation Method of Fault Condition with Decision Rule of Rough Set in Building Air-conditioning System
Masaki Yumoto · IEEJ Transactions on Electronics Information and Systems · 2021
In a large-scale system like building air-conditioning system, measured time-series data is observed from many kinds of sensors. It is difficult to detect the fault by the administrators because only the limited experts can diagnose the unusual system. If we can extract characteristic changes of measured time-series data, we can calculate the evaluation value and grasp the sign of target fault condition. This paper proposes the evaluation method of fault condition with decision rule of rough set in building air-conditioning system. First, the proposal method extracts outline of target measured time-series data, and build the data set with qualitative values, which indicate the state of target system. Next, this method constructs the decision rule of a rough set with existence probability by comparison between normal and fault conditions. Finally, this method calculates evaluation value every time, based on the existence probability of each decision rules. Through practical experiments, it is confirmed that the proposal method can evaluate fault conditions called hunting, which occurs in supply air temp, water volume, and air volume.