定性モデルにもとづくラフ集合の決定ルールを利用したビル空調設備異常検知方法

抄録

In a 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. Thus, a new method is required, which can detect faults from measured data using computers automatically. This paper proposes the method of fault detection with rough set based on qualitative model of measured time-series data in building air- conditioning system. First, the proposal method converts target measured time-series data into data set based on target qualitative model. Next, this method constructs the decision rule of a rough set by comparison of the data set for every block. Finally, this method detects fault through comparison of evaluation values. Through practical experiments, it is confirmed that the proposal method can detect faults without expert knowledge in a building air-conditioning system.