关键词: 满意度, 报警阈值, 权重, 自适应

Abstract: The reasonable setting of process parameter alarm thresholds greatly influences the performance of an alarm system. In response to the limitations of traditional static threshold optimization, a novel satisfaction optimization based approach to self-adaptive adjustment of process alarm thresholds is explicitly introduced in this paper. Firstly, based on alarm treatment rates and alarm time recovery rates, a fuzzy reasoning strategy is employed to get the satisfaction index. Subsequently, the relations between the satisfaction index and FAR (false alarm rate), MAR (miss alarm rate) are used to calculate weights of FAR and MAR involved in the optimization objective function, in which kernel density estimations are conducted. Finally, numerical optimization methods are employed to achieve the optimal thresholds. Industrial data simulation results show that the proposed method has better environment adaptability and improved performance for alarm systems.

Key words: Satisfaction index, alarm thresholds, weights, adaptability