Abstract: In response to many multi-attribute decision-making (MADM) problems involved in chemical processes such as controller tuning, which suffer human's subjective preferential nature in human-computer interactions, a novel affective computing and preferential evolutionary solution is proposed to adapt human-computer interaction mechanism. Based on the stimulating response mechanism, an improved affective computing model is introduced to quantify decision maker's preference in selections of interactive evolutionary computing. In addition, the mathematical relationship between affective space and decision maker's preferences is constructed. Subsequently, a human-computer interactive preferential evolutionary algorithm for MADM problems is proposed, which deals with attribute weights and optimal solutions based on preferential evolution metrics. To exemplify applications of the proposedmethods, some test functions and, emphatically, controller tuning issues associated with a chemical process are investigated, giving satisfactory results.

Key words: Preference, Affective computing, Interactive evolutionary computation, Multi-attribute decision-making, Controller tuning

摘要： In response to many multi-attribute decision-making (MADM) problems involved in chemical processes such as controller tuning, which suffer human's subjective preferential nature in human-computer interactions, a novel affective computing and preferential evolutionary solution is proposed to adapt human-computer interaction mechanism. Based on the stimulating response mechanism, an improved affective computing model is introduced to quantify decision maker's preference in selections of interactive evolutionary computing. In addition, the mathematical relationship between affective space and decision maker's preferences is constructed. Subsequently, a human-computer interactive preferential evolutionary algorithm for MADM problems is proposed, which deals with attribute weights and optimal solutions based on preferential evolution metrics. To exemplify applications of the proposedmethods, some test functions and, emphatically, controller tuning issues associated with a chemical process are investigated, giving satisfactory results.

关键词: Preference, Affective computing, Interactive evolutionary computation, Multi-attribute decision-making, Controller tuning