Affective Preferences Mining Approach with Applications in Process Control
- PDF / 1,006,496 Bytes
- 10 Pages / 612.284 x 810.709 pts Page_size
- 59 Downloads / 186 Views
Affective Preferences Mining Approach with Applications in Process Control SU Chong ∗ ( ),
¨ Jing ( ), LU
ZHANG Danyang (),
LI Hongguang ∗ ()
(College of Information Science and Technology, Beijing University of Chemical Technology, Beijing 100029, China)
© Shanghai Jiao Tong University and Springer-Verlag GmbH Germany, part of Springer Nature 2020 Abstract: Traditional industrial process control activities relevant to multi-objective optimization problems, such as proportional integral derivative (PID) parameter tuning and operational optimizations, always demand for process knowledge and human operators’ experiences during human-computer interactions. However, the impact of human operators’ preferences on human-computer interactions has been rarely highlighted ever since. In response to this problem, a novel multilayer cognitive affective computing model based on human personalities and pleasurearousal-dominance (PAD) emotional space states is established in this paper. Therein, affective preferences are employed to update the affective computing model during human-machine interactions. Accordingly, we propose affective parameters mining strategies based on genetic algorithms (GAs), which are responsible for gradually grasping human operators’ operational preferences in the process control activities. Two routine process control tasks, including PID controller tuning for coupling loops and operational optimization for batch beer fermenter processes, are carried out to illustrate the effectiveness of the contributions, leading to the satisfactory results. Key words: affective computing, preferences, mining, process control CLC number: TP 18 Document code: A
0 Introduction It is well acknowledged that traditional process control optimization tasks, such as proportional integral derivative (PID) controller tuning[1-2] and operational optimizations[3] , have been widely circulated in academic and engineering communities, which usually rely too much on process models and operators’ experiences[4-5] . In other words, regarding these multiobjective optimization problems, it is hard to achieve ideal performances in the absence of accurate process models and operators’ experiences using traditional optimization methods[6-7] . Recently, affective intelligence has attracted much attention on the formations of decision preferences and the achievements of group consistencies through human-computer interactions. Unlike traditional interactive decision-making methods[6-7] , affective intelligence enjoys better quantitative representations of human’s willingness in decision-making. Hence, for the purpose of improving the efficiency of multi-objective optimizations and alleviating the operators’ workloads, it is necessary to make an in depth investigation on the interactive generation mechanism of affective preferences. Received: 2020-04-01 Accepted: 2020-07-01 Foundation item: the National Natural Science Foundation of China (No. 61603023) ∗E-mail: [email protected], [email protected]
In recent years, the emerge
Data Loading...
