Data-driven System Identification of an Innovation Community Model. Issue 11 (2018)

• Record Type: Journal Article
• Authors: Olcay, Ertug; Dengler, Christian; Lohmann, Boris
• Is Part Of: IFAC-PapersOnLine. Volume 51:Issue 11(2018)
• Page Start: 1269
• Page End: 1274
• Publication Date: 2018
• Subjects: System Identification -- Multi-Agent Simulation -- Model-Based Planning; Automatic control -- Periodicals; 629.805
• DOI: 10.1016/j.ifacol.2018.08.358
• Languages: English
• ISSNs: 2405-8963

Abstract

Abstract: With the growing global competition, the importance of innovations for the success of many companies is increasing significantly. An important concept in an innovation process is the innovation communities, which develop and implement innovative ideas. The modeling of such non-physical systems is not a simple task. However, this can be performed with the agent-based modeling technique in a more natural way than by differential equations. Unfortunately, the resulting agent-based model is not well-suited for control design. By using input and output data, it is possible to approximate an agent-based model as a Takagi-Sugeno (TS) fuzzy model. In this work, approximation of an agent-based model as a TS fuzzy model is presented.