TY - JOUR
T1 - A cognitive map and fuzzy inference engine model for online design and self fine-tuning of fuzzy logic controllers
AU - Gonzalez, Jose L.
AU - Aguilar, Luis T.
AU - Castillo, Oscar
PY - 2009/11
Y1 - 2009/11
N2 - An integration of a cognitive map and a fuzzy inference engine is presented, as a cognitive-fuzzy model, targeting online fuzzy logic controller (FLC) design and self fine-tuning. The proposed model is different than previous proposed fuzzy cognitive maps in that it presents a hierarchical architecture in which the cognitive map process, available plant, and control objective data on represented knowledge to generate a complete FLC architecture and parameters description. Online assessment of measured data is processed for linguistic characterization of performance to determine the required FLC parameter's adjustments, the process is repeated until the control objective is reached. A mathematical model of the proposed approach is presented, and sample numerical data illustrate the following: (a) cognitive map construction, (b) start-up self finetuning, and (c) system's response to error of plant descriptive data. Simulation results demonstrate model interpretability, which suggests that the model is scalable and offers robust capability to generate near optimal controller, emulating human iterative design flow, and fine-tuning within the knowledge domain of cognitive map.
AB - An integration of a cognitive map and a fuzzy inference engine is presented, as a cognitive-fuzzy model, targeting online fuzzy logic controller (FLC) design and self fine-tuning. The proposed model is different than previous proposed fuzzy cognitive maps in that it presents a hierarchical architecture in which the cognitive map process, available plant, and control objective data on represented knowledge to generate a complete FLC architecture and parameters description. Online assessment of measured data is processed for linguistic characterization of performance to determine the required FLC parameter's adjustments, the process is repeated until the control objective is reached. A mathematical model of the proposed approach is presented, and sample numerical data illustrate the following: (a) cognitive map construction, (b) start-up self finetuning, and (c) system's response to error of plant descriptive data. Simulation results demonstrate model interpretability, which suggests that the model is scalable and offers robust capability to generate near optimal controller, emulating human iterative design flow, and fine-tuning within the knowledge domain of cognitive map.
UR - http://www.scopus.com/inward/record.url?scp=70349592180&partnerID=8YFLogxK
U2 - 10.1002/int.20379
DO - 10.1002/int.20379
M3 - Artículo
SN - 0884-8173
VL - 24
SP - 1134
EP - 1173
JO - International Journal of Intelligent Systems
JF - International Journal of Intelligent Systems
IS - 11
ER -