Evolving Fuzzy Models of Shape Memory Alloy Wire Actuators

This paper suggests Takagi-Sugeno-Kang (TSK) fuzzy models that characterize the position of Shape Memory Alloy (SMA) wire actuators. The systems dynamics are important because, since SMA wire actuators are included in control systems in various critical applications, the position control systems have to ensure very good performance indices. The output of these systems, viewed as controlled processes, is the position of the SMA wire actuators, and the input is the current signal which supplies the actuator, i.e., it flows through the wire. Starting with these two input and output signals directly related to the process, different numbers of additional TSK fuzzy model inputs and outputs obtained from past inputs and/or outputs are considered. The structures and parameters of the fuzzy models are evolved by an incremental online identification algorithm. Two evolving TSK fuzzy models are derived, they are next tested against the experimental data and compared. The experimental results indicate that the proposed fuzzy models are consistent with training and validation data.