Low-cost neuro-fuzzy control solution for servo systems with variable parameters

Abstract

This paper treats the design and implementation of a low-cost neuro-fuzzy control solution for a class of servo systems with an integral component and variable parameters. A hybrid Takagi-Sugeno PI-neuro-fuzzy controller (T-S PI-N-FC) is proposed and presented along with its relatively simple design approach. The solution carries out the on-line adaptation of a single parameter of the input membership functions of a TakagiSugeno PI-fuzzy controller with input integration (T-S PI-FC-II) by a single neuron trained by back propagation with momentumfactor in the framework of a model reference adaptive controller structure. The second parameter of the input membership functions is tuned by the modal equivalence principle. Linear matrix inequalities are proposed as sufficient stability conditions to be fulfilled by the parameters of the rule consequents of the T-S PI-FC-II in order to guarantee the stable design of the hybrid T-S PI-N-FC. The solution is validated by a case study using a set of three process parameters that correspond to a strip winding system laboratory equipment. Digital simulation results and experimental results are given.

Adaptable fuzzy control solutions for driving systems working under continuously variable conditions

“…variable reference, variable parameters (mainly variable moment of inertia, VMI) and variable load disturbance, which depends on the plant evolution, reported by the authors in [1]- [4]. Similar applications are also treated in other papers in the literature [6]- [9].…”

“…The two fuzzy control systems (TS-PI-FC with output integration and T-S PI-N-FC) ensure improved performance compared to the linear control system. The implementation of the hybrid T-S PI-N-FC on a BLDC motor-based servo system with a similar benchmark MM but with the parameters according to [29] leads to good experimental results presented in [4]. Table I.…”

“…The parameter B e is online adapted by the Model Reference Adaptive Control (MRAC) structure presented in Fig. 7 and is discussed in details in [4]. RM block sets the control system performance specifications by the (continuous-time) t.f.…”

“…Approach The structure of the fuzzy control system contains a hybrid Takagi-Sugeno PI-neuro-fuzzy controller (T-S PI-N-FC) [4] presented in Fig. 7, where: AB is the adaptation block, RM is the reference model, r is the reference input, e k is the control error, k is the index of the current sampling interval, 0 , ≥ ∈ k k Z , and q -1 is the backward shift operator.…”

“…In the developed analysis, the speed (main) controller was considered: in its classical PI controller (as the basic case), an extension for a fuzzy PI Takagi-Sugeno Fuzzy controller, a PI Quasi-Relay Sliding Mode Controller and a Neuro-Fuzzy Controller [1]- [4]. All solutions are based on the locally linearized MMs.…”