Implementation of feedback-linearization-modelled induction motor drive through an adaptive simplified neuro-fuzzy approach

Abstract

A simple modified version of neuro-fuzzy controller (NFC) method based on single-input, reduced membership function in conjunction with an intuitive flux-speed decoupled feedback linearization (FBL) approach of induction motor (IM) model is presented in this paper. The proposed NFC with FBL remarkably suppresses the torque and speed ripple and shows improved performance. Further, the modified NFC is tuned by genetic algorithm (GA) approach for optimal performance of FBL-based IM drive. Moreover, the GA searches the optimal parameters of the simplified NFC in order to ensure the global convergence of error. The proposed simplified NFC integrates the concept of fuzzy logic and neural network structure like a conventional NFC, but it has the advantages of simplicity and improved computational efficiency over the conventional NFC as the single input introduced here is an error (speed and torque) instead of two inputs, error and change in error, as in the conventional NFC. This structure makes the proposed NFC robust and simple as compared with conventional NFC and thus, can be easily applied to real-time industry application. The proposed system incorporated with different control methods is also validated with extensive experimental results using DSP2812. The effectiveness of the proposed method using FBL of IM drive is investigated in simulation as well as in experiment with different working modes. It is evident from the comparative results that the system performance is not deteriorated using the proposed simple NFC as compared to the conventional NFC; rather, it shows superior performance over PI-controller-based drive.

Closed-Loop Drive Detection and Diagnosis of Multiple Combined Faults in Induction Motor Through Model-Based and Neuro-Fuzzy Network Techniques

“…The input-output feedback linearization strategy makes it possible to find a state feedback loop in order to transform a nonlinear system into a fully or partially linear one [5]. The technique requires measurements of the state vector x in order to transform a multi-input nonlinear control system into a linear and controllable one.…”

“…There are many methods dedicated to control induction motors, however, the controlled part is subjected to strong nonlinearities and temporal variables, it is necessary to design control algorithms ensuring the robustness of the process against the uncertainties on the parameters and their variations. The input-output feedback linearization control has focussed on the attention owing to the simple design and on the perfect decoupling between rotor speed and flux, as well as fast dynamic response, even too easy implementation, robustness to parameter variations, and load disturbances [3][4][5].…”

Current Loop Control of Jet Fan Motors in Thu Thiem Tunnel by the Exact Linearization Method

“…In the control structure of induction motor on the dq coordinate system, the current i sd controls the flux, and the current i sq controls the torque. In order to design the controllers to ensure the stability of the system, there are linear control methods such as the PI controller or PI combined with optimization algorithms [13][14], ADRC controller [15], deadbeat [16] or nonlinear controllers such as the exact linearization, sliding mode, backstepping, neuron, robust nonlinear predictive control [17][18][19][20][21][22][23][24], etc. The typical linear control method is the PI controller, which has the advantage of simple design and little dependence on motor parameters.…”

Enhanced Performance of Indirect Vector Controlled Induction Motor Drive with a Modified Type 2 Neuro-Fuzzy Torque Controller in Interfacing with dSPACE DS-2812

“…However, some industries are still unwilling to use this controller as large computational burden is imposed by more membership functions (MFs), rules, particularly for self-tuning condition. The large sampling time because of high computational burden is not preferred for realtime industrial applications as it produces greater torque ripple [17,18].…”