An on-line trained neural controller with a fuzzy learning rate of the Levenberg–Marquardt algorithm for speed control of an electrical drive with an elastic joint

Response Attenuation of a Structure Equipped with ATMD under Seismic Excitations Using Methods of Online Simple Adaptive Controller and Online Adaptive Type-2 Neural-Fuzzy Controller

The present study aims to design a robust adaptive controller employed in the active tuned mass damper (ATMD) system to overcome undesirable vibrations in multistory buildings under seismic excitations. We propose a novel adaptive type-2 neural-fuzzy controller (AT2NF). All system parameters are taken as unknowns. The MLP neural network is used to extract the Jacobian and estimate the structural model; then, the estimated model is applied to the controller online. To tune the control force applied to the ATMD and achieve the control targets, the controller parameters are adaptively trained using the extended Kalman Filter (EKF) and the error back-propagation algorithm. A PID controller is also included in this method to increase the stability and robustness of the adaptive type-2 neural-fuzzy controller against seismic vibrations. An online simple adaptive controller (OSAC) is studied to demonstrate the suggested controller’s superiority. The OSAC is based on adaptive control of the implicit reference model. In this proposed method, the EKF is used to tune the controller parameters online as a novel feature. The uncertainty associated with identifying the mechanical properties of structures, such as mass and stiffness, is one of the primary challenges in the real-time control of structures. This paper investigates how both controllers cope with parametric uncertainties under far-field and near-field seismic excitation. According to numerical results, the AT2NF controller outperforms OSAC in minimizing the dynamic responses of the structure during an earthquake and accomplishing control objectives when the structure’s characteristics change.

Stability Analysis of the Modified Levenberg-Marquardt Algorithm for the Artificial Neural Network Training

The Levenberg-Marquardt and Newton are two algorithms that use the Hessian for the artificial neural network learning. In this article, we propose a modified Levenberg-Marquardt algorithm for the artificial neural network learning containing the training and testing stages. The modified Levenberg-Marquardt algorithm is based on the Levenberg-Marquardt and Newton algorithms but with the following two differences to assure the error stability and weights boundedness: 1) there is a singularity point in the learning rates of the Levenberg-Marquardt and Newton algorithms, while there is not a singularity point in the learning rate of the modified Levenberg-Marquardt algorithm and 2) the Levenberg-Marquardt and Newton algorithms have three different learning rates, while the modified Levenberg-Marquardt algorithm only has one learning rate. The error stability and weights boundedness of the modified Levenberg-Marquardt algorithm are assured based on the Lyapunov technique. We compare the artificial neural network learning with the modified Levenberg-Marquardt, Levenberg-Marquardt, Newton, and stable gradient algorithms for the learning of the electric and brain signals data set.

An Efficient Second-Order Algorithm for Self-Organizing Fuzzy Neural Networks

Intelligent computing technologies are useful and important for online data modeling, where system dynamics may be nonstationary with some uncertainties. In this paper, an efficient learning mechanism is developed for building self-organizing fuzzy neural networks (SOFNNs), where a second-order algorithm (SOA) with adaptive learning rate is employed, the network size and the parameters can be determined simultaneously in the learning process. First, all parameters of SOFNN are adjusted by using the SOA strategy to achieve fast convergence through a powerful search scheme. Second, the structure of SOFNN can be self-organized using the relative importance index of each rule. The fuzzy rules used in SOFNN with SOA (SOA-SOFNN) are generated or pruned automatically to reduce the computational complexity and potentially improve the generalization power. Finally, a theoretical analysis on the learning convergence of the proposed SOA-SOFNN is given to show the computational efficiency. To demonstrate the merits of our proposed approach for data modeling, several benchmark datasets, and a real world application associated with nonlinear systems modeling problems are examined with comparisons against other existing methods. The results indicate that our proposed SOA-SOFNN performs favorably in terms of both learning speed and prediction accuracy for online data modeling.