The paper is focused on issues related to the control of electrical drives with oscillations of state variables. The main problem deals with the construction of the mechanical part, which contains elastic elements used as a coupling between the motor machine and the load. In such cases, strict tracking of the reference trajectory is difficult, so damping of the disturbances is necessary. For this purpose, the full state vector of the object is applied as the feedback signal for the speed controller. This method is efficient and relatively easy to implement (including the hardware part). However, the control accuracy is dependent on the quality of the parameters identification and the invariance of the object. Thus, two adaptive structures are proposed for the two-mass system. Moreover, selected coefficients were optimized using metaheuristic algorithms (symbiotic organism search and flower pollination algorithm). After presentation of the preliminaries and mathematical background, tests were conducted, and the numerical simulations are shown. Finally, the experimental verification for the 0.5 kW DC machines was performed. The results confirm the theoretical concept and the initial assumptions: the state controller leads to the precise control of the drive with a long shaft; recalculation of the parameters can improve the work of the drive under changes of time constants; modern design tools are appropriate for this application.

In this paper, an adaptive speed controller of the electrical drive is presented. The main part of the control structure is based on the Recurrent Wavelet Neural Network (RWNN). The mechanical part of the plant is considered as an elastic connection of two DC machines. Oscillation damping and robustness against parameter changes are achieved using network parameters updates (online). Moreover, the various combinations of the feedbacks from the state variables are considered. The initial weights of the neural network and the additional gains are tuned using a modified version of the Grey Wolf Optimizer. Convergence of the calculation is forced using a new definition. For theoretical analysis, numerical tests are presented. Then, the RWNN is implemented in a dSPACE card. Finally, the simulation results are verified experimentally.

The article is focused on the application of neural models for state-variables estimation. The estimators are applied in the control structure (with the state speed controller) of the electric drive with an elastic shaft. The extended amount of feedback is an additional argument for the estimation of the signal. The calculations are performed for three deep neural structures based on the Convolutional Neural Network (CNN) and the long short-term memory (LSTM). The design stages and the overall concept in this case are completely different than with the applications of classical observers (e.g., the Luenberger, the Kalman filter) often used for similar objects. The direct identification of the mechanical part of the drive is not necessary. The parameters and the equations describing the plant are not used. Instead, the signals are used for training the neural networks. The results (performed for the nominal values of the two-mass system and presenting the robustness of the estimators) present the high precision of the signal estimation. The second part of the work deals with the hardware implementation of the neural estimators in the low-cost programmable device with the ARM core. The experimental transients confirm the features of the neural estimators noticed in the simulations.

External disturbances, uncertainties, and nonlinear behavior are problems that are commonly encountered by control system designers. In order to save on energy and materials, mechanical structures have become lighter and more flexible, which only exacerbates the control problem. To resolve this issue, robust and adaptive control strategies have been proposed and have recently gained a lot of interest in modern scientific literature. This article proposes a combination of both approaches: a sliding mode—radial basis function neural network controller applied to an electrical drive with a sophisticated mechanical structure. The proposed sliding surface provides robustness against parameter uncertainties, while the neural network adjusts itself to the current state of the drive and mitigates the oscillations resulting from the elastic connection with the load machine. This article proves the stability of the proposed control algorithm in the sense of Lyapunov, provides an in-depth numerical analysis, and compares those results with the experimental tests. The algorithm was implemented in a 1103 dSPACE fast-prototyping card and was used to control a 0.5 kW DC motor connected to the load machine by a long (thin) steel shaft.

This paper deals with the implementation of an adaptive speed controller applied for two electrical machines coupled by a long shaft. The two main parts of the study are the synthesis of the neural adaptive controller and hardware implementation using a low-cost system based on an STM Discovery board. The framework between the control system, the power converters, and the motors is established with an ARM device. A radial basis function neural network (RBFNN) is used as an adaptive speed controller. The net coefficients are updated (online mode) to ensure high dynamics of the system and correct work under disturbance. The results contain transients achieved in simulations and experimental tests.

Neural network approaches have commonly been used to solve complex mathematical equations in the literature. They have inspired the modifications of state controllers and are often implemented for electrical drives with an elastic connection. Given that the addition of a virtual signal can provide adaptive properties to classical controllers and that selected feedback signals can also be replaced with a virtual state variable from a neural network, several combinations can be considered and compared. In this paper, Radial Basis Function neural-network-based control algorithms are proposed in which online updating of the output weights is used. Analyses of simulation experiment results reveal that the proposed control algorithms significantly improve the operation of classic-state feedback controllers applied to two-mass systems in the presence of parameter uncertainty.