In this paper, the synthesis and the properties of the neural speed controller trained online are presented. The structure of the controller and the training algorithm are described. The resilient backpropagation (RPROP) algorithm was chosen for the training process of the artificial neural network (ANN). The algorithm was modified in order to improve controller operation. The specific properties of the controller, i.e., adaptation and auto-tuning, are illustrated by the results of both simulation and experimental research. An electric drive with permanent magnet synchronous motor (PMSM) was chosen for experimental research, due to its impressive dynamics. The obtained results indicate that the presented controller may be implemented in industrial applications.

This paper is dedicated to the motion control system of a multimass mechanism with occurring resonances and variable moment of inertia. The proposed concept of control structure for such mechanism consists of a filter damping higher resonance frequencies and an adaptive speed controller. The filter has properly selected fixed characteristics giving a compromised filtering effect in a range of resonance frequency variation, caused by the variable moment of inertia. The used neural adaptive controller realizes active damping of lower resonance frequencies, which are not eliminated by the resonance filter. This original concept is compared with a more complex solution, treated as a reference, which contains an offline-tuned resonance filter together with an offline-adjusted PI-two degrees of freedom controller. Good speed control dynamic properties of the proposed concept in comparison with the reference complex solution are proven by laboratory results.

This paper presents methods for parameter identification of mechanical resonance of two-mass and multi-mass electrical drive system. The presented methods were applied in the field of parameter identification. Various identification setups are considered: different identification models (ARX and OE), sampling periods and models orders. Results for two different excitation signals are presented: pseudo random binary signal and chirp wave. Spectral analysis is used to calculate frequency response data of electric drive with elastic connection. The discussed methods of identification are verified by both simulation and laboratory stand test.

In this paper, an analysis of various control structures for two-mass drive system with backlash are presented. Theoretical model of this complex mechanical system is derived and presented. Conventional PI speed controller is compared with 2DOF-PID controller considering delays in control path and location of resonances, PID controller with additional feedback signals and fuzzy PD-I controller. The comparison of the control process and its dynamics is based on integral and time-domain quality factors.

In this paper three methods of electric motor angular speed calculation are compared. The source of the measurement signal is a 14-bit absolute encoder. The authors compared the well-known classic methods M with more advanced approaches. First of the complex methods is based on utilization of phase loop lock system in an estimation process using on-line system model. The third method discussed in the paper is focused on application of Chebyshev filter. Short description of all of the mentioned method is followed by simulation and experimental results. The results are presented on an instance of permanent magnet synchronous motor drive, with both speed controller and speed calculation algorithms implemented in a digital signal processor system.

The paper presents laboratory tests of two selected structures of speed controller utilized in two mass system with elastic joint and backlash between motor and load. Theoretical model of the mechanical system has been derived and tested by simulation in previously published research. The aim of the article is to compare the best structure obtained by simulation with the conventional PI controller, treated as a reference. The PI speed controller was tuned according to symmetry criterion and the 2DOF-PID controller was tuned according to other method known from literature, delays in control path and location of resonances were considered. Comparison of control process was carried out on the basis of quality indicators.