The goal of this paper is to use artificial neural networks (ANNs) for online identification of induction-motor parameters. ANNs such as feedforward and recurrent networks will be used to develop an ANN as a memory for remembering the estimated parameters and for computing the parameters during transients. Simulations and experimental results will be presented for a nonlinear control system of induction motors. A digital signal processor will be used for the experimental investigation.

In this paper, two architectures of artificial neural networks (ANNs) are developed and used to correct the performance of sensorless nonlinear control of induction motor systems. Feedforward multilayer perception, an Elman recurrent ANN, and a two-layer feedforward ANN is used in the control process. The method is based on the use of ANN to get an appropriate correction for improving the estimated speed. Simulation and experimental results were carried out for the proposed control system. An induction motor fed by voltage source inverter was used in the experimental system. A digital signal processor and field-programmable gate arrays were used to implement the control algorithm.

This article presents measurements of electric power absorbed by a newly built facility for office and scientific research activities. These measurements highlighted the need for compensation of capacitive reactive power—not predicted by the designer—due to the vast use of LED lighting in the facility. The article also describes a reactive power compensation system, designed on the basis of the above-mentioned measurements, and the introduced control and measurement system that enables on-site monitoring and online analysis of consumed energy and power. The research was carried out using popular LED lighting sources available on the local market (Poland). Basic electrical parameters of the locally available LEDs were measured as a function of the changes in harmonic levels occurring in the supply voltage. The test illustrated that samples were characterized by a very low power factor, which decreased as the level of harmonic disturbances increased. On the basis of the measurements, the authors suggest that obligatory requirements should be introduced in regard to the minimum power factor at the level of 0.9 for popular LED lighting sources (below 25 W).

In this paper it is presented control system of distributed energy resources (DER) based on Ethernet POWERLINK Protocol. Authors develop a common method for communicating with The Inverter-Based Microgrid System. This paper presents the optimal storage sharing control method of grid connected generation system. This system consists of photovoltaic panels (PV), windmill with induction generator (WG), supercapacitors (SC), AGM battery, controllable load, power converters and electric power system. These components can be connected to make a micro-grid system controlled by Energy Management System based on DSP, ARM 9 processors and FPGA hardware. In a case study, it is analyzed how Ethernet POWERLINK Protocol can be used to build a communication channels between converters, load and management system. Simulation results are presented to demonstrate reliability of proposed control systems. The whole control scheme and communication protocol are implemented on a DSP and FPGA.

In the paper it is presented speed sensorless nonlinear control system using multiscalar model based MMB operating in the lower field weakening speed region. Nonlinear control methods can improve the performance of induction motor drives in transients. The maximum available output torque, which guarantees satisfactory motor dynamics in field weakening region, is calculated using the steady state dependencies of induction motor model. Full dynamic reaction to commanded changes or to disturbances that occur during operation at the voltage limit is enabled by reducing the excitation level in a fastest possible way. Experimental results are presented to demonstrate reliability of proposed controller. In the experimental implementation a 22 kW induction motor is used. The whole control scheme (including multiscalar control, speed computation and space vector PWM) are implemented on a DSP and FPGA.

Purpose – To develop general forms of multiscalar models of the induction motor and to present properties of the sensorless control systems based on such models. Design/methodology/approach – Previously presented multiscalar model of the induction motor based on a stator current and rotor flux vector is generalized as a model of type 1. New model of type 2 is defined for stator current and the vector which is directly controlled by a voltage vector. The above models are applied in a sensorless control system with speed observer. Dynamical properties of the sensorless control systems are investigated by simulations and experiments. Findings – Application of the multiscalar model of type 2 results in higher exactness of sensorless control system than application of the multiscalar model of type 1. Controlled variables are more smooth in transients. Research limitations/implications – This is not an analytical proof of stability of the control systems. Practical implications – Provides very useful information for development of sensorless control systems for the induction motor. Originality/value – This paper extends the known method of nonlinear control of the induction motor to the general form. It is possible to choose the sensorless control system of better properties than those used so far.