This paper proposes an approach to an ANN-based temperature controller design for a plastic injection moulding system. This design approach is applied to the development of a controller based on a combination of a classical ANN and integrator. The controller provides a fast temperature response and zero steady-state error for three typical heaters (bar, nozzle, and cartridge) for a plastic moulding system. The simulation results in Matlab Simulink software and in comparison to an industrial PID regulator have shown the advantages of the controller, such as significantly less overshoot and faster transient (compared to PID with autotuning) for all examined heaters. In order to verify the proposed approach, the designed ANN controller was implemented and tested using an experimental setup based on an STM32 board.

This paper proposes a new photovoltaic panel maximum-power-point optimizer based on a buck converter. It can be connected to the DC-link distributed energy harvesting system that should perform the true maximum-power-point tracking algorithm based on maintaining a constant DC link voltage. The algorithm is based on the sensorless hysteresis control and ensures high efficiency. Three different realizations of proposed hysteresis optimizers have been analyzed in the paper, including operation principle and adjustment of hysteresis intervals. An experimental study has been performed for a portable low-power photovoltaic system in case of different loads and irradiance levels. The efficiency of maximum power point tracking has been calculated analytically for different hysteresis intervals and validated by experiment, which proved a 97-98 % efficiency of tracking for different PV panel temperatures. The proposed solution is recommended to be used in small- and medium-sized power systems where the price of the conventional maximum power point tracking converter is very high and is comparable to the cost of the individual panel