Neural network technologies in control systems of cargo movement mechanisms

THE PURPOSE. Development and analysis of control systems for cargo movement mechanisms that do not contain a speed sensor in their structure. The use intelligent devices the implementation sensorless systems. study proposed solutions closed-type order to identify most optimal option provides best performance according criteria, this case, accuracy testing. METHODS. It is possible achieve these goals through mathematical modeling carried out Matlab Simulink simulation environment. RESULTS. In study, containing various kinds velocity observers structure was out. stability work under consideration evaluated taking into account external disturbing influences – inter-turn closure mode considered. CONCLUSION. have sensors demand on installed rooms with small area, objects elevated ambient temperatures increased pollution. compared sensor, system non-adaptive observer neural network observers. Optimal indicators were obtained NARMA-L2 neurocontroller. A combined several neuroregulators are trained dynamic engine parameters monitored dangerous modes may occur dynamics.