Abstract
A simplified synthesis of energy-efficient scalar systems of frequency control of an asynchronous motor is considered. A method for formulating special frequency-control laws calculated for a certain range of loads is considered for provision of energy efficiency. Calculation of the frequency-control law of an asynchronous electric drive is carried out based on iteration optimization, in which the number of iterations may reach a thousand. It is resolved to find a simplified procedure for formulation of a law applicable to engineering calculations. The hypothesis is raised that there is a “similarity” of laws of control for motors with relatively similar parameters of the equivalent scheme. This assumes that the control law (which is quasi-optimal) obtained for one motor can be applied to other electric machines with similar parameters with some degree of error. It is suggested that motors with similar parameters be distinguished by means of clustering based on self-organizing artificial neural networks (a Kohonen map). The number of clusters is selected based on the dispersion of the desired motor parameters, which is determined from the deviation of optimization criteria from the extreme. Finally, a hexagonal Kohonen map with 49 clusters is obtained in which each cluster is assigned a set of quasi-optimal laws. Thus, it is sufficient to correlate a motor with some cluster (in other words, classify it) which automatically defines a quasi-optimal control law. Procedures of formation and training of the network and parameters of realization of optimized control laws are provided.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
