Abstract
In order to synthesize adaptive control systems over asynchronous electric drive that includes a motor with defects or degradation, we proposed a structure and developed an algorithm for training a PID-neurocontroller based on a multilayer feedforward neural network. Such an approach makes it possible to operatively respond to a change in the characteristics of control object that occurs as a result of the emergence and development of damage and degradation of the motor. This, in turn, makes it possible to improve controllability of the motor, and, consequently, to prolong its operation life cycle and to enhance the energy efficiency of its operation. The proposed solutions, in contrast to the traditional, do not require the use of additional equipment for implementation. It is only needed to change a control program for the frequency converter based on the constructed algorithm. To implement the proposed solutions in practice, we synthesized an algorithm for training a neural network of the PID-neurocontroller with self-tuning. It enables the calculation of weights of the neurons that could be in the future used as the basis of software for a physical control system with the PID-neurocontroller. We mathematically modeled the operation of IM with breaks of the rotor bars and the short-circuited turns in the stator windings when using the proposed controller. An analysis of modeling results showed that the proposed approach to control the electric drive with a damaged IM makes it possible to decrease the amplitude and the number of non-basic harmonics of current and power signals of IM while maintaining the preset parameters of the technological process. Thus, our paper demonstrates the effectiveness of applying the proposed approach to the tasks on maintaining the predefined parameters of the technological process for the case of a stochastic change in the characteristics of control object
Highlights
Owing to the simplicity of design and relative reliabi lity of operation, the induction motor (IM) is currently the most common converter of electrical energy into mechanical energy and is a key element of most controlling elements both in industry and in the national economy [1,2,3]
Based on an analysis aimed at the implementation of adaptive control over the electric drive that includes IM with damages, we selected a PID neurocontroller based on neural networks (NN) of the multilayer perceptron type, which makes it possible to improve the response of the controller to the disturbances, which were not learnt by the perceptron
We have developed a structure of the control system over an induction motor, based on the adaptive PID-neurocontroller, which uses a multilayered feedforward neural network to derive values for the coefficients of the controller in the process of operation
Summary
Owing to the simplicity of design and relative reliabi lity of operation, the induction motor (IM) is currently the most common converter of electrical energy into mechanical energy and is a key element of most controlling elements both in industry and in the national economy [1,2,3]. One of the most important factors in this regard is the emergence or development of damage or degradation in IM, leading to changes in the characteristics during operation This leads in turn to the inefficiency of control systems tuned by standard methods using the law of PID-control. From the standpoint of the modern theory of automatic control, the application of multilayered NNs, as objects controllers, is adequate for the tasks that emerge in the cases when an analytical synthesis of a control system becomes quite a time-consuming task because of the complexity or unreliability of the employed mathematical model of the object Such a situation is inevitable if the object is a multiconnected system that includes nonlinearities while its operation is accompanied with uncontrollable changes in the dynamic properties over time, which is the case when IM is subject to damage or degradation. NN can be used in various modifications of engagement in the structure of a control system, such as: control with a reference model of the control object, the method of hybrid control, the method of inverse control, the method of direct neuro-control, and others
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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 call
