Fuzzy neural network inverse robust controller of induction motor speed regulation system and construction method

Abstract

The invention discloses a fuzzy neural network inverse robust controller of an induction motor speed regulation system and a construction method. The construction method comprises the following steps: using an inverter, an induction motor and a load as a whole to form an induction motor speed regulation system; connecting a fuzzy neural network inverse in the front of the induction motor speed regulation system in series to together form a reduced integration type speed pseudo-linear system; designing a robust controller for the obtained speed pseudo-linear system; and connecting a fuzzy neural network inverse and the robust controller to form a fuzzy neural network inverse robust controller so as to realize the high-precision robust control of the induction motor speed regulation system. The fuzzy neural network inverse robust controller can restrain parameter perturbation and load mutation, overcome unmodeled dynamic interferences, be used for designing a new control scheme of the induction motor speed regulation system and have wide application prospect in the reconstruction of an old induction motor speed regulation system. A control code of the system can be conveniently transplanted in various control chips, thereby greatly shortening a development period.

Description

Technical field [0001] The invention is a fuzzy neural network inverse robust controller of an induction motor speed regulation system and a construction method thereof. It is suitable for high-precision robust control of an induction motor driven by a current-controlled voltage source inverter, and belongs to electric drive control The technical field of the device. Background technique [0002] Induction motors have the advantages of simple structure, reliable operation, low cost, etc. With the practical use of vector control technology, it has gradually replaced DC motors and has been widely used in the field of industrial drives. The induction motor speed control system under the constant voltage-frequency ratio control mode based on the steady-state model can meet the general speed control requirements, but the load capacity is limited at low speed. The induction motor speed control system under the vector control mode based on the dynamic model has the advantages of good d...

AI Technical Summary

Problems solved by technology

However, since the rotor parameters and load torque of the induction motor are included in the vector control equation, the perturbation of the rotor parameters and the sudden change of the load torque will reduce the robustness of the system and affect the further improvement of the control effect.

The neural network inverse control method based on inverse system theory is applied to induction motor speed regulation. The inverse system constructed with neural network plus induction motor speed regulation system can realize linear decoupling control, but the neural network based on empirical risk minimization has local extremes. Small points, over-learning, and the choice of structure and type rely too much on experience. At the same time, in the actual operation of the induction motor, there are unmodeled dynamics such as load mutation, rotor resistance parameter perturbation, and magnetic saturation and iron loss. These uncertain factors Will cause model mismatch and make the system deviate from the expected control target

Images