FReOS-ELM-based piezoelectric actuation type FTS modeling method and system and control method and system

Abstract

The application discloses an FReOS-ELM-based piezoelectric actuation type FTS modeling method and system and control method and system. According to the application, a current expected output displacement value, a plurality of previous output displacement values, and input driving voltages are used as input values of a model and an input driving voltage value of a piezoelectric ceramic actuator component at a current time is used as an output value of the model, so that a hysteresis nonlinear multi-value mapping problem is solved and a tedious model inversion process is avoided. Besides, the model is converted into a linear equation model, so that the training time of the model is shortened greatly. And the precision is improved by using an infinitely differentiable function as a hidden-layer activation function. Moreover, on the basis of the regularization idea, a proportional parameter of a risk is introduced to avoid ill-conditioned matrix generation, so that the training stability and generalization performance of the model are improved substantially; and because of introduction of a forgetting factor for online adaptive parameter updating, the operation becomes convenient, the computing loading and information overloading phenomena are avoided and the adaptability of the model is enhanced.

Description

technical field [0001] The invention relates to the field of precision control, in particular to a FReOS-ELM-based piezoelectric-driven FTS modeling method, control method and system. Background technique [0002] Piezoelectric ceramic actuators have the advantages of small size, light weight, high rigidity, large output force, high output displacement resolution and fast dynamic response, and are widely used in fast tool servo systems (ie FTS, Fast Tool Servo). However, drivers made of piezoelectric materials have inherent hysteretic nonlinear characteristics, and FTS itself is affected by various external environmental factors, and it often requires high-frequency driving characteristics, which makes hysteretic nonlinear characteristics more complicated. In the precision drive system of FTS, it is a very challenging problem to solve the control error problem caused by the hysteresis nonlinear characteristic, and it is also a key problem to improve the control precision. ...

AI Technical Summary

Problems solved by technology

[0004] These models either have low precision and slow modeling speed, or it is difficult to model online or the inverse model is difficult to obtain; and almost none of them can be applied in a well-combined control, and most hysteretic nonlinear models must rely on Some other control links are used, such as PID control, repetitive control, etc.; even if there are a few hysteretic nonlinear models that can realize motion control, it is difficult for these models to perform effective online adaptive parameter adjustment

Images