Three-pole magnetic bearing rotor radial displacement soft measurement modeling method

Abstract

The invention discloses a three-pole magnetic bearing rotor radial displacement soft measurement modeling method, which comprises the following steps of using displacement as a state value, using control current as an observation value to respectively form a hidden Markov chain, and mutually coupling the two hidden Markov chains to form a coupled hidden Markov model; performing optimization training on the model parameters by adopting a genetic algorithm, a particle swarm optimization algorithm and a Baum-Welch algorithm in sequence to obtain final model parameters; establishing a coupling hidden Markov model corresponding to each group of sample databases as a sub-model according to the final model parameters; obtaining a group of optimal displacement state values and output probabilitiesof each sub-model by using a Viterbi algorithm, and calculating all the optimal displacement state values and output probabilities by using a weighted average method to obtain a displacement prediction value so as to form a soft measurement model. According to the method, the causal relationship and influence between the two degrees of freedom are established by utilizing the interdependence relationship between the multi-channel states, so that the modeling is more accurate, the advantages and disadvantages of the genetic algorithm and the particle swarm optimization algorithm are complementary, and the model parameter optimization effect is better.

Description

Technical field [0001] The invention relates to a magnetic bearing system used in the field of high-speed motor transmission, in particular to a soft-sensing modeling method for the rotor radial displacement of a three-pole magnetic bearing based on a coupled hidden Markov model. Background technique [0002] Magnetic bearing is a non-contact high-performance bearing that uses magnetic field force to suspend the rotor in the air gap between stators. In order to realize the stable suspension of the magnetic bearing rotor, a closed-loop displacement negative feedback control system needs to be established. Therefore, accurate real-time detection of rotor displacement is the key to the control system. Traditionally, the displacement sensor is generally used to detect the displacement of the rotor. The displacement sensor cannot meet the needs of high-speed and high-precision development of magnetic bearings due to problems such as large space occupation, high price, and low dynamic ...

AI Technical Summary

Problems solved by technology

However, the genetic algorithm has low convergence accuracy and long convergence time, which makes it difficult to meet the requirements of self-detection and real-time detection.

Images