Inertia estimation method based on single neuron network and adaptive adjustment strategy thereof

Abstract

The invention discloses an inertia estimation method based on a single neuron network and an adaptive adjustment strategy thereof. Firstly, an inertia estimation method based on a single neuron network is disclosed, the method introduces the single neuron network, and gain factors are dynamically adjusted according to deviation between a reference model and an estimation model by utilizing the strong self-learning capability of the single neuron network, so that the estimation model is closer to the reference model; secondly, the invention also discloses an adaptive adjustment strategy for theinertia estimation method, which adaptively adjusts the proportionality coefficient of neurons based on an instantaneous error energy function capable of reflecting error changes in real time, and limits the output of the strategy at the same time. According to the inertia estimation method provided by the invention, the estimation precision of inertia can be remarkably improved, the applicable working condition is not limited, and the implementation of an adaptive adjustment strategy enables an inertia estimation result to realize better compromise between stability and convergence speed. The method is simple in calculation and easy to debug, and can be used on line.

Description

technical field [0001] The invention belongs to the technical field of motors, and relates to inertia estimation of a permanent magnet synchronous motor drive system, in particular to an inertia estimation method based on a single neuron network and an adaptive adjustment strategy thereof. Background technique [0002] PMSM (Permanent Magnet Synchronous Motor) has been widely used in the industrial field due to its excellent characteristics such as high power density, large torque inertia ratio, and high efficiency. With the continuous improvement of the automation level, some servo control algorithms that improve the performance of PMSM systems require high-precision inertia estimation results, such as self-tuning of the speed loop controller, torque feedforward control, and load torque observation. Undoubtedly, imprecise inertia data can lead to suboptimal control performance of these methods. Therefore, it is very necessary to accurately estimate the system inertia compo...

AI Technical Summary

Problems solved by technology

In this case, the friction model will change, so the previously established fitting equations will not apply

Furthermore, the establishment of the fitting equations is time-consuming, which complicates the practical use of the model reference adaptation method

Images