Deadbeat predictive current control of permanent magnet synchronous motor based on variable step‐size adaline neural network parameter identification

Abstract

The fast and stable inner current loop in the permanent magnet synchronous motor control system is the key factor that ensures the torque control performance of the motor. The deadbeat predictive current control has good dynamic response performance, but it depends heavily on the precise mathematical model of the controlled object. The parameter mismatch will degrade the control performance. A deadbeat predictive current control method based on online parameter identification is proposed in this study. This method does not need to inject additional d ‐axis current to identify the parameters during the operation of the motor; it only needs to make full use of the inherent phenomenon that the q ‐axis current changes when the load of the motor changes during operation, and perform parameter identification. Aiming at the problem that the effect of parameter identification is easily affected by motor speed, a new variable step‐size neural network algorithm is designed in this study. The speed factor is introduced into step function to ensure the performance of the identification algorithm at a different speed. Finally, based on the new online parameter identification algorithm, the deadbeat predictive current control method is used to verify the experiment.

A Predictive Control Method for Improving the Robustness of Permanent Magnet Synchronous Motor

“…According to the above assumptions, the mathematical model of PMSM can be obtained [9][10][11]. The mathematical model in the synchronous rotating coordinate system can be expressed as:…”

“…Considering the error of the mechanical speed directly predicted by ( 9), the control strategy of rolling optimization and feedback correction is adopted. The rotational speed prediction error is [10,12]:…”

A Wide Adaptation Variable Step-size Adaline Neural Network Parameter Identification IPMSM Model Predictive Control Strategy

“…Although this method has low computational complexity and high identification accuracy, the multi-parameter identification process cannot be performed simultaneously. A variable step size Adaline neural network parameter identification method is proposed in [21]. This method constrains the step size by establishing a functional relationship between instantaneous error and step size, effectively reducing the steady-state error of motor parameter identification while improving the convergence rate of the identification results.…”

Online Filter Parameters Estimation in a Double Conversion UPS System for Real-Time Model Predictive Control Performance Optimization

“…Parameter estimation methods based on artificial neural networks (ANN) have also been proposed [23,24]. As reported in several studies, this type of technique has shown to be a very promising solution for parameters estimation [5,25].…”

“…Conversely, the Adaptive Linear Neuron (ADALINE) network corresponds to a simple single-layer neural network that does not require an offline training stage, being trained online. Therefore, its potential has been shown in several works regarding not only filter parameter estimation [2,12,24,26] but also current/voltage harmonic components identification [27,28] and flux estimation in electrical machines [23], which have reported a good estimation accuracy. Furthermore, according to [5,25], ADALINE-based parameter estimation techniques typically require lower computational burden and present faster convergence than more conventional estimation methods, including those based on EKFs [17,18,20] and MRAS [11,[14][15][16].…”