非线性伺服电动机的神经网络逆控制

伺服电动机由于存在接触过程的非线性、温漂等非线性因素的影响,很难建立其精确的数学模型,使得基于数学模型的控制困难。针对伺服电动机存在的非线性问题,提出了一种新颖的基于BP神经网络直接逆控制方法。首先,利用BP神经网络建立系统的正向模型(NNI),然后,设计基于神经网络的直接逆控制器(NNC),实现了对伺服电动机的自适应控制。在Lyapunov稳定性分析的基础上,给出了BP算法学习算子的选择方案,保证神经网络权值训练的快速收敛,同时,对训练BP神经网络控制器的专用算法(specialized learning)进行改进,利用NNI的输出求取权值调整的灵敏度函数。数字仿真结果表明提出的控制算法是简单有效的。

Stabilities Analysis of Electromechanical Nonlinear Vibration of Electric Machine

An electromechanical nonlinear model of rotor system of electric machine is built.Respondance curves in parameter excited nonlinear vibration of this system caused by electromagnetic forces are investigated.Further more,the analysis reveals the effects of various electromagnetic and mechanical parameters on resonances, and some valuable results are obtained.The analytical result of this paper provides electric machine with the condition of 1/2 subharmonic resonance under the electromechanical electromagnetic forces.Electromagnetic forces apparently affect the stability zone, and both linear term and nonlinear term can excite parametric resonance.The revealed dynamic phenomena provide some new theories and active methods for the fault recognition of electric machine and the defination of stability range,and the theoretical bases for qualitatively controlling the stable operating state of rotors.

Modelling of ultrasonic motor with dead-zone based on Hammerstein model structure

The ultrasonic motor (USM) possesses heavy nonlinearities which vary with driving conditions and load-dependent characteristics such as the dead-zone. In this paper, an identification method for the rotary travelling-wave type ultrasonic motor (RTWUSM) with dead-zone is proposed based on a modified Hammerstein model structure. The driving voltage contributing effect on the nonlinearities of the RTWUSM was transformed to the change of dynamic parameters against the driving voltage. The dead-zone of the RTWUSM is identified based upon the above transformation. Experiment results showed good agreement be- tween the output of the proposed model and actual measured output.

Preliminary Group Classification for One Class of Nonlinear Wave Equations

The group classification is carried out on the nonlinear wave equation utt = f（x,u, ux）uzz ＋ g（x,u,uz） by using the preliminary group classification approach. The generators of equivalence group are determined and the corresponding reduced forms are obtained. The result of the work is shown in table form.

Research on the soft start-up performance of hydro-viscous drive

The principle and structure of hydro-viscous drive(HVD) set is introduced. Through theoretical analysis of the HVD set start-up steadiness, the conclusions were obtained that the non-linearity of the pressure performance curve and dynamic pressure instability of the pilot-operated electro-hydraulic pressure relief valve, which is used for the HVD speed regulating purpose and usually works within micro flow-rate and low oil pressure state, are the main causes of the poor start-up steadiness. So a special speed regulating valve for HVD set is developed, with which the start-up steadiness of HVD set is much improved.

Nonlinear Dynamics of Permanent-magnet Synchronous Motor with v/f Control

The nonlinear dynamics of permanent-magnet synchronous motor(PMSM) with v/f control signals is investigated intensively.First,the equilibria and steady-state characteristics of the system are formulated by analytical analysis.Then,some of its basic dynamical properties,such as characteristic eigenvalues,Lyapunov exponents and phase trajectories are studied by varying the values of system parameters.It is found that when the values of the system parameters are smaller,the PMSM operates in stable domains,no matter what the values of control gains are.With the values of parameters increasing,the unstability appears and PMSM falls into chaotic operation.Furthermore,the complex dynamic behaviors are verified by means of simulation.

Modeling and simulation of non-linear dynamic process of the induction motor system with fluctuating potential loads

The induction motor system with fluctuating potential loads is a non-linear complex electro-mechanical system.With beam pumping motors as an example,this paper proposes a multiple factor non-linear mathematical model to study the operating performance of the induction motor system.This model consists of non-linear time varying electromagnetic field equations,mechanical wave equations of sucker rods and non-linear coupling equation of reducer and four-bar linkage.The equations are numerically solved by combining time-step finite element method(TS-FEM),finite difference method(FDM),a linear dimension reduction method and the Newton-Raphson method.Simulation results,which are validated by experiments,reveal the influence of the fluctuating potential load on magnetic field distributions,stator and rotor currents,the input power and the power factor.The model and simulation results provide theoretical and technical supports for subsequent researches on model simplification and energy saving technologies.

The influence of rolling bearing clearances on diagnostic signatures based on a numerical simulation and experimental evaluation

This paper presents investigations into the influences of bearing clearances on the diagnostic features of monitoring rolling-bearings. A nonlinear dynamic model of a deep groove ball bearing with five degrees of freedom is developed for numerical analysis under increased radial clearances which are due to not only the scenarios of bearing grades but also gradual wear with bearing service lifetime. The model incorporates local defects and clearance increments in order to gain the insight into the bearing dynamics under different fault cases along with clearance changes. Numerical results show that the vibrations at fault characteristic frequencies exhibit clear inconsistency with common understandings for different cases of increased clearances. This study highlights that it has to take into account the clearance effect, especially for the inner race fault, in order to avoid the under-estimate of fault sizes which may be indicated by the feature amplitude reduction.