The bic method generalized from ar model was adopted to determine the number of input neurons in grnn prediction model . the grnn was applied to single - step and multi - step ahead prediction of the vibration time series of a rotating machine , and its performance was compared with that of 3 - layers perceptrons network with error back propagation training algorithm ( bpnn ) . it is indicated that the grnn is more appropriate for prediction of time series than the bpnn , and the performance of grnn is qualified even with sparse sample data 研究了基于广义回归神经网络( grnn )的大型旋转机械振动状态预测，提出了应用bic准则确定grnn预测模型输入神经元数目的方法，将grnn用于大型机组振动峰?峰值时间序列的预测，与采用误差反向传播学习算法的三层前馈感知器网络( bpnn )的预测结果对比表明， grnn的预测性能优于bpnn ，而且，即使样本数据稀少，也能获得满意的预测结果。
As a result of the heightening of mechanical operation speed and the application of new materials and new structures , the nonlinear dynamic behavior in rotating machines is becoming increasingly outstanding and important . nonlinear dynamic phenomena in rotating machines cant be described , explained and predicted by rotordynamics based on linear system theory . along with the deepening and permeating of nonlinear scientific research , the nonlinear vibration of rotor systems has become an attractive field in recent years . from a point of view to set up the distinct corresponding relations between vibration states and failures of rotating machines , main advances in the research of rotor nonlinear vibration are summarized , and typical nonlinear dynamic phenomena and their forming mechanism are also summed up in the paper . the aim of the paper is to enrich the diagnostic knowledge base of rotating machines . 55refs 由于机械运转速度的不断提高和新型材料、新型结构的推广应用，旋转机械的非线性动力学行为日显突出和重要.基于线性系统原理的转子动力学理论与方法难以对实践中出现的丰富的非线性动力学现象作出准确的描述、阐释和预测.近年来，随着非线性科学研究的深入和渗透，转子系统非线性振动已成为应用力学和机械工程领域的研究热点之一.从有利于建立旋转机械振动状态集与故障集之间的映射关系出发，综述了近年来转子系统非线性振动研究的主要进展，总结了转子系统中出现的典型非线性动力现象及其产生机理，目的在于丰富旋转机械故障诊断知识库.参55
Based on the 40t - 43m portal crane , this paper analyzes deeply the problems which happen when the vibration monitoring technique is applied to the portal crane and puts forwards the ways of applying vibration monitoring technique to the lifting mechanism , enacts the original values of the relative judgement criteria of the lifting mechanism of the 40t - 43m portal crane and makes a under structure for the future state monitoring of crane 本文以40t ? 43m门座式起重机为对象，深入分析了振动监测技术在门机上应用所遇到的问题，提出了起升机构振动监测的方法，并制定了40t - 43m门座式起重机起升机构振动状态相对判断标准的初始值，为以后门座式起重机状态的监测打下基础。
