基于Fluent—BP神经网络的液体动静压轴承热特性分析

针对液体动静压轴承运转发热复杂的问题,应用Fluent软件对液体动静压轴承进行CFD仿真分析,获得不同输入状态下的油膜温度场分布以及轴承运转时的平均温度和最高温度。并在此基础上通过正交试验将Fluent仿真与BP神经网络相结合,实现对任意输入参数下轴承工作温度的预测,并对转速与供油压力以及供油压力与供油温度的综合作用效果进行分析。结果表明,主轴转速对轴承作用的效果比较显著,当轴承在高转速状态下运行时,需要提供高的供油压力来保证轴承的正常运转;当供油压力下降和供油温度上升同时出现时,轴承运转温度骤升,必须谨慎对待。利用BP神经网络的泛化功能,以少量的样本,可得到均匀全面的网络训练样本点,从而能快捷有效地实现对液体动静压轴承的热特性分析。     

小波包神经网络在轴承故障模式识别中的应用

基于不同点蚀模式的轴承振动信号的频域能量分布差异性,提出了基于小波包正交分解和BP神经网络的轴承点蚀故障模式识别技术。对轴承振动信号进行小波包正交四层分解,实现了信号空间完整拆分的同时得到了第四层由低频到高频的小波包分解系数,再分别进行单支重构得到各频段的成分。利用信号各频段的能量组成特征矢量作为神经网络的输入样本,对BP神经网络进行训练,获得模式识别网络;再用新数据进行网络的检验,结果证明网络的性能良好。     

基于BP神经网络的滚动轴承故障诊断研究

通过对滚动轴承振动信号的分析处理，提取能够反映轴承运行状态的特征量作为BP神经网络的输入，并用BP算法对该网络进行训练，利用神经网络的智能性来判断轴承所属的故障类型。仿真结果表明，该方法实用有效。     

用故障诊断方法判断机床主轴轴承的工作状态

阐述了利用轴承振动信号可判断机床主轴轴承的工作状态，通过频谱分析可对轴承进行故障诊断及预紧力确定；应用B＆K2148采集振动信号，MATLAB进行数据处理，对CKS6116型机床主轴前轴承进行了故障诊断与预紧力分析并取得了满意的效果。     

基于BP网络的机床主轴故障诊断研究

针对机床主轴在运转过程中由于高速、热变形和应力集中等原因而发生平移、旋转、压缩和伸展等,提出了一种基于BP神经网络和误差标定拟合对机床主轴轴心轨迹误差预测的方法。该方法首先通过实验测量出机床主轴轴心轨迹的偏心数据形成样本,运用BP神经网络对样本进行训练,然后根据样本训练结果预测机床主轴轴心偏转的将来值,最后通过三维张量空间分布函数分析将来值与理论值拟合情况得出机床运转状态。实验结果显示,当迭代次数epoch=2,训练误差为Validation=0.0052442时,训练后的拟合曲线拟合效果较好,此时BP训练状态最佳,训练后的主轴偏转结果能够反映和预测机床运转状态。本方法对于生产过程中的机床定期维修保养具有重要的指导意义。     

基于BP神经网络的水润滑艉轴承故障诊断研究

水润滑艉轴承是一种广泛应用于船舶等水中航行器推进系统的特种轴承,由于其工作的环境具有很大的不确定性,产品很容易出现各种故障,一旦故障产生将直接影响舰艇的安全航行和经济效益。本文利用Matlab软件的相关工具箱,基于神经网络的相关理论和方法,构建了BP神经网络模型来研究水润艉轴承工作时的摩擦因数、温度、噪声、振动等特征参数与轴承状态的关系,从而实现了对水润滑艉轴承工作状态的故障诊断。从Matlab仿真结果与实际情况的比对看,建立的BP神经网络可以很好的判断水润滑艉轴承的故障状态,能够在轴承早期故障时发出预警信号,提前对将要发生故障的轴承进行维修或更换,利用该方法可以有效提高水润滑艉轴承的使用性和安全性。     

基于PCA与BP神经网络的滚动轴承故障诊断

为了提高滚动轴承故障诊断效果,提出主成分分析结合BP神经网络的方法。简要介绍主成分分析法将轴承振动信号时域与频域的特征数据降维处理以及BP神经网络训练过程的原理。利用主成分分析与BP神经网络模型对凯斯西储大学轴承数据进行训练,将滚动轴承的状态类型作为网络输出结果。经过600组训练数据以及145组测试数据的仿真,结果表明主成分分析与BP网络模型比BP神经网络的训练误差精度相对提升了31.14%,测试误差精度相对提升了29.86%。     

复合式动静压轴承的结构设计及仿真分析

针对动静压电主轴在使用过程中存在轴向窜动的问题,结合动静压轴承的结构特点,在分析加工主轴运转中受力状况下,设计一种复合式动静压轴承,解决主轴运转过程中轴向窜动问题,并通过三维建模的方式,剖析了结构中的进油、回油、测压、冷却等系统的结构设计。以复合式动静压轴承设计参数为基础,通过利用FLUENT流体仿真软件和前处理软件GAMBIT重点对动静压止推轴承进行了不同转速状态下的仿真分析,得到油膜压力分布和温度分布云图,依此为依据,结合实际工况,进一步对止推轴承的不同工作载荷状态下的承载能力进行分析研究,并且结合实际情况分析结构设计的合理性,为后期的优化设计提供参考依据。     

矿井提升机主轴轴承状态监控研究

主轴是提升机重要组成零部件,主轴故障中轴承故障占比较高,实现轴承状态监测对提升主轴运行可靠性、降低故障发生率具有显著促进意义。基于此,综合使用Zig Bee网络、传感器检测技术以及信息融合分析技术构建主轴轴承状态监测系统。该系统采用传感器实现主轴振动、温度以及驱动电机电流、电压参数检测,通过Zig Bee网络将检测参数传输至服务器,通过服务器内置故障检测与诊断系统实现信息融合分析,达到判定轴承状态、故障预警等目的。现场测试发现,该系统可实时监测、记录主轴轴承状态,故障时发出预警信息,达到增强提升机主轴运行可靠性目的。     

基于EEMD_BP网络的滚珠丝杠副故障模式识别

针对在机械故障诊断领域,对信号的时频域处理分析提取特征值往往不能准确判断机械故障状态的问题。在对数控机床滚珠丝杠副振动信号研究中,提出了利用集合经验模态(EEMD)方法分析受到噪声干扰的3种不同状态的滚珠丝杠副振动信号。利用BP神经网络理论,以振动信号的时频域特征值及EEMD分解得到内禀模态函数(IFM)特征值作为输入,建立BP神经网络模型,并通过实验验证诊断网络模型的可靠性。     

A study on the development of a new conceptual automatic variable preload system for a spindle bearing

In machine-tool spindle systems, rolling bearings are generally the most widely used type of bearing, offering high stiffness and a large load capacity. The performance of bearings is greatly affected by the applied preload. This paper suggests a new automatic variable preload system that uses an eccentric mass device applied to the bearings of a spindle system. A spindle sustains centrifugal force when rotating. The eccentric mass device converts the radial direction force caused by the centrifugal force into axial force using an eccentric mass device. The eccentric mass device applies a small amount of force to the bearing when the spindle rotates at a low speed and applies large force to the bearing when the spindle rotates at a high speed. In this design, the device maintains a large preload at low speeds and lowers the preload at high speeds. Depending on the increase in the spindle rpm, the force that the eccentric mass device delivers to the axial direction will also increase. In addition, the preload applied to the bearings will be reduced. A finite element analysis was conducted to predict the shape of the eccentric mass device and changes of the preload. Based on the analysis results, a prototype was fabricated. According to the results of experiments conducted on the prototype, it was confirmed that the automatic variable preload device with the suggested structure operated satisfactorily. Also, vibration and noise of the prototype were measured and analyzed. The approach suggested in this study is expected to allow reduced manufacturing and operating costs, as the complex devices for hydraulic pressure or electricity required in existing variable preload devices can be eliminated.     

基于主轴电流信号多特征融合的刀具磨损状态监测

为实现在正常生产条件下进行刀具磨损的长期在线监测,提出了基于主轴电流信号和粒子群优化支持向量机模型(PSO-SVM)的刀具磨损状态间接监测方法。首先对数控机床主轴电机电流信号进行分析,将与刀具磨损相关的主轴电流信号多个特征参数和EMD能量熵进行特征融合作为输入特征向量;其次,通过粒子群寻优算法(PSO)对支持向量机模型(SVM)参数进行优化,建立基于主轴电流信号融合特征和PSO-SVM理论的刀具磨损状态识别模型;最后,通过实验采集某立式加工中心主轴在刀具不同磨损状态下电流信号进行验证,并与传统SVM模型、BP神经网络模型进行了对比分析。结果表明,所提出的方法具有较高的准确率和较好的泛化能力。能够实现正常生产条件下对刀具磨损的长期在线监测。     

A review on the preload technology of the rolling bearing for the spindle of machine tools

The performance of the spindle system and bearings in a machine tool is largely influenced by the preload applied to bearings. Therefore, it is a very important issue to determine a proper preload in bearings and apply it to bearings for satisfying the performance required in bearings according to its operation conditions. This study performed a review on the preload technologies through classifying these technologies into three categories; a preload configuration technology that properly determines the preload for optimizing the performance of bearings, a preload application technology that applies the determined preload to bearings during the operation of a spindle system as a reliable way, and a preload measurement technology that verifies the preload applied to an actual spindle system.     

基于递归熵及长短期记忆神经网络的滚动轴承退化趋势预测

针对滚动轴承退化趋势预测中的特征选择及模型优化问题,提出了基于相空间重构结合长短期记忆神经网络的滚动轴承退化趋势预测方法.首先,在滚动轴承退化特征灰色关联分析的基础上,对滚动轴承运行状态跟踪能力进行量化评估;然后,为统一描述各个特征对轴承退化状态的表征信息,采用谱聚类方法对滚动轴承运行状态进行了准确划分;最后,以滚动轴...     

HIPSN陶瓷轴承在高速电主轴中的应用

陶瓷轴承逐步在电主轴制造中得到应用.通过试验研究,对比分析不同类型磨用电主轴的振动、温升特性,为陶瓷球轴承的实际应用提供一定的技术依据.     

高速电主轴结构的改进

对高速电主轴轴承的配置和预紧方式的选择进行了分析研究,并建立了高速电主轴轴承-主轴系统的参数化有限元模型,运用ANSYS有限元分析软件的优化设计功能,以提高主轴刚度为目标,通过指定参数作为设计变量、状态变量和目标函数来建立分析程序,并以设计变量为自变量,不断改变其数值,迭代计算直至目标函数值达到最小,迭代过程中,状态变量用于控制自变量取值。结果表明:主轴支承跨距优化后,刚度和一阶固有频率得到了一定程度的提高,从而为电主轴结构的改进提供了理论基础。     

Application of backpropagation neural network for spindle vibration-based tool wear monitoring in micro-milling

This study develops a micro-tool condition monitoring system consisting of accelerometers on the spindle, a data acquisition and signal transformation module, and a backpropagation neural network. This study also discusses the effect of the sensor installations, selected features, and the bandwidth size of the features on the classification rate. To collect the vibration signals necessary for training the system model and verifying the system, an experiment was implemented on a micro-milling research platform along with a 700?μm diameter micro-end mill and a SK2 workpiece. A three-axis accelerometer was installed on a sensor plate attached to the spindle housing to collect vibration signals in three directions during cutting. The frequency domain features representing changes in tool wear were selected based on the class mean scatter criteria after transforming signals from the time domain to the frequency domain by fast Fourier transform. Using the appropriate vibration features, this study develops and tests a backpropagation neural network classifier. Results show that proper feature extraction for classification provides a better solution than applying all spectral features into the classifier. Selecting five features for classification provides a better classification rate than the case with four and three features along with the 30?Hz bandwidth size of the spectral feature. Moreover, combining the signals for tool condition from both direction signals provides a better classification rate than determining the tool condition using a one-direction single sensor.     

主轴系统的研究与轴承的应用

以HTC40n系列卧式数控车床为例,介绍了主轴系统的关键技术,并对主轴系统关键件的加工工艺与主轴轴承的精密装配等方面进行了分析与研究。     

Using neural networks for the diagnosis of localized defects in ball bearings

Two neural network based approaches, a multilayered feed forward neural network trained with supervised Error Back Propagation technique and an unsupervised Adaptive Resonance Theory-2 (ART2) based neural network were used for automatic detection/diagnosis of localized defects in ball bearings. Vibration acceleration signals were collected from a normal bearing and two different defective bearings under various load and speed conditions. The signals were processed to obtain various statistical parameters, which are good indicators of bearing condition, and these inputs were used to train the neural network and the output represented the ball bearing states. The trained neural networks were used for the recognition of ball bearing states. The results showed that the trained neural networks were able to distinguish a normal bearing from defective bearings with 100% reliability. Moreover, the networks were able to classify the ball bearings into different states with success rates better than those achieved with the best among the state-of-the-art techniques.     

一种主轴松刀卸荷机构在卧式加工中心上的应用

针对国内大多数加工中心主轴松刀机构都是将松刀力沿轴向作用在主轴轴承上的情况,设计了一种主轴松刀卸荷机构。该机构能有效改善主轴轴承的受力情况,从而延长了主轴轴承的使用寿命,保证了机床的加工精度。