Temperature prediction model for a high-speed motorized spindle based on back-propagation neural network optimized by adaptive particle swarm optimization

To predict the temperature of a motorized spindle more accurately,a novel temperature prediction model based on the back-propagation neural network optimized by adaptive particle swarm optimization(APSO-BPNN)is proposed.First,on the basis of the PSO-BPNN algorithm,the adaptive inertia weight is introduced to make the weight change with the fitness of the particle,the adaptive learning factor is used to obtain different search abilities in the early and later stages of the algorithm,the mutation operator is incorporated to increase the diversity of the population and avoid premature convergence,and the APSO-BPNN model is constructed.Then,the temperature of different measurement points of the motorized spindle is forecasted by the BPNN,PSO-BPNN,and APSO-BPNN models.The experimental results demonstrate that the APSO-BPNN model has a significant advantage over the other two methods regarding prediction precision and robustness.The presented algorithm can provide a theoretical basis for intelligently controlling temperature and developing an early warning system for high-speed motorized spindles and machine tools.

Research Progress of Key Technology of High-Speed and High Precision Motorized Spindles

High speed machining and high precision machining are two tendencies of themanufacturing technology worldwide. The motorized spindle is the core component of the machine toolsfor achieving the high speed and high precise machining, which affects the general developmentlevel of the machine tools to a great extent. Progress of the key techniques is reviewed in thispaper, in which the high speed and high precision spindle bearings, the dynamical and thermalcharacteristics of spindles, the design technique of the high frequency motors and the drivers, theanti-electromagnetic damage technique of the motors, and the machining and assembling technique areinvolved. Finally, tha development tendencies of the motorized spindles are presented.

异步电主轴三维热误差多物理场耦合分析及计算

为综合考虑高速异步电主轴径向形变及轴向形变对其热误差的影响,分析电主轴各部分损耗。计及径向及轴向形变热误差,提出一种基于电磁-热-机械多物理场耦合的电主轴形变分析方法。分析电主轴机械结构、损耗、温升、电磁等物理场的耦合关系,设计多物理场耦合热误差分析模型计算流程。对异步电主轴进行三维有限元建模,并对其采样点的温升进行计算,并通过实验得出采样点的温升曲线,对比两条电主轴采样点的温升曲线可以验证有限元仿真的准确性。在有限元模型基础上进行多物理场计算,计算结果表明,电主轴由于机械和电磁损耗产生轴向热误差为6.54μm,由于径向形变而产生的基频气隙磁感应强度畸变率为7.6%,基于Maxwell张力张量法得到径向热误差为39μm。研究结果为机床误差分析及优化设计提供了理论基础。

高速异步主轴电机磁链观测器的设计

实现宽速度范围内磁链的准确观测是高速异步主轴电机控制中需要解决的一大难题,针对传统电流模型和电压模型磁链观测器在不同速度都存在其各自的缺陷,受电机参数变化的影响较大,设计了一种采用开环电流模型和闭环电压模型相结合的闭环磁链观测器。为提升磁场控制的快速响应性,采用转子磁场定向,定子磁通调节的方式进行控制。同时采用此方法设计磁链观测器电压模型中没有漏感项,高速运行时,对参数变化不敏感。还从各观测器的数学模型对其参数的敏感性进行了分析,仿真和实验结果证实了该方法的有效性。

基于有限元的异步型电主轴电机电磁场分析和参数优化

基于经典的麦克斯韦瞬态电磁场分析理论,采用Ansoft有限元软件对异步型电主轴电动机进行工况仿真和瞬态磁场分析,旨在获取该电机的电磁转矩、效率、功率因数等主要工作指标,并探讨电机效率与定、转子轴向长度的变化规律。有限元分析结果验证了电机机械特性、效率与转速变化曲线、磁链分布、定子电磁参数变化等规律;仿真结果显示,在满足槽满率不大于75%的前提下,电机效率并非是铁心长度的一次函数,其峰值位于铁心长为155 mm左右。

高速异步主轴电机的热分析与冷却结构设计

高速主轴电机是电主轴的关键核心部件,电机发热直接影响电主轴的加工精度和运行可靠性。以一台10万转主轴异步电机为例,对高速异步主轴电动机进行深入的热分析,设计高效的散热冷却结构,确保主轴电机的可靠平稳运行。确定主轴电机的主要热源,研究转子转速、转子表面粗糙度对主轴电机风摩损耗的影响规律;考虑旋转磁场和谐波对铁耗计算的影响,采用齿轭分区的有限元法提高仿真精度,分析电机铁耗的分布规律。基于流体力学对电机进行3D热仿真,对比主流的周向螺旋型和轴向Z字型两种冷却结构的冷却效果,确定高效的冷却结构设计方案,并进一步采用转子铁心开空气槽的设计方案,增加转子铁心与转轴之间的热阻,提高电机的散热能力,确保电机的转轴温升在安全范围内,最后校核转子结构的机械强度,保证主轴电机运行的可靠性。

机床节能控制系统设计思路及实现方式分析——以立式机床为例

大型立式车床工作量巨大,长期处于高强度工作状态当中,其工作过程中会消耗大量的能源。为了做好节能减排工作,推动制造业节能转型升级,我们需要为立式机床设计节能控制系统,在不影响其生产效率的基础上,降低机床的能耗。借助PLC技术对立式机床的电气控制系统进行优化,并设计三项交流异步电机变频驱动控制系统,提升立式机床的技能水平。