共查询到20条相似文献,搜索用时 77 毫秒
1.
2.
精密和超精密磨削机理及磨削砂轮选择的研究 总被引:7,自引:0,他引:7
从磨削砂轮及其修整、磨削用量、磨床精度等主要方面总结达到精密和超精密磨削效果的必要措施。提出有关超精密磨削机理的技术发展前沿并着重介绍有关超硬材料砂轮超精密磨削的研究趋势。 相似文献
3.
通过磨削试验 ,应用KL信息距离法对磨削火花信号进行处理以识别磨削过程中砂轮磨损状态的变化。研究结果表明 :时域和频域中的信息距离方法均能有效识别磨削过程中不同的砂轮磨损状态 ,但频域信息距离方法计算工作量较小 ,响应速度较快 ,对硬件要求较低 ,更有利于实现在线监控。 相似文献
4.
针对CNC在线视觉识别刀具磨损状态信息源单一、易受干扰导致识别准确率低、可靠性差的问题,提出一种基于异构数据融合的识别方法。采用自主研发的在线视觉检测装置和TCP/IP通信技术,获取工件切痕图像和机床内置传感器数据;基于与磨损相关的异构数据特征信息,利用支持向量机构建初步识别模型;使用邓熵与加权证据理论融合初步识别结果,得到刀具磨损状态最终识别结果。研究结果表明,该识别方法对测试集的识别结果准确率达到100%,且识别结果的均方误差最小,有较强的抗干扰能力。 相似文献
5.
用声发射(AE)信号在线监测砂轮状态的方法,可以监测工件材料、加工要求和磨削参数经常变化环境下砂轮钝化程度和破碎;并采用神经网络建立传感器信号与砂轮状态之间的非线性关系. 相似文献
6.
7.
从磨削砂轮及其修整、磨削用量、磨床精度等主要方面总结达到精密和超精密磨削效果的必要措施。提出有关超精密磨削机理的技术发展前沿并着重介绍有关超硬材料砂轮超精密磨削的研究趋势。 相似文献
8.
9.
基于神经网络信息融合的发动机磨损磨粒识别 总被引:1,自引:0,他引:1
磨粒识别和分类是铁谱分析技术在发动机故障诊断和状态监测的关键环节.针对单一神经网络模型磨粒识别的局限性,提出了一种基于不同类型神经网络信息融合的磨粒智能识别方法.首先利用径向基函数(RBF)神经网络和反向传播(BP)神经网络对磨粒进行识别,得到2组初始识别结果, 归一化后作为2组基本概率分配函数,然后利用D-S证据理论对其融合得到最终识别结果.实例计算表明,与单一神经网络模型相比,提出的信息融合方法提高了磨粒识别的区分度和准确率,并具有良好的通用性和容错性. 相似文献
10.
11.
本文系统讨论了砂轮磨损对型面磨削精度的影响及其补偿的基本原理与方法。在型面磨削中可采用轴向补偿或径向补偿。当采用径向补偿时,非法向外补偿误差δ可由下式加以估算:δ=△R(1-cosγ)限制△R可以减小此误差,但更有效的办法是限制补偿角Υ。根本消除误差δ的最有效方法是法向补偿:由于这时γ≡0,磨损量△R理论上不造成误差。介绍了作者研制的两种能从主靠模型面自寻法向的法向补偿机构——“导电滚轮”式与“偏心曲拐”式法向补偿机构。 相似文献
12.
XU Xusong CAO Yanlong YANG Jiangxin Institute of Contemporary Manufacturing Engineering Zhejiang University Hangzhou China 《机械工程学报(英文版)》2006,19(1):140-142
A condition monitoring method of deep-hole drilling based on multi-sensor information fusion is discussed. The signal of vibration and cutting force are collected when the condition of deep-hole drilling on stainless steel OCr17Ni4Cu4Nb is normal or abnormal. Four eigenvectors are extracted on time-domain and frequency-domain analysis of the signals. Then the four eigenvectors are combined and sent to neural networks to dispose. The fusion results indicate that multi-sensor information fusion is superior to single-sensor information, and that cutting force signal can reflect the condition of cutting tool better than vibration signal. 相似文献
13.
WAN Daping HU Dejin WU Qi School of Mechanical Power Engineering Shanghai Jiaotong University Shanghai China ZHANG Yonghong School of Information Communication Nanjing University of Information Science & Technology Nanjing China 《机械工程学报(英文版)》2006,19(4):509-513
Automatic compensation of grinding wheel wear in dry grinding is accomplished by an image based online measurement method. A kind of PC-based charge-coupled device image recognition system is schemed out, which detects the topography changes of the grinding wheel surface. Profile data, which corresponds to the wear and the topography, is measured by using a digital image processing method. The grinding wheel wear is evaluated by analyzing the position deviation of the grinding wheel edge. The online wear compensation is achieved according to the measure results. The precise detection and automatic compensation system is integrated into an open structure CNC curve grinding machine. A practical application is carried out to fulfil the precision curve grinding. The experimental results confirm the benefits of the proposed techniques, and the online detection accuracy is less than 5μm. The grinding machine provides higher precision according to the in-process grinding wheel error compensation. 相似文献
14.
IN SITU TRUING/DRESSING OF DIAMOND WHEEL FOR PRECISION GRINDING 总被引:1,自引:0,他引:1
WAN Daping WANG Yan HU Dejin 《机械工程学报(英文版)》2008,21(3):46-51
An application for achieving on-machine truing/dressing and monitoring of diamond wheel is dealt with in dry grinding. A dry electrical discharge (ED) assisted truing and dressing method is adopted in preparation of diamond grinding wheels. Effective and precise truing/dressing of a diamond wheel is carried out on a CNC curve grinding machine by utilizing an ED assisted diamond dresser. The dressed wheel is monitored online by a CCD vision system. It detects the topography changes of a wheel surface. The wear condition is evaluated by analyzing the edge deviation of a wheel image. The benefits of the proposed methods are confirmed by the grinding experiments. The designed truing/dressing device has high material removal rate, low dresser wear, and hence guarantees a desired wheel surface. Real-time monitoring of the wheel profile facilitates determining the optimum dressing amount, dressing interval, and the compensation error. 相似文献
15.
16.
17.
18.
基于有限元Arbitrary Lagrangian Eulerian(ALE)方法和Archard磨损理论建立了CRH5型动车组车轮的磨损分析模型。通过静态以及稳态分析结合修型运算,获取了车轮在典型工况下的磨损规律,包括车轮踏面磨损程度和磨损量沿踏面分布的动态变化规律。基于以上工作,又对不同磨损程度的车轮进行了疲劳寿命分析,总结了在磨损过程中,车轮的疲劳损伤速率随磨损的动态规律。结果发现:车轮的疲劳损伤速率在初期时呈显著下降趋势,当磨损超过整个仿真磨损量的70%时趋于平稳。 相似文献
19.
表面粗糙度模糊神经网络在线辨识模型 总被引:8,自引:0,他引:8
为解决零件加工中表面粗糙度在线检测困难这一问题,提出一种基于模糊神经网络的零件表面粗糙度在线辨识方法,并以外圆纵向磨削为例,建立表面粗糙度模糊神经网络在线辨识模型.首先研究前人建立的外圆纵向磨削零件表面粗糙度理论公式及经验公式,得出加工中的工件速度、砂轮速度、磨削深度和纵向进给量对零件表面粗糙度有直接影响,并进一步提出以在线测得的加工中工件与砂轮的速度比、磨削深度和纵向进给量作为零件表面粗糙度辨识模型的输入.由于加工过程极其复杂,无法建立加工中零件表面粗糙度与加工参数之间的精确数学模型,故将模糊神经网络引入建模过程中.同时,由于加工中零件表面粗糙度的对数与加工参数的对数存在线性关系,故模型中采用了T-S型模糊推理.此模型应用于实际磨削加工中,建模型精度可达97%,这进一步证明此在线辨识方法的可行性. 相似文献