共查询到17条相似文献,搜索用时 156 毫秒
1.
2.
3.
为了实现数控车削批量加工刀具磨损状态的在线监测,在分析切削功率与刀具磨损量关系的基础上,考虑加工参数对切削功率的影响,基于正交实验设计与响应面法,建立了切削功率与刀具磨损量及加工参数之间的回归模型。提出一种实时更新切削功率阈值的刀具磨损状态在线监测方法。该方法首先对功率信号进行滤波处理,结合数控系统判断机床的运行状态,然后实时计算切削功率阈值并与实际加工过程切削功率进行比较来监测刀具的磨损状况。通过实验案例自动在线监测数控车削过程中刀具磨损的情况,验证了该方法的有效性。 相似文献
4.
5.
6.
7.
为实现刀具磨损状态的有效在线监测,提出一种基于一维卷积长短时记忆网络的多信号融合刀具磨损评估模型.该模型综合使用加工过程中主轴和工作台的振动和声发射信号,以实现信号间的优势互补,弥补单一信号的不足;基于一维卷积的特征学习能力和长短时记忆网络的时序特征分析能力,充分挖掘信号中包含的刀具磨损状态信息;最后通过全连接层和softmax分类器对刀具磨损状态进行评估.试验结果表明,该模型在各单一工况下对刀具磨损状态的识别准确率均可达93.8%以上,整体工况下识别准确率达95.3%,具有很好的稳定性和多工况通用性. 相似文献
8.
9.
《制造技术与机床》2019,(10)
刀具磨损状况的实时检测是目前机床加工状态监测的难点,而对刀具的振动信号分析的常用方法是利用神经网络模型来判断刀具磨损状态。为解决循环神经网络(RNN)模型训练过程中梯度容易消亡的现象,提出基于长短期记忆神经网络的刀具磨损状态在线监测。刀具在进行切削加工时,首先通过加速度传感器采集刀具振动信号,然后对振动信号小波包变换进行分解是让信号通过不同的滤波器进行有条件的选择,由此形成不同的能量值,用作为长短期记忆神经网络的特征输入,从而诊断出刀具磨损状态的3种状态故障;最后利用长短期记忆神经网络模型对处理时间序列的数据有比较好的效果,它可以捕捉长期的依赖关系和非线性动态变化。此外,通过与多层(BP)神经网络和(BP)神经网络故障诊断方法进行比较,结果表明,LSTM网络对刀具磨损状态在线监测更加有效。 相似文献
10.
11.
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。 相似文献
12.
为实现截齿截割过程中磨损程度的实时精准在线监测,提出了一种基于BP神经网络的截齿磨损程度多特征信号融合的检测方法。通过提取截割过程中不同磨损程度截齿的三向振动信号、红外温度信号和电流信号,建立了不同磨损程度截齿的多特征信号样本数据库,采用多特征信号样本对BP神经网络进行学习和训练,建立截齿磨损程度的识别模型,实现截齿磨损程度在线监测与精确识别。实验结果表明:基于BP神经网络的截齿磨损程度监测系统,网络判别结果和测试样本的实际磨损程度类别相符,该BP神经网络系统能够对截齿磨损程度类型进行准确的监测和识别。 相似文献
13.
《Mechanical Systems and Signal Processing》2007,21(1):466-479
Cutting tool wear degrades the product quality in manufacturing processes. Monitoring tool wear value online is therefore needed to prevent degradation in machining quality. Unfortunately there is no direct way of measuring the tool wear online. Therefore one has to adopt an indirect method wherein the tool wear is estimated from several sensors measuring related process variables. In this work, a neural network-based sensor fusion model has been developed for tool condition monitoring (TCM). Features extracted from a number of machining zone signals, namely cutting forces, spindle vibration, spindle current, and sound pressure level have been fused to estimate the average flank wear of the main cutting edge. Novel strategies such as, signal level segmentation for temporal registration, feature space filtering, outlier removal, and estimation space filtering have been proposed. The proposed approach has been validated by both laboratory and industrial implementations. 相似文献
14.
针对数控铣床不断老化导致刀具磨损预测模型误差较大,加工过程中动态数据难以在线采集等问题,提出一种数字孪生驱动的刀具磨损在线监测方法。采用神经网络对加工过程中的多源数据进行特征提取,建立考虑机床老化的刀具磨损时变偏差量化模型,并在此基础上提出数控铣削刀具磨损的在线预测方法;开发了面向刀具磨损的数控铣削数字孪生系统,在线感知加工过程中的动态数据并实时仿真刀具磨损过程;最后,将该方法应用于实际加工中并与其他的预测方法进行了对比,结果表明该方法有效降低了机床老化带来的误差,实现了刀具磨损的精确预测。 相似文献
15.
Development of a tool wear observer model for online tool condition monitoring and control in machining nickel-based alloys 总被引:1,自引:1,他引:0
X. Q. Chen H. Z. Li 《The International Journal of Advanced Manufacturing Technology》2009,45(7-8):786-800
Online monitoring and in-process control improves machining quality and efficiency in the drive towards intelligent machining. It is particularly significant in machining difficult-to-machine materials like super alloys. This paper attempts to develop a tool wear observer model for flank wear monitoring in machining nickel-based alloys. The model can be implemented in an online tool wear monitoring system which predicts the actual state of tool wear in real time by measuring the cutting force variations. The correlation between the cutting force components and the flank wear width has been established through experimental studies. It was used in an observer model, which uses control theory to reconstruct the flank wear development from the cutting force signal obtained through online measurements. The monitoring method can be implemented as an outer feedback control loop in an adaptive machining system. 相似文献
16.
S. Y. Liang Y. K. Kwon R. Y. Chiou 《The International Journal of Advanced Manufacturing Technology》2004,23(11-12):857-864
This paper discusses an analytical assessment of the effect of cutting tool flank wear on machining stability along the thrust direction in a turning operation based on an analysis of frequency band root-mean-square (RMS) level of the accelerometer signals. The energy content of machining at the tool-tip/workpiece interface along the flank is represented by the RMS signal level, in comparison to the random vibration of the cantilever portion of the tool holder. The RMS signals measured from a tool-post accelerometer in stable machining with tool wear effect are calculated using the frequency band RMS method at the first natural frequency of the cantilever portion of the tool holder. Increasing flank wear results in increasing stability and decreasing RMS in the thrust direction in machining. For model validation, a series of machining experiments were performed under the condition of various flank wear/land widths, while the RMS signals from a tool-post accelerometer were collected and studied. It was found that theoretical predictions were shown to be in agreement with experimental results. 相似文献