基于在线学习的数控加工刀具寿命动态预测方法

预测刀具寿命对保证零件质量和控制加工成本意义重大,但刀具磨损过程复杂多变,刀具剩余寿命受工况影响难以准确预测。针对以上问题,提出了一种基于在线学习的刀具寿命动态预测方法,以长短时记忆网络为基础模型,融合在线学习模块,使得模型能够在加工过程中自动更新参数,实现变工况下刀具寿命的精确预测。进行了铣削加工试验,结果表明,刀具寿命动态预测方法可以有效提升刀具寿命预测精度。     

基于主轴电流小波变换的刀具磨损状态监测

为消除机器人自动制孔系统中由于刀具磨损引起的孔径误差,提出一种基于主轴电流离散小波变换的刀具磨损状态在线监测以及寿命预测方法。首先根据主轴电流信号的波动规律,综合小波信号的正则性、相似性及曲线误差光滑性等要求,选用3阶多贝西小波基对主轴电流信号进行离散分解。结合刀具磨损规律,选取电流信号的3阶低频分解量作为刀具磨损状态监测的最有效特征,将电流信号的1阶高频分解量进行离散傅里叶变换,得到高频分量的频域特性,为电磁兼容设计提供依据;最后利用最小二乘法拟合刀具磨损量与主轴电流特征值的线性关系,通过监测主轴电流特征值,实现对刀具后刀面磨损量的在线监测以及刀具寿命预测。     

基于多参量状态信息融合的刀具磨损状态智能识别

鉴于刀具磨损监控在自动化生产中的重要性,建立了基于切削力和基于相对切削时间的两种磨损检测模型．切削力模型是利用回归算法和模糊分类技术建立的,通过检测切削力信号可在线识别刀具磨损状态．基于相对切削时间模型利用回归技术直接建立刀具磨损量与切削参数及时间的关系,可在较大的切削条件变化范围内实现对刀具磨损的识别．     

难加工材料刀具磨损检测技术研究与应用

利用刀具磨损检测技术,拍摄刀具后刀面磨损图像,以磨损图像为基础,分析刀具磨损状况、确定刀具磨损量,然后采用离散刀具磨损过程与有限元仿真相结合的方法实现长时间切削刀具磨损的仿真。对刀具磨损检测仪的原理、构成及检测过程等做了简要介绍,并对其在难加工材料切削参数优化、新刀具选用试切方面进行了初步应用。     

刀具声发射信号混沌特征提取及趋势分析

旨在建立一种基于多混沌特征演化分析的刀具磨损状态监测方法,通过计算刀具声发射信号的混沌特性参数分析其磨损趋势。建立首先基于混沌理论分析和描述刀具不同磨损阶段声发射信号的混沌特性,包括：定性描述,即重构相空间的奇异吸引子轨迹和庞加莱截面;定量描述,计算不同时间段声发射信号的关联维数、最大Lyapunov指数等。其次,采用最小二乘回归方法对所计算的混沌参数进行趋势分析。结果表明,声发射信号具有混沌特性,而且关联维数和最大Lyapunov指数演化趋势与刀具的磨损状态具有一定的关联,从而为刀具磨损状态的在线监测和预测提供了新思路。     

切削加工刀具磨损及其预测建模技术研究进展

刀具磨损不仅影响工件加工表面质量和加工精度,而且频繁地换刀还会降低加工效率、增加生产成本,通过研究刀具磨损机理,影响刀具磨损的因素以及刀具磨损预测模型建模技术,为降低刀具磨损提供技术支持。对切削加工过程中刀具磨损及其预测建模技术的研究进展进行了综述。首先,基于近年来刀具磨损机理研究进展,分别对几种主要刀具磨损机理的表现形式及特征进行了分析。其次,重点论述了切削加工过程中切削参数、刀具几何参数、刀具和工件材料特性及加工方法等因素对刀具磨损影响规律,总结分析了刀具磨损预测建模方法和形式。最后,结合制造业绿色节能的发展理念和高速发展的计算机技术,指出降低刀具磨损的加工方法和刀具磨损预测建模技术的未来发展方向。     

镗削声发射信号与镗刀磨损量关系的研究

 对镗削过程中声发射信号与刀具磨损之间的关系进行了实验研究和理论分析,得到了声发射信号的特征量与刀具磨损量之间的关系。本文提出用声发射信号随时间变化的记录长度内最大峰值电压V_(pmax)对时间f的累积均值(?)及累积均方差σ_t为在过程(In-Process)实时辨识镗刀磨损的特征量,以便实现刀具磨损的预报控制。     

基于萤火虫算法的CFRP材料铣削刀具结构优化

为了提高CFRP零件的加工表面质量和刀具寿命,针对其铣削加工的刀具结构进行了优化。设计了刀具结构参数与CFRP材料铣削加工表面粗糙度、后刀面磨损量之间的正交试验。应用极差分析法分析了刀具结构参数对CFRP材料加工表面粗糙度、后刀面磨损量的影响规律,并应用多元线性回归法建立了刀具结构参数与表面粗糙度、后刀面磨损量之间的数学模型。基于此模型,采用FA萤火虫算法,优化了刀具的结构参数,并进行了实验验证。结果表明:在试验参数范围内,刀具结构参数对于CFRP工件铣削表面粗糙度的影响程度依次为:后角、螺旋角、前角。当刀具的后角、螺旋角和前角增大时,工件的表面粗糙度都呈减小趋势,但减小的快慢程度不同;刀具结构参数对于后刀面磨损影响程度依次为:后角、螺旋角、前角。当刀具后角增大时,后刀面磨损量迅速上升,当螺旋角增大时,后刀面磨损量减小,当刀具的前角增大时,后刀面磨损量先减小后增大。采用FA萤火虫算法优化后的刀具结构对CFRP材料进行铣削实验,实验结果值与建立的模型预测值误差较小,表面粗糙度的误差率为3%,刀具后刀面磨损量的误差率为7.6%。     

刀具磨损估计的多传感器融合神经网络方法研究

研究了利用声发射、振动和电机功率信号经BP算法信息融合估计刀具磨损量的方法,采用简单有效的灰色模型关联分析法选择特征参数,研究了网络参数对性能的影响以及网络性能的稳定性。     

基于飞行过程数据的航空发动机故障诊断方法研究

针对航空发动机飞行过程数据,结合门控循环单元（GRU）动态网络和深度神经网络（DNN）,提出了一种数据驱动的航空发动机故障诊断结构。首先,从飞行数据中抽取发动机健康数据,并通过一组GRU网络建立发动机在健康状态下的动态模型。其次,通过GRU动态模型的预测值与真实测量信号生成残差信号,残差信号作为DNN网络的输入预测发动机健康参数。最后,通过诊断决策模块实现对发动机的故障检测与识别。使用仿真生成的真实飞行工况数据集对提出的故障诊断系统进行了验证。结果表明,相比于直接使用传感器测量数据,基于GRU网络的残差结构能够大幅提升故障检测和识别性能,故障检测和识别准确率分别可达96.51%和95.06%,并且对训练数据样本数量的依赖性较小,较少的训练样本也能获得很好的预测结果。     

Gaussian process regression model incorporated with tool wear mechanism

Cutting tool condition directly affects machining quality and efficiency. In order to avoid severely worn tools used during machining process and fully release the remaining useful life in the meanwhile, a reliable evaluation method of remaining useful life of cutting tools is quite necessary. Due to the variation of cutting conditions, it is a challenge to predict remaining useful life of cutting tools by a unified model. In order to address this issue, this paper proposes a method for predicting the remaining useful life of cutting tools in variable cutting conditions based on Gaussian process regression model incorporated with tool wear mechanism, where the predicted value at adjacent moments is constrained to a linear relationship by the covariance matrix of Gaussian model based on the assumption of progressive tool wear process, so the wear process under continuous changing conditions can be modelled. In addition to that, the input feature space and the output of the model are also enhanced by considering the tool wear mechanism for improving prediction accuracy. Machining experiments are performed to verify the proposed method, and the results show that the proposed could improve the prediction of tool remaining useful life significantly.     

Evaluation of tool wear and cutting performance considering effects of dynamic nodes movement based on FEM simulation

An accurate estimation of tool wear morphology can provide the opportunity to investigate the influence of tool wear on cutting performance as well as reduce the overall production cost. However, tool wear prediction is still a very challenging research issue. In this paper, a novel method for simulating the actual chip formation and wear evolution thorough the 3D finite element model has been carried out. In order to improve the accuracy of simulation results, the influence of worn tool, stress and temperature distribution on wear rate are considered. Then cutting experiment has been conducted by turning AISI1045 with uncoated carbide tools to validate the accuracy of the proposed model. The comparison between experimental and simulation results show good agreement which proves the ability of the proposed model in forecasting the tool wear. The validated finite element model has been further utilized studying how the worn tool affects the cutting performance including actual cutting rake, stress distribution, cutting force and temperature. The results of this paper not only provide a clear understanding of wear evolution between tool rake face and chip, but also are meaningful to optimize tool design and cutting parameters.     

铣削过程多参数监测策略研究

 通过在时域和频域对端铣过程铣削力和铣削振动信号特征的分析,提取出对铣刀磨损和破损状态变化十分敏感的特征参量,在此基础上提出了由基于铣削力的“时段比值”监测策略和基于铣削振动的“硬件比较”监测策略组成的多参数监测策略。     

基于磨粒磨损机理的机械磨损状态监测

针对机械设备磨损状态监测准确率较低的问题,基于不同磨损机理下磨粒具有不同的形状和纹理特征,提出了一种基于磨粒特征识别的机械磨损状态监测的数学模型。通过形状特征识别球状磨粒和切削磨粒,结合形状、纹理特征识别疲劳磨粒和严重滑动磨粒,基于提取的特征参数建立机械磨损状态监测的特征向量,通过量子粒子群优化(QPSO)的径向基函数神经网络模型,实现对机械磨损状态的监测和判别。实验结果表明:QPSO-RBF神经网络数学模型结构简单,比传统PSO-RBF神经网络模型的识别准确率高5%,可用于常见机械磨损状态的检测。      

TC4的铣削加工中铣削力和刀具磨损研究

通过TC4铣削加工时的铣削力试验,研究了干切削时和有氮气介质铣削时影响铣削力大小的几个因素,为提高金属去除率优化了切削参数。同时通过刀具磨损试验,对上述两种铣削方式,比较了在不同的切削速度下铣削时铣刀后刀面的磨损,证实了以氮气为切削介质能够大大地改善刀具的磨损状况和提高刀具的寿命。     

Cutting tool temperature prediction method using analytical model for end milling

Dramatic tool temperature variation in end milling can cause excessive tool wear and shorten its life, especially in machining of difficult-to-machine materials. In this study, a new analyt-ical model-based method for the prediction of cutting tool temperature in end milling is presented. The cutting cycle is divided into temperature increase and decrease phases. For the temperature increase phase, a temperature prediction model considering real friction state between the chip and tool is proposed, and the heat flux and tool-chip contact length are then obtained through finite element simulation. In the temperature decrease phase, a temperature decrease model based on the one-dimension plate heat convection is proposed. A single wire thermocouple is employed to mea-sure the tool temperature in the conducted milling experiments. Both of the theoretical and experi-mental results are obtained with cutting conditions of the cutting speed ranging from 60 m/min to 100 m/min, feed per tooth from 0.12 mm/z to 0.20 mm/z, and the radial and axial depth of cut respec-tively being 4 mm and 0.5 mm. The comparison results show high agreement between the physical cutting experiments and the proposed cutting tool temperature prediction method.     

钛合金TB6刀具磨损铣削实验研究

使用硬质合金刀具对钛合金TB6进行正交铣削实验,对比分析不同切削参数下的刀具磨损情况,并用实验结果进行回归分析得到刀具磨损的回归公式。结果表明:刀具主要磨损在后刀面,其磨损大都呈现一条带状磨损带,在速度增大时大磨损带变长,刀具易发生脆性破损,且在刀具表面会出现钛合金粘连;对刀具耐用度的影响大小依次为切削速度、进给量、切削宽度和切削深度;刀具磨损回归方程具有良好的回归方差,能够很好的对刀具寿命进行预测。