铣刀磨损量监测和剩余寿命预测方法研究

研究在线诊断端面铣刀磨损量和预测铣刀剩余寿命的方法。首先通过实验采集Y向铣削力作为监测信号,分析铣削力与刀具磨损量VB和刀具磨损时间之间的关系。然后,通过铣削力信号分析提取出有效监测特征向量,此特征向量作为BP神经网络的输入,用于刀具磨损量的监测和剩余寿命的预计。最后,通过实验证明,该神经网络模型误差很小,利用该方法能够正确地进行在线监测和预测。     

基于主轴电流和振动信号的数控机床刀具磨损在线预测

为了实现数控机床加工过程中刀具磨损状态的在线预测，提高数控机床智能化水平，提出一种基于主轴电流和振动信号的数控机床刀具磨损在线预测方法。这一在线预测方法采集能够反映刀具磨损状态的主轴电流和振动信号，对信号进行频域、时频分析处理，采用小波包分解和经验模态分解两种方法进行特征提取，得到与刀具磨损状态变化密切相关的特征值，按照递增或递减趋势进行保序回归操作，使用指数平滑方法进行平滑处理，由此建立基于遗传算法参数寻优的支持向量回归模型，用于预测刀具磨损量。试验及应用表明，应用这一在线预测方法，刀具磨损预测的平均误差在25μm以内，满足企业加工要求。     

基于高斯回归分析的高温合金刀具磨损在线预测方法

目前的高温合金刀具磨损在线预测方法预测时间过长,预测误差较大.为了解决上述问题,基于高斯回归分析方法建立了一种新的高温合金刀具磨损在线预测方法,设立高斯回归模型,分析切削力和刀具磨损时间序列数据,对数据进行划分,列出线性数据和非线性数据.引入平滑度理论对建立的高斯回归模型进行优化,借助构建的高斯回归模型计算刀具刀面的最...     

基于多通道融合及贝叶斯理论的刀具剩余寿命预测方法

刀具监测及可用剩余寿命(RUL)预测对降本增效及保证加工质量意义重大.针对单一传感器预测精度波动大、数据利用率低、可靠性低等问题,提出一种多通道信号融合及贝叶斯更新的刀具剩余寿命预测方法.通过计算多通道信号所提取特征的时间序列与对应时间矢量的斯皮尔曼等级相关系数对特征时序做单调性排序,取单调性得分高的特征用主成分分析进行融合并构建健康因子作为观测数据,基于贝叶斯理论及马尔科夫链蒙特卡洛采样估计退化模型参数,并随着时间推进及监测数据序贯可获,实时在线更新退化模型参数以逐渐逼近刀具磨损退化趋势,同时对每时刻剩余寿命进行迭代估计.所提方法可避免基于深度学习方法需要依赖大量全寿命数据离线训练预测模型且模型对新预测任务适应性有限的局限性.用PHM2010公开数据挑战赛中三槽球头硬质合金铣刀切削不锈钢过程磨损全寿命数据集验证了方法有效性.     

基于深度学习的铣刀剩余寿命预测方法研究

刀具剩余寿命预测对保证设备正常运行和提高生产效率具有重要意义.建立了一种改进的基于一维卷积神经网络(one-Dimensional Convolutional Neural Network,1DCNN)和双向门控循环单元(Bidirectional Gated Recurrent Unit,BiGRU)的铣刀剩余寿命预测混合模型.借助评分函数能对误差进行不同程度的惩罚,在均方误差函数的基础上引入评分函数,构造了一种基于均方误差和评分函数(MSE-Score)的调和平均(Harmonic Mean-MSE-Score,HM-MSE-Score)损失函数;利用卷积层和池化层代替BiGRUs处理后的全连接层,设计了1DCNN-BiGRUs-CP混合模型,实现铣刀剩余寿命预测.结合铣刀磨损实验,验证了该预测混合模型具有较高的预测精度和较快的运行速度,研究结果能为数控加工过程中铣刀剩余寿命预测提供理论依据.     

A880高压动叶片型面加工R5球头铣刀磨损机理与寿命研究

针对X22CrMo V12-1-5钢汽轮机A880高压动叶片型面加工R5球头铣刀磨损机理及寿命进行研究。通过模拟现场工况下的R5球头铣刀磨损实验得到刀具磨损曲线和刀具寿命,分析了R5球头铣刀的磨损失效机理,得到R5球头铣刀最大不崩刃许用切削长度和铣刀全寿命周期中可以加工的叶片数目。利用所得到的R5球头铣刀寿命量化模型对加工现场报废的R5球头铣刀做了剩余寿命挖掘,研究发现加工现场报废的刀具仍然具有较大的使用价值并根据模型预测了其剩余寿命。研究结论可应用于实际生产中R5球头铣刀的寿命管理,大幅度提高实际加工中R5球头铣刀的使用效率。     

基于迁移学习的刀具剩余寿命预测方法

在新加工工艺条件下,针对历史工艺条件下的刀具剩余寿命预测模型失效,且新工艺条件下缺乏足够的训练样本构建新预测模型的问题,提出一种基于动态对抗域适应的迁移学习方法,以快速构建新工艺条件下的刀具剩余寿命预测模型.首先,利用历史工艺条件下带寿命标签的过程监控数据样本,预训练源域的刀具剩余寿命预测模型.其次,通过对抗域适应训练,利用新工艺条件下的少量目标域样本,对源域预训练得到的预测模型进行部分模型参数的调整.利用调整后的模型进行新工艺条件下的刀具剩余寿命预测.最后,更新目标域样本,重复进行对抗域适应训练与预测操作,直至结束.以轮槽铣刀的加工为例,验证了所提方法的有效性.     

LS-SVM回归算法在刀具磨损量预测中的应用

提出了基于最小二乘支持向量机回归算法的刀具磨损量预测方法。该方法首先利用经验模态分解算法对非线性、非平稳的声发射信号进行平稳化处理,得到了若干个固有模态函数;然后建立了每个固有模态函数的自回归模型,并提取模型系数构造特征向量;最后采用最小二乘支持向量机回归算法实现了刀具磨损量的预测。该方法与神经网络预测算法相比,具有更高的预测准确率,可有效预测当前切削状态下10s后的刀具磨损量。     

一种离线刀具寿命预测管理系统的开发

提出了一种离线的刀具寿命预测管理系统,该系统集刀具寿命预测-评价-管理三大功能于一体.以刀具后刀面磨损量作为刀具寿命磨钝标准,以扩展的泰勒刀具寿命公式为理论基础,考虑机床刚度、刀具几何参数、零件特征、切削参数等因素对刀具寿命的影响,建立了刀具寿命回归模型.运用方差分析方法,对刀具寿命预测模型的拟合精度、预测精度及输入变量的显著性进行了评价.刀具寿命管理模块既可以浏览、查询、编辑刀具寿命相关信息,还可以刀具寿命管理文件,向刀具寿命预测和评价模块提供基础数据.     

盘铣刀铣削过程中刀具磨损研究

为实现对盘铣刀铣削转子过程中刀具磨损率预测,达到预测刀具有效加工时间的目的,采用线性回归方法建立了刀具磨损率预测模型,并验证了模型的准确性;基于该模型分析了工艺参数对刀具磨损率的影响规律。研究结果表明：当主轴转速增加时,刀具磨损率逐渐增大;当间歇进给量增加时,刀具磨损率先减小后增大;当加工倍率增加时,刀具磨损率逐渐增加。     

Prediction of tool wear using regression and ANN models in end-milling operation

Tool wear prediction plays an important role in industry for higher productivity and product quality. Flank wear of cutting tools is often selected as the tool life criterion as it determines the diametric accuracy of machining, its stability and reliability. This paper focuses on two different models, namely, regression mathematical and artificial neural network (ANN) models for predicting tool wear. In the present work, flank wear is taken as the response (output) variable measured during milling, while cutting speed, feed and depth of cut are taken as input parameters. The Design of Experiments (DOE) technique is developed for three factors at five levels to conduct experiments. Experiments have been conducted for measuring tool wear based on the DOE technique in a universal milling machine on AISI 1020 steel using a carbide cutter. The experimental values are used in Six Sigma software for finding the coefficients to develop the regression model. The experimentally measured values are also used to train the feed forward back propagation artificial neural network (ANN) for prediction of tool wear. Predicted values of response by both models, i.e. regression and ANN are compared with the experimental values. The predictive neural network model was found to be capable of better predictions of tool flank wear within the trained range.     

COMBINED EFFECTS OF FLANK AND CRATER WEAR ON CUTTING FORCE MODELING IN ORTHOGONAL MACHINING—PART II: BAYESIAN APPROACH-BASED MODEL VALIDATION

Flank and crater wear are the primary tool wear patterns during the progressive tool wear in metal cutting. Cutting forces may increase or decrease, depending on the combined contribution from the flank and/or crater wear. A two-dimensional (2D) slip-line field based analytical model has been proposed to model the force contributions from both the flank and crater wear. To validate the proposed force model, the Bayesian linear regression is implemented with credible intervals to evaluate the force model performance in orthogonal cutting of CK45 steels. In this study, the proposed analytical worn tool force model-based predictions fall well within the 75% credible intervals determined by the Bayesian approach, implying a satisfactory modeling capability of the proposed model. Based on the parametric study using the proposed force model, it is found that cutting forces decrease with the increasing crater wear depth but increase with the increasing flank wear length. Also, the predicted cutting forces are affected noticeably by the friction coefficients along the rake and flank faces and the ratio of crater sticking region to sliding region, and better knowledge of such friction coefficients and ratio is expected to further improve worn tool force modeling accuracy. Compared with the finite element approach, the proposed analytical approach is efficient and easy to extend to three-dimensional worn tool cutting configurations.     

Tool wear monitoring in drilling using force signals

Utilization of force signals to achieve on-line drill wear monitoring is presented in this paper. A series of experiments were conducted to study the effects of tool wear as well as other cutting parameters on the cutting force signals and to establish the relationship between force signals and tool wear as well as other cutting parameters when drilling copper alloy. These experiments involve four independent variables; spindle rotational speed ranging from 600 to 2400 rev min⁻¹, feed rate ranging from 60 to 200 mm min⁻¹, drill diameter ranging from 5 to 10 mm, and average flank wear ranging from 0.1 to 0.9 mm. A statistical analysis provided good correlation between average thrust and drill flank wear. The relationship between cutting force signals and cutting parameters as well as tool wear is then established. The relationship can then be used for on-line drill flank wear monitoring. Feasibility studies show that the use of force signal for on-line drill flank wear monitoring is feasible.     

On-machine tool prediction of flank wear from machined surface images using texture analyses and support vector regression

In this paper, a method for on-machine tool condition monitoring by processing the turned surface images has been proposed. Progressive monitoring of cutting tool condition is inevitable to maintain product quality. Thus, image texture analyses using gray level co-occurrence matrix, Voronoi tessellation and discrete wavelet transform based methods have been applied on turned surface images for extracting eight useful features to describe progressive tool flank wear. Prediction of cutting tool flank wear has also been performed using these eight features as predictors by utilizing linear support vector machine based regression technique with a maximum 4.9% prediction error.     

Modeling of cutting force under the tool flank wear effect in end milling Ti6Al4V with solid carbide tool

This paper presented a study of the relationship between cutting force and tool flank wear of solid carbide tool during the wet end milling Ti6Al4V. The modeling of 3D cutting force in end milling considering tool flank wear was discussed, which showed that for the given cutting conditions, tool geometries, and workpiece material, cutting force under the tool flank wear effect can be predicted easily and conveniently. In addition, the experimental work of end milling Ti6Al4V with solid carbide tool was developed to investigate the relationship between cutting force and tool flank wear, and comparison between experimental results and predicted results was discussed. The results showed that the proposed mathematical model can help to predict 3D cutting force under the tool flank wear effect with high accuracy.     

基于后刀面磨损的铣削加工误差研究

对铣削加工过程中后刀面磨损对加工精度的影响进行了分析和研究,建立了基于刀具后刀面磨损的铣削加工误差的数学模型。     

Tool wear estimation in machining based on the flank wear inclination angle changes using the FE method

Abstract

In this study, a FEM-based tool wear approach with a focus on the geometry of the worn tool, especially the changes of flank wear land inclination angle, was developed. The relationship between the variables of the wear rate equation and the average nodal temperature on the flank wear land through integrating FE-simulations of the cutting process and Response Surface Methodology (RSM) was determined in order to define the temperature as a function of wear rate model parameters. Then, that data was used to calibrate the wear rate equation which was obtained by establishing the relationship between the Usui wear rate equation and the geometry of the worn tool, using a MATLAB program. This approach was validated by comparing the predicted flank wear rates and experimental measurements. The estimated flank wear shows some improvement compare to the model with a constant inclination angle.     

Notch wear detection in cutting tools using gradient approach and polynomial fitting

Cutting tool wear is well known to affect the surface finish of a turned part. Various machine vision methods have been developed in the past to measure and quantify tool wear. The two most widely measured parameters in tool wear monitoring are flank wear and crater wear. Works carried out by several researchers recently have shown that notch wear has a more severe effect on the surface roughness compared to flank or crater wear. In this work, a novel gradient detection approach has been developed to detect the presence of micro-scale notches in the nose area of the cutting tool. This method is capable of detecting the location of the notch accurately from a single worn cutting tool image.     

Online tool condition monitoring in turning titanium (grade 5) using acoustic emission: modeling

This paper presents an online prediction of tool wear using acoustic emission (AE) in turning titanium (grade 5) with PVD-coated carbide tools. In the present work, the root mean square value of AE at the chip–tool contact was used to detect the progression of flank wear in carbide tools. In particular, the effect of cutting speed, feed, and depth of cut on tool wear has been investigated. The flank surface of the cutting tools used for machining tests was analyzed using energy-dispersive X-ray spectroscopy technique to determine the nature of wear. A mathematical model for the prediction of AE signal was developed using process parameters such as speed, feed, and depth of cut along with the progressive flank wear. A confirmation test was also conducted in order to verify the correctness of the model. Experimental results have shown that the AE signal in turning titanium alloy can be predicted with a reasonable accuracy within the range of process parameters considered in this study.     

Development of a tool wear observer model for online tool condition monitoring and control in machining nickel-based alloys

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.