基于多传感器数据融合的刀具磨损状态监测研究

刀具磨损状态是影响加工质量和生产效率的重要因素之一,传感器、特征提取、信息融合和机器学习等技术的发展为刀具状态监测提供了新思路,然而,建立精度高、鲁棒性好的多传感器系统仍是刀具状态检测的难点。以涂层硬质合金刀具对难加工材料30CrMnMoRE的铣削试验为基础,通过对不同刀具磨损状态下的切削力和切削振动进行采集分析,并比较多种特征提取和模式识别方法,建立了一种更为可靠的铣刀状态监测系统,实现了对高强度钢切削时的刀具磨损状态识别。     

变参数铣削刀具磨损状态监测研究

针对切削力旧有时域特征易受切削参数变动影响而不适用于变参数铣削刀具磨损状态监测的缺陷,采用了一组新的无量纲切削力时域特征(归一化切削力指标NCF、变异系数Cv和峰值力比MFR)。并以难加工材料TC4钛合金变参数铣削实验来验证新特征在变参数铣削刀具磨损状态监测上的有效性,分别以新旧特征作为SVM分类器的输入,分析和比较结果表明本文提出的无量纲切削力时域特征对切削参数变化不敏感,而仅对刀具磨损状态变化敏感,因此能够实现变参数铣削刀具磨损状态监测。     

基于特征自适应融合和集成学习的高性能铣削刀具状态监测

通过人工智能、工业大数据实时感知切削加工中的刀具状态是实现面向性能的制造的重要技术途径,也是高性能制造的关键内涵。然而,在目前的切削刀具状态监测算法中,特征提取过程多依赖于人工经验,这无疑限制了刀具状态监测技术的在高性能制造中的推广应用。因此,针对高性能加工监测中的自主性和准确性要求,基于特征自适应融合和集成学习技术,提了出一种面向高性能铣削的刀具磨损监测方法。所提出的监测方法能够根据特征的表现自动为其赋予不同的权重从而实现特征的自适应融合,同时利用AdaBoost集成学习算法,在自动融合特征的同时保证了状态监测精度。薄壁件铣削实验表明,监测结果与真实磨损间的RMSE和MAE值最大为10.44,最小可达5.16。所提出的方法能够自主、准确地监测航空类薄壁件铣削加工中的刀具磨损状态,解决了高性能铣削加工刀具磨损监测中的人工经验依赖问题。     

基于铣削噪声的刀具状态监测研究

建立了基于铣削噪声的刀具状态监控系统,以研究铣削过程中不同主轴转速、进给速率对刀具磨损状态的影响。试验表明,在2kHz~3kHz频率范围内,切削噪声与刀具磨损有着很好的相关性。在给定加工条件下,该系统能有效识别和预测刀具磨损状态。     

刀具磨损的机器视觉监测研究

为提高铣削加工时的刀具利用率、降低刀具成本,提出采用机器视觉技术在机监测铣刀磨损状态,及时更换刀具。建立刀具磨损监测系统,由电荷耦合器件(Charge coupled device,CCD)相机获取刀具磨损图像,通过图像预处理、阈值分割、基于Canny算子和亚像素的边缘检测方法建立刀具磨损边界,提取刀具磨损量。开展GH4169镍基高温合金铣削实验,将监测系统检测的磨损量与超景深显微镜的测量结果进行比对,结果表明:该系统具有较高的检测精度,可实现铣削加工时刀具磨损状态的在机监测。     

考虑电流和振动的涂层铣刀磨损规律实验研究

随着切削技术向着高速、高效和干式加工等方向发展,刀具涂层和切削状态监测技术成为影响切削技术发展的主要因素,研究刀具涂层以及刀具磨损引起的切削状态改变对促进制造业发展具有重要意义。利用铣削实验得到了相同切削条件下,不同涂层的3把硬质合金刀具的加工磨损情况。通过分析各个刀具磨损过程中铣削力信号、主轴电流信号以及切削振动信号的变化,得到了无涂层、Ti Al N涂层以及Al Ti N涂层刀具在切削过程中表现出的磨损规律。结果表明:Al Ti N涂层的耐磨性能更好,3把刀具的主轴电流有效值和切削振动信号质心频率的变化均有效反映了刀具磨损情况。在立铣加工过程中,可以将上述两种特征值用于刀具磨损实时在线监测。     

基于铣削力参数化模型的铣刀非均匀磨损状态监测方法研究

在航空结构件钛合金零件数控加工中,刀具非均匀磨损状态对工件的最终质量影响很大。为了及时发现并控制因刀具非均匀磨损导致的异常加工状态,对钛合金加工刀具非均匀磨损状态监测方法进行了研究。建立了基于刀具刃线参数化模型的铣削力参数化模型,实现了对钛合金加工刀具非均匀磨损状态的监测,解决了零件单件或首件加工中样本数据缺失条件下的钛合金加工刀具非均匀磨损状态准确监测难题。     

多传感器融合下多工况刀具磨损状态预测的深度森林方法研究

准确监测加工过程刀具磨损状态有助于避免因刀具失效导致的产品质量问题。 建立不同工况的刀具磨损监测模型,往 往需要对每组工况调参以保证精度。 为减少调参并保证预测精度,结合深度森林的超参数少、参数对模型不敏感和训练过程自 适应等优点,利用深度森林建立了多传感器信号及多工况下自主特征选择的刀具磨损状态预测模型。 基于 3 组不同工艺参数 下 TC18 铣削过程的多传感器及磨损数据,以及预测与健康管理(PHM)学会 2010 年高速数控机床刀具健康预测竞赛的开放数 据,深度森林在 3 组工况的预测精度分别为 95. 35% 、96. 63% 和 97. 06% ,在 PHM 数据上为 98. 95% ,验证了深度森林对多工况 下刀具磨损预测的高精度和适用性,为在线监测技术提供了有力的指导。     

基于故障数据库的高速铣削诊断的研究

通过对高速铣削过程中各种铣刀状态下采集的振动信号进行时域、频域分析,对比不同磨损程度刀具的振动信号,找出与刀具状态对应的信号特征。基于LabVIEW平台,开发出在线分析监测系统。由于铣削加工过程的复杂性以及监测系统中得到的特征数据结构复杂、种类繁多,因此将数据库技术应用于在线监测系统中,从而实现对监测系统中数据有效集中管理,提高系统的即时反应速度和运行效率,实现对刀具状态的准确判断。     

基于小波包和BP神经网络的刀具磨损状态识别

刀具磨损状态影响金属切削过程,因此监测刀具磨损状态对提高产品质量有着重要的意义。设计刀具磨损状态监测系统,利用传感器采集刀具振动信号,通过小波包对振动信号进行数据分析,并把不同频段的能量值作为刀具磨损状态的特征值,建立BP神经网络,从而在刀具磨损状态和振动信号特征向量之间建立映射关系,完成刀具磨损状态的监测。利用C++Builder和Matlab软件混合编程实现了系统的功能。试验表明,系统运行良好,能够对刀具磨损状态进行正确识别。     

基于80C196KC的刀具磨损监控系统

以异形螺杆包络铣削加工中的铣刀磨损监测系统算设计为前提，介绍了利用80C196KC为主控芯片的监测系统，同时阐述了系统设计中的关键技术与硬软件工作原理。     

高速切削刀具的发展现状

对国内外高速切削刀具的发展现状进行了综合评述 ,重点介绍了高速切削刀具材料和高速切削刀具技术 (包括刀具动平衡技术、刀柄系统、刀具安全性、可转位面铣刀结构、刀具监测技术等 )的开发及应用     

立铣加工刀具状态监控技术评述

综述了立铣加工刀具状态监控技术的研究现状.刀具状态监控技术在工业上的应用涉及到两种关键系统:一是具有不同智能水平的各种传感器系统,另一个是能把机床控制器所用的控制信号综合成能发觉刀具破损和反映刀具磨损程度信号的过程监控系统.这两种系统相结合,就能实现刀具状态监控系统在工业加工环境的应用.     

Rapid Sheet Metal Manufacturing. Part 1: Indirect Rapid Tooling

Rapid sheet metal manufacturing (RSMM) is a closed loop process for making sheet metal products which uses advanced computer-aided techniques and computer-controlled machines to produce non-ferrous tooling directly or indirectly. The tooling would be suitable for short-run production or design evaluation of sheet metal products for which prototyping cost and lead time are greatly reduced. The key aspect of this closed-loop process is the method used to fabricate and modify the sheet metal forming tool. Various approaches are adopted in the preparation of the tooling for onward embossing on a sheet metal. The three indirect approaches use selective laser sintering (SLS), stereolithography (SLA), and high-speed computer numerical controlled (CNC) milling to build the masters from computer data models. The masters are used in the vacuum casting process to generate the non-ferrous tooling. Comparisons on quality, lead time and cost are presented.     

天线调平垫板铣面工装的设计

对天线调平垫板的铣面工序进行了分析,在此基础上,设计了天线调平垫板铣面工装。介绍了工装的结构,以及应用工装进行天线调平垫板铣面的具体方法。这一工装结构简单,操作方便,定位准确,可以提高天线调平垫板的加工效率。     

Three-Dimensional Tool Compensation for a Three-Axis Turning Centre

Modern CNC turning centres are often equipped with powered tooling to enable radial or axial drilling, tapping or milling operations. If the machine tool is equipped with a fully controlled C-(spindle) axis the prospect of more complex milling operations becomes evident. However, for such operations, the requirements for tool compensation limit the work which can be achieved. This paper details an algorithm for 3D tool compensation when using a spherical end milling cutter as a radial tool in such a turning centre.     

基于主轴电流的铣削力间接监测方法

实时准确地监测铣削状态对于提高加工质量与加工效率具有重要意义,切削力作为重要的加工状态监测对象,因其监测设备昂贵且安装不便而受到限制,为此提出一种考虑刀具磨损的基于主轴电流的铣削力监测方法.首先基于切削微元理论建立了考虑后刀面磨损的铣削力模型,并通过铣削实验进行铣削力模型系数标定;然后对主轴电流与铣削力的关系进行理论建...     

Self-Learning Algorithm for Automated Design of Condition Monitoring Systems for Milling Operations

This paper investigates an approach, termed self-learning ASPS (automated sensor and signal processing selection), aimed at aiding the systematic design of condition monitoring systems for machining operations. The paper outlines a self-learning methodology for the classification of the system’s normal and faulty states and the selection of the most appropriate sensors and signal processing methods for detecting machining faults in end milling. The aim of the proposed approach is to enable the condition monitoring designer to use previous system faults or incidents to design an on-line monitoring system, reducing the system’s development time and cost. Force, acceleration and acoustic emission signals are used to design the condition monitoring systems for end milling operations. Gradual tool wear, catastrophic cutter breakage and tool collision are used for evaluating the proposed self-learning ASPS approach. The initial results show that the suggested algorithm can be applied for an automated, self-learning monitoring system for the selection of the most sensitive sensors and signal processing methods for machining faults and conditions.       

An approach to the evaluation of multivariate data during ball end milling free-form surface fragments

We present a method for investigating the process of ball end milling, a technology widely used in tool making and moulding. We analyse the main features of free-form surfaces used in this technology, and propose a sequence of steps to identify the most suitable milling strategy. The basic idea of such a sequence lies in the definition of the tangible fragments of free-form surfaces applicable to tool making. Tangible fragments represent the parts of tooling and signed radii that can distinguish both the active and transitional surfaces of tooling. Free-form surface fragments were selected since they are capable of securing definiteness in measurement of roughness parameters and surface errors. We investigated the operation capability of solid ball end milling cutters in terms of cutting tool edge micro-geometry. Cutting edge radius (r_n) and roughness parameters of the tool edge were measured to determine the relationship between new and worn tool edges. Roughness parameters were measured at different parts of the machined surfaces, which take on typical features of dies and moulds, such as inclined wall, ridge lines, valley lines, as well as, the active surfaces defined by signed radii. Surface error such as scallop height, gouging, tolerances and actual signed radii were measured at transitive surfaces. The traditional approach of evaluating roughness parameters was used to determine the suitability of factors such as milling operation, milling strategy and direction of milling. In addition, traditional approaches such as relationships, distributions and histograms were also used. We applied Khattree–Naik’s plot, which proves its suitability to visualise all the data being measured in the same units: microns and millimetres. Characteristic features of the ball end milling process, such as tool edge micro-geometry, geometry of the machined surface, and unit length of the transitive surface were applied in Khattree–Naik’s plots. We found that this plot was capable of processing multivariate data to distinguish specific markers of the quality of machined surfaces, which are produced in ball end milling.     

小型船舶轴系法兰铣孔工装的改进

在分析现有小型船舶轴系法兰铣孔工装存在主要问题的基础上,对铣孔工装进行针性地改进,并应用在实际生产过程中,提高了工作效率和降低劳动难度,同时满足了产品各项技术要求.