Effective training data selection in tool condition monitoring system

When neural networks (NNs) are used to identify tool conditions, the richness and size of training data are crucial. The training data set not only has to cover a wide range of cutting conditions, but also to capture the characteristics of the tool wear process. This data set imposes significant computing burdens, results in a complex identification model, and hampers the feasible application of NNs. In this paper, a training data selection method is proposed, and a systematic procedure is provided to perform this data selection. With this method, the generalization error surface is divided into three regions, and proper sampling factors are chosen for each region to prune the data points from the original training set. The quality of the training set is estimated by performance evaluation through decision making. In this work, SVM is used in the decision making method, and the generalization error is used as the performance evaluation criterion. The tradeoff between the generalization performance and the size of the training set is key to this selection. Experimental results have demonstrated that this selection strategy provides an effective and efficient training set, and the developed model based on this set is fast and reliable for tool condition identification.     

Development of a tool wear-monitoring system for hard turning

This paper describes an in-depth study on the development of a system for monitoring tool wear in hard turning. Hard turning is used in the manufacturing industry as an economic alternative to grinding, but the reliability of hard turning processes is often unpredictable. One of the main factors affecting the reliability of hard turning is tool wear. Conventional wear-monitoring systems for turning operations cannot be used for monitoring tools used in hard turning because a conglomeration of phenomena, such as chip formation, tool wear and surface finish during hard turning, exhibits unique behavior not found in regular turning operations. In this study, various aspects associated with hard turning were investigated with the aim of designing an accurate tool wear-monitoring system for hard turning. The findings of the investigation showed that the best method to monitor tool wear during hard turning would be by means of force-based monitoring with an Artificial Intelligence (AI) model. The novel formulation of the proposed AI model enables it to provide an accurate solution for monitoring crater and flank wear during hard turning. The suggested wear-monitoring system is simple and flexible enough for online implementation, which will allow more reliable hard turning in industry.     

A mixed-integer linear programming model for part mix, tool allocation, and process plan selection in CNC machining centres

A mixed-integer linear programming model is developed for the simultaneous determination of part mix, tool allocation and process plan selection in CNC machining centres. Illustration of the use of the model in a hypothetical example and its application to a real problem arising in deep seabed operations demonstrate the utility of the model as one more step towards the integration of computer-aided process planning (CAPP) tasks in CNC machining enviroments.     

Sensorless tool failure monitoring system for drilling machines

It is well known that on-line tool condition monitoring has great significance in modern manufacturing processes. In order to prevent possible damages to the workpiece or the machine tool, reliable techniques are required providing an on-line response to an unexpected tool failure. Drilling is one of the most fundamental machining operations and two of the most crucial issues related to it are tool wear and fracture. During the spindle process, the motor driver current is related to the drill condition: power consumption is higher for a worn drill in comparison to a sharp drill for the same process. This difference in power consumption can be self-correlated to obtain the resulting waveform variance to provide a merit figure for tool condition. This paper describes a driver current signal analysis to estimate the tool condition by using the discrete Wavelet Transform in order to extract the information from the original cutting force, and through an autocorrelation algorithm evaluate the tool wear in the form of an asymmetry weighting function. The current is monitored from the motor driver to give a sensorless approach. Experimental results are presented to show the algorithm performance, a complete sensorless tool failure system which allows the detection of tool failure as a function of spindle current in real time.     

Fuzzy similarity-based rough set method for case-based reasoning and its application in tool selection

Case-based reasoning (CBR) embodied in die and mold NC machining will extend the application of knowledge-based system by utilizing previous cases and experience. However, redundant features may not only dramatically increase the case memory, but also make the case retrieval algorithm more complicated. Additionally, traditional methods of feature weighting limit the development of CBR methodology. This paper presents a novel methodology to apply fuzzy similarity-based Rough Set algorithm in feature weighting and reduction for CBR system. The algorithm is used in tool selection for die and mold NC machining. The proposed method does not need to discretize continuous or real-valued features included in cases, from which can effectively reduce information loss. The weight of feature a_i is computed based on the difference of its dependency defined as γ_A−γ_A−{ai}, which also represents the significance of the corresponding feature. If the difference is equal to 0, the feature is considered to be redundant and should be removed. Finally, a case study is also implemented to prove the proposed method.     

High-speed machining of titanium alloys using the driven rotary tool

Machining of titanium at high cutting speeds such as from 4 m/s to 8 m/s is very challenging. In this paper, a new generation of driven rotary lathe tool was developed for high-speed machining of a titanium alloy, Ti–6Al–4V. The rotary tool was designed and fabricated based on the requirements of compact structure, sufficient stiffness and minimal edge runout. Cylindrical turning experiments were conducted using the driven rotary tool (DRT) and a stationary cutting tool with the same insert, for comparison in the high-speed machining of Ti–6Al–4V. The results showed that the DRT can significantly increase tool life. Increase in tool life of more than 60 times was achieved under certain conditions. The effects of the rotational speed of the insert were also investigated experimentally. Cutting forces were found to decline slightly with increase of the rotational speed. Tool wear appears to increase with the rotational speed in a certain speed range.     

Real-time tool wear monitoring in milling using a cutting condition independent method

This paper describes a new method to monitor end milling tool wear in real-time by tracking force model coefficients during the cutting process. The behavior of these coefficients are shown to be independent from the cutting conditions and correlated with the wear state of the cutting tool. The tangential and radial force model coefficients are normalized and combined into a single parameter for wear monitoring. A number of experiments with different workpiece materials are run to investigate the feasibility of tool wear monitoring using this method. We show that this method can be used in real-time to track tool wear and detect the transition point from the gradual wear region to the failure region in which the rate of wear accelerates.     

Measurement of milling tool vibrations during cutting using laser vibrometry

Spindle and tool vibration measurements are of great importance in both the development and monitoring of high-speed milling. Measurements of cutting forces and vibrations on the stationary spindle head is the most used technique today. But since the milling results depend on the relative movement between the workpiece and the tool, it is desirable to measure on the rotating tool as close to the cutters as possible. In this paper the use of laser vibrometry (LDV) for milling tool vibration measurements during cutting is demonstrated. However, laser vibrometry measurements on rotating surfaces are not in general straight forward. Crosstalk between vibration velocity components and harmonic speckle noise generated from the repeating revolution of the surface topography are problems that must be considered. In order to overcome the mentioned issues, a cylindrical casing with a highly optically smooth surface was manufactured and mounted on the tool to be measured. The spindle vibrations, radial tool misalignment, and out-of-roundness of the measured surface were filtered out from the signal; hence, the vibrations of the cutting tool were resolved. Simultaneous measurements of cutting forces and spindle head vibrations were performed and comparisons between the signals were conducted. The results showed that vibration velocities or displacements of the tool can be obtained with high temporal resolution during cutting load and therefore the approach is proven to be feasible for analysing high-frequency milling tool vibrations.     

Five-axis tool orientation smoothing using quaternion interpolation algorithm

In five-axis machining, abrupt changes of tool axes may deteriorate the part surface, hence smoothing of tool orientations becomes an important issue. In the present tool path generation procedure, the tool orientation smoothing method (TOS method) is coupled with the cutting error improvement method (CEI method). TOS method is used to smooth tool orientations in order to reduce cutting errors and increase the machining efficiency. CEI method modifies existing cutter location data (CL data) so that final cutting errors are kept within the required tolerance. Experimental results show that the tool paths generated by the present procedure have better machining efficiency, better surface quality, and no interferences between the tool and part surfaces.     

基于多决策属性的刀具选择规则提取算法研究

传统的规则提取算法只是对单一的条件属性特征推理单一的决策属性值进行规则提取,为实现刀具智能选择,本文提出了一种通过加工特征和工件尺寸对刀具进行选择的规则提取算法,采用粗糙集进行刀具型号的规则提取,对刀具尺寸的选择采用区间值的基本理论,最后通过一个实例验证该算法的有效性。     

Monitoring of tool fracture in end milling using induction motor current

This paper describes the use of induction motor current to monitor tool fracture in end milling operations. The principles of induction motors are studied in this paper to establish the relationship between the motor current and the motor torque. It is shown that the square of the stator current of induction motors is approximately proportional to the motor torque. Since the occurrence of tool fracture will cause variations in the motor torque, measurement of the stator current appears to be an indirect technique for monitoring tool fracture. A sensitivity analysis of the stator current to the occurrence of tool fracture is also reported. Finally, experimental results under varying cutting conditions have been presented to demonstrate the effectiveness of this approach for the detection of tool fracture in end milling operations.     

直齿圆锥齿轮精密锻造工艺及模具设计

针对直齿圆锥齿轮精锻成形中齿形充填不满及成形力过大导致模具损伤等问题,制定了中心分流法精锻直齿圆锥齿轮的工艺方案.以工艺方案和数值模拟结果为依据,设计了预锻分流区和分流终锻两套模具,并对精锻模具的模膛和结构设计要点进行了阐述.     

基于Web Service的刀具配送系统研究与实现

针对传统刀具管理系统存在的不足,提出了一种新的基于Web Service刀具配送系统,对系统的集成技术进行了研究,在此基础上完成了系统的设计,并成功实施。     

Blanking tool wear modeling using the finite element method

One of the main objectives of the numerical process design in metal forming is to develop adequate tool design and establish process parameter in order to increase tool life and to improve part quality and complexity while reducing manufacturing cost. The prediction of tool wear in sheet metal blanking/punching processes is investigated in this paper using the finite element method. A wear prediction model has been implemented in a finite element code in which the tool wear is a function of the normal pressure and some material parameters. A damage model is used in order to describe crack initiation and propagation into the sheet. The distribution of the tool wear on the tool profile is obtained and compared to industrial observations. Furthermore, a numerical investigation has been carried out to study the effect of tool wear on the burr formation.     

伺服刀架系统的反复反馈误差补偿控制

对于具有滞后特性的伺服刀架系统,采用自校正ＰＩＤ控制。在此基础上,为进一步提高伺服刀架系统的跟踪精度,提出了反复反馈误差补偿控制方法。理论分析和实验结果都表明,该控制方法以有效地提高伺服刀架的跟踪精度。     

机床主轴电机的选择研究

电主轴是机床的核心部件,本文就主轴电机的选择,从使用要求、控制要求和经济性要求等方面对各类电机进行了分析比较,结合相应调速系统的对比,选择出适合机床主轴用执行电机的类型和调速系统。     

Subshoulder formation during friction stir welding of steel using tungsten alloy tool

Abstract

A study was carried out on the friction stir welding of low alloy steel plates, to understand the influence of the tool profile on the tool wear rate, using a tungsten alloy tool. Three tool profiles were used for the wear study, namely, tool A with a concave shoulder and tapered pin of 2·8 mm, tool B with a flat shoulder and tapered pin of 2·6 mm and tool C with a concave shoulder and tapered pin of 2·6 mm. The tool wear characteristic was analysed by three methods, namely, the profile projector, weight loss and the image processing technique, and it was found that tool C gave reduced tool wear, when compared to the other tool profiles. In tool C, an impression of a step-like formation was generated automatically in the pin during welding and named as a subshoulder, which proved to be the optimised design.     

基于知识的电子装配CAPP技术研究

在对电子装配工艺设计过程中用到的知识进行分析的基础上,建立了知识的对象模型,采用对象类与产生式规则相结合的方法表示电子装配工艺设计知识,从而搭建出一个完全开放且面向对象的电子装配CAPP知识管理系统.