An epitrochoidal pocket—A new canned cycle for CNC milling machines

A machining strategy for milling a particular set of pockets with epitrochoidal boundary is proposed. The method is suitable to be integrated into the controller of a CNC milling machine and is particularly useful for machining chambers of rotary internal combustion engines (Wankel), rotary piston pumps and generally epitrochoidal-shaped housings. Motion generation is achieved by an algorithm which utilizes real-time CNC interpolation providing the highest possible accuracy, of which the milling machine is capable. The surface quality is controlled by applying roughing and finishing passes. The whole machining task can be programmed in a single block of the part program. Finally, the effectiveness of the proposed method is verified by simulation tests of the generated tool path.     

A CNC machine tool interpolator for surfaces of cross-sectional design

A machining strategy for milling a particular set of surfaces, obtained by the technique of cross-sectional design is proposed. The surfaces considered are formed by sliding a Bezier curve (profile curve) along another Bezier curve (trajectory curve). The curves are located in perpendicular planes. The method employs a three-axis CNC milling machine equipped with suitable ball-end cutter and is based on the locus-tracing concept. The algorithm described, utilizes a real-time CNC interpolator providing the highest possible accuracy, of which the milling machine is capable. The surface quality is controlled by keeping the distance between scallops within a programmed value. Finally, the whole machining task can be programmed in a single block of the part program.     

进化神经网络在机床工具损耗预测中的应用

设计了一个基于实数编码的改进进化算法优化神经网络的连接权和网络结构.该算法 可以根据种群停止进化代数自适应调节变异率、根据个体适应度调节变异量.加工实验表明采用 进化神经网络可以较准确预测出电火花铣削加工工具损耗,所提出的进化算法是有效的,预测结 果较标准BP神经网络高.该预测模型为电火花铣削加工工具在线自动补偿打下基础.     

Dimensional and geometrical errors of three-axis CNC milling machines in a virtual machining system

Virtual machining systems are applying computers and different types of software in manufacturing and production in order to simulate and model errors of real environment in virtual reality systems. Many errors of CNC machine tools have an effect on the accuracy and repeatability of part manufacturing. Some of these errors can be reduced by controlling the machining process and environmental parameters. However geometrical errors which have a big portion of total error need more attention. In this paper a virtual machining system which simulates the dimensional and geometrical errors of real three-axis milling machining operations is described. The system can read the machining codes of parts and enforce 21 errors associated with linear and rotational motion axes in order to generate new codes to represent the actual machining operation. In order to validate the system free form profiles and surfaces of virtual and real machined parts are compared in order to present the reliability and accuracy of the software.     

Algorithms for selecting cutters in multi-part milling problems

This paper describes geometric algorithms for automatically selecting an optimal sequence of cutters for machining a set of 2.5-D parts. In milling operations, cutter size affects the machining time significantly. Meanwhile, if the batch size is small, it is also important to shorten the time spent on loading tools into the tool magazine and establishing z-length compensation values. Therefore, in small-batch manufacturing, if we can select a set of milling tools that will produce good machining time on more than one type of parts, then several unnecessary machine-tool reconfiguration operations can be eliminated. In selecting milling cutters we consider both the tool loading time and the machining time and generate solutions that allow us to minimize the total machining time. In this paper we first present algorithms for finding the area that can be cut by a given cutter. Then we describe a graph search formulation for the tool selection problem. Finally, the optimal sequence of cutters is selected by using Dijkstra's shortest path planning algorithm.     

Towards efficient 5-axis flank CNC machining of free-form surfaces via fitting envelopes of surfaces of revolution

We introduce a new method that approximates free-form surfaces by envelopes of one-parameter motions of surfaces of revolution. In the context of 5-axis computer numerically controlled (CNC) machining, we propose a flank machining methodology which is a preferable scallop-free scenario when the milling tool and the machined free-form surface meet tangentially along a smooth curve. We seek both an optimal shape of the milling tool as well as its optimal path in 3D space and propose an optimization based framework where these entities are the unknowns. We propose two initialization strategies where the first one requires a user’s intervention only by setting the initial position of the milling tool while the second one enables to prescribe a preferable tool-path. We present several examples showing that the proposed method recovers exact envelopes, including semi-envelopes and incomplete data, and for general free-form objects it detects envelope sub-patches.     

High speed pocket milling planning by feature-based machining area partitioning

Pocket milling operations are involved in two and a half-dimensional (2.5D) machining. The machining area of a pocket has to be divided into several sub machining regions (SMRs) to effectively select the machining parameters for ordinary or high speed milling. A SMR of a pocket has its own characteristic geometry, which implicitly provides machining features used for the generation of strategies for high speed machining. This paper presents a methodology to partition a pocket machining area, as well as to identify machining features used for planning of high speed pocket machining. To generate the machining strategy, the attributes of machining features are defined, and evaluated through a machining volume slicing method. SMR-based partitioning rules are developed based on the geometric features of a pocket. The proposed partitioning algorithm is applied to both simple and complex shaped pockets. A case pocket volume is divided into several SMRs, represented by a tree structure containing associated information for pocket milling planning.     

A comprehensive adaptive approach to calculating the envelope surface of the digital models in CNC machining

The digital models are the fundamental elements used in the virtual simulation of CNC machining for process planning, result prediction, analysis, etc. The essential work to build the digital models of machined parts is the calculation of the envelope surface generated by moving a cutter surface relative to workpieces. This calculation is usually complicated, and the requirements in different cases are also varied. Hence, it is very beneficial to develop an effective approach for different requirements. In this work, a comprehensive envelope approach is established, and it adaptively choose 1) the elimination parameter among two cutter surface parameters, 2) the representation form of envelope surface, and 3) the discretization way, so it is robust to satisfy different requirements. The elimination parameter and representation form are adaptively chosen to improve the calculation efficiency by obtaining the closed-form representation of the envelope surface prior to the implicit one. The discretization way is further adaptively chosen to obtain approximately even point distribution to the applications of 3D and FEA modeling. Finally, comprehensive algorithms are proposed to effectively implement this adaptive envelope approach for different applications. The examples are given to the manufacturing of spiral bevel gears and five-axis CNC milling.     

Automated surface subdivision and tool path generation for -axis CNC machining of sculptured parts

As an innovative and cost-effective method for carrying out multiple-axis CNC machining, -axis CNC machining technique adds an automatic indexing/rotary table with two additional discrete rotations to a regular 3-axis CNC machine, to improve its ability and efficiency for machining complex sculptured parts. In this work, a new tool path generation method to automatically subdivide a complex sculptured surface into a number of easy-to-machine surface patches; identify the favorable machining set-up/orientation for each patch; and generate effective 3-axis CNC tool paths for each patch is introduced. The method and its advantages are illustrated using an example of sculptured surface machining. The work contributes to automated multiple-axis CNC tool path generation for sculptured part machining and forms a foundation for further research.     

Feature-based rule induction in machining operation using rough set theory for quality assurance

There have been many studies, mainly by the use of statistical modeling techniques, as to predicting quality characteristics in machining operations where a large number of process variables need to be considered. In conventional metal removal processes, however, an exact prediction of surface roughness is not possible or very difficult to achieve, due to the stochastic nature of machining processes. In this paper, a novel approach is proposed to solve the quality assurance problem in predicting the acceptance of computer numerical control (CNC) machined parts, rather than focusing on the prediction of precise surface roughness values. One of the data mining techniques, called rough set theory, is applied to derive rules for the process variables that contribute to the surface roughness. The proposed rule-composing algorithm and rule-validation procedure have been tested with the historical data the company has collected over the years. The results indicate a higher accuracy over the statistical approaches in terms of predicting acceptance level of surface roughness.     

数控加工中加工误差预测模型的研究

提出了一个在球头端铣加工中预测复杂曲面加工误差的理论模型.在理论模型的基础上,计算出了曲面各个部分的由刀具变形引起的加工误差.对影响加工误差的诸如切削模式、铣削位置角、曲面几何形状等各种切削状况进行了研究.最后,使用加工中心,在各种加工状况下.通过一系列实验对理论模型进行了验证.并利用计算机图形学工具对二者进行了建模仿真,结果显示理论值与实验值非常吻合.恰好证明了趣论模型在预测表面加工误差方面的适应性非常好.     

可微分抽象机混合编程系统

自动化编程是智能软件的核心挑战之一,使用程序执行轨迹或输入输出样例学习程序,是自动化编程的典型研究方法.这些方法无法弥合常规程序元素与神经网络组件间的隔阂,不能吸收经验信息输入、缺乏编程控制能力.给出了一种可无缝结合高级编程语言与神经网络组件的混合编程模型：使用高级编程语言元素和神经网络组件元素混合开发应用程序,其中,编程语言描述程序的框架、提供经验信息,关键复杂部分则用未定、可学习的神经网络组件占位,应用程序在可微分抽象机上运行生成程序的连续可微分计算图表示,然后使用输入输出数据,通过可微分优化方法对计算图进行训练,学习程序的未定部分,自动生成完整的确定性程序.可微分抽象机混合编程模型给出了一种能够将编程经验与神经网络自学习相结合的程序自动生成方法,弥合编程语言元素与神经网络元素间的隔阂,发挥并整合高级过程化编程和神经网络可训练学习编程各自的优势,将复杂的细节交给神经网络未定部分自动生成,降低编程难度或工作量,而适当的经验输入又有助于未定部分的学习,同时,为复用长期积累的宝贵编程经验提供输入接口.     

三维工序模型切削载荷动态变化的工艺优化策略

综合零件的加工特征及约束条件并引入布尔差运算,可以分解出零件典型面组并 生成对应的工艺路线谱系,达到零件加工工艺快速优化设计的目的。通过分析三维工序模型典 型面组加工时的动态特性,采用B 样条曲线插值参数化的方法构建刀具-工件接触区域动态边界 的统一数学模型,预测切削载荷动态变化状况,并进行切削参数优化达到有效控制切削载荷的 目的。最后以某零件的车削加工为例进行分析,验证该工艺优化策略的可行性。     

Research on multi-signal milling tool wear prediction method based on GAF-ResNext

A key aspect impacting the quality and efficiency of machining is the degree of tool wear. If the tool failure is not discovered in time, the quality of workpiece processing decreases, and even the machine tool itself may be harmed. To increase machining quality, efficiency and facilitate the intelligent advancement of the manufacturing industry, tool wear prediction is crucial. This research offers a multi-signal tool wear prediction method based on the Gramian angular field (GAF) and depth aggregation residual transform neural network (ResNext), enabling fast and accurate tool wear prediction. Specifically, the required one-dimensional signal is obtained through preprocessing including intercepting, splicing and wavelet threshold denoising of the force and vibration signals, and GAF is used to encode the obtained one-dimensional signal to generate a (224 × 224) data matrix. ResNext automatically extracts the features of the data matrix, establish the relationship between features and tool wear, and creates a tool wear prediction model based on GAF-ResNext. The ability of this method to predict tool wear has been trained and tested by milling experimental data. The experimental findings demonstrate the real-time, accuracy, dependability and universality of this method. This method has a better effect when compared to other research methods. The study's findings can boost machining productivity and offer technical support for intelligent tool wear early warning and intelligent manufacturing.     

The evolutionary development of roughness prediction models

The vigorous expansion of wind energy power generation over the last decade has also entailed innovative improvements to surface roughness prediction models applied to high-torque milling operations. Artificial neural networks are the most widely used soft computing technique for the development of these prediction models. In this paper, we concentrate on the initial data transformation and its effect on the prediction of surface roughness in high-torque face milling operations. An extensive data set is generated from experiments performed under industrial conditions. The data set includes a very broad set of different parameters that influence surface roughness: cutting tool properties, machining parameters and cutting phenomena. Some of these parameters may potentially be related to the others or may only have a minor influence on the prediction model. Moreover, depending on the number of available records, the machine learning models may or may not be capable of modelling some of the underlying dependencies. Hence, the need to select an appropriate number of input signals and their matching prediction model configuration.A hybrid algorithm that combines a genetic algorithm with neural networks is proposed in this paper, in order to address the selection of relevant parameters and their appropriate transformation. The algorithm has been tested in a number of experiments performed under workshop conditions with data sets of different sizes to investigate the impact of available data on the selection of corresponding data transformation. Data set size has a direct influence on the accuracy of the prediction models for roughness modelling, but also on the use of individual parameters and transformed features. The results of the tests show significant improvements in the quality of prediction models constructed in this way. These improvements are evident when these models are compared with standard multilayer perceptrons trained with all the parameters and with data reduced through standard Principal Component Analysis practice.     

微细电火花铣削加工CAD/CAM系统实现

基于分层扫描微细电火花铣削加工的基本思想和电极补偿策略,利用Pro/E进行零件造型设计和分层规划;然后利用OpenGL和Visual C＋＋6.0对Pro/NC生成的数据文件进行处理,开发了支持NC代码自动生成和电极轨迹动态仿真的CAM系统.该系统已应用于微细电火花数控加工系统,实现了微三维结构工件加工.     

Open-architecture of CNC system and mirror milling technology for a 5-axis hybrid robot

This paper presents an open-architecture of CNC system and mirror milling technology for a new-type 5-axis hybrid robot named TriMule. The CNC system with dual CPUs is developed first to achieve human-computer interaction and motion control. Then, three key technologies are integrated in the system for improving the control quality, including singularity avoidance, feedforward control considering joint couplings and real-time error compensation by using externally mounted encoders. Based on these control technologies for single robot system, a collaborative machining strategy on the mirror milling system that consists of two TriMule robots is proposed to control the machining wall thickness of large thin-walled structural parts. Experiments on the TriMule robot and mirror milling system verify that the acceptable machining accuracy on the NAS test part and large thin-walled structural part can be ensured by using the developed CNC system and technologies. The root mean square of wall thickness error using the collaborative machining strategy can be 41.67% lower than the case without using the strategy.     

Design of a decision support system for machine tool selection based on machine characteristics and performance tests

Economic globalization, together with heightened market competition and increasingly short product life cycles are motivating companies to use advanced manufacturing technologies. Use of high speed machining is increasingly widespread; however, as the technology is relatively new, it lacks a deep-rooted knowledge base which would facilitate implementation. One of the most frequent problems facing companies wishing to adopt this technology is selecting the most appropriate machine tool for the product in question and own enterprise characteristics. This paper presents a decision support system for high speed milling machine tool selection based on machine characteristics and performance tests. Profile machining tests are designed and conducted in participating machining centers. The decision support system is based on product dimension accuracy, process parameters such as feed rate and interpolation scheme used by CNC and machine characteristics such as machine accuracy and cost. Experimental data for process error and cycle operation time are obtained from profile machining tests with different geometrical feature zones that are often used in manufacturing of discrete parts or die/moulds. All those input parameters have direct impact on productivity and manufacturing cost. Artificial neural network models are utilized for decision support system with reasonable prediction capability.     

文本对抗样本攻击与防御技术综述

对抗样本攻击与防御是最近几年兴起的一个研究热点,攻击者通过微小的修改生成对抗样本来使深度神经网络预测出错。生成的对抗样本可以揭示神经网络的脆弱性,并可以修复这些脆弱的神经网络以提高模型的安全性和鲁棒性。对抗样本的攻击对象可以分为图像和文本两种,大部分研究方法和成果都针对图像领域,由于文本与图像本质上的不同,在攻击和防御方法上存在很多差异。该文对目前主流的文本对抗样本攻击与防御方法做出了较为详尽的介绍,同时说明了数据集、主流攻击的目标神经网络,并比较了不同攻击方法的区别。最后总结文本对抗样本领域面临的挑战,并对未来的研究进行展望。     

基于深度卷积神经网络的刀具寿命动态预测研究

刀具寿命预测对提高工件加工精度和生产加工效率具有重要意义.同工况下同型号刀具监测信号数据分布不一致,导致历史寿命预测模型对刀具寿命预测效果有限.鉴于此,提出一种基于深度卷积神经网络(DCNN)的刀具寿命动态预测方法.首先,利用DCNN挖掘历史刀具监测信号的退化趋势特征,构建刀具寿命预测模型,并加入注意力机制对DCNN输出进行加权,加强对刀具寿命特征的学习,提高寿命预测准确度;然后,通过基于KL散度对刀具监测信号数据分布不一致进行检测,从而在已有刀具寿命预测模型的基础上进行更新迭代;最后,利用迭代后的模型再次进行刀具寿命预测.所提出方法很好地体现了刀具实际加工过程对刀具寿命的影响,以铣削数据集为例验证了所提出方法的有效性.