数控电火花线切割加工参数优选的试验研究

针对数控高速走丝电火花线切割加工中的电参数的选取,本文运用二次通用旋转组合设计方法进行了工艺数据试验,提出了针对人工神经网络建模的数据预处理方法,建立了基于BP神经网络的电火花线切割加工参数模型。该模型可有效地反映高速走丝电火花线切割加工的工艺规律,实现在指定加工要求下的加工参数的优化选取。     

基于神经网络的电火花加工工艺选择模型研究

针对电火花加工工艺数据的特点,研究了神经网络输入输出数据的预处理方法,提出了基于对数变换的数据预处理算法,测试表明效果较优。分析了电火花加工工艺的特点及其复杂性,提出了基于神经网络的电火花加工工艺选择模型,该模型能模拟熟练操作者的决策过程。测试结果表明,该模型能真实反映机床本身的工艺特点,模型值和实测值相差较小,能实现在给定加工要求下电加工参数的自动选择。     

电火花加工工艺参数优化蚁群-模糊C均值算法的研究

电火花加工具有传统加工方法无法比拟的优点,但影响电火花加工效果的参数众多,因此加工参数的选取对于加工质量至关重要。提出了用蚁群算法改进的模糊C均值聚类算法来选取工艺参数。该方法基于经验数据,采用聚类分析技术寻找最能够代表一类数据的聚类中心作为最优工艺参数。仿真试验表明了该方法的有效性。     

智能化电火花加工CAPP系统的研究

针对电火花加工工艺的特点,采用专家系统与人工神经网络相给合实现电火花加工智能化CAPP系统——I-EDM-CAPP系统。建立了基于规则的简易Petri网SPN模型以实现加工方法的智能选取;采用复合神经网络（CNN）实现电参数学习模型,从而能够准确地选择并合理地扩展电加工工艺参数。     

NdFeB材料电火花加工工艺效果的预测模型

NdFeB材料由于高硬度、高脆性的特性,常规方法难以加工。电火花加工是加工硬脆材料的一种有效方法。为了实现高效、高质量的加工,对钕铁硼材料的电火花加工工艺规律需进行研究。本文中采用单因素实验法与正交试验法相结合进行实验设计。在大量试验的基础上,利用SPSS软件建立了电火花加工工艺模型。根据已建立的理论模型,对比回归结果与实际加工结果,验证了所建立的回归分析模型的合理性。通过设计新的实验,利用MATLAB软件预测电火花加工工艺效果,得出不同工艺参数下预测值与实际值相接近。     

TA7电火花加工实验研究与工艺参数优化

针对TA7钛合金难切削以及加工表面质量差的问题,在通用电火花机床上探究了空载电压、峰值电流、脉冲宽度以及脉冲间隔对TA7钛合金电火花加工中材料去除率与表面粗糙度的影响。设计中心复合实验,在实验数据的基础上采用多线回归技术建立材料去除率和表面粗糙度的二阶预测模型。方差分析结果表明预测模型可以正确映射出TA7钛合金电火花加工的工艺规律。以提高材料去除率降低表面粗糙度为目的建立工艺目标优化模型,根据实际加工条件对工艺参数的约束,设计粒子群算法求取优化模型的解集,通过实际加工对优化结果进行验证,结果表明该算法可以正确可靠的获得多约束条件下的最优加工参数。     

快走丝电火花线切割加工仿真系统

通过神经网络技术建立了快走丝电火花线切割加工工艺模型 ,利用穷举法建立了具有一定人工智能的工艺参数全局优化系统 ,开发了模具电火花加工过程仿真系统。该系统不仅可以精确预测加工效果 ,而且克服了工艺参数表的局限性 ,弥补了建立在工艺参数表基础上的参数自动选取系统的缺陷 ,实现了工艺参数全局最优化。测试结果及实际使用结果表明本文所建立的仿真系统反映了机床的加工工艺特性 ,预测误差基本控制在 8%内 ,系统的参数优化选取功能使机床的加工性能得以充分发挥。仿真系统具有广泛的通用性 ,可适用于不同类型的线切割加工机床。     

利用神经网络建立电火花加工工艺模型

以峰值电流、脉冲宽度、脉冲间隔、抬刀时间和加工时间为输入参数,以加工速度和表面粗糙度为输出参数,利用人工神经网络技术建立了电火花加工工艺模型。经过与实验数据的比较,认为该模型能精确地预测出给定条件下的加工速度和表面粗糙度,真实反映了机床的加工工艺规律。     

神经网络在工程陶瓷电火花加工中的应用研究

为解决工程陶瓷电火花加工中工艺参数与表面质量之间数学模型难以建立这一问题,提出将人工神经网络引入电加工领域中。建立了工程陶瓷电火花加工表面粗糙度随工艺参数变化的预测模型。实验结果表明,应用此模型能精确地预测出给定条件下的表面粗糙度,相对误差小,进而验证了该模型的可靠性。     

喷雾电火花铣削加工的能量分配与材料蚀除模型

针对喷雾电火花铣削加工(Electrical discharge milling, ED-milling)建立电蚀坑形成过程的热-流耦合模型,并改进电火花加工中放电能量在阴极及阳极分配系数的判断方法来为所建立的蚀除模型提供边界条件。此外,通过试验得到不同放电参数下的电蚀坑半径,并对蚀坑半径随脉宽和电流变化的规律采用最小二乘法进行拟合作为等离子体扩张方程。基于材料蚀除的热-流耦合二维模型,应用仿真-试验比对的方法得到雾中电火花铣削加工时放电能量在正极的分配系数近似为0.29,负极分配系数约为0.025。根据相关加工参数及所建立的模型,对喷雾电火花加工的电蚀坑尺寸进行计算并与试验测量结果进行对比,两者误差约在8%,证明该模型是可信的。通过对比试验和分析结果,可知喷雾电火花铣削加工中放电通道中的能量分配在阳极的比例远大于阴极,从而揭示了在雾中电火花加工中工件接正极时材料去除率更高的原因。通过所建立的阴、阳极的蚀除模型,用于对喷雾电火花加工的材料去除率、表面粗糙度等进行推导和预测,从而优化工艺参数并减少加工成本。此外,所建立的模型可进一步扩展应用到液中、气中等多种电火花加工(Electrical discharge machining, EDM)中,并为EDM加工机理的研究提供了一种可行的方法。     

基于改进BP网络的电火花加工工艺选择模型

提出了基于对数变换的数据预处理改进算法,测试表明效果较好。以加工面积、电极损耗比、表面粗糙度为输入参数,脉冲电流、脉冲宽度、脉冲间隙、放电间隙、伺服基准、伺服速度、加工速度为输出参数,提出了基于改进BP神经网络的电火花加工工艺选择模型。经过与实验数据的比较,该模型能真实反映机床的加工工艺规律,能实现在给定加工条件下进行电加工参数的自动选择。     

A method to predict possibility of arcing in EDM of TiB2p reinforced ferrous matrix composite

Electrical Discharge Machining (EDM) is very popular for machining conductive metal matrix composites (MMCs) because the hardness rendered by the ceramic reinforcements to these composites causes very high tool wear and cutting forces in conventional machining processes. EDM requires selection of a number of parameters for desirable results. Inappropriate parameter selection can lead to high overcuts, tool wear, excessive roughness, and arcing during machining and adversely affect machining quality. Arcing leads to short circuit gap conditions resulting in large energy discharges and uncontrolled machining. Arcing is a detrimental phenomenon in EDM which causes spoiling of workpiece and tool electrode and tends to damage the power supply of EDM machine. Parameter combinations that lead to arcing during machining have to be identified and avoided for every tool, work material, and dielectric combination. Proper selection of parameter combinations to avoid arcing is essential in EDM. In the work, experiments were conducted using L27 design of experiment to determine the parameter settings which cause arcing in EDM machining of TiB₂p reinforced ferrous matrix composite. Important EDM process parameters were selected in roughing, intermediate, and finishing range so as to study the occurrence of arcing. Using the experimental data, an artificial neural network (ANN) model was developed as a tool to predict the possibility of arcing for selected parameter combinations. This model can help avoid the parameter combinations which can lead to arcing during actual machining using EDM. The ANN model was validated by conducting validation experiments to ensure that it can work accurately as a predicting tool to know beforehand whether the selected parameters will lead to arcing during actual machining using EDM. Validation results show that the ANN model developed can predict arcing possibility accurately when the depth of machining is included as input variable for the model.     

Optimization of machining parameters in rotary EDM process by using the Taguchi method

Electrical discharge machining (EDM) is one of the advanced methods of machining. Most publications on the EDM process are directed towards non-rotational tools. But rotation of the tool provides a good flushing in the machining zone. In this study, the optimal setting of the process parameters on rotary EDM was determined. A total of three variables of peak current, pulse on time, and rotational speed of the tool with three types of electrode were considered as machining parameters. Then some experiments have been performed by using Taguchi's method to evaluate the effects of input parameters on material removal rate, electrode wear rate, surface roughness, and overcut. Moreover, the optimal setting of the parameters was determined through experiments planned, conducted, and analyzed using the Taguchi method. Results indicate that the model has an acceptable performance to optimize the rotary EDM process.     

Multi-objective optimization of electric-discharge machining process using controlled elitist NSGA-II

Parametric optimization of electric discharge machining (EDM) process is a multi-objective optimization task. In general, no single combination of input parameters can provide the best cutting speed and the best surface finish simultaneously. Genetic algorithm has been proven as one of the most popular multi-objective optimization techniques for the parametric optimization of EDM process. In this work, controlled elitist non-dominated sorting genetic algorithm has been used to optimize the process. Experiments have been carried out on die-sinking EDM by taking Inconel 718 as work piece and copper as tool electrode. Artificial neural network (ANN) with back propagation algorithm has been used to model EDM process. ANN has been trained with the experimental data set. Controlled elitist non-dominated sorting genetic algorithm has been employed in the trained network and a set of pareto-optimal solutions is obtained.

     

Artificial neural network model in surface modification by EDM using tungsten–copper powder metallurgy sintered electrodes

Electro-discharge machining (EDM) is a widely accepted nontraditional machining process used mostly for machining materials difficult to machine by conventional shearing process. Surface modification by powder metallurgy sintered tools is an uncommon aspect of EDM. Of late, it is being explored by many researchers. In the present paper, attempts have been made to model the surface modification phenomenon by EDM with artificial neural networks. Two output measures, material transfer rate and average layer thickness, have been correlated with different process parameters and presented in the form of plots. The predicted results are matching well with the experimental results.     

Development of an intelligent process model for EDM

This paper reports the development of an intelligent model for the electric discharge machining (EDM) process using finite-element method (FEM) and artificial neural network (ANN). A two-dimensional axisymmetric thermal (FEM) model of single-spark EDM process has been developed based on more realistic assumptions such as Gaussian distribution of heat flux, time- and energy-dependent spark radius, etc. to predict the shape of crater cavity, material removal rate, and tool wear rate. The model is validated using the reported analytical and experimental results. A neural-network-based process model is proposed to establish relation between input process conditions (discharge power, spark on time, and duty factor) and the process responses (crater geometry, material removal rate, and tool wear rate) for various work—tool work materials. The ANN model was trained, tested, and tuned using the data generated from the numerical (FEM) simulations. The ANN model was found to accurately predict EDM process responses for chosen process conditions. It can be used for the selection of optimum process conditions for EDM process.     

Rapid tooling aided by reverse engineering to manufacture EDM electrodes

The present work deals with the application of indirect rapid tooling (RT) technology to manufacture electrical discharge machining (EDM) copper electrodes from investment casting, with wax prototypes made by ThermoJet 3D printing, a rapid prototyping (RP) technique. The reverse engineering (RE) method is utilised to transform the point cloud data of an object surface, obtained from 3D digitising, in a 3D CAD surface model dataset. The methodology presented is fundamental to verify the prototype’s geometry for tooling so as to assure its metrological accuracy and to optimise foundry process parameters using finite element analysis (FEA). Based on a case study, some functional conclusions are presented for the application of RT in manufacturing EDM electrodes aided by 3D digitising and RE, validating the accomplishment by the integration of these technologies and methodologies in EDM manufacturing processes.     

电火花加工8418钢的工艺预测模型

在电火花加工中,加工工艺指标的结果与工艺参数的设置密切相关。一般情况下,操作者在进行实际执行之前,只能根据以往的加工规律以及经验手段对其结果进行预判,达到预先评估加工结果的目的。针对这一情况,提出一种适用于电火花加工工艺指标结果预测的模型,该模型的建立是基于支持向量回归理论的数学方法,并利用遗传算法优化该方法中的各参数。以电火花加工8418模具钢为例,结合正交试验方法和经验加工方法选取加工工艺参数,并记录工艺指标结果。为保证EDM工艺指标预测模型的准确性,将试验数据随机分成训练集和测试集,利用训练集训练EDM工艺指标预测模型,可得加工时间模型均方误差T_(MSE)=0.95′10~(-4),平方相关系数T_(R2)=0.99 1;工件去除率模型均方误差MRR_(MSE)=1.02′10~(-4),平方相关系数MRR_(R2)=0.999 3;电极损耗率模型均方误差EWR_(MSE)=1.11′10~(-4),平方相关系数EWR_(R2)=0.998 9。再利用测试集验证该模型,可见预测结果与试验结果之间的误差在5%以内,从而证明电火花加工8418钢工艺预测模型的准确性和有效性。     

Assessment of the dynamical properties in EDM process—detecting deterministic nonlinearity of EDM process

Time series of gap state were often used as feedback signal in electrical discharge machining (EDM) adaptive control systems. However, models precisely describing the EDM process have never been built because of the once believed stochastic nature of the EDM process. In this case, the power of adaptive controls in EDM had not been fully brought into play. Before building a feasible model, it is prerequisite to determine whether an efficient stable EDM process is nonlinear or linear, deterministic or stochastic. The main purpose of this paper is to investigate the deterministic nonlinearity of the process. A discriminating method was first provided to judge states in the gap at sampling intervals from voltage and current. Gap state was then statistically quantified from a train of discriminated states at sampling intervals within a specified period of time. Based on a time series of gap state data, we took use of surrogate data method to detect the nonlinearity of the process. From the results of two kinds of tests, it can be concluded that the deterministic nonlinearity of the process reflected by gap states is intrinsic.