Neural network modeling and analysis of the material removal process during laser machining

To manufacture parts with nano- or micro-scale geometry using laser machining, it is essential to have a thorough understanding of the material removal process in order to control the system behaviour. At present, the operator must use trial-and-error methods to set the process control parameters related to the laser beam, motion system, and work piece material. In addition, dynamic characteristics of the process that cannot be controlled by the operator such as power density fluctuations, intensity distribution within the laser beam, and thermal effects can significantly influence the machining process and the quality of part geometry. This paper describes how a multi-layered neural network can be used to model the nonlinear laser micro-machining process in an effort to predict the level of pulse energy needed to create a dent or crater with the desired depth and diameter. Laser pulses of different energy levels are impinged on the surface of several test materials in order to investigate the effect of pulse energy on the resulting crater geometry and the volume of material removed. The experimentally acquired data is used to train and test the neural network's performance. The key system inputs for the process model are mean depth and mean diameter of the crater, and the system outputs are pulse energy, variance of depth and variance of diameter. This study demonstrates that the proposed neural network approach can predict the behaviour of the material removal process during laser machining to a high degree of accuracy.     

应用基于学习的模糊逻辑智能选择铣削加工参数

分析传统专家系统在铣削加工参数智能选择应用中存在的问题，提出一种可实现铣削用量智能选择的模糊逻辑推理方法。构造了以刀具直径、加工深度和材料硬度为输入，铣削进给量为输出的模糊推理模型，给出基于人工神经网络与k-means聚类相结合的机器学习方法，实现了推理规则知识的自动获取。通过手册数据与模型推理结果的对比实验，表明给出的方法具有较好的铣削用量智能匹配性能，研究成果为实现铣削用量在线智能选择提供了一种新方法。     

Experimental analysis on Nd:YAG laser micro-turning of alumina ceramic

Laser micro-turning is a micro-machining strategy to machine cylindrical workpiece of hard-to-process materials such as ceramics. Laser micro-turning method is in high demand in the present high-precision manufacturing industries because of its wide and potential uses in various engineering fields such as automobile, electronics, aerospace, and biomedical applications, etc. In the present research, the experimental analysis of Nd:YAG laser micro-turning of cylindrical-shaped ceramic material has been made to explore the desired laser output responses, i.e., depth of cut and surface roughness by varying laser micro-turning process parameters such as lamp current, pulse frequency, and laser beam scanning speed. Single laser beam has been utilized for successful micro-turning operation. Experimental results revealed that the laser machining process parameters have great influences for achieving desired laser micro-turned depth and surface roughness characteristics during laser micro-turning of alumina ceramics. SEM and optical photographs have also been analyzed for better understanding of the laser micro-turning process for different parametric settings.     

Delamination analysis of the helical milling of carbon fiber-reinforced plastics by using the artificial neural network model

As carbon fiber-reinforced plastics are widely used in aeronautical and aerospace industries, the improvement of their processing quality is a crucial task. In recent years, helical milling, a brand new machining process that results in better hole quality with one-time machining, has been attracting increasing attention. Based on full factor experimental design, helical milling experiments were performed by using a special cutter. Using the data obtained from the experiments, the correlation between the delamination and the process parameters was established by developing an artificial neural network (ANN) model. MATLAB ANN Toolbox was used for modeling. The effects of the process parameters on delamination at the exit of the machined holes were analyzed by using this model and the predicted results. The significance of the process parameters in the improvement of the hole quality in helical milling was also assessed.     

Neural networks approach to the determination of the machining parameters

A neural networks based approach to determine the appropriate machining parameters such as speed, depth of cut and feed is proposed in this study. In this approach neural networks were used for building automatic process planning systems. Training of neural networks was performed with back propagation method by using data sets sampled in a standard handbook. These networks consist of simple processing, elements or nodes capable of processing information in response to external inputs. This approach saves computing time and storage space. In addition, it provides easy extendability as new data become available. Currently, the system provides three neural networks: for turning, for milling and for drilling operations. The performance of the trained neural network for drilling is evaluated to examine how well it predicts the machining parameters. Test results show that the neural network for the turning operation is able to predict the machining parameter values within an acceptable error rate.     

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。     

The efficacy of back propagation neural network with delta bar delta learning in predicting the wear of carbide inserts in face milling

Face milling is a process predominantly affected by dynamic variation of cutting forces, thermo-mechanical shocks and vibration leading to catastrophic tool failure along with gradual wear of the inserts. Keeping in view the industrial importance of this process, it is necessary to devise suitable methods to predict in advance the onset of tool failure without grossly impairing the machining set-up and the job. Hence, the applicability of back propagation neural network with delta bar delta learning rule for faster convergence has been studied with the above objective. The multi sensor based tool condition monitoring strategy shows that the learning rate adaptation scheme combined with the selection of suitable process parameters drastically reduces the training time of the artificial neural network without dispensing with the prediction accuracy.     

模具钢铣削中刀具磨损的试验研究

以面铣刀刀片磨损为研究对象,结合类神经网络系统建构高速数控铣削加工的预测模型。以加工参数为模型输入条件,刀腹磨耗为输出条件。采用多因素试验方法,选择切削速度、进给速度、切削深度三个试验参数,利用直交表式的试验计划法设计试验点。依照试验点铣削工件后再测量刀具加工后的刀腹磨耗量,进而求得倒传递网络所需的36组训练范例与11组验证数据。刀腹磨耗预测模式是利用类神经网络中的倒传递网络原理,以田口法求得倒传递网络参数的最优值。试验结果显示,刀腹磨耗随着切削速度、进给速度、切削深度增加而上升。铣削模具钢后,刀具磨耗预测值的平均误差为4.72%,最大误差为11.43%,最小误差为0.31%。整体而言,类神经网络对于铣削加工可进行有效预测。     

Joining of aluminium and copper materials with friction welding

Radial basis network (RBN), a special type of artificial neural networks (ANN), is introduced to the field of machining process modeling and simulation. This feed-forward three-layer fully interconnected neural network is successfully used to establish the relationship between the machining conditions (inputs) and process parameters (outputs) for the case of ball end milling. A set of four key input parameters is selected to represent the cutting conditions, while four important characteristics of the instantaneous cutting force are used as the output set. Experiments are conducted to train as well as to validate and assess the performance of the proposed network. In addition, a case study, consisting of a typical machining scenario found in industry, is performed to test and verify the model. A very good agreement is observed between the forces predicted by the new model and their experimental counterparts, thus validating the new approach.     

水辅助激光加工技术的实验研究

介绍水辅助激光打孔和切割实验研究。研究表明 ,用毫秒级YAG脉冲激光对不锈钢和Al2 O3 陶瓷加工时 ,熔屑易从加工区排出 ,有助于提高加工的表面质量 ;加工单晶硅时 ,加工表面易产生微裂纹 ,使加工质量变差。激光通过水层时 ,有能量损失 ,水层深度越深 ,能量损失越大。     

Parametric analysis and optimization of Nd:YAG laser micro-grooving of aluminum titanate (Al2TiO5) ceramics

Pulsed Nd:YAG Laser offers an excellent role for various micro-machining operations of a wide range of engineering materials such as ceramics, composites, diamond etc. The micro-machining of ceramics are highly demanded in the present industry because of its wide and potential uses in various field such as automobile, electronic, aero-space, and bio-medical engineering applications etc. Aluminum titanate (Al₂TiO₅) has tremendous application in automobile and aero engine industry due to its excellent thermal property. The present research paper deals with the response surface methodology based mathematical modeling and analysis on machining characteristics of pulsed Nd:YAG laser during micro-grooving operation on a work piece of aluminum titanate. In this present study, lamp current, pulse frequency, pulse width, assist air pressure and cutting speed of laser beam are considered as machining process parameters during pulsed Nd:YAG laser micro-grooving operation. The response criteria selected for analysis are deviation of taper and deviation of depth characteristics of micro-groove produced on a work piece made of aluminum titanate (Al₂TiO₅). The analysis of variance test has also been carried out to check the adequacy of the developed regression mathematical models. The optimal process parameter settings are assist air pressure of 1.3 kgf/cm², lamp current of 20.44 amp, pulse frequency of 1.0 kHz, pulse width of 10% of duty cycle, and cutting speed of 10 mm/s for achieving the predicted minimum deviation of taper and deviation of depth of laser micro-groove. From the analysis, it is evident that the deviation of taper angle and deviation of depth of the micro-groove can be reduced by a great extent by proper control of laser machining process parameters during micro-grooving on aluminum titanate (Al₂TiO₅).     

Hybrid (LASER + CNC) process for lubricant groove on linear guides

A novel hybrid process [LASER?+?computer numerical control (CNC) machining] is used to fabricate a linear motion guide. A 20-W pulsed fiber laser and a three-axis CNC machining center were combined to fabricate microscale lubrication grooves on a 5-mm wide linear guide contact surface made of SCM-440H material. Ablation fabrication speed was increased up to 1,000 mm/min (or 16.7 mm/s) with a great ablation quality without any tool wear. The mean values of patterned sizes of lubrication grooves were measured to be between 40 and 80?μm in width and between 150 and 275?μm in depth with a laser pulse repetition of 25 kHz. A specially designed optical device was compact enough to be installed on CNC machine. It was mounted on the CNC spindle and proved to be flexible enough to deliver the laser beam on to the work piece. The microscale ablation quality of the surface was of sufficient quality to be adopted on most linear motion related applications.     

基于混合算法的薄壁件铣削加工工艺参数优化

结合神经网络法和遗传算法的优点,提出了一种以倒传递神经网络法为基础的加工工艺参数优化方法,对薄壁件铣削加工工艺参数进行优化。将田口实验所得数据经倒传递神经网络进行训练与测试,来建立薄壁件铣削加工的信噪比预测器,并通过最大化信噪比,将铣削过程变异降至最低,进而找出最佳加工工艺参数组合。通过数值模拟与加工实验,验证了所提方法在薄壁件铣削加工工艺参数优化中的有效性。     

Automatic detection of depth of cut during end milling operation using acoustic emission sensor

Any shortfall in the required depth during milling machining can affect the dimensional accuracy of the part produced and can cause a catastrophic failure to the machine. Corrective remedies to fix the dimensions inaccuracy will increase the machining time and costs. In this work, a depth-of-cut monitoring system was proposed to detect depth of cut in real time using an acoustic emission sensor and prediction model. The characteristics of the sensor signal obtained in machining processes can be complex in terms of both nonlinearity and nonstationarity. To overcome this complexity, a regression model and an artificial neural network model were used to represent the relationship between the acoustic emission signal and the depth of cut. The model was tested under different machining cases and found to be efficient in predicting the depth of cut.     

工程塑料表面金属覆层的激光定域精细去除

结合激光刻蚀手段与数控加工技术,提出了一种基于数控激光铣削的工程塑料表面金属覆层定域精细去除方法。考虑不同位置的零件对加工质量的要求不同,通过激光烧蚀实验结果得到了保证图形边缘质量的精密切边加工工艺并确定了相应的工艺参数。开发了基于实际进给速度自适应调整激光能量的覆层金属定厚度高效去除技术,完成了图形内部余量的去除,解决了机床实际进给速度受动态性能限制无法达到预设值而导致的目标材料过烧蚀问题。最后,以典型零件复合式三维信号发送/接收器为例,通过对工件图形分区域变参数加工验证了所提出的方法的可行性。实验结果表明:采用基于数控激光铣削的金属覆层定域精细去除技术能够完成典型样件的精密加工,加工的三维金属图形衔接精准,边缘光顺整齐,热影响区范围小,能够满足该类零件高质高效的制造要求。     

ELECTRIC DISCHARGE MILLING AND MECHANICAL GRINDING COMPOUND MACHINING OF SILICON CARBIDE CERAMIC

Silicon carbide (SiC) ceramics have been widely used in modern industry. However, the manufacture of SiC ceramics is not an efficient process. This paper proposes a new technology of machining SiC ceramics with electrical discharge milling and mechanical grinding compound method. The compound process employs the pulse generator used in electrical discharge machining, and uses a water-based emulsion as the machining fluid. It is able to effectively machine a large surface area on SiC ceramics with a good surface quality. In this paper, the effects of pulse duration, pulse interval, peak voltage, peak current and feed rate of the workpiece on the process performance parameters, such as material removal rate, relative electrode wear ratio and surface roughness, have been investigated. A L₂₅ orthogonal array based on Taguchi method is adopted, and the experimental data are statistically evaluated by analysis of variance and stepwise regression. The significant machining parameters, the optimal combination levels of machining parameters, and the mathematical models associated with the process performance are obtained. In addition, the workpiece surface microstructure is examined with a scanning electron microscope and an energy dispersive spectrometer.     

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.     

Intelligent optimization and selection of machining parameters in finish turning and facing of Inconel 718

The heat-resistant super alloy material like Inconel 718 machining is an inevitable and challenging task even in modern manufacturing processes. This paper describes the genetic algorithm coupled with artificial neural network (ANN) as an intelligent optimization technique for machining parameters optimization of Inconel 718. The machining experiments were conducted based on the design of experiments full-factorial type by varying the cutting speed, feed, and depth of cut as machining parameters against the responses of flank wear and surface roughness. The combined effects of cutting speed, feed, and depth of cut on the performance measures of surface roughness and flank wear were investigated by the analysis of variance. Using these experimental data, the mathematical model and ANN model were developed for constraints and fitness function evaluation in the intelligent optimization process. The optimization results were plotted as Pareto optimal front. Optimal machining parameters were obtained from the Pareto front graph. The confirmation experiments were conducted for the optimal machining parameters, and the betterment has been proved.     

Parameter optimization of machining processes using teaching–learning-based optimization algorithm

The optimum selection of process parameters plays a significant role to ensure quality of product, to reduce the machining cost and to increase the productivity of any machining process. This paper presents the optimization aspects of process parameters of three machining processes including an advanced machining process known as abrasive water jet machining process and two important conventional machining processes namely grinding and milling. A recently developed advanced optimization algorithm, teaching–learning-based optimization (TLBO), is presented to find the optimal combination of process parameters of the considered machining processes. The results obtained by using TLBO algorithm are compared with those obtained by using other advanced optimization techniques such as genetic algorithm, simulated annealing, particle swarm optimization, harmony search, and artificial bee colony algorithm. The results show better performance of the TLBO algorithm.     

基于动力学不确定性的重型切削工艺参数优化

针对数控重型切削加工过程的切削稳定性具有不确定性的特点,提出了在切削稳定性和机床工作能力的约束下,获得最大材料去除率的工艺参数优化方法。根据重型切削加工的工艺特点建立三维动力学模型,以机床的固有频率、阻尼比、刚度和切削力系数作为不确定因素,结合排零定理和边理论对其进行不确定性分析,获得稳健的切削稳定性叶瓣图,结合切削深度、刀具直径和刀具齿数的关系,为加工过程选择能获得最大切削深度的刀具。在此基础上,建立工艺参数优化模型,选择最佳的轴向切削深度、径向切削深度和主轴转速的组合,最后以一台加工中心上某型号发动机缸体表面的粗加工过程为例进行了验证。