加工过程的智能控制方法现状及展望

切削过程恒力控制对于提高生产率、保证加工精度和提高刀具寿命具有重要作用.文章对国内外近20年恒切削力加工过程智能控制的研究现状作了回顾,尤其着重模糊控制及神经网络控制等控制方法在恒切削力加工过程控制中的应用,总结了加工过程智能控制在实际工业应用较少的原因及存在的问题.简单介绍了STEP-NC环境下加工过程智能控制的应用,并对将来的研究工作做了展望.     

神经网络在切削加工过程中的应用

文章提出了一种基于神经网络的自适应控制方法，并以非线性的切削加工过程为对象，进行了仿真。仿真结果表明，该系统在切削工况发生时变的情况下仍能实现恒切削力控制，具有很强的鲁棒性，达到了提高加工效率的目的。     

加工过程中基于最大熵的神经网络控制

切削过程恒力控制对于提高生产率、保证加工精度至关重要,本文将信息理论与神经网络理论相结合,提出了恒力切削过程中基于最大熵的神经网络控制,与自适应神经网络控制相比,具有收敛快,振荡小的特点.     

加工过程自适应模糊控制

由于加工过程受切削条件变化的影响，具有高度非线性性和时变性，传统的控制方法难以获得好的控制效果，为了保证加工的顺利进行，南京航空航天大学研究了一种新的控制方法──自适应模糊控制。为了提高模糊控制器的控制性能，提出了一种有效的逆推算法来对输出量化因子进行自适应调节。实验结果表明，这种自适应控制系统能在切削条件发生变化的情况下获得有效的恒力控制。     

BP神经网络在立铣刀结构参数优化中的应用

钛合金薄壁件的铣削加工过程中,刀具磨损速度快,并且工件容易变形,其主要因素是加工过程中切削力大,切削温度高。文章利用有限元仿真软件Advant Edge FEM铣削仿真数据,建立整体式立铣刀结构参数与切削力和切削温度的BP神经网络预测模型,并对切削预测模型进行了切削实验验证。在此基础上,利用BP神经网络模型的预测结果对整体式立铣刀的结构参数进行了优化,切削实验证明,优化后的刀具参数可以有效地降低切削力和切削温度,从而有效地改善过程中刀具的切削性能和工件的加工质量。     

基于改进瞬时刚性力模型的机床铣削加工监测

针对用于切削力预测的瞬时刚性力模型所需参数较多且依赖初步切削实验的问题,提出一种不需要切削实验的新型切削力预测方法,实现在实际工厂中监测机床铣削加工过程。在斜角切削模型和正交切削理论的基础上,对传统的瞬时刚性力模型进行改进,减少切削力预测所需的切削参数。改进后的模型仅需在铣削操作开始时从测量的主轴电机扭矩得到的剪切角参数,无需任何额外的传感器就可以实现铣削力预测。在所提模型中,刀具跳动的影响可通过每个切削刃处的旋转半径偏差表示,以精确预测切削力。为验证该模型的有效性,进行切削实验。结果表明：切削力的预测值与实测值吻合较好,在实际加工过程中,无需任何实验铣削或任何额外的力传感器就可以准确了解机床加工状态。     

复合排齿圈车削模型的有限元仿真

基于Deform3D软件平台,针对薄壁件复合排大齿圈建立三维有限元模型,并模拟了不同工艺参数下的车削加工过程,得到了切削过程中的切削力分布场和温度场。通过分析不同切削参数下切削力和切削热的变化规律,得出切削深度和进给量对切削力影响较大,而切削速度对切削热的影响大于切削深度和进给量。该研究结果为进一步优化工艺参数和加工变形控制提供了依据。     

基于VERICUT二次开发的数控加工切削力仿真研究

为解决传统有限元仿真软件在数控加工切削力仿真应用中效率低下的问题,论文介绍了一种基于VERICUT二次开发的数控加工过程切削力仿真的快速实现方法.在VC平台下,利用VERICUT软件提供的二次开发工具Optipath API(optimize path - application programming interface),在数控加工几何仿真完成后即时提取加工过程的切削参数.根据切削力经验模型,通过MFC(microsoftfoundation class)编程开发切削力仿真结果输出界面,得到数控加工过程中切削力数值的变化曲线,实现数控加工过程切削力仿真效率的显著提高.     

切削加工物理仿真系统结构研究

针对目前加工仿真局限于几何仿真的现状,基于有限元分析切削加工过程的理论,提出了一种切削加工物理仿真系统构建方案;并在C Builder开发环境上利用OpenGL技术、C 语言建立了虚拟加工环境,将切削过程中装夹力、切削力等物理因素的变化映射到虚拟制造系统中。与以往的仿真系统相比,可以除实现加工过程显示,还可实现加工误差、表面粗糙度的预测。     

恒力铣削智能控制算法研究与仿真(英文)

针对数控加工,建立了 2 种以切削力恒定为控制目标的在线智能控制系统。首先,利用 BP 神经网络对铣削过程进行了建模; 然后,基于 BP 神经网络和模糊控制理论,提出了 2 种以切削力恒定为控制目标的在线铣削控制算法; 最后,在变轴向切削深度条件下开展了仿真实验。相对于传统恒速切削,基于 BP 神经网络和模糊控制的在线智能控制系统分别节省了 13.9% 和 13.7% 的切削时间。     

Modelling the correlation between cutting and process parameters in high-speed machining of Inconel 718 alloy using an artificial neural network

An artificial neural network (ANN) model was developed for the analysis and prediction of the relationship between cutting and process parameters during high-speed turning of nickel-based, Inconel 718, alloy. The input parameters of the ANN model are the cutting parameters: speed, feed rate, depth of cut, cutting time, and coolant pressure. The output parameters of the model are seven process parameters measured during the machining trials, namely tangential force (cutting force, F_z), axial force (feed force, F_x), spindle motor power consumption, machined surface roughness, average flank wear (VB), maximum flank wear (VB_max) and nose wear (VC). The model consists of a three-layered feedforward backpropagation neural network. The network is trained with pairs of inputs/outputs datasets generated when machining Inconel 718 alloy with triple (TiCN/Al₂O₃/TiN) PVD-coated carbide (K 10) inserts with ISO designation CNMG 120412. A very good performance of the neural network, in terms of agreement with experimental data, was achieved. The model can be used for the analysis and prediction of the complex relationship between cutting conditions and the process parameters in metal-cutting operations and for the optimisation of the cutting process for efficient and economic production.     

雕刻表面球形铣削的分段变进给率加工

雕刻表面球形铣削加工中,根据刀头的受力模型,可以计算整个刀具路径上刀头的受力.刀具路径上加工深度变化时,若采用恒进给率,则刀具受力是变化的,为了安全保险起见,往往按最大受力来选择较低的恒进给率,整个加工效率很低.采用变进给率加工,即加工深度小时提高进给率,使刀具在整个路径上受力均匀.本文给出了路径上力的计算仿真方法,以及分段进给率的计算方法,可以指导实际的加工过程,这样既保证了加工过程的安全,又提高了生产率.     

基于BP神经网络数控机床切削能耗的研究

数控机床的能耗来源于工作时的电动机空载和切削过程中的负载消耗。分析切削过程中的切削速度、进给速度、切削深度等切削参数对数控机床能耗的影响;基于BP神经网络搭建数控机床能耗与切削参数的模型,简化了经验公式繁琐的计算过程;利用遗传算法对切削参数进行优化。对比试验表明:用优化后的参数进行加工,能明显地降低能耗,为加工过程能耗控制提供了一个良好的方案。     

Indirect cutting force measurement in multi-axis simultaneous NC milling processes

There have been many research works for the indirect cutting force measurement in machining process, which deal with the case of one-axis cutting process. In multi-axis cutting process, the main difficulties to estimate the cutting forces occur when the feed direction is reversed. This paper presents the indirect cutting force measurement method in contour NC milling processes by using current signals of servo motors. A Kalman filter disturbance observer and an artificial neural network (ANN) system are suggested. A Kalman filter disturbance observer is implemented by using the dynamic model of the feed drive servo system, and each of the external load torques to the x and y-axis servo motors of a horizontal machining center is estimated. An ANN system is also implemented with a training set of experimental cutting data to measure cutting force indirectly. The input variables of the ANN system are the motor currents and the feedrates of x and y-axis servo motors, and output variable is the cutting force of each axis. A series of experimental works on the circular interpolated contour milling process with the path of a complete circle has been performed. It is concluded that by comparing the Kalman filter disturbance observer and the ANN system with a dynamometer measuring cutting force directly, the ANN system has a better performance.     

Neural-network approach for predicting hole quality in reaming

Condition monitoring of the machining process is very important in today's precision manufacturing, especially in the case of reaming where in-process measurement of surface quality is difficult. In this paper, a new approach is presented for the condition monitoring in reaming using Artificial Neural Network. Acoustic emission, cutting force and vibration sensor data were measured during reaming operation and a multi-layer neural network was trained using these data with the conventional Back Propagation Algorithm for weight updation. Using force, vibration and acoustic emission parameters as input and Ra value of roughness, roundness error and residual stress as output, the network gave much superior results with sensor fusion.     

Modeling of tool wear in drilling by statistical analysis and artificial neural network

The useful life of a cutting tool and its operating conditions largely control the economics of the machining operations. Hence, it is imperative that the condition of the cutting tool, particularly some indication as to when it requires changing, to be monitored. The drilling operation is frequently used as a preliminary step for many operations like boring, reaming and tapping, however, the operation itself is complex and demanding.

Back propagation neural networks were used for detection of drill wear. The neural network consisted of three layers input, hidden and output. Drill size, feed, spindle speed, torque, machining time and thrust force are given as inputs to the ANN and the flank wear was estimated. Drilling experiments with 8 mm drill size were performed by changing the cutting speed and feed at two different levels. The number of neurons in the hidden layer were selected from 1, 2, 3, …, 20. The learning rate was selected as 0.01 and no smoothing factor was used. The estimated values of tool wear were obtained by statistical analysis and by various neural network structures. Comparative analysis has been done between statistical analysis, neural network structures and the actual values of tool wear obtained by experimentation.     

Tool flank wear prediction in CNC turning of 7075 AL alloy SiC composite

Flank wear occurs on the relief face of the tool and the life of a tool used in a machining process depends upon the amount of flank wear; so predicting of flank wear is an important requirement for higher productivity and product quality. In the present work, the effects of feed, depth of cut and cutting speed on flank wear of tungsten carbide and polycrystalline diamond (PCD) inserts in CNC turning of 7075 AL alloy with 10 wt% SiC composite are studied; also artificial neural network (ANN) and co-active neuro fuzzy inference system (CANFIS) are used to predict the flank wear of tungsten carbide and PCD inserts. The feed, depth of cut and cutting speed are selected as the input variables and artificial neural network and co-active neuro fuzzy inference system model are designed with two output variables. The comparison between the results of the presented models shows that the artificial neural network with the average relative prediction error of 1.03% for flank wear values of tungsten carbide inserts and 1.7% for flank wear values of PCD inserts is more accurate and can be utilized effectively for the prediction of flank wear in CNC turning of 7075 AL alloy SiC composite. It is also found that the tungsten carbide insert flank wear can be predicted with less error than PCD flank wear insert using ANN. With Regard to the effect of the cutting parameters on the flank wear, it is found that the increase of the feed, depth of cut and cutting speed increases the flank wear. Also the feed and depth of cut are the most effective parameters on the flank wear and the cutting speed has lesser effect.     

Prediction of flank wear by using back propagation neural network modeling when cutting hardened H-13 steel with chamfered and honed CBN tools

Productivity and quality in the finish turning of hardened steels can be improved by utilizing predicted performance of the cutting tools. This paper combines predictive machining approach with neural network modeling of tool flank wear in order to estimate performance of chamfered and honed Cubic Boron Nitride (CBN) tools for a variety of cutting conditions. Experimental work has been performed in orthogonal cutting of hardened H-13 type tool steel using CBN tools. At the selected cutting conditions the forces have been measured using a piezoelectric dynamometer and data acquisition system. Simultaneously flank wear at the cutting edge has been monitored by using a tool makers microscope. The experimental force and wear data were utilized to train the developed simulation environment based on back propagation neural network modeling. A trained neural network system was used in predicting flank wear for various different cutting conditions. The developed prediction system was found to be capable of accurate tool wear classification for the range it had been trained.