Recurrent ANN-based modelling of the dynamic evolution of the surface roughness in grinding

Grinding is critical in modern manufacturing due to its capacity for producing high surface quality and high-precision parts. One of the most important parameters that indicate the grinding quality is the surface roughness (R _a). Analytical models developed to predict surface finish are not easy to apply in the industry. Therefore, many researchers have made use of artificial neural networks. However, all the approaches provide a particular solution for a wheel–workpiece pair, not generalizing to new grinding wheels. Besides, these solutions do not give surface roughness values related to the grinding wheel status. Therefore, in this work the modelling of the dynamic evolution of the surface roughness (R _a) based on recurrent neural networks is presented with the capability to generalize to new grinding wheels and conditions taking into account the wheel wear. Results show excellent prediction of the surface finish dynamic evolution. The absolute maximum error is below 0.49 µm, being the average error around 0.32 µm. Besides, the analysis of the relative importance of the inputs shows that the grinding conditions have higher influence than the wheel characteristics over the prediction of the surface roughness confirming experimental knowledge of grinding technology users.

     

End mill design and machining via cutting simulation

This paper describes a design process for an end mill. A solid model of the designed cutter is constructed together with the computation of the cutter’s geometry, wheel geometry, and wheel positioning data for fabricating end mills with the required cutter geometry. The main idea of the process is to use the cutting simulation method to obtain the machined shape of an end mill by using Boolean operations between a given grinding wheel and a cylindrical workpiece (raw stock). The major design parameters of a cutter, such as rake angle and inner radius, can be verified by interrogating the section profile of its solid model. This study investigates the relationship between various dimensional parameters and proposes an iterative approach to obtain the required geometry of a grinding wheel and cutter location (CL) data for machining an end mill that satisfies the design parameters. This research was implemented using a commercial computer aided design (CAD) system with API function programming and is currently used by a commercial tool maker in Korea. It can eliminate the need to produce a physical prototype during the design stage and can be used in virtual cutting tests and analyses.     

Creep feed grinding optimization by an integrated GA-NN system

The present work is aimed to optimize creep feed grinding (CFG) process by an approach using integrated Genetic Algorithm-Neural Network (GA-NN) system. The aim of this creep feed grinding optimization is obtain the maximal metal removal rate (MRR) and the minimum of the surface roughness (R _a ). For optimization, metal removal rate is calculated with a mathematic formula and a Back Propagation (BP) artificial neural-network have been used to prediction of R _a . The parameters used in the optimization process were reduced to three grinding conditions which consist of wheel speed, workpiece speed and depth of cut. All of other parameters such as workpiece length, workpiece material, wheel diameter, wheel material and width of grinding were taken as constant. The BP neural network was trained using the scaled conjugate gradient algorithm (SCGA). The results of the neural network were compared with experimental values. It shows that the BP model can predict the surface roughness satisfactorily. For optimization of creep feed grinding process, an M-file program has been written in ‘Matlab’ software to integrate GA and NN. After generation of each population by GA, firstly, the BP network predicts R _a and then MRR has been calculated with mathematic formula. In this study, the importance of R _a and MRR is equal in the optimization process. By using this integrated GA-NN system optimal parameters of creep feed grinding process have been achieved. The obtained results show that, the integrated GA-NN system was successful in determining the optimal process parameters.     

虚拟砂轮的开发及其磨削性能分析

采用虚拟现实技术,开发了可交互的虚拟磨削加工环境．以正六面体作为磨粒的基本形态,并将该磨粒随机分布在砂轮基体上,建立虚拟砂轮的仿真物理模型以及磨粒与工件接触的数学模型．以平面磨削为例,进行了不同加工参数下磨削加工过程的动态仿真,测试了虚拟砂轮的磨削性能,并分析了工件表面粗糙度的影响因素．仿真结果与理论分析结果具有一致性,证明了将虚拟现实技术应用于磨削加工机理研究是可行的．     

Identification of effective engineering methods for controlling handheld workpiece vibration in grinding processes

The objective of this study is to identify effective engineering methods for controlling handheld workpiece vibration during grinding processes. Prolonged and intensive exposures to such vibration can cause hand-arm vibration syndrome among workers performing workpiece grinding, but how to effectively control these exposures remains an important issue. This study developed a methodology for performing their analyses and evaluations based on a model of the entire grinding machine-workpiece-hand-arm system. The model can simulate the vibration responses of a workpiece held in the worker's hands and pressed against a grinding wheel in order to shape the workpiece in the major frequency range of concern (6.3–1600 Hz). The methodology was evaluated using available experimental data. The results suggest that the methodology is acceptable for these analyses and evaluations. The results also suggest that the workpiece vibration resulting from the machine vibration generally depends on two mechanisms or pathways: (1) the direct vibration transmission from the grinding machine; and (2) the indirect transmission that depends on both the machine vibration transmission to the workpiece and the interface excitation transformation to the workpiece vibration. The methodology was applied to explore and/or analyze various engineering methods for controlling workpiece vibrations. The modeling results suggest that while these intervention methods have different advantages and limitations, some of their combinations can effectively reduce the vibration exposures of grinding workers. These findings can be used as guidance for selecting and developing more effective technologies to control handheld workpiece vibration exposures.     

Three dimensional thermal finite element simulation of electro-discharge diamond surface grinding

The key to achieve good surface integrity in the workpiece due to Electro-Discharge Diamond Grinding (EDDG) process, which is hybrid of grinding and EDM, is by preventing the excessive temperature and thermal stress generated during the process. EDDG in surface grinding mode called Electro-Discharge Diamond Surface Grinding (EDDSG), used for finishing operation, is a complex machining process where several disciplines of science and engineering are involved in its theory. The complexity of the process includes the random occurrence of spark during EDM process and nonlinear behavior of workpiece material includes temperature dependent thermal properties. The present work involves the development of a simulation model to simulate the complex EDDSG process which consists of simulation of each constituent process namely EDM and surface grinding for temperature and thermal stress distribution. In order to simulate the realistic complex conditions, the three dimensional FEM is used in the process of development of the model accounting the random occurrence of the spark during EDM. The effect of different dielectric fluid, duty factor and energy partition during EDM on the temperature distribution and MRR study related to EDM contribution are reported. It is observed that the spark contributes primarily to the temperature. The predicted results can be used to determine the surface integrity of the machined surface.     

A new approach for dynamic modelling of energy consumption in the grinding process using recurrent neural networks

Grinding is a critical machining process because it produces parts of high precision and high surface quality. Due to the semi-artisan production of the wheel, it is not possible to know in advance the performance of the wheel. One of the most useful parameters to characterize the grinding process is the specific grinding energy, which varies with the wear of the grinding wheel during its lifecycle. Thus, it would be useful to model the specific grinding energy in order to get information about the performance of the wheel before buying it. Unlike the typical applications of time series forecasting, in this work, a totally different issue is presented: the prediction of new and complete time series bounded in time without initial or historic values. In this context, an analysis of the effect of the time characteristics and the number of points of the time series on the prediction capabilities of the ANN is presented. The results of the analysis show that 200 points are enough to predict a complete time series up to 2000 mm³/mm of specific volume of material removed. Actually, it is shown that modelling the evolution of the grinding specific energy up to 2000 mm³/mm is possible. The net shows good capability to generalize to new grinding conditions, with errors below 23.65 %, and to new wheel characteristics, with errors below 20.01 %, which are satisfactory from the grinding process perspective.     

Accurate robotic belt grinding of workpieces with complex geometries using relative calibration techniques

Robotic belt grinding operations are performed by mounting a workpiece to the end effector and commanding it to move along a trajectory while maintaining contact with the belt grinding wheel. A constant contact force throughout the grinding process is necessary to provide a smooth finish on the workpiece, but it is difficult to maintain this force due to a multitude of installation, manipulation, and calibration errors. The following describes a novel methodology for robotic belt grinding, which primarily focuses on system calibration and force control to improve grinding performance. The overall theory is described and experimental results of turbine blade grinding for each step of the methodology are shown.     

基于卷积神经网络的平面磨削温度预测

为了减少磨削温度过高给零件带来热损伤等的负面影响,并提高零件产量、质量,本文建立了基于卷积神经网络的平面磨削温度预测模型.首先通过有限元仿真获得温度数据,并进行预处理,然后利用Google开源深度学习工具TensorFlow编写卷积神经网络程序,最后得到预测结果并与仿真值进行比较.结果表明,本文提出的基于卷积神经网络的磨削温度预测模型具有很强的学习能力以及非线性拟合能力,大大提高了磨削温度预测精度.     

A mathematical model for simulating and manufacturing ball end mill

The performance of ball end mill cutters in cutting operations is influenced by the configuration of the rake and clearance faces in the ball component. From the mathematical design of a cutting edge curve, the rake face can be defined by the rake angle and the width of the rake face at each cross section along the cutting edge. We propose the fundamental conditions that must govern the engagement between the grinding wheel and the designed rake face in order to avoid interference while machining a ball end mill. As a result, a new mathematical model for determining the wheel location and a software program for simulating the generation of the rake face of a ball end mill are proposed. In addition, methods for grinding the clearance face in both concave and flat-shapes are introduced. The flute surface generated by a disk wheel during the grinding process is determined on the basis of a tangency condition. The results of the experiment and the simulation are compared to validate the proposed model.     

Modeling and characterization of surface generation in fast tool servo machining of microlens arrays

A microlens array is composed of a series of microlens distributed in a regular pattern and has been used in a wide range of photonic products. Fast Tool Servo (FTS) machining is an enabling and efficient technology for fabricating high quality microlens arrays with submicrometer form accuracy and nanometric surface finish. Although there have been a number of studies on modeling and characterization of surface generation in Single Point Diamond Turning (SPTD), there is relatively little research on the modeling and characterization of surface generation in FTS machining of microlens arrays, which is radically different from SPTD and has additional process parameters. This paper therefore establishes a theoretical model for the prediction of surface generation in FTS machining of microlens arrays based on the cutting mechanism of FTS, cutting tool geometry, machining parameters, and the workpiece surface contour. A surface matching based method has been developed to characterize the surface quality of the microlens array as a whole instead of a single lens evaluation. A series of cutting experiments have been conducted, the actual results of which were found to largely agree with the predicted results. The successful development of the deterministic models and methods not only make the surface generation in FTS machining of microlens array more predictable, but also allow a better evaluation of the surface quality of the machined microlens array. It also helps to minimize or eliminate the need for conducting trial-and-error cutting experiments to optimize the machining process.     

凸轮磨恒线速加工过程曲线优化

为了提高凸轮轴的加工效率和加工精度,开发可用于凸轮轴磨削修整系统的动态优化模块。根据凸轮轴恒线速磨削原理,在Matlab中完成了数学模型的建模,采用三次样条曲线拟合插值法对加工过程曲线进行了优化,从而得到了波动更小的速度曲线并减少了恒线速度磨削所引起的联动轴响应问题。实验表明,该方法很好地实现了在二次磨削中对凸轮轴表面轮廓的修整,提高了凸轮轴的表面质量。     

Force control-based vibration suppression in robotic grinding of large thin-wall shells

Vibration suppression is a major difficulty in the grinding of low-stiffness large thin-wall shells. The paper proposes that effective workpiece vibration control can be performed by a novel force-controlled end-effector integrated into a robotic grinding workcell. First, a dynamics model is built to capture the characteristics and vibration suppression mechanism of force control-based robotic grinding, then a novel force control-based vibration suppression method is designed for grinding large thin-wall shells, and three robotic grinding tests are conducted to validate the effects of the new method and the grinding performance of the force control-based robotic grinding workcell. The results are: 75% reduction in the amplitude of workpiece vibration; effective suppression of non-tool passing frequency; stable grinding of large thin-wall shells remarkably enhancing grinding depth up to 0.3 mm per pass, grinding depth error less than ±0.1 mm, and significant improvement of the workpiece surface quality up to Ra=0.762 μm.     

磨矿粒度动态过程的一种快速Monte Carlo仿真方法

磨矿是降低矿物粒度的工业过程,产品粒度是磨矿过程的关键质量指标. 由于磨矿粒度难以在线检测且磨矿生产过程具有综合复杂特性,难以采用传统控制方法实现磨矿粒度的控制. 因此,建立磨矿粒度和关键工艺参数的动态模型对于磨矿运行控制和优化具有重要意义. 采用总量平衡原理获得磨矿粒度的微分方程模型多数情况下无法获得解析解. 而基于Monte Carlo （MC）方法的磨矿粒度模型能够精确模拟磨矿粒度分布的动态变化,但是其仿真效率低难以实用. 本文针对这一问题提出一种新的MC仿真方法： 在定总量方法的基础上引入新的颗粒移除机制,在移除过程中动态地分配各个粒级颗粒数目并保持破裂前后各个粒级颗粒所占总颗粒数的百分比不变,避免颗粒移除过程中由于粒级差异导致的抽样误差,且避免MC仿真速度随着仿真推进下降的问题. 仿真实验验证表明,本方法能够在保证一定精度前提下显著提高磨矿粒度MC仿真的计算速度. 最后,通过一个实例介绍了本文仿真模型在磨矿优化控制中的应用.     

Time-varying isobaric surface reconstruction and path planning for robotic grinding of weak-stiffness workpieces

Severe deformations and vibration usually occur when grinding the weak-stiffness workpieces, then fluctuate the grinding force and damage the surface. In this paper, the time-varying isobaric surface (TVIS) is defined as a virtual surface to generate constant force during robotic grinding. Based on it, a novel robotic grinding method, including contact trial and surface reconstruction, is proposed. In the contact trial process, the robot actively samples the deformation and stiffness of contact point with a force sensor. Then, a TVIS mesh is constructed to replace the original geometry of the workpiece, which is utilized for grinding path planning. Experiments have been conducted to verify the feasibility of this method. The result shows that the proposed method can achieve constant grinding force and is robust to the types of workpieces and the processing techniques. Furthermore, it is considered as an intelligent method for customized robotic machining of the weak-stiffness workpieces.     

Position-based force tracking adaptive impedance control strategy for robot grinding complex surfaces system

As a key technology of robot grinding, force control has great influence on grinding effects. Based on the traditional impedance control, a position-based force tracking adaptive impedance control strategy is proposed to improve the grinding quality of aeroengine complex curved parts, which considers the stiffness damping environmental interaction model, modifies the reference trajectory by a Lyapunov-based approach to realize the adaptive grinding process. In addition, forgotten Kalman filter based on six-dimensional force sensor is used to denoise the force information and a three-step gravity compensation process including static base value calculation, dynamic zero update and contact force real-time calculation is proposed to obtain the accurate contact force between tool and workpiece in this method. Then, to verify the effectiveness of the proposed method, a simulation experiment which including five different working conditions is conducted in MATLAB, and the experiment studying the deviation between the reference trajectory and the actual position is carried out on the robot grinding system. The results indicate that the position-based force tracking adaptive impedance control strategy can quickly respond to the changes of environmental position, reduce the fluctuation range of contact force in time by modifying the reference trajectory, compensate for the defect of the steady-state error of the traditional impedance control strategy and improve the surface consistency of machined parts.     

Analysis and optimization of fixture under dynamic machining condition with chip removal effect

Dynamic interactions in the tool–workpiece and workpiece–fixture systems significantly impinge on the quality of finished workpieces. The presented simulation system integrates the effects of workpiece fixture dynamics with the other factors contributing to the machining process dynamics. It provides more accurate prediction of the process output which helps in the design of the optimum fixture configuration prior to the production stage. Modelling of the frictional contact behaviour between the fixture element and the workpiece helps to improve the prediction accuracy of the simulation system which accelerates the convergence to the optimum fixture configuration design and consequently improves the machined part dimensional accuracy and geometric integrity. The developed simulation is capable of modelling complicated part geometries by interfacing with commercial ANSYS.V10^® packages. This research work minimizes the deformation of workpiece using integrated optimization tool of Genetic algorithm (GA) and ANSYS Parametric Design Language (APDL) of finite element analysis. The same layouts given by the above optimization tool are used in the experimental setup and it is found that the improved geometric tolerance of squarness and flatness of the given workpiece. The chip removal effect and frictional contact between the workpiece and the fixture elements are taken into account based on element death technique and nonlinear finite-element analysis. A Case study of an open slot milling process illustrates the application of the proposed improved geometric tolerance approach.     

Monitoring grinding wheel redress-life using support vector machines

Condition monitoring is a very important aspect in automated manufacturing processes. Any malfunction of a machining process will deteriorate production quality and efficiency. This paper presents an application of support vector machines in grinding process monitoring. The paper starts with an overview of grinding behaviour. Grinding force is analysed through a Short Time Fourier Transform (STFT) to identify features for condition monitoring. The Support Vector Machine (SVM) methodology is introduced as a powerful tool for the classification of different wheel wear situations. After training with available signal data, the SVM is able to identify the state of a grinding process. The requirement and strategy for using SVM for grinding process monitoring is discussed, while the result of the example illustrates how effective SVMs can be in determining wheel redress-life.     

Remote robotic underwater grinding system and modeling for rectification of hydroelectric structures

A submersible grinding robot has been designed to automate the dam gate metallic structure repair process. In order to measure and control the amount of material removed during the process, an empirical approach for modeling the material removal rate (MRR) of the underwater grinding application is proposed and presented in this paper. The objective is to determine the MRR in terms of the process parameters such as cutting speed and grinding power over a range of variable wheel diameters. Experiments show that water causes drag and a significant loss of power occurs during grinding. An air injector encasing the grinding wheel has been prototyped, and it is shown that power loss can be reduced by up to 80%. A model, based on motor characterization and empirical relations among system and process parameters, is developed for predicting MRR which will be used for the robotic grinding control system. A validation is carried out through experiments, and confirms the good accuracy of the model for predicting the depth of cut for underwater grinding. A comparative study for dry and underwater grinding is also conducted through experiments and shows that the MRR is higher for underwater grinding than in dry conditions at low cutting speeds.     

机车车轮对流传热系数计算

对流传热系数的准确计算对研究机车车轮温度场和应力场及其疲劳寿命预测有重要意义.针对HXD2机车车轮踏面制动过程,建立车轮及其绕流流场计算模型,应用CFD方法通过仿真得到机车车轮在不同运行速度下的对流传热系数.结果表明:由于车轮自身旋转,车轮表面不同位置处的对流传热系数不同;车轮上半迎风面的对流传热系数较大,下半迎风面较小,且都大于背风面数值.计算结果为研究机车车轮对流传热、蠕滑和制动等传热过程提供参考.