Multi-objective optimization for turning processes using neural network modeling and dynamic-neighborhood particle swarm optimization

In this paper, we introduce a procedure to formulate and solve optimization problems for multiple and conflicting objectives that may exist in turning processes. Advanced turning processes, such as hard turning, demand the use of advanced tools with specially prepared cutting edges. It is also evident from a large number of experimental works that the tool geometry and selected machining parameters have complex relations with the tool life and the roughness and integrity of the finished surfaces. The non-linear relations between the machining parameters including tool geometry and the performance measure of interest can be obtained by neural networks using experimental data. The neural network models can be used in defining objective functions. In this study, dynamic-neighborhood particle swarm optimization (DN-PSO) methodology is used to handle multi-objective optimization problems existing in turning process planning. The objective is to obtain a group of optimal process parameters for each of three different case studies presented in this paper. The case studies considered in this study are: minimizing surface roughness values and maximizing the productivity, maximizing tool life and material removal rate, and minimizing machining induced stresses on the surface and minimizing surface roughness. The optimum cutting conditions for each case study can be selected from calculated Pareto-optimal fronts by the user according to production planning requirements. The results indicate that the proposed methodology which makes use of dynamic-neighborhood particle swarm approach for solving the multi-objective optimization problems with conflicting objectives is both effective and efficient, and can be utilized in solving complex turning optimization problems and adds intelligence in production planning process.     

Pre-evaluation on surface profile in turning process based on cutting parameters

Traditional online or in-process surface profile (quality) evaluation (prediction) needs to integrate cutting parameters and several in-process factors (vibration, machine dynamics, tool wear, etc.) for high accuracy. However, it might result in high measuring cost and complexity, and moreover, the surface profile (quality) evaluation result can only be obtained after machining process. In this paper, an approach for surface profile pre-evaluation (prediction) in turning process using cutting parameters and radial basis function (RBF) neural networks is presented. The aim was to only use three cutting parameters to predict surface profile before machining process for a fast pre-evaluation on surface quality under different cutting parameters. The input parameters of RBF networks are cutting speed, depth of cut, and feed rate. The output parameters are FFT vector of surface profile as prediction (pre-evaluation) result. The RBF networks are trained with adaptive optimal training parameters related to cutting parameters and predict surface profile using the corresponding optimal network topology for each new cutting condition. It was found that a very good performance of surface profile prediction, in terms of agreement with experimental data, can be achieved before machining process with high accuracy, low cost, and high speed. Furthermore, a new group of training and testing data was also used to analyze the influence of tool wear on prediction accuracy.     

Measurement of properties of graphene sheets subjected to drilling operation using computer simulation

Drilling being one of the primary machining processes find wide spread applications in manufacturing of functional components. Optimization of drilling process performance requires critical understanding of process parameters which govern the mechanism of drilling process. Machining process at nanoscale level has been studied extensively using numerical modeling approaches owing to complexity in conducting experiments at nanoscale level. In this paper, we propose a new evolutionary approach based on multi-gene genetic programming (MGGP) to numerically model the drilling process of graphene sheet, a two dimensional nanoscale material. The performance of our proposed MGGP model is compared with that of the artificial neural network (ANN) and we observe that our predictions are well in agreement with the data obtained using conventional numerical approach for modeling machining process of nanoscale materials. We anticipate that our proposed MGGP model can find applications in optimizing the machining processes of nanoscale materials.     

Prediction of chip flow angle in orthogonal turning of mild steel by neural network approach

Improvement of chip control is a necessity for automated machining. Chip control is closely related to chip flow and it plays also a predominant role in the effective control of chip formation and chip breaking for the easy and safe disposal of chips, as well as for protecting the surface-integrity of the workpiece. Although several ways to predict the chip flow angle (CFA) have been subjected in some researches, a good approximation has not been achieved yet. In this study, using different indexable inserts and cutting conditions for turning of mild steel, the chip flow angles were measured and some of the collected data from this experimental study were used for training with a two hidden layered backpropagation neural network algorithm. A group was formed from randomly selected data for testing. The chip flow angle values found from multiple regression, neural network (NN) and studies of previous researchers under the same turning conditions of the present study were compared. It has been seen that the best prediction was obtained by neural network approach.     

A neural network based approach for background noise reduction in airborne acoustic emission of a machining process

Tool wear prediction has become an indispensable technique to prevent downtime in manufacturing and production processes. Airborne emission from a machining process using a low-cost microphone may provide a vital signal of tool health. However, the effect of background noise results in anomaly in data that may lead to wrong prediction of tool health. The paper presents an adaptive approach using neural networks for background noise filtration in acoustic signal for a turning process. Acoustic signal of a turning process is mixed with background noise from four different machines and introduced at different RPMs and feed-rate at a constant depth of cut. A comparison of Backpropagation neural network (BPNN), Self-organizing map and k-means clustering algorithm for noise filtration is investigated in this paper. In this regard, back-propagation neural network showed better performance with an average accuracy for all the four sources. It shows 100 % accuracy for grinding machine signal, 94.78 % accuracy for background signal from 3-axis milling machine, 45.57 % and 12.69 % for motor and 4-axis milling machine, respectively. Signal reconstruction is then done using Discrete cosine transform (DCT). The proposed technique shows a promising future for noise filtration in airborne acoustic data of a machining process.     

基于模糊神经网络的深孔加工刀具磨损率预测

刀具的过快磨损不仅增大加工成本,也影响工件的最终加工质量,因此预测和减少刀具磨损率具有重要意义。由于BP神经网络本身容易陷入局部极小值、收敛速度慢等缺陷,且深孔加工过程及其复杂,无法建立加工中刀具磨损率与加工参数之间的准确数学模型,故采用模糊神经网络建立BTA刀具磨损率在线钻削模型。仿真和实验结果表明,该模型能有效预测BTA刀具磨损率,对提高刀具寿命和加工深孔的质量具有一定的意义。     

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.     

面向加工特征的刀具和切削参数计算机辅助选择系统

切削刀具制造商面临围绕大量工件材料和加工特征为客户提供合理刀具和切削参数的现状,切削工艺规划的核心步骤也是刀具和切削参数的确定。确定刀具和切削参数一般多从零件材料角度出发,可能导致工件与刀具不匹配。文中提出面向加工特征的刀具和切削参数计算机辅助选择系统的开发。系统包括车削特征、铣削特征、钻削和镗削加工特征,系统利用特征图形作为用户交互式接口,采用关系数据库结合数据驱动和规则推理逻辑来选择刀具和切削参数,利用数学模型计算过程参数包括单工步加工工时、切削功率、最大粗糙度等,并辅助制定工序。以车刀和车削参数选择为例,介绍该系统的实现方法。该系统可以辅助设计师及工艺人员选择合理的刀具和切削参数。     

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。     

Parameter estimation for abrasive water jet machining process using neural networks

The abrasive water jet machining process, a material removal process, uses a high velocity jet of water and an abrasive particle mixture. The estimation of appropriate values of the process parameters is an essential step toward an effective process performance. This has led to the development of numerous mathematical and empirical models. However, the complexity of the process confines the use of these models for limited operating conditions; e.g., some of these models are valid for special material combinations while others are based on the selection of only the most critical variables such as pump pressure, traverse rate, abrasive mass flow rate and others that affect the process. Furthermore, these models may not be generalized to other operating conditions. In this respect, a neural network approach has been proposed in this paper. Two neural network approaches, backpropagation and radial basis function networks, are proposed. The results from these two neural network approaches are compared with that from the linear and non-linear regression models. The neural networks provide a better estimation of the parameters for the abrasive water jet machining process.     

Mathematical modelling of burr height of the drilling process using a statistical-based multi-gene genetic programming approach

Drilling is one of the important machining processes performed extensively in production industry. Literature emphasises that the output process parameters such as burr height, surface roughness, strength, etc. are related to and can be improved by the appropriate settings of the input process parameters. Recently, researchers have applied well-known computational intelligence methods such as regression analysis, artificial neural networks (ANNs), support vector regression (SVR), etc. in the prediction of performance characteristics of the drilling process. Alternatively, an evolutionary approach of multi-gene genetic programming (MGGP) that evolves the model structure and its coefficients automatically can be applied. Despite of being widely applied, MGGP has the limitation for producing models that over-fit on the testing data. One of the reasons attributed for this behaviour is the over-size of the evolved models. Therefore, a statistical-based MGGP (S-MGGP) approach is proposed and applied to the burr height data obtained from the drilling of AISI 316L stainless steel. In this proposed approach, Bayesian information criterion is embedded in its paradigm, which punishes the fitness of larger size models. The performance of S-MGGP and ANN models is found to be better than those of the standardised MGGP and SVR. Further, the parametric and sensitivity analysis conducted validates the robustness of our proposed model and is proved to capture the dynamics of the drilling phenomenon by unveiling dominant input process parameters and the hidden non-linear relationships.     

Application of soft computing techniques in machining performance prediction and optimization: a literature review

Machining is one of the most important and widely used manufacturing processes. Due to complexity and uncertainty of the machining processes, of late, soft computing techniques are being preferred to physics-based models for predicting the performance of the machining processes and optimizing them. Major soft computing tools applied for this purpose are neural networks, fuzzy sets, genetic algorithms, simulated annealing, ant colony optimization, and particle swarm optimization. The present paper reviews the application of these tools to four machining processes—turning, milling, drilling, and grinding. The paper highlights the progress made in this area and discusses the issues that need to be addressed.     

Selection of machining parameters for constrained machining problem using evolutionary computation

In this paper, the optimization of cutting parameters for constrained machining operations is reported. Modified genetic algorithm (MGA) is an evolutionary computation technique that has been proposed in this paper to solve the machining problem. Additional constraints have been incorporated to the multipass turning model. The optimization of drilling and facing parameters have also been carried out. To demonstrate the procedure and performance of the approach, an illustrative example is discussed. The results of the proposed algorithm are compared with other traditional and non-traditional techniques such as Newton’s method, hill climbing and ants colony technique.     

Application of artificial neural network and optimization algorithms for optimizing surface roughness, tool life and cutting forces in turning operation

Our goal is to propose a useful and effective method to determine optimal machining parameters in order to minimize surface roughness, resultant cutting forces and maximize tool life in the turning process. At first, three separate neural networks were used to estimate outputs of the process by varying input machining parameters. Then, these networks were used as optimization objective functions. Moreover, the proposed algorithm, namely, GA and PSO were utilized to optimize each of the outputs, while the other outputs would also be kept in the suitable range. The obtained results showed that by using trained neural networks with genetic algorithms as optimization objective functions, a powerful model would be obtained with high accuracy to analyze the effect of each parameter on the output(s) and optimally estimate machining conditions to reach minimum machining outputs.     

Characterisation of the workpiece dilatation phenomenon during machining using the neural network method. Application to NC turning

Dilatation of workpieces during machining is a major source of defects. With the current trend for re-treatment of cutting and cleaning fluids becoming compulsory, lubrication by a stream of oil and dry machining are becoming more widely used in aluminium alloy machining. Indeed, this makes it easier to recycle chippings and greatly simplifies the cleaning and grease removal phases for workpieces that are compulsory before any finishing surface treatment. However, the workpiece’s deformation during machining must be taken into account. This is especially true for NC turning of machining diameters with very tight tolerances. Here we propose a method based on the use of a neural network intended to model changes in the workpiece’s dimensions to correct tool paths. This study covered machining of workpieces made of 2017 T4 aluminium alloy during the turning phase. We first conducted preliminary tests on a workpiece to highlight workpiece dilatation. We then implemented a neural network to predict this deformation to be able to compensate for it. The results of a first test campaign gave us knowledge of the network then a second test campaign was used to validate that network. To finish off, we machined a test workpiece in order to test and analyse network performance.     

Prediction and analysis of surface roughness characteristics of a non-ferrous material using ANN in CNC turning

Surface roughness, an indicator of surface quality is one of the most-specified customer requirements in a machining process. For efficient use of machine tools, optimum cutting parameters (speed, feed, and depth of cut) are required. So it is necessary to find a suitable optimization method which can find optimum values of cutting parameters for minimizing surface roughness. The turning process parameter optimization is highly constrained and non-linear. In this work, machining process has been carried out on brass C26000 material in dry cutting condition in a CNC turning machine and surface roughness has been measured using surface roughness tester. To predict the surface roughness, an artificial neural network (ANN) model has been designed through feed-forward back-propagation network using Matlab (2009a) software for the data obtained. Comparison of the experimental data and ANN results show that there is no significant difference and ANN has been used confidently. The results obtained conclude that ANN is reliable and accurate for predicting the values. The actual R _a value has been obtained as 1.1999???m and the corresponding predicted surface roughness value is 1.1859???m, which implies greater accuracy.     

Vibration analysis of drilling machine using proposed artificial neural network predictors

Small tolerances are very important factors for drilling machines. Due to the mechanical friction on their moving parts, it is necessary to predict vibration effects. This investigation is focused on design of robust neural network predictors for analyzing vibration effects on moving parts of drilling machines. The research is divided into two parts; the first part is experimental investigation, the second part is simulation analysis with neural networks. Therefore, a real time drilling machine is used for vibrations under working conditions. The measured real vibration parameters are analyzed with neural network. As a result, simulation approaches show that radial basis neural network has superior performance to adapt real time parameters of drilling machines.     

Real-Time Prediction of Workpiece Errors for a CNC Turning Centre, Part 2. Modelling and Estimation of Thermally Induced Errors

Real-time modelling and estimation of thermally induced error have very important contributions for precision machining. In this paper, a novel radial basis function (RBF) neural network, which combines a regression tree and a radial basis function, has been considered and selected to model the thermally induced errors of CNC turning centres. Then, a simple and low-cost compact measurement system is applied to measure the time variant thermal errors of CNC turning centres. The thermally induced errors are estimated in real-time using the trained RBF neural network. The application of the measurement system and the novel RBF neural network are described in detail in this paper. The proposed approach is verified through some tests under different cutting conditions.     

MULTI-OBJECTIVE OPTIMIZATION OF ABRASIVE FLOW MACHINING PROCESSES USING POLYNOMIAL NEURAL NETWORKS AND GENETIC ALGORITHMS

Abrasive flow machining (AFM) is an economic and effective non-traditional machining technique, which is capable of providing excellent surface finish on difficult to approach regions on a wide range of components. With this method, it has become possible to substitute various time-consuming deburring and polishing operations that had often lead to non-reproducible results. In this paper, group method of data handling (GMDH)-type neural networks and Genetic algorithms (GAs) are first used for modelling of the effects of number of cycles and abrasive concentration on both material removal and surface finish, using some experimentally obtained training and testing data for brass and aluminum. Using such polynomial neural network models obtained, multi-objective GAs (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are then used for Pareto-based optimization of AFM considering two conflicting objectives such as material removal and surface finish. It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of AFM can be discovered by the Pareto-based multi-objective optimization of the obtained polynomial models. Such important optimal principles would not have been obtained without the use of both GMDH-type neural network modelling and multi-objective Pareto optimization approach.     

MULTI-OBJECTIVE OPTIMIZATION OF ABRASIVE FLOW MACHINING PROCESSES USING POLYNOMIAL NEURAL NETWORKS AND GENETIC ALGORITHMS

Abrasive flow machining (AFM) is an economic and effective non-traditional machining technique, which is capable of providing excellent surface finish on difficult to approach regions on a wide range of components. With this method, it has become possible to substitute various time-consuming deburring and polishing operations that had often lead to non-reproducible results. In this paper, group method of data handling (GMDH)-type neural networks and Genetic algorithms (GAs) are first used for modelling of the effects of number of cycles and abrasive concentration on both material removal and surface finish, using some experimentally obtained training and testing data for brass and aluminum. Using such polynomial neural network models obtained, multi-objective GAs (non-dominated sorting genetic algorithm, NSGA-II) with a new diversity preserving mechanism are then used for Pareto-based optimization of AFM considering two conflicting objectives such as material removal and surface finish. It is shown that some interesting and important relationships as useful optimal design principles involved in the performance of AFM can be discovered by the Pareto-based multi-objective optimization of the obtained polynomial models. Such important optimal principles would not have been obtained without the use of both GMDH-type neural network modelling and multi-objective Pareto optimization approach.