Surface Roughness Prediction Model Research Articles

Experimental Research on the Predictive Model for Surface Roughness of Titanium Alloy in Abrasive Belt Grinding

Titanium alloys have been applied to aerospacemedical and other fields. The surface roughness of titanium alloy about these areas is very high. Based on the results of orthogonal test, belt grinding surface roughness prediction model of TC4 Titanium alloy is established using linear regression method. The significant tests of regression equation are conducted and proved that the prediction model has a significant. The results indicate that the model has reliability on the prediction of surface roughness, abrasive belt grinding pressure has certain influence on the surface roughness, and grain size of belt and the belt linear speed have high significant influence on surface roughness and the influence coefficient are-0.9378 and-0.2317. While the contact wheel hardness and workpiece axial feeding speed have no significant influence on surface roughness.

Experimental and Modeling Study of the Turning Process of PA 6/Nano Calcium Carbonate Composite

Nowadays, polymeric nanocomposites have emerged as a new material class with rapidly growing use in industrial products because of good mechanical, thermal, and physical properties. Recently, the requirement of the direct machining of these materials has increased due to the production of the most of them by extrusion method in simple cross section and the increased demand for personalized products. In this work, the effect of turning parameters (cutting speed and feed) and nano calcium carbonate content on the machinability properties of polyamide 6/nano calcium carbonate composites was investigated by analysis of variance. A novel modeling approach of modified harmony search-based neural network was also utilized to create predictive models of surface roughness and total cutting force from the experimental data. The results revealed that the nano calcium carbonate content on polyamide 6 decreased the cutting forces significantly but did not have a significant effect on surface roughness. Moreover, the results for modeling total cutting forces and surface roughness showed that modified harmony search-based neural network is effective, reliable, and authoritative in modeling the turning process of polyamide 6/nano calcium carbonate composite.

Chip load sensitive performance in micro-face milling of engineering materials

The miniaturization of machine component is perceived by many as requirement for the future technological development of a broad spectrum of products. High-accuracy miniaturized components are increasingly demanded for various industries. Micro-component fabrication requires reliable and repeatable methods, with accurate analysis tools. Surface roughness is one of the most important parameters in the machining process. This research discusses an experimental approach to the development of mathematical model for surface roughness prediction before the milling process. This mathematical model is validated by equivalence variance test, i.e., F test. This study also presents the results of test done with high-speed face milling tool. The experiments were performed to investigate the influence of chip load on surface roughness along with other cutting parameters such as cutting speed and depth of cut for different engineering materials.

Prediction of Surface Roughness on CNC Turning Based on Monitoring of Cutting Force and Cutting Temperature

This paper presents the surface roughness model which is proposed and developed to predict the surface roughness in the CNC turning of the carbon steel with the coated carbide tool under various cutting conditions by using the response surface analysis with the Box-Behnken design based on the experimental results. The in-process monitoring of the cutting force and the cutting temperature is utilized to analyze the relation between the surface roughness and the cutting condition. The tool dynamometer and the infrared pyrometer are employed and installed on the turret of CNC turning machine to measure the in-process cutting force and cutting temperature. The models of cutting force ratio and cutting temperature are also developed based on the experimental data. The optimum cutting condition is determined referring to the minimum surface roughness of the surface plot, which is obtained from the developed surface roughness model. The experimental results show that the higher cutting speed gives the better surface roughness due to the higher cutting temperature, however the tool life becomes shorter. The feed rate is the most significant factor which affects the surface roughness, while a small depth of cut helps to improve the surface roughness. The effectiveness of the surface roughness prediction model has been proved by utilizing an analysis of variance (ANOVA) at 95% confident level. Hence, the surface roughness can be predicted and obtained easily referring to the developed surface roughness model.

An investigation of the machinability of PA 6/nano-CaCO3 composite

Nowadays, polymer nanocomposites have attracted manufacturers’ attention because of their good mechanical, thermal, and physical properties. Over the past decade, the requirement of the direct machining of polymer nanocomposites has increased due to the production of most polymer nanocomposites using the extrusion method in simple cross-section and the increased demand for personalized products. In this paper, the effect of milling parameters (spindle speed and feed per tooth) and nano-CaCO3 content on the machinability properties of PA 6/nano-CaCO3 composites was studied by analyzing variance. Harmony search-based neural network (HSNN) was then utilized to create predictive models of surface roughness and total cutting forces from the experimental data. The results revealed that the nano-CaCO3 content on PA 6 decreased the cutting forces significantly, but did not have a significant effect on surface roughness. Moreover, the results for modeling total cutting forces and surface roughness showed that HSNN is effective, reliable, and authoritative in modeling the surface roughness formation and total cutting force mechanism for end-milling of PA 6/nano-CaCO3 composites.

A Prediction Model for Surface Roughness in Milling Based on Projection Pursuit Regression

A novel prediction model for surface roughness based on Projection Pursuit Regression was proposed in this paper. Based on the new model, the effects of milling parameters on surface roughness in milling can be predicted, and the predicted value of surface roughness in the whole working range can be reached with the limited test data, thus the variation law of quality of machined surface following milling parameters can be obtained. Compared with the least square support vector machine, it can be revealed that on the base of the same samples, the construction speed of this Projection Pursuit Regression is 1~2 higher in order of magnitude than that of the least square support vector machine, while the prediction errors are 40 % of the latter. Thus, the prediction model based on Projection Pursuit Regression can be established fast and be forecasted in high-precision, it is suitable for prediction of surface roughness.

Prediction Model of Surface Roughness in Lenses Precision Turning

Due to the difficulties of processing lenses with complex surface,slow tool servo is applied in the turning of lenses.An exponential model,based on the five main cutting parameters including tool nose radius,feed,depth of cut,spindle speed and discrimination angle,for surface roughness prediction of lenses is developed by means of orthogonal experiment regression analysis.Meanwhile,a prediction model of surface roughness based on least squares support vector machine(LS-SVM) with radial basis function(RBF) is constructed.And orthogonal experiment swatches are studied,crossed grid search and leave-one-out cross-validation(LOO-CV) is applied to determine the model parameters.The comparison of LS-SVM model and exponential model is also carried out.Predictive LS-SVM model is found to be capable of better predictions for surface roughness and has correlation coefficient R2of 0.998 85,the root mean square error of 10.95%,and the mean absolute percent error of 9.28%.The experimental results and prediction of LS-SVM model show that effects of tool nose radius and feed are more significant than that of depth of cut on surface roughness of lenses turning.

Research on the prediction model of micro-milling surface roughness

Surface roughness is an important performance indication for micro-milling processing. Establishing a roughness-prediction model with high-precision is helpful to select the cutting parameters for micro-milling. Two prediction models are established by response surface method (RSM) and support vector machine regression (SVM) in this paper. Four cutting parameters are involved in the models (extended length of micro-milling tool, spindle speed, feed per tooth, and cutting depth in the axial direction). The models are established for material of brass. Experiments are carried out to verify the accuracy of the models. The results show that SVM prediction model has higher prediction accuracy, predict the variation law of micro-milling surface roughness better than RSM.

A Study of Cutting Parameters Optimization in High-Speed Milling GH4169 with TiAlN Coated Carbide Tool

The orthogonal experiment is processed for high-speed milling superalloy GH4169 with TiAlN coated carbide inserts. The surface roughness prediction model based on cutting parameters is established by using the least-squares regression method. And the effect of cutting parameters on surface roughness is studied. According to the prediction model of surface roughness, a model of cutting parameters optimization by using genetic algorithm based on annealing penalty function is established for maximum material removal rate under specified surface roughness values. Obtain the optimal parameter combination when the surface roughness Ra≤0.2µm, and the experimental validation is done. These results provide the basis for improving processing efficiency of processing GH4169 and choosing parameters under specified constraint conditions.

Study of Surface Roughness in Milling Carbon Fiber Reinforced Plastics Using PCD Tool

The surface roughness of carbon fiber reinforced plastics (CFRP) has been studied at different cutting parameters by using PCD tools. The effect of cutting parameters such as cutting velocity, cutting depth, cutting width as well as feed rate on roughness are analyzed. A predictive model for surface roughness in milling was established by regression analysis method. Based on the experimental results, the regression coefficient was calculated and the significance check of the regression equation was carried out. Results show that cutting depth has a significant effect on surface roughness and the next one is cutting velocity, then it is cutting width, feed rate has a little effect under the current experimental conditions. The regression is significant for the prediction model. The parameters used in milling can be selected to improve the quality of the surface based on the model of the paper.

Investigation of Surface Roughness in Hardened GCr15 Steel Turning with Mixed Ceramic Insert

An experimental investigation was conducted to determine the effects of cutting conditions on surface roughness in finish hard turning of GCr15 steel with mixed ceramic inserts based on design of experiment. The influence of cutting speed, feed rate and nose radius on surface roughness was assessed using analysis of variance (ANOVA). The result indicated that the feed is the dominant factor on surface roughness followed by nose radius. Due to the complexity of machining process, artificial neural network (ANN) was employed to develop the predictive model of surface roughness. Simulations were done to describe the relationship between surface roughness and cutting parameters based on the proposed model.

Surface Roughness Predictive Model of UNS A97075 Aluminum Pieces Obtained by Dry Turning Tests Based on the Cutting Forces

The present work shows an experimental study for a first approach of a surface roughness predictive model of UNS A97075 aluminum pieces obtained by dry turning tests based on the cutting forces. In a first step, a design of experiments (DOE) 25 was employed to analyse the influence of the cutting parameters and type of tool on the surface roughness with the objective to find out a combination of cutting conditions that allow obtaining a range of values of surfaces roughness according to the aeronautical specifications requierements. The factors considered for this design were the feed rate, spindle speed, depth of cut, type of tool (nose radious) and machined length (zone of the workpiece where the surface roughness measurements are taken). The obtained data was analysed by means of the analysis of variance (ANOVA) method. And secondly, with the previous selected conditions selected it was developed by multiple regression a model to predict the surface roughness by measuring the cutting forces generated during the dry turning tests of aluminum alloy UNS A97075 pieces. The predictive model of surface roughness obtained includes statistical values calculated from the forces sygnal in time and frequency domains.

Effect of Workpiece Material on Surface Roughness in Ultraprecision Raster Milling

This article presents theoretical and experimental investigations into the effect of the workpiece material on surface roughness in ultraprecision raster milling (UPRM). The influence of material elastic recovery on chip thickness and surface generation in UPRM is studied. A holistic surface roughness prediction model is developed by considering the influences of cutting parameters, tool geometry and the material elastic recovery on surface generation. The experimental results show that the proposed surface roughness prediction model makes a more precise prediction by adding the elastic recovery rate as a material factor, and the presence of elastic recovery improves the surface finishing of the raster milled surface. The material effect on surface roughness decreases with the increasing of feed rate. The precipitates in the machining of aluminum alloy 6061 result in the generation of imperfection on the raster milled surface. The machining of aluminum bronze has the greatest influence on surface roughness among the three materials being cut, which is due to its high elastic recovery rate and hardness.

Application of GONNS to predict constrained optimum surface roughness in face milling of high-silicon austenitic stainless steel

Surface roughness is a technical requirement for machined products and one of the main product quality specifications. In the present research, a genetically optimized neural network system (GONNS) is proposed for prediction of constrained optimal cutting conditions in face milling of a high-silicon austenitic stainless steel (UNS J93900) in order to minimize surface roughness. In order to attain minimum operation numbers and decrease the cost of machining, an experimental scheme was arranged by using Taguchi method. The considered parameters were cutting speed, feed, depth of cut, and engagement. Cutting force components and surface roughness were measured, and then analysis of variance is performed. The results show that the feed is the dominant factor affecting the surface roughness. Backpropagation artificial neural network was utilized to create predictive models of surface roughness and cutting forces exploiting the experimental data, and the genetic algorithm was employed to find the constrained optimum of surface roughness. Finally, in order to validate the method, an experiment with the obtained optimal cutting condition was carried out, and the results were compared with the predicted value of surface roughness. The corresponding results show the capability of GONNS to predict constrained surface roughness.

Influence of cutting parameters on tool wear and surface roughness in hard turning of AISI H11 tool steel using ceramic tools

In machining of parts, surface quality is one of the most specified customer requirements. Major indication of surface quality on machined parts is surface roughness. There are various machining parameters which have an effect on the surface roughness, but these effects have not been adequately quantified. In order for manufacturers to maximize their gains from utilizing finish hard turning, accurate predictive models for surface roughness and tool wear must be constructed. This paper utilizes response surface methodology (RSM) for modeling to predict surface roughness and tool wear for variety of cutting conditions in finish hard turning. The experimental data obtained from performed experiments in finish turning of hardened AISI H-11 steel have been utilized. Decrease in feed rate and increase in cutting speed resulted in significant increase in surface quality. However, increase in cutting speed also produced relatively higher tool wear. Also depth of cut did not significantly affect the tool wear and surface roughness.

In-process prediction of surface roughness in turning of Ti–6Al–4V alloy using cutting parameters and vibration signals

In this work, an attempt has been made to use vibration signals for in-process prediction of surface roughness during turning of Ti–6Al–4V alloy. The investigation was carried out in two stages. In the first stage, only acceleration amplitude of tool vibrations in axial, radial and tangential directions were used to develop multiple regression models for prediction of surface roughness. The first and second order regression models thus developed were not found accurate enough (maximum percentage error close to 24%). In the second stage, initially a correlation analysis was performed to determine the degree of association of cutting speed, feed rate, and depth of cut and the acceleration amplitude of vibrations in axial, radial, and tangential directions with surface roughness. Subsequently, based on this analysis, feed rate and depth of cut were included as input parameters aside from the acceleration amplitude of vibrations in radial and tangential directions to develop a refined first order multiple regression model for surface roughness prediction. This model provided good prediction accuracy (maximum percentage error 7.45%) of surface roughness. Finally, an artificial neural network model was developed as it can be readily integrated into a computer integrated manufacturing environment.

Optimal Machining Parameters for Achieving the Desired Surface Roughness in Turning of Steel

Due to the widespread use of highly automated machine tools in the metal cutting industry, manufacturing requires highly reliable models and methods for the prediction of output performance in the machining process. The prediction of optimal manufacturing conditions for good surface finish and dimensional accuracy plays a very important role in process planning. In the steel turning process the tool geometry and cutting conditions determine the time and cost of production which ultimately affect the quality of the final product. In the present work, experimental investigations have been conducted to determine the effect of the tool geometry (effective tool nose radius) and metal cutting conditions (cutting speed, feed rate and depth of cut) on surface finish during the turning of EN-31 steel. First and second order mathematical models are developed in terms of machining parameters by using the response surface methodology on the basis of the experimental results. The surface roughness prediction model has been optimized to obtain the surface roughness values by using LINGO solver programs. LINGO is a mathematical modeling language which is used in linear and nonlinear optimization to formulate large problems concisely, solve them, and analyze the solution in engineering sciences, operation research etc. The LINGO solver program is global optimization software. It gives minimum values of surface roughness and their respective optimal conditions.

Integrated Monitoring of Surface Roughness and Chip Formation by Utilizing Cutting Force and Cutting Temperature

This research presents the integration of the surface roughness and chip formation monitoring by using the cutting force and the cutting temperature during the in-process turning. The surface roughness prediction model is proposed by utilizing the response surface analysis with the Box-Behnken design. The effects of cutting parameters on the cutting force and the cutting temperature are investigated. The cutting force and the cutting temperature are measured to help analyze the relation between the surface roughness and the cutting conditions. The models of the cutting force ratio and the cutting temperature are also proposed based on the experimental data. The in-process monitoring of chip formation is developed to detect the continuous chip and the broken chip by utilizing the power spectrum density of dynamic cutting force and the variance of the dynamic cutting temperature.The broken chip formation is required for the reliable turning operation. The algorithm is proposed to obtain the broken chip by changing the cutting conditions during the cutting process based on the cutting force and the cutting temperature. It has been proved by series of cutting experiments that the proposed surface roughness model can be effectively used to predict the surface roughness, and the broken chip is well identified by the proposed method.

Development of surface roughness optimisation and prediction for the process of wire electro-discharge grinding

This paper investigates the technological capabilities of a hybrid micro machining process for performing wire electro-discharge grinding (WEDG). In particular, micro wire electrical discharge machining (μWEDM) is employed in combination with a rotating submergible spindle to perform WEDG. In this research, first a machining strategy for workpiece preparation is presented. Then, the effects of different machining setup parameters on the achievable surface finish after WEDG are investigated. In particular, an experimental study was conducted to identify the most statistically significant setup parameters for performing the main cut that affect the resulting surface quality. A signal-to-noise (S/N) ratio analysis was conducted to optimise the technological parameters for performing WEDG. By modifying the discharge energy for main cuts when performing WEDG surface finish comparable to that of μWEDM can be achieved. In addition, a simple and cost-effective method for on-the-machine estimation of resulting surface roughness is proposed. Especially, by applying inductive learning a surface roughness prediction model for WEDG can be generate based on data acquired by monitoring on-line the process.

The evolutionary development of roughness prediction models

The vigorous expansion of wind energy power generation over the last decade has also entailed innovative improvements to surface roughness prediction models applied to high-torque milling operations. Artificial neural networks are the most widely used soft computing technique for the development of these prediction models. In this paper, we concentrate on the initial data transformation and its effect on the prediction of surface roughness in high-torque face milling operations. An extensive data set is generated from experiments performed under industrial conditions. The data set includes a very broad set of different parameters that influence surface roughness: cutting tool properties, machining parameters and cutting phenomena. Some of these parameters may potentially be related to the others or may only have a minor influence on the prediction model. Moreover, depending on the number of available records, the machine learning models may or may not be capable of modelling some of the underlying dependencies. Hence, the need to select an appropriate number of input signals and their matching prediction model configuration.A hybrid algorithm that combines a genetic algorithm with neural networks is proposed in this paper, in order to address the selection of relevant parameters and their appropriate transformation. The algorithm has been tested in a number of experiments performed under workshop conditions with data sets of different sizes to investigate the impact of available data on the selection of corresponding data transformation. Data set size has a direct influence on the accuracy of the prediction models for roughness modelling, but also on the use of individual parameters and transformed features. The results of the tests show significant improvements in the quality of prediction models constructed in this way. These improvements are evident when these models are compared with standard multilayer perceptrons trained with all the parameters and with data reduced through standard Principal Component Analysis practice.