Surface Roughness Prediction Model Research Articles

Optimization method for rough-finish milling allowance based on depth control of milling affected layer

The optimization of machining allowance has an important influence on the machining quality of workpieces. This paper determined an optimization method for rough-finish milling allowance based on depth control of milling affected layer. Firstly, the coupling influence of rough-finish milling cutting depth on milling affected layer depth was studied by experiment. Secondly, the influence rule of rough milling and finish milling on the affected layer depth was studied by experiment, and the prediction model of the milling affected layer depth based on the cutting depth of rough milling and finish milling was established, as well as the surface roughness prediction model of the finish milling cutting depth. Finally, the effectiveness of the optimization results was verified by experiments. The experimental results show the optimized machining parameters can increase the machining efficiency by 31.2%, and the milling affected layer is 91 μm, which indicates that the depth of milling affected layer is effectively controlled.

Knowledge-based neural network for surface roughness prediction of ball-end milling

Theoretical modeling for surface roughness of ball-end milling generally results in low prediction accuracy due to the lack of machining information, excessive computational costs, and uncertainty of manual adjustment parameters. Besides, data-driven methods are limited in practical applications due to the lack of theoretical support or ‘black-box problems’ of neural network. To deal with these problems as mentioned above, this paper presents a coupling model for surface roughness prediction by combining the theoretical model of surface roughness and the data-driven approach. The core process is the secondary modeling with regard to the predictive result of theoretical model, which is realized by utilizing the knowledge-based neural networks with radial basis functions (KBaNN_RBF). Firstly, a theoretical model is established for the surface roughness prediction of ball-end milling by using the tool parameters and machining parameters. The output of the theoretical model is embedded into KBaNN_RBF as a priori knowledge. Secondly, low-dimensional features are extracted from the monitoring signals and adopted as the input of KBaNN_RBF for secondary modeling. And, the network structure is optimized by utilizing particle swarm optimization (PSO). Finally, ball-end milling experiment is carried out to verify the effectiveness of the presented KBaNN_RBF. Experimental results show that KBaNN_RBF is highly effective in improving the prediction accuracy and compressing the confidence interval (CI). Moreover, the comparison results show that the effectiveness of KBaNN_RBF is far superior to the traditional methods, such as back propagation neural network (BPNN) and support vector machine (SVM). This paper provides theoretical guidance for accurate monitoring of surface roughness in real industrial settings.

A new theoretical model for surface roughness prediction in rotational abrasive finishing process

Rotational abrasive finishing (RAF) is a new nano-finishing technique in which the finishing forces are applied to the workpiece by the opposite rotations of a stirring-blades and the workpiece. The RAF process allows for finishing the inner and outer surfaces of workpieces, particularly complex ones with axial symmetry. The present study aims to propose a new theoretical model to obtain deeper insights into the material removal mechanism, surface roughness prediction, and forces in RAF process. Since the abrasive-workpiece interaction is random and complex in nature in the RAF, some initial assumptions were considered. To validate the repeatability of the experimental results, the experiments were designed based on the Response surface method (RSM). To validate the new proposed theoretical model, a number of influential parameters were investigated. It was found that the stirring-blade speed (S), working gap (W), and abrasive grain size (A) had significant effects on Ra. The minimum surface roughness (Ra) was obtained to be 46.87 nm at a rotational speed of 600 rpm, a working gap of 1 mm, and grain size of 18 μm. The experimental results were relatively in good agreement with the theoretical results so that the maximum error was about 24%. This can be assumed that the most important explanation for the difference between the theoretical and experimental results can be attributed to the initial theoretical assumptions.

Predictive model of surface roughness in milling of 7075Al based on chatter stability analysis and back propagation neural network

Predictive model of surface roughness in milling of 7075Al based on chatter stability analysis and back propagation neural network

Predictive modeling of surface roughness in hard turning with rotary cutting tool based on multiple regression analysis, artificial neural network, and genetic programing methods

This present paper deals with the results of setting up and evaluating the quality of surface roughness (SR) prediction models through hard turning with self-driven rotary cutting tools for 40X steel shaft with hardness 45HRC. The cutting parameters are considered to establish the SR prediction model include angle tilt of cutting tool axis, depth of cut, feed rate, and cutting speed. The predictive models (PM) are established utilizing Multi-variables Regression Analysis (MRA), Artificial Neural Network (ANN), and Genetic Programming (GP) methods. In this regard, four MRA, four ANN, and three GP structures are considered to select the most suitable model. The criteria to estimate the PM quality include Coefficient of Determination ( R2), Mean Square Error (MSE), and Mean Absolute Percent Error (MAPE). Whereby, two data sets were collected to construct regression models (RM) and to serve verification. That dataset was originated from 63 experiments (Ep) including 54 Ep for establishing PM and 9 extensive experiments (EEp) for testing PM. The prediction criteria of the MRA3 model gave the best results in four MRA models with R2 of 0.99, MSE of 0.042, and MAPE of 8.087%. The ANN1 gives the most reliable assessment criteria in four ANN models and the GP3 model gave the best in three GP models. The results of predicting the SR value between the selected MRA and ANN and GP models will be assessed in detail. Accordingly, the evaluation criteria of the ANN1 model are the best with the smallest MSE (0.032) and MAPE (7.207%). The MRA3 and GP3 have a lower confidence predictive criteria value than the ANN1 model.

Milling mechanism and surface roughness prediction model in ultrasonic vibration-assisted side milling of Ti–6Al–4 V

Milling mechanism and surface roughness prediction model in ultrasonic vibration-assisted side milling of Ti–6Al–4 V

Modelling and optimization of surface roughness in chemical mechanical polishing based on DNN-GA

The surface quality of Lithium Niobate (LiNbO3) has a significant influence on photonics and optoelectronics components. However, the prediction and optimization models of surface roughness were not accurate due to the random parameters. Hence, a prediction model of surface roughness is established based on an improved neural network, and a new method is proposed to optimize the arguments in chemical mechanical polishing (CMP) process. In the model, the structure of the neural network is optimized according to data features rather than choosing networks randomly. To improve the model accuracy, the optimal number of hidden layers is 4 and the corresponding amounts of nodes in each layer are 46, 34, 28, and 33, respectively. ReLU function is chosen as activation function. Subsequently, the relationship between surface roughness and processing parameters is built and the variation process of surface roughness is particularly considered. The accuracy and generalization ability of the model is verified by the experiments with the Mean Absolute Percentage Error (MAPE) of 6.42% and Root Mean Square Error (RMSE) of 0.403. Furthermore, the Genetic Algorithm (GA) method based on the selected model is applied to optimize processing arguments under the target surface roughness value of 0.3 nm. The accuracy of the fusion model is also validated by experiments with an error of 13.3%.

Research on surface roughness prediction in turning Inconel 718 based on Gaussian process regression

Nickel-based alloy Inconel 718 is widely used in aircraft engine industry because of its good mechanical properties. Inconel 718 is a typical difficult-to-machine material and its price is relatively expensive. Therefore, accurate prediction of Inconel 718 machined surface roughness with small sample space can improve machining efficiency, optimize process parameters and reduce machining cost. In this paper, a method is proposed to characterize the influence of cutting parameters on roughness by stablishing the corresponding relationship between the proportional hyperparameters in the multivariate kernel function and the cutting speed, cutting deep, feed rate and the rake angle of the tool. A multi input single output (MISO) multivariate Gaussian process regression (GPR) surface roughness prediction model with cutting speed, cutting depth, feed rate and tool rake angle as input variables and surface roughness as output variables is established. The model can not only output the predicted value of surface roughness, but also give the reliability of the predicted value. Experimental results show that the proportional hyperparameter has an independent adjustment function, and the influence of the process parameters characterized by the proportional hyperparameter on the surface roughness is consistent with the experimental results. The experimental results show that the average relative error of MISO multivariate GPR surface roughness prediction model proposed in this paper is 1.5%, which can accurately predict the surface roughness in small sample space.

Research on prediction method of surface roughness in weak magnetorheological shear thickening fluid polishing

A joint prediction method of “mathematical modeling and finite element calculation” is proposed to improve the prediction of machining quality in weak magnetorheological shear thickening fluid polishing of complex surfaces. The study proceeded in several steps. First, based on both impact energy model and material removal model, a numerical prediction model of surface roughness is established. Second, based on the multi-peak fitting method, the field-induced rheological properties of the polishing fluid are characterized and material properties of the flow field medium in the polishing zone are defined. Third, the numerical boundaries of polishing flow velocity and shear stress in the above prediction model are obtained. Fourth, the polishing experiments with parameters consistent with the above simulation model are conducted, and the initial surface roughness values are substituted into the above prediction model. The results show that the joint prediction method can effectively predict the machining quality of workpiece surface. The absolute error of Sa value of surface roughness is up to 10.6 nm, and the maximum relative error is 12.3%.

Surface roughness prediction for turning based on the corrected subsection theoretical model

To obtain an accurate prediction model of surface roughness on the premise of low experimental cost in precision machining processes, this paper proposes two error correction models of the subsection theoretical model of arithmetic mean height roughness (Ra) in turning. The prediction performance of the two error correction models was evaluated by 25 groups of turning data of AISI1045 steel. The determination coefficient (R2) of the 10 random runs of the two correction models are both above 0.9, the mean squared error (MSE) is lower than 0.05, and the standard deviations (StdDev) of R2 and MSE are 0.01. The experimental results show that the two error correction models significantly improve the prediction accuracy and stability of the subsection theoretical model. Moreover, the influence of turning parameters and tool geometry on Ra based on the two correction models and the subsection theoretical model as well as the advantages and disadvantages of the three models is analysed, which provide an effective guidance for the selection of parameters and the prediction model in actual machining.

Experimental investigations and modeling for multi-pass laser micro-milling by soft computing-physics informed machine learning on PMMA sheet using CO2 laser

Laser micro-machining has gained significant attraction from industries and researchers due to the wide range of processability and material flexibility with micro-scale accuracy. However, only a few process variables and soft computing approaches are taken into consideration in micro-scale sectors. This provides the opportunity to explore a new and relatively unexplored area of physics-informed advanced soft computing techniques for laser beam machining. This study aims to develop a framework to investigate the micro-milling capabilities of 10 mm thick poly-methyl-methacrylate (PMMA) using various input parameters such as laser power (8–16 W), scanning speed (25–50 mm/s), number of passes (2–6), and incident energy (0.107–0.64 J/mm). A soft computing technique to build depth, width and surface roughness prediction models on a CO2 laser machine, is presented. Advanced soft computing approaches such as random forest, gradient boost, ridge regression, linear regression, support vector regression and gaussian process regression are evaluated to predict the microchannel's depth, surface roughness, and kerf width. The proposed work is validated experimentally and compared with the different prediction/regression models available in the literature. The values of hyper tuning parameters are optimized using by grid search method. Based on the 5-fold cross-validation analysis, the most accurate predictions of the depth, surface roughness and kerf width could be achieved through the gaussian process regression (GPR) model with highest accuracy of 98.34 %, 97.68 % and 96.38 % for depth, surface roughness and kerf width respectively.

A physics-informed machine learning model for surface roughness prediction in milling operations

A physics-informed machine learning model for surface roughness prediction in milling operations

Effect of Ball Burnishing Pressure on Surface Roughness by Low Plasticity Burnishing Inconel 718 Pre-Turned Surface.

The low plasticity burnished surface roughness is significantly affected by the low plasticity burnishing (LPB) parameters. This research proposed the analytical prediction model to predict the LPBed surface roughness and optimal LPB pressure based on Hertz contact mechanics and the slip-line field theory. In this study, the surface formatted process was divided into the smoothing stage (SS) and the indentation stage (IS). The smoothing mechanism of SS and the deterioration mechanism of IS were analyzed theoretically. The analytical prediction model for the LPBed surface roughness was proposed based on Hertz contact mechanics and slip-line field theory. The proposed analytical prediction model was validated by the LPBed surface roughness of AISI 1042, and the error of the analytically predicted results was less than 13.3%. After validation, the proposed model was applied to predict the LPBed surface roughness of Inconel 718. The single-factor experiments were conducted. The error between the proposed model prediction results and experimental results was less than 7% for the LPBed surface roughness of Inconel 718. The optimal LPB pressure interval was calculated to be [12.2 MPa, 17.5 MPa], corresponding to the experimental one as [12 MPa, 18 MPa]. It indicated that the proposed model could accurately predict the LPBed surface roughness and conduct the LPB processing.

Application of Combined Prediction Model in Surface Roughness Prediction

In order to improve the stability work piece surface roughness prediction model after machining, LM algorithm, least squares algorithm and proportional conjugate gradient algorithm are used to build the prediction model of the cutting process of AL-7075 aluminum alloy. Two error analysis methods are used to compare the combination model with other single models. The study found that the forecasting model is more accurate and stable than the single forecasting model, and closer to the actual measurement results. The combination model provides a new way to predict the surface roughness of the work piece after machining and provides a theoretical basis for selecting the three main factors of machining.

Prediction of Surface Roughness of U71Mn Steel Milling Based on RBF Neural Network

In order to predict the surface roughness of U71Mn high manganese steel before actual milling operation, an orthogonal experiment was designed. Based on the intelligent algorithm of Radial Basis Functions (RBF) neural network, an accurate prediction model of surface roughness is done with MATLAB. By comparing the predicted data of RBF neural network model with the actual measured data, it is proven that the model is accurate and effective.

Prediction of Surface Roughness in Gas-Solid Two-Phase Abrasive Flow Machining Based on Multivariate Linear Equation.

The main purpose of this study is to explore a surface roughness prediction model of Gas-Solid Two-Phase Abrasive Flow Machining. In order to achieve the above purpose, an orthogonal experiment was carried out. Q235 steel as processing material and white corundum with different particle sizes as abrasive particles were used in the experiment. Shape and spindle speed were the main reference factors. The range method and factor trend graph are used to comprehensively analyze the experimental results of different processing stages of the detection point, and the optimal parameter combination of A3B2C1D2 was obtained. According to the experimental results, a multiple linear regression equation was established to predict the surface roughness, and the experimental results were solved and significantly analyzed by software to obtain a highly reliable prediction model. Through experiments, modeling and verification, it is known that the maximum error between the obtained model and the actual value is 0.339 μm and the average error is 0.00844 μm, which can better predict the surface roughness of the gas-solid two-phase flow abrasive pool.

Prediction model of surface roughness of selective laser melting formed parts based on back propagation neural network

AbstractIn this article, selective laser melting (SLM) equipment is used to print 316L stainless steel parts under different process parameters, and the surface roughness of the parts is measured. Based on back propagation neural networks (BP neural networks, BPNN), the upper surface roughness prediction model is established. The laser power, scanning speed, and scanning interval are used as model input, and the surface roughness of the workpiece is output. This model can easily and quickly predict the surface roughness of SLM metal printing, with high prediction accuracy, and can provide a basis for the optimization of SLM process parameters.

Surface roughness prediction model in high-speed dry milling CFRP considering carbon fiber distribution

The surface roughness of carbon fiber-reinforced polymer (CFRP) components is extremely important because of the increasing demand for higher performance, reliability, and longer lifetime in aerospace and other manufacturing industries. However, the cutting mechanisms of CFRP are still unclear, which limits its formation mechanism prediction for surface roughness. Thus far, this study presents three action mechanisms in the CFRP machining process: accumulation bouncing on the matrix, impact effect on carbon fibers, and workpiece self-action. The workpiece self-action was reflected and calculated using the light rope model, which is new in CFRP machining. Furthermore, the formation mechanisms of surface roughness were first elucidated in the high-speed dry (HSD) milling of CFRP. An accurate surface roughness prediction model was theoretically formulated considering the kinematics, dynamics, and carbon fiber distribution. Surface roughness was expressed as the three-dimensional arithmetic mean height. The surface roughness prediction model was established and confirmed to have a high prediction accuracy of 90.05%, demonstrating that the distribution of carbon fibers was the main influencing factor of the surface roughness. Moreover, nonlinear regression analysis was used to clarify the effects of cutting parameters on the surface roughness, impact effect, and relationship between the surface roughness and impact effect. The study verified the feasibility of HSD milling CFRP, and it also provided guidance for breaking the low-speed machining limits by improving the machining process.

Prediction of Surface Roughness of SLM Built Parts after Finishing Processes Using an Artificial Neural Network

A known problem of additive manufactured parts is their poor surface quality, which influences product performance. There are different surface treatments to improve surface quality: blasting is commonly employed to improve mechanical properties and reduce surface roughness, and electropolishing to clean shot peened surfaces and improve the surface roughness. However, the final surface roughness is conditioned by multiple parameters related to these techniques. This paper presents a prediction model of surface roughness (Ra) using an Artificial Neural Network considering two parameters of the SLM manufacturing process and seven blasting and electropolishing processes. This model is proven to be in agreement with 429 experimental results. Moreover, this model is then used to find the optimal conditions to be applied during the blasting and the electropolishing in order to improve the surface roughness by roughly 60%.

Optimization of High-speed Dry Milling Process Parameters Based on Improved ELM and Genetic Algorithm

High-speed dry grinding has the characteristics of high processing efficiency and clean environment. The high-speed dry grinding method meets the requirements of the green and efficient development of the national manufacturing industry. However, inappropriate cutting parameters seriously affect the surface quality of the workpiece and cause the workpiece to be scrapped. Therefore, this paper proposed an optimization method based on the combination of the improved extreme learning machine neural network (ELM) for high-speed dry milling surface roughness prediction model and genetic algorithm (GA). The Taguchi orthogonal experiment results show that the surface roughness of high-speed dry milling can be accurately predicted by the improved ELM and thereafter the optimal cutting parameter combination can be determined by GA.