Prediction of surface roughness in CNC turning by model-assisted response surface method

Misaka, Takashi; Herwan, Jonny; Ryabov, Oleg; Kano, Seisuke; Sawada, Hiroyuki; Kasashima, Nagayoshi; Furukawa, Yoshiyuki

doi:10.1016/j.precisioneng.2019.12.004

Cited by 44 publications

(11 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Many machining parameter optimization studies have employed Kriging method to build surrogate models. Misaka et al [30] utilized Kriging model to successfully predict roughness in the turning process of titanium alloy, with a cutting tool of carbide. Leball et al [31] displayed that Kriging is effective when being applied on prediction of material removal rate (MRR) and tool life(TL) regarding titanium alloy milled by a carbide tool process.…”

Section: Kriging Modelmentioning

confidence: 99%

Corner-milling process parameter optimization regarding H62 brass using Kriging model and improved particle swarm optimization algorithm

Meng

Wang

Liao

et al. 2020

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

Single-pass corner milling is common in machining process. Machining quality and cost are the two most important goals for machining process. Machining quality is greatly affected by deformation and mechanical property. Cutting temperature has a very important effect on tool wear, mechanical property, deformation and machining precision. In this paper, cost per volume (CPV) and machining temperature are selected as objectives. To reduce the cost of research, AdvantEdge simulation software was used to simulating the machining process and examined for its accuracy. Comparing the result of AdvantEdge with physical experiments, it showed an average 8% error on CPV and a 6% error on temperature. Given this comparison, simulation data were used to train Kriging model as the surrogate model. Kriging model manifested high accuracy, showing mean error of 6% and 3% in terms of CPV and temperature on validation points. To solve the multi-objective problem, a K-means particle swarm optimization (PSO) was constructed, which outperformed traditional adaptive gird algor (AGA) by finding the better optimal solutions, meanwhile consuming lesser time. Optimization result showed that corner milling should have a low-level spindle speed to ensure low cost and low temperature. High feed rate, cutting depth and cutting width will result in low cost along with high temperature. Optimal parameters should be chosen from Pareto set according to different practical needs. This integrated method manifested its applicability in solving multi-objective problems.

show abstract

Section: Kriging Modelmentioning

confidence: 99%

Corner-milling process parameter optimization regarding H62 brass using Kriging model and improved particle swarm optimization algorithm

Meng

Wang

Liao

et al. 2020

J Braz. Soc. Mech. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…3,4 Many influencing factors, such as cutting parameters, cutting forces, workpiece materials, tool parameters, and the vibration between the workpiece and tool, should be considered in the 3D surface topography prediction model. 5,6 According to the research status of surface topography prediction, there are three methods: artificial intelligence, 1,4,[7][8][9] experimental methods, [10][11][12][13][14][15][16] and theoretical analysis methods. 17,18 The advantages and disadvantages of the three methods are apparent.…”

Section: Introductionmentioning

confidence: 99%

Investigation on the surface roughness modeling and analysis for ultra-precision diamond turning processes constrained by the complex multisource factors

Yang

Sun

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part B:

View full text Add to dashboard Cite

Ultra-precision machining is widely used in the manufacturing of national defense and sophisticated civil products because of its high precision, nearly no surface damage and other advantages. The surface roughness of a workpiece is the key indicator of ultraprecision machining technology, which is affected by many factors in the process of machining. However, the existing surface roughness prediction model only considers a single error factor between the tool and workpiece, lacking comprehensive consideration of multisource error factors. Therefore, based on the research of the single error factor, multisource errors that affect the surface roughness of a workpiece in machining was investigated in this paper. A prediction model of workpiece surface roughness under multisource error affecting was established to improve the accuracy of prediction models. According to the vibration model, the sensitive direction of roughness can be determined. In the axial direction, the error of each point on the surface is superimposed with the theoretical surface shape to obtain the final surface profile. The three-dimensional morphology was established and the two-dimensional topography can be obtained by intercepting the three-dimensional topography. The roughness simulation value is obtained by extracting the peak value of each point of the two-dimensional topography. A single-point diamond turning experiment is performed to verify the simulation models. The result concluded from the experiment is compared with the simulation result, showing that the error between the simulation and the experiment is less than 4%, which is of great significance to optimizing machining process parameters and improving machining precision of workpiece surfaces for ultraprecision single point diamond turning.

show abstract

“…Through simulation and experiments, the authors show that the model can well predict target values. Misaka et al [17] proposed a machining surface quality prediction model based on the Co-Kriging method. They proved through experiments that the developed model achieves a satisfactory prediction accuracy only when the amount of data is small.…”

Section: Introductionmentioning

confidence: 99%

An Effective PSO-LSSVM-Based Approach for Surface Roughness Prediction in High-Speed Precision Milling

Tian

2021

IEEE Access

View full text Add to dashboard Cite

Surface roughness is one of the important indicators to measure the surface quality of parts processed, in addition to the cutting parameters affecting the surface roughness, the inevitable tool wear during the cutting process also makes the surface roughness constantly changing. In order to achieve highprecision prediction of machined surface roughness, a high-speed precision milling surface roughness prediction method based on particle swarm optimization least squares support vector machine (PSO-LSSVM) is proposed in this paper. The prediction method uses standardized cutting parameters and tool wear as the input variables, and uses the LSSVM algorithm to model the relationship between the input variables and the surface roughness, the improved PSO algorithm is used to optimize the hyperparameters of LSSVM so as to improve the generalization ability. In order to verify the effectiveness and superiority of PSO-LSSVM predictive performance, two surface roughness prediction models have been developed based on support vector machine (SVM) and response surface method (RSM), respectively. With the same sample conditions, average relative error and root mean square error of PSO-LSSVM prediction model are the smallest, and the correlation coefficient of PSO-LSSVM method is the largest. It is indicate that the surface roughness prediction accuracy and generalization ability based on PSO-LSSVM are the best under different cutting parameters.

show abstract

Prediction of surface roughness in CNC turning by model-assisted response surface method

Cited by 44 publications

References 17 publications

Corner-milling process parameter optimization regarding H62 brass using Kriging model and improved particle swarm optimization algorithm

Corner-milling process parameter optimization regarding H62 brass using Kriging model and improved particle swarm optimization algorithm

Investigation on the surface roughness modeling and analysis for ultra-precision diamond turning processes constrained by the complex multisource factors

An Effective PSO-LSSVM-Based Approach for Surface Roughness Prediction in High-Speed Precision Milling

Contact Info

Product

Resources

About