scholarly journals Prediction of Surface Roughness of 304 Stainless Steel and Multi-Objective Optimization of Cutting Parameters Based on GA-GBRT

2019 ◽  
Vol 9 (18) ◽  
pp. 3684 ◽  
Author(s):  
Tao Zhou ◽  
Lin He ◽  
Jinxing Wu ◽  
Feilong Du ◽  
Zhongfei Zou
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
Stainless Steel ◽  
Surface Quality ◽  
Regression Tree ◽  
Cutting Parameters ◽  
304 Stainless Steel ◽  
Gradient Boosting ◽  
Multi Objective Optimization ◽  
Multi Objective

Establishing and controlling the prediction model of a machined surface quality is known as the basis for sustainable manufacturing. An ensemble learning algorithm—the gradient boosting regression tree—is incorporated into the surface roughness modeling. In order to address the problem of a high time cost and tendency to fall into a local optimum solution when the grid search and conjugate gradient method is adopted to obtain the super-parameters of the ensemble learning algorithm, a genetic algorithm is employed to search for the optimal super-parameters in the training process, and a genetic-gradient boosting regression tree (GA-GBRT) algorithm is developed. A fitting goodness of fit is taken as the fitness function value of the genetic algorithm and combined with k-fold cross-validation, as such, the initial model parameters of the gradient boosting regression tree are optimized. Compared to the optimized artificial neural network (ANN) and support vector regression (SVR) and combined with the cutting experiment of 304 stainless steel with a micro-groove tool, a genetic algorithm multi-objective optimization model with the highest cutting efficiency and a supreme surface quality was constructed by applying the GA-GBRT model. The response relationship reveals the non-linear interaction that occurs between the cutting parameters and the surface roughness of 304 stainless steel that is machined by the micro-groove tool. As indicated by the results obtained from the multi-objective optimization, the cutting efficiency can be enhanced by increasing the cutting speed and depth within a small range of surface quality variations. The GA-GBRT model is validated to be reliable in making a prediction of the surface roughness and optimizing the cutting parameters with turning and milling data.

scholarly journals Analysis and Multi-Objective Optimization for Reducing Energy Consumption and Improving Surface Quality during Dry Machining of 304 Stainless Steel

Materials ◽  
2020 ◽  
Vol 13 (21) ◽  
pp. 4693
Author(s):  
Feilong Du ◽  
Lin He ◽  
Haisong Huang ◽  
Tao Zhou ◽  
Jinxing Wu
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
Stainless Steel ◽  
Energy Consumption ◽  
Surface Quality ◽  
Feed Rate ◽  
Cutting Parameters ◽  
304 Stainless Steel ◽  
Multi Objective Optimization ◽  
Multi Objective

Cutting quality and production cleanliness are main aspects to be considered in the machining process, and determining the optimal cutting parameters is a significant measure to reduce energy consumption and optimize surface quality. In this paper, 304 stainless steel is adopted as the research objective. The regression models of the specific cutting energy, surface roughness, and microhardness are constructed and the inherent influence mechanism between cutting parameters and output responses are analyzed by analysis of variance (ANOVA). The desirability analysis method is introduced to perform the multi-objective optimization for low energy consumption (LEC) mode and low surface roughness (LSR) mode. Optimal combination of process parameters with composite desirability of 0.925 and 0.899 are obtained in such two modes respectively. As indicated by the results of multi-objective genetic algorithm (MOGA), genetic algorithm (GA) combined with weighted-sum-type objective function and experiment, the relative deviation values are within 10%. Moreover, the results also reveal that the feed rate is the most significant factor affecting the three responses, while the correlation of cutting depth is less noticeable. The effect of low feed rate on microhardness is primarily related to the mechanical load caused by extrusion, and the influence at high feed rate is determined by plastic deformation.

Research on Optimization of Cutting Parameters Based on Genetic Algorithm

2011 ◽  
Vol 121-126 ◽  
pp. 4640-4645 ◽  
Author(s):  
Shu Ren Zhang ◽  
Xue Guang Li ◽  
Jun Wang ◽  
Hui Wei Wang
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
Surface Quality ◽  
Bp Neural Network ◽  
Prediction Method ◽  
Cutting Parameters ◽  
Multi Objective Optimization ◽  
Experiment Data ◽  
Optimization Of Cutting Parameters ◽  
Working Efficiency

Three elements of Cutting dosages have a great effect on parts surface quality and working efficiency, the best organization of cutting three elements for parts surface quality must be found before machining, in order to surface roughness and machining cost of parts, multi-objective optimization model is established in this paper, model is solved by using genetic algorithm. Based on the BP neural network of three layers, forecasting model of surface roughness is established. According to existing experiment data and optimized cutting dosages, analysis and prediction of surface roughness is done. Machining experiment is done by using optimized data. The experiment result verifies feasibility of this optimistic method and prediction method of surface roughness.

scholarly journals Multi-Objective Optimization of Turning Operation of Stainless Steel Using a Hybrid Whale Optimization Algorithm

2020 ◽  
Vol 4 (3) ◽  
pp. 64 ◽  
Author(s):  
Mahamudul Hasan Tanvir ◽  
Afzal Hussain ◽  
M. M. Towfiqur Rahman ◽  
Sakib Ishraq ◽  
Khandoker Zishan ◽  
...  
Keyword(s):  
Surface Roughness ◽  
Stainless Steel ◽  
Optimization Algorithm ◽  
Cutting Parameters ◽  
Whale Optimization Algorithm ◽  
Multi Objective Optimization ◽  
Turning Operation ◽  
Multi Objective ◽  
Whale Optimization ◽  
Optimum Cutting

In manufacturing industries, selecting the appropriate cutting parameters is essential to improve the product quality. As a result, the applications of optimization techniques in metal cutting processes is vital for a quality product. Due to the complex nature of the machining processes, single objective optimization approaches have limitations, since several different and contradictory objectives must be simultaneously optimized. Multi-objective optimization method is introduced to find the optimum cutting parameters to avoid this dilemma. The main objective of this paper is to develop a multi-objective optimization algorithm using the hybrid Whale Optimization Algorithm (WOA). In order to perform the multi-objective optimization, grey analysis is integrated with the WOA algorithm. In this paper, Stainless Steel 304 is utilized for turning operation to study the effect of machining parameters such as cutting speed, feed rate and depth of cut on surface roughness, cutting forces, power, peak tool temperature, material removal rate and heat rate. The output parameters are obtained through series of simulations and experiments. Then by using this hybrid optimization algorithm the optimum machining conditions for turning operation is achieved by considering unit cost and quality of production. It is also found that with the change of output parameter weightage, the optimum cutting condition varies. In addition to that, the effects of different cutting parameters on surface roughness and power consumption are analysed.

scholarly journals Multi-objective optimization and analysis for laser beam cutting of stainless steel (SS304) using hybrid statistical tools GA-RSM

2021 ◽  
Vol 1201 (1) ◽  
pp. 012030
Author(s):  
A D Tura ◽  
H B Mamo ◽  
D G Desisa
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
Stainless Steel ◽  
Laser Beam ◽  
Response Surface ◽  
Focal Point ◽  
Cutting Speed ◽  
Machining Parameters ◽  
Multi Objective ◽  
The Impact

Abstract A laser beam machine is a non-traditional manufacturing technique that uses thermal energy to cut nearly all types of materials. The quality of laser cutting is significantly affected by process parameters. The purpose of this study is to use a genetic algorithm (GA) in conjunction with response surface approaches to improve surface roughness in laser beam cutting CO2 with a continuous wave of SS 304 stainless steel. The effects of the machining parameters, such as cutting speed, nitrogen gas pressure, and focal point location, were investigated quantitatively and optimized. The tests were carried out using the Taguchi L9 orthogonal mesh approach. Analysis of variance, main effect plots, and 3D surface plots were used to evaluate the impact of cutting settings on surface roughness. A multi-objective genetic algorithm in MATLAB was used to achieve a minimum surface roughness of 0.93746 μm, with the input parameters being 2028.712 mm/m cutting speed, 11.389 bar nitrogen pressure, and a focal point position of - 2.499 mm. The optimum results of each method were compared, as the results the response surface approach is less promising than the genetic algorithm method.

Multi-Objective Optimization of Magneto Rheological Abrasive Flow Nano Finishing Process on AISI Stainless Steel 316L

2020 ◽  
Vol 63 ◽  
pp. 98-111
Author(s):  
S. Kathiresan ◽  
B. Mohan
Keyword(s):  
Surface Roughness ◽  
Stainless Steel ◽  
Initial Surface ◽  
Multi Objective Optimization ◽  
Stainless Steel 316L ◽  
Volume Percentage ◽  
Multi Objective ◽  
Input Variables ◽  
Number Of Cycles ◽  
Magneto Rheological

In this experimental work, Magneto rheological abrasive flow nano finishing processes were conducted on AISI Stainless steel 316L work pieces that are widely used in medical implants. The focus of the present study is to assess the effect of input variables namely the volume percentage of iron (Fe) particles, silicon carbide (SiC) abrasive particles in the Magneto rheological abrasive fluid and number of cycles on the final surface roughness at nano level as well as the material removal rate. The volume % of Fe particles were taken as 20, 25 and 30 and the volume % of SiC particles were taken as 10, 15 and 20. The different number of cycles considered for the study is 100,200 and 300. There are 20 different set of experiments with different combinations of input variables mentioned have been carried out based on the experimental design derived through central composite design technique. The minimum surface roughness observed is 23.34 nanometer (nm) from the initial surface roughness of 1.92 micro meter (µm). Towards optimizing the input process variables, a multi objective optimization was carried out by using response surface methodology.

High-pressure jet-assisted turning of AISI 304: Experimental and multi-objective optimization approach

2017 ◽  
Vol 232 (6) ◽  
pp. 734-750 ◽  
Author(s):  
Sayed E Mirmohammadsadeghi ◽  
H Amirabadi
Keyword(s):  
Genetic Algorithm ◽  
Surface Roughness ◽  
High Pressure ◽  
Cutting Force ◽  
Process Parameters ◽  
Optimization Approach ◽  
Multi Objective Optimization ◽  
Aisi 304 ◽  
Multi Objective ◽  
304 Austenitic Stainless Steel

High-pressure jet-assisted turning is an effective method to decrease the cutting force and surface roughness. Efficiency of this process is related to application of proper jet pressure proportional to other process parameters. In this research, experiments were conducted for high-pressure jet-assisted turning in finishing AISI 304 austenitic stainless steel, based on response surface method. Against the expectations, the maximum jet pressure could not lead to the most efficient results, which means that applying high-pressure jet-assisted turning without considering optimal process parameters will diminish the improving effects of high-pressure jet assistance. For this purpose, two artificial neural networks were trained by genetic algorithm to model the surface roughness and cutting force based on the process parameters. Ultimately, nondominated sorting genetic algorithm was implemented for multi-objective optimization of process. Results demonstrated that the employed method provides an effective approach that indicates optimized range of process parameters.

Sign in / Sign up

Export Citation Format

Share Document