Multi-objective optimisation of machining process parameters using deep learning-based data-driven genetic algorithm and TOPSIS

Wu, Pengcheng; He, Yan; Li, Yufeng; He, Jingsen; Liu, Xueqian; Wang, Yulin

doi:10.1016/j.jmsy.2022.05.016

Cited by 54 publications

(16 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The results showed that a data-driven thermodynamic model based on biogas upgrading can enhance the accuracy of model prediction. Wu et al 19 proposed a deep learning-based data-driven approach to optimize process parameters, and their research found that the proposed method could efficiently and economically identify optimal process parameters. Therefore, utilizing physical experimental data to drive statistical models to obtain more accurate statistical models with fewer costs of 3D printing experiments seems to be a promising solution.…”

Section: Introductionmentioning

confidence: 99%

“…The results showed that a data‐driven thermodynamic model based on biogas upgrading can enhance the accuracy of model prediction. Wu et al 19 . proposed a deep learning‐based data‐driven approach to optimize process parameters, and their research found that the proposed method could efficiently and economically identify optimal process parameters.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Multi‐objective Bayesian modeling and optimization of 3D printing process via experimental data‐driven method

Ding,

Wang,

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

The instability of product quality and low printing efficiency are the main obstacles to the widespread application of 3D printing in the manufacturing industry. Optimizing printing parameters can substantially improve product quality and printing efficiency. However, existing methods for optimizing process parameters primarily rely on computationally expensive numerical simulations or costly physical experiments, which cannot balance model accuracy and experiment cost. To the best of our knowledge, almost no relevant papers have been found to address the issues of product quality and printing efficiency in 3D printing from experimental data‐driven perspective. In this paper, we propose a method that integrates multiobjective Bayesian optimization (MOBO) with experimental data‐driven, aiming at obtaining more accurate optimization results at a lower cost. Distinguishing from previous studies, the proposed method utilizes experimental data instead of predicted values to update the model and find the optimal process parameters based on expected hypervolume improvement. The results of the 3D printing case study show that the proposed method can better model and optimize the highly fluctuating 3D printing process and obtain the optimal process parameters at a much lower cost. In addition, confirmatory experiments verify that the proposed method achieves higher printing efficiency while maintaining product quality.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Multi‐objective Bayesian modeling and optimization of 3D printing process via experimental data‐driven method

Ding,

Wang,

et al. 2024

Quality & Reliability Eng

View full text Add to dashboard Cite

show abstract

“…However, for the marine predator algorithm, although it has excellent characteristics such as being derivative-free, having fewer parameters, and being flexible and simple, it also suffers from poor convergence, easy entrapment in local optimal solutions, and other shortcomings, requiring further research. Wu et al [12], developed data-driven prediction functions for different optimization objectives based on artificial intelligence and transformed the developed optimization objective prediction functions into surrogate models. They then used TOPSIS to find the best processing parameters from the generated Pareto set.…”

Section: Introductionmentioning

confidence: 99%

Multi-stage manufacturing process parameter optimization method based on improved marine predator algorithm

Jiang,

Zhan,

et al. 2024

Eng. Res. Express

View full text Add to dashboard Cite

Product quality is crucial in manufacturing, and process parameters are key factors influencing product dimensions, performance, and other indicators. However, the current production processes face challenges such as complex mechanisms, mutual influences among multiple stages, and difficulties in optimizing process parameters. In response to these issues, this paper proposes a multi-stage manufacturing process parameter optimization method based on an improved marine predator algorithm. To address the modeling difficulties arising from the strong coupling of multiple stages in the manufacturing process, a multi-stage modeling strategy is employed. The method utilizes a multi-gene genetic programming (MGGP) approach to explore the nonlinear relationships between process parameters and quality indicators, establishing a multi-stage parameter optimization objective model. To enhance the efficiency of solving the optimization objective model, an improved marine predator algorithm (QNMPA) is introduced. This algorithm utilizes a reverse learning strategy and hybrid control parameters to improve optimization capabilities, aiming to achieve global optimal solutions. Using the rubber extrusion process in a specific factory as an example, the proposed method is validated to effectively address challenges in multi-stage process parameter optimization and improve the stability of product quality.

show abstract

“…Also, the desirability function approach is among the multi-objective optimization methods extensively used in many industrial sectors because of the advantages it presents [21][22][23][24][25][26][27][28]. Several researchers have adopted the GRA method as a multi-objective optimization method for cutting conditions due to its effectiveness in making the right decision for selecting the optimal parameters [29][30][31][32][33][34][35].…”

Section: Introductionmentioning

confidence: 99%

Statistical analysis, modeling and multi-objective optimization of parameters intermittent turning process of AISI D3

Khelfaoui

Yallese

Ouelaa

et al. 2023

JMES

View full text Add to dashboard Cite

Intermittent machining is characterized by its complex and irregular context. This intermittency causes machining to occur under difficult conditions that greatly influence the technological performance parameters. The aim of the present work is to evaluate the effects of input parameters, cutting speed, Vc, depth of cut, ap, tool nose radius, r and feed rate, f, on surface roughness, Ra, tangential cutting force, Fz, motor power consumption, Pm, cutting power, Pc and material removal rate (MRR), during intermittent turning (IT) of AISI D3 tool steel. Machining was performed with a triple CVD coated carbide tool (AI2O3/TiC/TiCN) by adopting a Taguchi L9 (3^4) experimental design. The ANOVA and RSM methods were used to analyze the effects of cutting factors on the outputs parameters resulting in statistical prediction models. In addition, a multi-objective optimization of the cutting conditions exploiting the desirability function (DF) was done according to four cases of relative importance corresponding to different industrial contexts. Furthermore, the grey relational analysis (GRA) method was applied and compared with the DF method. The results show that the optimal regime found by the DF method, (r =1.6mm, Vc= 240 m/min, f = 0.084 mm/rev and ap = 0.64 mm), favors Ra and MRR. On the other hand, for the GRA method, the combination of (r = 0.4 mm, Vc = 240 m/min f = 0.08 mm/rev and ap = 0.3 mm) favors the minimization of Fz, Pm and Pc. This work presents an originality because the results found are very useful in the field of optimization for a better control of the process IT.

show abstract

Multi-objective optimisation of machining process parameters using deep learning-based data-driven genetic algorithm and TOPSIS

Cited by 54 publications

References 30 publications

Multi‐objective Bayesian modeling and optimization of 3D printing process via experimental data‐driven method

Multi‐objective Bayesian modeling and optimization of 3D printing process via experimental data‐driven method

Multi-stage manufacturing process parameter optimization method based on improved marine predator algorithm

Statistical analysis, modeling and multi-objective optimization of parameters intermittent turning process of AISI D3

Contact Info

Product

Resources

About