Cargando…

Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process

This paper uses Pareto-optimized frames and injection molding process parameters to optimize the quality of UAV housing parts with multi-objective optimization. Process parameters, such as melt temperature, filling time, pressure, and pressure time, were studied as model variables. The quality of a...

Descripción completa

Detalles Bibliográficos
Autores principales: Chang, Hanjui, Zhang, Guangyi, Sun, Yue, Lu, Shuzhou
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322716/
https://www.ncbi.nlm.nih.gov/pubmed/35890672
http://dx.doi.org/10.3390/polym14142896
_version_ 1784756373556297728
author Chang, Hanjui
Zhang, Guangyi
Sun, Yue
Lu, Shuzhou
author_facet Chang, Hanjui
Zhang, Guangyi
Sun, Yue
Lu, Shuzhou
author_sort Chang, Hanjui
collection PubMed
description This paper uses Pareto-optimized frames and injection molding process parameters to optimize the quality of UAV housing parts with multi-objective optimization. Process parameters, such as melt temperature, filling time, pressure, and pressure time, were studied as model variables. The quality of a plastic part is determined by two defect parameters, warpage value and mold index, which require minimal defect parameters. This paper proposes a three-stage optimization system. In the first stage, the main node position of the electronic chip in the module is collected by the unified sampling method, and the chip calculation index of these node positions is analyzed by the mold flow analysis software. In the second stage, the kriging function predicts the mathematical relationship between the mold index and warpage value and the process parameters, such as melt temperature, filling time, packing pressure, and packing time. In the third stage, using LHD sampling and non-dominant rank genetic algorithm II, a convergence curve of warp value is found near the Pareto optimal frontier. In the fourth stage, the fitting degree of Pareto optimal leading edge curve points was verified by analytical experiments. According to experimental verification, it can be seen that the injection molding factors are pressure and pressure time, because the injection molding time and pressure time are completely positively correlated with the mold indicators, the correlation is the strongest, the mold temperature and glue temperature are not the main influencing factors, and the mold temperature shows a certain degree of negative correlation. In this experiment, the die index is mainly improved by injection time and pressure, optimal injection parameter factor combination and minimum injection index, the optimization rate of the die index is up to 96.2% through genetic algorithm optimization nodes and experimental verification, the average optimization rate of the four main optimization nodes is 91.2%, and the error rate with the actual situation is only 8.48%, which is in line with the needs of actual production, and the improvement of the UAV IME membrane is realized.
format Online
Article
Text
id pubmed-9322716
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-93227162022-07-27 Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process Chang, Hanjui Zhang, Guangyi Sun, Yue Lu, Shuzhou Polymers (Basel) Article This paper uses Pareto-optimized frames and injection molding process parameters to optimize the quality of UAV housing parts with multi-objective optimization. Process parameters, such as melt temperature, filling time, pressure, and pressure time, were studied as model variables. The quality of a plastic part is determined by two defect parameters, warpage value and mold index, which require minimal defect parameters. This paper proposes a three-stage optimization system. In the first stage, the main node position of the electronic chip in the module is collected by the unified sampling method, and the chip calculation index of these node positions is analyzed by the mold flow analysis software. In the second stage, the kriging function predicts the mathematical relationship between the mold index and warpage value and the process parameters, such as melt temperature, filling time, packing pressure, and packing time. In the third stage, using LHD sampling and non-dominant rank genetic algorithm II, a convergence curve of warp value is found near the Pareto optimal frontier. In the fourth stage, the fitting degree of Pareto optimal leading edge curve points was verified by analytical experiments. According to experimental verification, it can be seen that the injection molding factors are pressure and pressure time, because the injection molding time and pressure time are completely positively correlated with the mold indicators, the correlation is the strongest, the mold temperature and glue temperature are not the main influencing factors, and the mold temperature shows a certain degree of negative correlation. In this experiment, the die index is mainly improved by injection time and pressure, optimal injection parameter factor combination and minimum injection index, the optimization rate of the die index is up to 96.2% through genetic algorithm optimization nodes and experimental verification, the average optimization rate of the four main optimization nodes is 91.2%, and the error rate with the actual situation is only 8.48%, which is in line with the needs of actual production, and the improvement of the UAV IME membrane is realized. MDPI 2022-07-16 /pmc/articles/PMC9322716/ /pubmed/35890672 http://dx.doi.org/10.3390/polym14142896 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Chang, Hanjui
Zhang, Guangyi
Sun, Yue
Lu, Shuzhou
Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title_full Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title_fullStr Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title_full_unstemmed Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title_short Non-Dominant Genetic Algorithm for Multi-Objective Optimization Design of Unmanned Aerial Vehicle Shell Process
title_sort non-dominant genetic algorithm for multi-objective optimization design of unmanned aerial vehicle shell process
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9322716/
https://www.ncbi.nlm.nih.gov/pubmed/35890672
http://dx.doi.org/10.3390/polym14142896
work_keys_str_mv AT changhanjui nondominantgeneticalgorithmformultiobjectiveoptimizationdesignofunmannedaerialvehicleshellprocess
AT zhangguangyi nondominantgeneticalgorithmformultiobjectiveoptimizationdesignofunmannedaerialvehicleshellprocess
AT sunyue nondominantgeneticalgorithmformultiobjectiveoptimizationdesignofunmannedaerialvehicleshellprocess
AT lushuzhou nondominantgeneticalgorithmformultiobjectiveoptimizationdesignofunmannedaerialvehicleshellprocess