Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants

This study presents a multi-objective optimization framework for designing cylindrical triply periodic minimal surface (TPMS) lattices tailored for bone implant applications. Using an artificial neural network (ANN) as a surrogate model trained on simulated data, four key properties—ultimate stress...

Full description

Saved in:
Bibliographic Details
Main Authors: Mansoureh Rezapourian, Ali Cheloee Darabi, Mohammadreza Khoshbin, Irina Hussainova
Format: Article
Language:English
Published: MDPI AG 2025-07-01
Series:Biomimetics
Subjects:
Online Access:https://www.mdpi.com/2313-7673/10/7/475
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849733783410966528
author Mansoureh Rezapourian
Ali Cheloee Darabi
Mohammadreza Khoshbin
Irina Hussainova
author_facet Mansoureh Rezapourian
Ali Cheloee Darabi
Mohammadreza Khoshbin
Irina Hussainova
author_sort Mansoureh Rezapourian
collection DOAJ
description This study presents a multi-objective optimization framework for designing cylindrical triply periodic minimal surface (TPMS) lattices tailored for bone implant applications. Using an artificial neural network (ANN) as a surrogate model trained on simulated data, four key properties—ultimate stress (U), energy absorption (EA), surface area-to-volume ratio (SA/VR), and relative density (RD)—were predicted from seven lattice design parameters. To address anatomical variability, a novel implant size-based categorization (small, medium, and large) was introduced, and separate optimization runs were conducted for each group. The optimization was performed via the NSGA-II algorithm to maximize mechanical performance (U and EA) and surface efficiency (SA/VR), while filtering for biologically relevant RD values (20–40%). Separate optimization runs were conducted for small, medium, and large implant size groups. A total of 105 Pareto-optimal designs were identified, with 75 designs retained after RD filtering. SHapley Additive exPlanations (SHAP) analysis revealed the dominant influence of thickness and unit cell size on target properties. Kernel density and boxplot comparisons confirmed distinct performance trends across size groups. The framework effectively balances competing design goals and enables the selection of size-specific lattices. The proposed approach provides a reproducible pathway for optimizing bioarchitectures, with the potential to accelerate the development of lattice-based implants in personalized medicine.
format Article
id doaj-art-ceb1e2d5de6c4e1e9c72073bf8ae383d
institution DOAJ
issn 2313-7673
language English
publishDate 2025-07-01
publisher MDPI AG
record_format Article
series Biomimetics
spelling doaj-art-ceb1e2d5de6c4e1e9c72073bf8ae383d2025-08-20T03:07:57ZengMDPI AGBiomimetics2313-76732025-07-0110747510.3390/biomimetics10070475Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone ImplantsMansoureh Rezapourian0Ali Cheloee Darabi1Mohammadreza Khoshbin2Irina Hussainova3Department of Mechanical and Industrial Engineering, Tallinn University of Technology, 19086 Tallinn, EstoniaInstitut für Materialprüfung, Werkstoffkunde und Festigkeitslehre, Universität Stuttgart, Pfaffenwaldring 32, 70569 Stuttgart, GermanyDepartment of Mechanical Engineering, Shahid Rajaee Teacher Training University, Lavizan, Tehran 1678815811, IranDepartment of Mechanical and Industrial Engineering, Tallinn University of Technology, 19086 Tallinn, EstoniaThis study presents a multi-objective optimization framework for designing cylindrical triply periodic minimal surface (TPMS) lattices tailored for bone implant applications. Using an artificial neural network (ANN) as a surrogate model trained on simulated data, four key properties—ultimate stress (U), energy absorption (EA), surface area-to-volume ratio (SA/VR), and relative density (RD)—were predicted from seven lattice design parameters. To address anatomical variability, a novel implant size-based categorization (small, medium, and large) was introduced, and separate optimization runs were conducted for each group. The optimization was performed via the NSGA-II algorithm to maximize mechanical performance (U and EA) and surface efficiency (SA/VR), while filtering for biologically relevant RD values (20–40%). Separate optimization runs were conducted for small, medium, and large implant size groups. A total of 105 Pareto-optimal designs were identified, with 75 designs retained after RD filtering. SHapley Additive exPlanations (SHAP) analysis revealed the dominant influence of thickness and unit cell size on target properties. Kernel density and boxplot comparisons confirmed distinct performance trends across size groups. The framework effectively balances competing design goals and enables the selection of size-specific lattices. The proposed approach provides a reproducible pathway for optimizing bioarchitectures, with the potential to accelerate the development of lattice-based implants in personalized medicine.https://www.mdpi.com/2313-7673/10/7/475triply periodic minimal surfaces (TPMS)bone implantsmulti-objective optimizationmachine learningartificial neural network (ANN)mechanical property prediction
spellingShingle Mansoureh Rezapourian
Ali Cheloee Darabi
Mohammadreza Khoshbin
Irina Hussainova
Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
Biomimetics
triply periodic minimal surfaces (TPMS)
bone implants
multi-objective optimization
machine learning
artificial neural network (ANN)
mechanical property prediction
title Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
title_full Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
title_fullStr Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
title_full_unstemmed Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
title_short Multi-Objective Machine Learning Optimization of Cylindrical TPMS Lattices for Bone Implants
title_sort multi objective machine learning optimization of cylindrical tpms lattices for bone implants
topic triply periodic minimal surfaces (TPMS)
bone implants
multi-objective optimization
machine learning
artificial neural network (ANN)
mechanical property prediction
url https://www.mdpi.com/2313-7673/10/7/475
work_keys_str_mv AT mansourehrezapourian multiobjectivemachinelearningoptimizationofcylindricaltpmslatticesforboneimplants
AT alicheloeedarabi multiobjectivemachinelearningoptimizationofcylindricaltpmslatticesforboneimplants
AT mohammadrezakhoshbin multiobjectivemachinelearningoptimizationofcylindricaltpmslatticesforboneimplants
AT irinahussainova multiobjectivemachinelearningoptimizationofcylindricaltpmslatticesforboneimplants