Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method
Additive manufacturing (AM) has become a practical solution for fabricating lightweight and high-strength metallic lattice structures. The inverse optimisation of process-structure parameters to achieve high performance and minimised trial-and-error experiments has presented a persistent challenge....
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2023-12-01
|
| Series: | Virtual and Physical Prototyping |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17452759.2023.2266641 |
| _version_ | 1797640920859934720 |
|---|---|
| author | Keyu Shi Dongdong Gu He Liu Yusheng Chen Kaijie Lin |
| author_facet | Keyu Shi Dongdong Gu He Liu Yusheng Chen Kaijie Lin |
| author_sort | Keyu Shi |
| collection | DOAJ |
| description | Additive manufacturing (AM) has become a practical solution for fabricating lightweight and high-strength metallic lattice structures. The inverse optimisation of process-structure parameters to achieve high performance and minimised trial-and-error experiments has presented a persistent challenge. To address this problem, an inverse optimisation methodology has been proposed for coping with multiple conflicting performance objectives, consisting of mechanical properties and lightweight extent under AM-constraints. In the pursuit of greater accuracy, a physics-enhanced data-driven algorithm, i.e. encoding-stiffness-analysis multi-task Gaussian process regression, has been developed. This empowers us to precisely analyse how process-structure parameters impact the properties of AM-formed lattice structures. As an emerging machine learning method for AM, the physics-enhanced data-driven algorithm exhibits strong fitting capability and extrapolation performance, due to the interpretability provided by physical information. It has been applied as a surrogate model within the multi-objective genetic algorithm, facilitating the efficient design of parameters and the expansion of objective space. Notably, a deviation of less than 15% has been observed between predictive and experimental results, providing solid confirmation of our methodology's reliability. This confluence of physical insights and data-driven modelling holds substantial promise for accelerating the development of highly efficient designs. |
| first_indexed | 2024-03-11T13:38:06Z |
| format | Article |
| id | doaj.art-20d8ac040bb54a8bbe6eb67d40aea157 |
| institution | Directory Open Access Journal |
| issn | 1745-2759 1745-2767 |
| language | English |
| last_indexed | 2024-03-11T13:38:06Z |
| publishDate | 2023-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Virtual and Physical Prototyping |
| spelling | doaj.art-20d8ac040bb54a8bbe6eb67d40aea1572023-11-02T14:47:05ZengTaylor & Francis GroupVirtual and Physical Prototyping1745-27591745-27672023-12-0118110.1080/17452759.2023.22666412266641Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven methodKeyu Shi0Dongdong Gu1He Liu2Yusheng Chen3Kaijie Lin4Nanjing University of Aeronautics and AstronauticsNanjing University of Aeronautics and AstronauticsNanjing University of Aeronautics and AstronauticsNanjing University of Aeronautics and AstronauticsNanjing University of Aeronautics and AstronauticsAdditive manufacturing (AM) has become a practical solution for fabricating lightweight and high-strength metallic lattice structures. The inverse optimisation of process-structure parameters to achieve high performance and minimised trial-and-error experiments has presented a persistent challenge. To address this problem, an inverse optimisation methodology has been proposed for coping with multiple conflicting performance objectives, consisting of mechanical properties and lightweight extent under AM-constraints. In the pursuit of greater accuracy, a physics-enhanced data-driven algorithm, i.e. encoding-stiffness-analysis multi-task Gaussian process regression, has been developed. This empowers us to precisely analyse how process-structure parameters impact the properties of AM-formed lattice structures. As an emerging machine learning method for AM, the physics-enhanced data-driven algorithm exhibits strong fitting capability and extrapolation performance, due to the interpretability provided by physical information. It has been applied as a surrogate model within the multi-objective genetic algorithm, facilitating the efficient design of parameters and the expansion of objective space. Notably, a deviation of less than 15% has been observed between predictive and experimental results, providing solid confirmation of our methodology's reliability. This confluence of physical insights and data-driven modelling holds substantial promise for accelerating the development of highly efficient designs.http://dx.doi.org/10.1080/17452759.2023.2266641additive manufacturingmachine learningphysics-enhanced gaussian processmulti-objective optimisationinverse design |
| spellingShingle | Keyu Shi Dongdong Gu He Liu Yusheng Chen Kaijie Lin Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method Virtual and Physical Prototyping additive manufacturing machine learning physics-enhanced gaussian process multi-objective optimisation inverse design |
| title | Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method |
| title_full | Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method |
| title_fullStr | Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method |
| title_full_unstemmed | Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method |
| title_short | Process-structure multi-objective inverse optimisation for additive manufacturing of lattice structures using a physics-enhanced data-driven method |
| title_sort | process structure multi objective inverse optimisation for additive manufacturing of lattice structures using a physics enhanced data driven method |
| topic | additive manufacturing machine learning physics-enhanced gaussian process multi-objective optimisation inverse design |
| url | http://dx.doi.org/10.1080/17452759.2023.2266641 |
| work_keys_str_mv | AT keyushi processstructuremultiobjectiveinverseoptimisationforadditivemanufacturingoflatticestructuresusingaphysicsenhanceddatadrivenmethod AT dongdonggu processstructuremultiobjectiveinverseoptimisationforadditivemanufacturingoflatticestructuresusingaphysicsenhanceddatadrivenmethod AT heliu processstructuremultiobjectiveinverseoptimisationforadditivemanufacturingoflatticestructuresusingaphysicsenhanceddatadrivenmethod AT yushengchen processstructuremultiobjectiveinverseoptimisationforadditivemanufacturingoflatticestructuresusingaphysicsenhanceddatadrivenmethod AT kaijielin processstructuremultiobjectiveinverseoptimisationforadditivemanufacturingoflatticestructuresusingaphysicsenhanceddatadrivenmethod |