Review of transfer learning in modeling additive manufacturing processes

Tang, Yifan; Dehaghani, M. Rahmani; Wang, G. Gary

doi:10.1016/j.addma.2022.103357

Cited by 21 publications

(5 citation statements)

References 91 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is hypothetically compatible with the reduction of the prices of AM devices, especially those related to FDM technology (Kabir et al , 2020). Also, with the emergence of new materials and AM technologies, new trends in modelling (Tang et al , 2023), the fact that AM is now a highly standardized field (Phillips et al , 2022) and even the use of AM for non-industrial issues such as the creative industries (Abisuga and de Beer, 2023). But this may also be influenced by the emergence of Industry 5.0 because, since 2017, several academic efforts have been pushing the introduction of Industry 5.0 (Demir et al , 2019; Longo et al , 2020; Nahavandi, 2019).…”

Section: Discussionmentioning

confidence: 99%

“…As it is well known, a three-dimensional object can be manufactured from a digital model using AM, which has become commonplace in recent years with 3D printers widely available and new modelling methods (Tang et al , 2023). However, its industrial applications are still evolving alongside its expansion to non-specialized uses, as AM is a key component of Industry 4.0.…”

Section: Introductionmentioning

confidence: 99%

“…Also, the relationship between AM and new modelling methods (Tang et al , 2023) is important in the context of Industry 4.0 and digitalization.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Mapping and prospective of additive manufacturing in the context of Industry 4.0 and 5.0

Rodríguez-Martín,

Domingo,

Ribeiro

2024

RPJ

View full text Add to dashboard Cite

Purpose This study aims to investigate the scientific impact of additive manufacturing in recent years, considering its evolution as an Industry 4.0 technology and also in the current context of Industry 5.0. For this aim, advanced statistics and scientometric tools have been used. Design/methodology/approach This study aims to explore the trends and impacts of additive manufacturing, focusing on its evolution and its relationship with Industry 4.0 and 5.0. For this purpose, a scientometric study and a meta-analysis of data extracted from the scientific Scopus database have been carried out. R programming and specific bibliometric software have been used to conduct the research. Initially, the data were evaluated from various perspectives, including sources, topics and impact indexes, to assess trends derived from the volume of publications, the impact of sources and affiliations, as well as the production segmented by country and the relationships between authors from different countries. Subsequently, a meta-analysis on keywords has been carried out using two distinct clustering methodologies: link strength and fractionalization. The results obtained were compared to establish a specific taxonomy of the AM subtopics, considering AM as a single body of knowledge related to Industries 4.0 and 5.0 paradigms. The analyses carried out have shown the impact and strong evolution of additive manufacturing as a field of knowledge at the world level, both from the point of view of manufacturing processes and from the point of view of materials science. In addition, some differences have been detected depending on the country. As a result of the meta-analysis, four different subtopics have been detected, some of which are highly related to other technologies and approaches in Industries 4.0 and 5.0 paradigms. Additionally, it establishes a comprehensive taxonomy for AM research, serving as a foundational reference for future studies aimed at exploring the evolution and transformative impact of this technology. Findings The analyses carried out have shown the impact and strong evolution of additive manufacturing as a field of knowledge at the world level, both from the point of view of manufacturing processes and from the point of view of materials science. In addition, some differences have been detected depending on the country. As a result of the meta-analysis, four different subtopics have been detected: one of them directly related to the use of recently developed Industry 4.0 technologies in additive manufacturing. The results provide a starting point for prospective studies to understand the evolution and disruption of this technology. Originality/value The paper is original and is based on data systematically extracted from scientific databases. Then, a specific methodology based on different advanced tools was applied for scientometric evaluation and meta-analysis.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Mapping and prospective of additive manufacturing in the context of Industry 4.0 and 5.0

Rodríguez-Martín,

Domingo,

Ribeiro

2024

RPJ

View full text Add to dashboard Cite

show abstract

“…Despite these challenges and differences, LPBF and LDED share core physical phenomena like melting and solidification. This similarity offers the potential transferability for the ML model between LPBF and LDED [58]. Transfer learning techniques can leverage LPBF's advanced AI applications to inform less mature processes like LDED.…”

Section: Machine Learning Assisted In-situ Monitoring and Closed-loop...mentioning

confidence: 99%

Recent innovations in laser additive manufacturing of titanium alloys

Su,

Jiang,

Teng

et al. 2024

Int. J. Extrem. Manuf.

View full text Add to dashboard Cite

Titanium (Ti) alloys are widely used in frontier fields like aerospace and biomedical engineering. Laser additive manufacturing (LAM), as an innovative technology, is the key driver for the development of Ti alloys. Despite the significant advancements in LAM of Ti alloys, there remain challenges that need further research and development efforts. To recap the potential of LAM high-performance Ti alloy, this article systematically reviews LAM Ti alloys with up-to-date information on process, materials, and properties. Several feasible solutions to advance LAM Ti alloys were reviewed, including intelligent process parameters optimization, LAM process innovation with auxiliary fields and novel Ti alloys customization for LAM. The auxiliary energy fields (e.g., thermal, acoustic, mechanical deformation and magnetic fields) that can be applied during LAM Ti alloys affect the melt pool dynamics and solidification behaviour, altering microstructures and mechanical performances. Different kinds of novel Ti alloys customized for LAM, like peritectic α-Ti, eutectoid (α+β)-Ti, hybrid (α+β)-Ti, isomorphous β-Ti and eutectic β-Ti alloys are reviewed in detail. Furthermore, machine learning in accelerating the LAM process optimization and new materials development is also outlooked. The review summarizes the material properties and performance envelops and benchmarks the research achievements in LAM of Ti alloys. In addition, the perspectives and further trends in LAM of Ti alloys are also highlighted.

show abstract

“…Soft sensor models established based on historical operational data may not be applicable to new batches, leading to model degradation and misalignment issues. Considering that transfer learning can learn useful information from other fermentation batches to assist in completing tasks for the target fermentation batch and does not require training and prediction data to conform to the requirement of independent and identically distributed data [21], it is an effective way to solve the problem of soft sensor modeling for the fermentation process with multiple operating conditions across different batches. Transfer learning has been widely used in medical images, industrial processes, and so on [22,23].…”

Section: Principle and Solution Of Balanced Distribution Adaptationmentioning

confidence: 99%

Development and Optimization of a Novel Soft Sensor Modeling Method for Fermentation Process of Pichia pastoris

Wang

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper introduces a novel soft sensor modeling method based on BDA-IPSO-LSSVM designed to address the issue of model failure caused by varying fermentation data distributions resulting from different operating conditions during the fermentation of different batches of Pichia pastoris. First, the problem of significant differences in data distribution among different batches of the fermentation process is addressed by adopting the balanced distribution adaptation (BDA) method from transfer learning. This method reduces the data distribution differences among batches of the fermentation process, while the fuzzy set concept is employed to improve the BDA method by transforming the classification problem into a regression prediction problem for the fermentation process. Second, the soft sensor model for the fermentation process is developed using the least squares support vector machine (LSSVM). The model parameters are optimized by an improved particle swarm optimization (IPSO) algorithm based on individual differences. Finally, the data obtained from the Pichia pastoris fermentation experiment are used for simulation, and the developed soft sensor model is applied to predict the cell concentration and product concentration during the fermentation process of Pichia pastoris. Simulation results demonstrate that the IPSO algorithm has good convergence performance and optimization performance compared with other algorithms. The improved BDA algorithm can make the soft sensor model adapt to different operating conditions, and the proposed soft sensor method outperforms existing methods, exhibiting higher prediction accuracy and the ability to accurately predict the fermentation process of Pichia pastoris under different operating conditions.

show abstract

Review of transfer learning in modeling additive manufacturing processes

Cited by 21 publications

References 91 publications

Mapping and prospective of additive manufacturing in the context of Industry 4.0 and 5.0

Mapping and prospective of additive manufacturing in the context of Industry 4.0 and 5.0

Recent innovations in laser additive manufacturing of titanium alloys

Development and Optimization of a Novel Soft Sensor Modeling Method for Fermentation Process of Pichia pastoris

Contact Info

Product

Resources

About