Ontology Network-Based In-Situ Sensor Selection for Quality Management in Metal Additive Manufacturing

Roh, Byeong-Min; Kumara, Soundar; Yang, Hui; Simpson, Timothy W.; Witherell, Paul; Jones, Albert; Lu, Yan

doi:10.1115/1.4055853

Cited by 9 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This method could not fully explain more complex situations and could not relate simulation parameters with printing parameters. Other researchers have found that the process variant affects the as-built qualities [29][30][31][32][33][34][35][36][37][38][39]; they have indicated that the process plays a significant role in determining the anisotropic mechanical behaviors. However, there still lacks a linkage between such effects and morphing behaviors.…”

Section: State-of-the-art Reviewmentioning

confidence: 99%

Programmable Thermo-Responsive Self-Morphing Structures Design and Performance

et al. 2022

Self Cite

View full text Add to dashboard Cite

Additive manufacturing (AM), also known as 3D printing, was introduced to design complicated structures/geometries that overcome the manufacturability limitations of traditional manufacturing processes. However, like any other manufacturing technique, AM also has its limitations, such as the need of support structures for overhangs, long build time etc. To overcome these limitations of 3D printing, 4D printing was introduced, which utilizes smart materials and processes to create shapeshifting structures with the external stimuli, such as temperature, humidity, magnetism, etc. The state-of-the-art 4D printing technology focuses on the “form” of the 4D prints through the multi-material variability. However, the quantitative morphing analysis is largely absent in the existing literature on 4D printing. In this research, the inherited material anisotropic behaviors from the AM processes are utilized to drive the morphing behaviors. In addition, the quantitative morphing analysis is performed for designing and controlling the shapeshifting. A material–process–performance 4D printing prediction framework has been developed through a novel dual-way multi-dimensional machine learning model. The morphing evaluation metrics, bending angle and curvature, are obtained and archived at 99% and 93.5% R2, respectively. Based on the proposed method, the material and production time consumption can be reduced by around 65–90%, which justifies that the proposed method can re-imagine the digital–physical production cycle.

show abstract

Section: State-of-the-art Reviewmentioning

confidence: 99%

Programmable Thermo-Responsive Self-Morphing Structures Design and Performance

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Besides the abovementioned experimental analysis for developing a qualitative relationship between the process and the desired quality, other researchers used the data analytical methods [ 45 ], and machine learning model [ 46 , 47 , 48 ] to provide a probabilistic predictive model for providing guidance in assuring the as-built quality in the pre-processing stage. However, few researchers developed a novel multi-dimensional process-quality framework [ 49 , 50 , 51 , 52 , 53 ] that can provide a quantitative relation between the multiple process parameter and the build quality and provide a certain printable zone to control the quality as desired.…”

Section: Literature Reviewmentioning

confidence: 99%

Quality Quantification and Control via Novel Self-Growing Process-Quality Model of Parts Fabricated by LPBF Process

2022

View full text Add to dashboard Cite

Laser Powder Bed Fusion (LPBF) presents a more extensive allowable design complexity and manufacturability compared with the traditional manufacturing processes by depositing materials in a layer-wised manner. However, the process variability in the LPBF process induces quality uncertainty and inconsistency. Specifically, the mechanical properties, e.g., tensile strength, are hard to be predicted and controlled in the LPBF process. Much research has recently been reported exploring the qualitative influence of single/two process parameters on tensile strength. In fact, mechanical properties are comprehensively affected by multiple correlated process parameters with unclear and complex interactions. Thus, the study on the quantitative process-quality model of the metal LPBF process is urgently needed to provide an enough-strength component via the metal LPBF process. Recent progress in artificial intelligence (AI) and machine learning (ML) provides new insight into quality prediction in terms of computational accuracy and speed. However, the predictive model quality through the traditional AL/ML is heavily determined by the training data size, and the experimental analysis can be expansive on LPBF. This paper explores the comprehensive effect of the tensile strength of 316L stainless-steel parts on LPBF and proposes a valid quantitative predictive model through a novel self-growing machine-learning framework. The self-growing framework can autonomously expand and classify the growing dataset to provide a high-accuracy prediction with fewer input data. To verify this predictive model of tensile strength, specimens manufactured by the LPBF process with different group process parameters (laser power, scanning speed, and hatch spacing) are collected. The experimental results validate the predicted tensile strengths within a less than 3% deviation.

show abstract

“…Despite having its origins in the Semantic Web, ontology has found widespread use in numerous other domains. In the field of AM, Liu and Rosen [24] presented an ontology-based knowledge representation and reuse method for AM process design; Witherell et al [25] built several ontology-based metamodels for reusing AM process models; Roh et al [26] constructed several ontology-based laser and heat metamodels for metal AM; Lu et al [27] proposed an ontology-based digital solution for integrated and collaborative AM; Dinar and Rosen [28] constructed a general ontology for AM design; Hagedorn et al [29] developed an ontology-based approach for creative design in AM; Liang [30] established an ontology-based knowledge framework for AM process design; Kim et al [31] constructed an AM design ontology to facilitate analysis of manufacturability; Sanfilippo et al [32] built an ontology-based model for AM; Ali et al [33] constructed an ontology that represents product life cycle knowledge in AM; Xiong et al [34] developed an ontology-based process design platform for wire arc AM; Ko et al [35] studied construction of rules for AM design based on ontology and machine learning; Chen et al [36] constructed an ontology-based Bayesian network model to represent the causal links between AM design and process parameters, as well as structure and mechanical properties; Roh et al [37] established an ontology-based process map capturing all data in a metal AM process chain; Mayerhofer et al [38] developed an ontology that represent the information regarding the capabilities of AM processes, materials, and machines; Li et al [39] developed an ontology for knowledge representation in LPBF process planning; Roh et al [40] created network-based ontologies that capture the relationship between process variables and sensor data in real-time, as well as the relationship between as-built component characteristics and related physical phenomena; Hasan et al [41] established an ontological framework for process defects knowledge modelling in LPBF; Park et al [42] presented an ontology-based framework to facilitate collaborative knowledge management in the identification of data analytics opportunities in AM; Wang et al [43] built an ontology-supported embedding learning system for defect diagnosis in AM; Wang et al [44] developed an ontology for eco-design in AM that incorporates informative sustainability analysis. It is clear that ontologies not only support the representation of AM part data themselves, but, most importantly, have the capabilit...…”

Section: Introductionmentioning

confidence: 99%

Enriching Laser Powder Bed Fusion Part Data Using Category Theory

Qin,

Narasimharaju,

et al. 2024

JMMP

View full text Add to dashboard Cite

Laser powder bed fusion (LPBF) is a promising metal additive manufacturing technology for producing functional components. However, there are still a lot of obstacles to overcome before this technology is considered mature and trustworthy for wider industrial applications. One of the biggest obstacles is the difficulty in ensuring the repeatability of process and the reproducibility of products. To tackle this challenge, a prerequisite is to represent and communicate the data from the part realisation process in an unambiguous and rigorous manner. In this paper, a semantically enriched LPBF part data model is developed using a category theory-based modelling approach. Firstly, a set of objects and morphisms are created to construct categories for design, process planning, part build, post-processing, and qualification. Twenty functors are then established to communicate these categories. Finally, an application of the developed model is illustrated via the realisation of an LPBF truncheon.

show abstract

Ontology Network-Based In-Situ Sensor Selection for Quality Management in Metal Additive Manufacturing

Cited by 9 publications

References 43 publications

Programmable Thermo-Responsive Self-Morphing Structures Design and Performance

Programmable Thermo-Responsive Self-Morphing Structures Design and Performance

Quality Quantification and Control via Novel Self-Growing Process-Quality Model of Parts Fabricated by LPBF Process

Enriching Laser Powder Bed Fusion Part Data Using Category Theory

Contact Info

Product

Resources

About