Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing

Meister, Sebastian; Wermes, Mahdieu A. M.; Stüve, Jan; Groves, Roger M.

doi:10.1016/j.compositesb.2021.109160

Cited by 44 publications

(10 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These tasks may include detection of resin race-tracking in molds 135 , flow disturbances 136 , and unfilled zones formation 137 during the filling stage of an LCM process as well as inspection of broken-filaments during fiber production 138 . Novel AI-based methods for the inspection of the Automated Fiber Placement (AFP) process have also been presented by several researchers [139][140][141][142][143] . As part of health monitoring of structures, machine/deep learning models have been used for defect/damage detection [144][145][146][147][148][149][150] , characterization of cracks/delamination [151][152][153] and classification of impact levels 154 .…”

Section: The Meta-verse Of Composites Manufacturingmentioning

confidence: 99%

Graphene nanoparticles as data generating digital materials in industry 4.0

Ali

Irfan

Khan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

One of the potential applications of 2D materials is to enhance multi-functionality of structures and components used in aerospace, automotive, civil and defense industries. These multi-functional attributes include sensing, energy storage, EMI shielding and property enhancement. In this article, we have explored the potential of using graphene and its variants as data generating sensory elements in Industry 4.0. We have presented a complete roadmap to cover three emerging technologies i.e. advance materials, artificial intelligence and block-chain technology. The utility of 2D materials such as graphene nanoparticles is yet to be explored as an interface for digitalization of a modern smart factory i.e. “factory-of-the-future”. In this article, we have explored how 2D material enhanced composites can act as an interface between physical and cyber spaces. An overview of employing graphene-based smart embedded sensors at various stages of composites manufacturing processes and their application in real-time structural health monitoring is presented. The technical challenges associated with interfacing graphene-based sensing networks with digital space are discussed. Additionally, an overview of the integration of associated tools such as artificial intelligence, machine learning and block-chain technology with graphene-based devices and structures is also presented.

show abstract

Section: The Meta-verse Of Composites Manufacturingmentioning

confidence: 99%

Graphene nanoparticles as data generating digital materials in industry 4.0

Ali

Irfan

Khan

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…This digital replica has the potential to significantly transform the design process of COPV by obtaining a direct way to detect, classify, and correct laminate lay‐up defects based on real data from a physical object. [ 6,11 ]…”

Section: Introductionmentioning

confidence: 99%

“…[5,6,10] Thus, a thermographic monitoring system can track the fiber-band position and detect relevant defects during the manufacturing process. [10,11] With this information, computational tools, such as digital twins, can be developed. This digital replica has the potential to significantly transform the design process of COPV by obtaining a direct way to detect, classify, and correct laminate lay-up defects based on real data from a physical object.…”

mentioning

confidence: 99%

“…This digital replica has the potential to significantly transform the design process of COPV by obtaining a direct way to detect, classify, and correct laminate lay-up defects based on real data from a physical object. [6,11] In this work, we present the development of an image processing algorithm (IPA-Delfin) for the generation of a digital reconstruction of a Type-IV pressure vessel. The algorithm also integrates the movements of an industrial robot-based winding machine to digitally reconstruct the laminate pattern in real-time.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Development of an image processing algorithm (IPA‐Delfin) for the digital reconstruction of composite overwrapped pressure vessels

et al. 2023

View full text Add to dashboard Cite

Wet filament winding has been established as the primary manufacturing process for overwrapped pressure vessels. However, the prediction of the mechanical performance of pressure vessels is still not sufficiently accurate, mostly due to process‐induced deviations within the laminate structure. In this work, we present an image processing algorithm (IPA‐Delfin) that enables the real‐time generation of a digital reconstruction based on the actual geometry and position of the placed roving. A Type‐IV pressure vessel is analyzed under real manufacturing conditions. Our approach allows the measurement of the overlapping degree of roving within the laminate and the prediction of gaps. The results show that the fiber‐band width and the overlapping area vary significantly when the roving is placed directly on the vessel's polymer liner. A more constant and uniform fiber‐band width and overlapping area were observed when the filament winding took place on the previously placed roving. Hence, the IPA‐Delfin can be potentially used for the generation of digital twins of composite overwrapped pressure vessels.

show abstract

“…As a result, there is a gap between research and practice. The emergence of explainable AI (XAI) is expected to fill this gap [8][9]. However,…”

Section: Introductionmentioning

confidence: 99%

Novel XAI techniques for explaining GA applications in job scheduling

Chen¹,

Wang

2022

Preprint

View full text Add to dashboard Cite

Many evolutionary artificial intelligence (AI) technologies have been applied to assist job scheduling in manufacturing. Among them, genetic algorithms (GAs) are one of mainstream methods. However, GA applications in this field may not be easy to understand or communicate, especially to factory workers without relevant background knowledge, preventing widespread acceptance of such applications. To address this problem, the concept of explanatory AI (XAI) has been proposed. This study first reviews existing XAI techniques for explaining GA applications in job scheduling. Based on the review results, the problems faced by existing XAI techniques are summarized. To solve these problems, this study proposes several novel XAI techniques, including decision tree-based interpretation, dynamic transformation and contribution diagrams, and improved bar charts. To illustrate the effectiveness of the proposed methodology, it has been applied to a case in the literature. According to the experimental results, the proposed methodology can make up for the deficiencies of existing XAI methods in processing high-dimensional data and visualizing the contribution of feasible solutions, thereby satisfying all the requirements for an effective XAI technique for explaining GA applications in job scheduling. Furthermore, the proposed methodology can be easily extended to explain other evolutionary AI applications such as ant colony optimization (ACO), particle swarm optimization (PSO), artificial bee colony (ABC) in job scheduling.

show abstract

Investigations on Explainable Artificial Intelligence methods for the deep learning classification of fibre layup defect in the automated composite manufacturing

Cited by 44 publications

References 23 publications

Graphene nanoparticles as data generating digital materials in industry 4.0

Graphene nanoparticles as data generating digital materials in industry 4.0

Development of an image processing algorithm (IPA‐Delfin) for the digital reconstruction of composite overwrapped pressure vessels

Novel XAI techniques for explaining GA applications in job scheduling

Contact Info

Product

Resources

About