A multi-objective Gaussian process approach for optimization and prediction of carbonization process in carbon fiber production under uncertainty

Ramezankhani, Milad; Crawford, Bryn; Khayyam, Hamid; Naebe, Minoo; Seethaler, Rudolf; Milani, Abbas S.

doi:10.1007/s42114-019-00107-6

Cited by 17 publications

(10 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As such, select systems have been successfully modeled using this strategy and few critical comparisons between studies can be made. Studies include modeling the production of carbon fibre [48] [49], optimization of the automated fibre placement process [50], modeling of the dynamic cure process [51], as well as the assessment of defects for quality control, namely fibre orientation [52] and delamination [53] [54].…”

Section: Current State-of-the-art For Machine Learning In Compositesmentioning

confidence: 99%

“…The latter studies demonstrated that the machine learning model choices can be well relevant to the larger distributed supply chains. Further, the inclusion of multi-objective design optimization techniques under considerations of uncertainty extended these models to broader industrial applications [52] [53].…”

Section: Current State-of-the-art For Machine Learning In Compositesmentioning

confidence: 99%

See 1 more Smart Citation

A Mini-Review and Perspective on Current Best Practice and Emerging Industry 4.0 Methods for Risk Reduction in Advanced Composites Manufacturing

Crawford¹,

Khayyam²,

Milani³

2021

OJCM

Self Cite

View full text Add to dashboard Cite

The manufacturing of composite structures is a highly complex task with inevitable risks, particularly associated with aleatoric and epistemic uncertainty of both the materials and processes, as well as the need for in-situ decision-making to mitigate defects during manufacturing. In the context of aerospace composites production in particular, there is a heightened impetus to address and reduce this risk. Current qualification and substantiation frameworks within the aerospace industry define tractable methods for risk reduction. In parallel, Industry 4.0 is an emerging set of technologies and tools that can enable better decision-making towards risk reduction, supported by data-driven models. It offers new paradigms for manufacturers, by virtue of enabling in-situ decisions for optimizing the process as a dynamic system.However, the static nature of current (pre-Industry 4.0) best-practice frameworks may be viewed as at odds with this emerging novel approach. In addition, many of the predictive tools leveraged in an Industry 4.0 system are black-box in nature, which presents other concerns of tractability, interpretability and ultimately risk. This article presents a perspective on the current state-of-the-art in the aerospace composites industry focusing on risk reduction in the autoclave processing, as an example system, while reviewing current trends and needs towards a Composites 4.0 future.

show abstract

Section: Current State-of-the-art For Machine Learning In Compositesmentioning

confidence: 99%

Section: Current State-of-the-art For Machine Learning In Compositesmentioning

confidence: 99%

A Mini-Review and Perspective on Current Best Practice and Emerging Industry 4.0 Methods for Risk Reduction in Advanced Composites Manufacturing

Crawford¹,

Khayyam²,

Milani³

2021

OJCM

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are two main weaknesses of scalarized multi-objective learning: (i) the determination of an appropriate hyperparameter λ that properly reflects the purpose of the user is not trivial, and (ii) only a single solution can be obtained, from which little insight into the problem can be gained [36]. Most of the efforts on solving multi-objective ML problems can be solved using Pareto-based multi-objective optimization methodology particularly due to the great success of multi-objective optimization using evolutionary algorithms and other population-based stochastic search methods [37]. Pareto-based multi-objective learning approaches are more powerful compared to learning algorithms with a scalar cost function in addressing various topics of ML tasks [36].…”

Section: Multi-objective Learningmentioning

confidence: 99%

“…As stated in pervious sections, ML techniques have some limitations, and a hybrid ML technique can potentially capture more characteristics of complex systems to overcome these limitations. Recent studies of hybrid models combining different ML techniques have shown promising results [22,37]. There are various types of frameworks to develop hybrid models, and it is unknown that which hybrid model can perform the best in data-driven learning.…”

Section: Hybrid Data-driven Learningmentioning

confidence: 99%

A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling With Application in Industry 4.0

et al. 2020

Self Cite

View full text Add to dashboard Cite

To meet the challenges of manufacturing smart products, the manufacturing plants have been radically changed to become smart factories underpinned by industry 4.0 technologies. The transformation is assisted by employment of machine learning techniques that can deal with modelling both big or limited data. This manuscript reviews these concepts and present a case study that demonstrates the use of a novel intelligent hybrid algorithms for Industry 4.0 applications with limited data. In particular, an intelligent algorithm is proposed for robust data modelling of nonlinear systems based on input-output data. In our approach, a novel hybrid data-driven combining the Group-Method of Data-Handling and Singular-Value Decomposition is adapted to find an offline deterministic model combined with Pareto multi-objective optimization to overcome the overfitting issue. An Unscented-Kalman-Filter is also incorporated to update the coefficient of the deterministic model and increase its robustness against data uncertainties. The effectiveness of the proposed method is examined on a set of real industrial measurements. INDEX TERMS Industry 4.0; Big data modelling; Limited data modelling, Multi-objective optimization. NOMENCLATURE CNN

show abstract

“…[9,35] The mechanism of photooxidation, thermal oxidation, and chemical derivatization of polyacrylonitrile (PAN) indicated that the nitrile content was increased after the photooxidation at long wavelengths. [36] The chemical derivatization reaction was accompanied by the formation of first-order amide and carbonyl groups, [37] and was aimed to illustrate the mechanism of degradation and to provide a guidance for industrial utilization of R-ABS. [38] The most important method of using R-ABS is doping R-ABS in virgin acrylonitrile-butadiene-styrene (V-ABS) copolymer plastics.…”

Section: Introductionmentioning

confidence: 99%

Chain Extension, Phase Interface Reparation and Mechanical Property of Recycled Acrylonitrile‐Butadiene‐Styrene by Epoxidized Styrene‐Butadiene‐Styrene

Shu

et al. 2020

Macro Materials & Eng

View full text Add to dashboard Cite

For ABS, the styrene-acrylonitrile (SAN) block copolymer phase is the matrix phase, polybutadiene (PB) phase is the disperse phase, and styrene-acrylonitrile block copolymer grafted polybutadiene (SAN-g-PB) is the compatibilizer. [9] From the viewpoint of processing, ABS from the discarded products can be processed repeatedly for reuse. [10] However, as a result of aging arising from the service, the mechanical properties of recycled ABS (R-ABS) are usually inferior to virgin ABS (V-ABS), especially the decreased impact strength. This limits the application and reuse of R-ABS. [10] Recycling is an efficient way to manage and treat waste plastics. It has been a significant section of industry since plastics now involve every aspect of our living. [11-25] The International Organization for Standardization (ISO) and the American Society for Testing and Materials (ASTM) have standardized the classification and there are four main techniques for recycling waste plastics. These include reuse (primary), mechanical recycling (secondary), chemical recycling (tertiary), and energy recovery (quaternary). [26-28] Plastic recycling is a valuable practice to save 20-50% from the point of market price in comparison with their virgin counterparts. [29,30] However, lots of recycled The demand for processing recycled acrylonitrile-butadiene-styrene copolymer plastics (R-ABS) grows fast. Herein, epoxidized styrene-butadienestyrene (ESBS) with reactive groups including polybutadiene (PB) phase, epoxidized polybutadiene (EPB) phase and polystyrene phase is prepared by modifying SBS with an in situ peroxyformic acid method. Both chain extension and phase interface reparation of R-ABS are successfully reported by simple melt blending. Compared with R-ABS, when ESBS content is 15 wt%, the average molecular weight (M w) of the ESBS/R-ABS is increased from 118.01 to 612.51 kDa. The particle size of the dispersed phase is decreased obviously. The compatibility between these two phases became better. The average notch impact strength of R-ABS is 5.72 kJ m −2. When the ESBS content is 15 wt%, the average notch impact strength of ESBS/R-ABS reaches 13.90 kJ m −2 , which is increased by 143% compared with that of R-ABS. The notch impact strength of ESBS/R-ABS is close to that of virgin ABS. The reported high-value usage of R-ABS has a great potential for industrial-scale applications.

show abstract

A multi-objective Gaussian process approach for optimization and prediction of carbonization process in carbon fiber production under uncertainty

Cited by 17 publications

References 30 publications

A Mini-Review and Perspective on Current Best Practice and Emerging Industry 4.0 Methods for Risk Reduction in Advanced Composites Manufacturing

A Mini-Review and Perspective on Current Best Practice and Emerging Industry 4.0 Methods for Risk Reduction in Advanced Composites Manufacturing

A Novel Hybrid Machine Learning Algorithm for Limited and Big Data Modeling With Application in Industry 4.0

Chain Extension, Phase Interface Reparation and Mechanical Property of Recycled Acrylonitrile‐Butadiene‐Styrene by Epoxidized Styrene‐Butadiene‐Styrene

Contact Info

Product

Resources

About