Advances in machine learning-aided design of reinforced polymer composite and hybrid material systems

Okafor, Christian Emeka; Sunday, Iweriolor; Ani, Okwuchukwu Innocent; Ahmad, Shahnawaz; Mehfuz, Shabana; Ekwueme, Godspower Onyekachukwu; Chukwumuanya, Okechukwu Emmanuel; Abonyi, Sylvester Emeka; Ekengwu, Ignatius Echezona; Chikelu, Okechukwu Peter

doi:10.1016/j.hybadv.2023.100026

Cited by 35 publications

(4 citation statements)

References 150 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machining of WPCs, producing special geometries, finishing varnishes, impregnation layers, and refractory protection are specific topics that should receive more attention from researchers. Modern IT, like modeling, simulations, artificial intelligence, and machine learning, should be applied to predict and optimize the performance of manufactured WPCs [ 90 ].…”

Section: Discussionmentioning

confidence: 99%

Effect of Moisture on the Mechanical Properties of Wood–Plastic Composites Hybridized with Metal Grid Layers

Perišić,

Kalevski,

Grujić

et al. 2023

Polymers

View full text Add to dashboard Cite

Wood–plastic composites (WPCs) are some of the most common modern composite materials for interior and exterior design that combine natural waste wood properties and the molding possibility of a thermoplastic polymer binder. The addition of reinforcing elements, binding agents, pigments, and coatings, as well as changes to the microstructure and composition, can all affect the quality of WPCs for particular purposes. To improve the properties, hybrid composite panels of WPCs with 30 wt. % and 40 wt. % of wood content and reinforced with one or three metal grid layers were prepared sequentially by extrusion and hot pressure molding. The results show an average 20% higher moisture absorption for composites with higher wood content. A high impact test (HIT) revealed that the absorbed energy of deformation increased with the number of metal grid layers, regardless of the wood content, around two times for all samples before water immersion and around ten times after water absorption. Also, absorbed energy increases with raised wood content, which is most pronounced in three-metal-grid samples, from 21 J to 26 J (before swelling) and from 15 J to 24 J (after swelling). Flexural tests follow the trends observed by HIT, indicating around 65% higher strength for samples with three metal grid layers vs. samples without a metal grid before water immersion and around 80% higher strength for samples with three metal grid layers vs. samples without a grid after water absorption. The synthesis route, double reinforcing (wood and metal), applied methods of characterization, and optimization according to the obtained results provide a WPC with improved mechanical properties ready for an outdoor purpose.

show abstract

Section: Discussionmentioning

confidence: 99%

Effect of Moisture on the Mechanical Properties of Wood–Plastic Composites Hybridized with Metal Grid Layers

Perišić,

Kalevski,

Grujić

et al. 2023

Polymers

View full text Add to dashboard Cite

show abstract

“…By analyzing historical data, ML algorithms can identify the key factors influencing polymer quality and recommend adjustments to process parameters in real time. ML-based quality prediction and control enable the proactive management of product variability, ensuring consistent quality standards and meeting customer specifications [21,22]. Finally, ML techniques can power real-time decision-support systems that assist operators and engineers in making informed decisions during polymerization processes.…”

Section: Machine Learning and Polymerizationmentioning

confidence: 99%

Artificial Neural Network Modeling in the Presence of Uncertainty for Predicting Hydrogenation Degree in Continuous Nitrile Butadiene Rubber Processing

Madhuranthakam,

Hourfar,

Elkamel

2024

Processes

View full text Add to dashboard Cite

The transition from batch to continuous production in the catalytic hydrogenation of nitrile butadiene rubber (NBR) into hydrogenated NBR (HNBR) marks a significant advance for applications under demanding conditions. This study introduces a continuous process utilizing a static mixer (SM) reactor, which notably achieves a hydrogenation conversion rate exceeding 97%. We thoroughly review a mechanistic model of the SM reactor to elucidate the internal dynamics governing the hydrogenation process and address the inherent uncertainties in key parameters such as the Peclet number (Pe), dimensionless time (θτ), reaction coefficient (R), and flow rate coefficient (q). A comprehensive dataset generated from varied parameter values serves as the basis for training an artificial neural network (ANN), which is then compared against traditional models including linear regression, decision tree, and random forest in terms of efficacy. Our results clearly demonstrate the ANN’s superiority in predicting the degree of hydrogenation, achieving the lowest root mean squared error (RMSE) of 3.69 compared to 21.90 for linear regression, 4.94 for decision tree, and 7.51 for random forest. The ANN’s robust capability for modeling complex nonlinear relationships and dynamics significantly enhances decision-making, planning, and optimization of the reactor, reducing computational demands and operational costs. In other words, this approach allows users to rely on a single ML-based model instead of multiple mechanistic models for reflecting the effects of possible uncertainties. Additionally, a feature importance study validates the critical impact of time and element number on the hydrogenation process, further supporting the ANN’s predictive accuracy. These findings underscore the potential of ML-based models in streamlining and enhancing the efficiency of chemical production processes.

show abstract

“…Samuel (1959) initially proposed the concept of machine learning, which is the study of how to enable computers to learn without being explicitly programmed. A subfield of artificial intelligence called machine learning makes use of a variety of factual and probabilistic approaches to teach computers how to discover hidden patterns (input-output linkages) in vast and frequently noisy data sets (Okafor et al, 2023). According to purposes and training methods, machine learning can be categorized into three broad approaches namely unsupervised learning, supervised learning and reinforcement learning (Chung et al, 2023).…”

Section: Machine Learningmentioning

confidence: 99%

Reduction of Losses and Wastage in Seafoods: The Role of Smart Tools and Biosensors Based on Artificial Intelligence

Ayısı Larbı,

Osei

2024

Journal of AI

View full text Add to dashboard Cite

This paper reviews current knowledge on the role of smart tools and biosensors based on artificial intelligence in reducing seafood loss and wastage. This study shows that a variety of biosensors, categorised according to how they function, can be used to measure the quality of seafood. These include optical biosensors, enzyme-based biosensors, immunosensors, microbial biosensors, DNA-based biosensors, electrochemical biosensors, optical biosensors, tissue-based biosensors, and piezoelectric biosensors. Among these biosensors, optical biosensors, electrochemical biosensors, and mechanical biosensors are the most significant. Again, this study report that, for seafood traceability and management, a variety of smart solutions including blockchain technology, quick response (QR) codes, data analytics, digital twins, and radio frequency identification (RFID) tags can be utilised. Catch data, vessel tracking data, and data from the processing plant are some of the different data sources that can be utilised to trace seafood products. Artificial intelligence tools like neural networks, deep learning, machine learning, and others can be used to forecast and improve seafood quality. It is crucial to study the development of biosensors that can properly identify the earliest signs of seafood contamination or rotting.

show abstract

Advances in machine learning-aided design of reinforced polymer composite and hybrid material systems

Cited by 35 publications

References 150 publications

Effect of Moisture on the Mechanical Properties of Wood–Plastic Composites Hybridized with Metal Grid Layers

Effect of Moisture on the Mechanical Properties of Wood–Plastic Composites Hybridized with Metal Grid Layers

Artificial Neural Network Modeling in the Presence of Uncertainty for Predicting Hydrogenation Degree in Continuous Nitrile Butadiene Rubber Processing

Reduction of Losses and Wastage in Seafoods: The Role of Smart Tools and Biosensors Based on Artificial Intelligence

Contact Info

Product

Resources

About