The Resin Transfer Moulding process receives great attention from both academia and industry, owing to its superior manufacturing rate and product quality. Particularly, the progression of its mould filling stage is crucial to ensure a complete reinforcement saturation. Contemporary process simulation methods focus primarily on physics-based approaches to model the complex resin permeation phenomenon, which are computationally expensive to solve. Thus, the application of machine learning and data-driven modelling approaches is of great interest to minimise the cost of process simulation. In this study, a comprehensive dataset consisting of mould filling patterns of the Resin Transfer Moulding process at different injection locations for a composite dashboard panel case study is presented. The problem description and significance of the dataset are outlined. The distribution of this comprehensive dataset aims to lower the barriers to entry for researching machine learning approaches in composite moulding applications, while concurrently providing a standardised baseline for evaluating newly developed algorithms and models in future research works.

Composite materials are increasingly important in making high-performance products. However, contemporary composites manufacturing processes still encounter significant challenges that range from inherent material stochasticity to manufacturing process variabilities. This paper proposes a novel smart Industrial Internet of Things framework, which is also referred to as an Artificial Intelligence of Things (AIoT) framework for composites manufacturing. This framework improves production performance through real-time process monitoring and AI-based forecasting. It comprises three main components: (i) an array of temperature, heat flux, dielectric, and flow sensors for data acquisition from production machines and products being made, (ii) an IoT-based platform for instantaneous sensor data integration and visualisation, and (iii) an AI-based model for production process forecasting. Via these components, the framework performs real-time production process monitoring, visualisation, and prediction of future process states. This paper also presents a proof-of-concept implementation of the framework and a real-world composites manufacturing case study that showcases its benefits.

Process simulation is frequently adopted to facilitate the optimization of the resin transfer molding process. However, it is computationally costly to simulate the multi-physical, multi-scale process, making it infeasible for applications involving huge datasets. In this study, the application of K-nearest neighbors and artificial neural network metamodels is proposed to build predictive surrogate models capable of relating the mold-filling process input-output correlations to assist mold designing. The input features considered are the resin injection location and resin viscosity. The corresponding output features investigated are the number of vents required and the resultant maximum injection pressure. Upon training, both investigated metamodels demonstrated desirable prediction accuracies, with a low prediction error range of 5.0% to 15.7% for KNN metamodels and 6.7% to 17.5% for ANN metamodels. The good prediction results convincingly indicate that metamodeling is a promising option for composite molding applications, with encouraging prospects for data-intensive applications such as process digital twinning.

The accurate diagnosis of machine breakdowns is crucial for maintaining operational safety in smart manufacturing. Despite the promise shown by deep learning in intelligent fault diagnosis, the scarcity of labeled sensors data, particularly for equipment failure instances, poses a significant challenge. This limitation hampers the development of robust classification models. Existing methods like model-agnostic meta-learning (MAML) do not adequately address variable working conditions, thus limiting effective knowledge transfer. To address these challenges, a Related Task Aware Curriculum Meta-learning (RT-ACM) enhanced fault diagnosis framework is proposed in this paper, inspired by human cognitive learning processes. RT-ACM improves training by considering the relevance of auxiliary sensor working conditions, adhering to the principle of "paying more attention to more relevant knowledge", and focusing on "easier first, harder later" curriculum sampling. This approach aids the meta-learner in achieving a superior convergence state. Extensive experiments on three real-world datasets demonstrate the superiority of RT-ACM framework.

Factorization models have been successfully applied to the recommendation problems and have significant impact to both academia and industries in the field of Collaborative Filtering ( CF ). However, the intermediate data generated in factorization models’ decision making process (or training process , footprint ) have been overlooked even though they may provide rich information to further improve recommendations. In this article, we introduce the concept of Convergence Pattern, which records how ratings are learned step-by-step in factorization models in the field of CF. We show that the concept of Convergence Patternexists in both the model perspective (e.g., classical Matrix Factorization ( MF ) and deep-learning factorization) and the training (learning) perspective (e.g., stochastic gradient descent ( SGD ), alternating least squares ( ALS ), and Markov Chain Monte Carlo ( MCMC )). By utilizing the Convergence Pattern, we propose a prediction model to estimate the prediction reliability of missing ratings and then improve the quality of recommendations. Two applications have been investigated: (1) how to evaluate the reliability of predicted missing ratings and thus recommend those ratings with high reliability. (2) How to explore the estimated reliability to adjust the predicted ratings to further improve the predication accuracy. Extensive experiments have been conducted on several benchmark datasets on three recommendation tasks: decision-aware recommendation, rating predicted, and Top- N recommendation. The experiment results have verified the effectiveness of the proposed methods in various aspects.