Metallographic analyses of nodular iron casting methods are based on visual comparisons according to measuring standards. Specifically, the microstructure is analyzed in a subjective manner by comparing the extracted image from the microscope to pre-defined image templates. The achieved classifications can be confused, due to the fact that the features extracted by a human being could be interpreted differently depending on many variables, such as the conditions of the observer. In particular, this kind of problem represents an uncertainty when classifying metallic properties, which can influence the integrity of castings that play critical roles in safety devices or structures. Although there are existing solutions working with extracted images and applying some computer vision techniques to manage the measurements of the microstructure, those results are not too accurate. In fact, they are not able to characterize all specific features of the image and, they cannot be adapted to several characterization methods depending on the specific regulation or customer. Hence, in order to solve this problem, we propose a framework to improve and automatize the evaluations by combining classical machine vision techniques for feature extraction and deep learning technologies, to objectively make classifications. To adapt to the real analysis environments, all included inputs in our models were gathered directly from the historical repository of metallurgy from the Azterlan Research Centre (labeled using expert knowledge from engineers). The proposed approach concludes that these techniques (a classification under a pipeline of deep neural networks and the quality classification using an ANN classifier) are viable to carry out the extraction and classification of metallographic features with great accuracy and time, and it is possible to deploy software with the models to work on real-time situations. Moreover, this method provides a direct way to classify the metallurgical quality of the molten metal, allowing us to determine the possible behaviors of the final produced parts.

In order to ensure the optimal state of recovered molding sand inside a foundry, it is necessary to avoid temperature peaks and to ensure optimal humidity conditions prior to reusing the sand. Sand that is too hot or without optimal moisture can cause production delays due to a long mixing process, excessive consumption of raw materials, or poor agglutination. To ensure a stable and optimal sand temperature, many foundries choose to incorporate coolers into their process, however, it is a solution that is not always viable, either due to their high cost or a lack of space within the facility. Another solution is to incorporate water sprinklers into the cooling drum which contribute by reducing the temperature of the castings and the sand, but these systems do not prevent temperature peaks from occurring. Therefore, here, we present a control methodology, based on a digital architecture that, governed by an intelligent digital twin allows us to know the real situation and the current rate of production, providing suggestions for water addition. The obtained system reduces the average temperature and its variation, as well as eliminates temperature peaks, giving a more controlled manufacturing process.

The manufacturing process carried out in the investment casting industry suffers from problems similar to other production processes. In addition, the high requirements of the customers and the industries that require these parts mean that high quality standards must be met. If those requirements are not achieved, this leads to the rejection of the manufactured parts. Therefore, given the current technology revolution (i.e., Industry 4.0) and the possibilities offered by tools such as digital twins and artificial intelligence, it is possible to work on a generation of intelligent systems that can reduce and even avoid these problems. Therefore, this study proposes the creation of a digital twin based on artificial intelligence to work on proactively identifying problems before they happen and, if they are detected, launch an optimization process that offers corrective actions to solve them. More specifically, this work focuses on the analysis of the manufacturing process (definition, KPI extraction, capture, distribution, and visualization), the creation of a base system for the integral management of process optimization, and experiments developed for determining the best method for making predictions. Additionally, we propose a recommender system to (i) avoid the appearance of porosities and (ii) keep the elongation of the parts in the ranges desired by the customer.

Industrial pouring processes operate under highly dynamic conditions where small deviations can lead to defects, scrap, and production losses. Although modern foundries are equipped with multiple sensors and visual inspection systems, most monitoring approaches remain fragmented, unimodal, and difficult to interpret. Furthermore, annotated anomalous samples in industrial settings are scarce, hindering the development of traditional methods. As a result, many critical pouring anomalies are detected too late or lack sufficient contextual information for effective decision making. In this work, we propose a multimodal framework for industrial scene characterisation that combines visual information and process signals through an explainable Mixture-of-Experts (MoE)-style expert-fusion strategy. First, we deploy an ensemble of specialised modules that collaborate to identify regions of interest, assess pouring quality, and contextualise events within the production process, thereby generating an interpretable description of pouring events. Second, we introduce a novel anomaly detection method for multimodal video data, combining a self-supervised transformer with an outlier-aware clustering algorithm. Our approach effectively identifies rare anomalies without requiring extensive manual labelling. The resulting information is structured into a digital twin-ready representation, supporting synchronisation between the physical system and its virtual counterpart. This solution provides a scalable, deployable pathway to transform heterogeneous industrial data into actionable knowledge, supporting advanced monitoring, anomaly detection, and quality control in real foundry environments.

Metallographic analyses of nodular iron casting methods are based on visual comparisons according to measuring standards. In fact, iron foundry workers have a poster that describes several characterizations of the metallographies and, showing the real metal in a microscope, they try to subjectively check the similarity between those examples and the real one. Currently, there are new approaches related to the application of machine vision and deep learning classifications. Although these aforementioned methods are more precise and accurate, they are more resource consuming, difficult to manage, and less scalable than other simpler methods that do not use the classical way of working with images. Moreover, for day-by-day work, this kind of precision is not needed, and this task must be carried out as fast as possible. Hence, this research work presents a novel approach to apply the same kind of comparisons carried out by human beings, but with the precision of a computer. Specifically, we construct a well-characterized vector database, populated with several metallographies analysed using accurate methods. Then, all images are represented by an embedding that tries to transform them into a vector representation to, finally, create the final classification and characterization of a specific metallography when applied a similarity search method in our learnt knowledge database.