Abstract
This paper examines the concept of learning factories and their role in addressing contemporary challenges in the production sector. Learning factories integrate learning and production environments, offering hands-on experiences to develop essential competencies for modern manufacturing. Originating from initiatives like the Germany's "Lernfabriken" in the late 1980s and the National Science Foundation's funding in the 1990s, learning factories have gained global prominence. They serve as platforms for research, education, and workforce development, attracting students and workers from diverse sectors. Examples from Europe, the United States, and China illustrate various approaches to leveraging learning factories for industrial advancement and skill development. Overall, learning factories play a vital role in fostering innovation, enhancing competitiveness, and driving economic growth in the manufacturing sector.

Abstract
This study examines the impact of Inverter-Based Distributed Generators (IIDGs) on short-circuit currents detected by the main relay at the head of a radial feeder. It highlights how changes in fault currents induced by these inverter technologies can significantly affect the effectiveness and reliability of network protection systems. Key variables, such as the level of IIDGs penetration and the relative location of faults with respect to the relay, have been identified as influential factors. The significance of these findings lies in their contribution to a deeper understanding of how inverter fault responses and the integration of IIDGs alter fault currents. To mitigate the adverse effects associated with the insertion of IIDGs, a fault-detection and tripping strategy based on the inverse-time overcurrent curve is proposed. The suggested strategies not only improve fault detection accuracy but also ensure an appropriate response to variations in network conditions.

Abstract
Lately, the field of optical computing resurfaced with the demonstration of a series of novel photonic neuromorphic schemes for autonomous and inline data processing promising parallel and light-speed computing. We emphasize the Photonic Extreme Learning Machine (PELM) as a versatile configuration exploring the randomness of optical media and device production to bypass the training of the hidden layer. Nevertheless, the implementation of this framework is limited to having the output layer performed digitally. In this work, we extend the general PELM implementation to an all-optical configuration by exploring the amplitude modulation from a spatial light modulator (SLM) as an output linear layer with the main challenge residing in the training of the output weights. The proposed solution explores the package pyTorch to train a digital twin using gradient descent back-propagation. The trained model is then transposed to the SLM performing the linear output layer. We showcase this methodology by solving a two-class classification problem where the total intensity reaching the camera predicts the class of the input sample.

Abstract
Image segmentation for detecting illegal landfill waste in aerial images is essential for environmental crime monitoring. Despite advancements in segmentation models, the primary challenge in this domain is the lack of annotated data due to the unknown locations of illegal waste disposals. This work mainly focuses on evaluating segmentation models for identifying individual illegal landfill waste segments using limited annotations. This research seeks to lay the groundwork for a comprehensive model evaluation to contribute to environmental crime monitoring and sustainability efforts by proposing to harness the combination of agnostic segmentation and supervised classification approaches. We mainly explore different metrics and combinations to better understand how to measure the quality of this applied segmentation problem.

Abstract
Traditionally, scheduling literature has focused mainly on solving problems related to processing jobs with non- assembly operations. Despite the growing interest in the assembly literature in recent years, knowledge of the problem is still in its early stages in many aspects. In this regard, we are not aware of any previous contributions that address the assembly scheduling problem with just-in-time objectives. To fill this gap, this paper studies the 2-stage assembly scheduling problem minimising the sum of total earliness and total tardiness. We first analyse the relationship between the decision problem and the generation of the due dates of the jobs, and identify the equivalences with different related decision problems depending on the instances. The properties and conclusions obtained in the analysis are applied to design two constructive heuristics and a composite heuristic. To evaluate our proposals, different heuristics from the state-of-the-art of related scheduling problems are adapted, and a computational evaluation is carried out. The excellent behaviour of the proposed algorithms is demonstrated by an extensive computational evaluation.

Abstract
Numerous pose estimation methodologies demonstrate a decrement in accuracy or efficiency metrics when subjected to highly cluttered scenarios. Currently, companies expect high-efficiency robotic systems to close the gap between humans and machines, especially in logistic operations, which is highlighted by the requirement to execute operations, such as navigation, perception and picking. To mitigate this issue, the majority of strategies augment the quantity of detected and matched features. However, in this paper, it is proposed a system which adopts an inverse strategy, for instance, it reduces the types of features detected to enhance efficiency. Upon detecting 2D polygons, this solution perceives objects, identifies their corners and edges, and establishes a relationship between the features extracted from the perceived object and the known object model. Subsequently, this relationship is used to devise a weighting system capable of predicting an optimal final pose estimation. Moreover, it has been demonstrated that this solution applies to different objects in real scenarios, such as intralogistic, and industrial, provided there is prior knowledge of the object's shape and measurements. Lastly, the proposed method was evaluated and found to achieve an average overlap rate of 89.77% and an average process time of 0.0398 seconds per object pose estimation.