The Internet of Things (IoT) technologies plays a key role in the Fourth Industrial Revolution (Industry 4.0). This implies the digitisation of the industry and its services to improve productivity. To obtain the necessary information throughout the different processes, useful data streams are obtained to provide Artificial Intelligence and Big Data algorithms. However, strategic decision-making based on these algorithms may not be successful if they have been developed based on inadequate low-quality data. This research work proposes a set of metrics to measure Data Quality (DQ) in streaming time series, and implements and validates a set of techniques and tools that allow monitoring and improving the quality of the information. These techniques allow the early detection of problems that arise in relation to the quality of the data collected; and, in addition, they provide some mechanisms to solve these problems. Later, as part of the work, a use case related to industrial field is presented, where these techniques and tools have been deployed into a data management, monitoring and data analysis platform. This integration provides additional functionality to the platform, a Decision Support System (DSS) named DQ-REMAIN (Data Quality REport MAnagement and ImprovemeNt) , for decision-making regarding the quality of data obtained from streaming time series.

As a consequence of the projected world population growth, world meat consumption is expected to grow. Therefore, meat production needs to be improved, although it cannot be done at any cost. Maintaining the health and welfare status of animals at optimal levels has traditionally been a main concern of farmers, and more recently, consumers. In this article the Poultry Chain Management (PCM) platform is presented. It aims at collecting data across the different phases of the poultry production chain. The collection of this data not only contributes to determine the quality of each phase and the poultry production chain as a whole, but more importantly, to identify critical issues causing process inefficiencies and to support decision-making towards the holistic improvement of the production chain. Results showed that the information gathered can be exploited to make different suggestions to guarantee poultry welfare, and ultimately, improve the quality of the meat.

Zero-Defect Manufacturing (ZDM) is a promising strategy for reducing errors in industrial processes, aligned with Industry 4.0 and digitalization, aiming to carry out processes correctly the first time. ZDM relies on digital tools, notably Artificial Intelligence (AI), to predict and prevent issues at both product and process levels. This study’s goal is to significantly reduce errors in machining large parts. It utilizes data from process models and in situ monitoring for AI-driven predictions. AI algorithms anticipate part deformation based on manufacturing data. Mechanistic models simulate milling processes, calculating tool deflection from cutting forces and assessing geometric and dimensional errors. Process monitoring provides real-time data to the models during execution. The research focuses on a high-value component from the oil and gas industry, serving as a test piece to predict geometric errors in machining based on the deviation of cutting forces using AI techniques. Specifically, an AISI 1095 steel forged flange, intentionally misaligned to introduce error, undergoes multiple milling operations, including 3-axis roughing and 5-axis finishing, with 3D scans after each stage to monitor progress and deviations. The work concludes that Support Vector Machine algorithms provide accurate results for the estimation of geometric errors from the machining forces.

Variational quantum algorithms (VQAs) are hybrid algorithms that combine quantum computing capabilities with classical machine learning (ML) tasks, utilizing classical optimizers to train parametrized quantum circuits. This work demonstrates their practical utility by addressing regression tasks in an industrially relevant context: modelling dendritic solidification in metals, a process crucial for determining mechanical properties in additive manufacturing. By comparing a classical surrogate model based on extreme gradient boosting with a hybrid classical-quantum VQA model, this work shows that VQAs can serve as a viable alternative for computationally expensive surrogate modelling. These findings highlight the potential of VQAs to tackle complex physical phenomena in high-cost computational scenarios, advancing their application in real-world industrial ML challenges.