The popularity of railway transportation has been on the rise over the past decades, as it has been able to provide safe, reliable, and highly available service. The main challenge within this domain is to reduce the costs of preventive maintenance and improve operational efficiency. To tackle these challenges, one needs to investigate and provide new approaches to enable quick and timely data collection, transfer, and storage aiming at easier and faster analysis whenever needed. In this thesis, we aim at enabling the monitoring and analysis of collected signal data from a train propulsion system. The main idea is to monitor and analyze collected signal data gathered during the regular operation of the propulsion control unit or data recorded during the regular train tests in the real-time simulator. To do so, we have implemented a solution to enable train signal data collection and its storage into a .txt and .CSV file to be further analyzed in the edge node and in the future connected to the cloud for further analysis purposes. In our analysis, we focus on identifying signal anomalies and predicting potential failures using MathWorks tools. Two machine learning techniques, unsupervised and supervised learning, are implemented. Additionally, in this thesis, we have investigated ways of how data can be efficiently managed. We have also reviewed existing edge computing solutions and anomaly detection approaches using a survey as a suitable method to identify relevant works within the state of the art.

Intelligent manufacturing plays an important role in Industry 4.0. Key technologies such as artificial intelligence (AI), big data analytics (BDA), the internet of things (IoT), cyber-physical systems (CPSs), and cloud computing enable intelligent manufacturing systems (IMS). Artificial intelligence (AI) plays an essential role in IMS by providing typical features such as learning, reasoning, acting, modeling, intelligent interconnecting, and intelligent decision making. Artificial intelligence's impact on manufacturing is involved in Industry 4.0 through big data analytics, predictive maintenance, data-driven system modeling, control and optimization, human-robot collaboration, and smart machine communication. The recent advances in machine and deep learning algorithms combined with powerful computational hardware have opened new possibilities for technological progress in manufacturing, which led to improving and optimizing any business model.

Improvements in energy efficiency in Industry 4.0 is the main imperative in manufacturing. An important challenge in many fields of complex industrial processes is energy-efficient optimization. The basic idea of the energy efficiency optimization algorithm is to find the optimal assigned value of process parameters to achieve the lowest energy cost and the best working conditions. Applying the multi-objective approach for solving real industry optimization problems is a challenging task. Therefore, this chapter provides an overview of the most significant issues in multi-objective optimization problem. Improving energy efficiency with the multi-objective optimization has opened new opportunities for technological progress in Industry 4.0.