Diego Vargas

The advent of Industry 4.0 has precipitated the digitization of myriad industrial processes, a feat attributable to the implementation of sophisticated digital enablers such as artificial intelligence (AI) and the Internet of Things (IoT). These technological advances have facilitated the implementation of various innovative applications, especially in the field of predictive maintenance. This approach facilitates more precise estimation of the remaining useful life (RUL) of equipment, determination of the health index (HI) of machinery, and planning of effective maintenance schedules that circumvent unexpected and costly shutdowns in industrial operations. The employment of hybrid approaches founded on machine learning algorithms in the domain of predictive maintenance signifies a perpetually evolving field of research, wherein novel techniques, methodologies, and strategies are proposed to enhance maintenance efficiency and reliability. In order to furnish a substantial and exhaustive compendium of information, a methodical literature review is hereby presented, offering a meticulous survey of the hybrid approaches utilized within this domain. The study analyzed 77 papers from the 914 papers found on the topic, to find and organize the body of knowledge, and presents a lucid taxonomy, the primary algorithms employed in hybrid approaches, the most prevalent datasets, the applicable technology architectures, and the maturity level of these solutions. This study provides a robust conceptual foundation for future research, underscoring the significance of hybrid approaches as a promising field of study, with considerable potential for advancement in the realm of industrial predictive maintenance.

In the ongoing transition to renewable energy sources, power converters have become indispensable. Their prevalence is increasing, enabling efficient energy conversion, enhancing reliability and stability, and optimizing power extraction from renewable sources. Multi-port dc/dc power converters are widely used because they offer advantages in managing multiple sources and loads. However, designing an automatic control system for these converters presents a challenge due to their complexity. Many configurations for multi-port dc/dc power converters have been proposed, featuring diverse combinations of controllers, modulation techniques, and topologies tailored to specific applications. The body of knowledge on these configurations has grown. Yet, papers have been published according to the authors’ areas of specialization, thus generating a scattered and unorganized body of knowledge and making it difficult to discern research trends and open challenges. Previous studies have attempted to organize knowledge about these configurations, but they have not established a systematic mapping process that follows a rigorous and objective methodology. This paper conducts a systematic mapping study on Automatic Control Systems of multi-port dc/dc power converters. Our study analyzed 122 papers from the 777 papers found around the topic to find and organize the body of knowledge on topology, controller, efficiency, number of elements, modulation technique, and practical applications. This systematic mapping provides a foundational framework for researchers, aiming to inspire further exploration and the development of innovative controller systems in multi-port dc/dc power converters. We found the application of machine learning techniques in dc/dc power converters constitutes an open challenge in these devices.

Standardization and collaborative integration are fundamental for the implementation of Industry 4.0. The Open Communication Platform Unified Architecture (OPC UA) standard plays a crucial role in communication by enabling the development of heterogeneous systems and facilitating the seamless exchange of data between devices. To take full advantage of OPC UA’s capabilities, it is necessary to unlock other application services, such as cloud computing. By having more tools at their disposal, industries can increase their efficiency and optimize data-driven decision making. In this study, it was proposed to use OPC UA standard in a Client/Server model to leverage OPC UA paradigms along with Software Development Kits (SDKs). The development was carried out using Python as the programming language, both to host the server on a Raspberry Pi 4B and to set up the client on a Personal Computer (PC). This client will centralize the data for sending to the Clever Cloud logging platforms and for web visualization on Tago.IO. The interoperability problem of communicating between two platforms with different Operating Systems (OS) was addressed by integrating the OPC UA standard. The configured interval of 10 s recorded an average of 11.11 s, with a maximum timeout of 59 s for data-logging temperature, pressure, humidity, and altitude. The client proved to be Hypertext Transfer Protocol Secure (HTTPS) compliant, allowing connection to Web platforms.