This paper proposes a novel disturbance-observer-based complementary sliding-mode (DO-CSM) speed controller for the field-oriented controlled permanent-magnet synchronous motor (FOC-PMSM) drive system. At first, the rotor speed dynamics of the PMSM drive system considering the lumped disturbance, which consists of external disturbances, parametric uncertainties and unmodeled dynamics, is presented. Then, the classic CSM speed controller using the saturation function and a typical artificial neural network (ANN)-based CSM speed controller, i.e., the Elman NN (ENN)-based intelligent CSM (ENN-ICSM) speed controller for the FOC-PMSM drive system are reviewed. Afterward, the design of the proposed DO-CSM speed controller, which combines the CSM controller using the signum function with the super-twisting sliding-mode observer (STSMO), is presented. In such a speed controller, the rotor speed tracking is accomplished by the adopted CSM controller, whereas the STSMO is employed to estimate and compensate the lumped disturbance in the rotor speed dynamics. Finally, experimental comparisons among the proposed DO-CSM speed controller, the classic CSM speed controller and three selected ENN-ICSM speed controllers are carried out. Experimental results verify the effectiveness and superiority of the proposed DO-CSM speed controller.

This review paper looks briefly at conventional approaches and examines the intelligent means for fault diagnosis (FD) and condition monitoring (CM) of electrical drives in detail, especially the ones that are common in Industry 4.0. After giving an overview on fault statistics, standard methods for the FD and CM of rotating machines are first visited, and then its orientation towards intelligent approaches is discussed. Major diagnostic procedures are addressed in detail together with their advancements to date. In particular, the emphasis is given to motor current signature analysis (MCSA) and digital signal processing techniques (DSPTs) mostly used for feature engineering. Consequently, the statistical procedures and machine learning techniques (stemming from artificial intelligence—AI) are also visited to describe how FD is carried out in various systems. The effectiveness of the amalgamation of the model, signal, and data-based techniques for the FD and CM of inductions motors (IMs) is also highlighted in this review. It is worth mentioning that a variety of neural- and non-neural-based approaches are discussed concerning major faults in rotating machines. Finally, after a thorough survey of the diagnostic techniques based on specific faults for electrical drives, several open problems are identified and discussed. The paper concludes with important recommendations on where to divert the research focus considering the current advancements in the FD and CM of rotating machines.

This review paper comprehensively analyzes the prognosis of rotating machines (RMs), focusing on mechanical-flaw and remaining-useful-life (RUL) estimation in industrial and renewable energy applications. It introduces common mechanical faults in rotating machinery, their causes, and their potential impacts on RM performance and longevity, particularly in wind, wave, and tidal energy systems, where reliability is crucial. The study outlines the primary procedures for RUL estimation, including data acquisition, health indicator (HI) construction, failure threshold (FT) determination, RUL estimation approaches, and evaluation metrics, through a detailed review of published work from the past six years. A detailed investigation of HI design using mechanical-signal-based, model-based, and artificial intelligence (AI)-based techniques is presented, emphasizing their relevance to condition monitoring and fault detection in offshore and hybrid renewable energy systems. The paper thoroughly explores the use of physics-based, data-driven, and hybrid models for prognosis. Additionally, the review delves into the application of advanced methods such as transfer learning and physics-informed neural networks for RUL estimation. The advantages and disadvantages of each method are discussed in detail, providing a foundation for optimizing condition-monitoring strategies. Finally, the paper identifies open challenges in prognostics of RMs and concludes with critical suggestions for future research to enhance the reliability of these technologies.

Proton Exchange Membrane Fuel Cell (PEMFC) systems represent a crucial clean energy component, offering a sustainable alternative to traditional power sources. However, ensuring the dependable and optimal performance of PEMFC systems is essential for their widespread adoption and integration into various applications, ranging from transportation to stationary power generation. To overcome the challenges associated with maintaining the reliability and efficiency of PEMFC systems, there is a growing reliance on Artificial Intelligence (AI)-based diagnosis techniques. AI has emerged as a transformative tool in analyzing complex data patterns, detecting anomalies, and facilitating autonomous decision-making. In the context of PEMFC systems, AI-driven methodologies offer innovative solutions for diagnosing faults, predicting system performance, and optimizing operational parameters. By using AI techniques such as Machine Learning (ML), Neural Networks (NN), expert systems, and data-driven approaches, researchers aim to enhance the reliability, efficiency, and durability of PEMFC systems while minimizing downtime and maintenance costs. The application of AI in PEMFC system diagnosis involves the development of sophisticated algorithms capable of analyzing various data sources, including sensor readings, system parameters, and environmental conditions. These algorithms can detect anomalies, diagnose faults, and provide recommendations for remedial actions in real-time, ensuring continuous and reliable operation of PEMFC systems. While previous papers may have addressed aspects of PEMFC system diagnosis, this comprehensive survey aims to systematically synthesize existing literature to identify shared concepts and research gaps. This extensive survey encompasses a spectrum of AI methodologies, Machine Learning (ML) algorithms, Neural Networks (NN), expert systems, and data-driven approaches associated with diagnosing PEMFC systems. We reviewed over 750 papers to identify shared concepts and real-world implementation issues for future research directions.

This paper proposes an analytical formulation of a maximum torque per ampere (MTPA) technique, accounting for the magnetic saturation of the iron core, specifically developed for Synchronous Reluctance Motors (SynRMs). The proposed MTPA is based on a magnetic saturation model of the SynRM, which has been obtained after simplifying a more complete magnetic model, including also cross saturation effects. This simplified magnetic model, and consequently the proposed MTPA, can be easily parameterized directly starting from a unique set of tests for the off-line identification of the motor, without the need for any complex, time consuming, and cumbersome finite element analysis (FEA) of the machine under test. The proposed MTPA has been tested experimentally on a suitably developed test set-up. Results obtained with the proposed MTPA have been compared experimentally with both the classic MTPA and the real MTPA. Results clearly show that the proposed technique permits a significant increase of the torque per ampere (TPA) with respect to the case of the classic MTPA, which does not consider magnetic saturation. TPA increase varies from 5% at 3 Nm load to 18% at 12 Nm load. Moreover, the loss of maximum torque, with respect to the real MTPA, obtained at the maximum speed and load torque with the proposed MTPA is about 15%, whereas the loss of maximum torque obtained with the classic MTPA is about 38.5%.

The importance of renewable energy exploitation reduces the energy dependence on fossil fuels. Despite technological progress, in several remote areas and small islands the energy production is nowadays dominated by the utilization of fossil fuels. With new, increasingly stringent laws on polluting emissions and the need to lower production costs, it is necessary to exploit as many renewable sources as possible. In order to implement these considerations, it was decided to study renewable energy production. The study was carried out by estimating the energy production on a monthly and annual basis considering a mix of three plants, namely marine, solar, and wind. Simulations on wave production were carried out on a new device developed by the research team at the University of Palermo. In order to be able to perform these simulations, input climate data are required. These data are normally available in literature or obtainable by using specific GIS tools. As criterium, the Levelized Cost of Energy, normally applied to a single technology, is extended to the entire energy mix. Minimizing this parameter, the best solution is individuated, and capable of supplying 50% of the summer electrical load with renewable energy sources. The results carried out from a case study based in aeolian islands show that the solar production reaches 10.2%, the wind production reaches 45.47% and sea wave production reaches 3.04%. In this way, the diesel production decreases to 41.29%. This method can be easily applied for several small islands, estimating for several sites the ability to reduce the energy production from fossil fuels.