Gearboxes are essential mechanical components for power transmission. Among them, planetary gearboxes stand out for their compact design and high reduction ratio, making them particularly advantageous in various sectors such as energy generation, transportation, and robotics. Like all mechanical components under load, they are susceptible to different types of degradation, including wear, cracks, chipping, and even broken teeth. Such defects can negatively impact transmission quality, potentially leading to system shutdowns and endangering operators. This necessitates an autonomous monitoring solution that can respond in real-time. This paper presents a robust monitoring methodology for diagnosing faults in planetary gearboxes. The approach begins with filtering the monitoring signals using Variational Mode Decomposition (VMD). The filtered signal is then transformed into a time–frequency image using Wavelet Transform (WT). These images are subsequently used to train a transfer learning network. To ensure the robustness of the proposed intelligent solution, a data augmentation step is included to address issues of data scarcity and imbalanced datasets. Experimental validation demonstrates the effectiveness of the proposed methodology under different operating conditions. • Autonomous, intelligent fault diagnosis methodology for planetary gearboxes. • Signal filtering using variational mode decomposition for noisy environments. • Solutions to data scarcity and dataset imbalance in intelligent diagnosis.

Lithium-ion battery diagnosis is critical for ensuring optimal performance and mitigating safety risks; however, challenges remain due to overlapping electrochemical processes and dynamic operating conditions. This study introduces the dynamic impedance spectra to enable a comprehensive diagnosis of LIBs’ behaviors with active battery charging. For starters, the voltage drifts caused by the state of charge (SOC) shifts and polarization effects are eliminated by applying a moving average filter. The time-resolved impedance spectra and the corresponding equivalent circuit model (ECM) parameters are extracted and continuously updated to decouple and monitor electrochemical processes across timescales. Kramers-Kronig (K-K) validation confirms the dynamic impedance measurement validity, with residuals below 0.5%. The analysis of ECM parameter evolution provides in-situ insights into the electrochemical dynamics and material properties during the battery charging process.

Bearing monitoring plays an important role in the condition monitoring of wind turbines. Failures in this critical component can lead to unexpected shutdowns, significantly reducing the efficiency of the energy system. Therefore, the implementation of advanced monitoring tools is essential to ensure reliability, availability, and cost-effective operation. Digital Twin (DT) technology enables the achievement of these objectives and helps address the issue of limited data. This paper presents a monitoring methodology based on Digital Twin technology for bearing fault diagnosis. It relies on a four degrees of freedom (4-DOF) bearing model and the simulation of faults that can affect this component. A machine learning-based adaptation is proposed, starting with dimensionality reduction through an encoder network, followed by a hybrid network combining Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM). This network extracts physical information from the model and adapts it to the noise in the experimental fault signatures. The results were obtained through experimental validation using a dataset from the Machinery Failure Prevention Technology (MFPT) demonstrate the effectiveness of this methodology for bearing fault diagnosis under various operating conditions.

Tidal stream turbines (TSTs) are crucial for renewable energy generation but face challenges from marine biofouling , significantly impacting their efficiency. Traditional methods for predicting performance and detecting biofouling rely on empirical models and manual inspections, which are often time-consuming and less accurate. This study introduces RegStack, a novel machine learning-based ensemble model, to enhance the prediction of power and thrust coefficients ( C P and C T ) and accurately classify biofouling levels in TSTs. Unlike conventional models, RegStack integrates L1 and L2 regularization into a stacking framework, improving robustness, generalization, and interpretability. The model dynamically balances the strengths of multiple regression and classification algorithms , optimizing predictive accuracy while mitigating overfitting. Comprehensive experiments were conducted using an extensive dataset of tidal stream turbine performance metrics under varying operational and environmental conditions. The RegStack model outperformed conventional approaches, achieving a coefficient of determination ( R 2 ) of 0.989 for performance predictions, with minimal mean absolute error (MAE) and mean squared error (MSE). Additionally, the model achieved 98.39% classification accuracy , with precision and recall of 0.97, and an F1-score of 0.97 in biofouling detection, demonstrating its effectiveness in real-time turbine health monitoring. By providing an automated, data-driven alternative to traditional methods, this study underscores the potential of advanced machine learning techniques in optimizing TST operations, reducing maintenance costs, and enhancing the reliability of marine renewable energy systems. The proposed RegStack model offers a scalable framework applicable to other renewable energy technologies , supporting sustainable energy advancements.

Prognostic learning systems (PLS) primarily rely on and delve into understanding the behavior of degradation lifecycles. Linear degradation often serves as the prevailing trend for labeling performance indicators (PI) in Remaining Useful Life (RUL) or Health Index (HI) estimations. Nevertheless, some studies explore deriving HI directly from PI, capturing state of health (SoH) variations more effectively. Disregarding the impact of operating condition disturbances on PI measurements reveals that systems do not strictly follow a linear degradation path during deterioration. At certain Health Stages (HS), a system maintains a specific SoH before continuing to deteriorate, sometimes even briefly returning to a better SoH. These multivariate conditions (MVC) arise from factors such as integrated control systems and system resilience. In this less-explored perspective, following procedural data preprocessing, this study aims to enhance data quality in terms of RUL ground truth labeling by considering aspects of temporary stability and performance backup. To assess data quality improvements, a comparative study investigates various adaptive learning systems across multiple evaluation stages and metrics, focusing on generalization as the main criterion for accuracy assessment. Recognizing the inherent non-linearity in PI degradation patterns has proven to be a pivotal element in cleansing feature spaces for PLS, consequently bolstering its generalization capability. This enhancement ultimately contributes to the development of more effective maintenance schedules.

The increasing reliance on advanced power systems in critical infrastructure highlights the need to enhance cybersecurity resilience. This study tackles this crucial issue through Exploratory Data Analysis (EDA) and Representation Learning (RL). Several real-world, complex power system datasets characterized by their large size, dynamic nature, and high imbalance are examined. EDA serves as a fundamental step to provide insights into power system event scenarios, supported by a comprehensive preprocessing strategy that includes managing missing values, reducing dimensionality, denoising, removing outliers, and addressing class imbalance. Missing values are thoughtfully handled by evaluating mean values. Dimensionality reduction involves removing insignificant features that might provide misleading information, along with integrating Principal Component Analysis (PCA). Class-specific denoising and outlier removal follow, with denoising utilizing various algorithms and a diverse range of wavelet functions to improve data quality. Robust outlier removal is achieved through iterative analyses and distance-based techniques. To address class imbalance, the Synthetic Minority Over-Sampling Technique (SMOTE) is employed, ensuring a balanced and representative dataset. For RL, deep learning models such as Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Units (GRU), and their Multiverse Recurrent Expansions with Multiple Repeats (MV-REMR) are used in a comparative study. The results demonstrate promising and satisfactory outcomes for all models, with MV-REMR delivering the best performance. This study integrates diverse techniques into a unified EDA and RL approach, offering valuable insights into power system cybersecurity forensics, addressing current challenges, and promoting resilient and adaptive cybersecurity measures in power systems.

Smart grids have emerged as a complex structure integrating communication networks, distributed energy resources, and intelligent devices. However, this integration has resulted in the manifestation of various vulnerabilities, raising signifi-cant security concerns and challenges. Present-day smart grids are vulnerable to various cyberattacks, and researchers have dedicated efforts to detect, mitigate, and prevent these attacks using diverse techniques. This paper focuses specifically on replay attacks within smart grids, recognizing the critical need to address this particular threat. Through a comprehensive review of existing literature regarding the detection, mitigation, and prevention of replay attacks across smart grids, microgrids, and cyber-physical systems (CPSs), we aim to provide insights into effective defense strategies applicable to various interconnected energy infrastructures.

Biofouling poses a significant challenge to the efficiency and performance of tidal stream turbines. This study proposes a novel approach utilizing Fast R-CNN for biofouling detection and coverage estimation in tidal stream turbines. We use a real biofouling dataset collected from four turbines installed on the pier of Ikitsuki Bridge in Hirado, Nagasaki, Japan, over 8 months, containing both clean and biofouled turbine images. Employing various augmentation techniques, we enhanced the dataset’s robustness. Our method achieved a remarkable 94% accuracy in detecting and classifying biofouled turbine blades. Additionally, using the OpenCV library in Python, we estimated the extent of biofouling coverage on turbine blades, offering valuable insights for maintenance and optimization efforts and assisting informed decision-making on strategies for tidal stream turbine maintenance and performance optimization.

It has been shown that an analytical model including amplitude, phase shift, and the mean value of the phase currents in seven-phase electrical machines can be used as relevant information for fault detection, isolation, and estimation. However, this model fails to estimate the fault severity accurately under noisy conditions, especially for faults affecting the mean value. Therefore, the model is extended with the noise as the fourth parameter. Two approaches are considered before the estimation performance is evaluated: the noise level is estimated, or the currents are first denoised. The simulation results with different combinations of noise level and fault severity show that both approaches are efficient and enhance the fault severity estimation, even under high-noise conditions (SNR as low as 5dB). Besides, the analytical model, including the noise, agrees well with the numerical model.

This study addresses the biofouling challenges in Tidal Stream Turbines (TSTs) to ensure their reliable and optimal operation. In this context, it is proposed an effective methodology employing a soft voting ensemble transfer learning-based approach for the detection and extent classification of biofouling. The proposed framework incorporates essential components such as data augmentation and pre-processing, including image resizing and data segmentation, forming a comprehensive video image-based approach. To overcome the constraint of limited data, experimental investigations were conducted, resulting in the acquisition of two datasets: one from the TST platform at Shanghai Maritime University (SMU) and the other from the tidal turbulence test facility at Lehigh University (LU). The three prominent convolutional neural network models, namely Visual Geometry Group (VGG), Residual Network (ResNet) and MobileNet, trained on these datasets, demonstrate precise detection and classification of turbine conditions, achieving an accuracy of 83% for the SMU dataset and 90% for the LU dataset. The noted disparity in accuracy for the SMU dataset is attributed to its smaller size, highlighting the significant impact of dataset scale on classification performance. This study provides valuable insight into the development of effective biofouling detection and classification strategies for TST systems. • Provide a soft voting ensemble transfer learning-based tool for real-time biofouling detection and estimation. • Data augmentation using rotation, scaling, flipping, zooming, and brightening of the cropped input images. • Data pre-processing including image resizing and data segmentation using the segment anything model.

High-speed bearings play a vital role in the functionality of modern wind turbines. Accurately estimating impending failure and predicting the remaining useful life (RUL) of bearings brings significant benefits in scheduling maintenance strategies and preventing sudden turbine shutdowns. This paper discusses a reliability enhancement prognosis framework for high-speed wind turbine bearings based on a measured representative vibration signature. A health indicator is constructed using a sliding window adaptive threshold (SWAT) to map the degradation behavior of the bearings into RUL. The Gated recurrent unit (GRU)-based deep learning algorithm shows promising predictive performance in terms of mean absolute error (MAE) and relative accuracy (RA).

Buildings are one of the prominent sectors among global primary energy consumption. A large portion of this energy consumption is influenced by occupancy interaction with the buildings. Occupancy prediction in buildings without intruding their privacy helps to enhance the building energy management. Due to the complex relations of the inputs and the temporal dependency, modeling accurate occupancy predictions is highly difficult. The use of Deep Learning (DL) algorithms is one of the best approaches for accomplishing this goal. This paper provides an analysis using horizontally cascaded Long Short-Term Memory (LSTM) model as a baseline for occupancy prediction. The proposed horizontally cascaded LSTM model focuses on learning local patterns and dependencies within their input sequences, and both short term and long terms dependencies in temporal direction along with the relation between other input features, allowing for a more comprehensive understanding of the input data. This architecture can capture a broader range of information from the collected building data and learn more heterogeneity in occupancy presence behavior. The models are also compared for different prediction window sizes. The OPTUNA optimization is utilized for hyper-parameter tuning and to determine number of LSTMs to be cascaded. The proposed models function better for smaller window size and optimization of number of cascaded LSTMs are essential for improving the accuracy of the model. The paper also shows that for window sizes, 2–4 LSTMs are optimal to cascade.

This paper investigates the use of transfer learning models for detecting and classifying biofouling extent in tidal stream turbines. It provides a comprehensive exploration of a soft voting ensemble approach to deal with a multiclass image detection problem. In this context, three well-known convolutional neural network models, namely VGG16, ResNet50, and MobileNetV2, are the primary focus of the proposed study and are trained on an experimental dataset issued from the Shanghai Maritime University tidal stream turbine platform.

This paper proposes to map a machine learning path forward for tidal stream turbines biofouling detection and estimation. The proposed review covers an overview of biofouling and its impact on tidal stream turbines, current techniques for detecting and estimating biofouling, recent developments, and challenges in the field, as well as several promising prospects for biofouling detection and estimation.

International audience

International audience

Deployment of autonomous underwater vehicle have became a focal point for many industrial application. The main challenge to the autonomous underwater vehicle is the finite mission time during the operation in a harsh environment. The most efficient way to reduce the operational and maintenance costs, and increase the efficiency of the system, the autonomous under water vehicles have to be recharged under water during the operation. This paper proposes an analysis of one side com-pensation topology and indexes some parameters to be considered when designing an inductive contactless power transfer system for AUV charging.

Despite the rich literature dealing with induction motor faults detection, the automatic decision on the health operating condition has received scarce attention. This paper aims at demonstrating the usefulness of the combination of the Maximum Likelihood (ML) and the detection theory for induction motor faults detection. In particular, it proposes to use stator currents as medium for faults detection. Indeed, under faulty conditions, additional spectral components appear in the stator currents spectrum. This paper proposes to use a constant false alarm rate (CFAR) detector of these components. The objective is to decide between two hypothesis; the motor is healthy or faulty. The generalized likelihood ratio test (GLRT) is used to tackle this binary hypothesis testing problem.Monte Carlo simulations have been performed in order to evaluate the statistical performance of the proposed approach. Then, the proposed algorithm has been evaluated on experimental data for broken rotor bars fault detection.

This paper presents the modeling steps of a shrouded tidal stream turbine. The main goal of this modeling is to allow the behavior simulation of the converter in order to anticipate its operation under specific conditions and its later development. The observation time scale of the operation system may extend from tidal period (several hours) to converter switching period (milliseconds to microseconds). An assessment of different modeling methodology, based on instantaneous and average models, is carried out. Instantaneous modeling offers the possibility to observe system electrical dynamics, which are driven by power switches, at the expense of an important computational time. In that respect, an average modeling is considered for greater period-scale analyses. So as to reduce the computational time induced by the power electronic modeling, cosimulations between Simulink and PSIM are also established. Simulation results are furthermore compared with some experimental data of an industrial shrouded tidal stream turbine prototype immersed and tested in real off-grid condition. The results and differences observed are sufficiently relevant to consider these models as references for further development.

This work presents a variational mode decomposition (VMD) based detector for bearing fault in electrical machines. Its performance is compared to that of the ensemble empirical mode decomposition (EEMD) based. A notch filter based Pearson correlation was developed and used to extract the dominant mode. Experimental results showed that the VMD outperformed in terms of statistical features. As a result, the VMD-based notch filter could be a promising methodology for bearing fault detection and degradation prediction.

This paper deals with the implementation of a Model Predictive Control (MPC) system for a classroom in a container building ventilation system and the associated indoor climate through controlling the airflow rate to the zone. A dynamic thermal model for the building system is formulated using the three resistors and two capacitors (3R2C) lumped capacitance method, and linearized using the Taylor's series expansion. This model is used for the proposed MPC implementation for thermal comfort management with energy optimization. Simulation results demonstrate the significance of the MPC controller in handling the constraints, multi-objective control, and producing optimal control strategy. The energy optimization results of the MPC have shown 31% of energy consumption reduction compared to a conventional controller.

Most of signals in the electrical machines and drives are non-Gaussian and highly nonlinear in nature. A useful set of techniques for examining these kinds of signals relies on the spectral representations of higher-order statistics (HOS), well-known as polyspectra. They describe statistical dependences of frequency components that are neglected by traditional spectral measures. The bispectrum is the most used HOS, and studying higher-order correlations provides more information about the electromechanical system's behavior. It helps in building more accurate diagnostic models. Based on this proper relationship the overall aim of the current work is the interpretation of the stator current tidal turbine bispectrum under imbalanced rotor blades condition. Based on this proper relationship, the overall aim of the current work is the interpretation of the permanent magnet synchronous generator (PMSG)-based tidal current turbine (TCT) stator current bispectrum for the diagnosis of biofouling. The proposed bispectrum-based diagnosis method has been tested using experimental data issued from a TCT experiencing biofouling emulated by an attachment on the turbine rotor. The achieved results clearly indicate the feasibility and efficacy of the proposed method.

Due to the characteristics of predictability and high energy density in tidal current resources, tidal stream turbine generation systems have been developed in the last decades around the world. Speed control would be necessary to perform the maximum power point tracking (MPPT) task under varying marine current conditions. Considering that various disturbances or parameter uncertainties may deteriorate the system performance, the active disturbance rejection control (ADRC) strategy seems to be an interesting solution for controller designs. In this paper, an ADRC strategy is applied in the speed control loop for realizing MPPT under disturbances of current velocity and turbine torque. The system performance of the proposed ADRC is compared with PI and high-order sliding mode (HOSM) control strategies. The operation under swell wave disturbance is also carried out. This simulation-based comparative study shows the effectiveness and advantages of the ADRC controller over conventional PI controller in terms of quick convergence, overshoots elimination, and better performance under disturbances.

In this paper, new frequency and phasor estimators are presented. These estimators are based on the maximum-likelihood technique and exploit the multidimensional nature of electrical signals. To minimize the likelihood function, we present an optimization algorithm based on the Newton-Raphson technique. While the performance of Fourier-based estimators significantly degrades when the window length is not equal to a multiple of the fundamental half-period, the proposed estimators perform well regardless of the window length. Simulation results show that the proposed estimators clearly outperform the discrete-time Fourier transform in terms of total vector error and frequency error whatever the signal-to-noise ratio, harmonic and interharmonic distortion, and off-nominal frequency deviation are. The benefits of the proposed estimators are also illustrated with real power system data obtained from the DOE/EPRI National Database of power system events.

This paper deals with the design and application of an emulator to reproduce the dynamic behavior of of tidal turbines to feed a remote load. The proposed emulator provides a flexible platform to investigate different operating conditions of the tidal turbine, and supervise the system variables in real time. Simulation and experimental results are presented to validate the proposed emulator and illustrate the operation of the proposed topology. This emulator can be used for sizing analysis, site evaluation, testing power converter topologies, and evaluating control strategies.

This paper provides a comparative evaluation of phasor estimation signal processing tools, namely the least square estimator and the linear Kalman filter. Comparative investigations are carried out using simulated signals for a power grid voltage sag disturbance. For both techniques, the fundamental frequency is assumed known, hence the estimated phasor parameters are amplitude and initial phase. Simulation results are provided to highlight each technique suitability and limitations to estimate the phasor for power quality monitoring.

This paper investigates the use of instantaneous symmetrical components (ISCs) for mechanical faults detection in inverter-fed induction motors under closed-loop control. The proposed fault detection approach is based on the computation of the ISCs of the stator currents. The positive sequence power spectral density (PSD) is estimated using ESPRIT and least squares (LS). Then, mechanical fault detection is considered as a binary hypothesis test and solved using the generalized likelihood ratio test (GLRT). Both stator currents and the modulating signals issued from the control-loops are demonstrated to be efficient for fault detection. Simulation results on an analytical model of an inverter-fed induction motor illustrate the effectiveness of the proposed approach, leading to an effective fault detection procedure for load torque oscillation in inverter-fed induction motor under closed-loop operation.

This paper deals with a fault detection method based on an empirically data-driven approach combined to a statistical tool. This approach is an enhanced version of the empirical mode decomposition. The proposed fault detector application to bearing defects in wind turbine based on induction generator clearly shows that it is well suited for stationary and non-stationary behavior regardless the rank of the intrinsic mode function introduced by the fault.

This paper deals with the optimal design and energy management of a hybrid wind/tidal/PV power generation system. The optimal combination of these renewable power sources is achieved using linear programming with high reliability as main constraints under various scenarios/conditions such as the location, solar radiation, and temperature. The proposed optimization approach is assessed for the off-grid site of the Ouessant French Island located in Bretagne (France), where the load demand is about 16GWh/year. The achieved results highlight the efficiency and reliability of the proposed algorithm for sizing a hybrid power generation system to match the site load demand.

This paper deals with a new classification techniques for power quality analysis. Specifically, the proposed technique aims at discriminating between four classes, where each class depends on the number of non-zero symmetrical components. By reformulating the classification problem as a pure model order selection one, we propose a classifier based on Information Theoretical Criteria. The performances of this proposed classifier are evaluated using Monte Carlo simulations with synthetic three-phase signals. Simulation results illustrate the effectiveness of the proposed classifier for power quality disturbances classification.

Smart grids have urged a radical reappraisal of distribution networks and power quality requirements, which demand to continuously monitor grid conditions. This allows for early classification of power quality degeneration. In this context, this paper proposes an improved algorithm for phasor estimation and fault type classification in smart grid applications. The proposed algorithm is specifically composed of two steps: first, the phasor estimation from the input signals, which can be executed on the Phasor Measurement Unit (PMU). While step two concerns the fault type classification using the pha-sor estimation. Specifically, we propose to estimate the phasor parameters, (frequency, amplitude and initial phase) using least square method. Then, fault type classification is obtained using symmetrical component algorithm. The proposed algorithm can be used for the identification of power quality disturbances. It has been evaluated, compared, and studied with simulated data. Simulation results show accurate phasor estimations and accurate fault type classification in presence of noise.

Smart grids have initiated a radical reappraisal of distribution networks function where the integration of renewable energy sources, load demand control, and effective use of the network are indexed as the most important keys for smart grid expansion and deployment regardless each country policies. One of the most efficient ways of effective use of these grids would be to continuously monitor their conditions. This allows for early detection of power quality degeneration facilitating therefore a proactive response, prevent a fault ride-through the renewable power sources, minimizing downtime, and maximizing productivity. In this smart grid context, this paper proposes the evaluation and comparison of advanced signal processing tools, namely the Hilbert transform and the ensemble empirical mode decomposition method for the detection of voltage sags as they are the most commonly encountered power quality disturbances.

This paper deals with the Fault Ride-Through (FRT) capability assessment of a Doubly-Fed Induction Generator (DFIG)-based Wind Turbine (WT) using High-Order Sliding Mode (HOSM) control. Indeed, it has been recently suggested that sliding mode control is a solution of choice to the FRT problem. In this context, this paper proposes HOSM as an improved solution that handle the classical sliding mode chattering problem. Indeed, the main and attractive features of HOSMs are robustness against external disturbances (e.g. grid) and chattering-free behavior (no extra mechanical stress on the drive train). Simulations using the NREL FAST code on a 1.5-MW wind turbine are carried-out to evaluate ride-through performance of the proposed HOSM control strategy in case of grid frequency variations and unbalanced voltage sags.

In recent years the electric power generation has entered into a new development era, which can be described mainly by increasing concerns about climate change, through the energy transition from hydrocarbon to clean energy resources. In order to power system enhance reliability, efficiency and safety, renewable and nonrenewable resources are integrated together to configure so-called hybrid systems. Despite the experience accumulated in the power networks, designing hybrid system is a complex task. It has become more challenging as far as most renewable energy resources are random and weather/climatic conditions-dependant. In this challenging context, this paper proposes a critical state-of-the-art review of hybrid generation systems planning expansion and indexes multi-objective methods as strategies for hybrid energy systems optimal design to satisfy technical and economical constraints.

Failure detection has always been a demanding task in the electrical machines community; it has become more challenging in wind energy conversion systems because sustainability and viability of wind farms are highly dependent on the reduction of the operational and maintenance costs. Indeed the most efficient way of reducing these costs would be to continuously monitor the condition of these systems. This allows for early detection of the generator health degeneration, facilitating a proactive response, minimizing downtime, and maximizing productivity. This paper provides then an assessment of a failure detection techniques based on the homopolar component of the generator stator current and attempts to highlight the use of the Ensemble Empirical Mode Decomposition (EEMD) as a tool for failure detection in wind turbine generators for stationary and non stationary cases.