13 June 2017 in IET Renewable Power Generation
Wave energy is one of the most attractive forms of renewable energy. The reasons include its promising availability, predictability, persistence, and power density. This study focuses on all linear generator designs and technologies which have been used so far in direct‐drive wave energy converters (DD‐WECs). Currently, linear permanent magnet generators (LPMG) have been proposed as the most advantageous generator system developed for DD‐WECs. After a brief description of linear generator based wave energy converters, all proposed state‐of‐the‐art of LPMG topologies available in the literature are discussed and compared in terms of flux path, core type, location of PMs, and etc. In addition, other linear generator technologies such as linear switched reluctance and linear superconducting generators, as an alternative to LPMGs, are reviewed. Finally, based on the surveyed quantitative comparisons performed in previous works, eight major concepts are evaluated in terms of economic and operational aspects.
1 August 2022 in IEEE Access
This article presents an intelligent and accurate framework for fault diagnosis of induction motors using light gradient boosting machine (LightGBM). The proposed framework offers promising generalization ability when the testing data contains new unseen operating conditions unavailable during the training process. After the acquisition of vibration signals and feature extraction in multiple domains, we perform an iterative feature selection (FS) approach by utilizing a modified version of recursive feature elimination (RFE) and the features’ importance scores obtained by LightGBM. To prevent overfitting and subsequent selection bias, an outer resampling loop encompasses the whole process of our RFE-LightGBM algorithm. Moreover, instead of the conventional resampling methods based on K-fold cross-validation (CV) or leave-one-out CV (LOOCV), we use a new scheme called leave-one-loading-out CV ( LOLO-CV ). Leveraging LOLO-CV , the proposed FS method identifies the optimal feature subset, making the fault diagnosis robust under changing operating conditions. Then, the final classification is performed with optimal feature subset by training a new LightGBM model with adjusted hyperparameters employing Bayesian optimization. Experimental results from two real case studies show that our proposed fault diagnosis framework achieves accuracies between 98.55% and 100% for various testing scenarios. For example, for the worst-case testing scenario in the bearing dataset of Case Western Reserve University where the no-load data (0hp) is absent during the training process and is only used for testing, the testing accuracy of LightGBM classifier before and after applying the proposed RFE-LightGBM-FS method is 88.04% to 97.23%, respectively. Using the Bayesian hyperparameter optimization further improves the accuracy to 98.55%.
7 June 2018 in IEEE Transactions on Magnetics
Linear-machine-based direct-drive systems are attracting extensive attention for many industrial applications including wave energy conversion and railway traction. By using a linear machine, the complexity of linear motion systems is considerably reduced due to the elimination of the rotary to linear conversion mechanism. In this paper, a novel linear stator spoke-type permanent magnet (PM) vernier (LSSPMV) machine is presented in which the surface-mounted radial magnets used in conventional linear stator-PM vernier machines are replaced by spoke-type magnets that are magnetized parallel to the direction of motion. The proposed machine adopts a non-magnetic space between PMs and stator pole shoes decreasing the leakage flux and leading to higher flux linkage of armature winding. After designing the proposed LSSPMV machine and comparing it with its existing counterpart, the finite-element method results reveal that the thrust force density and the efficiency of the proposed machine are higher than that of the existing one as a result of utilizing spoke-type PMs.
8 April 2025 in IEEE Transactions on Power Electronics
This study explores alternative framework configurations for adapting thermal machine learning models for power converters by combining transfer learning (TL) and federated learning (FL) in a piecewise manner. This approach inherently addresses challenges such as varying operating conditions, data sharing limitations, and security implications. The framework starts with a base model that is incrementally adapted by multiple clients via adapting three state-of-the-art domain adaptation techniques: fine-tuning, transfer component analysis, and deep domain adaptation. The Flower framework is employed for FL, using federated averaging for aggregation. Validation with field data demonstrates that fine-tuning offers a straightforward TL approach with high accuracy, making it suitable for practical applications. Benchmarking results reveal a comprehensive comparison of these methods, showcasing their respective strengths and weaknesses when applied in different scenarios. Locally hosted FL enhances performance when data aggregation is not feasible, whereas cloud-based FL becomes more practical with a significant increase in the number of clients, addressing scalability and connectivity challenges.
1 January 2025 in IET Electric Power Applications
MKMuhammad Dayyan Hussain Khan
Muhammad Dayyan Hussain Khan
This paper addresses the challenge of limited labelled data in induction machine fault diagnosis by applying deep transfer learning with convolutional neural networks to classify ball bearing health conditions. Specifically, the objective is to classify ring and cage failures in ball bearings using a limited dataset acquired from an experimental test bench. Unlike traditional approaches that rely on vibration sensors, this study uses noninvasive current signals. Moreover, this study introduces a novel preprocessing approach that filters out the fundamental frequency of the current signal to enhance fault‐related harmonics in time–frequency representations generated via continuous wavelet transform and short‐time Fourier transform. Five pre‐trained convolutional neural networks—ResNet18, ResNet50, VGG16, AlexNet and GoogLeNet—are fine‐tuned on these representations, demonstrating up to a 47% improvement in classification accuracy. Furthermore, the approach maintains high accuracy even with only 10% of the original dataset, showcasing its sample efficiency. This work contributes to a scalable and data‐efficient solution for reliable condition monitoring in industrial settings, further advancing the use of current signals for fault diagnosis.