Multilevel inverters have gained increasing interest for advanced energy-conversion systems due to their features of high-quality produced waveforms, modularity, transformerless operation, voltage and current scalability, and fault-tolerant operation. However, these merits usually come with the cost of a high number of components. Over the past few years, proposing new multilevel inverters with a lower component count has been one of the most active topics in power electronics. The first aim of this work is to update and summarize the recently developed multilevel topologies with a reduced component count, based on their advantages, disadvantages, construction, and specific applications. Within the framework, both single-phase and three-phase topologies with symmetrical, and asymmetrical operations are taken into consideration via a detailed comparison in terms of the used component count and type. The second objective is to propose a comparative method with novel factors to take component ratings into account. The effectiveness of the proposed method is verified by a comparative study.

Image-based 3D reconstruction is a challenging task that involves inferring the 3D shape of an object or scene from a set of input images. Learning-based methods have gained attention for their ability to directly estimate 3D shapes. This review paper focuses on state-of-the-art techniques for 3D reconstruction, including the generation of novel, unseen views. An overview of recent developments in the Gaussian Splatting method is provided, covering input types, model structures, output representations, and training strategies. Unresolved challenges and future directions are also discussed. Given the rapid progress in this domain and the numerous opportunities for enhancing 3D reconstruction methods, a comprehensive examination of algorithms appears essential. Consequently, this study offers a thorough overview of the latest advancements in Gaussian Splatting.

Detection and isolation of single and mixed-faults in a gearbox are very important to enhance the system reliability, lifetime, and service availability. This paper proposes a hybrid learning algorithm, consisting of Multilayer Perceptron (MLP)- and Convolutional Neural Network (CNN)-based classifiers, for diagnosis of gearbox mixed faults. Domain knowledge features are required to train the MLP classifier, while the CNN classifier can learn features itself, allowing to reduce the required knowledge features for the counterpart. Vibration data from an experimental setup with gearbox mixed faults is used to validate the effectiveness of the algorithms and compare them with conventional methods. The comparative study shows that accuracies and robustness of the individual MLP- and CNN-algorithms are better than those of the compared methods and can be significantly improved using data fusion at the feature level. Furthermore, the robustness of the algorithm is secured under noises by combining the results of individual classifiers.

This paper proposes a novel online fault diagnosis scheme for industrial powertrains without using historical faulty or labelled training data. The proposed method combines one-class support vector machine (SVM)-based anomaly detection and supervised convolutional neural network (CNN) algorithms to online detect multiple faults and fault severities under variable speeds and loads. The one-class SVM algorithm is to derive a score for defining faults or health classes in the first stage, and the resulting health classes are used as the training data for the CNN-based classifier in the second stage. Within this framework, the self-supervised learning of the proposed CNN algorithm allows the online diagnosis scheme to learn features based on the latest data. The effectiveness of the scheme is validated via a comparison study using experimental data from an in-house test setup. Finally, the online implementation of the proposed scheme on the test setup is briefly introduced.

This paper proposes a method for calculating a health indicator (HI) for low-speed axial rolling element bearing (REB) health assessment by utilizing the latent representation obtained by variational inference using Variational Autoencoders (VAEs), trained on each speed reference in the dataset. Further, versatility is added by conditioning on the speed, extending the VAE to a conditional VAE (CVAE), thereby incorporating all speeds in a single model. Within the framework, the coefficients of autoregressive (AR) models are used as features. The dimensionality reduction inherent in the proposed method lowers the need of expert knowledge to design good condition indicators. Moreover, the suggested methodology allows for setting the probability of false alarms when encoding new data points to the latent variable space using the trained model. The effectiveness of the proposed method is validated based on two different datasets: from a workshop test of an offshore drilling machine and from an in-house test rig for axial bearings. In both datasets, the HI is exceeding the warning and alarm levels with a probability of false alarm (PFA) of 10 –6, and the method is most effective at lower shaft speeds.