This study proposes an active neutral point clamped bidirectional multilevel converter, consisting of cascaded H-bridges fed by flying capacitors and T-type interconnections. It ensures any combination and polarity of flying capacitors in the current path, allowing a simple voltage balancing within the same voltage-pole. The flying capacitor voltages are scaled by factor of 2, enabling multiple switching vector combination for intermediate voltage-poles, as well as extending the number of voltage-poles. The suggested topology can reduce number of switches as compared to the counterparts. The framework also presents a method of balancing capacitor voltage. The feasibility and performance of the proposed solutions are verified by simulation results.

This article proposes an active learning scheme to detect multiple faults in permanent magnet synchronous motors in dynamic operations without using historical labelled faulty training data. The proposed method combines the self-supervised anomaly detector based on a local outlier factor (LOF and a deep Q-network (DQN) supervised reinforcement learner to classify interturn short-circuit, local demagnetisation, and mixed faults. The first fault, which is detected by LOF and verified by an expert during maintenance, is used as training data for the DQN classifier. From that point onward, the LOF anomaly detector and DQN fault classifiers are working in tandem in the identification of new faults, which require expert intervention when either of them identifies a fault. The robustness of the scheme against dynamic operations, mixed fault, and imbalanced training datasets is validated via a comparative study using stray flux data from an in-house test setup.

Due to their superior reliability, efficiency, and robustness as compared to unipolar dc grid systems, bipolar dc grid systems are quickly gaining traction for renewable energy integration. However, progress in developing multiport converters resulting in lower costs, more compact designs, and higher power density in bipolar microgrid systems has been slow. As a result, a new isolated multiport dc-dc converter with bipolar inherently symmetric outputs (MIBDC) is proposed in this study. The suggested converter has a competitive advantage over its few counterparts in terms of the number of input ports, voltage gain, and natural symmetry of the outputs. Furthermore, because the proposed MIBDC uses a fixed transformer with only one primary and secondary winding for any number of inputs, it considerably decreases component count and control complexity. The proposed converter's operation is quantitatively tested in simulation and on OPAL-OP5700 RT's hardware-in-the-loop (HIL) validation platform for independent and simultaneous power transfer from multiple sources with varying voltages.

Bipolar DC grids are gaining great attention in modern power systems due to their superiority over Unipolar DC grids and AC grids. Existing studies on DC microgrid operations and controls individually investigate voltage control and balancing, power-sharing, and fault-tolerant operation. However, simultaneous investigation of voltage control, balancing, fault-tolerant operation and maximizing intermittence renewable energy in bipolar dc grids is important to understand the overall system behaviour. This paper presents a grid-connected bipolar DC microgrid architecture and control strategies to maximize the intermittence renewable energy usage, and reliable operation under fault conditions. The proposed DC microgrid can ensure reliable operation under healthy and faults conditions while utilising a high percentage of renewable energy, being verified through numerical results.

An isolated multiple input dc-dc converter (MIC) with unidirectional buck-boost characteristics and simultaneous power transfer is proposed for multi-sources in renewable energy systems in this paper. When compared to existing isolated MICs, the proposed MIC significantly reduces the component count and control complexity since it requires a fixed coupled inductor with only one primary and secondary winding each for any number of inputs and does not require any phase-shifted pulse-width modulation. The operation of the proposed converter for simultaneous power transfer from multiple sources with varying voltages is numerically verified in simulation and validated on OPAL-RT’s OP5700 hardware-in-the-loop (HIL) validation platform.

This article proposes a novel online fault diagnosis scheme for industrial powertrains without using historical faulty or labeled training data. The proposed method combines a 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.

Pitch systems are among the most failure-prone components in wind turbines. Winding failures in pitch motors are common due to high start-up loads and poor ventilation. This article presents a diagnostics scheme that can detect the stator winding failures in the pitch motors under time-varying speed and load conditions. The proposed approach based on three-phase motor currents can be directly integrated into the motor drive and can be used for induction as well as permanent magnet synchronous machines. The extended Park's vector calculated on the motor currents is order tracked based on the supply frequency from the drive using Vold-Kalman filter. The approach is shown to be robust under arbitrary load and speed variations in a laboratory setup of a pitch drive.

A new multilevel converter topology is proposed in this paper. Low component count and compact design are the main features of the proposed topology. Furthermore, the proposed converter is a capacitor-, inductor-, and diode-free configuration, allowing reducing the converter footprint, increasing the lifetime and simplifying the control strategy. Further, a comparative study is carried out to highlight the merits of the proposed circuit as compared to existing multilevel topologies. Finally, simulation results for the three-level version using different modulation strategies are presented.

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.

Thermal protection limits are equally important as mechanical specifications when designing electric drivetrains. However, properties of motor drives like mass/length of copper winding or heat dissipation factor are not available in producers' catalogs. The lack of this essential data prevents the effective selection of drivetrain components and makes it necessary to consult critical design decisions with equipment's suppliers. Therefore, in this paper, the popular loadability curves that are available in catalogs become a basis to formulate a method that allows to estimate temperature rise of motor drives. The current technique allows for evaluating a temperature rise of a motor drive for any overload magnitude, duty cycle, and ambient temperature, contrary to using a discrete set of permissible overload conditions that are provided by manufacturers. The proposed approach is based on industrially adopted practices, greatly improves flexibility of a design process, and facilitates communication in a supplier-customer dialog.