Search

This paper introduces a sophisticated approach for identifying and categorizing broken rotor bars in direct torque-controlled (DTC) induction motors. DTC is implemented in industrial drive systems as a suitable control method to preserve torque control performance, which sometimes shows its impact on fault-representing frequencies. This is because of the DTC’s closed-loop control nature, whichtriesto reduce speed and torque ripples by changing the voltage profile. The proposed model utilizes the modified Shapley Additive exPlanations (SHAP) technique in combination with gradient-boosting decision trees (GBDT) to detect and classify the abnormalities in BRBs at diverse (0%, 25%, 50%, 75%, and 100%) loading conditions. To prevent overfitting of the proposed model, we used the adaptive fold cross-validation (AF-CV) technique, which can dynamically adjust the number of folds during the optimization process. By employing extensive feature engineering in the original dataset and then applying Shapely Additive exPlanations(SHAP)-based feature selection, our methodology effectively identifies informative features from signals (three-phase current, three-phase voltage, torque, and speed) and motor characteristics. The gradient-boosting decision tree (GBDT) classifier, trained using the given characteristics, extracts consistent and reliable classification performance under different loading circumstances and enables precise and accurate detection and classification of broken rotor bars. The proposed approach (SHAP-Fusion GBDT with AF-CV) is a major advancement in the field of machine learning in detecting motor anomalies at varying loading conditions and proved to be an effective mechanism for preventative maintenance and preventing faults in DTC-controlled induction motors byattaining an accuracy rate of 99% for all loading conditions.

The reliable operation of power transmission networks depends on the timely detection and localization of faults. Fault classification and localization in electricity transmission networks can be challenging because of the complicated and dynamic nature of the system. In recent years, a variety of machine learning (ML) and deep learning algorithms (DL) have found applications in the enhancement of fault identification and classification within power transmission networks. Yet, the efficacy of these ML architectures is profoundly dependent upon the abundance and quality of the training data. This intellectual explanation introduces an innovative strategy for the classification and pinpointing of faults within power transmission networks. This is achieved through the utilization of variational autoencoders (VAEs) to generate synthetic data, which in turn is harnessed in conjunction with ML algorithms. This approach encompasses the augmentation of the available dataset by infusing it with synthetically generated instances, contributing to a more robust and proficient fault recognition and categorization system. Specifically, we train the VAE on a set of real-world power transmission data and generate synthetic fault data that capture the statistical properties of real-world data. To overcome the difficulty of fault diagnosis methodology in three-phase high voltage transmission networks, a categorical boosting (Cat-Boost) algorithm is proposed in this work. The other standard machine learning algorithms recommended for this study, including Support Vector Machine (SVM), Decision Trees (DT), Random Forest (RF), and K-Nearest Neighbors (KNN), utilizing the customized version of forward feature selection (FFS), were trained using synthetic data generated by a VAE. The results indicate exceptional performance, surpassing current state-of-the-art techniques, in the tasks of fault classification and localization. Notably, our approach achieves a remarkable 99% accuracy in fault classification and an extremely low mean absolute error (MAE) of 0.2 in fault localization. These outcomes represent a notable advancement compared to the most effective existing baseline methods.

The hairpin winding configuration has been attracting attention as a solution to increase the power density of electric vehicle motors by enhancing the slot-filling factor. However, this winding configuration brings high AC losses during high-speed operation and we require new approaches to tackle this challenge. This paper considers reducing AC losses by proposing two main methods: correct transposition of conductors in parallel paths, and enhancing the number of conductor layers in a slot. First, the proper connection of conductors in parallel paths is considered, and the essential rules for this purpose are described. Next, the paper uses a numerical approach to deal with the effect of incorrect conductor transposition in winding paths on generating additional AC losses due to circulating currents. Finally, the impact of the number of conductor layers in the mitigation of AC losses is also discussed in detail. According to the results, by increasing the number of layers, ohmic losses in the layer near the slot opening dramatically decrease. For instance, ohmic losses in the layer near the slot opening of the eight-layer setup were 82% less than the two-layer layout.

In order to define the best design structure of the synchronous reluctance motor (SynRM) rotor, optimization must be carried out, implying the selection of the best alternative for each specific criterion. The optimization of an electrical machine is a complicated work involving meeting different criteria requirements while dealing with a range of constraints. In order to implement the optimization, it is necessary to process a huge number of options, changing the combinations of the factors affecting criteria and restrictions, which is a time-consuming process. This research presents the optimization technique that gives a mathematically proven solution of the optimal rotor design of a synchronous reluctance machine obtained by using metamodels in the form of local polynomial approximations. Analysis of the results of numerical modeling and experimental investigation has been performed in order to validate the developed technique and recommendations. SynRM rotor was manufactured, with the stator to be taken from the 1.1 kW W21 WEG induction motor, which makes possible the relevant experimental study. The performance analysis of the developed SynRM is shown in the paper.

Additive manufacturing (AM) is a key technology for advancing many fields, including electrical machines. It offers unparalleled design freedom together with low material waste and fast prototyping, which is why it has become to focus of many researchers. For electrical machines, AM allows the production of designs with optimized mechanical, electromagnetic and thermal parameters. This paper attempts to give the reader an overview of the existing research and thermal solutions which have been realized with the use of AM. These include novel heat sink and heat exchanger designs, solutions for cooling the machine windings directly, and additively manufactured hollow windings. Some solutions such as heat pipes, which have been produced with AM but not used to cool electrical machines, are also discussed, as these are used in conventional designs and will certainly be used for additively manufactured electrical machines in the future.

Electrical machines are to face different challenging factors during operation, such as high unexpected or excessive loads, unusual properties of the working environment, or intense fluctuations in rotation speed. Therefore, maintenance questions and predicting the accuracy of an equipment’s condition have great importance. This study is based on the theory of vibration reliability. This article introduces the most common faults of bearings in electrical machines and discusses their diagnostic possibilities. Experimental setup, as well as studied bearing failures, are described. The accuracy of conducted experiments is introduced.

This paper presents the analytical calculation of the heat transfer coefficient of a complex housing shape of a Totally Enclosed Fan-Cooled (TEFC) industrial machine when it works below 20% of its nominal speed or close to stall. Therefore, passive cooling is dominant, and most of the heat is extracted by the combination of natural convection and radiation phenomena. Under these conditions, the area-based composite approach was used for the development of the analytical calculation method. A test rig using a TEFC Synchronous Reluctance Motor (SynRM) was constructed, and the collected experimental data was used to validate the proposed analytical method successfully.