Nowadays detection of deterioration of electrical motors is an important topic of research. Vibration signals often carry diagnostic information of a motor. The authors proposed a setup for the analysis of vibration signals of three-phase induction motors. In this paper rotor fault diagnostic techniques of a three-phase induction motor (TPIM) were presented. The presented techniques used vibration signals and signal processing methods. The authors analyzed the recognition rate of vibration signal readings for 3 states of the TPIM: healthy TPIM, TPIM with 1 broken bar, and TPIM with 2 broken bars. In this paper the authors described a method of the feature extraction of vibration signals Method of Selection of Amplitudes of Frequencies – MSAF-12. Feature vectors were obtained using FFT, MSAF-12, and mean of vector sum. Three methods of classification were used: Nearest Neighbor (NN), Linear Discriminant Analysis (LDA), and Linear Support Vector Machine (LSVM). The obtained results of analyzed classifiers were in the range of 97.61 % – 100 %.

Recent developments in electrical power systems are concerned not only with static power flow control but also with their control during dynamic processes. Smart Grids came into being when it was noticed that the traditional electrical power system structure was lacking in reliability, power flow control, and consistency in the monitoring of phasor quantities. The Phasor Measurement Unit (PMU) is one of the main critical factors for Smart Grid (SG) operation. It has the ability to provide real-time synchronized measurement of phasor quantities with the help of a Global Positioning System (GPS). However, when considering the installation costs of a PMU device, it is far too expensive to equip on every busbar in all grid stations. Therefore, this paper proposes a new approach for the Optimum Placement of the PMU problem (OPP problem) to minimize the installed number of PMUs and maximize the measurement redundancy of the network. Exclusion of the unwanted nodes technique is used in the proposed approach, in which only the most desirable buses consisting of generator bus and load bus are selected, without considering Pure Transit Nodes (PTNs) in the optimum PMU placement sets. The focal point of the proposed work considers, most importantly, the case factor of the exclusion technique of PTNs from the optimum PMU locations, as prior approaches concerning almost every algorithm have taken PTNs as their optimal PMU placement sets. Furthermore, other case factors of the proposed approach, namely, PMU channel limits, radial bus, and single PMU outage, are also considered for the OPP problem. The proposed work is tested on standard Institute of Electrical and Electronics Engineering (IEEE)-case studies from MATPOWER on the MATLAB software. To show the success of the proposed work, the outputs are compared with the existing techniques.

Fault diagnosis techniques of electrical motors can prevent unplanned downtime and loss of money, production, and health. Various parts of the induction motor can be diagnosed: rotor, stator, rolling bearings, fan, insulation damage, and shaft. Acoustic analysis is non-invasive. Acoustic sensors are low-cost. Changes in the acoustic signal are often observed for faults in induction motors. In this paper, the authors present a fault diagnosis technique for three-phase induction motors (TPIM) using acoustic analysis. The authors analyzed acoustic signals for three conditions of the TPIM: healthy TPIM, TPIM with two broken bars, and TPIM with a faulty ring of the squirrel cage. Acoustic analysis was performed using fast Fourier transform (FFT), a new feature extraction method called MoD-7 (maxima of differences between the conditions), and deep neural networks: GoogLeNet, and ResNet-50. The results of the analysis of acoustic signals were equal to 100% for the three analyzed conditions. The proposed technique is excellent for acoustic signals. The described technique can be used for electric motor fault diagnosis applications.

Inter-turn short-circuit faults (ITSC) in the stator winding of large synchronous machines are among the most critical failures in power systems and may lead to severe insulation damage and unplanned outages. At the same time, such faults, due to their nature in critical industrial scenarios, make it difficult to collect sufficiently rich labeled datasets for data-driven and deep-learning-based diagnostic methods. Training diagnostic models purely on simulated signals often results in a severe domain shift between the digital twin and the physical machine due to nonlinearities, mechanical noise, and measurement imperfections, causing a significant degradation of performance when the model is deployed in practice. This paper proposes a hybrid diagnostic framework that combines a nonlinear physics-based digital twin of a synchronous machine, formulated using an extended Park’s transformation model with a dedicated fault loop, with a Domain-Adversarial Neural Network (DANN) driven by a minimal physics-guided feature vector composed of the 100 Hz and 200 Hz harmonic amplitudes of the excitation current. Simulated data from the digital twin are used as a labeled source domain, whereas test-bench measurements of the excitation current form an unlabeled target domain, enabling unsupervised sim-to-real transfer of the stator fault resistance. The proposed architecture achieves accurate regression of the stator fault-loop resistance on a laboratory machine without any labeled measurements of real faults. Experimental results demonstrate Mean Absolute Error (MAE) below 3% across the investigated fault severity range, significantly outperforming baseline approaches that lack domain adaptation. The industrial significance of this approach lies in its potential to facilitate a transition from reactive to predictive maintenance. By enabling early-stage detection, the framework allows power plant operators to avoid catastrophic failures and significantly reduce exceptionally high costs associated with unplanned outages and cascading grid disturbances.