AI Networking Cookbook: Practical recipes for AI-assisted network automation and development
TL;DR
Preliminary results show that the fuzzy logic-based processor described herein can be used for accurately detecting broken bars in induction motors and can be used for accurately detecting broken bars in induction motors.
Results showed that the DSP-based online condition monitoring system was more accurate and better at detecting faults than earlier methods, making it a good fit for usage in industrial applications.
The problem of fault diagnosis in electrical motors has an important impact on the supervision of dynamic systems, and model-based methods are efficient tools for this purpose. In this regard, this work presents a novel method for detecting inter-turn short circuits (ITSCs) in the stator windings of permanent magnet synchronous motors (PMSMs). The approach is based on algebraic identification to process the motor voltage signals, estimating the offsets, amplitudes, and phases of the fundamental and third-harmonic components. Fault detection is performed in two steps: first, a voltage imbalance index is evaluated to determine the presence of abnormal operating conditions. Subsequently, characteristic patterns in the estimated parameters are analyzed to identify both the fault type and the affected phase(s). The experimental results show that single-phase ITSC faults produce a reduction in the offset of the faulted phase together with an increase in its third-harmonic amplitude, whereas phase-to-phase ITSC faults lead to an increase in the offsets of the affected phases and nearly identical third-harmonic amplitudes between them. In both cases, only minor variations are observed in the estimated phase angles. The effectiveness of the proposed methodology is supported through theoretical analysis and validated experimentally using voltage measurements acquired from a PMSM test bench. The results demonstrate that the proposed technique can accurately identify fault conditions through voltage imbalance and harmonic-pattern analysis, providing a practical and computationally efficient methodology for PMSM stator winding fault diagnosis.
The outcomes prove that the integrated technical framework (time-domain features + FR + SVM) provides zero false alarms and a balanced diagnostic system that combines computational speed with high precision.
Capacitor banks are widely used in modern power systems for reactive power compensation and voltage regulation. However, switching operations of mechanically switched capacitors (MSCs) can generate transient phenomena, such as inrush currents, which may resemble fault currents and lead to misoperation of protection systems. Therefore, accurate detection and classification of transient events are essential for reliable system operation. This study proposes a hybrid approach for transient signal analysis and classification by integrating the discrete wavelet transform (DWT) with artificial intelligence (AI) techniques, including probabilistic neural networks and fuzzy inference systems (FIS). The DWT performs time–frequency analysis to extract multi-scale wavelet features from three-phase current signals. The proposed method enables both discrimination between inrush and fault currents and multi-class classification of transient events among six capacitor switching conditions, namely base case, pre-insertion resistor, pre-insertion inductor, current limiting reactor, 6% reactor, and synchronous closing. The methodology is validated using PSCAD/EMTDC simulations under isolated and back-to-back capacitor switching scenarios. The results demonstrate that the proposed DWT–AI approach achieves high classification accuracy exceeding 95%, outperforming conventional methods based on DWT alone and DWT combined with FIS. Furthermore, the proposed method improves protection system performance by reducing false tripping caused by transient inrush currents, while maintaining reliable fault detection capability. The findings confirm that integrating time–frequency signal processing with AI-based classification provides an effective and practical solution for transient event discrimination in MSC capacitor bank systems.
This research presents an internet of things (IoT-based) system for real-time monitoring and control of a three-phase induction motor that enables continuous monitoring, early fault detection, and predictive maintenance, thereby improving overall operational efficiency and reducing downtime.
This paper investigates the diagnosis of Inter-Turn Short-Circuit (ITSC) faults in Permanent Magnet Synchronous Machines (PMSM) under controlled experimental conditions. The study is based on stator current signals acquired for different speeds, load levels, and fault severities. Since time-domain waveforms under variable speed drive do not clearly reveal the fault, Shannon entropy is used to capture variations in signal complexity and extract a discriminative feature. This feature is then used as input to a Multi-Layer Perceptron (MLP) classifier. The experimental results show that the proposed approach can effectively distinguish healthy and faulty conditions, achieving mean values of 92.8% accuracy, 94% precision, 96.6% recall, and 95.2% F1-score. These results demonstrate the potential of Shannon entropy combined with MLP for reliable ITSC fault diagnosis in PMSMs.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.