More Like this

1. A Physics-Enhanced CNN–LSTM Predictive Condition Monitoring Method for Underground Power Cable Infrastructure

   https://doi.org/10.3390/a18100600  

   Moutassem, Zaki; Bounaim, Doha; Li, Gang (October 2025, Algorithms)

   Underground high-voltage transmission cables, especially high-pressure fluid-filled (HPFF) pipe-type cable systems, are critical components of urban power networks. These systems consist of insulated conductor cables housed within steel pipes filled with pressurized fluids that provide essential insulation and cooling. Despite their reliability, HPFF cables experience faults caused by insulation degradation, thermal expansion, and environmental stressors, which, due to their subtle and gradual nature, complicate incipient fault detection and subsequent fault localization. This study presents a novel, proactive, and retrofit-friendly predictive condition monitoring method. It leverages distributed accelerometer sensors non-intrusively mounted on the HPFF steel pipe within existing manholes to continuously monitor vibration signals in real time. A physics-enhanced convolutional neural network–long short-term memory (CNN–LSTM) deep learning architecture analyzes these signals to detect incipient faults before they evolve into critical failures. The CNN–LSTM model captures temporal dependencies in acoustic data streams, applying time-series analysis techniques tailored for the predictive condition monitoring of HPFF cables. Experimental validation uses vibration data from a scaled-down HPFF laboratory test setup, comparing normal operation to incipient fault events. The model reliably identifies subtle changes in sequential acoustic patterns indicative of incipient faults. Laboratory experimental results demonstrate a high accuracy of the physics-enhanced CNN–LSTM architecture for incipient fault detection with effective data feature extraction. This approach aims to support enhanced operational resilience and faster response times without intrusive infrastructure modifications, facilitating early intervention to mitigate service disruptions. 

   more » « less
2. Echo-AE: A Physics-Informed Seq2Seq-Attention-Autoencoder for Predictive Maintenance of Underground Power Cable Infrastructure

   Moutassem, Zaki; Bounaim, Doha; Li, Gang (October 2025, Reliability engineering systems safety)

   Predictive maintenance for underground high-pressure fluid-filled (HPFF) power cables remains a critical challenge due to the weak and intermittent nature of fault-induced signals and the limited accessibility of buried infrastructure. This paper proposes a physics-informed Seq2Seq-attentionautoencoder acoustic monitoring (Echo-AE) model for predictive maintenance in underground HPFF cable systems. The Echo-AE model is developed based on a physics-informed loss function that incorporates both physics-based constraints and prediction errors. A controlled experimental setup of underground HPFF cable systems was used to capture continuous acoustic monitoring data, where three fault severity levels were generated, resulting in 4 million acoustic samples spanning normal operations and 15 fault events, and producing an imbalanced dataset with a 117:1 normal-tofault ratio to simulate real-world scenarios in which early-stage faults are rare. Results demonstrated Echo-AE’s superior early-stage fault detection capability compared with traditional models, with an F1-score of 0.8313, precision of 0.7864, recall of 0.8816, and an accuracy of 0.9936. The model exhibits fast convergence (20 epochs) and an area under the receiver operating characteristic curve of 0.998. Threshold sensitivity analysis revealed an optimal operation point that balances false positives and false negatives. 

   more » « less
3. Partial Discharge Localization along Medium Voltage Cables

   https://doi.org/10.1109/IEMDC60492.2025.11061155  

   Dhamala, Bhuban; Ghassemi, Mona (May 2025, IEEE)

   Statistics indicate that more than 85% of equipment failures are related to insulation failure. Such faults can lead to brownouts and blackouts and in the transportation electrification context can also impact the safety of personnel or jeopardize missions, which is highly unacceptable. In this regard, predicting a fault before it occurs to do planned maintenance is needed where partial discharge (PD) activity can be used as an indicator. The paper presents a model based on the time of arrival (ToA) approach for PD localization in medium voltage (MV) cables which are a critical component in powertrains and distribution grid connections. The cable considered, which is a three-phase MV cable with three single-core armored copper conductors is modeled using a frequency-dependent wideband model in EMTP. The model accurately represents the cable's behavior by incorporating the skin effect and the impact of semiconducting layers on signal propagation. The attenuation coefficient is calculated for varying frequencies and lengths to evaluate the effect of the semiconducting metallic screen and attenuation voltages. An empirical relationship is developed by injecting PD signals at predefined locations and analyzing arrival time differences at cable terminals, linking propagation velocity, cable length, and ToA. The proposed methodology ensures precise PD localization, highlighting its potential for enhancing diagnostic accuracy in cable systems. 

   more » « less
4. Smart Coils for Mitigation of Motor Reflected Overvoltage Fed by SiC Drives

   https://doi.org/10.1109/APEC43580.2023.10131221  

   Fard, Majid T.; He, JiangBiao; Sadoughi, Milad; Mirafzal, Behrooz; Fateh, Fariba (March 2023, IEEE)

   High dv/dt from the emerging SiC variable-frequency drives can easily induce overvoltage across the motor stator winding terminals, especially for long-cable-connected and high-voltage motor-drive systems. Due to the fast switching speed and surge impedance mismatch between cables and motors, this overvoltage can be two times or even higher than the DC-bus voltage of the inverter, resulting in motor insulation degradation or irreversible breakdown. The most common solution to mitigate such overvoltage is to install a dv/dt or a sinewave filter at the output of the drive, which decreases the efficiency and power density of the system. Among different stator coils, the first one (close to the drive side) is the most susceptible to insulation breakdown since it experiences higher overvoltage than the others due to the nonlinear distribution of the reflected surge voltages. In this paper, an innovative high-efficiency ultracompact mitigation solution is introduced, which is a tiny auxiliary circuit embedded inside the motor stator (or at the motor terminal box), specifically across the first few coils of each phase (i.e., smart coils). The proposed smart coil circuit effectively mitigates the surge overvoltage, which can be scalable to any type of motor-drive systems, regardless of cable length and semiconductor rise time. The proposed solution can dramatically improve the reliability, efficiency, and power density of motor-drive systems. 

   more » « less
5. Vector based acoustic sensing for mechanical fault classification through convolutional neural networks

   https://doi.org/10.3397/1/377324  

   Ippili, Srinivasa R; Russell, Matthew B; Wang, Peng; Herrin, David W (May 2025, Noise Control Engineering Journal)

   Many industries are keenly interested in detecting and classifying faults before systems are sent to the customer or fail in use. A common approach is measuring the vibration of the machine and then using a classifier to check whether a fault is present. However, this process is difficult to automate because accelerometers are applied to the unit under test and are sometimes difficult to install and maintain due to complicated surface conditions. Accurate contact-based sensing is difficult when trying to check each rotating machinery assembly product during end-of-line quality control examinations or when evaluating the machine health of pre-installed rotating machinery. A deep learning-based fault classification system using both scalar and vector acoustic signals is a promising alternative that can replace the traditional error-prone, contact-based methods. Acoustic sound pressure and particle velocity measurements capture the directional fault signature of the mechanical defects in electric motors, and a one-dimensional convolutional neural networks (1D-CNNs) approach is proposed to process raw sensing data and eliminate the need for manual feature extraction. An experimental case study is performed to test the proposed 1D-CNN based fault classification on three different mechanically faulty electric motors across a variety of speeds. The results from acoustic pressure and particle velocity signals are compared against those from accelerometer signals. The experimental study confirms the feasibility of the proposed 1D-CNN on acoustic signals to be an excellent replacement for contact-based methods when assessing and classifying the machine fault condition. © 2025 Institute of Noise Control Engineering. 

   more » « less