Somayeh Soroush

Dr. Somayeh Soroush

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
2 October 2026 in Electronics
Verified
Journal Article
Open access
PDF file
SSSomayeh Soroush
Somayeh Soroush
SASamir Abood
Samir Abood
AAAnnamalai Annamalai
Annamalai Annamalai
MCMohamed Chouikha
Mohamed Chouikha
TNTurk Nejress
Turk Nejress
Power electronic systems are evolving from conventional fixed-function converters toward intelligent, adaptive, and cyber-physical energy-conversion platforms in which modulation, predictive control, artificial intelligence (AI), digital twins (DTs), fault diagnosis, and cybersecurity increasingly interact within a unified closed-loop architecture. This paper presents an integrated review and mathematical framework for next-generation modulation and control of power electronic systems, with an emphasis on advanced modulation, predictive control, AI-assisted adaptation, converter-oriented digital state estimation, fault-tolerant operation, and cyber-resilient control. The proposed framework links converter dynamics, state and parameter estimation, physical faults, cyber disturbances, supervisory anomaly assessment, and mode-dependent control reconfiguration. Two clearly separated validation levels complement the literature synthesis: experimentally measured operating data are used to establish physically representative operating conditions, whereas a dedicated converter-control model is used to evaluate closed-loop dynamic resilience. Under a combined physical/cyber disturbance, resilient reconfiguration reduced the post-event speed RMSE from 9.203 to 0.425 rad/s, the peak speed error from 29.999 to 1.724 rad/s, and the maximum current from 69.112 to 10.662 A, while eliminating 829 current-constraint violations observed without resilience. Across 100 randomized Monte Carlo trials, the mean post-event RMSE decreased from 11.951 ± 3.060 to 0.769 ± 0.291 rad/s, with the corresponding 95% confidence interval narrowing from 11.351–12.550 to 0.712–0.826 rad/s. The results provide simulation-based, closed-loop evidence that coordinated state estimation, anomaly assessment, and resilient reconfiguration can substantially limit disturbance propagation while maintaining converter-control performance under combined physical and cyber abnormalities. Hardware-in-the-loop and embedded real-time implementation remain subjects for future validation.

1 October 2026 in Machines
Verified
Journal Article
Open access
PDF file
SSSomayeh Soroush
Somayeh Soroush
SASamir Abood
Samir Abood
AAAnnamalai Annamalai
Annamalai Annamalai
MCMohamed Chouikha
Mohamed Chouikha
TNTurk Nejress
Turk Nejress
This paper presents an adaptive digital twin framework for intelligent fault diagnosis and predictive health monitoring of a coupled multi-machine electric drive system. The experimental platform consists of two synchronous motors and a synchronous generator arranged in an interconnected electromechanical configuration and instrumented through the Lucas-Nülle laboratory platform. A physics-based digital representation is integrated with experimental measurements to reproduce the electrical and mechanical behavior of the drive system under different operating conditions. Physical-to-digital residuals are subsequently used for health assessment, fault detection, fault isolation, and intelligent classification. Experimental validation under five load conditions resulted in mean root-mean-square errors of 0.0391 N·m for torque, 0.1079 A for motor current, and 0.4555 V for motor voltage, with an overall mean normalized RMSE of 4.16%. The experimentally validated healthy-state digital twin was subsequently evaluated using model-based current-sensor, voltage-sensor, and torque-degradation scenarios. Channel-specific residual analysis successfully detected and isolated the abnormalities under investigation. Using digital twin residual features, an Ensemble classifier achieved a test accuracy of 98.61%, outperforming Artificial Neural Network (ANN) and Support Vector Machine (SVM) classifiers. In addition, a prognostic indicator was developed to characterize progressive degradation, with threshold crossings observed at simulated severities of 1.26%, 12.44%, and 17.37% for voltage-sensor deviation, torque degradation, and current-sensor deviation, respectively. The results demonstrate that integrating experimentally validated digital twin modeling, residual-based diagnostics, intelligent classification, and degradation monitoring provides a unified framework for condition assessment of coupled multi-machine electric-drive systems.

14 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SSSomayeh Soroush
Somayeh Soroush
SASamir Abood
Samir Abood
AAAnnamalai Annamalai
Annamalai Annamalai
MCMohamed Chouikha
Mohamed Chouikha
TNTurk Nejress
Turk Nejress
Power electronic systems are evolving from conventional fixed-function converters toward intelligent, adaptive, and cyber-physical energy-conversion platforms in which modulation, predictive control, artificial intelligence (AI), digital twins (DTs), fault diagnosis, and cybersecurity increasingly interact within a single closed-loop architecture. This paper presents an integrated review and unified mathematical framework for next-generation modulation and control of power electronic systems, with emphasis on advanced pulse-width and space-vector modulation, model predictive control (MPC), AI-assisted adaptation, DT-enabled monitoring, fault-tolerant operation, and cyber-resilient control. Unlike conventional reviews that address these technologies independently, the proposed framework links switched-converter dynamics, state and parameter estimation, residual-based diagnosis, physical faults, cyber disturbances, risk-adaptive control, and mode-dependent reconfiguration within a common formulation. The literature synthesis is complemented by an illustrative experimental case study that uses measured electrical machine operating data to evaluate the DT-based diagnostic and monitoring layers of the proposed architecture. Across five evaluated load conditions, the DT maintained a mean normalized root-mean-square error of 4.16%, with health indices remaining above 0.90, demonstrating consistent healthy-state tracking. Under representative injected sensor and torque-degradation scenarios, channel-specific residuals provided clear separation between healthy and abnormal conditions. AI-based residual classification achieved test accuracies above 97% across the evaluated classifiers, with the best-performing model reaching 98.61%. These experimentally grounded results support the feasibility of DT-assisted health assessment and intelligent diagnosis within the proposed cross-layer framework, while closed-loop integration of modulation, predictive control, fault-tolerant reconfiguration, and cyber-resilient operation remains an important direction for future experimental validation.

1 September 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SSSomayeh Soroush
Somayeh Soroush
SASamir Abood
Samir Abood
AAAnnamalai Annamalai
Annamalai Annamalai
MCMohamed Chouikha
Mohamed Chouikha
TNTurk Nejress
Turk Nejress
This paper presents an adaptive digital twin framework for intelligent fault diagnosis and predictive health monitoring of a coupled multi-machine electric drive system. The experimental platform consists of two synchronous motors and a synchronous generator arranged in an interconnected electromechanical configuration and instrumented through the Lucas-Nülle laboratory platform. A physics-based digital representation is integrated with experimental measurements to reproduce the electrical and mechanical behavior of the drive system under different operating conditions. Physical-to-digital residuals are subsequently used for health assessment, fault detection, fault isolation, and intelligent classification. Experimental validation under five load conditions resulted in mean root-mean-square errors of 0.0391 N·m for torque, 0.1079 A for motor current, and 0.4555 V for motor voltage, with an overall mean normalized RMSE of 4.16%. The experimentally validated healthy-state digital twin was subsequently evaluated using model-based current-sensor, voltage-sensor, and torque-degradation scenarios. Channel-specific residual analysis successfully detected and isolated the abnormalities under investigation. Using digital-twin residual features, an Ensemble classifier achieved a test accuracy of 98.61%, outperforming ANN and SVM classifiers. In addition, a prognostic indicator was developed to characterize progressive degradation, with threshold crossings observed at simulated severities of 1.26%, 12.44%, and 17.37% for voltage-sensor deviation, torque degradation, and current-sensor deviation, respectively. The results demonstrate that integrating experimentally validated digital-twin modeling, residual-based diagnostics, intelligent classification, and degradation monitoring provides a unified framework for condition assessment of coupled multi-machine electric-drive systems.