Faeez Masurkar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Faeez Masurkar has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Nitesh Prakash Yelve
Indian Institute of Technology Bombay
5 shared publications Peter Tse
Department of Systems Engineering and Engineering Management, City University of Hong Kong, Kowloon Tong, Hong Kong
5 shared publications- Peter W. Tse
Department of Systems Engineering and Engineering Management, City University of Hong Kong, Hong Kong, China
5 shared publications Peter W. Tse
3 shared publications- Javad Rostami
City University of Hong Kong
2 shared publications Kim Ming Ng
Smart Engineering Asset Management Laboratory (SEAM) and Croucher Optical Non-Destructive Testing and Quality Inspection Laboratory (CNDT), Department of Systems Engineering and Engineering Management, City University of Hong Kong, Kowloon, Hong Kong
2 shared publications
Latest Publications
- Open Access
- 17 September 2026
- Published by AccScience Publishing in International Journal of AI for Materials and Design
- Vol. 3 (3) , 026310028
Physics-guided machine learning for ultrasonic crack-depth quantification in laboratory rail specimens using laser ultrasonics
Accurate quantification of crack depth is essential for ensuring the structural integrity and operational safety of railway infrastructure. Conventional ultrasonic inspection techniques primarily focus on defect detection and often require baseline measurements or expert interpretation, limiting their suitability for autonomous structural health monitoring. This study proposes a physics-guided machine learning (ML) framework for baseline-free ultrasonic crack-depth quantification in rail-track structures using ultrasonic guided-wave and data-driven regression models. Rayleigh-wave ultrasonic signals were acquired from 13 rail specimens, comprising three healthy specimens and ten specimens with crack depths ranging from 2 to 20 mm. Each specimen was tested 25 times, resulting in a database of 325 ultrasonic measurements. After signal preprocessing, nine physics-guided damage-sensitive features, including amplitude, energy, attenuation, arrival time, and wavelet-based descriptors, were extracted to characterize crack-induced changes in wave propagation. Four regression algorithms, namely Gradient Boosted Regression Trees (GBRT-LSBoost), Random Forest (RF), Support Vector Regression (SVR), and Gaussian Process Regression (GPR), were evaluated using independent test data and specimen-wise, grouped cross-validation. Model interpretability and robustness were further assessed through feature importance, permutation importance, feature ablation, correlation analysis, and uncertainty quantification. The results show that amplitude and attenuation-based features are the most influential predictors of crack depth, whereas time-of-flight and several wavelet features contribute marginally. Among the four nonlinear ML models, Random Forest achieved the best independent-test performance (R² = 0.961, RMSE = 1.610 mm), closely followed by GBRT-LSBoost (R² = 0.960, RMSE = 1.623 mm) which could be suitable for field deployment under complex and dynamic conditions. Notably, a peak-amplitude-only linear regression baseline achieved lower error (R² = 0.995, RMSE = 0.563 mm), demonstrating the strong approximately linear relationship between transmitted Rayleigh-wave amplitude and prescribed crack depth under the controlled laboratory conditions. The results demonstrate the feasibility of the proposed feature-level physics-guided regression framework under controlled laboratory conditions, while further validation using a larger number of independent specimens and naturally occurring service cracks is required before field deployment.
- 17 September 2026
- Published by AccScience Publishing in International Journal of AI for Materials and Design
- Vol. 3 (3) , 026310028
Open AccessPhysics-guided machine learning for ultrasonic crack-depth quantification in laboratory rail specimens using laser ultrasonics
Accurate quantification of crack depth is essential for ensuring the structural integrity and operational safety of railway infrastructure. Conventional ultrasonic inspection techniques primarily focus on defect detection and often require baseline measurements or expert interpretation, limiting their suitability for autonomous structural health monitoring. This study proposes a physics-guided machine learning (ML) framework for baseline-free ultrasonic crack-depth quantification in rail-track structures using ultrasonic guided-wave and data-driven regression models. Rayleigh-wave ultrasonic signals were acquired from 13 rail specimens, comprising three healthy specimens and ten specimens with crack depths ranging from 2 to 20 mm. Each specimen was tested 25 times, resulting in a database of 325 ultrasonic measurements. After signal preprocessing, nine physics-guided damage-sensitive features, including amplitude, energy, attenuation, arrival time, and wavelet-based descriptors, were extracted to characterize crack-induced changes in wave propagation. Four regression algorithms, namely Gradient Boosted Regression Trees (GBRT-LSBoost), Random Forest (RF), Support Vector Regression (SVR), and Gaussian Process Regression (GPR), were evaluated using independent test data and specimen-wise, grouped cross-validation. Model interpretability and robustness were further assessed through feature importance, permutation importance, feature ablation, correlation analysis, and uncertainty quantification. The results show that amplitude and attenuation-based features are the most influential predictors of crack depth, whereas time-of-flight and several wavelet features contribute marginally. Among the four nonlinear ML models, Random Forest achieved the best independent-test performance (R² = 0.961, RMSE = 1.610 mm), closely followed by GBRT-LSBoost (R² = 0.960, RMSE = 1.623 mm) which could be suitable for field deployment under complex and dynamic conditions. Notably, a peak-amplitude-only linear regression baseline achieved lower error (R² = 0.995, RMSE = 0.563 mm), demonstrating the strong approximately linear relationship between transmitted Rayleigh-wave amplitude and prescribed crack depth under the controlled laboratory conditions. The results demonstrate the feasibility of the proposed feature-level physics-guided regression framework under controlled laboratory conditions, while further validation using a larger number of independent specimens and naturally occurring service cracks is required before field deployment.
- Open Access
- 15 August 2026
- Published by IntechOpen
Nondestructive Testing of Underwater Unmanned Vehicles Using Guided Waves
The present study focuses on detection and localization of disbond damage in hybrid composites used in fabricating the outer body structure of autonomous underwater unmanned vehicles (AUVs). This is accomplished by employing ultrasonic guided waves (UGW) generated through piezoelectric transducers (PZTs) that are permanently affixed to the bodies of AUVs. The suitable excitation frequency of ~250 kHz was determined through dispersion analysis and wave-structure analysis. Thereafter, a Gaussian-windowed tone-burst signal centered at 250 kHz was used as an excitation signal to excite ultrasonic guided waves in the submerged structure. Numerical simulations showed the propagation of guided wave modes as well as Scholte waves at the solid-water interface. In disbonded specimens, mode conversion and additional scattered wave packets were seen due to the interaction between the waves and the damage. This interaction allowed for the detection and localization of damage through time-domain signal analysis. Both the simulation and experimental results showed good agreement with a maximum error under 1.5%. Thus, the proposed approach shows strong potential for nondestructive testing (NDT) of underwater AUVs with cost-effective permanently attached PZT sensors.
- 15 August 2026
- Published by IntechOpen
Open AccessNondestructive Testing of Underwater Unmanned Vehicles Using Guided Waves
The present study focuses on detection and localization of disbond damage in hybrid composites used in fabricating the outer body structure of autonomous underwater unmanned vehicles (AUVs). This is accomplished by employing ultrasonic guided waves (UGW) generated through piezoelectric transducers (PZTs) that are permanently affixed to the bodies of AUVs. The suitable excitation frequency of ~250 kHz was determined through dispersion analysis and wave-structure analysis. Thereafter, a Gaussian-windowed tone-burst signal centered at 250 kHz was used as an excitation signal to excite ultrasonic guided waves in the submerged structure. Numerical simulations showed the propagation of guided wave modes as well as Scholte waves at the solid-water interface. In disbonded specimens, mode conversion and additional scattered wave packets were seen due to the interaction between the waves and the damage. This interaction allowed for the detection and localization of damage through time-domain signal analysis. Both the simulation and experimental results showed good agreement with a maximum error under 1.5%. Thus, the proposed approach shows strong potential for nondestructive testing (NDT) of underwater AUVs with cost-effective permanently attached PZT sensors.
- Open Access
- 23 September 2025
- Published by AccScience Publishing in International Journal of AI for Materials and Design
- p. 025310028
Structural health monitoring of metal structures using an improved carbon nanotube bucky paper sensor and LSTM neural network
In this paper, an improved fabrication method is presented for fabricating carbon nanotube (CNT) based multi-functional bucky paper (CNT-BP) sensors that will be primarily used for adaptive sensing in structural health monitoring applications. A large number of BPs were fabricated using multi-walled CNTs with varying methanol-CNT compositions, sonication times, temperatures, curing durations, membrane thicknesses, and electrode placements to determine the optimal configuration for large-scale production. The obtained optimal configuration of the ingredients that yields an adequate sensitivity and ductility of the CNT-BP was then employed for measuring the crack propagation behavior in the fatigued samples. Further, a long short-term memory (LSTM)-based neural network was proposed for prognosis in a metallic plate with fatigue crack propagation. The actual crack lengths of the fatigue crack obtained by the high-speed digital camera were correlated with that predicted by the CNT-BP-based model and LSTM, showing good agreement. Thus, the present study demonstrates that the proposed improved method of CNT-BP is highly efficient in the diagnosis and prognosis of fatigue cracks in metallic structures.
- 23 September 2025
- Published by AccScience Publishing in International Journal of AI for Materials and Design
- p. 025310028
Open AccessStructural health monitoring of metal structures using an improved carbon nanotube bucky paper sensor and LSTM neural network
In this paper, an improved fabrication method is presented for fabricating carbon nanotube (CNT) based multi-functional bucky paper (CNT-BP) sensors that will be primarily used for adaptive sensing in structural health monitoring applications. A large number of BPs were fabricated using multi-walled CNTs with varying methanol-CNT compositions, sonication times, temperatures, curing durations, membrane thicknesses, and electrode placements to determine the optimal configuration for large-scale production. The obtained optimal configuration of the ingredients that yields an adequate sensitivity and ductility of the CNT-BP was then employed for measuring the crack propagation behavior in the fatigued samples. Further, a long short-term memory (LSTM)-based neural network was proposed for prognosis in a metallic plate with fatigue crack propagation. The actual crack lengths of the fatigue crack obtained by the high-speed digital camera were correlated with that predicted by the CNT-BP-based model and LSTM, showing good agreement. Thus, the present study demonstrates that the proposed improved method of CNT-BP is highly efficient in the diagnosis and prognosis of fatigue cracks in metallic structures.
- 17 May 2025
- Published by Springer Nature
- p. 469-478
Theoretical Estimation of the Dispersion Curves in an Orthotropic Composite Plate
- 17 May 2025
- Published by Springer Nature
- p. 469-478
Theoretical Estimation of the Dispersion Curves in an Orthotropic Composite Plate
- 17 April 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
- Vol. 236 (15) , 8527-8541
Nondestructive testing of rails using nonlinear Rayleigh waves
The present research focuses on evaluating the dislocation-induced material nonlinearity in rails caused by falling of parapets or large rocks during an earthquake or land-slide and consequently appraising their health status using an amplitude-based nonlinear parameter based on Rayleigh wave propagation. The falling of parapets or large rocks onto the rail is simulated through a laboratory experiment. Several cases are considered here with impacts of varying intensities to demonstrate the capability of the nonlinear parameter in diagnosing such damages in the rails. It is found that for a pristine specimen, the first peak of the amplitude-based nonlinear parameter matches well with the physics-based nonlinear parameter, whereas there is a considerable deviation between the two for the specimen with impact damage. Moreover, the linear ultrasonic parameter is also evaluated for different states of damage for studying its effectiveness in diagnosing impact damages in rails. The results reveal that the nonlinear ultrasonic-based method proposed here is very sensitive and helps characterize the health status of the rails in a baseline-free manner.
- 17 April 2022
- Published by SAGE Publications in Proceedings of the Institution of Mechanical Engineers, Part C: Journal of Mechanical Engineering Science
- Vol. 236 (15) , 8527-8541
Nondestructive testing of rails using nonlinear Rayleigh waves
The present research focuses on evaluating the dislocation-induced material nonlinearity in rails caused by falling of parapets or large rocks during an earthquake or land-slide and consequently appraising their health status using an amplitude-based nonlinear parameter based on Rayleigh wave propagation. The falling of parapets or large rocks onto the rail is simulated through a laboratory experiment. Several cases are considered here with impacts of varying intensities to demonstrate the capability of the nonlinear parameter in diagnosing such damages in the rails. It is found that for a pristine specimen, the first peak of the amplitude-based nonlinear parameter matches well with the physics-based nonlinear parameter, whereas there is a considerable deviation between the two for the specimen with impact damage. Moreover, the linear ultrasonic parameter is also evaluated for different states of damage for studying its effectiveness in diagnosing impact damages in rails. The results reveal that the nonlinear ultrasonic-based method proposed here is very sensitive and helps characterize the health status of the rails in a baseline-free manner.
- 11 January 2021
- Published by Springer Nature
- p. 149-160
Development of Lamb and Rayleigh Wave-Based Nonlinearity Parameters for Estimating the Remnant Life of Fatigued Plate Structures
- 11 January 2021
- Published by Springer Nature
- p. 149-160
Development of Lamb and Rayleigh Wave-Based Nonlinearity Parameters for Estimating the Remnant Life of Fatigued Plate Structures
- 2 November 2020
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 20 (5) , 2678-2693
Interrogating the health condition of rails using the narrowband Rayleigh waves emitted by an innovative design of non-contact laser transduction system
The article reports an innovative optical system that is designed to interrogate the health condition of macroscopically intact rail specimens by measuring its inherent nonlinearity using the narrowband Rayleigh waves. A line-arrayed pattern is developed through the optical system that generates narrowband Rayleigh waves with high power on the surface of the rail. As a result of lattice-anharmonicity, a second harmonic is produced in the wave that is sensed by a scanning laser Doppler vibrometer. The spectral amplitudes of the first and generated second harmonics are used to calculate the inherent nonlinearity using an amplitude-based nonlinearity equation. These measurements are carried out on the head, web, and foot of the rail. The performance of the non-contact experiment is also compared with that of a contact experiment carried out using wedge transducers. The experimentally evaluated nonlinearity of the rail steel is further compared with that obtained using a physics-based nonlinearity equation that relies on the higher-order elastic constants. Agreement of the results shows that the new optical system is effective in generating Rayleigh waves in rails and thereby measuring the inherent nonlinearity of the rail track. The estimation of inherent nonlinearity may help in diagnosing the health status of the macroscopically intact rail specimens in terms of their microstructural consistency and level of dissolved impurities before fixing them on a track.
- 2 November 2020
- Published by SAGE Publications in Structural Health Monitoring
- Vol. 20 (5) , 2678-2693
Interrogating the health condition of rails using the narrowband Rayleigh waves emitted by an innovative design of non-contact laser transduction system
The article reports an innovative optical system that is designed to interrogate the health condition of macroscopically intact rail specimens by measuring its inherent nonlinearity using the narrowband Rayleigh waves. A line-arrayed pattern is developed through the optical system that generates narrowband Rayleigh waves with high power on the surface of the rail. As a result of lattice-anharmonicity, a second harmonic is produced in the wave that is sensed by a scanning laser Doppler vibrometer. The spectral amplitudes of the first and generated second harmonics are used to calculate the inherent nonlinearity using an amplitude-based nonlinearity equation. These measurements are carried out on the head, web, and foot of the rail. The performance of the non-contact experiment is also compared with that of a contact experiment carried out using wedge transducers. The experimentally evaluated nonlinearity of the rail steel is further compared with that obtained using a physics-based nonlinearity equation that relies on the higher-order elastic constants. Agreement of the results shows that the new optical system is effective in generating Rayleigh waves in rails and thereby measuring the inherent nonlinearity of the rail track. The estimation of inherent nonlinearity may help in diagnosing the health status of the macroscopically intact rail specimens in terms of their microstructural consistency and level of dissolved impurities before fixing them on a track.