Embedded Files
Research Domain
Research Synopsis:
Research Synopsis:
My research domain focuses on advanced manufacturing systems, with applications in smart manufacturing, data-driven artificial intelligence, and sustainable manufacturing.
Cyber-Physical Systems (CPS) in smart manufacturing systems integrate the Industrial Internet of Things (IIoTs), industrial control and monitoring systems, and Big Data analytics into manufacturing operations. The resilience of CPS enhances the safety, security, and reliability of advanced manufacturing processes.
The rapid evolution of IIoTs and advanced sensor technologies, coupled with data-driven AI, is revolutionizing smart manufacturing by moving beyond basic shop floor automation toward systems characterized by autonomous, interconnected machines enabled through advanced sensor fusion.
These objectives align with various research initiatives and funding organizations, including NSF (via CMMI), DOE-AMO, and ARO.
To enable successful on-demand smart manufacturing systems, my research focuses on:
integrating cost-effective smart sensors into existing machinery for digital transformation.
employing data-driven AI methodologies for process monitoring and optimization.
enhancing the cyber-physical resiliency of advanced manufacturing operations.
Research Contributions
Cyber-physical security for additive manufacturing
Cyber-physical security for additive manufacturing
Objective: To detect process alteration due to cyber-attacks in real-time based on noisy optical videos.
Objective: To detect process alteration due to cyber-attacks in real-time based on noisy optical videos.
Methodologies:
Captured layer-wise video acquisition of fused filament fabrications (FFF).
Image processing with adaptive thresholding, image segmentation, image binarization.
Multi-dimensional tensor decomposition and feature extraction from layer-wise texture descriptor tensors.
Anomaly detection with Hotelling's T2 monitoring statistics.
✳️Funding: National Science Foundation (NSF)-(No. CMMI-2046515).
Selected publications:
Mamun, A. A., Liu, C., Kan, C., & Tian, W. (2022). Securing cyber-physical additive manufacturing systems by in-situ process authentication using streamline video analysis. Journal of Manufacturing Systems, 62, 429-440. https://doi.org/10.1016/j.jmsy.2021.12.007 (✳️)
Mamun, A. A., Liu, C., Kan, C., & Tian, W. (2021). Real-time process authentication for additive manufacturing processes based on in-situ video analysis. Procedia Manufacturing, 53, 697-704. https://doi.org/10.1016/j.promfg.2021.06.068
Shi, Z., Mamun, A. A., Kan, C., Tian, W., & Liu, C. (2023). An LSTM-autoencoder based online side channel monitoring approach for cyber-physical attack detection in additive manufacturing. Journal of Intelligent Manufacturing, 1-17. https://doi.org/10.1007/s10845-021-01879-9
Condition monitoring and diagnosis of rotating machinery
Objective: Multi-channel sensor fusion for real-time bearing fault diagnosis based on acoustics and vibration signals.
Objective: Multi-channel sensor fusion for real-time bearing fault diagnosis based on acoustics and vibration signals.
Methodologies:
Conducted experimentation with the Machinery Fault Simulator® (MFS), applying multi-channel vibro-acoustic sensors for condition monitoring.
Developed sensor-fusion based novel algorithm with tensor decomposition to diagnose faults in the rotary machinery.
Developed a model for missing data imputation through Bayesian CP tensor factorization.
Developed a domain adaptation-based modeling using heterogeneous data for fault diagnosis.
Funding:
🔷The U.S. Army Engineer Research and Development Center (ERDC), Institute of Systems Engineering Research (ISER).
✳️National Science Foundation (NSF)-(No. CMMI-2046515).
Selected publications:
Mamun, A. A., Bappy, M. M., Mudiyanselage, A. S., Li, J., Jiang, Z., Tian, Z., ... & Tian, W. (2023). Multi-channel sensor fusion for real-time bearing fault diagnosis by frequency-domain multilinear principal component analysis. The International Journal of Advanced Manufacturing Technology, 124(3), 1321-1334. https://doi.org/10.1007/s00170-022-10525-4 (🔷)
Mamun, A. A., Bappy, M. M., Bian, L., Fuller, S., Falls, T. C., & Tian, W. (2023). Missing signal imputation for multi-channel sensing signals on rotary machinery by tensor factorization. Manufacturing Letters, 35, 1109-1118. https://doi.org/10.1016/j.mfglet.2023.08.097 (✳️)
Mamun, A. A., Guerra-Zubiaga, D. A., Peng, Y. (2024). Smart systems for real-time bearing faults diagnosis by using vibro-acoustic sensor fusion with Bayesian optimized 1-D CNNs. Nondestructive Testing and Evaluation (2024): 1-25. https://doi.org/10.1080/10589759.2024.2375567
Nguimfack, R., Bappy, M. M., Mamun, A. A., Bian, L., Tian, W. (2024). Domain adaptation of time series data collected from heterogenous sensors-a case Study on real-time rotary machinery fault diagnosis. Manufacturing Letters. 41S (2024) pp. 1535-1543. https://doi.org/10.1016/j.mfglet.2024.09.180 .
High-dimensional streaming data analytics and feature extraction methods
Objective: Advancing data-driven AI methodologies to effectively manage uncertainty and nonstationary in multi-dimensional streaming data.
Objective: Advancing data-driven AI methodologies to effectively manage uncertainty and nonstationary in multi-dimensional streaming data.
Methodologies:
Real-time process monitoring, product inspection, and quality control through the integration of IoT devices and sensors.
Develop a framework for selecting the most suitable dimensionality reduction method to compute multi-dimensional streaming data.
Focus falls on dimensionality reduction to discover meaningful and informative subspaces, intending to reduce computational complexity and boost model adaptation.
Selected publications:
Mamun, A. A., Nabi, M. M., Islam, F., Bappy, M. M., Uddin, M. A., Hossain, M. S., & Talukder, A. (2023). Streamline video-based automatic fabric pattern recognition using Bayesian-optimized convolutional neural network. The Journal of The Textile Institute, 1-14. https://doi.org/10.1080/00405000.2023.2269760
Mamun, A. A., Islam, M, I., Sayeed, M. A., Al-Kouz, W., Noor, A. (2024). Multilinear principal component analysis-based tensor decomposition for real-time fabric weave pattern recognition from high-dimensional streaming data. Pattern Analysis and Applications 27, 100 (2024). https://doi.org/10.1007/s10044-024-01318-4
Mamun, A. A., Bappy, M. M., & Noor, A. (2024). Investigating the performance of linear and multilinear subspace-based feature extraction methods: a case study in fabric weave pattern recognition. Applied Intelligence. (under review).
Sustainable manufacturing and factory for the future for reducing carbon footprint
Objective: Energy and water consumption optimization in advanced manufacturing systems.
Objective: Energy and water consumption optimization in advanced manufacturing systems.
Methodologies:
Experimental design is implemented in the operational milling strategies, including feed rate, spindle speed, and depth of cut.
Reduction of long-term key performance indicators (KPI) can be set to a baseline by reducing energy and water consumption in manufacturing sectors.
Best available techniques for reducing energy and water consumption in manufacturing operations.
Selected publications:
Mamun, A. A., Bormon, K. K., Rasu, M. N. S., Talukder, A., Freeman, C. , Burch, R., & Chander, H. (2022). An assessment of energy and groundwater consumption of textile dyeing mills in Bangladesh and minimization of environmental impacts via long-term key performance indicators (KPI) baseline. Textiles, 2(4), 511-523. https://doi.org/10.3390/textiles2040029
Guerra-Zubiaga, D. A., Mamun, A. A., & Gonzalez-Badillo, G. (2018). An energy consumption approach in a manufacturing process using design of experiments. International Journal of Computer Integrated Manufacturing, 31(11), 1067-1077. https://doi.org/10.1080/0951192X.2018.1493234
Mamun, A. A., Uddin, M, A., Sayeed, M. A., Bappy, M. M., Talukder, A. (2024). Energy consumption modeling in industrial sewing operations: A case study on carbon footprint measurement in the apparel industry. Manufacturing Letters 41S (2024) pp. 1635-1644. https://doi.org/10.1016/j.mfglet.2024.09.190.
Proposals, Grants and Funding
External
Co-PI: Gollapalli, R., Hossain, K., Sayeed, M. A., Mamun, A. A. “Equipment: MRI-Acquisition of
a Scanning Electron Microscope for Advancing Transformative Research and Enriching
Experiential Learning,” University of North Alabama,” NSF, $ 721,821, Nov. 2024. (Under review).
Co-PI: Hossain, K., Sayeed, M. A., Gollapalli, R., Mamun, A. A. “Acquisition of a Powder X-Ray Diffractometer for Fostering Transformative Research and Enriching Experiential Learning,” University of North Alabama,” NSF, $ 160,000, Nov. 2024. (Under review).
Co-PI: Kim, T., Mamun, A. A., Hassanpoor, S., Uddin, M. A. “The Development of Intelligent Stress Monitoring System for Astronauts via Multimodal Sensory Signal Fusion,” Baylor University and University of North Alabama, Humans in Space Challenge, June 2024. (Under review).
Co-PI: Sealy, W., McClain, M., M. A. Mamun, A. A. “Framework for Additive Manufacturing for Customized Product Qualification and Validation,” Purdue University and University of North Alabama, NSF – Cyber-Physical Systems Program. (Under preparation).
Internal
Mamun, A. A., Uddin, M, A., Sayeed, M. A., Bappy, M. M., Talukder, A. (2024). Data-driven life cycle assessment-based energy consumption modeling for measuring carbon footprints: a case study in the apparel industry., University of North Alabama, E&IP Departmental Travel Grant, $ 1,500, Apr. 2024. (Funded).
Mamun, A. A. “Advancing cyber-physical protection: dual monitoring systems for Additive Manufacturing processes”, University of North Alabama, CASE Faculty Research and Development Grant, $ 1,500, Apr. 2024. (Funded).
Research Projects Supported By
Page updated
Google Sites
Report abuse