Dr. Ali Al-Dulaimi advances degradation modeling and remaining useful life prediction

With nearly 25 years of cross-disciplinary experience in Data Analysis, Quality & Project Management, and Electrical & Computer Engineering, Dr. Ali Al-Dulaimi is a researcher and instructor dedicated to advancing Data Science and AI. His pioneering work in degradation modeling and Remaining Useful Life (RUL) prediction enhances system diagnostics and predictive maintenance, setting new benchmarks in the field while reinforcing BUV’s academic excellence and research impact. 

Throughout his academic career, Dr. Ali has made significant contributions to the field of degradation modeling and prognostics by developing innovative methodologies to tackle complex challenges. Among his key breakthroughs is the development of a novel category in degradation modeling, where he introduced generalized hybrid non-linear filtering frameworks capable of handling both linear and non-linear degradation behaviors simultaneously. This approach enables highly accurate predictions and achieves near-optimal results without requiring prior knowledge of a system’s true degradation path. 

His research in Remaining Useful Life (RUL) estimation has led to several pioneering achievements, including: 

• The first parallel hybrid deep learning models for RUL estimation, 

• The first noisy hybrid deep learning model, trained and tested on real-world noisy datasets, 

• The first multi-path parallel noisy hybrid framework for RUL estimation, 

• Setting new benchmarks in the field with unparalleled predictive accuracy. 

Dr. Ali’s commitment to innovation has been recognized with several prestigious awards, including the Best Academic Paper Award at the 2020 IEEE International Conference on Prognostics and Health Management (ICPHM 2020) and the Prediction Era Award (2019), presented by the Community Initiatives Program in Montreal, Canada. 

In addition to his research in engineering, Dr. Ali has expanded the application of AI into medicine. Recently, Dr. Ali established a collaboration with UK researchers to develop a machine learning and Radio Frequency (RF) sensing system for monitoring femoral bone fractures. This system enables non-invasive, real-time tracking of the healing process without radiation exposure while maintaining high classification accuracy in assessing fracture stages. By integrating RF sensing with AI, this research has the potential to revolutionize personalized orthopedic treatment strategies, ensuring timely interventions and improved patient outcomes. 

With several interdisciplinary collaborations underway, Dr. Ali’s research not only strengthens BUV’s academic reputation but also accelerates the advancement of AI-powered solutions across engineering, healthcare, and beyond. 

Read more of his papers on this topic:

[1] A. Al-Dulaimi, A. Asif and A. Mohammadi, “Modeling Degradation Paths Based on Interactive Multiple Model Particle Filters for Prognostic Health Management”, IISE Annual Conference, QCR-S8: Reliability Analysis – II, 2018. 497-502. 

[2] A. Al-Dulaimi, S. Zabihia, A. Asif, and A. Mohammadi, “A multimodal and hybrid deep neural network model for Remaining Useful Life estimation,” Computers in Industry, vol. 108, pp. 186-196, 2019.  

 [3] A. Al-Dulaimi, S. Zabihi, A. Asif, A. Mohammadi, “NBLSTM: Noisy and Hybrid CNN and BLSTM-based Deep Architecture for Remaining Useful Life Estimation”,  ASME Journal of Computing and Information Science in Engineering, no. 1182, 2019.  

 [4] A. Al-Dulaimi, A. Asif, and A. Mohammadi, “Noisy Parallel Hybrid model of NBGRU and NCNN Architectures for Remaining Useful Life Estimation,” Quality Engineering, Special Issue on Reliability Engineering, vol. 32, issue 3, pp. 371-387, 2020. 

 [5] A. Al-Dulaimi, A. Asif and A. Mohammadi, “Multipath Parallel Hybrid Deep Neural Networks Framework for Remaining Useful Life Estimation,” IEEE (ICPHM), pp 1-7 2020. [Best Academic Paper Award].