(3as) Hybrid Monitoring Methods for Detection, Diagnosis and Classification
A number of algorithms have been developed in order to improve existing fault detection and diagnosis performance. These algorithms integrate a number of different data-driven driven tools and methods. Multiscale wavelet-based representation of data can be used in order to handle data that is autocorrelated, non-Gaussian, and noisy (Bakshi, 1998). Hypothesis testing methods such as the Generalized Likelihood Ratio (GLR) technique can be used in order to provide the best possible detection for a fixed false alarm rate (Reynolds & Lou, 2010). Moreover, certain model-based methods have been developed in order to monitor process drifts and degradations in the process model, even when a process is operating under control (Sheriff et al., 2019).
This work will discuss different hybrid monitoring algorithms that were developed, their features, and practical applications, which include fault detection, diagnosis and classification of the benchmark Tennessee Eastman Process (TEP), and online monitoring of fouling in industrial heat exchangers (Basha et al., 2020; Sheriff et al., 2017, 2018, 2019).
Research Interests: Process systems engineering with an emphasis on the development of machine learning-based methods for process modeling, estimation, fault detection, and control. The algorithms and tools developed are utilized in many applications to improve the operation of various chemical, environmental, biological, and electrical systems.
Teaching Interests: My goal is to encourage students to seek knowledge while pursuing their passion, through the utilization of self-improvement and assessment techniques, which are geared to assist students to visualize the bigger picture while thinking critically when making decisions. I have experience instructing diverse student populations on two branch campuses of Texas A&M University, in College Station, Texas, and Doha, Qatar. These include a range of sophomore, junior, and senior undergraduate level courses, namely Process Dynamics and Control, Process Safety, Chemical Engineering Materials, Petroleum Engineering Numerical Methods, and Chemical Engineering Fundamentals. I do also have experience mentoring both undergraduate and graduate students for research. I believe in promoting passion in the pursuit of knowledge, ensuring global access to education, and helping individuals visualize the larger picture and importance of different concepts they are presented with.
Bakshi, B. R. (1998). Multiscale PCA with application to multivariate statistical process monitoring. AIChE Journal, 44(7), 1596â1610. https://doi.org/10.1002/aic.690440712
Basha, N., Sheriff, M. Z., Kravaris, C., Nounou, H., & Nounou, M. (2020). Multiclass data classification using fault detection-based techniques. Computers and Chemical Engineering, 136, 1â11. https://doi.org/10.1016/j.compchemeng.2020.106786
Reynolds, M. R., & Lou, J. (2010). An Evaluation of a GLR Control Chart for Monitoring the Process Mean. Journal of Quality Technology, 42(3), 287â310. https://doi.org/10.1080/00224065.2010.11917825
Sheriff, M. Z., Karim, M. N., Nounou, H. N., & Nounou, M. N. (2018). Process monitoring using PCA-based GLR methods: A comparative study. Journal of Computational Science, 27, 227â246. https://doi.org/10.1016/j.jocs.2018.05.013
Sheriff, M. Z., Mansouri, M., Karim, M. N., Nounou, H., & Nounou, M. (2017). Fault detection using multiscale PCA-based moving window GLRT. Journal of Process Control, 54, 47â64. https://doi.org/10.1016/j.jprocont.2017.03.004
Sheriff, M. Z., Nounou, H., Nounou, M., & Karim, M. N. (2019). Monitoring process degradation through operating regime based process monitoring. AIChE Spring Meeting and Global Congress on Process Safety: Process Control Monitoring and Analytics.