Concurrent Model-Based Anomaly Detection and Diagnosis
Early anomaly detection and diagnosis in commercial buildings can significantly decrease energy wastage and occupancy discomfort and improve system reliability and equipment life. Recent advances in connected physical systems, information technology, and statistical methodology have made it feasible to provide comprehensive data-enabled anomaly detection techniques that facilitate building operations in large-scale cyber-physical systems such as modern commercial buildings. This study introduces a novel, real-time anomaly detection framework, called concurrent anomaly detection and diagnosis (C-ADD). C-ADD operates at three levels to detect anomalies, namely: (i) pointwise anomaly detection, (ii) behavior anomaly detection, and (iii) contextual and collective anomaly detection. The detected anomalies are then classified using the building operators' activity log.
Speaker Bio
Ali Mehmani is a head of Data Science; Core Research at Prescriptive Data. Before Prescriptive Data, Ali was a Postdoctoral Research Associate at the Data Science Institute of Columbia University’s engineering school. Ali specializes in Multidisciplinary Optimization, Complex System Design, Machine Learning, Deep Structural Networks, and Cyber-Physical Systems, with a focus on the following topics: heuristic optimization algorithms, deep learning, recurrent neural networks, multi-fidelity modeling and optimization; and with a primary application focus on wind energy and building energy efficiency. Ali received his B.Sc. degree in mechanical engineering in 2007, an M.Sc. degree in aerospace engineering in 2010, and his Ph.D. in Mechanical Engineering in 2015. Ali has authored 2 book chapters, and more than 35 international journal and conference articles. He is a Certified Energy Manager (CEM), Certified Measurement; Verification Professional (CMVP), and Professional Energy Manager. Ali is also a professional member of IEEE, ASME, and is both a Senior Member of AIAA, and a selected member of the AIAA Multidisciplinary Design Optimization Technical Committee. Ali serves as a reviewer for 15 international journals in the areas of design, computing, and energy. He is involved in organizing and chairing technical sessions on emerging topics in the ASME IDETC, and ASME Power and Energy conferences including ASME Artificial Intelligence and Machine Learning (2020), ASME Metamodel-based Design Optimization (2016-2020), and ASME Wind Energy Systems (2015-2016).