Fault detection strategy combining NARMAX model and Bhattacharyya distance for process monitoring     

Lakhdar Aggoun  Yahya Chetouani 《Journal of The Franklin Institute》2021,358(3):2212-2228

The complexity of modern chemical and petrochemical plants is becoming increasingly problematic in the recent years. At the same time, the demands to ensure safety and reliability of process operations rise. Early detection of abnormal event in complex real systems decrease maintenance cost and lead to guarantee the safety of human operators and environment. In the present work, a fault detection (FD) method which exploits the advantages of black-box modeling and statistical measure for fault detection in real chemical process as a distillation column is proposed. This technique is developed by applying the Nonlinear Auto-Regressive Moving Average with eXogenous input (NARMAX) model and Bhattacharyya distance (BD). In order to determine the NARMAX model, a real data set recorded during normal operations is used. Then, the BD is used to quantify on-line the dissimilarity between the current and reference probability distributions of the residual obtained from the NARMAX model for fault detection purposes. The ability of the proposed FD approach is demonstrated using real fault of separation unit. The obtained results indicate that the developed technique produces favorable performance compared to the conventional Cumulative Sum (CUSUM) test.  相似文献   

Investigating the use and effectiveness of diverse types of materials in the delivery and support of lab sessions for multimedia subjects and students     

Emmanuel Tsekleves  Amar Aggoun  John Cosmas 《British journal of educational technology : journal of the Council for Educational Technology》2013,44(5):857-868

This research study explores the use of different lab material, investigating which types of materials contribute the most to the delivery and support of laboratory (lab) sessions to design, skill‐based and technical courses in higher education in the UK. A qualitative research methodology was employed for this investigation and included both key stakeholders in academia, including 75 students and 12 tutors. An investigation was also conducted tracking student activity on the university's e‐learning facility (U‐link). Our key findings indicate that overall electronic material is considered the most effective type of material for the delivery of a lab session. This is followed by print, video and lastly audio material according to student responses and video, print and audio material according to tutor responses. Student and tutor responses varied per individual module/subject area. Video material was regarded by students and tutors as the most effective type for the delivery of skill‐based lab sessions and generally for independent learning, and electronic material was regarded as the most effective type for the delivery of technical and design lab sessions. Lastly, student tracking revealed that the introduction of video lab material in two modules increased the average time spent by students on U‐link by 58% for the technical module and 97% for the skill‐based module respectively.  相似文献