Session: DA-15-02 Coke Drum Damage Mechanisms and Material Evaluation

Paper Number: 106180

106180 - A Comparative Study on Ai/ml - Based Transient Temperature Predictions and Real-Time Operational Transient Temperature Data of Coke Drum 

Uncertainties in the real-time operational practice result in the deviation of actual as-operated time-varying parameters from planned operational time-varying parameters. Coke drums experience severe transient thermal-induced cyclic stresses, which results in unanticipated low-cycle fatigue damage. The reliability of coke drum health is of greater importance as it is associated with the increased need for Inspection frequencies and unwelcome shutdowns. As a result, the need for online monitoring and predicting the health integrity of coke drum components is growing among plant operators.
In setting up an asset health integrity and monitoring system, operators must decide which efficiency, timeliness, precision, quality, and reliability to emphasize. The time-varying transient temperature is the dominant parameter that has a stimulating effect on the fatigue life of the coke drum. Establishing the methodology to predict the future transient temperature profiles of typical operational sequences is of great significance to predicting the health integrity status of the coke drum.
Artificial Intelligence and Machine learning (AI/ML) tools are used to develop a predictive model. Using the data sets of the transient thermal temperature profiles of the coke drum recorded during operation, the AI/ML-based prediction model is trained. A case study to generate transient temperature predictions using AI/ML algorithms will be presented in this paper. The results are compared with the real-time as-operated transient temperature profile data sets.

Keywords: Artificial Intelligence, machine learning, predictive maintenance, digital twin

Presenting Author: Srinivasan V. Indian Institute of Technology Delhi

Presenting Author Biography: Srinivasan Venkataraman is an Assistant Professor in the Department of Design at Indian Institute of Technology-Delhi. His broad interests are in the areas of Design Creativity and Innovation, Design Theory and Methodology, Virtual and Augmented Reality, Universal Design & Assistive Technology and User-Centered Design.

Authors:

Balaji Srinivasan ENGINEERS INDIA LIMITED
Srinivasan V. Indian Institute of Technology Delhi