Safety of a chemical plant and its personnel is always a priority. During expansion projects and unit upgrades, often changes in one equipment may result in upset conditions for a downstream equipment. At the most benign level, this can cause the relief valves to open, losing valuable products to the flare thereby affecting the economics of that unit. A more severe case can damage equipment or result in loss of life. As a result, it is paramount that process safety and consideration of system-wide consequences are at the forefront of any decision making process. One challenge in accounting for process safety incidents is that accurate modeling is complex, time-intensive, and requires many inputs [1]. Heat exchangers are a great example of this complexity. Heat exchanger modeling using first principles can be complicated [2]. At the same time, setting up experiments is not always practical [3]. The advent of machine learning and Artificial Neural Network (ANN)-based models have shown significant promises in addressing complex problems in many areas in recent times, heat exchangers [3,4]. This work expands on these by proposing how ANN can be used to predict process safety metrics. Specifically, we apply ANN to predict heat exchanger safety ratings. This metric is used to measure the severity of a heat exchanger tube rupture, an event that is listed under API 521 as a credible overpressure scenario [5-7]. In the event of a tube rupture, the tube side can quickly overpressure the shell side. Upon the shell side pressure increasing beyond the hydrotest pressure, the shell material is prone to fail, potentially resulting in a catastrophic outcome [8]. By training ANN to a set of tube rupture simulation data, we are able to bypasses the need for tedious non-steady state equations. Lastly, we illustrate how these predictions can be used to develop tube-rupture resilient heat exchanger networks.
References:
[1] Crowl, D. A., & Louvar, J. F. (2001). Chemical process safety: fundamentals with applications. Pearson Education.
[2] Shah, R. K., & Sekulic, D. P. (2003). Fundamentals of heat exchanger design. John Wiley & Sons.
[3] Wang, Q., Xie, G., Zeng, M., & Luo, L. (2006). Prediction of heat transfer rates for shell-and-tube heat exchangers by artificial neural networks approach. Journal of Thermal Science, 15(3), 257-262.
[4] Mohanraj, M., Jayaraj, S., & Muraleedharan, C. (2015). Applications of artificial neural networks for thermal analysis of heat exchangers–a review. International Journal of Thermal Sciences, 90, 150-172.
[5] Harhara, A., & Hasan, M. F. (2020). Dynamic modeling of heat exchanger tube rupture. BMC Chemical Engineering, 2(1), 1-20.
[6] Harhara, A., & Hasan, M. F. (2019). Incorporating Process Safety into Heat Exchanger Network Synthesis and Operation. In Computer Aided Chemical Engineering (Vol. 47, pp. 221-226). Elsevier.
[7] API Standard 521. (2014). Pressureâ€Relieving and Depressuring Systems.
[8] Hellemans, M. (2009). The safety relief valve handbook: design and use of process safety valves to ASME and International codes and standards. Elsevier.
