Automatic Flare-Stack Monitoring
- R. Janssen (Siqura B. V.) | N. Sepasian (Siqura B. V.)
- Document ID
- Society of Petroleum Engineers
- SPE Production & Operations
- Publication Date
- February 2019
- Document Type
- Journal Paper
- 18 - 23
- 2019.Society of Petroleum Engineers
- combustion control, flare-stack monitor
- 9 in the last 30 days
- 64 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 10.00|
|SPE Non-Member Price:||USD 30.00|
Flare stacks must be monitored continuously to ensure ignition of released gases during the plant operation. Generally, the process of flare detection refers to detecting the presence or absence of a flare. Flare monitoring adds the capability of tracking the size of the flare to this process. By setting lower and upper monitoring boundaries, an alarm can be generated if the flare becomes too small or too big. Reliable flare-stack monitoring becomes crucial to ensure that no unburned toxic or waste gas is released into the atmosphere, causing environmental issues and possible fire hazards. It also gives the operator an extra handle to optimize the production process. In this paper, we introduce an automatic flare-detection and monitoring system. Our user-friendly system is computer-vision-based, plug-and-play, and designed as a built-in part of the camera. By taking advantage of the geometrical properties of the flare as well as temporal information obtained by video analytics, we create a monitoring system that is robust to various parameters such as wind direction. To the best of our knowledge, we are the first to present an automatic flare-stack-monitoring system with flare-size tracking and automatic event signaling. Our presented system has been tested for live monitoring in the Rotterdam Botlek area, The Netherlands. The preliminary results illustrate a reliable system that is free of false alarms.
|File Size||487 KB||Number of Pages||6|
Chamberlain, G. A. 1997. Developments in Design Methods for Predicting Thermal Radiation From Flares. Chemical Engineering, Research and Design 65 (4): 299–309.
De-Faveri, D. M., Fumarola, G., Zonato, C. et al. 1985. Estimate Flare Radiation Intensity. Hydrocarbon Processing 64 (5): 89–91.
Erden, F., Ugur Toreyin, B., Birey Soyer, E. et al. 2012. Wavelet-Based Flickering Flame Detector Using Differential PIR Sensors. Fire Safety Journal 53: 13–18. https://doi.org/10.1016/j.firesaf.2012.06.006.
Gunay, O., Ugur Toreyin, B., Kose, K. et al. 2012. Entropy-Functional-Based Online Adaptive Decision Fusion Framework With Application to Wildfire Detection in Video. IEEE Trans. on Image Processing 21 (5): 2853–2865. https://doi.org/10.1109/TIP.2012.2183141.
Haddad, R. A. and Akansu, A. N. 1991. A Class of Fast Gaussian Binomial Filters for Speech and Image Processing. IEEE Trans. on Signal Processing 39 (3): 723–727. https://doi.org/10.1109/78.80892.
Hwang, J., Kim, Y., Kim, L. S. et al. 2001. An Advanced Contrast Enhancement Using Partially Overlapped Sub-Block Histogram Equalization. IEEE Trans. on Circuits and Systems for Video Technology 11 (4): 475–484. https://doi.org/10.1109/76.915354.
Li, X., Hu, W., Shen, C. et al. 2013. A Survey of Appearance Models in Visual Object Tracking. Trans. on Intelligent Systems and Technology (TIST) (ACM) 4 (4). https://doi.org/10.1145/2508037.2508039.
Polesel, A., Ramponi, G., and John Mathews, V. 2000. Image Enhancement Via Adaptive Unsharp Masking. IEEE Transactions on Image Processing 9 (3): 505–510. https://doi.org/10.1109/83.826787.
Toreyin, B. U. 2009. Fire Detection Algorithms Using Multimodal Signal and Image Analysis. PhD dissertation, Bilkent University, Department of Elec-trical and Electronics Engineering (January 2009).
Verstockt, S., Vanoosthuyse, A., Van Hoecke, S. et al. 2010. Multisensor Fire Detection by Fusing Visual and Nonvisual Flame Features. In Image and Signal Processing, 333–341. Berlin Heidelberg: Springer-Verlag.
Verstockt, S. 2011. Multi-Modal Video Analysis for Early Fire Detection. PhD dissertation, Ghent: Faculteit Ingenieurswetenschappen en Architectuur Universiteit Ghent. (December 2011).