Real-Time Pore Blockage Quantification in Hydropower Drainage Pump Inlets via Canny Edge Detection and HSV Segmentation
Abstract
As a core component of the diversion tunnel in hydropower stations, the drainage pump is prone to blockage in its inlet filter due to severe water calcification inside the tunnel. In this study, the present study proposes a computer-vision-based detection method to assess the blockage degree of the inlet filter's pores. Specifically, the outline of the small pores in the inlet screen of the drainage pump unit was captured using the Canny edge detection algorithm. Then the pore and non-pore areas of the filter were distinguished with the HSV color model. Finally, the degree of blockage was determined by calculating the proportion of pore areas within the filter screen. When applied to a real hydropower station using 12 images sampled at 15-day intervals, this developed computer vision technology achieved 13.6% average error against manual annotations and demonstrated real-time processing (<1s/image on 4-core/8GB edge devices) effective detection for the pores blockage degree of the drainage pump's inlet filter screen, by quantitatively assessing the blockage degree, it provides critical metrics that enable predictive maintenance scheduling and performance evaluation, thereby ensuring reliable hydraulic performance and minimizing downtime in the hydropower station's drainage system.
Full Text:
PDFReferences
Kannaujia, V., S. P. Bhore and H. S. Goyal. (2024) Failure Analysis of Submersible Pumps-A Review. In: Ghoshal, S.K., Samantaray, A.K., Bandyopadhyay, S. (eds) Recent Advances in Industrial Machines and Mechanisms. IPROMM 2022. Lecture Notes in Mechanical Engineering. Springer, Singapore.
Iqbal, U., J. Barthelemy and P. Perez. (2022) An AIoT Solution for Visual Blockage Detection at Culverts, in NVIDIA Technical Blog [Online]. Available: https://developer.nvidia.com/zh-cn/blog/an-aiot-solution-for-visual-blockage-detection-at-culverts/.
Affortunati, S. and B. G. Zagar. (2022) Application of Impedance Spectroscopy and Tomography to Monitor Calcite Deposits in Drainage Pipes, Elektrotechnik & Informationstechnik, vol. 139, pp. 524–534, 2022, doi:10.1007/s00502-022-01058-5.
Iqbal, U., J. Barthelemy, W. Li and P. Perez. (2021) Automating Visual Blockage Classification of Culverts with Deep Learning, Applied Sciences, vol. 11, no. 16, pp. 7561, 2021, doi:10.3390/app11167561.
Singal, S. K., V. Gupta and M. Sood. (2022) A Numerical Study to Determine the Impact of Trash Rack Blockage on Head Loss, Water and Energy International, vol. 65, no. 7, pp. 6–11.
Hribernik, A. (2020) Evaluation of Clogged Hydropower Plant Trash Rack Losses, Journal of Mechanical Engineering, vol. 66, no. 2.
Cui, X., T. Wen, J. Li, D. Wu, Y. Fan, Y. Jin et al. (2022) Migration and Deposition Characteristics of Particles in Sand Layers with Fluctuating Water Levels, Water, Air, & Soil Pollution, vol. 233, no. 4, pp. n.p.
Tao, H., Z. Wu, Y. Zhou et al. (2023) Establishment of a Dimensional Analysis–Based Prediction Model for the Head Loss of Pre-Pump Micro-Pressure Filters for Micro-Irrigation, Irrigation Science, vol. 41, pp. 803–815.
Liu, D. G., Y. Yang, C. J. Mao et al. (2022) A Comparative Study on Hydrodynamics and Hydrochemistry Coupled Simulations of Drainage Pipe Crystallization Blockage in Karst Tunnels, Journal of Earth Science, vol. 33, pp. 1179–1189.
Ogie, R. I., S. Dunn, T. Holderness and E. Turpin. (2017) Assessing the Vulnerability of Pumping Stations to Trash Blockage in Coastal Mega-Cities of Developing Nations, Sustainable Cities and Society, vol. 28, pp. 53–66.
Kim, J. H. (2019) Spiral Impeller Apparatus for Spurt Pump, KR102019607B1.
Rana, D., S. Bichinepally, S. Kalra, A. Nandan, and N. A. Siddiqui. (2023) Comparative Analysis of Ultrafiltration for Produced Water from Oil and Gas Industry, in Advances in Waste Management, N. A. Siddiqui, A. S. Baxtiyarovich, A. Nandan, and P. Mondal, Eds. Lecture Notes in Civil Engineering, vol. 301. Springer, Singapore.
Fujita, C., M. S. Akhtar, R. Hidaka, et al. (2022) Mitigation of Groundwater Iron–Induced Clogging by Low–Cost Bioadsorbent in Open Loop Geothermal Heat Pump Systems, Applied Water Science, vol. 12, p. 30.
Roche, S. D. (2018) Self–Cleaning Pre–Filter for a Water Circulation Pump, US Patent 10070629B2.
Frank, L. (2021) Pond Pump with Filter Cleaning Arrangement, EP Patent 3314126B1.
Korostelev, S. V. (2019) Acoustic Emitter Device for Regular Cleaning of a Downhole Filter, WO Patent 2019151895A1.
Nallakukkala, S. and B. Lal. (2023) Machine Learning for Scale Deposition in Oil and Gas Industry, in Machine Learning and Flow Assurance in Oil and Gas Production, B. Lal, C. B. Bavoh, and J. K. Sahith Sayani, Eds. Springer, Cham.
Canny, J. (1986) A Computational Approach to Edge Detection, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. PAMI–8, no. 6, pp. 679–698, doi:10.1109/TPAMI.1986.4767851.
Suneetha, A. and E. S. Reddy (2020) Robust Gaussian Noise Detection and Removal in Color Images Using Modified Fuzzy Set Filter, Journal of Intelligent Systems, vol. 30, no. 1, pp. 240–257.
Wedianto, A., H. L. Sari and H. Zuzaantri. (2016) Analisa Perbandingan Metode Filter Gaussian, Mean dan Median Terhadap Reduksi Noise, Jurnal Media Infotama, vol. 12, no. 1.
Chakrapani, Y. S., N. V. Rao, and M. Kamaraju. (2021) A Survey of Sobel Edge Detection VLSI Architectures, Journal of Physics: Conference Series, vol. 1804, no. 1, p. 012151.
Rosenfeld, A. and A. Kak. (1976) Digital Picture Processing, p. 457. Academic Press.
Kitchen, L. and A. Rosenfeld. (1982) Gray–Level Corner Detection, Pattern Recognition Letters, vol. 1, no. 2, pp. 92–102.
Smith, A. R. (1978), Color Gamut Transform Pairs, ACM SIGGRAPH Computer Graphics, vol. 12, no. 3, pp. 12–19.
Flores–Vidal, P. A., D. Gómez, J. Castro, and J. Montero. (2022) New Aggregation Strategies in Color Edge Detection with HSV Images, in Information Processing and Management of Uncertainty in Knowledge–Based Systems, D. Ciucci et al., Eds. Communications in Computer and Information Science, vol. 1602. Springer, Cham, doi:10.1007/978-3-031-08974-9_29.
Heyns, P. S., R. Deetlefs, A. J. Oberholster, T. R. Botha, P. S. Els, and D. H. Diamond. (2020) Computer Vision for Rail Surface Defect Detection, Condition Monitor, TN.403, pp. 6–10.
Shafiabadi, M., A. Kamkar–Rouhani, S. R. G. Riabi, A. R. Kahoo, and B. Tokhmechi. (2021) Erratum to: Identification of Reservoir Fractures on FMI Image Logs Using Canny and Sobel Edge Detection Algorithms, Oil & Gas Science and Technology, vol. 76, p. 33.
Akter, Y. A., M. A. Rahman and M. O. Rahman. (2020) Quantitative Analysis of Mouza Map Image to Estimate Land Area Using Zooming and Canny Edge Detection, TELKOMNIKA Telecommunication Computing Electronics and Control, vol. 18, pp. 3293–3302.
Gunawan, G., H. Nuriyanto, S. Sriadhi, A. Fauzi, A. Usman, and F. Fadlina, et al. (2018) Mobile Application Detection of Road Damage Using Canny Algorithm, in Proceedings of the 1st International Conference on Green and Sustainable Computing (ICoGeS), vol. 1019. Institute of Physics.
DOI: https://doi.org/10.31449/inf.v49i33.9010
This work is licensed under a Creative Commons Attribution 3.0 License.