Universitat Politècnica de Catalunya. Doctorat en Intel·ligència Artificial, Universitat Politècnica de Catalunya. Departament de Ciències de la Computació, Universitat Politècnica de Catalunya. KEMLG - Grup d'Enginyeria del Coneixement i Aprenentatge Automàtic
المصدر:
International Journal of Structural and Civil Engineering Research. :135-143
Worldwide, sewer networks are designed to transport wastewater to a centralized treatment plant to be treated and returned to the environment. This is a critical process for preventing waterborne illnesses, providing safe drinking water and enhancing general sanitation in society. To keep a perfectly operational sewer network several inspections are manually performed by a Closed-Circuit Television system to report the obstruction level which may trigger a cleaning operative. In this work, we design a methodology to train a Convolutional Neural Network (CNN) for identifying the level of obstruction in pipes. We gathered a database of videos to generate useful frames to fed into the model. Our resulting classifier obtains deployment ready performances. To validate the consistency of the approach and its industrial applicability, we integrate the Layer-wise Relevance Propagation (LPR) algorithm, which endows a further understanding of the neural network behavior. The proposed system provides higher speed, accuracy, and consistency in the sewer process examination. This work is partially supported by the Consejo Nacional de Ciencia y Tecnologia (CONACYT), Estudiante No. CVU: 630716, by the RIS3CAT Utilities 4.0 SENIX project (COMRDI16-1-0055), cofounded by the European Regional Development Fund (FEDER) under the FEDER Catalonia Operative Programme 2014- 2020. It is also partially supported by the Spanish Government through Programa Severo Ochoa (SEV2015-0493), by the Spanish Ministry of Science and Technology through TIN2015-65316-P project, and by the Generalitat de Catalunya (contracts 2017-SGR-1414).
