Closed-circuit video (CCTV) inspection has been the most popular technique for visually evaluating the interior status of pipelines in recent decades. Certified inspectors prepare the pipe repair document based on the CCTV inspection. The traditional manual method of assessing structural wastewater conditions from pipe repair documents takes a long time and is prone to human mistakes. The automatic identification of necessary texts has received little attention. Computer Vision based Machine Learning models failed to estimate structural damage because they are not entirely understood and have difficulty providing high data needs. Hence, they have problems providing physically consistent findings due to their high data needs. Currently, a very small curated annotated image and video data set with well-defined, precisely labeled categories to test Computer Vision based Machine Learning models.
This study provides a valuable method to determine the pipe defect rating of the pipe repair documents by developing an automated framework using Natural Language Processing (NLP) on very small, curated annotated images, video data, and more text data. The text used in this study is broken into grammatical units using NLP technologies. The next step in the analysis entails using words to find the frequency of pipe defects and then classify them into respective defect ratings for pipe maintenance.
The proposed model achieved 95.0% accuracy, 94.9% recall, 95% specificity, 95.9% precision score, and 95.7% F1 score, showing the potential of the proposed model to be used in large-scale pipe repair documents for accurate and efficient pipeline failure detection to improve the quality of the pipeline.