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 sewage structural 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. By building an automated framework employing Natural Language Processing (NLP), this study presents an effective technique to automate the identification of the pipe defect rating of the pipe repair documents. NLP technologies are employed to break down textual material into grammatical units in this research. Further analysis entails using words to discover pipe defect symptoms and their frequency and then combining that information into a single score. Our model achieves 95.0% accuracy,94.9% sensitivity, 94.4% 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. Keywords: Sewer pipe inspection, Defect detection, Natural language processing, Text recognition
翻译:近几十年来,闭路电视(CCTV)检查是目视评估管道内部状况的最流行技术。经认证的检查员根据闭路电视检查,编写管道修理文件。传统手工方法,从管道修理文件评估污水结构状况需要很长时间,容易发生人为错误。自动识别必要的文本很少引起注意。通过建立一个使用自然语言处理(NLP)的自动框架,这项研究为自动确定管道修理文件的管道缺陷等级提供了一种有效的技术。使用NLP技术,将文字材料破碎成本项研究的语法单位。进一步的分析需要用文字来发现管道缺陷症状及其频率,然后将信息合并成一个分数。我们的模型实现了95.0%的准确度、94.9%的灵敏度、94.4%的特性、95.9%的精确度和95.7%的F1分,显示了拟议模型在大规模管道修理文件中用于准确和高效检测管道故障以提高管道质量的潜力。关键词:Sewer管道检查、Defect检测、自然语言处理、文本识别。