Abstract: As pipelines take an increasingly important role in energy transportation, their health management is necessary. In-pipe inspection is a common pipeline life maintains method. The signal obtained through internal inspection contains strong noise and interference where the internal environment of the pipeline is extremely complicated. Thus, it is challenging to accurately identify the defect signal. A defect detection algorithm framework based on feature boosting is proposed by using the multi sensing pipeline pig as the detection signals. Through boosting construction of features and hierarchical classification, the framework can not only correctly classify various signals in the internal detection signals but also realize the accurate identification of defect signals. Concurrently, in order to demonstrate the high flexibility and robustness of the detection framework, experiments and verifications have been carried out on specimens in three different environments i.e. laboratory environment, simulated environment and actual environment. In the classification of actual environmental detection signals, comparisons with different algorithms have been undertaken and quantitatively evaluated using the F-score and demonstrated the effectiveness of the proposed framework.

Key words: in-pipe inspection, defect detection and location, multi-sensor fusion, Feature Boosting