Periodic inspections are required for the safe operation of large pressure vessels such as spherical tanks. Inspection robots have been applied in large pressure vessels due to their low cost and high efficiency. This paper presents a robotic system for the inspection of spherical tanks, which can identify and track weld lines on the shortest running route. Two-dimensional (2D) weld maps were prepared for robot path planning on the basis of the actual distribution of weld lines. In 2D weld maps, indispensable repetitive lines were added to form an Eulerian circuit that traversed all weld lines. In addition, an improved Fleury algorithm was proposed to solve Eulerian circuit and plan an optimal running route for robot inspection. To accurately identify weld lines, deep learning networks were constructed and trained with weld line data sets, which were captured by the camera mounted in the front of the robot.The laboratory experiments indicated that the inspection robot could identify weld lines within 0.2-0.25 s and track weld lines with a maximum offset of ±20 mm. The experiment results demonstrated that the robot could plan the shortest path to traverse all weld lines on the experimental platform. In the field tests, the virtual simulation of weld path planning on spherical tanks was explored in detail. The field tests of a spherical tank (3000 m 3 ) verified that the robotic system could improve the efficiency and stability of inspection operations and replace manual inspection with automated weld line recognition and weld path planning.
Abstract:In this paper, information entropy and ensemble learning based signal recognition theory and algorithms have been proposed. We have extracted 16 kinds of entropy features out of 9 types of modulated signals. The types of information entropy used are numerous, including Rényi entropy and energy entropy based on S Transform and Generalized S Transform. We have used three feature selection algorithms, including sequence forward selection (SFS), sequence forward floating selection (SFFS) and RELIEF-F to select the optimal feature subset from 16 entropy features. We use five classifiers, including k-nearest neighbor (KNN), support vector machine (SVM), Adaboost, Gradient Boosting Decision Tree (GBDT) and eXtreme Gradient Boosting (XGBoost) to classify the original feature set and the feature subsets selected by different feature selection algorithms. The simulation results show that the feature subsets selected by SFS and SFFS algorithms are the best, with a 48% increase in recognition rate over the original feature set when using KNN classifier and a 34% increase when using SVM classifier. For the other three classifiers, the original feature set can achieve the best recognition performance. The XGBoost classifier has the best recognition performance, the overall recognition rate is 97.74% and the recognition rate can reach 82% when the signal to noise ratio (SNR) is −10 dB.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.