Classification and Inspection of Debonding Defects in Solid Rocket Motor Shells Using Machine Learning Algorithms

Abstract

Debonding problems along the propellant/liner/insulation interface are a critical factor affecting the integrity of solid rocket motors and one of the major causes of their structural failure. Due to the complexity of interface debonding detection and its low accuracy, a method of wavelet packet transform (WPT) combined with machine learning is proposed. In this research, multi-layer structure specimens were prepared to simulate the structure of a solid rocket motor. First, ultrasonic non-destructive testing technology was used to obtain defect data. Then, WPT algorithm was employed to extract characteristic signals of the defect data. Moreover, k-nearest neighbor model, Random Forest model and support vector machine model were applied to the classification. The results showed that the accuracies of the three models were 84.67%, 90.66% and 95.33%, respectively. Positive results indicate that WPT with machine learning model exhibited excellent classification performance. Therefore, WPT combined with machine learning can achieve a precise classification of debonding defects and has the potential to assist or even automate the debonding inspection process of solid rocket motors.

Structural Health Monitoring of Solid Rocket Motors: From Destructive Testing to Perspectives of Photonic-Based Sensing

“…One of the primary applications of machine learning in this domain involves the accurate interpretation of continuously collected data from sensors embedded within SRMs [79]; machine learning algorithms can identify patterns and anomalies associated with strain, temperature, and other critical factors. Nondestructive imaging techniques have also been used in this field of defect diagnosis [22,80,81]. These algorithms learn to recognize precursor signals that indicate potential issues, allowing engineers to proactively address problems before they escalate.…”

Lightweight RepVGG-Based Cross-Modality Data Prediction Method for Solid Rocket Motors

“…Hoffmann et al [19] used a multilayer perceptron (MLP) to analyze the defect problem of SRM's propellant interface. At the same time, Guo and colleagues [20] proposed a wavelet packet transformation (WPT) method combined with machine learning, which also achieved good results.…”

Automatic defect recognition in ultrasonic infrared thermography by deep learning of temporal signals

“…By analyzing the thermal patterns, it is possible to identify defects in the target. In recent years, more and more researchers have been using ultrasonic infrared thermography for defect detection [1][2][3] . There are also various studies using deep learning approaches in infrared thermography for defect identification.…”