In engineering structures that are subject to cyclic loading, monitoring and assessing fatigue crack growth (FCG) plays a crucial role in ensuring reliability. In this study, the acoustic emission (AE) technique was used to monitor the FCG behavior of 2.25Cr1Mo0.25V steel in real-time. Specifically, an AE multi-parameter analysis was conducted to qualitatively assess the crack growth condition and quantitatively correlate the crack growth rate with AE. Various AE parameters were extracted from AE signals, and the performances of different AE parameters were analyzed and discussed. The results demonstrated that four stages of FCG, which correspond to macrocrack initiation, stable crack growth with low crack growth rate, stable crack growth with high crack growth rate, and unstable crack growth, are distinctly identified by several AE time domain parameters. The sudden and continuous occurrence of many AE signals with high count (>100) and high energy (>40 mV·ms) can provide early and effective warning signs for accelerated crack growth before final failure occurs. Moreover, linear correlations between crack growth rate and different AE parameters are established for quantifying crack growth. Based on the AE multi-parameter analysis, it was found that the count, energy, and kurtosis are superior AE parameters for both qualitatively and quantitatively characterizing the FCG in 2.25Cr1Mo0.25V steel. Results from this research provide an AE strategy based on multi-parameter analysis for effective monitoring and assessment of FCG in engineering materials.

Efficient and accurate predictions of creep rupture life are essential for ensuring the integrity of high-temperature components. In this work, a machine learning-based framework is developed for the quick screening of crucial features and accurate prediction of the creep rupture life of modified 9Cr-1Mo steels. A feature screening protocol based on correlation filtering and sequential feature selection techniques is established for identifying critical features that significantly affect the prediction performance from a set of numerous descriptors. Moreover, several machine learning algorithms are employed for model training to examine their ability to map the complex nonlinear interactions between multivariate features and creep life. The results show that the test stress, test temperature, tempering time, and the contents of S and Cr are identified as the crucial features that greatly influence the life prediction performance of modified 9Cr-1Mo steels. Moreover, the Gaussian process regression (GPR) model with these five selected crucial features exhibits the highest prediction accuracy among various machine learning strategies. Finally, an additional dataset out of model training and testing is used to further validate the efficacy of the constructed GPR model. The validated results demonstrate that most creep data are distributed inside the two-factor band lines. Results from this work show that the developed machine learning framework can offer high accuracy and excellent adaptability in predicting the creep life of modified 9Cr-1Mo steels under various environmental conditions.

Mechanical structures, such as pressure vessels and pipes, need careful inspection and monitoring to avoid serious corrosion failure. Detecting and identifying corrosion damage from acoustic emission (AE) signals is of significant importance for the safety and reliability of engineering structures in structural health monitoring. The identification accuracy largely depends on how well the damage features are being used. This paper presents a new approach for extracting effective damage features and accurately identifying different damage from AE signals during corrosion monitoring. Specifically, the proposed approach combines ensemble empirical mode decomposition and linear discriminant analysis to analyze the AE signals generated from an intergranular corrosion process. The results show that three damage modes, including environmental noise, intergranular corrosion, and the formation and propagation of cracks can be successfully detected and identified from complicated AE waveforms. The proposed approach is capable of providing reliable, direct and visualized corrosion damage detection and identification in structural health monitoring. Results from this study will guide complementary efforts aimed at detecting and identifying different damage from AE signals, and providing supporting knowledge regarding the industrial application of AE monitoring.