Search

Automated system log anomaly detection plays a crucial role in ensuring service reliability. Existing methods incompletely utilize structured log entries, resulting in the loss of key information such as components and time. Besides, due to the limitations of labeled data, models trained by a single system are difficult to apply to other systems. Therefore, we propose a cross-system log anomaly detection method named LogGT, which simultaneously models log events, components and time, leveraging labeled system knowledge to achieve anomaly detection in unlabeled systems. Specifically, we firstly design a heterogeneous graph to accurately represent the interactions between different events and components in the log sequence. Then, in order to avoid noise interference and conduct cross-system semantic analysis, we employ BERT to extract log sentence vectors, and Normalizing Flow is used to optimize them for smoother node embedding. A Graph Transformer Architecture with Time Intervals (GTAT) is proposed to model heterogeneous graphs by integrating time feature, allowing for a comprehensive analyze of execution order and time anomalies. Additionally, we design a semantic weighting method and utilize a novel domain-adapted transfer learning technology to effectively transfer the heterogeneous graph features of the source system to the target system. Experimental results demonstrate that LogGT outperforms five log anomaly detection methods, achieving an average anomaly detection F1-score higher than 0.95. Moreover, the AUC value of GTAT exceeds the sequence model by more than 2.3%. • A novel log heterogeneous graph modeling method is proposed. • The Normalizing Flow-based BERT model is utilized to generate smooth log semantic. • A Graph Transformer Architecture with Time Interval for order and time anomalies. • A domain-adapted transfer learning with semantic weights for feature transfer. • The comprehensive evaluation of LogGT on three different system datasets. [ABSTRACT FROM AUTHOR]

• Low-cycle multiaxial fatigue experiments are conducted for Q235B steel welded material. • Equivalent cyclic stress-strain curves and hysteresis loops are obtained. • Specimens under non-proportional paths show certain extent of additional hardening effect. • Proposed fatigue parameter incorporates energy on weighted critical plane and orthogonal plane. • The proposed fatigue parameter provides a superior ability to make life prediction. Low-cycle torsional and multiaxial fatigue experiments are carried out for thin-walled Q235B steel welded specimens under both in-phase and 90° out-of-phase loading paths. A remarkable non-proportional additional hardening effect exists in the Q235B steel welded material under the 90° out-of-phase loading paths. A new energy-based fatigue parameter is proposed that incorporates the shear strain energy on the weighted critical plane and the normal strain energy on both the weighted critical plane and orthogonal plane. The proposed energy-based fatigue parameter provides a superior ability to make life prediction for the Q235B steel welded material under the torsional and multiaxial loading paths. [ABSTRACT FROM AUTHOR]

Corrosion fatigue (CF) experiments of G20Mn5QT cast steel and Q355D steel butt-welded joint are conducted with loading frequencies of 1 Hz and 10 Hz. The decrease of loading frequency resulting in a reduction in the CF life of specimens. The average percentage of CF life reduction are 6.4% (S = 300 MPa), 53.5% (S = 260 MPa), 17.5% (S = 220 MPa), 34.3% (S = 190 MPa), 38.6% (S = 160 MPa) and 80.5% (S = 130 MPa), respectively. The CF failure mechanism remains unchanged regardless of the loading frequency. Based on continuum damage mechanics (CDM), a novel CF life prediction model is proposed, in which the effect of loading frequencies is introduced by the evolution of corrosion pits. The prediction model considers the coupling effect of fatigue and corrosion, and it achieves the prediction of CF life of the butt-welded joints using experiment data at higher loading frequency. The accuracy and universality of the prediction model are verified by predicting the CF life of other specimens. [Display omitted] • The S–N curves of butt-welded joints under different loading frequencies is obtained. • The corrosion fatigue failure mechanism of butt-welded joints is analyzed. • A corrosion fatigue life prediction model considering loading frequency is proposed. • The prediction of corrosion fatigue life of the butt-welded joints is achieved. • The accuracy and universality of the prediction model are verified. [ABSTRACT FROM AUTHOR]