Orthotropic steel decks (OSDs) serve as critical load-bearing components in long-span steel bridges, but high-amplitude welding residual stresses (WRSs) generated during the welding process pose significant threats to structural integrity. To mitigate these stresses, post-weld heat treatment (PWHT) has emerged as a promising technique. This investigation first establishes a semi-structural thermo-elasto-plastic finite element model of the Deck-U-rib-Diaphragm system with a six-pass welding sequence. The temperature field is modeled via a double-ellipsoidal heat source and birth–death element approach. Subsequently, thermo-mechanical coupling analysis is conducted to investigate the distribution characteristics of Von Mises residual stresses. The stress relief effect of PWHT is then explored by comparing different holding temperatures (T) and holding times (t), achieving a balance between stress reduction effectiveness and economic efficiency, when T = 550 °C and t = 40 min. Finally, full-scale experimental tests are designed, and the hole-drilling method is utilized to validate the numerical simulation results. This research provides valuable insights for the design of PWHT processes for OSDs.
Accurate shape control during steel truss incremental launching remains a persistent challenge in bridge engineering, primarily due to dynamic geometric variations induced by continuous spatial translation. Conventional measurement-based approaches often lead to inaccurate error determination and insufficient control criteria due to continuous geometric variations during structural movement. This study presents a novel Long Short-Term Memory (LSTM)-based methodology for real-time prediction and adaptive control of shape errors in launching processes. First, an error matrix is established based on the actual pushing measurement plan, and numerous error splines are generated using virtual assembly technology. These splines are output as an error matrix and encoded into a machine-readable format, leading to the establishment of a sliding window method for recursive prediction and updates of the predictions (measured values). Then, the LSTM model is trained using this sliding window approach, achieving a root mean square error(RMSE) of 0.03 on the test set. Field experiments demonstrate that the predicted values from the LSTM model closely align with the measured values, maintaining short-term shape error prediction accuracy within 3 mm. However, prediction accuracy diminishes for longer time steps as the step length increases. Following model updates with measured data, the accumulated prediction error rapidly decreases. The proposed prediction method for shape errors during pushing exhibits high accuracy and versatility in similar projects, significantly reducing time spent on manual error handling and minimizing computational inaccuracies.