DCDan Chen

Dan Chen

*This is an algorithmically generated author record based on publicly available information.

Dan Chen has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Predicting Engineering-Defined Failure Risk Levels of Metal-Loss-Related Pipeline Girth Weld Defects Under Incomplete Engineering Data

    by Ke Wang, Min Zhang, Dan Chen, Weifeng Ma, Shuai Zhang, Wei Wu, Weixin Gao

    Predicting engineering-defined failure risk levels for pipeline girth welds …is challenging because engineering records may be incomplete Conventional models often struggle with incomplete engineering inputs, as standard imputation pipelines tend to treat estimated values as equally reliable observations, losing critical missingness patterns. To address this, we propose a missingness-aware tabular deep learning method. Our framework integrates feature values, missingness masks, and feature-confidence scores into a unified representation to distinguish observed and incomplete inputs. Architecturally, the method leverages missingness-aware feature representations through mask and confidence embeddings to learn nonlinear feature interactions directly from incomplete samples. To ensure stability on small, imbalanced datasets, a parameter-efficient ensemble structure with a shared representation layer and multiple lightweight prediction branches is designed. During training, a structured-missingness-robust strategy simulates realistic systematic missing patterns common in engineering records, such as missing material-parameter or defect-size groups. At the output stage, the model provides risk classification probabilities alongside predictive uncertainty (derived from branch disagreement or probability entropy) to flag boundary cases for manual engineering review. Experimental results on a highly imbalanced dataset, in which high-risk samples account for only 0.97% of the observations, demonstrate a more balanced trade-off between overall classification performance and high-risk sample identification compared with representative baselines under the engineering-defined risk classification setting. Under five-fold stratified cross-validation, the model achieved an accuracy of 91.70% ± 1.94%, a Macro-F1 score of 66.54% ± 3.24%, a balanced accuracy of 79.74% ± 11.75%, and a high-risk recall of 52.00% ± 37.76% across folds, corresponding to 51.85% in pooled out-of-fold prediction. Predictive entropy provided supplementary information for prioritizing potentially unreliable predictions, although the effectiveness of different uncertainty indicators varied.

  • Open Access

    Constraint-Driven Fracture Toughness Assessment of Unequal-Wall-Thickness X80-X60 Girth Welded Pipelines Using SENT Specimens

    by Ke Wang, Min Zhang, Dan Chen, Weifeng Ma, Weizhe Hao, Xuan Yang

    Unequal-wall-thickness X80-X60 girth welded joints used in pipeline transition sections exhibit strong local mechanical heterogeneity, while the wall-thickness transition also introduces a separate structural geometry effect. Conventional homogeneous or weld-metal-only descriptions may therefore be insufficient for interpreting the fracture response of single-edge-notched tension (SENT) specimens sampled from such joints. In this study, a constraint-driven fracture toughness assessment was conducted for single-edge-notched tension (SENT) specimens representing the X80 base metal, X80 heat-affected zone (HAZ), weld metal, X60 HAZ, and X60 base metal as five distinct material regions. Miniature tensile tests provided the local constitutive input for these regions. The numerical procedure was verified against published SENT force versus crack-mouth-opening-displacement (CMOD) data; because direct SENT fracture-toughness tests for the present X80-X60 target joint are not yet available, the literature comparison is treated as verification of the modeling procedure rather than direct validation of the target joint. Parametric analyses were then performed for an initial crack ratio of a0/W = 0.10–0.30, a thickness-to-width ratio of B/W = 0.50–1.50, weld width = 10–30 mm, HAZ width = 1–9 mm, and different weld/HAZ strength combinations. The simulations show asymmetric crack-tip plastic deformation toward the lower-strength X60 side. Increasing the crack length increases crack-tip opening displacement (CTOD), whereas increasing B/W, weld width, or HAZ width generally reduces CTOD by increasing local constraint. The influence of weld strength is strongly coupled with the strength level of the adjacent HAZs. The results are therefore interpreted as numerical CTOD-response trends for a heterogeneous SENT specimen; direct experimental fracture-toughness measurements of the target X80-X60 joint remain an important subject of follow-up work.