Siying Qu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Siying Qu has a total of 4 co-authors. Here are the top co-authors by number of shared publications:
- Songhui Li
State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China
1 shared publication - Xunnan Liu
State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China
1 shared publication - Yan Zhang
State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China
1 shared publication - Yi Liu
State Key Laboratory of Water Cycle and Water Security, China Institute of Water Resources and Hydropower Research, Beijing 100038, China
1 shared publication
Latest Publications
- Open Access
High-Sensitivity Identification of Micro-Voids at Thick Steel Shell–Concrete Interfaces Using Elastic Wave Analysis and Feature Attention Mechanisms
The steel–concrete interface in steel–concrete composite structures is susceptible to interfacial void defects during both casting and service, posing a significant threat to structural load-bearing capacity. For early-stage micro-voids exceeding 2 mm in height, signal variations are weak and exhibit response characteristics similar to dense states, leading to feature ambiguity when using conventional criteria based on time-domain amplitude and attenuation or frequency-domain peak values and resulting in a high risk of missed detections. To address this limitation for early warning purposes, this study proposes a high-sensitivity identification method integrating an impact elastic wave response feature system with a feature-attention gated multi-layer perceptron (Feature-attention MLP). Based on full-scale model experiments from an engineering project, the temporal and spectral evolution patterns of impact elastic wave responses under varying dense conditions were analyzed. A comprehensive feature system, including time-domain statistical descriptors, spectral peaks, and sub-band energy distributions, was constructed, with Random Forest used for feature importance ranking and Top-K selection. An MLP classifier was then developed for automatic discrimination of dense states. A feature-level attention gating mechanism was introduced to enable adaptive weighting across feature dimensions, enhancing sensitive features while suppressing noise and structural variability. The final lightweight classifier contains 4052 trainable parameters, enabling rapid execution with an average CPU inference time of approximately 1.24 ms per sample. The average CPU inference time was approximately 1.24 ms per sample. Under the original train–validation split, the recall-prioritized operating point achieved a Void recall of 0.978 and a weighted F1-score of 0.780, accompanied by a non-negligible false-positive screening burden. Stratified five-fold internal validation yielded a balanced accuracy of 0.682 ± 0.021 and a Void recall of 0.845 ± 0.035 under the inner-validation-optimized threshold. These results demonstrate the preliminary potential of the proposed lightweight framework for engineering-oriented micro-void screening under the investigated full-scale conditions.
Open AccessHigh-Sensitivity Identification of Micro-Voids at Thick Steel Shell–Concrete Interfaces Using Elastic Wave Analysis and Feature Attention Mechanisms
The steel–concrete interface in steel–concrete composite structures is susceptible to interfacial void defects during both casting and service, posing a significant threat to structural load-bearing capacity. For early-stage micro-voids exceeding 2 mm in height, signal variations are weak and exhibit response characteristics similar to dense states, leading to feature ambiguity when using conventional criteria based on time-domain amplitude and attenuation or frequency-domain peak values and resulting in a high risk of missed detections. To address this limitation for early warning purposes, this study proposes a high-sensitivity identification method integrating an impact elastic wave response feature system with a feature-attention gated multi-layer perceptron (Feature-attention MLP). Based on full-scale model experiments from an engineering project, the temporal and spectral evolution patterns of impact elastic wave responses under varying dense conditions were analyzed. A comprehensive feature system, including time-domain statistical descriptors, spectral peaks, and sub-band energy distributions, was constructed, with Random Forest used for feature importance ranking and Top-K selection. An MLP classifier was then developed for automatic discrimination of dense states. A feature-level attention gating mechanism was introduced to enable adaptive weighting across feature dimensions, enhancing sensitive features while suppressing noise and structural variability. The final lightweight classifier contains 4052 trainable parameters, enabling rapid execution with an average CPU inference time of approximately 1.24 ms per sample. The average CPU inference time was approximately 1.24 ms per sample. Under the original train–validation split, the recall-prioritized operating point achieved a Void recall of 0.978 and a weighted F1-score of 0.780, accompanied by a non-negligible false-positive screening burden. Stratified five-fold internal validation yielded a balanced accuracy of 0.682 ± 0.021 and a Void recall of 0.845 ± 0.035 under the inner-validation-optimized threshold. These results demonstrate the preliminary potential of the proposed lightweight framework for engineering-oriented micro-void screening under the investigated full-scale conditions.