CLChunpeng Liu
Chunpeng Liu
*This is an algorithmically generated author record based on publicly available information.
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Chunpeng Liu has a total of 14 co-authors. Here are the top co-authors by number of shared publications:
- Tze Liang Lau
Universiti Sains Malaysia, Tuanku Syed Sirajuddin Engineering Campus
5 shared publications - Xinyu Wan
School of Civil Engineering, Tuanku Syed Sirajuddin Engineering Campus, Universiti Sains Malaysia, Nibong Tebal 14300, Malaysia
2 shared publications - Binxiangyu Xiao
Universiti Sains Malaysia
1 shared publication Changwen Tang
1 shared publicationChunpeng Liu
1 shared publicationDianah Mazlan
1 shared publication
Latest Publications
- Open Access
- 2 November 2026
- Published by Elsevier in Case Studies in Construction Materials
- Vol. 25
Effects of carbonization temperature on the performance of bamboo fiber-reinforced cementitious composites and their potential applications in deicing pavement
- 2 November 2026
- Published by Elsevier in Case Studies in Construction Materials
- Vol. 25
Open AccessEffects of carbonization temperature on the performance of bamboo fiber-reinforced cementitious composites and their potential applications in deicing pavement
- 17 July 2026
- Published by Springer Nature
- p. 103-112
Dynamic Characteristics and Seismic Performance of an Aseismically Designed Reinforced Concrete Building for Sustainability
- 17 July 2026
- Published by Springer Nature
- p. 103-112
Dynamic Characteristics and Seismic Performance of an Aseismically Designed Reinforced Concrete Building for Sustainability
- 18 May 2026
- Published by Elsevier in Structures
- Vol. 89
Prediction of post-earthquake node damage using two-step intelligent method for prefabricated steel structures
- 18 May 2026
- Published by Elsevier in Structures
- Vol. 89
Prediction of post-earthquake node damage using two-step intelligent method for prefabricated steel structures
- Open Access
- 16 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4973
An SSA-Optimized LSTM-Transformer for Multivariate Short-Horizon Forecasting of Safety-Critical Variables in Severe PWR Transients
Severe transients in nuclear power plants (NPPs) are strongly coupled and highly nonstationary, which makes reliable short-horizon multivariate forecasting difficult for conventional sequence models. To address this challenge, this study develops a hybrid LSTM-Transformer forecasting framework for severe nuclear accident time series and uses the Sparrow Search Algorithm (SSA) as a task-oriented joint hyperparameter optimization tool for nuclear accident forecasting. In this framework, the self-attention mechanism captures long-range temporal dependencies and cross-variable interactions, while the LSTM component strengthens the modeling of short-term dynamics and local temporal memory. SSA is employed as a task-oriented joint hyperparameter optimization tool to adapt key model settings, including the number of attention heads, encoder depth, model dimension, LSTM hidden units, and dropout rate, for severe nuclear accident forecasting. In addition, a regularized training strategy combining dropout and validation-based early stopping is adopted to alleviate overfitting and improve training stability. The main comparison results are reported as mean ± standard deviation over 20 independent runs with the same data split and different random seeds. Experiments on high-fidelity PCTran/APR1400 simulations covering LOCA, LACP, and SLBIC scenarios, together with a severity-shifted LOCA test, demonstrate strong and statistically stable predictive performance. Across the three representative accident scenarios, the proposed framework achieves mean values of 0.943 ± 0.009, 0.951 ± 0.007, and 0.946 ± 0.010, while maintaining about 30% lower mean nRMSE and nMAE than the strongest LSTM-Transformer baseline. A 2 × 2 ablation study shows that regularization mainly improves training efficiency, reducing the required epochs by a range of about 36–41%, whereas SSA primarily improves predictive accuracy through better hyperparameter selection. Their combination provides the best overall generalization. Cross-severity LOCA evaluation further confirms the robustness of the proposed model, yielding mean = 0.885 ± 0.017 and mean nRMSE = 0.100 ± 0.010. The model also achieves low inference latency (P50 = 7.6 ms per sample), indicating its computational potential for near-real-time multivariate forecasting in safety-critical transient monitoring.- 16 May 2026
- Published by MDPI AG in Applied Sciences
- Vol. 16 (10) , 4973
Open AccessAn SSA-Optimized LSTM-Transformer for Multivariate Short-Horizon Forecasting of Safety-Critical Variables in Severe PWR Transients
Severe transients in nuclear power plants (NPPs) are strongly coupled and highly nonstationary, which makes reliable short-horizon multivariate forecasting difficult for conventional sequence models. To address this challenge, this study develops a hybrid LSTM-Transformer forecasting framework for severe nuclear accident time series and uses the Sparrow Search Algorithm (SSA) as a task-oriented joint hyperparameter optimization tool for nuclear accident forecasting. In this framework, the self-attention mechanism captures long-range temporal dependencies and cross-variable interactions, while the LSTM component strengthens the modeling of short-term dynamics and local temporal memory. SSA is employed as a task-oriented joint hyperparameter optimization tool to adapt key model settings, including the number of attention heads, encoder depth, model dimension, LSTM hidden units, and dropout rate, for severe nuclear accident forecasting. In addition, a regularized training strategy combining dropout and validation-based early stopping is adopted to alleviate overfitting and improve training stability. The main comparison results are reported as mean ± standard deviation over 20 independent runs with the same data split and different random seeds. Experiments on high-fidelity PCTran/APR1400 simulations covering LOCA, LACP, and SLBIC scenarios, together with a severity-shifted LOCA test, demonstrate strong and statistically stable predictive performance. Across the three representative accident scenarios, the proposed framework achieves mean values of 0.943 ± 0.009, 0.951 ± 0.007, and 0.946 ± 0.010, while maintaining about 30% lower mean nRMSE and nMAE than the strongest LSTM-Transformer baseline. A 2 × 2 ablation study shows that regularization mainly improves training efficiency, reducing the required epochs by a range of about 36–41%, whereas SSA primarily improves predictive accuracy through better hyperparameter selection. Their combination provides the best overall generalization. Cross-severity LOCA evaluation further confirms the robustness of the proposed model, yielding mean = 0.885 ± 0.017 and mean nRMSE = 0.100 ± 0.010. The model also achieves low inference latency (P50 = 7.6 ms per sample), indicating its computational potential for near-real-time multivariate forecasting in safety-critical transient monitoring. - Open Access
- 15 March 2026
- Published by Elsevier in Results in Engineering
- Vol. 30
Seismic microzonation maps of Vs30 and fundamental frequency (f0) for plain areas using single-station microtremor data and bayesian neural networks
- 15 March 2026
- Published by Elsevier in Results in Engineering
- Vol. 30
Open AccessSeismic microzonation maps of Vs30 and fundamental frequency (f0) for plain areas using single-station microtremor data and bayesian neural networks
- 17 February 2026
- Published by Springer Nature
- p. 294-306
Structural Damage and Ground Motion Characteristics of the 2015 Sabah Earthquake
- 17 February 2026
- Published by Springer Nature
- p. 294-306
Structural Damage and Ground Motion Characteristics of the 2015 Sabah Earthquake