Ning Zhou

Mr. Ning Zhou

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 July 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YPYi pu Peng
Yi pu Peng
NZNing Zhou
Ning Zhou
WWWANGBING Wang
WANGBING Wang
HGHongjun Gan
Hongjun Gan
To explore a more accurate prediction method for subgrade settlement induced by underpass construction, this study takes the existing railway project of Ningbo Yuanyi Road underpass as a case to construct a subgrade settlement prediction model based on the Mamba neural network. Using monitoring data collected using on-site automated monitoring robots as the data foundation, the prediction results of the improved transformer, long short-term memory (LSTM), time-series dense encoder (Tide), and decomposition-linear (Dlinear) neural networks are compared. The research results show that the Mean Squared Error (MSE) and Mean Absolute Error (MAE) of the proposed Bi-Mamba model are 0.279 and 0.276, respectively, demonstrating higher prediction accuracy than comparative models such as iTransformer and LSTM. Additionally, ablation experiments verify that the attention gating module in the model reduces the MSE by 9.1%, serving as a key component for improving accuracy. This study provides an advanced data-driven prediction method for subgrade settlement forecasting, offering technical references for similar engineering projects.

21 October 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YPYi pu Peng
Yi pu Peng
HGHongjun Gan
Hongjun Gan
ZTZhiyuan Tang
Zhiyuan Tang
NZNing Zhou
Ning Zhou
WWWANGBING Wang
WANGBING Wang
In order to study the impact on the shock effect when a high-speed train passes over a concrete-filled steel tube (CFST) tied-arch bridge, a dynamic load test was carried out in the background of the Qinjiang River Bridge in Qinzhou, Guangxi Province, to test the bridge displacements, accelerations, and dynamic stresses. The bridge finite element model was coupled with a CRH2 train model developed in SIMPACK to perform ANSYS–SIMPACK co-simulation of vehicle–bridge interactions. Model reliability was verified by comparing simulated results with field measurements under matched operating conditions. On this basis, a parametric study was conducted for single-line operation with a mainline spacing of 4.2–5.4 m (0.4 m increments) and train speeds of 80–270 km/h (10 km/h increments), yielding 80 working conditions to evaluate hanger impact responses. The results indicate that the ANSYS–SIMPACK co-simulation provides reliable predictions. Compared with long hangers, short hangers exhibit larger stress impact coefficients. As train speed increases, the hanger impact effect shows a wavelike increasing trend. When the speed approaches 180–200 km/h, the excitation nears the bridge’s dominant natural frequency, and impact effects on bridge components peak, identifying a critical speed range that is more prone to inducing vehicle–bridge resonance; the impact coefficient of the shock effect on both sides of the train is different: the coefficient on the far side of the bridge is about 2 times of that on the near side of the bridge, so when the impact coefficient is regulated, the unevenness of the impact of the shock effect on both sides can be taken into account. Single-line operation can introduce a lateral load bias on the train, and the distance of the train from the center line is positively correlated with the impact size of the shock effect, with the stress impact coefficient of the shock effect on both sides of the bridge and span deflection increasing as the spacing of the main line increases.