The Smoothed Particle Hydrodynamics (SPH) method has been applied to solve the Boussinesq equations in order to simulate hypothetical one-dimensional dam break flows (DBFs) across varying depth ratios. Initial simulations reveal that the influence of Boussinesq terms remains minimal during the early stages of DBF when the depth ratio is less than 0.4. However, these terms become increasingly significant at later stages of the flow. In comparison to simulations based on the Saint-Venant equations, the Boussinesq-SPH model underestimates flow depths in regions of constant elevation while overestimating the propagation speed of the positive surge wave, with this overestimation becoming more pronounced as the depth ratio increases. Notably, the first and third Boussinesq terms exert the greatest influence on the simulation results. The findings also indicate the presence of non-hydrostatic pressure distributions within the DBF, which contribute to the accelerated movement of the positive surge. This study offers valuable insights into the modelling of flows that exhibit non-hydrostatic behaviour, and the results may be instrumental in improving the analysis of similar flow phenomena, especially those involving complex pressure distributions and wave propagation dynamics.
Blast-induced ground vibration, a by-product of rock fragmentation, presents significant challenges, particularly in areas adjacent to residential structures, where excessive vibration can cause structural damage and propagate cracks. This study proposes a novel framework integrating Principal Component Analysis (PCA) and Artificial Neural Networks (ANN) to predict Peak Particle Velocity (PPV), a critical metric for assessing ground vibration intensity. Field data were gathered from Singareni coal mines, capturing a range of blasting parameters, including burden, spacing, explosive quantity, and maximum charge per delay. PCA was employed to identify and retain the most influential variables, reducing dimensionality while preserving essential information. The optimised subset of features was subsequently used to train the ANN model. The model’s performance was evaluated using regression analysis, yielding a high coefficient of determination (R² = 0.92), indicating its robustness and accuracy in predicting PPV. A comparative analysis with conventional empirical equations demonstrated the superiority of the ANN model, which consistently provided more precise estimates of vibration intensity. The integration of PCA not only improved model performance but also enhanced computational efficiency by eliminating redundant parameters. This research underscores the potential of combining advanced statistical techniques with machine learning models to improve the predictability of blast-induced ground vibrations. The proposed framework offers a practical tool for mine operators to mitigate the environmental impact of blasting activities, particularly in sensitive areas.
Field data collection is a crucial component of geological surveys in hydraulic engineering. Traditional methods, such as manual handwriting and data entry, are cumbersome and inefficient, failing to meet the demands of digital and intelligent recording processes. This study develops an intelligent speech recognition and recording method tailored for hydraulic engineering geology, leveraging specialized terminology and speech recognition technology. Initially, field geological work documents are collected and processed to create audio data through manual recording and speech synthesis, forming a speech recognition training dataset. This dataset is used to train and construct a speech-to-text recognition model specific to hydraulic engineering geology, including fine-tuning a Conformer acoustic model and building an N-gram language model to achieve accurate mapping between speech and specialized vocabulary. The model's effectiveness and superiority are validated in practical engineering applications through comparative experiments focusing on decoding speed and character error rate (CER). The results demonstrate that the proposed method achieves a word error rate of only 2.6% on the hydraulic engineering geology dataset, with a single character decoding time of 15.5ms. This performance surpasses that of typical speech recognition methods and mainstream commercial software for mobile devices, significantly improving the accuracy and efficiency of field geological data collection. The method provides a novel technological approach for data collection and recording in hydraulic engineering geology.
To address the complexities and inaccuracies associated with traditional methods of concrete compactness monitoring, in this paper, a real-time monitoring approach based on long short-term memory (LSTM) networks has been developed. Traditional methods often involve cumbersome data processing and yield large errors, especially in complex environments, in contrast, the proposed method leverages the LSTM network's ability to process time-series data, enhancing accuracy in detecting compactness defects within concrete structures, and the ultrasonic wave velocity through concrete under standard conditions has been set as a baseline value. The platform can visualize the curve of ultrasonic propagation speed in the monitored concrete over time, allowing for a direct comparison with the baseline to assess the extent and location of potential defects. The degree of deviation from the baseline indicates the compactness and defect severity, facilitating more accurate monitoring. Additionally, a user-friendly monitoring platform interface has been designed using Mock Plus, enabling rapid prototyping and optimization for enhanced data visualization and user interaction, this design allows for effective real-time monitoring, data processing, and user engagement. By integrating advanced machine learning techniques with intuitive platform design, the proposed method offers a significant improvement in monitoring concrete compactness, potentially benefiting both research and practical applications in structural health monitoring.
Open Access
Journal Metrics
Journal Overview
Associated Journals