Prediction of Water Inrush in Long-Lasting Shutdown Karst Tunnels Based on the HGWO-SVR Model

Liu, Dunwen; Xu, Qian; Tang, Yu; Jian, Yinghua

doi:10.1109/access.2020.3047626

Cited by 13 publications

(7 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Indeed, we should verify how hybrid ML techniques can improve the prediction precision of groundwater inflows into tunnels. For instance, Liu et al 80 used a hybrid model to predict groundwater inrush into karts tunnels and found good results. It would therefore be interesting to investigate in-depth the application of these methods in different geological and hydrogeological conditions.…”

Section: Considerations On Machines Learning Methodsmentioning

confidence: 99%

Evaluation methods for groundwater inflows into rock tunnels: a state-of-the-art review

Frenelus¹,

Peng²,

Zhang³

2021

IJH

View full text Add to dashboard Cite

Groundwater inflow into tunnels is always a salient topic in Hydrology, Hydraulic Engineering, Hydrogeology, Rock Engineering and allied sciences. In fact, tunnels particularly built below the groundwater table, often face groundwater inflows during their excavation, and even sometimes after they are put into operation. These inflows, habitually regarded as unpredictable geological hazards, cause instabilities in the surrounding rocks of tunnels, and lead to considerable damages such as injuries, loss of lives, and huge-scaled economic expenses. It is argued that groundwater conditions are of decisive significance for the design and running of tunnels. Therefore, accurate prediction or evaluation of groundwater inflows into tunnels is of paramount importance. Such prediction, although it is still challenging, has been broached by many researchers with diverse methods. However, a state-of-the-art review of these methods has not yet been presented. This paper reviews the assessment methods of groundwater inflows into tunnels built in rocky media. The results mainly include analytical, semi-analytical, empirical, semi-empirical, numerical, machine learning, and other methods used in the field. This was made possible by selecting and analysing relevant scientific articles published by various worldwide Journals. In addition, some recommendations and future trends are pointed out. This paper can provide useful references in understanding groundwater inflows prediction in different points of view and their limits in terms of applicability and accuracy.

show abstract

Section: Considerations On Machines Learning Methodsmentioning

confidence: 99%

Evaluation methods for groundwater inflows into rock tunnels: a state-of-the-art review

Frenelus¹,

Peng²,

Zhang³

2021

IJH

View full text Add to dashboard Cite

show abstract

“…In order to illustrate the advantages of the proposed PGPM, the performance of existing PGPMs based on Support Vector Regression (SVR) [21], Decision Tree [22], Random Forest [23], LSTM [24], and Bi-LSTM [25] were compared with the Attention-Bi-LSTM PGPM proposed in the paper, and the main experimental parameters of PGPMs based on SVR, Decision Tree, and Random Forest were tuned, as shown in Tables 2-4, respectively. From Tables 2-4, the best parameters of each algorithm could be determined, for the best prediction accuracy was achieved.…”

Section: Parameter Tuning and Statistical Analysismentioning

confidence: 99%

An Improved Generating Energy Prediction Method Based on Bi-LSTM and Attention Mechanism

Zhang

et al. 2022

Electronics

View full text Add to dashboard Cite

The energy generated by a photovoltaic power station is affected by environmental factors, and the prediction of the generating energy would be helpful for power grid scheduling. Recently, many power generation prediction models (PGPM) based on machine learning have been proposed, but few existing methods use the attention mechanism to improve the prediction accuracy of generating energy. In the paper, a PGPM based on the Bi-LSTM model and attention mechanism was proposed. Firstly, the environmental factors with respect to the generating energy were selected through the Pearson coefficient, and then the principle and implementation of the proposed PGPM were detailed. Finally, the performance of the proposed PGPM was evaluated through an actual data set collected from a photovoltaic power station in Suzhou, China. The experimental results showed that the prediction error of proposed PGPM was only 8.6 kWh, and the fitting accuracy was more than 0.99, which is better than existing methods.

show abstract

“…Although remarkable achievements have been obtained by scholars in references, [13][14][15][16][17][18] difficulties still exist to construct a clear multifactor mathematical model using the conventional fatigue life estimation models, 19,20 as well as the prediction accuracy of the models needs to be further improved. With the advancement and popularization of machine learning (ML) algorithms, artificial intelligence methods are recently used in several studies to develop models for forecasting performances of materials and components including fatigue characteristics, [21][22][23][24] battery state of charge, 25 fault diagnosis, 26 karst tunnel water inrush, 27 airport taxiway planning and gate allocation, 28,29 and bearing performance. 30 Among them, the support vector regression (SVR) algorithm, which is based on support vector machines (SVM), has encouraging learning performance in solving the regression problem with small samples.…”

Section: Introductionmentioning

confidence: 99%

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Wang

Liu

2023

Fatigue Fract Eng Mat Struct

View full text Add to dashboard Cite

An intelligent prediction model of rubber fatigue life considering strain ratios based on the support vector regression (SVR) and an improved sparrow search algorithm (ISSA) is proposed. In order to solve the problem that traditional methods may lead to unsatisfactory prediction results, we establish a prediction model based on SVR. To further improve the prediction accuracy, we utilize the ISSA algorithm to optimize various hyper‐parameters in the model. Fatigue tests of filled natural rubber on dumbbell‐type specimens are performed and applied to verify the effectiveness of the proposed model. The results show that the ISSA optimized SVR (ISSA‐SVR) model is superior in terms of prediction accuracy, convergence speed, and stability compared with SVR models using the grid search or some standard optimization algorithms. Furthermore, comparisons of some published related models demonstrate that the ISSA‐SVR has the most accurate predictive results, which gather within 1.5 times the dispersion lines.

show abstract

Prediction of Water Inrush in Long-Lasting Shutdown Karst Tunnels Based on the HGWO-SVR Model

Cited by 13 publications

References 32 publications

Evaluation methods for groundwater inflows into rock tunnels: a state-of-the-art review

Evaluation methods for groundwater inflows into rock tunnels: a state-of-the-art review

An Improved Generating Energy Prediction Method Based on Bi-LSTM and Attention Mechanism

Intelligent prediction of fatigue life of natural rubber considering strain ratio effect

Contact Info

Product

Resources

About