Machine learning model for predicting structural response of RC slabs exposed to blast loading

Almustafa, Monjee K.; Nehdi, Moncef L.

doi:10.1016/j.engstruct.2020.111109

Cited by 56 publications

(10 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A common method to measure the influence of different features on the results is permutation feature importance (PFI) [55]. The core idea of PFI is that if a certain input variable (Xi) has a great influence on the result, the prediction accuracy will significantly decrease by randomly arranging Xi, during which the order of other variables is unchanged.…”

Section: Effects Of Different Input Parametersmentioning

confidence: 99%

Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques

Peng

Unluer

2022

Construction and Building Materials

View full text Add to dashboard Cite

Section: Effects Of Different Input Parametersmentioning

confidence: 99%

Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques

Peng

Unluer

2022

Construction and Building Materials

View full text Add to dashboard Cite

“…PFI is a new global model-agnostic explanation technique that was recently used to identify the most relevant features in many fields, such as medicine [45], agriculture [46], and engineering [47]. Similarly, the SHAP method has been applied successfully to interpret local and global ML predictions in several studies in order to predict the risk of water erosion [48], estimate pairwise acquisition [49], investigate the factors that contribute to freight truck-related crashes [50], estimate the occurrence of benthic macroinvertebrate species [51], and predict the fuel properties of the chars [52].…”

Section: Locationmentioning

confidence: 99%

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

et al. 2021

View full text Add to dashboard Cite

Machine learning (ML) models are commonly used in solar modeling due to their high predictive accuracy. However, the predictions of these models are difficult to explain and trust. This paper aims to demonstrate the utility of two interpretation techniques to explain and improve the predictions of ML models. We compared first the predictive performance of Light Gradient Boosting (LightGBM) with three benchmark models, including multilayer perceptron (MLP), multiple linear regression (MLR), and support-vector regression (SVR), for estimating the global solar radiation (H) in the city of Fez, Morocco. Then, the predictions of the most accurate model were explained by two model-agnostic explanation techniques: permutation feature importance (PFI) and Shapley additive explanations (SHAP). The results indicated that LightGBM (R2 = 0.9377, RMSE = 0.4827 kWh/m2, MAE = 0.3614 kWh/m2) provides similar predictive accuracy as SVR, and outperformed MLP and MLR in the testing stage. Both PFI and SHAP methods showed that extraterrestrial solar radiation (H0) and sunshine duration fraction (SF) are the two most important parameters that affect H estimation. Moreover, the SHAP method established how each feature influences the LightGBM estimations. The predictive accuracy of the LightGBM model was further improved slightly after re-examination of features, where the model combining H0, SF, and RH was better than the model with all features.

show abstract

“…For reinforced concrete slabs, Almustafa et al [8] has predicted their behaviour when subjected to blast loads utilizing a random forests model. In their study, the prediction of maximum displacement is carried out by the model using ten independent variables.…”

Section: Introductionmentioning

confidence: 99%

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

Punnappilly,

Baskar

2024

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Since limited research results are available in the area of blast wave interactions with structural surfaces, a comparative study is undertaken to ascertain the interaction effects of blast waves generated by exploding spherical and cylindrical charges on the surface of a concrete structural unit. The effective blast pressure experienced by a concrete unit is evaluated and its distribution across the front face is studied here for two distinct charge shapes, namely spherical and cylindrical. The finite element analysis is carried out for nine different scaled distances. Random forests algorithm was utilized to analyze the 450 observations to evaluate the results and build predictive models. The best models were selected based on standard performance indicators. For cylindrical charges, the aspect ratio was also factored in the analysis. The distribution of effective pressure indicates unique patterns for the two different charge shapes in the graphical comparison. The effective pressures caused by the cylindrical charge shape for the specific aspect ratios considered here are lower by 84 % on average compared to the effect caused by a spherical charge, which results from the distinct characteristics of blast waves generated by the explosion of cylindrical charges.

show abstract

Machine learning model for predicting structural response of RC slabs exposed to blast loading

Cited by 56 publications

References 43 publications

Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques

Analyzing the mechanical performance of fly ash-based geopolymer concrete with different machine learning techniques

An Interpretable Machine Learning Model for Daily Global Solar Radiation Prediction

Comparative study of the influence of charge shapes on the distribution of blast pressure on a structural unit

Contact Info

Product

Resources

About