دورية أكاديمية

Indirect Determination Approach of Blast-Induced Ground Vibration Based on a Hybrid SSA-Optimized GP-Based Technique

التفاصيل البيبلوغرافية
العنوان: Indirect Determination Approach of Blast-Induced Ground Vibration Based on a Hybrid SSA-Optimized GP-Based Technique
المؤلفون: Zhaoxin Jiang, Hongyan Xu, Hui Chen, Bei Gao, Shijie Jia, Zhi Yu, Jian Zhou
المصدر: Advances in Civil Engineering, Vol 2021 (2021)
بيانات النشر: Wiley, 2021.
سنة النشر: 2021
المجموعة: LCC:Engineering (General). Civil engineering (General)
مصطلحات موضوعية: Engineering (General). Civil engineering (General), TA1-2040
الوصف: The accurate determination of blast-induced ground vibration has an important significance in protecting human activities and the surrounding environment. For evaluating the peak particle velocity resulting from the quarry blast, a robust artificial intelligence system combined with the salp swarm algorithm (SSA) and Gaussian process (GP) was proposed, and the SSA was used to find the optimal hyperparameters of the GP here. In this regard, 88 datasets with 9 variables including the ratio of bench height to burden (H/B) and the ratio of spacing to burden (S/B) were selected as the input variables, while peak particle velocity (PPV) was measured. Then, an ANN model, an SVR model, a GP model, an SSA-GP model, and three empirical models were established, and the predictive performance was evaluated by using the root-mean-square error (RMSE), determination coefficient (R2), value account for (VAF), Akaike Information Criterion (AIC), Schwarz Bayesian Criterion (SBC), and the run time. After comparing, it is found that the proposed SSA-GP yielded a superior performance and the ratio of bench height to burden (H/B) was the most sensitive variable.
نوع الوثيقة: article
وصف الملف: electronic resource
اللغة: English
تدمد: 1687-8086
1687-8094
Relation: https://doaj.org/toc/1687-8086; https://doaj.org/toc/1687-8094
DOI: 10.1155/2021/6694918
URL الوصول: https://doaj.org/article/a94535f7a1ab4a1b80347c2c9f261a31
رقم الأكسشن: edsdoj.94535f7a1ab4a1b80347c2c9f261a31
قاعدة البيانات: Directory of Open Access Journals
الوصف
تدمد:16878086
16878094
DOI:10.1155/2021/6694918