Jahed Armaghani Danial, Hajihassani Mohsen, Marto Aminaton, Shirani Faradonbeh Roohollah, Mohamad Edy Tonnizam
Department of Geotechnics and Transportation, Faculty of Civil Engineering, Universiti Teknologi Malaysia, 81310 UTM Skudai, Johor Bahru, Johor, Malaysia.
Construction Research Alliance, Universiti Teknologi Malaysia, 81310 UTM Skudai, Johor Bahru, Johor, Malaysia.
Environ Monit Assess. 2015 Nov;187(11):666. doi: 10.1007/s10661-015-4895-6. Epub 2015 Oct 4.
Blast operations in the vicinity of residential areas usually produce significant environmental problems which may cause severe damage to the nearby areas. Blast-induced air overpressure (AOp) is one of the most important environmental impacts of blast operations which needs to be predicted to minimize the potential risk of damage. This paper presents an artificial neural network (ANN) optimized by the imperialist competitive algorithm (ICA) for the prediction of AOp induced by quarry blasting. For this purpose, 95 blasting operations were precisely monitored in a granite quarry site in Malaysia and AOp values were recorded in each operation. Furthermore, the most influential parameters on AOp, including the maximum charge per delay and the distance between the blast-face and monitoring point, were measured and used to train the ICA-ANN model. Based on the generalized predictor equation and considering the measured data from the granite quarry site, a new empirical equation was developed to predict AOp. For comparison purposes, conventional ANN models were developed and compared with the ICA-ANN results. The results demonstrated that the proposed ICA-ANN model is able to predict blast-induced AOp more accurately than other presented techniques.
居民区附近的爆破作业通常会产生严重的环境问题，可能对周边地区造成严重破坏。爆破引起的空气超压（AOp）是爆破作业最重要的环境影响之一，需要进行预测以将潜在的破坏风险降至最低。本文提出了一种通过帝国主义竞争算法（ICA）优化的人工神经网络（ANN），用于预测采石场爆破引起的AOp。为此，在马来西亚的一个花岗岩采石场对95次爆破作业进行了精确监测，并记录了每次作业的AOp值。此外，测量了对AOp影响最大的参数，包括每次延迟的最大装药量以及爆破面与监测点之间的距离，并用于训练ICA-ANN模型。基于广义预测方程并考虑花岗岩采石场的实测数据，开发了一个新的经验方程来预测AOp。为了进行比较，开发了传统的ANN模型并与ICA-ANN的结果进行比较。结果表明，所提出的ICA-ANN模型比其他现有技术能够更准确地预测爆破引起的AOp。
