摘要
模糊理论在岩质边坡稳定性评价中存在的知识获取和自适应能力较低等方面不足,而神经网络在模糊推理方面欠缺,因此,提出基于自适应神经元模糊推理系统的边坡稳定性评价方法。通过模型结构的建立、模型训练和测试,得到可用于边坡稳定性评价的基于自适应神经元模糊推理系统模型。测试结果表明,该模型计算结果与边坡实际稳定系数十分接近,对边坡稳定性的预测结果也与实际相符。与基于神经网络方法的计算结果比较,该方法在建模简便程度及计算精度等方面明显具有优势。
By establishing model structure,training and testing,the adaptive neural-net work-based fuzzy interference system model is obtained to evaluate the stability of slope.The testing results show that the calculation by the model almost reaches the practical stability factor of the slope,and the prediction is also coincident with the practical situation.The comparison with the neural network shows that the new model has the advantage of simplicity and high accuracy.
出处
《岩石力学与工程学报》
EI
CAS
CSCD
北大核心
2006年第z1期2785-2789,共5页
Chinese Journal of Rock Mechanics and Engineering
关键词
边坡工程
自适应神经元模糊推理系统
岩质边坡
稳定性评价
slope engineering
adaptive neural-net work based fuzzy interference system(ANFIS)
rock slope
stability evaluation
