【目的】针对现有桥梁施工线形预测方法的不足,提出一种基于自适应矩估计(adaptive moment estimation,Adam)优化反向传播(back propagation,BP)神经网络的连续刚构桥线形预测方法。【方法】以小乌江大桥为研究对象,通过正交试验确定了...【目的】针对现有桥梁施工线形预测方法的不足,提出一种基于自适应矩估计(adaptive moment estimation,Adam)优化反向传播(back propagation,BP)神经网络的连续刚构桥线形预测方法。【方法】以小乌江大桥为研究对象,通过正交试验确定了桥梁施工线形的敏感参数为混凝土容重、混凝土弹性模量、张拉控制应力和温度。以均方根误差、平均绝对误差、决定系数和运算耗时为评价指标,在初始学习率相同的条件下,对梯度下降、梯度下降最小化、均方根传播和Adam四种优化算法的性能进行对比。【结果】基于Adam优化算法的BP神经网络收敛时的运算耗时为0.518 s,相较于其他三种优化算法,Adam优化算法下BP神经网络具有更快的收敛速度和更高的拟合精度。【结论】所提方法可较准确地预测连续刚构桥施工过程的线形。展开更多
针对电力领域文本数据分词准确性较低的问题,提出一种基于改进ADAM(adaptive moment estimation)算法的中文分词技术。选用Skip-Gram模型作为字嵌入模型,将字词转为分布式向量,搭建卷积神经网络-门控循环单元-条件随机场(CNN-Bi-GRU-CRF...针对电力领域文本数据分词准确性较低的问题,提出一种基于改进ADAM(adaptive moment estimation)算法的中文分词技术。选用Skip-Gram模型作为字嵌入模型,将字词转为分布式向量,搭建卷积神经网络-门控循环单元-条件随机场(CNN-Bi-GRU-CRF)模型实现电力领域文本语句的分割,提出一种改进的ADAM算法,通过控制不同时间窗口的学习率优化神经网络模型,提高模型训练速度。将所提算法运用于变电站SCD(system configuration description)文本数据分词的算例分析,通过与其他主流分词算法进行比较,验证所提分词技术的先进性与准确性。展开更多
Accurate modeling and parameter estimation of sea clutter are fundamental for effective sea surface target detection.With the improvement of radar resolution,sea clutter exhibits a pronounced heavy-tailed characterist...Accurate modeling and parameter estimation of sea clutter are fundamental for effective sea surface target detection.With the improvement of radar resolution,sea clutter exhibits a pronounced heavy-tailed characteristic,rendering traditional distribution models and parameter estimation methods less effective.To address this,this paper proposes a dual compound-Gaussian model with inverse Gaussian texture(CG-IG)distribution model and combines it with an improved Adam algorithm to introduce a method for parameter correction.This method effectively fits sea clutter with heavy-tailed characteristics.Experiments with real measured sea clutter data show that the dual CGIG distribution model,after parameter correction,accurately describes the heavy-tailed phenomenon in sea clutter amplitude distribution,and the overall mean square error of the distribution is reduced.展开更多
文摘【目的】针对现有桥梁施工线形预测方法的不足,提出一种基于自适应矩估计(adaptive moment estimation,Adam)优化反向传播(back propagation,BP)神经网络的连续刚构桥线形预测方法。【方法】以小乌江大桥为研究对象,通过正交试验确定了桥梁施工线形的敏感参数为混凝土容重、混凝土弹性模量、张拉控制应力和温度。以均方根误差、平均绝对误差、决定系数和运算耗时为评价指标,在初始学习率相同的条件下,对梯度下降、梯度下降最小化、均方根传播和Adam四种优化算法的性能进行对比。【结果】基于Adam优化算法的BP神经网络收敛时的运算耗时为0.518 s,相较于其他三种优化算法,Adam优化算法下BP神经网络具有更快的收敛速度和更高的拟合精度。【结论】所提方法可较准确地预测连续刚构桥施工过程的线形。
文摘针对电力领域文本数据分词准确性较低的问题,提出一种基于改进ADAM(adaptive moment estimation)算法的中文分词技术。选用Skip-Gram模型作为字嵌入模型,将字词转为分布式向量,搭建卷积神经网络-门控循环单元-条件随机场(CNN-Bi-GRU-CRF)模型实现电力领域文本语句的分割,提出一种改进的ADAM算法,通过控制不同时间窗口的学习率优化神经网络模型,提高模型训练速度。将所提算法运用于变电站SCD(system configuration description)文本数据分词的算例分析,通过与其他主流分词算法进行比较,验证所提分词技术的先进性与准确性。
文摘Accurate modeling and parameter estimation of sea clutter are fundamental for effective sea surface target detection.With the improvement of radar resolution,sea clutter exhibits a pronounced heavy-tailed characteristic,rendering traditional distribution models and parameter estimation methods less effective.To address this,this paper proposes a dual compound-Gaussian model with inverse Gaussian texture(CG-IG)distribution model and combines it with an improved Adam algorithm to introduce a method for parameter correction.This method effectively fits sea clutter with heavy-tailed characteristics.Experiments with real measured sea clutter data show that the dual CGIG distribution model,after parameter correction,accurately describes the heavy-tailed phenomenon in sea clutter amplitude distribution,and the overall mean square error of the distribution is reduced.
