###
:2019,28(3):250-254
本文二维码信息
码上扫一扫!
基于自适应学习率BP神经网络的火点定位模型
(1.陕西国防工业职业技术学院, 西安 710300;2.西安全阶智能科技有限公司, 西安 710016)
Fire Location Model Based on Adaptive Learning Rate BP Neural Network
(1.Shaanxi Institute of Technology, Xi'an 710300, China;2.Xi'an full scale Intelligent Technology Co. Ltd., Xi'an 710016, China)
摘要
图/表
参考文献
相似文献
本文已被:浏览 180次   下载 141
投稿时间:2018-09-23    修订日期:2018-10-19
中文摘要: 为了解决传统BP (Back Propagation)神经网络收敛较慢的问题,通过BP神经网络搭建火点预测模型,采用一种自适应学习率的方法改进BP神经网络,经比较该算法收敛较快,模型输出可达到预期效果.同时利用现场可编程逻辑门阵列(FPGA)的动态可重构技术实现了改进后的神经网络,通过仿真和结果测试,该设计在预测结果的基础上又大大减少了预测时间,为环保预测、检测轨迹规划提供了一定的理论基础.
Abstract:In order to solve the problem of slow convergence of traditional BP (Back Propagation) neural network, through the BP neural network build the fire point prediction model, we use an adaptive learning rate method to improve the BP neural network, by comparison, the algorithm converges faster, and the output of the model achieves the desired effect. At the same time, an improved algorithm is realized by using the dynamic reconfigurable technology of FPGA. Through the simulation and results test, the design greatly reduces the prediction time on the basis of the prediction results and provides a theoretical basis for environmental prediction and detection trajectory planning.
文章编号:     中图分类号:    文献标志码:
基金项目:
引用文本:
王古森,高波.基于自适应学习率BP神经网络的火点定位模型.计算机系统应用,2019,28(3):250-254
WANG Gu-Sen,GAO Bo.Fire Location Model Based on Adaptive Learning Rate BP Neural Network.COMPUTER SYSTEMS APPLICATIONS,2019,28(3):250-254

用微信扫一扫

用微信扫一扫