基于神经网络的建筑施工质量评价Construction quality evaluation based on neural network
张敏
摘要(Abstract)：
基于Bayes判别理论的施工质量评价方法存在施工质量评价精度低、无法直观描述施工质量的优劣情况等弊端,因此,提出基于BP神经网络的建筑施工质量评价方法,设计BP神经网络结构,基于该结构对BP神经网络算法进行推导,得到总量误差。为了避免总量误差出现反向扩散产生运算精度降低的问题,在BP神经网络的算法推导过程中采用误差函数梯度下降法,对神经元实施突出权值修正,主要修正隐含层J与输出层M权值以及输出层I与隐含层J的权值,对神经元权值进行修改时考虑到误差曲面的变化影响,提高BP神经网络的运算精度。采用修正后的BP神经网络算法对某建筑施工质量进行实际评价,得出的评价结果与预期结果相符,可实现对建筑施工质量的评价。实验结果说明,所提方法可以提高建筑施工质量评价精度,能准确、直观地反映施工质量的优劣,评价效果佳。
关键词(KeyWords)： 建筑施工;质量评价;BP神经网络;梯度下降;施工质量;神经元权值
基金项目(Foundation):
作者(Author): 张敏
DOI: 10.16652/j.issn.1004-373x.2018.17.038
参考文献(References)：
- [1]AKIMOTO T,SUENAGA Y,WALLACE R S.Automatic creation of 3D facial models[J].IEEE computer graphics and applications,1993,13(5):16-22.
- [2]YANG J,ZHANG D,FRANGI F.Two-dimensional PCA:a new approach to appearance-based face representation and recognition[J].IEEE transactions on pattern analysis and machine intelligence,2004,26(1):131-137.
- [3]HUMAN D R,PARENT R E.Obtaining complex behavior form simple rules[J].The visual computer,1998,23(4):332-347.
- [4]YAO J F S A.Texture mapping approach to 3-D facial image synthesis[J].Computer graphics forum,1988,7(2):129-134.
- [5]王璇,薛瑞.基于BP神经网络的手写数字识别的算法[J].自动化技术与应用,2014,33(5):5-10.WANG Xuan,XUE Rui.The algorithm of handwritten digit recognition based on BP neural network[J].Techniques of automation and applications,2014,33(5):5-10.
- [7]YOU X,CAO X.Study of liquid lithium coolant interaction based on BP neural network optimized by genetic algorithm[J].Journal of fusion energy,2015,34(4):918-924.
- [8]伍华丽,任心怡.基于模糊约束的数据库特定数据挖掘算法[J].计算机仿真,2016,33(10):240-243.WU Huali,REN Xinyi.Specific data mining algorithm based on fuzzy constraint database[J].Computer simulation,2016,33(10):240-243.
- [9]许金普.基于MMSE谱减算法的农产品市场信息语音识别技术[J].河南农业科学,2015,44(5):156-160.XU Jinpu.Speech recognition of agricultural market information based on MMSE spectral subtraction[J].Journal of Henan agricultural sciences,2015,44(5):156-160.
- [10]GLYDE H,BUCHHOLZ J M,NIELSEN L,et al.Effect of audibility on spatial release from speech-on-speech masking[J].Journal of the Acoustical Society of America,2015,138(5):3311-3319.