论文总字数：16277字

摘 要

环境质量评价是我国甚至我们的生活都是很重要的，一般是通过环境质量评价对这片地区的环境质量给出一个等级,把这些所评价的等级应用在环境管理、环境工程、环境标准的制订、环境规划等。很多人投入时间来研究环境质量评价方法,但都寥寥无果。后来很多人思考将人工神经网络思路来应用到环境质量评价的领域上,从而得出了使用BP算法来创建环境质量评价模型，并用于实际应用的环境质量评价。

通过对其市区大气质量评价结果来评测系统的性能，数据是在《环境空气质量标准》(GB3095-1996)要求的基础上筛选出来的,进行市区的大气进一步的分析评价。BP人工神经网络建模这种方法在大气质量评价领域中，准确率高，速度快，并且在处理大数据的情况中有更好的效果,让我们在建立大气环境质量模型时利用BP神经网络来评价麻烦的评价新的渠道.BP神经网络建模具有适用评价并且较为客观，并且相对简单精度较高，BP人工神经网络具有鲁棒性并且具有较强的识别能力,利用环境质量用于评价的BP人工神经网络模型，通过不断的改进使得来提高模型的性能。使用BP人工神经网络对环境质量评价模型，具有简单性、客观性、实用性的。

关键词: BP算法 专家样本 环境质量评价神经网络

Abstract

In order to facilitate the general residential to understand air quality condition promptly and accurately, using environmentappraisal question to establish multi-layer front neural network mathematical model, taking air qualitative index of on as the training sample, the training to the network is carried on,Environmental quality assessment is in our country and our lives are closely related, the environmental quality assessment can be the environmental quality of the area that the results of a judge, for environmental management, environmental engineering, environmental standards, environmental planning advice. A lot of people study the quality of the research into the environmental quality evaluation, but most methods can not be practical.. A lot of people think about artificial neural network method to study environmental quality evaluation, and get a set of methods of using BP algorithm to establish environmental quality evaluation model, and for the actual environmental quality evaluation

On the urban air quality evaluation results: in reached "ambient air quality standard(GB3095 1996) grade a standard requirements based on urban air of [lower font inconsistent] for further analysis of the forecast. In the previous experiments show that BP artificial neural network model in evaluation of atmospheric quality assessment of, fast speed, in large data highlight his features, for the case in which a large amount of data training can get better effect, the BP neural network for complex atmospheric environment quality evaluation of new channels. BP neural network evaluation objective, evaluation model is generally applicable and simple evaluation method, evaluation precision higher merit; BP artificial neural network has characteristics of high recognition ability and strong robust, BP artificial neural network model of environmental quality assessment of the continuous time improved the performance of the model to improve. Using BP artificial neural network to evaluate the environmental quality is a simple, objective and practical method..

Key words：air quality appraisal; BP neural network; non-linearity; topology structure; curve of error; data fitting; threshold value

摘要 II

Abstract II

绪论 1

1.1课题背景和意义 1

1.2 国内外的发展状况 1

1.2.1 国内的发展情况 1

1.2.2空气评价的发展趋势 1

1.3 人工神经网络 2

1.4 对空气质量的标准分析 2

第二章 BP神经网络和模糊综合评价法 3

2.1 概述 3

2.2 BP神经网络的结构 3

2.3 BP学习算法 3

第三章 MATLAB在神经网络上的应用 5

3.1 概述 5

3.2 MATLAB的特点 5

3.2.1 MATLAB的语言特点 5

3.2.2 MATLAB的技术特点 6

3.2.3 MATLAB的功能特点 6

3.3 MATLAB在神经网络上的应用 7

4.1模型建立 9

4.2网络层数的确定 9

4.3神经网络的准备工作 10

4.3.1 确定网络结构及相关参数 11

4.3.2 确定网络拓扑结构 12

4.3.3 确定网络的相关参数 13

4.3.4BP神经网络效果检验 14

4.3.5 BP 网络模型训练误差分析 15

4.4模糊综合评价法 17

4.4.1建立模糊综合评判的数学模型 17

4.4.2 确定评价标准 17

4.4.3确定隶属函数 17

4.4.4 综合评判模型 18

4.5 结果分析 19

第五章 总结 20

参考文献: 21

致谢 22

第一章绪论

请支付后下载全文，论文总字数：16277字