共查询到18条相似文献,搜索用时 125 毫秒
1.
为了提高传统BP神经网络预测模型精度,避免BP网络容易陷入局部极值、收敛速度慢等问题,将BP神经网络与Ada-boost算法相结合,提出了一种Adaboost集成BP神经网络模型.结合磁县观台煤矿原煤生产成本相关数据,建立了原煤生产成本预测的Adaboost集成BP神经网络模型,将该模型用于实际的原煤成本预测.结果表明:该模型预测精度高于传统的BP神经网络,收敛速度快,具有较强的鲁棒性,预测精度能满足实际预测需要,为原煤生产成本预测提供了一种新的途径,也为原煤生产成本控制提供了重要依据. 相似文献
2.
为了提高传统BP神经网络瓦斯涌出量预测模型精度,避免BP网络容易陷入局部极值、收敛速度慢等问题,将BP神经网络和Adaboost算法相结合,提出了一种BP-Adaboost强预测器模型.将该模型用于实际瓦斯涌出量预测,并进行了40次仿真实验.结果表明:该模型预测精度高于传统的BP神经网络,且收敛速度快,具有较强的鲁棒性,预测精度能满足实际工程需要,为瓦斯涌出量预测提供了一种新的途径. 相似文献
3.
4.
5.
针对回采工作面瓦斯涌出这样复杂的动态变化系统,提出了改进的和声搜索算法(IHS)与正则极速学习机(RELM)相结合的预测方法。对和声搜索算法的基本原理进行了研究,通过采用动态变化的PAR和BW值,优化和声搜索算法的全局搜索能力;利用IHS选取RELM中的输入层权值(IW)和隐含层阈值(B),以均方根误差为目标函数,提高了算法的预测精度。仿真实验结果表明,通过与已有的BP神经网络和SVM预测模型作对比,该方法具有更好的预测效果。 相似文献
6.
7.
8.
以绵阳市2014~2016年空气污染指数(API)以及SO_2、NO_2、PM_(10)等污染物为研究对象,探讨了绵阳市空气污染的变化规律,并分析它们与常规观测的地面气象资料之间的关系。尝试采用多元线性回归方法及BP神经网络方法建立污染预报模型,并检验分析两种模型的可行性。结果表明基于BP神经网络的预报模型在污染预报中可行,并建立基于BP神经网络进行空气质量预测的预测模型,利用历史资料进行验证。 相似文献
9.
10.
基于遗传神经网络模型的大气环境质量评价方法 总被引:9,自引:0,他引:9
设计了用遗传算法训练神经网络权重的新方法,实验结果显示了遗传算法快速学习网络权重和全局搜索的能力,有效地解决了BP算法的局部收敛问题。误差反向传播的遗传——神经网络(GA—BP)模型用于大气环境质量综合评价,具有简便、准确、客观和适应性强等优点。 相似文献
11.
Residential Preferences for River Network Improvement: An Exploration of Choice Experiments in Zhujiajiao,Shanghai, China 总被引:1,自引:0,他引:1
River networks have both ecological and social benefits for urban development. However, river networks have suffered extensive destruction as a result of urbanization and industrialization, especially in China. River restoration is a growth business but suffers poor efficiency due to a lack of social understanding. Assessing the benefits of river system restoration and recognizing public preferences are critical for effective river ecosystem restoration and sustainable river management. This study used a choice experiment with a multinomial logit model and a random parameter logit model to assess respondents’ cognitive preferences regarding attributes of river networks, and their possible sources of heterogeneity. Results showed that riverfront condition was the attribute most preferred by respondents, while stream morphology was the least preferred. Results also illustrated that the current status of each of three river network attributes was not desirable, and respondents would prefer a river network with a “branch pattern,” that is “limpid with no odor,” and “accessible with vegetation.” Estimated willingness to pay was mainly affected by household monthly income, residential location, and whether respondents had household members engaged in a water protection career. The assessment results can provide guidance and a reference for managers, sponsors, and researchers. 相似文献
12.
本文介绍了一个以Models-3为基础的自动化空气质量数值预报系统,该系统通过Gambas、Yabasic和R语言等工具进行开发,集成WRF-SMOKE-CMAQ三个模式,可通过监测数据进行自动修正,完成空气质量业务数值预报,并将结果发布到Web服务器上进行呈现。该系统对硬件的要求较低,将部署于一台DELL Optiplex 9010工作站上,设置6km—2km双层嵌套,进行成都市空气质量数值预报。本文分析了成都市2014年1月1日至2014年12月31日的空气质量数值预报结果,评价系统对成都市NO_2、SO_2、PM_(10)、PM_(2.5)、O_3、CO以及空气质量指数(AQI)的预报效果。结果显示,系统对于成都市2014年空气质量变化情况趋势的预报效果较好,302天有效预报中,24小时直接预报的空气质量等级准确率为58.27%,AQI预报相关系数0.71,观测值自动修正预报对24小时空气质量预报具有明显改善效果,使其等级预报准确率达到64.9%,相关系数提高到0.89。 相似文献
13.
Spatial Prediction of Ground Subsidence Susceptibility Using an Artificial Neural Network 总被引:3,自引:0,他引:3
Ground subsidence in abandoned underground coal mine areas can result in loss of life and property. We analyzed ground subsidence
susceptibility (GSS) around abandoned coal mines in Jeong-am, Gangwon-do, South Korea, using artificial neural network (ANN)
and geographic information system approaches. Spatial data of subsidence area, topography, and geology, as well as various
ground-engineering data, were collected and used to create a raster database of relevant factors for a GSS map. Eight major
factors causing ground subsidence were extracted from the existing ground subsidence area: slope, depth of coal mine, distance
from pit, groundwater depth, rock-mass rating, distance from fault, geology, and land use. Areas of ground subsidence were
randomly divided into a training set to analyze GSS using the ANN and a test set to validate the predicted GSS map. Weights
of each factor’s relative importance were determined by the back-propagation training algorithms and applied to the input
factor. The GSS was then calculated using the weights, and GSS maps were created. The process was repeated ten times to check
the stability of analysis model using a different training data set. The map was validated using area-under-the-curve analysis
with the ground subsidence areas that had not been used to train the model. The validation showed prediction accuracies between
94.84 and 95.98%, representing overall satisfactory agreement. Among the input factors, “distance from fault” had the highest
average weight (i.e., 1.5477), indicating that this factor was most important. The generated maps can be used to estimate
hazards to people, property, and existing infrastructure, such as the transportation network, and as part of land-use and
infrastructure planning. 相似文献
14.
15.
三维电极电解硝基苯废水处理实验研究 总被引:4,自引:0,他引:4
以涂膜活性炭-活性炭为填充粒子,对三维电极电解硝基苯废水进行了研究。通过实验探讨了投盐量、槽电压、主电极间距、反应时间及初始浓度对电解硝基苯废水的影响。结果表明,三维电极在电极间距为9mm、槽电压为20V、硫酸钠投加量为1.5g/L、pH值为6、电解时间为90min的条件下,硝基苯去除率可达90%以上。在三维电极电解作用下,硝基苯转化为可生化和低毒的苯胺,苯胺在三维电极电解作用下还可以得到进一步的降解。 相似文献
16.
17.
苑继超 《中国环境管理干部学院学报》2014,(5):59-61
通过承钢烧结机脱硫出口SO2的比对监测,发现在线及手持监测设备正常但监测数据仍比对不合格。进行CO干扰实验,得出CO对采用"定电位电解法"的手持SO2分析仪有正干扰,并得出了干扰系数。现场实地测试后,利用干扰系数对监测数据进行人工修正,对比结果合格。应用"定点位电解法"监测烧结机烟气中低浓度SO2时,应人工修正或加装剔除CO影响的元件。 相似文献