共查询到20条相似文献,搜索用时 203 毫秒
1.
2.
以灰分、全水分为煤样指标建模了煤炭发热量的非线性二次回归预测模型,通过测试及对比,该模型具有较高的预测精度,预测结果能够满足工程需要,预测效果优于线性回归模型及神经网络模型等。另外,该预测模型还具有容易程序实现、操作简便等特点 相似文献
3.
4.
5.
为了提高水泵能耗影响因素分析的准确性及预测模型的精度,文章提出了一种基于图片特征提取的水泵能耗多元线性回归预测模型。研究以上海某个住宅小区配置的二次供水水泵系统作为研究对象。首先,对采集到的水泵系统历史运行数据进行预处理并将一维时间序列转换为二维的格拉姆角场(gramian angular field,GAF)图像。随后,利用时间序列及图片相关性判定方法,对14个参数进行筛选,得到相应的能耗特征。最后,结合特征筛选结果,基于多元线性回归预测模型,研究了不同相关性判定方法下的最优预测模型问题。结果表明,相较于两种时间序列特征筛选方法,基于图片的特征筛选方法表现出了更佳的适应性,输入特征数量为4的情况下,其预测模型在测试集上的决定系数(R2)分别提升了0.87%、3.36%,均方误差(mean square error,MSE)分别降低了10.38%、28.26%,平均绝对误差(mean absolute error,MAE)分别降低了6.11%、24.57%。研究结论为后续水泵系统能耗特征的筛选提供了新的思路,并为上海地区水泵系统的能耗分析及预测提供理论参考。 相似文献
6.
采用线性回归分析的方法对热激发煤矸石的化学成分与其火山灰活性指数(PAI)之间的相关性进行了分析,在此基础上建立了利用热激发煤矸石的化学成分来预测其火山灰活性的预测模型,并对模型的显著性、误差及适用范围进行了检验和分析。 相似文献
7.
8.
9.
10.
11.
12.
P. D. Sarkisov L. D. Konovalova N. Yu. Mikhailenko E. G. Vinokurov 《Glass and Ceramics》2007,64(11-12):377-381
The general state of the glass industry in Russia at the present stage is analyzed. It is shown that on the basis of the production volume of sheet glass and glass containerware the glass industry is one of the largest industrial sectors in Russia. An intermediate-term forecast of the demand for the main resources—gas, electricity, sand, dolomite, soda, and cullet—is constructed on the basis of a determination of the trends in the further growth of glass production in Russia. 相似文献
13.
14.
15.
为实现铜转炉渣产出量的及时准确预报,提出应用数据挖掘技术从现场积累的大量生产数据中发掘相关规律.首先应用线性回归技术建立了仅考虑主要影响因素(铜锍含铁量)的粗略预报模型,而后,应用神经网络技术建立了考虑到多个次要影响因素的误差补偿模型,从而改进预报效果.利用实际生产数据对模型进行了仿真测试,仿真结果表明,模型预报效果良好. 相似文献
16.
以原始时间序列数据为基础,建立瓷砖出口量的模拟和预测改进的GM(1,1)模型,通过实例证明了本文提出的改进模型的精度比常规模型的精度要高,预测结果能为我国建筑陶瓷行业制定经营决策和出口政策提供参考。 相似文献
17.
In this work, we propose extending the production planning decisions of a chemical process network to include optimal contract selection under uncertainty with suppliers and product selling price optimization. We use three quantity-based contract models: discount after a certain purchased amount, bulk discount, and fixed duration contracts. We propose the use of general regression models to describe the relationship between selling price, demand, and possibly other predictors, such as economic indicators. For illustration purposes, we consider three demand-response models (i.e., selling price as a function of demand) that are typically encountered in the literature: linear, constant-elasticity, and logit. We develop a mixed-integer nonlinear two-stage stochastic programming that accounts for uncertainty in both supply (e.g., raw material spot market price) and demand (random nature of the residuals of the regression models) for the planning of the process network. The proposed method is illustrated with two numerical examples of chemical process networks. 相似文献
18.
19.
《Reinforced Plastics》2003,47(10):10
THE FEARED return of a slump in European glass reinforced plastic (GRP) production in 2002 failed to materialise, reported Dr. Uwe Bültjer, managing director of German association AVK-TV at the 6th International AVK-TV Confer-ence on 7-8 October in Baden-Baden. In fact, an increase of 0.8% was seen overall — mainly a result of high demand for GRP pipes and a slight increase in sheet moulding compound (SMC) production.This is a short news story only. Visit www.reinforcedplastics.com for the latest plastics industry news. 相似文献
20.
Mohammad R. Sabzalian Mehdi Khashei Mostafa Ghaderian 《Journal of the American Oil Chemists' Society》2014,91(12):2091-2099
Inexpensive and rapid methods for measurement of seed oil content by near infrared reflectance spectroscopy (NIRS) are useful for developing new oil seed cultivars. Adopting default multiple linear regression (MLR), the predictions of safflower oil content were made by 20–140 samples using a Perten Inframatic 8620 NIR spectrometer. Although the obtained interpolation results of MLR had desired accuracy, the extrapolation was extremely poor. The extrapolation determination coefficient (R2) and standard error (SE) of cross validation for MLR models were 0.63–0.78 and 3.71–4.44, respectively. In order to overcome the accuracy limitation of linear MLR models, a common suggestion is to use a nonlinear artificial neural network (ANN); however, it needs a large number of data to yield significant accurate results. We developed a novel robust hybrid fuzzy linear neural (HFLN) network to capture simultaneously linear and nonlinear patterns of data with a limited number of safflower samples. Empirical extrapolation results showed that the HFLN had higher R2 (=0.85) and lower SE (=1.83) compared to those obtained by MLR and ANN models. It is concluded that hybrid methodologies could be used to construct efficient and appropriate models for estimation of seed oil content set up on NIR system. 相似文献