共查询到20条相似文献,搜索用时 125 毫秒
1.
生物发酵过程中关键生化变量难以直接检测,提出了一种利用基于敏感性与特异性的变量投影重要性(SSVIP)方法优化神经网络逆系统(NNI)的软测量方法。根据逆系统理论建立软测量模型,采用VIP变量优选方法,对软测量模型中的辅助变量进行优化。为了进一步提高VIP方法优选变量的性能,利用模型敏感性与特异性的概念,重新定义了VIP筛选阈值,确定最优的发酵过程软测量模型的变量。构造神经网络近似最优逆系统软测量模型,实现对发酵过程中关键过程变量的估计。通过Pensim仿真平台进行实验研究,结果表明经过辅助变量优选的神经网络逆系统软测量模型具有更高的估计精度和泛化能力。 相似文献
2.
MC-UVE-GA-PLS算法用于精馏软测量辅助变量选择 总被引:1,自引:0,他引:1
《计算机与应用化学》2015,(11)
现代工业生产的复杂化使得候选辅助变量增多,大量的输入变量会使软测量模型过拟合,影响模型的预测效果。针对这个问题,提出了一种蒙特卡洛无信息变量消除结合遗传算法偏最小二乘(MC-UVE-GA-PLS)选择辅助变量的方法。该方法在运用GA算法搜索最优变量子集之前,采用MC-UVE方法消除与模型不相关的变量,使GA算法能有效地搜索出对响应变量预测贡献最大的变量子集。用本文提出的方法建立了工业精馏塔浓度软测量模型,仿真结果表明本文提出的辅助变量选择方法不仅能提高模型的预测能力,而且能简化模型的复杂性。 相似文献
3.
常压蒸馏产品质量软测量改进方法及应用 总被引:8,自引:4,他引:4
针对石油化工生产过程基于统计模型的产品质量软测量中普遍存在的软测量模型适用工作范围小、难以反映进料原料性质变化的问题,探讨和应用了机理分析和统计建模相结合的软测量方法。针对一个实际常减压蒸馏产品质量软测量和控制问题.通过机理分析、实际操作数据分析并结合操作人员经验,选择能够反映进料原料性质变化的过程变量作为统计模型的输入以克服进料原料性质变化的影响,将有些直接测量的输入变量按照机理关系进行计算得到的新的变量作为统计建模的输入变量,使其和产品质量之间具有更宽范围的近似线性关系,提高软测量模型的泛化能力:某厂常减压蒸馏装置的实际应用结果表明了该方法的有效性。 相似文献
4.
5.
软传感器在工业中被广泛应用于预测与产品质量密切相关的关键过程变量,这些变量很难在线测量。要建立一个高精度的软传感器,选择合适的辅助变量是至关重要的。针对这个问题,本文通过耦合训练集的BIC准则以及验证集的MSE准则得到一个混合整数非线性规划问题,并将该MINLP问题分成内外两层结构,外层采用遗传算法对二元整数变量进行寻优,内层在整数变量固定之后退化成了较易于求解的非线性规划问题。在此基础上经过进一步分析提出了基于混合准则的变量选择方法,然后将所得辅助变量子集代入BP神经网络进行软测量建模。最后,通过4组案例对所提出方法进行验证。结果表明,所提出方法建立的软测量模型具有较好的预测性能。 相似文献
6.
针对污水处理过程中化学需氧量(chemical oxygen demand, COD)难以在线测量的问题,提出了一种基于径向基函数(radial basis function, RBF)神经网络的软测量模型.首先,用污水处理厂实测数据挑选出与COD相关的过程变量作为输入变量;其次,基于RBF神经网络建立出水COD软测量模型,利用自适应遗传算法改进的麻雀搜索算法(adaptive genetic algorithm improved sparrow search algorithm, AGAISSA)优化RBF神经网络的中心值、宽度值以及权值,通过改进麻雀位置更新公式以及引入遗传算法中的自适应交叉和变异操作保证了软测量模型的精度;最后,将RBF神经网络的软测量模型应用于污水处理厂实测数据加以验证,结果表明:AGAISSA优化RBF神经网络模型能够对出水COD进行准确的预测,具有较高的预测精度. 相似文献
7.
现代工业过程建模中,生产过程的多变量、非线性及动态性会导致模型复杂度增高且建模精度降低.针对这一问题,将非负绞杀算法(NNG)嵌入长短期记忆(LSTM)神经网络,提出一种基于LSTM神经网络及其输入变量选择的动态软测量算法.首先,通过参数优化生成训练好的LSTM神经网络,利用其出色的历史信息记忆能力处理工业过程中的动态、时滞等问题;其次,采用NNG算法对LSTM网络输入权重进行压缩,剔除冗余变量,提高模型精度,并采用网格搜索法与分块交叉验证对其超参数寻优;最后,将算法应用于某火电厂脱硫过程排放烟气SO2浓度软测量建模,并与其它先进算法进行性能比较.实验结果表明所提算法能有效剔除冗余变量,降低模型复杂度并提高其预测性能. 相似文献
8.
针对生物发酵过程中关键生化参量的在线检测问题,提出一种基于平均影响值的神经网络(NN-MIV)变量选择方法。发酵过程初始软测量模型含有多个辅助变量,MIV方法计算辅助变量对主变量的外部贡献率,NN方法计算辅助变量对主变量的内部贡献率,文中将两种方法综合提出了NN-MIV方法,其计算出的辅助变量对主变量的贡献率稳定性好。利用筛选出最优辅助变量建立软测量模型,对青霉素发酵过程做了数值仿真实验,与传统的变量筛选方法相比,该方法筛选出的辅助变量少,建立的软测量模型估计精度高。 相似文献
9.
10.
11.
Stock index forecasting is one of the most difficult tasks that financial organizations, firms and private investors have to face. Support vector regression (SVR) has become a popular alternative in stock index forecasting tasks due to its generalization capability in obtaining a unique solution. However, the major limitation of SVR is that it cannot capture the relative importance of independent variables to the dependent variable when many potential independent variables are considered. This study incorporates feature selection method and SVR for building stock index forecasting model. The proposed model uses multivariate adaptive regression splines (MARS), an effective nonlinear and nonparametric regression methodology, to identify important forecasting variables. The obtained significant predictor variables are then served as the inputs for the SVR model. Experimental results reveal that the obtained important variables from MARS can improve the forecasting performance of the SVR models. Moreover, the MARS results provide useful information about the relationship between the selected predictor variables and stock index through the obtained basis functions, important predictor variables and the MARS prediction function. Hence, the proposed stock index forecasting model can generate good forecasting performance and exhibits the capability of identifying significant predictor variables, which provide valuable information for further investment decisions/strategies. 相似文献
12.
《Journal of Process Control》2014,24(6):975-990
Soft sensor technology is an important means to estimate important process variables in real-time. Modeling for soft sensor system is the core of this technology. Most nonlinear dynamic modeling methods integrate the processes of building the dynamic and static relationships between secondary and primary variables, which limits the estimation accuracy for primary variables. To avoid the problem, a kind of soft sensor model consisting of a dynamic model in cascade with a static one is proposed. The model identification and update online are conducted in substep way. In order to improve the model update efficiency, two improved Gauss–Newton recursive algorithms, which avoid nonsingular covariance matrix, are proposed for time-invariant and time-variant soft sensor systems. The uniform convergence for dynamic model parameter and the existence of estimation deviations for static model parameters are proved for time-invariant soft sensor system. The parameters of time-variant soft sensor system would be boundedly convergent. Case study confirms that, on the basis of the proposed model and recursive algorithms, the dynamic and static characteristics of soft sensor system can be described efficiently, and the primary variables are ensured to be estimated accurately. 相似文献
13.
基于独立分量分析的重整加热炉过程监控 总被引:1,自引:0,他引:1
独立分量分析方法(ICA),不需要有关系统模型和系统变量的先验知识,是近几年才发展起来的1种新的统计方法,解决了系统模型或系统变量不确定的问题.应用此方法从重整加热炉运行时产生的大量不是相互独立的测量变量中,分离出少数必要的潜隐变量,用I<'2>和Q统计控制图对这些变量进行实时监控,结果证明对保证重整加热炉的长期、平稳、安全的运转起了重要作用. 相似文献
14.
It is important to select input variables when the neural network forecasting model is proposed. In this pa-per, by using the autocorrelation function on input variables sets selection for neural network forecasting model, a systemic and scienti[ic method for input variables sets selection is put forward. FFT is adopted to accomplish the speediness calculation, which enhances the maneuverability of this approach. A forecasting example is given, whos eresult indicates that the method is effective. 相似文献
15.
16.
配电网线路故障预测是提升配电网可靠性指标的重要手段,为了构建性能稳定、预测能力强的线路故障预测模型,需要保证模型输入特征变量的有效性、强相关性和无冗余性。为合理确定线路故障预测模型的输入特征变量,本文采用数据探索和挖掘的分析方法对馈线故障及其影响因素之间的关系进行了分析研究,以皮尔森相关系数为计算指标,对大量实际馈线故障数据与其影响因素进行相关性统计,从馈线故障的时间-地域特性、外部影响因素、自相关特性、运行影响因素等四个维度筛选出了馈线故障影响因素特征变量作为馈线故障预测模型的输入变量,直观有效地剔除无关故障特征变量。因此,所提出方法可用于配电网大数据的预处理分析和提取,为配电网故障预测提供重要方法和数据基础。 相似文献
17.
The analysis of travel mode choice is an important task in transportation planning and policy making in order to understand and predict travel demands. While advances in machine learning have led to numerous powerful classifiers, their usefulness for modeling travel mode choice remains largely unexplored. Using extensive Dutch travel diary data from the years 2010 to 2012, enriched with variables on the built and natural environment as well as on weather conditions, this study compares the predictive performance of seven selected machine learning classifiers for travel mode choice analysis and makes recommendations for model selection. In addition, it addresses the importance of different variables and how they relate to different travel modes. The results show that random forest performs significantly better than any other of the investigated classifiers, including the commonly used multinomial logit model. While trip distance is found to be the most important variable, the importance of the other variables varies with classifiers and travel modes. The importance of the meteorological variables is highest for support vector machine, while temperature is particularly important for predicting bicycle and public transport trips. The results suggest that the analysis of variable importance with respect to the different classifiers and travel modes is essential for a better understanding and effective modeling of people’s travel behavior. 相似文献
18.
Yuan-Jang Jiang Matthew Huei-Ming Ma Wei-Zen Sun Kuan-Wu Chang Maysam F. Abbod Jiann-Shing Shieh 《Artificial Life and Robotics》2012,17(2):241-244
The purpose of this study is to use ensembled neural networks (ENN) to model survival rate for the patients with out-of-hospital cardiac arrest (OHCA). We also use seven different sensitivity analyses to find out the important variables to establish a comprehensive and objective assessment method for the OHCA patients. After pre-filtering, we obtained 4,095 data for building this ENN model. The data have been divided into 60?% data for training, 20?% data for validation, and 20?% data for testing. The 11 inputs, including response time, on-scene time, patient transfer time, time to cardiopulmonary resuscitation (CPR), CPR on the scene, using drugs, age, gender, using airway, using automated external defibrillator (AED), and trauma type, and one output variable have been selected as ENN model structure. The results have been shown that ENN can model the OHCA patients and CPR on the scene, using drugs, on-scene time, and using airway in the top 4 of these 11 important variables after 7 different sensitivity analyses. Moreover, these four variables have also been shown significant differences when we use traditional one variable statistics analysis for these variables. 相似文献
19.
Hyunkyoo Cho Sangjune Bae K. K. Choi David Lamb Ren-Jye Yang 《Structural and Multidisciplinary Optimization》2014,50(5):717-738
In the reliability-based design optimization (RBDO) process, surrogate models are frequently used to reduce the number of simulations because analysis of a simulation model takes a great deal of computational time. On the other hand, to obtain accurate surrogate models, we have to limit the dimension of the RBDO problem and thus mitigate the curse of dimensionality. Therefore, it is desirable to develop an efficient and effective variable screening method for reduction of the dimension of the RBDO problem. In this paper, requirements of the variable screening method for deterministic design optimization (DDO) and RBDO are compared, and it is found that output variance is critical for identifying important variables in the RBDO process. An efficient approximation method based on the univariate dimension reduction method (DRM) is proposed to calculate output variance efficiently. For variable screening, the variables that induce larger output variances are selected as important variables. To determine important variables, hypothesis testing is used in this paper so that possible errors are contained in a user-specified error level. Also, an appropriate number of samples is proposed for calculating the output variance. Moreover, a quadratic interpolation method is studied in detail to calculate output variance efficiently. Using numerical examples, performance of the proposed method is verified. It is shown that the proposed method finds important variables efficiently and effectively 相似文献
20.
中国可持续发展系统动力学仿真模型—能源部分 总被引:7,自引:0,他引:7
本文介绍了中国可持续发展系统动力学仿真模型的能源模块,包括矿物燃料生产,矿物燃料投资,能源需求,电能需求及生产,核能生产和可再生能源等子模块,描述了主要模块的结构和主要变量关系,最后描绘了主要变量的总体模拟预测结果。 相似文献