共查询到20条相似文献,搜索用时 687 毫秒
1.
采用神经网络的方法建立水泥预分解窑煅烧工段的预测模型.选择合理的状态与控制变量,通过采集实际运行数据来训练神经网络.构建的基于BPNN神经网络的煅烧预测模型能够较好地拟合采样数据,具有较好的泛化能力. 相似文献
2.
3.
4.
通过对某石化公司循环冷却水系统生产运行数据的分析,选取了对腐蚀速率影响较大的水质参数,借助神经网络良好的非线性能力,基于BP神经网络建立了腐蚀速率的预测模型.利用该模型对循环冷却水系统一定周期腐蚀速率的预测结果较好. 相似文献
5.
结合小波神经网络基本原理,提出一种粒子群优化小波神经网络的瓦斯浓度预测模型。对小波神经网络基本原理进行分析,然后,利用粒子群对小波神经网络参数进行优化,并构建预测模型;最后,以P1~P5监测点的煤矿瓦斯浓度数据为基础,将其输入预测模型中进行训练。结果表明:粒子群优化后的小波神经网络在瓦斯浓度预测方面,数值更接近真实值,同时迭代次数在110次左右即达到稳定。 相似文献
6.
通过室内CO2腐蚀模拟实验获得实验数据,利用灰色理论对CO2腐蚀参数进行分析确定CO2腐蚀的主要影响因素,建立BP神经网络腐蚀速率预测模型,利用主要影响因素进行网络训练。利用此模型预测徐深气田某井的腐蚀剖面,预测结果表明:BP神经网络预测结果与气井实验结果接近,体现了BP神经网络在处理非线性数据方面的优越性。灰色理论、神经网络预测模型的研究对于徐深气田CO2腐蚀研究有一定的指导意义。 相似文献
7.
针对燃煤机组选择性催化还原(SCR)系统出口氮氧化物(NOx)预测模型精度不高的问题,提出一种基于最大信息系数(MIC)和长短期记忆(LSTM)神经网络的预测模型方法。首先采用MIC估计各变量的延迟时间,对数据进行时延重构;然后采用重构后数据的MIC值作为评价各输入变量和输出变量间相关性大小的指标,并结合基于关联性的特征选择算法(CFS)进行输入变量筛选;最后基于时延重构和变量筛选后的数据,采用LSTM神经网络建立了SCR出口氮氧化物浓度动态预测模型。该模型被用于广东某320 MW燃煤机组实际运行数据分析。结果表明,经时延重构和变量筛选后所建立的LSTM预测模型具有较高精度,优于深度神经网络(DNN)模型和径向基函数(RBF)神经网络模型,平均绝对百分比误差达2.58%,均方根误差达2.02,可满足现场运用要求。 相似文献
8.
9.
工业循环冷却水腐蚀速率模型的研究 总被引:1,自引:0,他引:1
循环冷却水在工业生产中占有很大比重,而腐蚀是循环冷却水系统中常见的水质故障,严重影响工业生产中设备的运行。通过对某石化公司水质数据的分析,选取对腐蚀速率影响较大的水质参数,凭借神经网络良好的非线性能力,基于NARX神经网络建立了腐蚀速率预测模型。利用该模型对循环冷却水系统腐蚀速率进行预测,结果较好,说明该模型可行,且具有良好的应用前景。 相似文献
10.
11.
利用MATLAB工具箱中的BP神经网络模型建立了乙烯裂解炉的三层神经网络模型,应用该模型分析和预测了裂解产物乙烯和丙烯的收率。预测结果与生产过程数据的比较表明,该模型能适合实际生产过程,可用于乙烯生产的预测分析和预测控制。 相似文献
12.
13.
In this work advanced nonlinear neural networks based control system design algorithms are adopted to control a mechanistic model for an ethanol fermentation process. The process model equations for such systems are highly nonlinear. A neural network strategy has been implemented in this work for capturing the dynamics of the mechanistic model for the fermentation process. The neural network achieved has been validated against the mechanistic model. Two neural network based nonlinear control strategies have also been adopted using the model identified. The performance of the feedback linearization technique was compared to neural network model predictive control in terms of stability and set point tracking capabilities. Under servo conditions, the feedback linearization algorithm gave comparable tracking and stability. The feedback linearization controller achieved the control target faster than the model predictive one but with vigorous and sudden controller moves. 相似文献
14.
Scarlett Chen Zhe Wu Panagiotis D. Christofides 《American Institute of Chemical Engineers》2022,68(6):e17456
In this paper, we propose a control Lyapunov-barrier function-based model predictive control method utilizing a feed-forward neural network specified control barrier function (CBF) and a recurrent neural network (RNN) predictive model to stabilize nonlinear processes with input constraints, and to guarantee that safety requirements are met for all times. The nonlinear system is first modeled using RNN techniques, and a CBF is characterized by constructing a feed-forward neural network (FNN) model with unique structures and properties. The FNN model for the CBF is trained based on data samples collected from safe and unsafe operating regions, and the resulting FNN model is verified to demonstrate that the safety properties of the CBF are satisfied. Given sufficiently small bounded modeling errors for both the FNN and the RNN models, the proposed control system is able to guarantee closed-loop stability while preventing the closed-loop states from entering unsafe regions in state-space under sample-and-hold control action implementation. We provide the theoretical analysis for bounded unsafe sets in state-space, and demonstrate the effectiveness of the proposed control strategy using a nonlinear chemical process example with a bounded unsafe region. 相似文献
15.
利用MATLAB工具箱中的BP神经网络模型建立了乙烯裂解炉的三层神经网络模型,分析和预测了裂解产物乙烯和丙烯的收率,将预测的结果和生产过程数据作比较,结果表明,该模型的预测值和实际生产数据值吻合很好,可用于乙烯生产的预测分析和预测控制。 相似文献
16.
以供应链多级库存为研究背景,建立以生产为中心的供应、生产和销售3个环节的多级库存集成化动态模型,并对模型进行仿真优化。结合训练神经网络的混合算法GA-BP算法,提出了基于遗传算法与人工神经网络相结合的优化预测模型。最后给出实例说明GA-BP算法优化预测模型的求解过程,验证了模型的可行性。 相似文献
17.
M. Erdem Günay Ramazan Yldrm 《Chemical engineering journal (Lausanne, Switzerland : 1996)》2008,140(1-3):324-331
In this study, the design of Pt-Co-Ce/Al2O3 catalyst for the low temperature CO oxidation in hydrogen streams was modeled using artificial neural networks. The effects of five design parameters, namely Pt wt.%, Co wt.%, Ce wt.%, calcination temperature and calcination time, on CO conversion were investigated by modeling the experimental data obtained in our laboratory for 30 catalysts. Although 30 points data set can be considered as small for the neural network modeling, the results were quite satisfactory apparently due to the fact that the experimental data generated with response surface method were well balanced over the experimental region and it was very suitable for neural network modeling. The success of neural network modeling was more apparent when the number of data points was increased to 120 by using the time on stream as another input parameter. It was then concluded that the neural network modeling can be very helpful to improve the experimental works in catalyst design and it may be combined with the statistical experimental design techniques so that the successful models can be constructed using relatively small number of data points. 相似文献
18.
In the area of nonlinear predictive control, several control schemes using artificial neural networks have been proposed. In this work, the issues relating to the information contents of the data used to train the neural network components of these nonlinear predictive control schemes are considered. This raises questions about the design of experiments. A class of feedback-feedforward nonlinear controller based on the model predictive structure (also known as Internal Model Control, IMC, structure) is investigated. The implementation and performance of these neural network based controllers, together with comparisons to other nonlinear and linear controllers, are illustrated on two nonlinear continuous-stirred-tank-reactor simulations. 相似文献
19.
20.
针对化工过程中广泛使用的连续搅拌反应釜(CSTR),提出一种基于神经网络的模型预测控制策略,采用分段最小二乘支持向量机辨识Hammerstein-Wiener模型系数的方法,在此基础上建立线性自回归模式〖DK〗(ARX)结构和高斯径向基神经网络串联的非线性预测控制器。利用BP神经网络训练预测控制输入序列和拟牛顿算法求解非线性预测控制律,从而实现一种基于支持向量机Hammerstein-Wiener辨识模型的非线性神经网络预测控制算法。对CSTR的仿真结果表明,该方法能够更有效地跟踪控制反应物浓度。 相似文献