检索结果-内蒙古大学图书馆

Improving extrapolation capabilities of a data-driven prediction model for control of an air separation unit

COMPUTERS & CHEMICAL ENGINEERING 2025年 194卷

作者： Krespach, Valentin Blum, Nicolas Pottmann, Martin Rehfeldt, Sebastian Klein, Harald Tech Univ Munich Inst Plant & Proc Technol TUM Sch Engn & Design Dept Energy & Proc Engn Boltzmannstr 15 D-85748 Garching Germany Linde GmbH Linde Engn Dr Carl von Linde Str 6-14 D-82049 Pullach Germany

In model predictive control, fully data-driven prediction models can be used besides common (non-)linear prediction models based on first-principles. Although no process knowledge is required while relying only on sufficient data, they suffer in their extrapolation capability which is shown in the present work for the control of an air separation unit. In order to compensate for the deficits in the extrapolation behavior, a further data source, here a digital twin, is deployed for additional data generation. The plant data set is augmented with the artificially generated data giving rise to a hybrid model in terms of data generation. It is shown that this model can significantly improve the prediction quality informer extrapolation areas of the plant data set. Even conclusions about the uncertainty behavior of the prediction model can be found.

关键词： Advanced process control Extrapolation data augmentation data-driven prediction model Air separation

来源：评论

学校读者我要写书评

暂无评论

data-driven prediction model for adjusting burden distribution matrix of blast furnace based on improved multilayer extreme learning machine

引用

SOFT COMPUTING 2018年第11期22卷 3575-3589页

作者： Su, Xiaoli Zhang, Sen Yin, Yixin Liu, Yanan Xiao, Wendong Univ Sci & Technol Beijing Sch Automat & Elect Engn Beijing 100083 Peoples R China Univ Sci & Technol Beijing Minist Educ Sch Automat & Elect Engn Key Lab Knowledge Automat Ind Proc Beijing 100083 Peoples R China

Reasonable burden distribution matrix is one of important requirements that can realize low consumption, high efficiency, high quality and long campaign life of the blast furnace. This paper proposes a data-driven prediction model of adjusting the burden distribution matrix based on the improved multilayer extreme learning machine (ML-ELM) algorithm. The improved ML-ELM algorithm is based on our previously modified ML-ELM algorithm (named as PLS-ML-ELM) and the ensemble model. It is named as EPLS-ML-ELM. The PLS-ML-ELM algorithm uses the partial least square (PLS) method to improve the algebraic property of the last hidden layer output matrix for the ML-ELM algorithm. However, the PLS-ML-ELM algorithm may have different results in different trails of simulations. The ensemble model can overcome this problem. Moreover, it can improve the generalization performance. Hence, the EPLS-ML-ELM algorithm is consisted of several PLS-ML-ELMs. The real blast furnace data are used to testify the data-driven prediction model. Compared with other prediction models which are based on the SVM algorithm, the ELM algorithm, the ML-ELM algorithm and the PLS-ML-ELM algorithm, the simulation results demonstrate that the data-driven prediction model based on the EPLS-ML-ELM algorithm has better prediction accuracy and generalization performance.

关键词： Extreme learning machine Multilayer extreme learning machine Blast furnace Burden distribution matrix Ensemble model data-driven prediction model

来源：评论

学校读者我要写书评

暂无评论

Current sensor fault diagnosis and fault-tolerant control for single-phase PWM rectifier based on a hybrid model-based and data-driven method

引用

IET POWER ELECTRONICS 2020年第18期13卷 4150-4157页

作者： Xia, Yang Xu, Yan Gou, Bin Nanyang Technol Univ Sch Elect & Elect Engn Singapore Singapore Southwest Jiaotong Univ Sch Elect Engn Chengdu Peoples R China

In this study, a hybrid model-based and data-driven method is proposed for the current sensor fault diagnosis used in single-phase pulse width modulation (PWM) rectifier. According to the principle of model-based methods, the proposed diagnostic method is based on signal prediction and residual generation. Differently, instead of a mathematical model, the signal prediction model is developed based on a data-driven method. Non-linear autoregressive exogenous learning model, randomised learning technique, and extreme learning machine are utilised to generate the data-driven prediction model. Once the fault is detected, fault-tolerant control is activated by substituting the predicted signal for the information of faulty sensors. The offline test shows that the proposed method is able to predict the sensor signal accurately with the root mean square error of 4.276 x 10(-5). In addition, hardware-in-the-loop tests are conducted to verify the feasibility and reliability of the proposed method in the real-time application.

关键词： autoregressive processes learning (artificial intelligence) electric sensing devices PWM rectifiers fault diagnosis fault tolerant control data handling feedforward neural nets control engineering computing current sensor fault diagnosis fault-tolerant control single-phase PWM rectifier data-driven method single-phase pulse width modulation rectifier model-based methods diagnostic method mathematical model signal prediction model nonlinear autoregressive exogenous learning model data-driven prediction model sensor signal prediction hybrid model-based method residual generation randomised learning extreme learning machine hardware-in-the-loop tests real-time application

来源：评论

学校读者我要写书评

暂无评论

A study on source domain selection for transfer learning-based cross-building cooling load prediction

引用

ENERGY AND BUILDINGS 2024年 324卷

作者： Zhang, Qiang Niu, Jide Tian, Zhe Bao, Lingling Luo, Jinghui Wang, Mingyuan Cao, Yaqi Hebei Univ Engn Coll Energy & Environm Engn Hebei Technol Innovat Ctr HVAC Engn Handan 056038 Peoples R China Tianjin Univ Sch Environm Sci & Engn Tianjin Key Lab Built Environm & Energy Tianjin 300072 Peoples R China Hebei Univ Engn Anal & Testing Lab Ctr Handan 056038 Peoples R China

Transfer learning (TL) can utilize data from information-rich source domain buildings to help information-poor target domain buildings establish cooling load prediction models, thereby enabling cross-building cooling load prediction. However, the prediction performance varies based on the type of source domain building used, making the reasonable selection of source domain buildings crucial. Traditionally, data similarity of source- target building pairs is measured to identify the appropriate source domain building. Yet, this method will result in erroneous judgments if the similarity index used is inappropriate, the target domain building's available data are scarce, or all candidate source domain buildings exhibit weak similarities. To address this issue, this study explores the selection of source domain buildings based on building feature consistency in a data-centric manner. Specifically, 81 buildings with different features and 240 source-target building pairs are designed. The TL method is then used to develop prediction models for each pair. The decision tree method is finally employed to evaluate the correlation between the feature consistency of source-target building pairs and model prediction performance. From this correlation, a selection strategy is derived that specifies the consistency requirements for three key features (scale, function, and climate zone) of source-target building pairs at different accuracy levels. This strategy offers a methodical guide for the selection of the source domain building.

关键词： Building cooling load data-driven prediction model Transfer learning Limited data

来源：评论

学校读者我要写书评

暂无评论

Limited data-oriented building heating load prediction method: A novel meta learning-based framework

引用

ENERGY AND BUILDINGS 2024年 308卷

作者： Lu, Yakai Peng, Xingyu Li, Conghui Tian, Zhe Kong, Xiangfei Hebei Univ Technol Sch Energy & Environm Engn Tianjin 300401 Peoples R China Tianjin Univ Sch Environm Sci & Engn Key Lab Efficient Utilizat Low & Medium Grade Ener MOE Tianjin 300072 Peoples R China

data-driven models have been widely used in building heating load prediction, but often fail when facing limited data. Previous studies have shown transfer learning can assist model learning of target building under limited data by means of other source building data, however, which is subject to the similarity between source and target building. Selecting similar source building data is not easy, especially when the target building is with limited data. This paper, therefore, proposes a novel meta learning-based framework for building heating load prediction. Using meta learning method, a set of promising model parameters is trained by local and global learning on multiple source buildings data. The obtained model parameters has the ability to get quickly trained with few data in each source building, which is further used as model initialization parameters of target building to assist model learning. Framework validity is confirmed by 550 groups of practical buildings data (50 are as target buildings for testing and 500 are as source buildings). The results showed the proposed framework could reduce the prediction errors by 2.04 %similar to 61.59 % compared with six common transfer learning methods. The novel meta learning-based framework provides an effective solution for building heating load prediction with limited data.

关键词： Building heating load data-driven prediction model Limited data Meta learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of ANN and SVM models Combined with Wavelet Preprocess for Groundwater Depth prediction

引用

WATER 2017年第10期9卷 781页

作者： Zhou, Ting Wang, Faxin Yang, Zhi Anhui Agr Univ Sch Engn Hefei 230036 Anhui Peoples R China Anhui & Huaihe River Inst Hydraul Res Hefei 230088 Anhui Peoples R China Inst Huai River Water Resources Protect Bengbu 233001 Peoples R China

Reliable prediction of groundwater depth fluctuations has been an important component in sustainable water resources management. In this study, a data-driven prediction model combining discrete wavelet transform (DWT) preprocess and support vector machine (SVM) was proposed for groundwater depth forecasting. Regular artificial neural networks (ANN), regular SVM, and wavelet preprocessed artificial neural networks (WANN) models were also developed for comparison. These methods were applied to the monthly groundwater depth records over a period of 37 years from ten wells in the Mengcheng County, China. Relative absolute error (RAE), Pearson correlation coefficient (r), root mean square error (RMSE), and Nash-Sutcliffe efficiency (NSE) were adopted for model evaluation. The results indicate that wavelet preprocess extremely improved the training and test performance of ANN and SVM models. The WSVM model provided the most precise and reliable groundwater depth prediction compared with ANN, SVM, and WSVM models. The criterion of RAE, r, RMSE, and NSE values for proposed WSVM model are 0.20, 0.97, 0.18 and 0.94, respectively. Comprehensive comparisons and discussion revealed that wavelet preprocess extremely improves the prediction precision and reliability for both SVM and ANN models. The prediction result of SVM model is superior to ANN model in generalization ability and precision. Nevertheless, the performance of WANN is superior to SVM model, which further validates the power of data preprocess in data-driven prediction models. Finally, the optimal model, WSVM, is discussed by comparing its subseries performances as well as model performance stability, revealing the efficiency and universality of WSVM model in data driven prediction field.

关键词： groundwater depth data-driven prediction model wavelet transform support vector machine artificial neural network

来源：评论

学校读者我要写书评

暂无评论

Energy price prediction using data-driven models: A decade review

引用

COMPUTER SCIENCE REVIEW 2021年 39卷 100356-100356页

作者： Lu, Hongfang Ma, Xin Ma, Minda Zhu, Senlin Purdue Univ Construct Engn & Management W Lafayette IN 47907 USA Southwest Univ Sci & Technol Sch Sci Mianyang 621010 Sichuan Peoples R China Tsinghua Univ Dept Earth Syst Sci Beijing 100084 Peoples R China Yangzhou Univ Coll Hydraul Sci & Engn Yangzhou 225127 Jiangsu Peoples R China Nanjing Hydraul Res Inst State Key Lab Hydrol Water Resources & Hydraul En Nanjing 210029 Peoples R China

The accurate prediction of energy price is critical to the energy market orientation, and it can provide a reference for policymakers and market participants. In practice, energy prices are affected by external factors, and their accurate prediction is challenging. This paper provides a systematic decade review of data-driven models for energy price prediction. Energy prices include four types: natural gas, crude oil, electricity, and carbon. Through the screening, 171 publications are reviewed in detail from the aspects of the basic model, the data cleaning method, and optimizer. Publishing time, model structure, prediction accuracy, prediction horizon, and input variables for energy price prediction are discussed. The main contributions and findings of this paper are as follows: (1) basic prediction models for energy price, data cleaning methods, and optimizers are classified and described;(2) the structure of the prediction model is finely classified, and it is inferred that the hybrid model and prediction architecture with multiple techniques are the focus of research and the development direction in the future;(3) root mean square error, mean absolute percentage error, and mean absolute error are the three most frequently used error indicators, and the maximum mean absolute percentage error is less than 0.2;(4) the ranges of data size and data division ratio for energy price prediction in different horizons are given, the proportion of the test set is usually in the range of 0.05-0.35;(5) the input variables for energy price prediction are summarized;(6) the data cleaning method has a more significant role in improving the accuracy of energy price prediction than the optimizer. (C) 2020 Elsevier Inc. All rights reserved.

关键词： Energy price data-driven prediction model Natural gas Crude oil Electricity Carbon

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：