检索结果-内蒙古大学图书馆

data-driven identification and comparison of full multivariable models for propofol-remifentanil induced general anesthesia

引用

JOURNAL OF process control 2024年 139卷

作者： Yumuk, Erhan Copot, Dana Ionescu, Clara M. Neckebroek, Martine Univ Ghent Dept Electromech Syst & Met Engn Res lab Dynam Syst & Control Ghent Belgium Ghent Univ Hosp Dept Anesthesia Corneel Heymanslaan 10 B-9000 Ghent Belgium

In this paper, we present results with clinical data to enable a 2x2 input-output multivariable patient model for hypnosis and analgesia. Nonlinear multi -drug interaction models are identified from data recorded from 70 patients undergoing surgery during total intravenous anesthesia (TIVA) with several medical monitors for variables such as Bispectral Index, Nociception level (Medasense), skin conductance (Medstorm) and advanced spectral analysis conductance (AnspecPro). Bispectral index measures the depth of hypnosis (lack of consciousness), while nociception related indices from Medasense, Medstorm, and AnspecPro devices measure levels related to analgesia (lack of reaction to noxious stimuli). A comparison is given among three response surface model (RSM) structures - Minto, Greco, and Reduced Greco - for hypnotic and analgesic states during Propofol-Remifentanil interaction. The identified models capture the pharmacodynamic properties of dose-effect concentrations of Propofol/Remifentanil while the pharmacokinetic part of the patient model is calculated from patient's biometric values using Schnider/Minto (SM), and Eleveld/Eleveld (EE) models. In presence of strict clinical protocols delivering data under poor identifiability conditions, we propose two methods of identification: (i) based on steady-state gains, and (ii) using all available data which includes part of the dynamic transient. The model parameters are optimized with Genetic Algorithm based on a goodness of fit performance measure complemented with root mean square error. The results suggest that the EE model combination is advantageous for Bispectral index pharmacokinetic modeling at the cost of numerical complexity, therefore reducing the uncertainty left to be identified in the pharmacodynamic part of the patient model. By contrast, the SM model combination is less computationally demanding and provides some improvement in the RSM accuracy for nociception level indicators. The comparison of three

关键词： Response surface models Depth of anesthesia Closed loop control of anesthesia Multivariable models Nonlinear gain Multivariable control

来源：评论

学校读者我要写书评

暂无评论

Semi-Supervised Soft Sensor modeling for Industrial Dynamic Information Mining Based on Two-Path Weight Comparison

Semi-Supervised Soft Sensor Modeling for Industrial Dynamic ...

引用

data Driven control and Learning Systems (DDCLS)

作者： Ruining Jia Xinyi Jin Xinru Ni Mengjiao Ruan Zeyu Yang Peiliang Wang Huzhou Key Laboratory of Intelligent Sensing and Optimal Control for Industrial Systems School of Engineering Huzhou University Huzhou P. R. China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Deep learning methods can extract reliable feature representations from massive process data to build accurate soft sensor models. However, the data in actual industrial production is often nonlinear, dynamic, and even limited in label samples due to untimely sampling and analysis. Aiming at the above problems, this paper proposes a semi-supervised soft sensor modeling method (SSACF-LSTM) for industrial dynamic information mining based on two-path weight comparison. An unsupervised long short-term memory network (LSTM) encoder-decoder is utilized to extract the hidden dynamic nonlinear information in unlabeled samples. This information is then spliced and masked with the initial input, which is subsequently fed into a deep neural network encoder-decoder for pretraining to learn a self-supervised task that mines correlation information between sequences as well as between samples that is useful for the model. In addition, the LSTM with attentional convolutional fusion serves as an auxiliary path that mines correlation information between variables directly from the initial input to complement the information extracted by self-supervision. Finally, the results of both are linearly weighted to obtain the final prediction. The method is validated in a debutanizer process. The results show that SSACF-LSTM can utilize both labeled and unlabeled data to extract quality-related features for soft sensor modeling, which is better than the semi-supervised LSTM network with historical feature fusion (HFF-ssLSTM), semi-supervised stacked auto-encoder (SSAE), and variational auto-encoder regression (SVAER).

关键词： Correlation Accuracy Soft sensors Production Feature extraction data models data mining

来源：评论

学校读者我要写书评

暂无评论

A Decomposition-based Encoder-Decoder Framework for Multi-step Prediction of Burn-Through Point in Sintering process

A Decomposition-based Encoder-Decoder Framework for Multi-st...

引用

Industrial Cyber-Physical Systems (ICPS)

作者： Yuhan Xie Bocun He Xinmin Zhang Zhihuan Song State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China

Sintering process is a critical step in the ironmaking process. Burn-through point (BTP), as a key performance index of sintering ore, has a great influence on the quality of the sintering product. The existing prediction methods attempt to use a single model to establish the relationship between variables. However, due to the strong volatility, uncertainty, and multivariable coupling of sintering process, the traditional prediction model cannot produce reliable predictions. In order to deal with the complex characteristics of sintering process, this paper proposes a decomposition-based encoder-decoder modeling framework, in which a sequence decomposition module is designed to decompose the input time series into different sub-sequences. Then, these sub-sequences are constructed by the encoder-decoder models separately. The effectiveness of the proposed multi-step ahead prediction modeling framework was evaluated in a real-world sintering process. Compared with the traditional prediction modeling framework, the proposed modeling framework has more accurate results in multi-step ahead prediction.

关键词： Couplings Uncertainty Time series analysis Sintering Predictive models Cyber-physical systems data models

来源：评论

学校读者我要写书评

暂无评论

A review of semi-supervised learning for industrial process regression modeling 40

A review of semi-supervised learning for industrial process ...

引用

40th Chinese control conference (CCC)

作者： Xu, Wen Tang, Jian Xia, Heng Beijing Univ Technol Fac Informat Technol Beijing 100124 Peoples R China Beijing Lab Smart Environm Protect Beijing 100124 Peoples R China

ISBN: (纸本)9789881563804

It is difficult to directly measure the parameters such as product quality and environmental protection index in complex industrial process by testing instrument. This is mainly caused by the restriction of site environment, measurement technology and economic cost. The establishment of data-driven soft sensor model is one of the effective methods for online estimation of these difficult parameters. However, the truth values of these difficult-to-detect parameters are usually obtained after off-line laboratory analysis. This method has the disadvantage of high time lag and high cost, which leads to the lack of labeled samples used to construct soft sensor. In contrast, a large number of auxiliary variables can be acquired and stored in real time through industrial control systems, which are used as input of soft sensor model. This makes Semi-supervised Learning (SSL) become a research hotspot. The reason is that it can make full use of a small number of labeled samples and a large number of unlabeled samples to improve the generalization performance of soft sensor model. With this in mind, this article aims to provide an overview of existing SSL methods for industrial process regression modeling. At first, a brief description of the basic idea, assumptions and applications of SSL is given. Secondly, the semi-supervised regression (SSR) method for industrial process is described from several perspectives. Then, the research difficulties of SSR are pointed out. Finally, the research and outlook is carried out, and the future research direction is pointed out, that is, combining the characteristics of specific industrial process to build the SSR intelligent soft sensor model based on multi-mode data.

关键词： Complex industrial processes Soft sensing Semi-supervised learning Integrated learning Semi-supervised regression modeling

来源：评论

学校读者我要写书评

暂无评论

Quantum Enhanced AI to Predict the Traffic Flow

Quantum Enhanced AI to Predict the Traffic Flow

引用

Emerging Research in Computational Science (ICERCS), International conference on

作者： Thenmozhi M Abishake S Dhayal S R Rohit Kanna P R Department of Artificial Intelligence and Data Science Sri Eshwar College of Engineering (Autonomous) Coimbatore India

ISBN: (数字)9798331534967

ISBN: (纸本)9798331534974

This research work proposes a quantum traffic flow prediction system based on the difficulty of traffic congestion in cities. The system uses real-time traffic data, details on weather condition, and the behavioral patterns of drivers flexibly by incorporating machine learning along with quantum algorithms as an integrated approach. The data is collected through different data collection instruments namely, traffic sensors, GPS devices, and weather stations, making the data set holistic for analysis. In this model, the basic traditional algorithms of Long Short- Term Memory (LSTM) and Convolutional Neural Networks (CNN) are applied together with quantum-based optimization approaches including the Quantum Genetic Algorithm (QGA) and Learning Vector Quantization (LVQ). The QGA component is involved in the process of feature selection and modeling parameters, LVQ operates on traffic patterns classification. Together, these quantum-enhanced algorithms increase system efficiency and ensure efficient input-output work, especially when working with extensive and variable data arrays. Hence, the present research captures the flow of the model development process and establishes the evaluation of the current model’s efficiency over the conventional prediction models. Outcomes indicate considerable enhancements in predicting novelties and regulating congestion characteristic of the system’s suitability for smart city structures and urban traffic applications.

关键词： Accuracy Vector quantization Computational modeling Predictive models Traffic control Prediction algorithms Classification algorithms Convolutional neural networks Meteorology Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Multi-source and multimodal data fusion for improved management of a wastewater treatment plant

引用

JOURNAL OF ENVIRONMENTAL CHEMICAL ENGINEERING 2023年第6期11卷

作者： Strelet, Eugeniu Peng, You Castillo, Ivan Rendall, Ricardo Wang, Zhenyu Joswiak, Mark Braun, Birgit Chiang, Leo Reis, Marco S. Univ Coimbra Dept Chem Engn CIEPQPF Rua Silvio LimaPolo II-Pinhal de Marrocos P-3030790 Coimbra Portugal Dow Chem Co USA Lake Jackson TX USA

Wastewater treatment plants (WWTPs) are complex systems presenting stochastic, non-linear, and non stationary behavior, which makes their operational management very challenging. In this context, data collected from distributed sources across the plant play a central role in the optimized operation and control of WWTPs. However, even when available, the use of collected data is far from trivial due to the coexistence of asynchronous measurements, data with different granularity, measurements of different quality (precision, accuracy), multimodal sources (sensors, spectra, images, hyphenated instrumentation), among other aspects related to the data life cycle. Such heterogeneity in process data characteristics hinders the application of most off-the-shelf data analytics methods. Flexible solutions able to cope with the complexity of systems and of the data they generate are therefore necessary to overcome these limitations and enable an effective analysis and operation of WWTPs. In this article, data-fusion approaches for handling multiple heterogeneous sources of process data are developed and comparatively tested. Priority is given to solutions that can flexibly be adapted to different specific operational contexts. The methodologies are tested on an industrial case study (WWTP), where the concentration of a toxin in the effluent stream is to be predicted from available heterogeneous data. Single and multi-source modeling approaches are contemplated and a nested cross-validation method was developed to handle the time-series nature of the models. Bayesian fusion synergistically combines data from different sources considering their uncertainty, standing out among the methodologies tested as offering a good balance in terms of accuracy (RMSEP = 1.34), stability (prequential IQR = 0.034), and flexibility (to accommodate missing and new sources).

关键词： Heterogeneous data fusion Multimodal data Wastewater treatment plant Industry 4.0 data-driven modeling

来源：评论

学校读者我要写书评

暂无评论

Research on data-driven continuous casting billet quality prediction modeling approach

Research on data-driven continuous casting billet quality pr...

引用

Electronic Information Engineering and Computer Communication (EIECC), International conference on

作者： Xuan Zhang Jingcheng Wang Binbin Zhang Chao Ma XATU School of Electronic Information Engineering Xi’an China Department of Automation XATU School of Electronic Information Engineering SJTU Shanghai China

ISBN: (数字)9798331534622

ISBN: (纸本)9798331534639

The unreasonable use of process control procedures and composition ratios in the continuous casting production process will have an extremely bad impact, resulting in low steel qualification rate, smelting process energy consumption and other serious problems. In response to the above problems, a continuous casting billet quality prediction model is established from the causes of continuous casting billet quality defects, incorporating data-driven. The process parameters corresponding to the two continuous casting billet qualities, AQ0E1 and DV0A1, were first preprocessed using data cleaning and dimensionality reduction methods. A data-driven approach was adopted to establish a continuous casting billet quality prediction model using shuffling frog leaping algorithm (SFLA), genetic algorithm (GA) and BP neural network to form a hybrid evolutionary neural network (HENN) continuous casting billet quality classification prediction model. The prediction accuracy of AQ0E1 and DV0A1 can reach 88.33% and 90.38%, respectively. The model in this paper has higher accuracy and good stability than traditional methods, the continuous casting billet can be accurately predicted, it is convenient to quickly trace back to the cause of defects in continuous casting billet, and it has a certain guiding significance for the development of intelligent continuous casting industrial production.

关键词： Casting Billets Accuracy Neural networks process control Production Predictive models data models Stability analysis Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deployment of Ontologies as Knowledge Reasoning Technique for Making Autonomous Robots: A Survey

Deployment of Ontologies as Knowledge Reasoning Technique fo...

引用

Intelligent control, Computing and Communications (IC3), International conference on

作者： Nidhi Mishra Balasubramaniam Kumaraswamy Department of CS & IT Kalinga University Raipur India

ISBN: (数字)9798331527495

ISBN: (纸本)9798331527501

Knowledge Representation and Reasoning (KR & R) is a burgeoning subject in the realm of Artificial Intelligence. Its primary objective is to depict data pertaining to a certain field, especially for use in path planning applications. Utilising ontology-based methods for knowledge representation and reasoning enhances understanding of the environment for task processing. Ontology is a valuable instrument for gathering knowledge pertaining to the environment, events, and actions. This enhances the efficacy of path planning and the autonomy of robots. Knowledge reasoning approaches are essential for dynamically deducing novel conclusions, particularly in non-deterministic situations. This work thoroughly investigates the process of representing information using ontology and analyses reasoning techniques that play a vital role in path planning. Furthermore, we offer a comprehensive analysis of several planned domain description dialects, ontology editors, developers, and robot simulations systems in the subsequent sections.

关键词： Surveys Analytical models Computational modeling Instruments Ontologies Cognition Path planning Intelligent control Autonomous robots

来源：评论

学校读者我要写书评

暂无评论

37th International conference on Advanced Information Networking and Applications, AINA 2023

37th International Conference on Advanced Information Networ...

引用

37th International conference on Advanced Information Networking and Applications, AINA 2023

ISBN: (纸本)9783031284502

The proceedings contain 160 papers. The special focus in this conference is on Advanced Information Networking and Applications. The topics include: D-insta: A Decentralized Image Sharing Platform;simulation modeling of Human Aortic Valve Blood Flow;ramification of Sentiments on Robot-Based Smart Agriculture: An analysis Using Real-Time Tweets;the Digital Humanities Trend in Chinese Film History: A Case Study of Filmmaker Lvban;A Tool for Creation of Virtual Exhibits Presented as iiIF Collections by Intelligent Agents;recommender Systems in the Museum Sector: An Overview;Towards the Enrichment of iiIF Framework with Semantically Annotated and Geo-Located images;Comparison of ML Solutions for HRIR Individualization Design in Binaural Audio;Performance analysis of a BESU Permissioned Blockchain;AI-Powered Drone to Address Smart City Security Issues;range Proofs with Constant Size and Trustless Setup;sensorless Predictive Maintenance: An Example on a ‘Not 4.0’ Coffee Machine Production process;An Integrated System for Vibration Suppression Using Fuzzy control and 2D-LiDAR;attendance System via Internet of Things, Blockchain and Artificial Intelligence Technology: Literature Review;an Overview and Current Status of Blockchains Performance;AgriBIoT: A Blockchain-Based IoT Architecture for Crop Insurance;distribution of the Training data Over the Shortest Path Between the Servers;a Decentralized Architecture for Electric Vehicle Charging Platform;services and Operations of Electric Vehicle System by Virtual Power Plant in Rural Area;a Triangulation Based Water Level Measuring System for a Water Reservoir Tank;A System Architecture for Heterogeneous Time- Sensitive Networking Based on SDN;a Parking System Based on Priority Scheme;DTAG: A Dynamic Threshold-Based Anti-packet Generation Method for Vehicular DTN;prediction in Smart Environments and Administration: Systematic Literature Review;Optimal and Suboptimal Routing Protocols for WSN;CL-DECCM-SA: A Cluster-based Delauna

关键词：

来源：评论

学校读者我要写书评

暂无评论

Information Entropy-Based Fault Detection for Quality-Related processes

Information Entropy-Based Fault Detection for Quality-Relate...

引用

data Driven control and Learning Systems (DDCLS)

作者： Yongye Zhu Jinglin Zhou College of Information Science & Technology Beijing University of Chemical Technology Beijing China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Canonical Correlation analysis (CCA) is currently very popular in the field of data-driven fault detection. The CCA method usually assumes that the data obeys a Gaussian distribution, but the sample data collected in the actual complex industrial production process often has non-Gaussian characteristics, and the CCA method is not very suitable for modeling this kind of data. In order to extend the applicability of the CCA method from Gaussian data space to non-Gaussian data space, this paper proposes an information entropy-based quality-related process fault detection method (ECCA) based on CCA. First, the ECCA approach takes as its objective function to maximize the mutual information of typical pairs of variables in the space of process and quality variables. The objective function is also optimized using Particle Swarm Optimization (PSO) algorithm to solve for the optimal pairs of typical variables; Second, when considering the extraction of the next pair of independent typical variable pairs, the extraction of independent typical variable pairs can be achieved by resorting to the framework of the Partial Least Squares (PLS) algorithm in combination with the minimization of the information entropy of the residuals in the space of the process and quality variables; Third, a truncation criterion for the number of typical variables is identified; Fourth, T 2 and Te 2 statistics are constructed to monitor the system; Finally, the ECCA method is applied to synthetic data and TE process data for comparison with the traditional CCA method. Experimental validation shows that the ECCA method has better monitoring performance than the traditional CCA method in monitoring quality-related process faults.

关键词： Correlation Fault detection process control Linear programming data mining Object recognition Information entropy

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：