☆ 4.7 Article

A novel method of neural network model predictive control integrated process monitoring and applications to hot rolling process

EXPERT SYSTEMS WITH APPLICATIONS (2024)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Engineering, Marine

A Novel Damage Identification Method for Steel Catenary Risers Based on a Novel CNN-GRU Model Optimized by PSO

Zhongyan Liu et al.

Summary: The safety evaluation of steel catenary risers (SCRs), a new type of riser connecting offshore platforms and submarine pipelines, is of great significance due to the long-term exposure to waves and currents. This study proposes a damage identification method for SCRs using acceleration time series signals at multiple locations. A convolutional neural network (CNN) is used to obtain spatial information, while a gated recurrent unit (GRU) neural network is employed to study the variable period characteristics. By combining a CNN with a GRU, a CNN-GRU model is established and optimized using particle swarm optimization (PSO) to form the PSO-CNN-GRU (PCG) model. Experimental results show that the proposed PCG model outperforms existing models (CNN, GRU, and CNN-GRU) in SCR damage identification.

JOURNAL OF MARINE SCIENCE AND ENGINEERING (2023)

添加到收藏夹

Article Metallurgy & Metallurgical Engineering

Strip Thickness and Profile-Flatness Prediction in Tandem Hot Rolling Process Using Mechanism Model-Guided Machine Learning

Yu Liu et al.

Summary: This study focuses on the complex characteristics of quality control in the hot strip rolling process. A new prediction model for strip thickness, profile, and flatness is developed using machine learning guided by a rolling mechanism model. The fusion of rolling mechanism and process data, combined with optimization algorithms, improves the accuracy of the model. The results show a significant improvement in prediction accuracy, providing theoretical guidance for controlling strip quality and improving the quality of hot-rolled products.

STEEL RESEARCH INTERNATIONAL (2023)

添加到收藏夹

Article Green & Sustainable Science & Technology

Control of denitration system in cement calcination process: A Novel method of Deep Neural Network Model Predictive Control

Qingquan Xu et al.

Summary: This article introduces a denitration process control strategy for cement calcination based on Deep Neural Network Model Predictive Control (DNN-MPC). The proposed method solves the problems of long delay, nonlinearity, and high data complexity in the denitration system by introducing a time series deep belief network (TS-DBN) prediction model, and uses the model predictive control framework to address the volatility and uncertainty issues in the system. Experimental results show that this method has higher accuracy and stronger robustness in controlling NOx emissions, while reducing the use of ammonia.

JOURNAL OF CLEANER PRODUCTION (2022)

添加到收藏夹

Article Metallurgy & Metallurgical Engineering

Research on High-Precision Transverse Thickness Difference Control Strategy Based on Data Mining in 6-High Tandem Cold Rolling Mills

Yan-Wen Wang et al.

Summary: A random forest predictive model is established in this study to meet the requirement of a dead flat transverse thickness profile for electrical steel strip in a 5-stand 6-high universal crown mill (UCM) tandem cold rolling mills. The control strategy consists of multiple methods, including hydraulic work roll bending system (WRB), hydraulic intermediate roll bending system (IRB), and hydraulic intermediate roll shifting system (IRS). The application of this strategy on a 1420 mm 5-stand 6-high UCM tandem cold rolling mills shows remarkable results with an increase in the rate of TTD less than or equal to 7 mu m from 38.58% to 67.74%.

STEEL RESEARCH INTERNATIONAL (2022)

添加到收藏夹

Article Automation & Control Systems

Coordinate control of strip thickness-crown-tension based on inverse linear quadratic in tandem hot rolling mill

Yafeng Ji et al.

Summary: A multivariable optimizing strategy based on ILQ control theory is proposed to improve the control accuracy of thickness, crown, and tension in hot strip finishing mill. The proposed ILQ control strategy shows excellent control performance compared to the PI controller, with a smaller maximal overshoot of 24.13% when strip crown, thickness, and tension step signals are added simultaneously. This strategy has certain guiding significance for the actual production of hot rolling.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

添加到收藏夹

Article Engineering, Aerospace

Robust Multiple Model Predictive Control for Ascent Trajectory Tracking of Aerospace Vehicles

Rui Cao et al.

Summary: This article proposes a control scheme for aerospace vehicles that combines the guardian maps theory and multimodel predictive control. It uses offline design and online optimization to handle uncertainty and initial deviation with reduced online computation. Additionally, a transient trajectory design method is introduced to reconstruct the trajectory and modify the tracking command in the case of large initial errors.

IEEE TRANSACTIONS ON AEROSPACE AND ELECTRONIC SYSTEMS (2022)

添加到收藏夹

Article Engineering, Chemical

Autogenerated Multilocal PLS Models without Pre-classification for Quality Monitoring of Nonlinear Processes with Unevenly Distributed Data

Lin Xuan You et al.

Summary: To achieve desired product qualities, monitoring the operational status is necessary. Traditional multivariate statistical process control techniques are not suitable for monitoring unevenly distributed process data. This study proposes the use of a multilocal partial least-squares (ML-PLS) model to monitor a wide operation process.

INDUSTRIAL & ENGINEERING CHEMISTRY RESEARCH (2022)

添加到收藏夹

Article Automation & Control Systems

DDPG-based continuous thickness and tension coupling control for the unsteady cold rolling process

Wenying Zeng et al.

Summary: This paper presents a model-free controller based on Deep Deterministic Policy Gradient (DDPG) for thickness and tension control in the unsteady rolling process of cold rolling. By utilizing strategies such as dividing state space variables with the mechanism model, defining reward function and state normalization, the DDPG controller copes with random disturbance and complex uncertainties, achieving better accuracy, stability, and rapidity than the proportional integral (PI) controller.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

添加到收藏夹

Article Automation & Control Systems

Thickness prediction of thin strip cold rolling based on VBGM-RBF

Yue Huang et al.

Summary: This paper proposes a radial basis function neural network based on VBGM-RBF to predict the thickness of cold-rolled thin strip, which shows high accuracy and generalization performance in predicting the thickness of cold-rolled strips, and can be well-applied to the production of thin strip steel.

INTERNATIONAL JOURNAL OF ADVANCED MANUFACTURING TECHNOLOGY (2022)

添加到收藏夹

Article Automation & Control Systems

A Residual-Generator-Based Plug-and-Play Control Scheme Toward Enhancing Power Quality in AC Microgrids

Shannan Luo et al.

Summary: In this article, an active power quality control scheme centered on an observer-based residual generator is proposed for power quality improvement in AC microgrids. The scheme, realized by a plug-and-play configuration, comprises of the control of the power electronic converter, the flexible structure, and the optimization algorithm. The active power quality controller with the plug-and-play flexible structure is designed using the observer-based realization of the Youla parameterization, allowing for improvement of power quality without changing the original controller's structure or parameters. The controller's optimization is achieved by tuning the Youla parameterization system in the plug-and-play flexible structure through a gradient descent optimizing algorithm.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2022)

添加到收藏夹

Article Automation & Control Systems

A quality-related distributed fault detection method for large-scale sequential processes

Xueyi Zhang et al.

Summary: In this paper, a novel distributed fault detection method based on quality-related modified regularized slow feature analysis (QMRSFA) is proposed to deal with dynamics, connection relation, and outliers in large-scale sequential processes. The method eliminates outliers using robust preprocessing methods and decomposes the whole production process into different sub-processes using process knowledge. Experimental results verify the practicality and feasibility of the proposed method.

CONTROL ENGINEERING PRACTICE (2022)

添加到收藏夹

Article Computer Science, Hardware & Architecture

BP Neural Network Combination Prediction for Big Data Enterprise Energy Management System

Sen Xu et al.

Summary: This study proposed a combination prediction method based on the BP neural network to predict the energy consumption of an enterprise EMS, using various models to predict and analyze the energy consumption of the energy management system. The results showed that the average relative error of this method is 3.327% and 1.298% respectively, which are significantly lower than existing approaches, improving prediction accuracy.

MOBILE NETWORKS & APPLICATIONS (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Single and Multi-label Fault Classification in rotors from unprocessed multi-sensor data through deep and parallel CNN architectures

Nikhil A. Sonkul et al.

Summary: This study addresses two issues related to fault classification in machinery using Convolution Neural Network and Deep Learning techniques for single faults and multi-label faults classification, showing effective results for both types of faults.

EXPERT SYSTEMS WITH APPLICATIONS (2021)

添加到收藏夹

Article Environmental Sciences

Prediction of nitrogen oxide emission concentration in cement production process: a method of deep belief network with clustering and time series

Xiaochen Hao et al.

Summary: This study proposes a NOx emission concentration prediction model using a deep belief network with clustering and time series features in cement production, which has higher accuracy, stability, and generalization ability.

ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH (2021)

添加到收藏夹

Article Energy & Fuels

Prediction of oil well production based on the time series model of optimized recursive neural network

Yuefei Cheng et al.

Summary: In this study, a method using LSTM and GRU to predict oil field production was developed to improve upon the shortcomings of traditional Arps decline model predictions. Through case studies, it was found that LSTM and GRU can provide effective oil production predictions based on different input parameters, serving as a real-time auxiliary basis for oil well production planning.

PETROLEUM SCIENCE AND TECHNOLOGY (2021)

添加到收藏夹

Article Automation & Control Systems

A nonlinear full condition process monitoring method for hot rolling process with dynamic characteristic

Chuanfang Zhang et al.

Summary: Hot rolling process (HRP) is a complex industrial process that requires monitoring of both loaded and idle conditions. This study proposes a novel nonlinear full condition process monitoring model combining dissimilarity index and support data vector description for condition identification. Utilizing t-SNE to extract NPC for SFA and CA analysis, the proposed model's monitoring performance is verified through real-world application.

ISA TRANSACTIONS (2021)

添加到收藏夹

Article Automation & Control Systems

A novel mass flow controller for tandem hot rolling mills

U. Knechtelsdorfer et al.

Summary: In tandem hot strip rolling mills, roll speed synchronization is crucial to ensuring constant strip tension and improving thickness quality. Cascade master-slave control structure is typically used to maintain uniform mass flow in the mill stands.

JOURNAL OF PROCESS CONTROL (2021)

添加到收藏夹

Article Engineering, Manufacturing

Application of convolutional neural networks for prediction of strip flatness in tandem cold rolling process

Yu Wang et al.

Summary: This paper develops a prediction model based on CNN to accurately predict strip flatness under different conditions. Data preprocessing methods like the isolated forest algorithm and data folding technique were utilized. The model achieved high accuracy by modifying the loss function and using an Inception module as the basic network structure.

JOURNAL OF MANUFACTURING PROCESSES (2021)

添加到收藏夹

Proceedings Paper Automation & Control Systems

Application on Neural PID Control of MN-AGC in Continuous Hot Strip Rolling

Li Bo-qun et al.

Summary: The rolling technique process requires powerful technical support, and the control level of rolling technique has reached a turning point. Introducing new control theories and methods, such as the single neuron adaptive control strategy, has significantly improved the gauge control accuracy and quality in hot strip mills.

PROCEEDINGS OF THE 33RD CHINESE CONTROL AND DECISION CONFERENCE (CCDC 2021) (2021)

添加到收藏夹

Article Engineering, Civil

Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation

Shuai Gao et al.

JOURNAL OF HYDROLOGY (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A multi-product job shop scenario utilising Model Predictive Control

Tobias Sprodowski et al.

EXPERT SYSTEMS WITH APPLICATIONS (2020)

添加到收藏夹

Article Automation & Control Systems

Switching Tube-Based MPC: Characterization of Minimum Dwell-Time for Feasible and Robustly Stable Switching

Bernardo Andres Hernandez Vicente et al.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL (2019)

添加到收藏夹

Article Engineering, Chemical

Adaptive prediction model for fluidized catalytic cracking processes based on the PLS method

Sung Young Kim et al.

ASIA-PACIFIC JOURNAL OF CHEMICAL ENGINEERING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

A new T-S fuzzy model predictive control for nonlinear processes

Ilyes Boulkaibet et al.

EXPERT SYSTEMS WITH APPLICATIONS (2017)

添加到收藏夹

Article Automation & Control Systems

Observer-critic structure-based adaptive dynamic programming for decentralised tracking control of unknown large-scale nonlinear systems

Bo Zhao et al.

INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE (2017)

添加到收藏夹

Article Automation & Control Systems

A novel dynamic non-Gaussian approach for quality-related fault diagnosis with application to the hot strip mill process

Kai Zhang et al.

JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS (2017)

添加到收藏夹

Article Automation & Control Systems

A novel data-based quality-related fault diagnosis scheme for fault detection and root cause diagnosis with application to hot strip mill process

Liang Ma et al.

CONTROL ENGINEERING PRACTICE (2017)

添加到收藏夹

Review Computer Science, Artificial Intelligence

Modeling of the hot metal silicon content in blast furnace using support vector machine optimized by an improved particle swarm optimizer

Xia Xu et al.

NEURAL COMPUTING & APPLICATIONS (2016)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Nonlinear Model Predictive Controller With Multiagent Online Optimizer for Automotive Cold-Start Hydrocarbon Emission Reduction

Ahmad Mozaffari et al.

IEEE TRANSACTIONS ON VEHICULAR TECHNOLOGY (2016)

添加到收藏夹

Review Multidisciplinary Sciences

Principal component analysis: a review and recent developments

Ian T. Jolliffe et al.

PHILOSOPHICAL TRANSACTIONS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2016)

添加到收藏夹

Article Automation & Control Systems

Decentralized Adaptive Optimal Control of Large-Scale Systems With Application to Power Systems

Tao Bian et al.

IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS (2015)

添加到收藏夹

Article Automation & Control Systems

Robust Distributed Model Predictive Control of Constrained Continuous-Time Nonlinear Systems: A Robustness Constraint Approach

Huiping Li et al.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL (2014)

添加到收藏夹

Article Metallurgy & Metallurgical Engineering

A simplified adaptive interval Type-2 fuzzy control in practical industrial application

Zhou Hai-bo et al.

JOURNAL OF CENTRAL SOUTH UNIVERSITY (2014)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Extended Kalman filter-based Elman networks for industrial time series prediction with GPU acceleration

Jun Zhao et al.

NEUROCOMPUTING (2013)

添加到收藏夹

Article Automation & Control Systems

Tube-based robust nonlinear model predictive control

D. Q. Mayne et al.

INTERNATIONAL JOURNAL OF ROBUST AND NONLINEAR CONTROL (2011)

添加到收藏夹

Article Engineering, Aerospace

Modeling and Model Reference Adaptive Control of Aircraft with Asymmetric Damage

Yu Liu et al.

JOURNAL OF GUIDANCE CONTROL AND DYNAMICS (2010)

添加到收藏夹

Article Automation & Control Systems

Min-max Model Predictive Control of Nonlinear Systems: A Unifying Overview on Stability

Davide Martino Raimondo et al.

EUROPEAN JOURNAL OF CONTROL (2009)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Nonlinear predictive control to track deviated power of an identified NNARX model of a hydro plant

Nand Kishor

EXPERT SYSTEMS WITH APPLICATIONS (2008)

添加到收藏夹

Article Engineering, Electrical & Electronic

A refinement procedure for PID controllers

I Kaya et al.

ELECTRICAL ENGINEERING (2006)

添加到收藏夹

Article Automation & Control Systems

Predictive control of switched nonlinear systems with scheduled mode transitions

P Mhaskar et al.

IEEE TRANSACTIONS ON AUTOMATIC CONTROL (2005)

添加到收藏夹

Article Automation & Control Systems

Nonlinear process monitoring using JITL-PCA

C Cheng et al.

CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS (2005)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.