The Experts below are selected from a list of 885 Experts worldwide ranked by ideXlab platform

Chuanhou Gao - One of the best experts on this subject based on the ideXlab platform.

  • Online process monitoring based on incremental LPP
    2011
    Co-Authors: Jiusun Zeng, Chuanhou Gao, Shihua Luo
    Abstract:

    Process monitoring by manifold learning has become an important research area. This paper proposes an online process monitoring scheme based on incremental locality preserving projection (LPP). As new data sample arrives, the algorithm makes use of the previous computation results to update the neighbor structure; and also by using the eigenvectors at last time step as the initial vector of the Raleigh quotient iteration, thus achieves higher efficiency. The incremental LPP is then used to construct process monitoring model for Blast Furnace Ironmaking process. Application results show that the proposed method can efficiently track the time-varying characteristics of the process, discover faults of the process and reduce false alarms.

  • A refined prediction model of silicon content based on the Kalman Filter
    2010
    Co-Authors: Wei Pan, Jiusun Zeng, Xiang-guan Liu, Chuanhou Gao
    Abstract:

    Prediction of silicon content in hot metal is an important task in the control of Blast Furnace Ironmaking process. Due to the complexity of Blast Furnace Ironmaking process, most predictive models may work well under stable conditions, however, when the production is instable, the performance may deteriorate, which means loss of much valuable information contained in the variables. Actually, the residuals of the predictive model consist of two parts, i.e., unmodelled information and noise. In this paper, a TGARCH model (Threshold autoregressive conditional heteroskedasticity model) is used to predict silicon content in hot metal and the residuals are modeled by a Kalman Filter. The Kalman filter is used to separate the unmodeled information from noise and the captured information is then incorporated into the original model. The proposed method was tested on data collected from a medium-sized Blast Furnace. Simulation results shows that Kalman filter well improve the accuracy of TGARCH model.

  • Data-driven predictive control for Blast Furnace Ironmaking process
    Computers & Chemical Engineering, 2010
    Co-Authors: Jiusun Zeng, Chuanhou Gao
    Abstract:

    Abstract High performance control of Blast Furnace (BF) Ironmaking process is a difficult problem due to the high temperature and hostile measurement conditions for measuring devices in the process. Previous research focused on developing of accurate predictive models for silicon content in hot metal ([SI]) while control of the whole process is seldom discussed. In the present work, a data-driven predictive control method based on subspace method is presented for the Blast Furnace Ironmaking process. The algorithm is based on input–output data and easy to implement. Simulation results show the algorithm is effective for the control application. Finally, various practical issues concerning predictive control of Blast Furnace Ironmaking process are also addressed, such as constraint handling, control objective and output set-point selection, adaptive strategy, etc.

  • a chaos based iterated multistep predictor for Blast Furnace Ironmaking process
    Aiche Journal, 2009
    Co-Authors: Chuanhou Gao, Jiming Chen, Jiusun Zeng, Xueyi Liu, Youxian Sun
    Abstract:

    The prediction and control of the inner thermal state of a Blast Furnace, represented as silicon content in Blast Furnace hot metal, pose a great challenge because of complex chemical reactions and transfer phenomena taking place in Blast Furnace Ironmaking process. In this article, a chaos-based iterated multistep predictor is designed for predicting the silicon content in Blast Furnace hot metal collected from a pint-sized Blast Furnace. The reasonable agreement between the predicted values and the observed values indicates that the established high dimensional chaotic predictor can predict the evolvement of silicon series well, which conversely render the strong indication of existing deterministic mechanism ruling the dynamics of complex Blast Furnace Ironmaking process, i.e., a high-dimensional chaotic system is suitable for representing the Blast Furnace system. The results may serve as guidelines for characterizing Blast Furnace Ironmaking process, an extremely complex but fascinating field, with chaos in the future investigation. © 2009 American Institute of Chemical Engineers AIChE J, 2009

  • A chaos‐based iterated multistep predictor for Blast Furnace Ironmaking process
    AIChE Journal, 2009
    Co-Authors: Chuanhou Gao, Jiming Chen, Jiusun Zeng, Xueyi Liu, Youxian Sun
    Abstract:

    The prediction and control of the inner thermal state of a Blast Furnace, represented as silicon content in Blast Furnace hot metal, pose a great challenge because of complex chemical reactions and transfer phenomena taking place in Blast Furnace Ironmaking process. In this article, a chaos-based iterated multistep predictor is designed for predicting the silicon content in Blast Furnace hot metal collected from a pint-sized Blast Furnace. The reasonable agreement between the predicted values and the observed values indicates that the established high dimensional chaotic predictor can predict the evolvement of silicon series well, which conversely render the strong indication of existing deterministic mechanism ruling the dynamics of complex Blast Furnace Ironmaking process, i.e., a high-dimensional chaotic system is suitable for representing the Blast Furnace system. The results may serve as guidelines for characterizing Blast Furnace Ironmaking process, an extremely complex but fascinating field, with chaos in the future investigation. © 2009 American Institute of Chemical Engineers AIChE J, 2009

Jiusun Zeng - One of the best experts on this subject based on the ideXlab platform.

  • Online process monitoring based on incremental LPP
    2011
    Co-Authors: Jiusun Zeng, Chuanhou Gao, Shihua Luo
    Abstract:

    Process monitoring by manifold learning has become an important research area. This paper proposes an online process monitoring scheme based on incremental locality preserving projection (LPP). As new data sample arrives, the algorithm makes use of the previous computation results to update the neighbor structure; and also by using the eigenvectors at last time step as the initial vector of the Raleigh quotient iteration, thus achieves higher efficiency. The incremental LPP is then used to construct process monitoring model for Blast Furnace Ironmaking process. Application results show that the proposed method can efficiently track the time-varying characteristics of the process, discover faults of the process and reduce false alarms.

  • Identification of the Optimal Control Center for Blast Furnace Thermal State Based on the Fuzzy C-means Clustering
    ISIJ International, 2011
    Co-Authors: Shihua Luo, Jiusun Zeng, Jian Huang, Qiansheng Zhang
    Abstract:

    It is required to maintain silicon content in hot metal ([Si]) at a stable level to ensure smooth operation of the Blast Furnace Ironmaking process. However, current Blast Furnace control strategy always leads to frequent fluctuation of silicon content in hot metal. To stabilize Blast Furnace operation, this article attempts to identify the optimum control centre of silicon content through exploring the operational data of Blast Furnace Ironmaking process. A quantitative analysis of the impact of thermal state on the smelting efficiency and intensity is presented by combining wavelet denoising and fuzzy c-means (FCM) clustering. Simulation results show that the commonly adopted mean value of historical data is not necessarily the optimum state of Blast Furnace operation. There exists some optimum state lower than the mean value, under which higher smelting efficiency and intensity can be achieved. It is also proved that the “low silica smelting practice” attempt in the steel industry is feasible and meaningful.

  • A refined prediction model of silicon content based on the Kalman Filter
    2010
    Co-Authors: Wei Pan, Jiusun Zeng, Xiang-guan Liu, Chuanhou Gao
    Abstract:

    Prediction of silicon content in hot metal is an important task in the control of Blast Furnace Ironmaking process. Due to the complexity of Blast Furnace Ironmaking process, most predictive models may work well under stable conditions, however, when the production is instable, the performance may deteriorate, which means loss of much valuable information contained in the variables. Actually, the residuals of the predictive model consist of two parts, i.e., unmodelled information and noise. In this paper, a TGARCH model (Threshold autoregressive conditional heteroskedasticity model) is used to predict silicon content in hot metal and the residuals are modeled by a Kalman Filter. The Kalman filter is used to separate the unmodeled information from noise and the captured information is then incorporated into the original model. The proposed method was tested on data collected from a medium-sized Blast Furnace. Simulation results shows that Kalman filter well improve the accuracy of TGARCH model.

  • Optimal operation strategy extraction for Blast Furnace Ironmaking process based on fuzzy C-means clustering
    2010 8th World Congress on Intelligent Control and Automation, 2010
    Co-Authors: Xihua Chen, Jiusun Zeng
    Abstract:

    Two key variables in Blast Furnace Ironmaking - silicon content in hot metal ([Si]) and hot metal temperature (FeW) are considered and used to represent the thermal state in hot metal, while hourly output of hot metal (Fe/H) is used to represent the efficiency of Ironmaking. The data is preprocessed by wavelet analysis to denoise and remove outliers. Fuzzy C-means clustering (FCM) is then used to identify the relation between efficiency of Ironmaking and smelting intensity by using the processed data. Simulation based on data collected from No.7 Blast Furnace of Handan Steel show that the mean value of historical data (0.45) is not the stable thermal state of Blast Furnace. The system is more stable and has higher smelting intensity when silicon content is around 0.41, which shows that “low silica smelting practice” attempt in the steel industry can lower the energy consumption while keeping the smelting intensity and smooth production. It is proved that appropriate level of silicon content will lead to safe, smooth production with lower energy consumption and higher production.

  • Data-driven predictive control for Blast Furnace Ironmaking process
    Computers & Chemical Engineering, 2010
    Co-Authors: Jiusun Zeng, Chuanhou Gao
    Abstract:

    Abstract High performance control of Blast Furnace (BF) Ironmaking process is a difficult problem due to the high temperature and hostile measurement conditions for measuring devices in the process. Previous research focused on developing of accurate predictive models for silicon content in hot metal ([SI]) while control of the whole process is seldom discussed. In the present work, a data-driven predictive control method based on subspace method is presented for the Blast Furnace Ironmaking process. The algorithm is based on input–output data and easy to implement. Simulation results show the algorithm is effective for the control application. Finally, various practical issues concerning predictive control of Blast Furnace Ironmaking process are also addressed, such as constraint handling, control objective and output set-point selection, adaptive strategy, etc.

Ping Zhou - One of the best experts on this subject based on the ideXlab platform.

  • Robust stochastic configuration network multi-output modeling of molten iron quality in Blast Furnace Ironmaking
    Neurocomputing, 2020
    Co-Authors: Jin Xie, Ping Zhou
    Abstract:

    Abstract Blast Furnace Ironmaking (BFI) is currently the most widely used method of pig iron smelting. In order to achieve efficient and reasonable control, how to quickly and accurately obtain the molten iron quality (MIQ) model is a key issue. Aiming at this problem, this paper applies robust stochastic configuration networks (RSCNs) based on kernel density estimation (KDE) into the BFI modeling to obtain the MIQ model with good modeling accuracy and strong robustness quickly and effectively. Firstly, the network model is incrementally constructed by adding neurons one by one using the conventional SCNs algorithm. Secondly, in order to solve the problem of insufficient robustness of conventional SCNs, kernel density estimation algorithm is introduced to obtain the corresponding probability density estimates of each training set, and it's used as the penalty weight introduced into constructing process of conventional SCNs. At the same time, the network output weight is obtained by an improved method to solve the problem that the output weight of the conventional RSCNs is abnormal in the multi-output modeling application. Finally, modeling experiments based on actual industrial data of BFI production verified that RSCNs can achieve good modeling accuracy and strong robust performance.

  • Modeling error PDF optimization based wavelet neural network modeling of dynamic system and its application in Blast Furnace Ironmaking
    Neurocomputing, 2018
    Co-Authors: Ping Zhou, Wang Chenyu, Hong Wang, Tianyou Chai
    Abstract:

    Abstract In general, the modeling errors of dynamic system model are a set of random variables. The traditional performance index of modeling such as means square error (MSE) and root means square error (RMSE) cannot fully express the connotation of modeling errors with stochastic characteristics both in the dimension of time domain and space domain. Therefore, the probability density function (PDF) is introduced to completely describe the modeling errors in both time scales and space scales. Based on it, a novel wavelet neural network (WNN) modeling method is proposed by minimizing the two-dimensional (2D) PDF shaping of modeling errors. First, the modeling error PDF by the traditional WNN is estimated using data-driven kernel density estimation (KDE) technique. Then, the quadratic sum of 2D deviation between the modeling error PDF and the target PDF is utilized as performance index to optimize the WNN model parameters by gradient descent method. Since the WNN has strong nonlinear approximation and adaptive capability, and all the parameters are well optimized by the proposed method, the developed WNN model can make the modeling error PDF track the target PDF, eventually. Simulation example and application in a Blast Furnace Ironmaking process show that the proposed method has a higher modeling precision and better generalization ability compared with the conventional WNN modeling based on MSE criteria. Furthermore, the proposed method has more desirable estimation for modeling error PDF that approximates to a Gaussian distribution whose shape is high and narrow.

  • Data-driven recursive subspace identification based online modelling for prediction and control of molten iron quality in Blast Furnace Ironmaking
    IET Control Theory & Applications, 2017
    Co-Authors: Ping Zhou, Dai Peng, Heda Song, Tianyou Chai
    Abstract:

    In Blast Furnace Ironmaking operation, the molten iron temperature and the silicon content ([Si]) are two key molten iron quality (MIQ) indices. The measurement, modelling and control of these indices have always been of importance in metallurgic engineering and automation. In this study, data-driven methods for online prediction and control of multivariate MIQ indices are proposed by integrating hybrid modelling and control techniques together. First, a data-driven hybrid method that combines canonical correlation analysis and correlation analysis is proposed to identify the most influential controllable variables as the modelling inputs from multitudinous factors. Then a data-driven online model for prediction of MIQ is established by recursive subspace identification (R-SI) with forgetting factor. Unlike the conventional SI modelling, the proposed R-SI-based online modelling only identifies subspace matrices for a data-driven input-output model without explicitly estimating the system matrices, which can reduce the computation complexity. Finally, a predictive controller is designed to maintain the MIQ indices at an expected level by using the developed MIQ prediction model as an online predictor. Since the parameters of the predictor are updated adaptively by the latest process data, the predictive controller can produce more reliable and stable control performance. Experiments using industrial data have verified the superiority and practicability of the proposed methods.

Tianyou Chai - One of the best experts on this subject based on the ideXlab platform.

  • Modeling error PDF optimization based wavelet neural network modeling of dynamic system and its application in Blast Furnace Ironmaking
    Neurocomputing, 2018
    Co-Authors: Ping Zhou, Wang Chenyu, Hong Wang, Tianyou Chai
    Abstract:

    Abstract In general, the modeling errors of dynamic system model are a set of random variables. The traditional performance index of modeling such as means square error (MSE) and root means square error (RMSE) cannot fully express the connotation of modeling errors with stochastic characteristics both in the dimension of time domain and space domain. Therefore, the probability density function (PDF) is introduced to completely describe the modeling errors in both time scales and space scales. Based on it, a novel wavelet neural network (WNN) modeling method is proposed by minimizing the two-dimensional (2D) PDF shaping of modeling errors. First, the modeling error PDF by the traditional WNN is estimated using data-driven kernel density estimation (KDE) technique. Then, the quadratic sum of 2D deviation between the modeling error PDF and the target PDF is utilized as performance index to optimize the WNN model parameters by gradient descent method. Since the WNN has strong nonlinear approximation and adaptive capability, and all the parameters are well optimized by the proposed method, the developed WNN model can make the modeling error PDF track the target PDF, eventually. Simulation example and application in a Blast Furnace Ironmaking process show that the proposed method has a higher modeling precision and better generalization ability compared with the conventional WNN modeling based on MSE criteria. Furthermore, the proposed method has more desirable estimation for modeling error PDF that approximates to a Gaussian distribution whose shape is high and narrow.

  • Data-driven recursive subspace identification based online modelling for prediction and control of molten iron quality in Blast Furnace Ironmaking
    IET Control Theory & Applications, 2017
    Co-Authors: Ping Zhou, Dai Peng, Heda Song, Tianyou Chai
    Abstract:

    In Blast Furnace Ironmaking operation, the molten iron temperature and the silicon content ([Si]) are two key molten iron quality (MIQ) indices. The measurement, modelling and control of these indices have always been of importance in metallurgic engineering and automation. In this study, data-driven methods for online prediction and control of multivariate MIQ indices are proposed by integrating hybrid modelling and control techniques together. First, a data-driven hybrid method that combines canonical correlation analysis and correlation analysis is proposed to identify the most influential controllable variables as the modelling inputs from multitudinous factors. Then a data-driven online model for prediction of MIQ is established by recursive subspace identification (R-SI) with forgetting factor. Unlike the conventional SI modelling, the proposed R-SI-based online modelling only identifies subspace matrices for a data-driven input-output model without explicitly estimating the system matrices, which can reduce the computation complexity. Finally, a predictive controller is designed to maintain the MIQ indices at an expected level by using the developed MIQ prediction model as an online predictor. Since the parameters of the predictor are updated adaptively by the latest process data, the predictive controller can produce more reliable and stable control performance. Experiments using industrial data have verified the superiority and practicability of the proposed methods.

Zuo Haibin - One of the best experts on this subject based on the ideXlab platform.

  • Energy-Saving,Emission-Reducing and Low Carbon Ironmaking,Realizing Scientific Development of BF Production in China
    China Metallurgy, 2010
    Co-Authors: Zuo Haibin
    Abstract:

    In this paper,an overview of Blast Furnace Ironmaking in China and technological progress in fields of energy-saving,high Blast temperature,large-scale equipment etc.are introduced.Subsequently,scientific development concept of Ironmaking technologies is deeply exposited.The contents include: strengthen adjustment of Ironmaking industrial structure,change development model and change concepts.On the base of high-grade burden,aiming at low-carbon Ironmaking,seek proper smelting intensity,rational oxygen-enrichment and PCI,increase Blast temperature and decrease coke rate.Improve gas distribution and energy utilization,lowering all types of energy consumption involving Blast and power etc.Decrease emission and strengthen innocuous treatment.Thus some new breakthrough in the aspects of low consumption,high efficiency,high quality,long campaign life and environment protection are achieved.Meanwhile,resolute measures should be taken to rectify the disorder in Ironmaking production and prohibit backward production capacity return or continue producing.To sum up,energy-saving,emission reduction and low-carbon Ironmaking are the central steps of realizing scientific development of Blast Furnace Ironmaking in China.

  • Scientific Development Strategy of Blast Furnace Ironmaking Technology in China
    Ironmaking & Steelmaking, 2008
    Co-Authors: Zuo Haibin
    Abstract:

    Saving energy and reducing consumption vigorously,developing circular economy,and main methods for promoting scientific development of Blast Furnace Ironmaking technology in China are discussed,including improving productivity of single Furnace,reducing fuel rate with high Blast temperature,high PCI rate and etc.,being environment friendly,beneficiation of burden and etc.