A Fuzzy Control Strategy of Burn-Through Point Based on the Feature Extraction of Time-Series Trend for Iron Ore Sintering Process

Du, Sheng; Wu, Min; Chen, Luefeng; Zhou, Kailong; Hu, Jie; Cao, Weihua; Pedrycz, Witold

doi:10.1109/tii.2019.2935030

Cited by 41 publications

(11 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similarly, in the basic automation part, a bunker‐level expert controller was developed to maintain normal operation, and a coordinating control algorithm was employed to coordinate the bunker‐level controller and BTP to get the desired sintering machine velocity. Motivated by the two‐level control method, Du et al [ 37 ] first extracted the global and local trend features of the time series, and then devised a fuzzy controller using the Mann–Kendall test method. Wang and Wu [ 38 ] presented a two‐level hierarchical ICS based on the soft‐sensor calculation of BTP and the vertical sintering speed.…”

Section: Review Of Data‐driven Methods In the Sintering Processmentioning

confidence: 99%

“…Li et al [30] Dynamic time feature expanding and extracting framework for FeO content prediction Liu et al [31] LSTM network for the chemical composition prediction Gao et al [32] Integrated model combining PCA with GA for tumble strength prediction Ye et al [33] TS model combined with a local thermal non-equilibrium (LTNE) model for tumble strength prediction Du et al [34] Fuzzy time series model for BTP prediction Yan et al [27] Denoising spatial-temporal encoder-decoder network for BTP prediction Chen et al [35] Hybrid just-in-time learning soft sensor (HJITL-SS) for CCR prediction Hu et al [36] Customized kernel-based Fuzzy C-Means (CKFCM) clustering method for CCR prediction Control Du et al [37] A fuzzy controller using the Mann-Kendal for BTP control Wang and Wu [38] A two-level hierarchical intelligent control system for BTP control Chen et al [39] Takagi-Sugeno (T-S) fuzzy model for BTP control Ying et al [40] Proportional-integral-derivative (PID) neural network for ignition temperature control Cao et al [41] An expert control system for ignition temperature control Optimization Zhou et al [42] Multi-objective and multi-time-scale optimization model for CCR Huang et al [43] A low-carbon and low-cost blending scheme for reducing the energy consumption Hu et al [44] An online optimization model for CCR Wu et al [45] An intelligent integrated optimization system (IIOS) for proportioning Wang et al [46] Cascade multi-objective optimization model (CMOM) for proportioning Abbreviations: BTP, burn-through point; CCR, comprehensive carbon ratio; GA, genetic algorithm; LSTM, long short-term memory; PCA, principal component analysis.…”

Section: Predictionmentioning

confidence: 99%

See 1 more Smart Citation

Data‐driven modelling methods in sintering process: Current research status and perspectives

et al. 2022

View full text Add to dashboard Cite

The sintering process, as a primary modus of the blast furnace ironmaking industry, has enormous economic value and environmental protection significance for the iron and steel enterprises. Recently, with the emergence of artificial intelligence and big data, data‐driven modelling methods in the sintering process have increasingly received the researchers' attention. But now, there is still no systematic review of the data‐driven modelling approaches in the sintering process. Therefore, in this article, we conduct a comprehensive overview and prospects on the data‐driven models for the purpose of intelligent sintering. First, the mechanism and characteristics of the sintering process are introduced and analyzed elaborately. Second, the detailed research status of the sintering process is illustrated from four aspects: key parameters prediction, control, optimization, and others. Finally, several challenges and promising modelling methods such as deep learning in the sintering process are outlined and discussed for future research.

show abstract

Section: Review Of Data‐driven Methods In the Sintering Processmentioning

confidence: 99%

Section: Predictionmentioning

confidence: 99%

Data‐driven modelling methods in sintering process: Current research status and perspectives

et al. 2022

View full text Add to dashboard Cite

show abstract

“…In [23], there are presented an optimization model of coke efficiency and a fuzzy controller of the sintering point. The main idea is to improve coke efficiency using an intelligent integrated sintering point control strategy.…”

Section: The Current State Of Synthesis Methods Of Control Systems Of...mentioning

confidence: 99%

Modeling of Phosphorus Production Processes and Developing a Management Structure Based on Grey Systems

Toktasynova¹,

Suleimenov²,

Kulakova³

2021

View full text Add to dashboard Cite

The agglomeration process is one of the complex, multidimensional technological processes; it takes place under conditions of a large number of disturbing influences. As a result, the amount of return during sintering reaches 40-50%. The work is devoted to the development of a mathematical model capable of predicting and controlling the sintering point based on real-time data. As the main parameters for the construction of predictive models, data measured in real time were used – the temperature in the vacuum chambers and the gas velocity determined through the measured pressure (rarefaction) in the vacuum chambers. This paper describes the methodology and basic algorithms for modeling agglomeration processes, starting from the ingress of the charge into the sinter machine and ending with the production of a suitable agglomerate. The obtained curves of the developed mathematical model of temperature in vacuum chambers served as the basis for testing the forecast model based on the use of the theory of gray systems and the optimization algorithm of the "swarm of particles". Based on the developed mathematical model, a system for predicting the sintering point is constructed, which is the basis for determining the quality of the agglomerate, which will reduce the return volume during sintering. The general structure of the sinter control system based on a dynamic predictive model is also proposed. The practical significance of the developed predictive model based on the theory of gray systems is as follows: - forecast of the sintering point value of the agglomerate and synthesis of the control action based on the forecast; - the algorithm for constructing a mathematical model of the forecast can be used for any process that has the character of a "gray exponential law".

show abstract

“…52,53 The Hurst exponent can measure the self-similarity of the time series. In addition, the predictability of time series can be evaluated by the Hurst exponent, which is expressed as H. 54 when H is 0.5, time series is random and unpredictable. Time series can described as nonpersistent when H ∈ [0,0.5).…”

Section: Hurst Exponent Analysis Of Componentsmentioning

confidence: 99%

Network traffic prediction method based on wavelet transform and multiple models fusion

Tian

2020

Int J Communication

View full text Add to dashboard Cite

Summary Accurate prediction of network traffic is an important premise in network management and congestion control. In order to improve the prediction accuracy of network traffic, a prediction method based on wavelet transform and multiple models fusion is presented. Mallat wavelet transform algorithm is used to decompose and reconstruct the network traffic time series. The approximate and detailed components of the original network traffic can be obtained. The characteristics of approximate components and detail components are analyzed by Hurst exponent. Then, according to the different characteristics of the components, autoregressive integrated moving average model (ARIMA) is chosen as the prediction model for the approximate component. Least squares support vector machine (LSSVM) is used to predict detail component. Meanwhile, an improved particle swarm optimization (PSO) algorithm is proposed to optimize the parameters of the LSSVM model. Gauss‐Markov estimation algorithm is adapted to fuse the predicted values of multiple prediction models. The variance of fusion prediction error is smaller than that of single prediction model, and the prediction accuracy is improved. Two actual datasets of network traffic are studied. Compared with other state‐of‐the‐art models, the case study results indicate that the proposed prediction method has a better prediction effect.

show abstract

A Fuzzy Control Strategy of Burn-Through Point Based on the Feature Extraction of Time-Series Trend for Iron Ore Sintering Process

Cited by 41 publications

References 41 publications

Data‐driven modelling methods in sintering process: Current research status and perspectives

Data‐driven modelling methods in sintering process: Current research status and perspectives

Modeling of Phosphorus Production Processes and Developing a Management Structure Based on Grey Systems

Network traffic prediction method based on wavelet transform and multiple models fusion

Contact Info

Product

Resources

About