Silicon content prediction of hot metal in blast furnace based on attention mechanism and CNN-IndRNN model

The stability of blast furnace temperature is an important condition to ensure the efficient production of hot metal. Accurate prediction of silicon content in hot metal is of great significance to the control of blast furnace temperature in iron and steel plants. At present, the accuracy of most silicon prediction models can only be guaranteed when the furnace condition is stable. However, due to many factors affecting the silicon content in hot metal of blast furnace, and there are large noises, large delays and large fluctuations in the data, the previous prediction results are of limited guiding significance to the actual production. In this paper, combined with the actual situation, the convolution neural network is used to extract the furnace condition characteristics, and then combined with the attention mechanism and the IndRNN model to get the prediction results, so that the prediction can better adapt to the fluctuating data set. The experimental results show that the prediction error of this model is lower than that of other models, which provides a new solution for the research of silicon content in hot metal of blast furnace.

Download Full-text

MULTISCALE AND FRACTAL ANALYSIS OF SILICON CONTENT TIME SERIES OBSERVED IN BLAST FURNACE HOT METAL USING HURST EXPONENT CHAIN

Fractals ◽

10.1142/s0218348x1550036x ◽

2015 ◽

Vol 23 (04) ◽

pp. 1550036 ◽

Cited By ~ 1

Author(s):

SHIHUA LUO ◽

FAN GUO ◽

DEJIAN LAI ◽

FANG YAN ◽

FEILAI TANG

Keyword(s):

Time Series ◽

Blast Furnace ◽

Negative Correlation ◽

Hurst Exponent ◽

Silicon Content ◽

Coarse Grained ◽

Fluctuation Analysis ◽

Hot Metal ◽

Iron And Steel ◽

Generalized Hurst Exponent

Hurst exponent is an important measure of nonlinearity of dynamical time series. In this paper, using rescaled-range ([Formula: see text]/[Formula: see text]) analysis, multi-fractal detrended fluctuation analysis (MF-DFA) methods, the multiscale Hurst exponent (MHE) and the multiscale generalized Hurst exponent (MGHE) of coarse-grained silicon content ([Si]) time series in blast furnace (BF) hot metal were calculated. First, we collected these [Si] time series from No. 1 BF of Nanchang Iron and Steel Co. and No. 10 BF of Xinyu Iron and Steel Co. in Jiangxi Province, China. Then, we analyzed and compared the estimated Hurst exponents and the generalized Hurst exponent of these observed time series with some simulated time series. Our results show that the observed time series from these BFs have negative correlation with the Hurst exponent less than 0.5, the generalized Hurst exponent [Formula: see text] is a nonlinear function of [Formula: see text], and such negative correlation and local various structure persist in their moving averages of the observed time series up to lag 5 or 10.

Download Full-text

Prediction Model of Hot Metal Silicon Content Based on Improved GA-BPNN

Computational Intelligence and Neuroscience ◽

10.1155/2021/1767308 ◽

2021 ◽

Vol 2021 ◽

pp. 1-10

Author(s):

Zeqian Cui ◽

Yang Han ◽

Chaomeng Lu ◽

Yafeng Wu ◽

Mansheng Chu

Keyword(s):

Neural Network ◽

Blast Furnace ◽

Time Delay ◽

Network Model ◽

Neural Network Model ◽

Silicon Content ◽

Large Time ◽

Hot Metal ◽

Multiple Control ◽

Data Set

The inconsistency of the detection period of blast furnace data and the large time delay of key parameters make the prediction of the hot metal silicon content face huge challenges. Aiming at the problem that the hot metal silicon content is not consistent with the detection period of time series of multiple control parameters, the cubic spline interpolation fitting model was used to realize the data integration of multiple detection periods. The large time delay of the blast furnace iron making process was analyzed. Moreover, Spearman analysis was combined with the weighted moving average method to optimize the data set of silicon content prediction. Aiming at the problem of low prediction accuracy of the ordinary neural network model, genetic algorithm was used to optimize parameters on the BP neural network model to improve the convergence speed of the model to achieve global optimization. Combined with the autocorrelation analysis of the hot metal silicon content, a modified model for the prediction of hot metal silicon content based on error analysis was proposed to further improve the accuracy of the prediction. The model comprehensively considers problems such as data detection inconsistency, large time delay, and inaccuracy of prediction results. Its average absolute error is 0.05009, which can be used in actual production.

Download Full-text