Time series analysis and prediction on complex dynamical behavior observed in a blast furnace

Miyano, Takeshi; Kimoto, S; Shibuta, Hiroshi; Nakashima, Ken; Ikenaga, Yasuharu; Aihara, Kazuyuki

doi:10.1016/s0167-2789(99)00135-9

Cited by 43 publications

(36 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But there is the room of examination whether the detected time series clusters have stationarity condition. Once the data passes the stationarity test (Test(S)) [26,41], we can investigate details of non-linear dynamics behind each cut length by using the causal analysis [34,35]. …”

Section: Discussion and Future Researchmentioning

confidence: 99%

Detection of changes in non-linear dynamics for time series based on the theory of KM2O-Langevin equations

Hidaka

Okabe

2011

Japan J. Indust. Appl. Math.

View full text Add to dashboard Cite

This paper presents a framework for detecting changes in non-linear dynamics for time series based on the theory of KM 2 O-Langevin equations. This paper has two contributions one is to define the pseudo determinacy function that deduces the non-linear dynamics behind the subsequences of the time series data the other is to define the distance of dynamics between the subsequences by the pseudo determinacy function to understand how and when the non-linear dynamics changes. In contrast to the existing methods such as Singular-Spectrum Analysis and Recurrence Quantification Analysis the proposed method can distinguish the difference between a temporal outlier and a change in non-linear dynamics. Moreover, applying the proposed method to the real data, we found the indirect relation between the change in non-linear dynamics and some outer force (the actress in TV commercial or attack by competitors).

show abstract

Section: Discussion and Future Researchmentioning

confidence: 99%

Detection of changes in non-linear dynamics for time series based on the theory of KM2O-Langevin equations

Hidaka

Okabe

2011

Japan J. Indust. Appl. Math.

View full text Add to dashboard Cite

show abstract

“…To online predict the silicon content, various data-driven soft sensor modeling approaches, including various neural networks, [7][8][9][10][11][12][13][14] partial least squares, 14,15) fuzzy inference systems, 16) nonlinear time series analysis, [17][18][19][20] subspace identification, 21) support vector regression (SVR) and least squares SVR (LSSVR), [22][23][24] and others [25][26][27][28][29] have been investigated. A recent overview of black-box models for short-term silicon content prediction in blast furnaces can be referred to.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Chen

Liu

2017

ISIJ Int.

View full text Add to dashboard Cite

Development of accurate soft sensors for online quality prediction (e.g., silicon content) in an industrial blast furnace is a difficult task. A novel just-in-time-learning (JITL) prediction approach using adaptive feature-weighting for similar samples is developed. First, a dual-objective joint-optimization framework is proposed to introduce both input and output information into the model. Then, a suitable similarity criterion with feature weighting strategy is formulated, which is not considered in conventional JITL methods. Moreover, the trade-off parameter in the joint-optimization problem can be chosen automatically, without the time-consuming cross-validation procedure. The proposed method is applied to online predict the silicon content in an industrial blast furnace in China. Compared with other JITL-based soft sensors, better prediction performance has been obtained.

show abstract

“…Thus, data-driven modeling is being investigated quite intensively recently in an attempt to solve this intractable problem. In the process of data-driven modeling, the frequently used tools include neural net, [6][7][8][9][10][11] partial least squares, 12,13) fuzzy mathematics, 14) nonlinear time series analysis, 15,16) chaos, [17][18][19] etc. The main motivation is that, most of these tools have universal nonlinear approximation capabilities and can approach any function in any precision.…”

Section: Introductionmentioning

confidence: 99%

Application of Least Squares Support Vector Machines to Predict the Silicon Content in Blast Furnace Hot Metal

Jian

Gao

et al. 2008

ISIJ Int.

View full text Add to dashboard Cite

Time series analysis and prediction on complex dynamical behavior observed in a blast furnace

Cited by 43 publications

References 22 publications

Detection of changes in non-linear dynamics for time series based on the theory of KM2O-Langevin equations

Detection of changes in non-linear dynamics for time series based on the theory of KM2O-Langevin equations

Adaptive Weighting Just-in-Time-Learning Quality Prediction Model for an Industrial Blast Furnace

Application of Least Squares Support Vector Machines to Predict the Silicon Content in Blast Furnace Hot Metal

Contact Info

Product

Resources

About