scholarly journals Research and Application of a Rolling Gap Prediction Model in Continuous Casting

Metals ◽  
2019 ◽  
Vol 9 (3) ◽  
pp. 380 ◽  
Author(s):  
Zhufeng Lei ◽  
Wenbin Su
Keyword(s):  
Continuous Casting ◽  
Process Parameters ◽  
Principal Component ◽  
Casting Process ◽  
Support Vector ◽  
New Approach ◽  
Value Prediction ◽  
Svm Model ◽  
Roll Gap

Control of the roll gap of the caster segment is one of the key parameters for ensuring the quality of a slab in continuous casting. In order to improve the precision and timeliness of the roll gap value control, we proposed a rolling gap value prediction (RGVP) method based on the continuous casting process parameters. The process parameters collected from the continuous casting production site were first dimension-reduced using principal component analysis (PCA); 15 process parameters were chosen for reduction. Second, a support vector machine (SVM) model using particle swarm optimization (PSO) was proposed to optimize the parameters and perform roll gap prediction. The experimental results and practical application of the models has indicated that the method proposed in this paper provides a new approach for the prediction of roll gap value.

The Spinning Quality Control Management Based on Decision Making by Data Mining Techniques

2018 ◽  
Vol 7 (1) ◽  
pp. 72
Author(s):  
Khalid AA Abakar ◽  
Chongwen Yu
Keyword(s):  
Data Mining ◽  
Kernel Functions ◽  
Support Vector ◽  
Ann Model ◽  
Data Mining Techniques ◽  
Yarn Quality ◽  
Yarn Properties ◽  
Svm Model ◽  
Rbf Kernel

This work demonstrated the possibility of using the data mining techniques such as artificial neural networks (ANN) and support vector machine (SVM) based model to predict the quality of the spinning yarn parameters. Three different kernel functions were used as SVM kernel functions which are Polynomial and Radial Basis Function (RBF) and Pearson VII Function-based Universal Kernel (PUK) and ANN model were used as data mining techniques to predict yarn properties. In this paper, it was found that the SVM model based on Person VII kernel function (PUK) have the same performance in prediction of spinning yarn quality in comparison with SVM based RBF kernel. The comparison with the ANN model showed that the two SVM models give a better prediction performance than an ANN model.

scholarly journals A Methodology Based on FT-IR Data Combined with Random Forest Model to Generate Spectralprints for the Characterization of High-Quality Vinegars

Foods ◽  
2021 ◽  
Vol 10 (6) ◽  
pp. 1411
Author(s):  
José Luis P. Calle ◽  
Marta Ferreiro-González ◽  
Ana Ruiz-Rodríguez ◽  
Gerardo F. Barbero ◽  
José Á. Álvarez ◽  
...  
Keyword(s):  
Random Forest ◽  
Raw Materials ◽  
Principal Component ◽  
Hierarchical Cluster ◽  
Raw Material ◽  
Support Vector ◽  
Protected Designation Of Origin ◽  
Ft Ir

Sherry wine vinegar is a Spanish gourmet product under Protected Designation of Origin (PDO). Before a vinegar can be labeled as Sherry vinegar, the product must meet certain requirements as established by its PDO, which, in this case, means that it has been produced following the traditional solera and criadera ageing system. The quality of the vinegar is determined by many factors such as the raw material, the acetification process or the aging system. For this reason, mainly producers, but also consumers, would benefit from the employment of effective analytical tools that allow precisely determining the origin and quality of vinegar. In the present study, a total of 48 Sherry vinegar samples manufactured from three different starting wines (Palomino Fino, Moscatel, and Pedro Ximénez wine) were analyzed by Fourier-transform infrared (FT-IR) spectroscopy. The spectroscopic data were combined with unsupervised exploratory techniques such as hierarchical cluster analysis (HCA) and principal component analysis (PCA), as well as other nonparametric supervised techniques, namely, support vector machine (SVM) and random forest (RF), for the characterization of the samples. The HCA and PCA results present a clear grouping trend of the vinegar samples according to their raw materials. SVM in combination with leave-one-out cross-validation (LOOCV) successfully classified 100% of the samples, according to the type of wine used for their production. The RF method allowed selecting the most important variables to develop the characteristic fingerprint (“spectralprint”) of the vinegar samples according to their starting wine. Furthermore, the RF model reached 100% accuracy for both LOOCV and out-of-bag (OOB) sets.

scholarly journals Cancer Discrimination Using Fourier Transform Near-Infrared Spectroscopy with Chemometric Models

2015 ◽  
Vol 2015 ◽  
pp. 1-8 ◽  
Author(s):  
Hui Chen ◽  
Zan Lin ◽  
Chao Tan
Keyword(s):  
Cancer Diagnosis ◽  
Near Infrared ◽  
Nir Spectroscopy ◽  
Principal Component ◽  
Classification Model ◽  
Support Vector ◽  
Biomedical Analysis ◽  
First Derivative ◽  
Svm Model ◽  
High Prediction

Near-infrared (NIR) spectroscopy technique offers many potential advantages as tool for biomedical analysis since it enables the subtle biochemical signatures related to pathology to be detected and extracted. In conjunction with advanced chemometrics, NIR spectroscopy opens the possibility of their use in cancer diagnosis. The study focuses on the application of near-infrared (NIR) spectroscopy and classification models for discriminating colorectal cancer. A total of 107 surgical specimens and a corresponding NIR diffuse reflection spectral dataset were prepared. Three preprocessing methods were attempted and least-squares support vector machine (LS-SVM) was used to build a classification model. The hybrid preprocessing of first derivative and principal component analysis (PCA) resulted in the best LS-SVM model with the sensitivity and specificity of 0.96 and 0.96 for the training and 0.94 and 0.96 for test sets, respectively. The similarity performance on both subsets indicated that overfitting did not occur, assuring the robustness and reliability of the developed LS-SVM model. The area of receiver operating characteristic (ROC) curve was 0.99, demonstrating once again the high prediction power of the model. The result confirms the applicability of the combination of NIR spectroscopy, LS-SVM, PCA, and first derivative preprocessing for cancer diagnosis.

Development of Electromagnetic Swirling Flow in Immersion Nozzle in Continuous Casting Process of Steel

2011 ◽  
Vol 295-297 ◽  
pp. 1284-1288 ◽  
Author(s):  
De Wei Li ◽  
Zhi Jian Su ◽  
Li Wei Sun ◽  
Katsukiyo Marukawa ◽  
Ji Cheng He
Keyword(s):  
Continuous Casting ◽  
Swirling Flow ◽  
Casting Process ◽  
Continuous Casting Process ◽  
New Process ◽  
Electromagnetic Generator ◽  
Set Up ◽  
The Magnetic Field ◽  
Immersion Nozzle

Swirling flow in an immersion nozzle is effective on improving quality of casting block and casting speed in continuous casting process of steel. However, a refractory swirl blade installed in the nozzle is liable to cause clogging, which limit the application of the process. In this study a new process is proposed, that is a rotating electromagnetic field is set up around an immersion nozzle to induce a swirling flow in it by Lorentz force. New types of swirling flow electromagnetic generator are proposed and the effects of the structure of the generator, the coil current intensity and frequency on the magnetic field and on the flow field in the immersion nozzle are numerically analyzed.

Optimization of CC Tail Bloom Operation

2012 ◽  
Vol 602-604 ◽  
pp. 478-481
Author(s):  
Hong Pan
Keyword(s):  
Continuous Casting ◽  
Casting Process ◽  
Continuous Casting Process

Cut-to-length bloom can not be controlled at the end of continuous casting process, and the yield of bloom is low. In order to improve the yield of bloom, the CC tail bloom system is proposed according to the bloom continuous casting conditions of equipment and process. Importantly, it is applied in the optimization of tail bloom operation in continuous casting process. Industrial tests show that the yield of bloom is improved obviously, with the quality of bloom is controlled as before.

scholarly journals Mold Level Predict of Continuous Casting Using Hybrid EMD-SVR-GA Algorithm

Processes ◽  
2019 ◽  
Vol 7 (3) ◽  
pp. 177 ◽  
Author(s):  
Zhufeng Lei ◽  
Wenbin Su
Keyword(s):  
Continuous Casting ◽  
Production Control ◽  
Moving Average ◽  
Time Series Prediction ◽  
Casting Process ◽  
Support Vector ◽  
Intrinsic Mode Functions ◽  
Autoregressive Moving Average Model ◽  
Mode Decomposition ◽  
Moving Average Model

The prediction of mold level is a basic and key problem of continuous casting production control. Many current techniques fail to predict the mold level because of mold level is non-linear, non-stationary and does not have a normal distribution. A hybrid model, based on empirical mode decomposition (EMD) and support vector regression (SVR), is proposed to solve the mold level in this paper. Firstly, the EMD algorithm, with adaptive decomposition, is used to decompose the original mold level signal to many intrinsic mode functions (IMFs). Then, the SVR model optimized by genetic algorithm (GA) is used to predict the IMFs and residual sequences. Finally, the equalization of the predict results is reconstructed to obtain the predict result. Several hybrid predicting methods such as EMD and autoregressive moving average model (ARMA), EMD and SVR, wavelet transform (WT) and ARMA, WT and SVR are discussed and compared in this paper. These methods are applied to mold level prediction, the experimental results show that the proposed hybrid method based on EMD and SVR is a powerful tool for solving complex time series prediction. In view of the excellent generalization ability of the EMD, it is believed that the hybrid algorithm of EMD and SVR is the best model for mold level predict among the six methods, providing a new idea for guiding continuous casting process improvement.

scholarly journals Acquiring High-Quality Oil Casing Steel 26CrMoVTiB under Optimal Continuous Casting Process Conditions

Metals ◽  
2019 ◽  
Vol 9 (9) ◽  
pp. 993
Author(s):  
Yingying Zhai ◽  
Kefeng Pan ◽  
Dapeng Wu
Keyword(s):  
Continuous Casting ◽  
Water Flow ◽  
Process Parameters ◽  
Casting Speed ◽  
Casting Process ◽  
Solidification Structure ◽  
Process Conditions ◽  
Equiaxed Crystal ◽  
Continuous Casting Process ◽  
Simulation Results

While the solidification macrostructure of continuous cast billets is an important factor influencing the final performance and rolling yield of oil casing steel, the continuous casting process parameters have a direct influence on the solidification structure. This study simulated the solidification process of the continuous casting round billets of oil casing steel using a cellular automaton–finite element (CAFE) model. According to the simulation results, at a superheat degree of 20–35 K, a casting speed of 1.9–2.1 m/min, and a secondary cooling specific water flow of 0.34–0.45 L/Kg, the solidification structure had a relatively high equiaxed crystal ratio and small average grain radius. Guided by the simulation results, this paper establishes optimal process schemes for producing 26CrMoVTiB steel round billets, comparatively analyzes the equiaxed crystal ratio and central shrinkage of round billets produced according to these schemes, and defines the optimal continuous casting process conditions, which are: superheat degree = 25 K, casting speed = 2.1 m/min, and specific water flow = 0.35 L/Kg. When adopting these process parameters, the 26CrMoVTiB steel round billets demonstrate a tiny central shrinkage and an equiaxed crystal ratio of 45.2%.

A framework of characteristics identification and source apportionment of water pollution in a river: a case study in the Jinjiang River, China

2012 ◽  
Vol 65 (11) ◽  
pp. 2071-2078 ◽  
Author(s):  
Haiyang Chen ◽  
Yanguo Teng ◽  
Jinsheng Wang
Keyword(s):  
Water Pollution ◽  
Water Quality ◽  
Source Apportionment ◽  
Comprehensive Evaluation ◽  
Principal Component ◽  
Anthropogenic Pollution ◽  
Ammonia Nitrogen ◽  
Support Vector ◽  
Jinjiang River

A framework for characteristics identification and source apportionment of water pollution in the Jinjiang River of China was proposed in this study for evaluation. A total of 114 water samples which were generated between May 2009 and September 2010 at 13 sites were collected and analysed. First, support vector machine (SVM) and water quality pollutant index (WQPI) were used for water quality comprehensive evaluation and identifying characteristic contaminants. Later, factor analysis with nonnegative constraints (FA-NNC) was employed for source apportionment. Finally, multi-linear regression of the absolute principal component score (APCS/MLR) was applied to further estimate source contributions for each characteristic contaminant. The results indicated that the water quality of the Jinjiang River was mainly at the third level (65.79%) based on national surface water quality permissible standards in China. Ammonia nitrogen, total phosphorus, mercury, iron and manganese were identified as characteristic contaminants. Source apportionment results showed that industrial activities (63.16%), agricultural non-point source (16.50%) and domestic sewage (12.85%) were the main anthropogenic pollution sources which were influencing the water quality of Jinjiang River. This proposed method provided a helpful framework for conducting water pollution management in aquatic environment.

Sign in / Sign up

Export Citation Format

Share Document