Abstract:Real-time precise control of the BOF steelmaking end-point can effectively improve the quality of steel output. The flame spectra change obviously in different stages of steelmaking. It can be used to control the end-point of steelmaking effectively with the machine learning method. Due to a large amount of spectral data and the lack of reliability and real-time performance of the existing methods for spectral feature extraction, a characteristic spectral wavelength selection method based on window competitive adaptive reweighted sampling (WCARS) combined with iterative successive projection algorithm (ISPA) was proposed in this paper. This method can effectively solve the problem of over-fitting and reduce the complexity of high-dimensional data calculation. After dividing the spectral data along the wavelength direction in the window, CARS was used to select the feature window band. The iterative selection was combined with a traditional successive projection algorithm, and the characteristic wavelengths were selected through repeated iteration. On this basis, support vector machine regression (SVR) was used to establish the carbon content prediction model of steelmaking end-point. 363 sets of spectral data of the later stage of steelmaking were collected as an experimental sample and preprocessed by Savitzky-Golay smoothing. The input of the SVR model was 10 characteristic wavelength data selected by WCARS-ISPA, and the output was carbon content. The training set and test set were divided by the Kennard-Stone algorithm. The average prediction error of carbon content, the hit ratio of prediction error within ±2% and the average running time of 30 times were selected as the evaluation indexes. The results indicated that the average prediction error is 1.413 2%, the hit ratio is 90.63%, and the running time is 0.019 679 s. Compared with the model of full spectra and characteristic wavelengths selected by four different feature selection methods of WCARs-ISPA, CARS-SPA, WCARS and SPA, the WCARS-ISPA model has the lowest error and the highest hit ratio. In this paper, a new flame spectral characteristic wavelength extraction method was proposed. Window competitive adaptive reweighted sampling was combined with an iterative successive projection algorithm to select the wavelength, and a prediction model of end-point carbon content is established on this basis. The experimental results showed that this method could effectively extract the spectral characteristics of flame. This model can accurately predict the endpoint of BOF steelmaking and meet the requirements of real-time control of industrial production.
[1] FENG Shi-chao, WANG Yan-hong, DING Rui-feng(冯士超, 王艳红, 丁瑞锋). Metallurgical Industry Automation(冶金自动化), 2016, 237(2): 1.
[2] CHU Xiao-li, SHI Yun-ying, CHEN Pu, et al(褚小立, 史云颖, 陈 瀑,等). Journal of Instrumental Analysis(分析测试学报), 2019, 38(5): 603.
[3] ZHANG Cai-jun, HAN Yang, HE Shi-yu, et al(张彩军, 韩 阳, 何世宇, 等). Chinese Journal of Scientific Instrument(仪器仪表学报), 2018, 39(1): 24.
[4] Stadler A, Windisch T, Diepold K. Fire Safety Journal, 2014, 66(5): 1.
[5] Golgiyaz S, Talu M F, Onat C. Fuel, 2019, 255: 115827.
[6] Chang J C, Wang J C, Wang Z, et al. Complexity, 2018, https://doi.org/10.1155/2018/8682725.
[7] Yin Z J,Luo Q,Tang T T,et al. Advances in Engineering Research, 2016, 116: 341.
[8] Fan W, Shan Y, Li G Y, et al. Food Analytical Methods, 2012, 5(3): 585.
[9] Cheng L, Zhao T L, Li C, et al. Food Chemistry, 2017, 221(Apr. 15): 990.
[10] Shao Y L, Zhao Q, Chen Y R, et al. Optik, 2015, 126(23): 4539.
[11] LI Pao, ZHOU Jun, JIANG Li-wen, et al(李 跑, 周 骏, 蒋立文, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2019, 39(5): 1428.
[12] Tang R N, Chen X P, Li C. Applied Spectroscopy, 2018, 72(5): 740.
[13] Zhang F, O’Donnel Lauren J. Support Vector Regression. in: Machine Learning, Academic Press, 2020, 123.
[14] Tang B W, Zhu Z X, Shin H S, et al. Information Sciences, 2017, 420: 364.