A hybrid model combining wavelet transform and recursive feature elimination for running state evaluation of heat-resistant steel using laser-induced breakdown spectroscopy.

Heat-resistant steel is widely used in various industries, and the running state is of great importance for equipment function and safety. In this work, laser-induced breakdown spectroscopy (LIBS) is applied to evaluate the running state of steel using indicators of micro and macro properties. The hybrid model based on wavelet threshold denoising (WTD) and K-fold-support vector machine-recursive feature elimination (K-SVM-RFE) is proposed to estimate the different indictors of various service conditions of steel. Fourteen T91 specimens, including 4 industrial specimens obtained from different service conditions in the power plant boiler, were used as the analytes. Firstly, the noise signal of the LIBS spectra of each specimen was analyzed and removed with WTD. Secondly, an improved approach K-SVM-RFE was applied to select the optimal feature subset and build the classification models of aging grade and hardness grade. The influence of denoising pretreatment on model performance was compared and discussed. Finally, the assessment matrix, established using the indicators from the aging grade and hardness grade, was used to evaluate the running state of steel. The results show that the test assessment matrix obtained with the hybrid model based on WTD and K-SVM-RFE is consistent with the reference matrix on the running state of steel.

[1]  Zhanxia Zhang,et al.  Application of wavelet transform to background correction in inductively coupled plasma atomic emission spectrometry , 2003 .

[2]  Haibin Yu,et al.  Applications of laser-induced breakdown spectroscopy in the aluminum electrolysis industry , 2018 .

[3]  Walter Bendick,et al.  New low alloy heat resistant ferritic steels T/P23 and T/P24 for power plant application , 2007 .

[4]  Walid Tawfik Y. Mohamed.  Improved LIBS limit of detection of Be, Mg, Si, Mn, Fe and Cu in aluminum alloy samples using a portable Echelle spectrometer with ICCD camera , 2008 .

[5]  C. Paranhos,et al.  Identification and classification of polymer e-waste using laser-induced breakdown spectroscopy (LIBS) and chemometric tools , 2017 .

[6]  Wenbing Li,et al.  Estimation of the mechanical properties of steel via LIBS combined with canonical correlation analysis (CCA) and support vector regression (SVR) , 2018 .

[7]  Debahuti Mishra,et al.  SVM-BT-RFE: An improved gene selection framework using Bayesian T-test embedded in support vector machine (recursive feature elimination) algorithm , 2015 .

[8]  H. Zeng,et al.  Comparative study of the matrix effect in Cl analysis with laser-induced breakdown spectroscopy in a pellet or in a dried solution layer on a metallic target , 2016 .

[9]  Wenbing Li,et al.  Estimation of the aging grade of T91 steel by laser-induced breakdown spectroscopy coupled with support vector machines , 2018 .

[10]  Chunhua Wang,et al.  A highly accurate protein structural class prediction approach using auto cross covariance transformation and recursive feature elimination , 2015, Comput. Biol. Chem..

[11]  Ying Xue,et al.  In silico prediction of spleen tyrosine kinase inhibitors using machine learning approaches and an optimized molecular descriptor subset generated by recursive feature elimination method , 2013, Comput. Biol. Medicine.

[12]  Yongfeng Lu,et al.  Evaluation of sample preparation methods for rice geographic origin classification using laser-induced breakdown spectroscopy , 2018 .

[13]  Å. Rinnan,et al.  The potential of laser-induced breakdown spectroscopy for industrial at-line monitoring of calcium content in comminuted poultry meat , 2016 .

[14]  Yong He,et al.  Challenging applications for multi-element analysis by laser-induced breakdown spectroscopy in agriculture: A review , 2016 .

[15]  Nelmarie Louw,et al.  Variable selection in kernel Fisher discriminant analysis by means of recursive feature elimination , 2006, Comput. Stat. Data Anal..

[16]  Yixiang Duan,et al.  Progress of Chemometrics in Laser-induced Breakdown Spectroscopy Analysis , 2015 .

[17]  W. Ni,et al.  A partial least squares and wavelet-transform hybrid model to analyze carbon content in coal using laser-induced breakdown spectroscopy. , 2014, Analytica chimica acta.

[18]  K. Sawada,et al.  Z-phase Formation during Creep and Aging in 9–12% Cr Heat Resistant Steels , 2006 .

[19]  N. Senesi,et al.  Laser-induced breakdown spectroscopy (LIBS) to measure quantitatively soil carbon with emphasis on soil organic carbon. A review. , 2016, Analytica chimica acta.

[20]  David Zhang,et al.  Feature selection and analysis on correlated gas sensor data with recursive feature elimination , 2015 .

[21]  Satoru Miura,et al.  Measurement of Concrete Strength Using the Emission Intensity Ratio between Ca(II) 396.8 nm and Ca(I) 422.6 nm in a Nd:YAG Laser-Induced Plasma , 2006, Applied spectroscopy.

[22]  Soon-Hyo Chung,et al.  Microstructure and creep rupture characteristics of an ultra-low carbon ferritic/martensitic heat-resistant steel , 2007 .

[23]  Kihong Park,et al.  Elemental composition of Arctic soils and aerosols in Ny-Ålesund measured using laser-induced breakdown spectroscopy , 2017 .

[24]  Yongfeng Lu,et al.  Detection of Trace Elements in Active Luminescent Glass Using Laser-induced Breakdown Spectroscopy Combined with Laser-induced Fluorescence , 2016 .

[25]  Z. Hu,et al.  Structure degradation of 25Cr35Ni heat-resistant tube associated with surface coking and internal carburization , 1998 .

[26]  Elisabetta Tognoni,et al.  Estimation of calcified tissues hardness via calcium and magnesium ionic to atomic line intensity ratio in laser induced breakdown spectra , 2007 .

[27]  J. Heitz,et al.  Laser-induced optical breakdown spectroscopy of polymer materials based on evaluation of molecular emission bands. , 2017, Spectrochimica acta. Part A, Molecular and biomolecular spectroscopy.

[28]  Y. Hassebo,et al.  Design and construction of Q-switched Nd:YAG laser system for LIBS measurements , 2012 .

[29]  Jun Li,et al.  Correlation between aging grade of T91 steel and spectral characteristics of the laser-induced plasma , 2015 .

[30]  Haibin Yu,et al.  A method for improving wavelet threshold denoising in laser-induced breakdown spectroscopy , 2015 .

[31]  S. H. Kilcoyne,et al.  Hardness determination of bio-ceramics using laser-induced breakdown spectroscopy , 2011 .

[32]  Pablo M. Granitto,et al.  Improved multiclass feature selection via list combination , 2017, Expert Syst. Appl..

[33]  Elisabetta Tognoni,et al.  [INVITED] Signal and noise in Laser Induced Breakdown Spectroscopy: An introductory review ☆ , 2016 .

[34]  Lujia Han,et al.  A novel denoising method for laser-induced breakdown spectroscopy: Improved wavelet dual threshold function method and its application to quantitative modeling of Cu and Zn in Chinese animal manure composts , 2017 .

[35]  Pierre Dupont,et al.  Kernel methods for heterogeneous feature selection , 2015, Neurocomputing.

[36]  Anongnart Srivihok,et al.  Wrapper Feature Subset Selection for Dimension Reduction Based on Ensemble Learning Algorithm , 2015 .

[37]  J. Moros,et al.  Adaptive approach for variable noise suppression on laser-induced breakdown spectroscopy responses using stationary wavelet transform. , 2012, Analytica chimica acta.

[38]  Reinhard Noll,et al.  Investigation of matrix effects in laser-induced breakdown spectroscopy plasmas of high-alloy steel for matrix and minor elements ☆ , 2005 .

[39]  Naomie Salim,et al.  Feature unionization: A novel approach for dimension reduction , 2017, Appl. Soft Comput..

[40]  Zijiang Yang,et al.  Feature selection for high-dimensional multi-category data using PLS-based local recursive feature elimination , 2014, Expert Syst. Appl..

[41]  Jia-jia Jiang,et al.  Automatic variable selection method and a comparison for quantitative analysis in laser-induced breakdown spectroscopy , 2018 .

[42]  Fabienne Boué-Bigne,et al.  Laser-induced breakdown spectroscopy applications in the steel industry: Rapid analysis of segregation and decarburization , 2008 .

[43]  E. Pereira-Filho,et al.  Calibration strategies for the direct determination of Ca, K, and Mg in commercial samples of powdered milk and solid dietary supplements using laser-induced breakdown spectroscopy (LIBS). , 2017, Food research international.

[44]  Fujimitsu Masuyama,et al.  History of Power Plants and Progress in Heat Resistant Steels , 2001 .

[45]  Lionel Canioni,et al.  Good practices in LIBS analysis: Review and advices , 2014 .

[46]  K. Sridharan,et al.  Corrosion behavior of ferritic–martensitic steel T91 in supercritical water , 2006 .

[47]  T. Kannengiesser,et al.  In situ laser-induced breakdown spectroscopy measurements of chemical compositions in stainless steels during tungsten inert gas welding ☆ , 2018 .

[48]  X. Shao,et al.  A background and noise elimination method for quantitative calibration of near infrared spectra , 2004 .

[49]  J.-B. Sirven,et al.  Evaluation and optimization of the robustness of a multivariate analysis methodology for identification of alloys by laser induced breakdown spectroscopy , 2016 .

[50]  Qinmei Shen,et al.  Signal enhancement of lead and arsenic in soil using laser ablation combined with fast electric discharge , 2010 .

[51]  Md. Musfiqur Rahman,et al.  Method development, matrix effect, and risk assessment of 49 multiclass pesticides in kiwifruit using liquid chromatography coupled to tandem mass spectrometry. , 2018, Journal of chromatography. B, Analytical technologies in the biomedical and life sciences.