Improvement in classification accuracy of stainless steel alloys by laser-induced breakdown spectroscopy based on elemental intensity ratio analysis

Laser-induced breakdown spectroscopy(LIBS) is a useful technique for accurate sorting of metal scrap by chemical composition analysis.In this work,a method for intensity-ratiobased LIBS classification of stainless steel applicable to highly fluctuating LIBS signal conditions is proposed.The spectral line pairs for intensity ratio calculation are selected according to elemental concentration and upper levels of emission lines.It is demonstrated that the classification accuracy can be significantly improved from that of full-spectra principal component analysis or intensity-based analysis.The proposed method is considered to be suited to an industrial scrap sorting system that requires minimal maintenance and low system price.     

Classification of steel based on laser-induced breakdown spectroscopy combined with restricted Boltzmann machine and support vector machine

In recent years, a laser-induced breakdown spectrometer (LIBS) combined with machine learning has been widely developed for steel classification. However, the much redundant information of LIBS spectra increases the computation complexity for classification. In this work, restricted Boltzmann machines (RBM) and principal component analysis (PCA) were used for dimension reduction of datasets, respectively. Then, a support vector machine (SVM) was adopted to process feature information. Two models (RBM-SVM and PCA-SVM) are compared in terms of performance. After optimization, the accuracy of the RBM-SVM model can achieve 100%, and the maximum dimension reduction time is 33.18 s, which is nearly half of that of the PCA model (53.19 s). These results preliminarily indicate that LIBS combined with RBM-SVM has great potential in the real-time classification of steel.     

A rapid classification method of aluminum alloy based on laser-induced breakdown spectroscopy and random forest algorithm

As an important non-ferrous metal structural material most used in industry and production,aluminum(Al) alloy shows its great value in the national economy and industrial manufacturing.How to classify Al alloy rapidly and accurately is a significant, popular and meaningful task.Classification methods based on laser-induced breakdown spectroscopy(LIBS) have been reported in recent years. Although LIBS is an advanced detection technology, it is necessary to combine it with some algorithm to reach the goal of rapid and accurate classification. As an important machine learning method, the random forest(RF) algorithm plays a great role in pattern recognition and material classification. This paper introduces a rapid classification method of Al alloy based on LIBS and the RF algorithm. The results show that the best accuracy that can be reached using this method to classify Al alloy samples is 98.59%, the average of which is 98.45%. It also reveals through the relationship laws that the accuracy varies with the number of trees in the RF and the size of the training sample set in the RF. According to the laws, researchers can find out the optimized parameters in the RF algorithm in order to achieve,as expected, a good result. These results prove that LIBS with the RF algorithm can exactly classify Al alloy effectively, precisely and rapidly with high accuracy, which obviously has significant practical value.     

Identification of heavy metal-contaminated Tegillarca granosa using laser-induced breakdown spectroscopy and linear regression for classification

Tegillarca granosa (T. granosa) is susceptible to heavy metals, which may pose a threat to consumer health. Thus, healthy and polluted T. granosa should be distinguished quickly. This study aimed to rapidly identify heavy metal pollution by using laser-induced breakdown spectroscopy (LIBS) coupled with linear regression classification (LRC). Five types of T. granosa were studied, namely, Cd-, Zn-, Pb-contaminated, mixed contaminated, and control samples. Threshold method was applied to extract the significant variables from LIBS spectra. Then, LRC was used to classify the different types of T. granosa. Other classification models and feature selection methods were used for comparison. LRC was the best model, achieving an accuracy of 90.67%. Results indicated that LIBS combined with LRC is effective and feasible for T. granosa heavy metal detection.     

奥氏体321不锈钢在550 ℃静态铅铋共晶合金中的腐蚀行为

奥氏体321不锈钢常用作核反应堆冷却剂主管道结构材料,铅铋共晶合金是第四代核能系统（Gen Ⅳ）铅冷快堆冷却剂的主要候选材料。为研究321不锈钢与高温液态铅铋共晶合金的相容性,对321不锈钢在550 ℃液态铅铋共晶合金中的200、400、600 h腐蚀现象进行了研究。对不同腐蚀时间后腐蚀试样的表面和截面分别进行了XRD和SEM、EDS检测。结果发现：在321不锈钢试样表面产生了一种随腐蚀时间增加先生长后脱落的含O、Ti、Pb元素的化合物（Ti₂O和Pb₂O₃）;在321不锈钢基体与铅铋共晶合金交界处会产生一层随腐蚀时间增加不断增厚的扩散层;321不锈钢在铅铋共晶合金中发生溶解腐蚀,在Fe、Cr元素不断向铅铋共晶合金中溶解时,伴随着Pb、Bi元素向基体中的渗透。     

氚污染不锈钢、铜、铝金属干法去污研究

为了考察氚污染金属干法去污的去污效率,对氚污染不锈钢、铜和铝进行了紫外线、臭氧、加热及联合（紫外线、臭氧与加热）去污实验研究。研究结果表明：紫外线单独照射去污效率较差,加热可明显提高去污效率,500 ℃联合172 nm的紫外线去污4 h对不锈钢表面氚去污率可达99.2%;臭氧对铜有较好的去污效率,臭氧与加热（500 ℃）的组合对不锈钢、铝、铜的去污率均高于99.2%;高温（500 ℃）较低温（300 ℃）去污效率高;氚去污后金属放置30 d表面氚有所增加,主要是氚的扩散和渗透所致;氚污染不锈钢存在4种氚吸附态。     

A strategy to significantly improve the classification accuracy of LIBS data:application for the determination of heavy metals in Tegillarca granosa

Tegillarca granosa, as a popular seafood among consumers, is easily susceptible to pollution from heavy metals. Thus, it is essential to develop a rapid detection method for Tegillarca granosa. For this issue, five categories of Tegillarca granosa samples consisting of a healthy group; Zn, Pb, and Cd polluted groups; and a mixed pollution group of all three metals were used to detect heavy metal pollution by combining laser-induced breakdown spectrometry(LIBS) and the newly proposed linear regression classification-sum of rank difference(LRC-SRD)algorithm. As the comparison models, least regression classification(LRC), support vector machine(SVM), and k-nearest neighbor(KNN) and linear discriminant analysis were also utilized. Satisfactory accuracy(0.93) was obtained by LRC-SRD model and which performs better than other models. This demonstrated that LIBS coupled with LRC-SRD is an efficient framework for Tegillarca granosa heavy metal detection and provides an alternative to replace traditional methods.     

几种钎料对钛合金/不锈钢钎焊接头的钎缝强度与界面的影响

采用4种成分的银基钎料制备了钛合金/不锈钢钎焊接头,用力学性能试验、金相试验、扫描电镜分析及电子探针分析方法,测量了钎缝强度,分析了断口形貌和钎缝界面组织.研究表明:不锈钢/Ag95CuNiLi/钛合金钎缝强度可达220 MPa,在不锈钢/Ag95CuNiLi扩散区形成了脆性相;不锈钢/Ag88Al10MnSi/钛合金钎缝强度为242 MPa,不锈钢/ Ag88Al10MnSi一侧的钎缝区易形成裂纹;不锈钢/Ag85Al8Sn/钛合金钎缝强度只有123 MPa;不锈钢/Ag85Al8SnNi/钛合金钎缝强度可达280 MPa,钎料与母材冶金结合较好.     

Impact of Material Configuration Behind First Wall on Helium Formation in In-Vessel Components of Fusion Reactor

The results of neutron transport calculations of the He formation based on the JENDL gas-production cross section file are discussed for some metals and alloys, namely ²⁷A1, Ti, ⁵¹V, Cr, ⁵⁵Mn, Fe, Ni, Zr, Mo, austenitic stainless steel (Ti modified 316 SS: PCA), Ni-base alloy (Inconel 625), ferritic steel (Fe-11Cr-1Mo: HT-9), Ti-base alloy (Ti-6A1-4V) and V-base alloy (V-5Cr-5Ti). Impacts of the two shields having the steel-rich and the H₂O-rich compositions and the two blankets having the Li₂O/Be-base and the liquid Li/Be-base compositions on the He formation rate in the above-mentioned metals and alloys are discussed. The relation between the He formation rate and the fast neutron flux (14.1 MeV>E>0.1 MeV) is investigated. The decrease of He formation at any distance Δ from the first wall more than Δ_as, the distance where the shape of neutron spectrum reaches its asymptotic form, is modelled by the simple formula based on the exponential dependence, as those reported so far for the fast neutron flux and the displacement damage rate.     

氚污染部件干法去污技术

针对核退役工程中存在的大量含氚废物处理问题,利用设计组装的干法去污处理装置对氚污染的金属进行了加热、紫外线、臭氧去污研究.结果表明,升高温度可明显提高去污效果;220 ℃用365 nm紫外线照射3 h对不锈钢的表面去污效率可达99%;臭氧与加热联合作用更有利于提高去污效率,220 ℃时去污3 h,臭氧对不锈钢、铝、黄铜的去污效率可达95%以上;而去污完毕经放置后,金属的氚表面活度会有所增加.     

Weighted-averaging-based classification of laser-induced breakdown spectroscopy measurements using most informative spectral lines

In this study, efficient spectral line selection and weighted-averaging-based processing schemes are proposed for the classification of laser-induced breakdown spectroscopy(LIBS) measurements. For fast on-line classification, a set of representative spectral lines are selected and processed relying on the information metric, instead of the time consuming full spectrum based analysis. The most informative spectral line sets are investigated by the joint mutual information estimation(MIE)evaluated with the Gaussian kernel density, where dominant intensity peaks associated with the concentrated components are not necessarily most valuable for classification. In order to further distinguish the characteristic patterns of the LIBS measured spectrum, two-dimensional spectral images are synthesized through column-wise concatenation of the peaks along with their neighbors.For fast classification while preserving the effect of distinctive peak patterns, column-wise Gaussian weighted averaging is applied to the synthesized images, yielding a favorable trade-off between classification performance and computational complexity. To explore the applicability of the proposed schemes, two applications of alloy classification and skin cancer detection are investigated with the multi-class and binary support vector machines classifiers, respectively. The MIE measures associated with selected spectral lines in both applications show a strong correlation to the actual classification or detection accuracy, which enables to find out meaningful combinations of spectral lines. In addition, the peak patterns of the selected lines and their Gaussian weighted averaging with neighbors of the selected peaks efficiently distinguish different classes of LIBS measured spectrum.     

钛合金/不锈钢钎焊接头的组织特征

采用金相显微镜，电子显微镜，X射线能谱仪、显微硬度、力学试验等检测手段，对TA17钛合金／Ag95CuNiLi／0Cr18Ni10Ti不锈钢钎焊接头的组织特征进行了分析、结果表明：钎缝中不锈钢／钎料一侧，形成了三层金属间化合物钎缝组织：在钛合金／钎料一侧，形成两个组织区域：同时，银沿钛合金晶间扩散；在凝固钎焊接头的钎缝中，靠近不锈钢一侧出现了Ti、Cu的富集；靠近钛合金一侧Cu原子的含量明显升高，钎缝中心区基本上是纯银；钎缝中除不锈钢／钎料扩散层外，其他各微区的显微硬度并没有增加；从钎缝断口分析也证明钎缝中靠近不锈钢一侧是接头最薄弱的位置。     

Quantitative analysis of steel and iron by laser-induced breakdown spectroscopy using GA-KELM

According to the multiple researches in the last couple of years, laser-induced breakdown spectroscopy(LIBS) has shown a great potential for rapid analysis in steel industry.Nevertheless, the accuracy and precision may be limited by complex matrix effect and selfabsorption effect of LIBS seriously. A novel multivariate calibration method based on genetic algorithm-kernel extreme learning machine(GA-KELM) is proposed for quantitative analysis of multiple elements(Si, Mn, Cr, Ni, V, Ti, Cu, Mo) in forty-seven certified steel and iron samples.First, the standardized peak intensities of selected spectra lines are used as the input of model.Then, the genetic algorithm is adopted to optimize the model parameters due to its obvious capability in finding the global optimum solution. Based on these two steps above, the kernel method is introduced to create kernel matrix which is used to replace the hidden layer's output matrix. Finally, the least square is applied to calculate the model's output weight. In order to verify the predictive capability of the GA-KELM model, the R-square factor(R~2), Root-meansquare Errors of Calibration(RMSEC), Root-mean-square Errors of Prediction(RMSEP) of GAKELM model are compared with the traditional PLS algorithm, respectively. The results confirm that GA-KELM can reduce the interference from matrix effect and self-absorption effect and is suitable for multi-elements calibration of LIBS.     

The classification of plants by laser-induced breakdown spectroscopy based on two chemometric methods

The applications of laser-induced breakdown spectroscopy(LIBS) on classifying complex natural organics are relatively limited and their accuracy still requires improvement.In this work,to study the methods on classification of complex organics,three kinds of fresh leaves were measured by LIBS.100 spectra from 100 samples of each kind of leaves were measured and then they were divided into a training set and a test set in a ratio of 7:3.Two algorithms of chemometric methods including the partial least squares discriminant analysis(PLS-DA) and principal component analysis Mahalanobis distance(PCA-MD) were used to identify these leaves.By using 23 lines from 16 elements or molecules as input data,these two methods can both classify these three kinds of leaves successfully.The classification accuracies of training sets are both up to 100% by PCA-MD and PLS-DA.The classification accuracies of the test set are 93.3% by PCA-MD and 97.8% by PLS-DA.It means that PLS-DA is better than PCA-MD in classifying plant leaves.Because the components in PLS-DA process are more suitable for classification than those in PCA-MD process.We think that this work can provide a reference for plant traceability using LIBS.     

A novel strategy for quantitative analysis of soil pH via laser-induced breakdown spectroscopy coupled with random forest

pH is one of the significant properties of soil,and is closely related to the decomposition of soil organic matter,anion-cation balance,growth of plants and many other soil processes.In the present work,laser-induced breakdown spectroscopy(LIBS) technique coupled with random forest(RF) was proposed to quantify the pH of soil.First,LIBS spectra of soil was collected,and some common elements in soil were identified based on the National Institute of Science and Technology database.Then,in order to obtain a better predictive result,the influence of different input variables(full spectrum,different spectral ranges,the intensity of characteristic bands and characteristic lines) on the predictive performance of RF calibration model was explored with the evaluation indicators of root mean square error(RMSE) and coefficient of determination(R2),the characteristic bands of four elements(AI,Ca,Mg and Si) were determined as the optimal input variables.Finally,the predictive performance of RF calibration model was compared with partial least squares calibration model with the optimal input variables and model parameters,and RF calibration model showed a better predictive performance,and the four evaluation indicators of R_p~2,RMSEP,mean absolute error and mean relative error were 0.9687,0.1285,0.1114 and 0.0136,respectively.It indicates that LIBS technique coupled with RF algorithm is an effective method for pH determination of soil.     

Fatigue strength of dissimilar welded joints for the main vessel of an LMFBR

The employment of welded joints composed of dissimilar metals is one simple and inexpensive way to connect a main vessel made of austenitic stainless steel and a roof slab constructed of ferritic steel in the design of liquid metal fast reactors. Since dissimilar-metal welded joints have not been used for such large structures so far in Japan, the structural integrity of this type of joint should be carefully examined for such a design option to be selected. Here various kinds of tests were conducted for eleven types of welded joints of 50 mm thickness to obtain this fundamental strength characteristics. Type 304 stainless steel was used as one of the parent metals in all the joints. They differ from each other in regard to the type of ferritic steel, welding metal and welding procedure. Low-cycle fatigue tests were conducted for round-bar specimens made from these welded joints at room temperature. Fatigue crack-propagation tests were also conducted for some of the joints. Tests after manufacturing a large-scale shell model were also conducted. The results of these tests demonstrated that the present manufacturing technique can, produce welded joints of high quality and reliability. A trial calculation for actual design conditions showed the existence of large margins against fatigue failure or fatigue crack-propagation of a significant amount.     

Segregation of alloying elements to free surfaces during irradiation

Recent transmission electron microscopy examinations of a number of face-centered-cubic and body-centered-cubic metals and alloys irradiated by heavy ions or by high-energy electrons have shown thatdynamic interactions of displacement damage with impurities and alloying elements lead to segregation and/or to the formation of second phases at internal surfaces such as voids. To date, the phenomenon has been observed in an experimental 18Cr8Ni1Si stainless steel, in commercial 316L stainless steel, in vanadium and in nickel. In the electron irradiated Fe18Cr8Ni1Si alloy, analysis of the segregation-induced strain field around the voids indicates that during irradiation minor substitutional alloying elements with negative and positive size factors segregate towards and away from the void surface respectively. Preliminary Auger spectroscopy analysis indicates that a similar segregation phenomenon occurs at the external irradiated surface in nickel-ion bombarded 18Cr8Ni1Si stainless steel. These results suggest that undersized substitutional elements may tend to preferentially interchange positions with oversized solutes in interstitial sites, and that transport by interstitials may dominate segregation to defect sinks.     

Hybrid classification of coal and biomass by laser-induced breakdown spectroscopy combined with K-means and SVM

Laser-induced breakdown spectroscopy(LIBS) is a new technology suitable for classification of various materials. This paper proposes a hybrid classification scheme for coal, municipal sludge and biomass by using LIBS combined with K-means and support vector machine(SVM)algorithm. In the study, 10 samples were classified in 3 groups without supervision by K-means clustering, then a further supervised classification of 6 kinds of biomass samples by SVM was carried out. The results show that the comprehensive accuracy of the hybrid classification model is over 98%. In comparison with the single SVM classification model, the hybrid classification model can save 58.92% of operation time while guaranteeing the accuracy. The results demonstrate that the hybrid classification model is able to make an efficient, fast and accurate classification of coal, municipal sludge and biomass, furthermore, it is precise for the detection of various kinds of biomass fuel.     

Polonium evaporation and adhesion experiments for the development of polonium filter in lead–bismuth cooled reactors

Fundamental experiments were performed to determine the adhesion characteristics of polonium to different metals and to develop a filter for polonium evaporated from neutron-irradiated LBE. The results of the first experiments suggested that adhesion characteristics are almost the same for stainless steel and nickel metal. The results of the preliminary experiments for a polonium filter suggested that stainless steel mesh with thin wires could effectively collect polonium evaporated from neutron-irradiated LBE. In the experiments, stainless steel wire mesh was used, but from the results of adhesion experiment, it is expected that the same effect can be obtained with wire mesh made of other kinds of metal.     

Research and Improvement of Pu Sample Property Measurement Based on Fast Neutron Multiplicity Counter

Fast neutron multiplicity counting (FNMC) analysis method can effectively measure the properties of samples. Based on the fourth-order FNMC analytical equations, a set of three-layer fast neutron multiplicity counters with six liquid scintillators per layer was constructed for Geant4 simulation, and the values of related parameters were determined. Metal Pu sample with 1 cm iron, aluminum, carbon, and stainless steel packaging material was externally simulated, and the sample satisfied the assumption by the equation adaptive analysis. The measurement parameters such as detection efficiency and multiplicity counting rate were simulated. When the mass of Pu sample is less than 500 g, the increase of sample solution mass deviation is less than 1.20% with carbon as packaging material, and the influence of iron material and stainless steel material is less. According to the measurement results, the self-multiplication factor was corrected for the sample without shell, and the third-order polynomial fitting equation was obtained and the goodness of fit is 0.933. The corrected solution mass deviation of sample with mass less than 1 kg is less than 6.00%. The results show that the medium-heavy metal with thickness of 1 cm has little effect on the measurement of Pu samples. The combination of the fast neutron multiplicity counter and the coefficient correction method can achieve more accurate measurement of the sample properties.