A method for identifying carbon steel based on its emission spectrum using a steel plate cutting laser

Abstract

To provide a determination method of a carbon steel that can reliably identify a type of carbon steel before processing by a simple determination method without using a high-spec laser light source or a spectroscope in the LIBS method and can measure an element ratio specific to carbon steel.SOLUTION: A discrimination method of carbon steel in LIBS measurement of carbon steel using a near-infrared multimode fiber laser light source to control the laser pulse width and oscillation signal with a pulse controller, includes: using a cutting laser head to perform elemental analysis of carbon steel in a wavelength range of 200 nm to 600 nm; and using spectral peaks of iron, chromium and manganese to determine the type of carbon steel from the relative ratio of the peak heights.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to a method for determining carbon steel based on the emission spectrum of carbon steel using a steel plate cutting laser, and in particular to a method for determining carbon steel based on emission spectrum analysis using a small spectrometer and AI data processing. [Background technology]

[0002] Laser cutting equipment is a tool used to cut carbon steel. While lasers were previously only capable of cutting carbon steel plates approximately 20 mm thick, the recent increase in the power output of multimode fiber lasers has led to the emergence of laser cutting machines capable of cutting carbon steel plates 50 mm or thicker. However, if the processing conditions for the target steel plate are incorrectly selected and the wrong type of carbon steel is processed, the suboptimal processing conditions can not only result in a decrease in processing quality, but can also cause excessive spatter, potentially damaging parts of the processing equipment, including the laser head. Effective preventative measures include identifying the type of carbon steel and measuring the elemental ratios before processing.

[0003] For this reason, laser-induced breakdown spectroscopy (LIBS), an analytical method that involves irradiating the surface of the sample to be analyzed with high-energy pulsed laser light, turning the sample's atoms and ions into plasma, and then spectroscopically measuring the element-specific light emitted when the sample's atoms return from an excited state to their ground state, is attracting attention.

[0004] The mainstream laser light source for LIBS is a nanosecond pulse laser (Non-Patent Document 1), (Non-Patent Document 2), but recently there have been reports of a double-pulse type that combines microsecond and nanosecond pulses (Non-Patent Document 3), and of measuring the iron element in an aluminum alloy using a UV wavelength (380 millisecond pulse laser) and artificial intelligence (AI) (Non-Patent Document 4), and the spectrometers used in this research are multi-channel and have extremely high wavelength resolution.

[0005] However, these methods have drawbacks, such as the high specifications of the laser light source or spectrometer, making them expensive to offer as an option for each laser processing machine in India and other developing countries where there is high demand for carbon steel. [Prior art documents] [Non-patent literature]

[0006] [Non-Patent Document 1] Yamamoto, KY, et al., Laser-induced breakdown spectroscopy analysis of solids using a long-pulse (150 ns) Q-switched Nd: YAGlaser. Applied spectroscopy, 2005. 59 (9): p. 1082-1097. [Non-patent document 2] Sturm, V., et al., Carbon analysis of steel using compact spectrometer and passively Q-switched laser for laser-induced breakdown spectroscopy. Optics Express, 2019. 27 (25): p. 36855-36863. [Non-patent document 3] Cui, M., et al., Improved analysis of manganese in steel samples using collinear long-short double pulse laser-induced breakdown spectroscopy (LIBS). Applied spectroscopy, 2019. 73 (2): p. 152-162. [Non-patent document 4] Shuang, Q., et al., The Accuracy Improvement of Fe Element in Aluminum Alloy by Millisecond Laser Induced Breakdown Spectroscopy Under Spatial Confinement Combined With Support Vector Machine. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2022. 42 (2): p. 582-586. Summary of the Invention [Problem to be solved by the invention]

[0007] Therefore, an object of the present invention is to provide a method for determining carbon steel that can reliably identify the type of carbon steel before processing using a simple determination method without using a high-spec laser light source or spectrometer, and that can measure the element ratios specific to carbon steel. [Means for solving the problem]

[0008] As a result of extensive research, the inventors have come to the following invention. [1] A method for distinguishing carbon steel is provided, characterized in that in LIBS measurement of carbon steel using a near-infrared multimode fiber laser light source, the laser pulse width and oscillation signal are controlled by a pulse controller, an elemental analysis of the carbon steel is performed using a cutting laser head in a wavelength range of 200 nm to 600 nm, and the type of carbon steel is determined from the relative ratio of the peak heights using the spectral peaks of iron, chromium, and manganese. [2] In [1], a method for distinguishing carbon steel is provided, characterized in that the LIBS measurement generates a spectrometer trigger signal from the laser oscillation signal to a pulse generator, sends it to the spectrometer, and the spectrometer acquires data synchronized with the laser oscillation and performs synchronous spectroscopy. [3] In [1], a method for distinguishing carbon steel is provided, characterized in that AI using a convolutional neural network is used to determine the type of carbon steel, and peak heights included in the wavelength range of actual spectrum measurement data are used as learning data for training, thereby distinguishing the type of carbon steel. [Brief explanation of the drawings]

[0009] [Figure 1] FIG. 1 is a diagram showing the configuration of a measuring instrument according to the present invention. [Figure 2] FIG. 1 shows the results of measuring the emission spectrum of S15C carbon steel, obtained by setting the laser pulse width to 25 microseconds and synchronizing the spectrometer with a trigger signal. [Figure 3] FIG. 1 shows part of the spectral data of each representative sample and a standard substance. [Figure 4] FIG. 2 is a schematic diagram of a reading flow of processing according to the present invention. [Figure 5] FIG. 2 is a schematic diagram of a learning flow of processing according to the present invention. [Figure 6] FIG. 1 is a schematic diagram of a flow of determination processing according to the present invention. [Figure 7] FIG. 1 is a conceptual diagram showing the structure of a CNN used in the present invention. [Figure 8] This is a diagram showing a schematic diagram of AI judgment processing in which database model generation is always performed as a separate process by cooperation between a CPU and a GPU. [Figure 9] FIG. 10 is a diagram showing the results of the transition of accuracy (individual judgment) over time (number of days) when judgment is made from the spectral data of each carbon steel. [Figure 10] This figure shows the results of the transition of accuracy (by concentration) over time (number of days) for each of the low, medium, and high carbon steel concentration ranges (low concentration: S15C and S20C, medium concentration: S35C, high concentration: S45C and S55C) for the determination accuracy when determining from the spectral data of each carbon steel. [Figure 11] FIG. 10 is a diagram showing the correlation between the individual determination accuracy rate and precision. [Figure 12] FIG. 10 is a diagram showing the correlation between the accuracy rate of concentration-specific determination and precision. BEST MODE FOR CARRYING OUT THE INVENTION

[0010] Laser source, spectrometer, synchronization Figure 1 shows the configuration of the measuring device of the present invention. A 1000W, 1080nm near-infrared multimode fiber laser was equipped with an HSG Laser cutting laser head, and the laser pulse width and oscillation signal were controlled by a pulse controller. Typically, in LIBS measurements of carbon steel, spectrometer measurements are used to quantitatively analyze elemental concentrations using the elemental ratio of iron to carbon, which exists in the 190nm to 195nm range. However, in this invention, a compact spectrometer with a wavelength range of approximately 200nm to 600nm was used. This wavelength range was adopted because measurements in the 190nm to 200nm wavelength range are difficult to distinguish from noise, even when the laser pulse width is set to 10 microseconds.

[0011] The spectrometer generates a spectrometer trigger signal from the laser oscillation signal and sends it to the pulse generator to acquire data synchronized with the laser oscillation. Thus, synchronization between the laser oscillation and the spectrometer signal is key to measuring the emission spectrum. When setting up the pulse generator, the laser oscillation signal generated by the burst signal is input to the external trigger of the pulse generator, and the first laser oscillation signal is sent to the spectrometer with a pulse width of 10 to 300 microseconds determined by the spectrometer. The trigger signal to the spectrometer can be set anywhere from one shot, and can be delayed by 0 to 1000 microseconds using the delay function.

[0012] Positional relationship with specimen head Carbon steel samples (S15C, S20C, S35C, S45C, and S55C) purchased from Standard Test Piece Co., Ltd. were degreased with alcohol and then fixed to a stage. The spectrometer's input fiber cable was installed near the center of the laser head and the sample. During spectrum measurement, an appropriate amount of compressed air was released from the laser head in synchronization with the laser irradiation to prevent spatter from ablation from entering the laser head. The laser head was angled 30 to 90 degrees, preferably 45 to 90 degrees, relative to the sample surface, and positioned 10 to 15 mm from the sample surface. The input fiber cable was angled 45 to 90 degrees relative to the sample surface and positioned 5 to 50 mm from the sample surface.

[0013] Measurement peaks of each element Figure 2 shows an example of an emission spectrum measurement result for S15C carbon steel, obtained by setting the laser pulse width from 10 to 300 microseconds and synchronizing the spectrometer with the trigger signal. Compared to using a nanosecond laser, the overall spectral intensity is very low and proportional to the pulse width. However, referring to existing literature and the NIST database, we observed peaks for iron (Fe) at 372 nm, 373 nm, 386 nm, and 527 nm, a peak for chromium (Cr) at 358 nm, and a peak for manganese (Mn) at 403 nm. Furthermore, the spectral intensity tended to increase as the wavelength increased to 600 nm. This is presumably due to the effects of the emission of elements in the compressed air during laser irradiation and the emission due to laser heating of the sample surface. Furthermore, emission spectra of other carbon steels (S15C, S20C, S35C, S45C, and S55C) were similarly measured.

[0014] Carbon steel determination using spectral data and AI Using a Python-based program, we created a numerical calculation AI and a neural network (NN) AI. Based on the LIBS simulation data for the carbon steel used, the numerical calculation AI used the relative ratio of peaks contained in a specific wavelength range of the actual measurement data to calculate the most similar peak shape from several types of carbon steel simulation data. Next, we showed the website where the "NIST LIBS Database" is sourced. https: / / physics.nist.gov / PhysRefData / ASD / LIBS / libs-form.html For the AI ​​numerical calculation, the spectral data was preprocessed and used as input for the program. Preprocessing involved reading spectral data saved in text or CSV format, and extracting the peak position, intensity, and wavelength of peaks in a specified wavelength range (arbitrarily set between 200 and 600 nm) using Python library functions. A specified number of peaks were extracted from the acquired peak group in descending order, and normalized to the smallest peak among them. The same procedure was performed on the simulation data, changing the wavelength range (arbitrarily set between 200-600 nm) and the number of peaks, and the simulation data and spectral data were compared in descending order of intensity. The comparison was carried out by calculating the squared error of the normalized peak intensity between each simulation data and spectral data, and the simulation data with the smallest squared error was presented as the discrimination result.

[0015] On the other hand, NN-AI is an AI that uses a convolutional neural network (CNN), a type of NN. In this case, peaks contained in specific wavelength ranges of actual measurement data were used as learning data for training to identify materials. CNN is specifically a deep learning algorithm that mimics the "neurons" in the human brain, and by learning data it is able to extract features from visible light spectrum data and distinguish between them. Deep learning was applied to material identification.

[0016] Here, the spectral data (wavelength range (set arbitrarily between 200-600 nm)) was preprocessed and used as input for CNN. Preprocessing involved reading spectral data saved in text or CSV format, and extracting the peak position, intensity, and wavelength of peaks in the specified wavelength range using functions from the Python library. A specified number of peaks were extracted from the acquired peak group in descending order, and normalized to the smallest peak among them. Specifically, peaks were obtained by loading the spectral data of known metals into the library and used as a standard for comparison. For this, the SciPy find_peaks library was used to detect peaks. Two peaks were searched for within each specified wavelength range, so if there were three sets of specified wavelength ranges, a total of six peaks would be found. If there were fewer than two peaks, a data error was detected.

[0017] The CNN was constructed using an open-source library and consists of an input layer, convolutional layer, pooling layer, and output layer. The normalized peak intensity is used as input, and the input layer is one-dimensional, corresponding to the number of specified peaks. The convolutional layer is one-dimensional, ranging from 32 to 256 (32, 64, 128, 256), with a kernel size of 4 to 25 (2*2, 3*3, 5*5). The activation functions used were Rectified Linear Unit (Relu), Sigmoid, Tanh, and Softmax. The output layer is one-dimensional, corresponding to the number of carbon steel types.

[0018] Based on the spectral data of each representative sample shown in Figure 3, the aforementioned data reading, preprocessing, and database construction calculations are performed. While building the database, the spectral data of the sample to be identified is collated and subjected to a judgment calculation process to determine the identity. Figures 4 to 6 show schematic diagrams of the reading, learning, and judgment processes of the present invention. Specifically, deep learning algorithms used in image recognition are applied to the field of image recognition because they can extract features from input images and distinguish them by learning data. Here, spectral images are recognized, and the CNN structure goes through a series of processes from the input layer, convolutional layer, and pooling layer to the activation layer, fully connected layer, and output layer, with each layer gradually extracting more abstract features from the input image data. This process allows the deep learning model to learn patterns in complex images and extract important information for classification and recognition. Figure 7 shows a conceptual diagram of the CNN structure used in this invention. From the left, the input layer (InputLayer∈R^16), two hidden layers (HiddenLayer∈R^12, HiddenLayer∈R^10), and output layer (OutputLayer∈R^1) are shown. The mechanism for image recognition and judgment is as follows: first, image data is supplied to the input layer, and features are extracted through the convolutional layer and pooling layer. Next, a nonlinear transformation is performed by the activation layer, and these features are integrated through the fully connected layer. Finally, predictions for classification and recognition are made in the output layer. Through this series of processes, deep learning models gain the ability to recognize and judge images with high accuracy for specific tasks.

[0019] [Table 1]

[0020] Table 1 shows the results of a comparison of the accuracy of numerical calculation AI and NN-AI using spectral data for each carbon steel. The accuracy of the numerical calculation AI was approximately 20%, while the NN-AI was approximately four times higher at 84%. If we simply assume that accuracy is equal to the accuracy rate, the probability that an average person would correctly identify the five types of carbon steel is 20%, so the numerical calculation AI can be considered to be closer to an AI modeled after an average person. On the other hand, the NN-AI suggests that it is likely to be at the level of an expert or specialist with experience in laser processing. Therefore, we investigated improvements to the NN-AI and changes and trends in its accuracy, leading to the present invention.

[0021] Here, the accuracy of the concentration types and the accuracy of individual types were assessed. The accuracy rate is the number of answers judged correct by the user divided by the number of data points entered into the discrimination AI, and accuracy can be expressed as the number of correct answers divided by the data points used for testing. The data input to the training AI was set to n, the data used for training to 0.8*n, and the data used for testing to 0.2*n. Each training model was calculated using the data used for training (data used for training to 0.8*n). The accuracy of the models generated by each training calculation was then calculated using the value calculated for the data used for testing (data used for testing to 0.2*n) as the number of correct answers during testing divided by the data points used for testing. The models in this case were neural network models generated by the training AI through training. The coefficients n of 0.8 and 0.2 were determined based on empirical data in this field. To verify the accuracy of a model, the data is divided into data used for learning (Training Data) and data not used (Validation Data), and the rule of thumb is generally a ratio of 7:3 or 8:2. For example, we used "History of Artificial Intelligence and Deep Learning" by SONY (registered trademark). The website is https: / / www.comm.tcu.ac.jp / mds-center / Resources / SNCs / PDFs / 07-0_WhatIsDeepLearning%C2%A9SNC.pdf.

[0022] The original NN-AI system saved each piece of judged spectral data in a database, modeled that database, and used it to judge carbon steel from the next piece of spectral data. As a result, when the AI ​​had to build a model from the database and then make a judgment each time, it took more than a minute to judge 20 or more pieces of data. However, by using a CPU and GPU in conjunction to constantly run database model generation as a separate process, as shown in Figure 8, the AI ​​judgment process was shortened to less than 10 seconds.

[0023] Figure 9 shows the accuracy trends over time (number of days) for the judgment accuracy when each carbon steel was judged from spectral data (individual judgment) and for the judgment (concentration judgment) divided into low, medium, and high carbon steel concentrations (low concentration: S15C and S20C, medium concentration: S35C, high concentration: S45C and S55C). Initially, each judgment showed an accuracy of over 80%, but for the individual judgment (Figure 9), the accuracy dropped sharply to below 60% on the eighth day, and for the low, medium, and high concentration judgment (Figure 10), the accuracy also showed a slight drop on the fourth day. This change was due to a significant change in the fixed position of the incident fiber of the spectrometer, which caused a change in the spectral data, causing the NN-AI to recognize the data as different from previous data. Therefore, additional data was acquired and the database was rebuilt while the incident fiber angle was fixed, and the accuracy of the individual judgment recovered to the 80% range. If the measurement conditions (sample position, laser position, and device settings) are fixed, for example, data can be measured for approximately six hours or more, and even if the AI ​​is trained on the large amount of data obtained, the accuracy rate can be over 80% if the accuracy is good. In this case, it was necessary to ensure stability by preventing wear inside the laser during long-term measurements. Furthermore, even if the accuracy and accuracy rate decrease for a certain period of time due to fluctuations in the positional relationship between the laser head and sample, or the positional relationship with the incident fiber, experience shows that accuracy tends to recover within 50 data points at the earliest, and around 100 data points on average, and the accuracy rate also recovers.

[0024] Figures 11 and 12 show the correlation between the accuracy rate and precision. The graphs are plotted for each number of judgment cycles. The number of judgment cycles refers to the number of repeated calculations performed to minimize the prediction error. The X axis represents the number of judgment cycles, the Y1 axis represents the accuracy rate, and the Y2 axis represents the accuracy. For individual judgments, the accuracy rate remained stable at 86–88%, while the accuracy rate initially remained below 50% and increased to 80% by the fourth cycle. In other words, if the accuracy rate is 80%, it is estimated that if 6–9 spectral data points are acquired during measurement and judgment is performed by majority vote, as with commercially available portable LIBS, there will be almost no judgment errors. On the other hand, for concentration-specific judgments, even when the accuracy exceeds 90%, the accuracy rate fluctuates irregularly, ranging from 67–85%. This is due to the frequent misjudgments between the S15C and S35C judgments. Ultimately, the accuracy rate remained stable at 86% thanks to the "supervised learning" function, demonstrating that concentration-specific discrimination is an AI with fewer errors than individual judgments. The wavelength range to be analyzed is preferably 350 to 550 nm, and it is particularly preferable to set 400 to 410 nm as the criterion for AI, which can increase the accuracy rate of the determination.

[0025] Using a laser for cutting steel plates and a small spectrometer, it became possible to measure the emission spectra of each carbon steel and use NN-AI to identify the type of carbon steel. Although the intensity of the emission spectrum was weaker than that of measurements using existing nanosecond lasers, a spectrum showing the elemental peaks of iron, chromium, and manganese in carbon steel was obtained without using a vacuum spectrometer, argon gas, or nitrogen gas. The accuracy of the developed NN-AI tended to vary depending on the hardware environment, but by improving the AI ​​program and data acquisition, the AI ​​judgment was completed in less than 10 seconds and achieved an accuracy rate of over 80%.

Claims

1. In the LIBS measurement of carbon steel, a near-infrared multimode fiber laser light source attached to a cutting laser head is used, and the laser pulse width and oscillation signal are controlled by a pulse controller. A vacuum spectrometer, argon gas, or nitrogen gas is not used, and the laser pulse width is set to 10 to 300 microseconds in the wavelength range of 200 nm to 600 nm. In the elemental analysis of carbon steel, the emission spectrum of the carbon element is not used, but the peaks of the emission spectra of the elements iron, chromium, and manganese are used to perform judgment calculation processing and distinguish the type of carbon steel. A method for distinguishing carbon steel, characterized in that a spectrometer trigger signal is generated from a laser oscillation signal and sent to a pulse generator, which is then sent to the spectrometer, the spectrometer acquiring data synchronized with the laser oscillation and spectroscopy in synchronization, reading and transferring data based on the spectral data of a typical sample, performing calculations to reconstruct a learning database related to the elements of carbon steel using the results of elemental analysis of the carbon steel, and while constructing the database, performing a judgment calculation process to compare the spectral data of the sample to be judged, and using AI using a convolutional neural network to judge the type of carbon steel, training the peak heights included in the wavelength range of actual spectral measurement data as learning data, thereby distinguishing between types of carbon steel S15C to S55C.

2. 2. The method for distinguishing carbon steel according to claim 1, wherein the determination calculation process for collating the spectral data of the sample to be determined is performed in parallel, with the CPU processing data transmission and integration between the three processes of spectral data acquisition, database construction calculation, and material determination calculation, and the GPU processing the database construction and material determination calculations, so that database model generation is always performed as a separate process by cooperation between the CPU and GPU, and the type of carbon steel is determined by using AI using a convolutional neural network to train the peak heights included in the wavelength range of actual spectral measurement data as learning data, and distinguishing the type of carbon steel from S15C to S55C.

Images