Intelligent method, system and equipment for chemical component analysis and performance prediction of die steel

Abstract

The invention relates to the technical field of component analysis, in particular to an intelligent method, system and equipment for chemical component analysis and performance prediction of die steel. The plasma is obtained through laser excitation of the die steel, the spectral signal of the plasma is analyzed, elements with extremely low concentration can be detected, multiple elements in a sample can be analyzed at the same time, compared with a chemical titration method, time is saved, the analysis efficiency is improved, the elements can be recognized more accurately through comparison of multiple characteristic spectral lines, and the detection accuracy is improved. The detection sensitivity of low-concentration elements can be improved by using a plurality of spectral lines, data of a plurality of characteristic spectral lines can be used for more accurate quantitative analysis, more reliable element concentration information is provided, and a concentration-signal intensity relation model is established by acquiring spectral signal intensity under a plurality of preset concentrations, so that the detection sensitivity of the elements with low concentration is improved. Therefore, the spectral signal intensity is more accurately converted into the element concentration, complex spectral data can be converted into a visual concentration value, and the accuracy and reliability of quantitative analysis can be improved.

Description

Technical Field

[0001] The present invention relates to the technical field of component analysis, and in particular to an intelligent method, system and equipment for chemical component analysis and performance prediction of die steel. Background Art

[0002] Mold steel is used to make cold stamping dies and die-casting dies. Molds are the main processing tools for mechanical manufacturing, radio instruments, motors, electrical appliances, industrial production, etc. The quality of the mold directly affects the quality of the pressure processing technology, the precision output of the product and the production cost. Since the cold stamping die needs to withstand impact loads, and nickel and manganese can increase toughness, mold steel with a certain content of nickel and manganese is suitable for making cold stamping dies. The die-casting mold has high wear resistance requirements, and high carbon content and chromium and molybdenum can provide high hardness and strength. Therefore, mold steel with high carbon content and a certain content of chromium and molybdenum is suitable for making die-casting molds.

[0003] At present, the main method for chemical composition analysis of mold steel is chemical titration. Its principle is to cut and crush the sample into small particles and then dissolve it in an acidic medium to an appropriate concentration, and then select a titrant for titration detection and analysis. However, the above method requires selecting a suitable titrant based on the elemental composition to be analyzed. Multiple elemental compositions may require selecting multiple titrants for multiple tests, which is time-consuming and labor-intensive. Therefore, it is necessary to study an intelligent method for chemical composition analysis and performance prediction of mold steel to analyze the chemical composition of mold steel, and then predict and evaluate the mold performance, so as to facilitate the selection of whether to use it to manufacture cold stamping dies or die-casting molds based on its performance. Summary of the invention

[0004] The main purpose of the present invention is to provide an intelligent method for chemical composition analysis and performance prediction of mold steel, aiming to solve the technical problems in the prior art.

[0005] The present invention proposes an intelligent method for chemical composition analysis and performance prediction of mold steel, comprising:

[0006] The mold steel is excited by laser to obtain plasma;

[0007] Acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals;

[0008] Acquire a plurality of characteristic spectral lines according to the spectrum diagram, and acquire a corresponding actual wavelength according to each of the characteristic spectral lines;

[0009] Compare each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength;

[0010] Obtaining a concentration-signal intensity curve graph, and obtaining an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph;

[0011] The performance characteristic evaluation values ​​of the mold steel are predicted according to the actual concentration values ​​of the multiple elements, and the mold steel is classified for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include a wear resistance performance evaluation value and a toughness performance evaluation value.

[0012] Preferably, the step of obtaining a spectrum graph according to the plurality of spectrum signals comprises:

[0013] Using a spectrometer to convert each of the spectral signals into an initial electrical signal, and amplifying each of the initial electrical signals to obtain a corresponding analog electrical signal;

[0014] An analog-to-digital converter is used to obtain the voltage value of each analog electrical signal at multiple preset time points, and the maximum voltage value is extracted as the maximum input voltage;

[0015] Obtaining the number of quantization levels of the analog-to-digital converter, and calculating the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels;

[0016] Calculate the corresponding discrete quantization level index according to the ratio of each voltage value to the quantization step length;

[0017] A spectrometer is used to plot the plurality of discrete quantization level indexes to obtain a spectrum graph.

[0018] Preferably, the step of using a spectrometer to plot the plurality of discrete quantization level indexes to obtain a spectrum graph comprises:

[0019] The minimum wavelength and maximum wavelength of the spectrometer are obtained, and the wavelength step is calculated according to the minimum wavelength, the maximum wavelength and the discrete quantization level index, wherein the calculation formula is:

[0020]

[0021] Among them, B(C) represents the wavelength step, Z(D) represents the maximum wavelength, Z(X) represents the minimum wavelength, and L(J) represents the number of quantization levels;

[0022] The corresponding wavelength is calculated according to the wavelength step, the minimum wavelength and a plurality of discrete quantization level indexes, wherein the calculation formula is:

[0023]

[0024] Where A represents the wavelength, B(C) represents the wavelength step, Z(X) represents the minimum wavelength, L(S) represents the wavelength step size, nrepresents the nth discrete quantization level index, n represents the sequence number of the discrete quantization level index, and m represents the number of discrete quantization level indexes;

[0025] Convert each of the discrete quantization level indexes into a corresponding signal strength;

[0026] The spectrum graph coordinate axis is established with wavelength as the X-axis and signal intensity as the Y-axis, and each signal intensity and corresponding wavelength of each spectral signal are plotted on the spectrum graph coordinate axis through a broken line to obtain a spectrum graph.

[0027] Preferably, the step of obtaining a plurality of characteristic spectral lines according to the spectrum diagram, and obtaining a corresponding actual wavelength according to each of the characteristic spectral lines comprises:

[0028] Extracting multiple peaks of each broken line in the spectrum graph to obtain multiple characteristic spectrum lines;

[0029] Sorting the plurality of characteristic spectral lines in order of magnitude to obtain a spectral line sorting table;

[0030] Selecting the first characteristic spectral line from the spectral line ranking table as the detection spectral line;

[0031] The corresponding actual wavelength is obtained from the spectrum diagram according to the detected spectrum line.

[0032] Preferably, the step of obtaining a concentration-signal intensity curve graph, and obtaining an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph comprises:

[0033] Obtaining the spectral signal intensity of the element corresponding to the actual wavelength at multiple preset concentrations;

[0034] A concentration-signal intensity coordinate axis is established with the preset concentration as the X-axis and the spectral signal intensity as the Y-axis;

[0035] Mark each preset concentration and the corresponding spectral signal intensity as a connection point on the concentration-signal intensity coordinate axis;

[0036] Connecting the plurality of connection points through a curve to obtain a concentration-signal intensity curve graph;

[0037] Obtaining the slope of a concentration-signal intensity curve, and obtaining the actual signal intensity according to the product of the slope of the curve and the actual wavelength;

[0038] The actual signal intensity is matched with the concentration-signal intensity curve to obtain the actual concentration value of each element.

[0039] Preferably, the step of predicting the performance characteristic evaluation value of the mold steel according to the actual concentration values ​​of the multiple elements, and classifying the mold steel for use according to the performance characteristic evaluation value comprises:

[0040] Obtain the weight coefficient of the actual concentration value of each element, and perform weighted calculation based on the actual concentration value of each element and the corresponding weight coefficient to obtain the overall performance score of the mold steel;

[0041] Determining whether the total performance score is less than a preset performance score;

[0042] If the total performance score is less than the preset performance score, it is determined that the performance of the die steel is poor;

[0043] If the total performance score is not less than the preset performance score, obtaining the standard concentration range of each element;

[0044] Determine whether the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is greater than a preset number;

[0045] If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is greater than a preset number, it is determined that the performance of the mold steel is poor;

[0046] If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is not greater than a preset number, the performance of the mold steel is determined to be good, and the actual concentration values ​​of carbon, chromium, molybdenum, nickel and manganese in the mold steel are extracted;

[0047] The wear resistance evaluation value is calculated according to the actual concentration values ​​of the carbon element, the chromium element, and the molybdenum element and their corresponding weight coefficients, wherein the calculation formula is:

[0048] N(X)=C*α+Cr*β+Mo*γ;

[0049] Wherein, N(X) represents the wear resistance evaluation value, C represents the carbon element, α represents the weight coefficient of the carbon element, Cr represents the chromium element, β represents the weight coefficient of the chromium element, Mo represents the molybdenum element, and γ represents the weight coefficient of the molybdenum element;

[0050] Determining whether the wear resistance evaluation value is greater than a first preset value;

[0051] If the wear resistance evaluation value is greater than the first preset value, it is determined that the die steel is suitable for manufacturing a die-casting die;

[0052] The toughness performance evaluation value is calculated according to the actual concentration values ​​of the nickel element and the manganese element and their corresponding weight coefficients, wherein the calculation formula is:

[0053] R(X)=Ni*δ+Mn*ε;

[0054] Wherein, R(X) represents the toughness performance evaluation value, Ni represents the nickel element, δ represents the weight coefficient of the nickel element, Mn represents the manganese element, and ε represents the weight coefficient of the manganese element;

[0055] Determining whether the toughness performance evaluation value is greater than a second preset value;

[0056] If the wear resistance evaluation value is greater than the second preset value, it is determined that the die steel is suitable for manufacturing cold stamping dies.

[0057] The present application also provides an intelligent system for chemical composition analysis and performance prediction of mold steel, including:

[0058] A processing module, used for exciting the mold steel by laser to obtain plasma;

[0059] A first acquisition module, used for acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals;

[0060] A second acquisition module, used to acquire a plurality of characteristic spectral lines according to the spectrum diagram, and acquire a corresponding actual wavelength according to each of the characteristic spectral lines;

[0061] A comparison module, used to compare each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength;

[0062] A third acquisition module is used to obtain a concentration-signal intensity curve graph, and obtain an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph;

[0063] A prediction module is used to predict performance characteristic evaluation values ​​of mold steel according to actual concentration values ​​of multiple elements, and classify the mold steel for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include wear resistance performance evaluation values ​​and toughness performance evaluation values.

[0064] Preferably, the first acquisition module includes:

[0065] A conversion unit, used to convert each of the spectral signals into an initial electrical signal using a spectrometer, and amplify each of the initial electrical signals to obtain a corresponding analog electrical signal;

[0066] An extraction unit, used to obtain the voltage value of each analog electrical signal at a plurality of preset time points by using an analog-to-digital converter, and extract the maximum voltage value as the maximum input voltage;

[0067] A first calculation unit, used for obtaining the number of quantization levels of the analog-to-digital converter, and calculating the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels;

[0068] A second calculation unit, configured to calculate a corresponding discrete quantization level index according to a ratio of each voltage value to a quantization step size;

[0069] The drawing unit is used for drawing the plurality of discrete quantization level indexes using a spectrometer to obtain a spectrum diagram.

[0070] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the intelligent method for chemical composition analysis and performance prediction of mold steel when executing the computer program.

[0071] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent method for chemical composition analysis and performance prediction of mold steel are implemented.

[0072] The beneficial effects of the present invention are as follows: the present invention obtains plasma by laser excitation of mold steel and analyzes its spectral signal, and can detect extremely low concentration elements, and can also simultaneously analyze multiple elements in the sample, including metal elements and non-metal elements. Compared with the chemical titration method, it not only saves time, but also improves the analysis efficiency. By comparing multiple characteristic spectral lines, the elements can be identified more accurately and the possibility of misidentification can be reduced. The use of multiple spectral lines can improve the detection sensitivity of low-concentration elements. The data of multiple characteristic spectral lines can be used for more accurate quantitative analysis and provide more reliable element concentration information. By obtaining the spectral signal intensity at multiple preset concentrations, an accurate concentration-signal intensity relationship model can be established, so that the spectral signal intensity can be more accurately converted into element concentration. The use of a concentration-signal intensity curve can convert complex spectral data into intuitive concentration values, which can improve the accuracy and reliability of quantitative analysis. The performance of the mold steel is determined according to the actual concentration value of each element. The concentrations of different elements have a direct impact on the performance of the mold steel. Accurately measuring these concentrations can more accurately predict the performance of the mold steel, and can provide a detailed performance evaluation based on the actual concentration of the chemical composition, which is more accurate than relying solely on experience or standard specifications. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 The figure is a schematic diagram of a method flow according to an embodiment of the present invention.

[0074] Figure 2 FIG. 1 is a schematic diagram of a system structure according to an embodiment of the present invention.

[0075] Figure 3 A schematic diagram of the internal structure of a computer device according to an embodiment of the present application.

[0076] Figure 4 This is a schematic diagram of a spectrum diagram according to an embodiment of the present application.

[0077] The realization of the purpose, functional features and advantages of the present invention will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0078] It should be understood that the specific embodiments described herein are only used to explain the present invention, and are not used to limit the present invention.

[0079] like Figure 1-Figure 4 As shown, the present application provides an intelligent method for chemical composition analysis and performance prediction of mold steel, including:

[0080] S1, excitation treatment of mold steel by laser to obtain plasma;

[0081] S2, acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals;

[0082] S3, obtaining a plurality of characteristic spectral lines according to the spectrum diagram, and obtaining a corresponding actual wavelength according to each of the characteristic spectral lines;

[0083] S4, comparing each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength;

[0084] S5, obtaining a concentration-signal intensity curve graph, and obtaining an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph;

[0085] S6. Predicting performance characteristic evaluation values ​​of the mold steel according to actual concentration values ​​of multiple elements, and classifying the mold steel for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include a wear resistance performance evaluation value and a toughness performance evaluation value.

[0086] As described in the above steps S1-S6, mold steel is a steel material used to manufacture molds such as injection molds, cold stamping molds, hot forging molds, and die-casting molds. Molds are the main processing tools for mechanical manufacturing, radio instruments, motors, electrical appliances, industrial production, etc. The quality of the mold directly affects the quality of the pressure processing process, the precision output of the product, and the production cost. Therefore, it is necessary to analyze the chemical composition of the mold steel to predict and evaluate the mold performance. At present, the chemical composition analysis method of mold steel is mainly chemical titration. Its principle is to cut and crush the sample into small particles and then dissolve it in an acidic medium to an appropriate concentration, and then select a titrant for titration detection and analysis. However, the above method requires the selection of a suitable titrant based on the elemental composition to be analyzed. Multiple elemental compositions may require the selection of multiple titrants for multiple tests, which is time-consuming and labor-intensive. The present invention uses laser to excite mold steel to obtain plasma, and obtains a spectrum according to multiple spectral signals of the plasma, wherein the plasma is a gaseous substance composed of free electrons and charged ions, and the free electrons in the plasma collide with atoms or molecules and generate characteristic spectra. The chemical composition of the mold steel can be analyzed by these spectral signals. By using an appropriate excitation source, such as an arc, plasma or laser, it is ensured that all elements in the sample can be fully excited. Since the spectral signal generated by the plasma is very strong and highly sensitive, extremely low concentration elements can be detected by laser excitation of the mold steel to obtain plasma and analyze its spectral signal, and multiple elements in the sample, including metal elements and non-metal elements, can be analyzed simultaneously. Compared with the chemical titration method, it not only saves time but also improves the analysis efficiency. For example, Figure 4As shown, there are four complete broken lines in the spectrum graph, each of which represents a different element. Multiple characteristic spectral lines of each element are obtained through the spectrum graph, and the actual wavelength of each element is obtained based on the characteristic spectral line. Each actual wavelength is then compared with the element characteristic spectral line database to obtain the element corresponding to the actual wavelength. By comparing multiple characteristic spectral lines, the element can be identified more accurately and the possibility of misidentification can be reduced. The use of multiple spectral lines can improve the detection sensitivity of low-concentration elements. Because the intensities of different spectral lines may be different, comprehensive analysis can improve the detection capability. The data of multiple characteristic spectral lines can be used for more accurate quantitative analysis and provide more reliable element concentration information. Moreover, since the characteristic spectral line of each element has significant intensity at a specific wavelength, unlike the background noise, by selecting multiple characteristic spectral lines, the element signal and noise can be effectively distinguished. Therefore, by comparing multiple characteristic spectral lines, the interference of background noise on element identification can be reduced, and the accuracy of the results can be improved. The spectral signal intensity of the element corresponding to the actual wavelength at multiple preset concentrations, and a concentration-signal intensity curve diagram is established based on the multiple spectral signal intensities of the element corresponding to the actual wavelength and the corresponding preset concentrations, and then the actual concentration value of each element is obtained according to the actual wavelength and the concentration-signal intensity curve diagram. By obtaining the spectral signal intensity at multiple preset concentrations, an accurate concentration-signal intensity relationship model can be established, so as to more accurately convert the spectral signal intensity into element concentration. The use of the concentration-signal intensity curve diagram can convert complex spectral data into intuitive concentration values, which can improve the accuracy and reliability of quantitative analysis. The performance of the mold steel is determined according to the actual concentration value of each element. The concentrations of different elements have a direct impact on the performance of the mold steel (such as hardness, strength, wear resistance, etc.). Accurately measuring these concentrations can more accurately predict the performance of the mold steel, and can provide detailed performance evaluation based on the actual concentration of the chemical composition, which is more accurate than relying solely on experience or standard specifications.

[0087] In one embodiment, the step S2 of obtaining a spectrum graph according to the plurality of spectrum signals comprises:

[0088] S21, the step of obtaining a spectrum graph according to the plurality of spectrum signals comprises:

[0089] S22, using a spectrometer to convert each of the spectral signals into an initial electrical signal, and amplifying each of the initial electrical signals to obtain a corresponding analog electrical signal;

[0090] S23, using an analog-to-digital converter to obtain voltage values ​​of each analog electrical signal at multiple preset time points, and extracting the maximum voltage value as the maximum input voltage;

[0091] S24, obtaining the number of quantization levels of the analog-to-digital converter, and obtaining the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels, wherein the calculation formula is:

[0092]

[0093] Among them, L(C) represents the quantization step size, D(Z) represents the maximum input voltage, and L(J) represents the number of quantization levels;

[0094] S25, calculating the corresponding discrete quantization level index according to the ratio of each voltage value to the quantization step length, wherein the calculation formula is:

[0095]

[0096] Among them, L(S) i represents the i-th discrete quantization level index, D(Y) i represents the i-th voltage value, L(B) represents the quantization step size, and i represents the sequence number of the voltage value;

[0097] A spectrometer is used to plot the plurality of discrete quantization level indexes to obtain a spectrum graph.

[0098] As described in the above steps S21-S25, the present invention converts each spectral signal into an initial electrical signal by using a spectrometer, and amplifies each initial electrical signal to obtain a corresponding analog electrical signal. By amplifying the initial electrical signal, the strength of the weak spectral signal can be increased, so that even low-concentration elements can be detected. After the signal is amplified, the background noise and interference can be better overcome to obtain clearer spectral data. The amplification process can accurately obtain spectral data even in complex samples, which is particularly suitable for the analysis of samples with multiple elements such as mold steel. By amplifying the signal, the measurement fluctuation caused by equipment fluctuation or environmental change can be reduced, which helps to improve the resolution and accuracy of the signal, thereby facilitating more accurate identification and quantification of elements in the subsequent process. The components are obtained by using an analog-to-digital converter to obtain the voltage values ​​of each analog electrical signal at multiple preset time points, and the maximum voltage value is extracted as the maximum input voltage. The quantization level number of the analog-to-digital converter is obtained, and the quantization step length is obtained by the ratio of the maximum input voltage and the quantization level number. The quantization step length refers to the minimum unit or interval between each quantization level in the quantization process. In the analog-to-digital converter, the quantization level number indicates the number of different amplitude levels used when the signal is discretized. Since the quantization step length determines the resolution of the data, a smaller step length can provide more accurate voltage measurement, thereby more accurately reflecting the spectral signal intensity. Through high-resolution quantization, weak signals can be better analyzed and the detection of low-concentration elements can be improved. The detection capability of the quantization step can reduce the error in the analog-to-digital signal conversion process and improve the reliability of the data through precise quantization step length. After calculating the quantization step length, the voltage value of the analog electrical signal can be measured more accurately, thereby improving the measurement accuracy of the element concentration, which is helpful for the subsequent more accurate and consistent analysis of the chemical element composition of the mold steel. The corresponding discrete quantization level index is calculated by the ratio of each voltage value to the quantization step length, where the discrete quantization level index refers to the index value used to identify the discrete data level during the quantization process, and a spectrogram is obtained by plotting multiple discrete quantization level indexes using a spectrometer. Since the spectrogram can intuitively display the signal strength of each discrete quantization level, it is easy to identify the spectral characteristics of different elements, and discrete quantization Level indexing can improve spectral resolution and help identify and distinguish spectral peaks of different elements in chemical composition. Through accurate quantization level indexing, the signal peaks in the spectrum can be more accurately located, thereby improving the measurement accuracy of element concentration. Each quantization level on the spectrum corresponds to a specific signal intensity, which can be used for quantitative analysis to facilitate subsequent estimation of the concentration of each element in mold steel. Moreover, discretizing the voltage value and drawing the spectrum can reduce the impact of background noise and improve the accuracy of data processing. After calculating the corresponding discrete quantization level index according to the ratio of each voltage value to the quantization step, the calculated discrete quantization level index may not be an integer, that is, the discrete quantization level index at this time will not fall exactly on the boundary of the quantization level.Therefore, it is necessary to round off the discrete quantization level index to obtain an integer discrete quantization level index. For example, when the maximum input voltage is 5V, the 12-bit analog-to-digital converter has 4096 quantization levels. At this time, the quantization step size is calculated according to the formula: When the second voltage value is 2.7V, the second discrete quantization level index is calculated according to the formula Since 2213.11 is not an integer, 2213.11 needs to be rounded to 2213. At this time, the actual discrete quantization level index should be 2213. It should be noted that the numbers 5, 12, 2213, 2213.11, etc. appearing above are all examples for clearly explaining the embodiments and are not the only limitation here.

[0099] In one embodiment, the step S25 of using a spectrometer to draw a plurality of the discrete quantization level indexes to obtain a spectrum diagram comprises:

[0100] S251, obtaining the minimum wavelength and maximum wavelength of the spectrometer, and calculating the wavelength step according to the minimum wavelength, maximum wavelength and discrete quantization level index, wherein the calculation formula is:

[0101]

[0102] Among them, B(C) represents the wavelength step, z(D) represents the maximum wavelength, Z(X) represents the minimum wavelength, and L(J) represents the number of quantization levels;

[0103] S252, calculating a corresponding wavelength according to the wavelength step, the minimum wavelength, and a plurality of discrete quantization level indexes, wherein the calculation formula is:

[0104]

[0105] Where A represents the wavelength, B(C) represents the wavelength step, Z(X) represents the minimum wavelength, L(S) represents the wavelength step size, n represents the nth discrete quantization level index, n represents the sequence number of the discrete quantization level index, and m represents the number of discrete quantization level indexes;

[0106] S253, converting each of the discrete quantization level indexes into a corresponding signal strength;

[0107] S254, establishing a spectrum graph coordinate axis with wavelength as the X-axis and signal intensity as the Y-axis, and plotting each signal intensity and corresponding wavelength of each spectrum signal on the spectrum graph coordinate axis through a broken line to obtain a spectrum graph.

[0108] As described in the above steps S251-S254, the present invention obtains the minimum wavelength and maximum wavelength of the spectrometer, and calculates the wavelength step size according to the minimum wavelength, maximum wavelength and discrete quantization level index, wherein the wavelength step size refers to the wavelength interval selected when measuring spectral data in spectral analysis. By calculating the wavelength step size, uniform sampling between the minimum wavelength and the maximum wavelength can be ensured, and data errors caused by uneven sampling can be reduced to cover the entire spectral range, thereby comprehensively analyzing all elements in the mold steel. The wavelength step size calculated according to the discrete quantization level index can provide appropriate resolution, help identify and analyze subtle differences in the spectrum, and improve data accuracy. The wavelength step size, the minimum wavelength and each discrete quantization level index are then calculated to obtain the wavelength step size. The corresponding wavelength, each wavelength calculated by wavelength step, minimum wavelength and multiple discrete quantization level indexes corresponds to a specific position on the spectrum graph, which can accurately calibrate each sampling point in the spectral data and improve the positioning accuracy of the wavelength. By calculating the wavelength of each quantization level, the spectral characteristics at each wavelength can be clearly displayed on the spectrum graph, which is helpful to identify and distinguish subtle spectral peaks. The wavelength is systematically calculated according to the wavelength step and quantization level index to ensure the consistency of data processing. Accurate wavelength calculation helps to clearly distinguish the characteristics of different elements in the spectrum and reduce the impact of spectral line overlap on the analysis results. By converting each discrete quantization level index into the corresponding signal intensity, and using wavelength as the X-axis and signal intensity as the Y-axis to establish a light Spectrum coordinate axis, each signal intensity and corresponding wavelength of each spectral signal are plotted on the spectrum coordinate axis through a broken line to obtain a spectrum, where the wavelength and signal intensity of each signal can be organized into a feature vector to form a matrix, each row represents a feature vector of a signal, and each column represents a different feature (wavelength and signal intensity). At the same time, in order to avoid the influence of different feature scales, the wavelength and signal intensity can be standardized. The commonly used method is to scale the features to the same range or standardize them to a standard normal distribution with a mean of 0 and a standard deviation of 1, and then select a suitable clustering algorithm (such as K-means clustering or hierarchical clustering), so that multiple spectral signals can be classified according to different elements, and then By drawing a spectrum graph with a broken line, the spectrum graph can intuitively display the signal intensity of each wavelength, making the spectral characteristics of the elements clear at a glance, which is helpful to identify and analyze the characteristic peaks of different chemical elements. The peak position on the spectrum graph corresponds to the characteristic wavelengths of different elements, which helps to accurately identify and distinguish the various elements present in mold steel. The concentration of each element can be quantitatively estimated through the signal intensity, providing detailed information about the composition of mold steel. Therefore, by converting the discrete quantization level index into signal intensity and drawing a spectrum graph, the spectral characteristics can be clearly displayed, the element peaks can be accurately identified, quantitative analysis can be supported, data analysis and interpretation can be optimized, and complex samples can be fully covered, so that more accurate and comprehensive results can be obtained when analyzing the chemical element composition of mold steel.

[0109] In one embodiment, the step S3 of acquiring a plurality of characteristic spectral lines according to the spectrum diagram and acquiring a corresponding actual wavelength according to each of the characteristic spectral lines comprises:

[0110] S31, extracting multiple peaks of each broken line in the spectrum graph to obtain multiple characteristic spectrum lines;

[0111] S32, sorting the plurality of characteristic spectral lines in order of magnitude to obtain a spectral line sorting table;

[0112] S33, selecting the first characteristic spectral line from the spectral line sorting table as the detection spectral line;

[0113] S34, obtaining the corresponding actual wavelength from the spectrum diagram according to the detected spectrum line.

[0114] As described in the above steps S31-S34, the present invention obtains multiple characteristic spectral lines by extracting multiple peaks of each element's broken line in the spectrum graph, and then sorting the multiple characteristic spectral lines in order of size to obtain a spectrum line sorting table, and then obtaining the actual wavelength of each element from the spectrum graph according to the detection spectrum line by selecting the characteristic spectrum line ranked first from the spectrum line sorting table as the detection spectrum line, wherein the spectrum line refers to the signal intensity peak at the wavelength displayed in the spectrum, and selecting the characteristic spectrum line ranked first in the sorting table as the detection spectrum line helps to determine the most representative feature in the spectrum graph, thereby improving the recognition accuracy of the actual wavelength of each element, and the sorted characteristic spectrum lines can help prioritize the analysis of the most significant element signals, reduce reliance on insignificant or noise interference spectrum lines, and optimize the effectiveness of element detection. By extracting the most significant characteristic spectrum lines, the actual wavelength of each element can be more accurately determined, which helps to improve the quantitative analysis accuracy of element concentrations. The clearly selected detection spectrum line can be used as the most characteristic reference point in the spectrum graph to help better interpret the spectral data and improve the interpretability of the results.

[0115] In one embodiment, the step S5 of obtaining a concentration-signal intensity curve graph and obtaining the actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph comprises:

[0116] S51, obtaining the spectral signal intensity of the element corresponding to the actual wavelength at multiple preset concentrations;

[0117] S52, establishing a concentration-signal intensity coordinate axis with the preset concentration as the X-axis and the spectral signal intensity as the Y-axis;

[0118] S53, marking each preset concentration and the corresponding spectral signal intensity as a connection point on the concentration-signal intensity coordinate axis;

[0119] S54, connecting the plurality of connection points through a curve to obtain a concentration-signal intensity curve graph;

[0120] S55, obtaining the slope of the concentration-signal intensity curve, and obtaining the actual signal intensity according to the product of the slope of the curve and the actual wavelength;

[0121] S56, matching the actual signal intensity with the concentration-signal intensity curve to obtain the actual concentration value of each element.

[0122] As described in the above steps S51-S56, the present invention establishes a concentration-signal intensity coordinate axis by taking the preset concentration as the X-axis and the spectral signal intensity as the Y-axis, and then marks each preset concentration and the corresponding spectral signal intensity as a connection point on the concentration-signal intensity coordinate axis, and connects multiple of the connection points through a curve to obtain a concentration-signal intensity curve graph. The concentration-signal intensity curve graph can establish a quantitative relationship between element concentration and spectral signal intensity, so that the actual concentration of the element in the sample can be directly inferred based on the spectral signal intensity. By drawing the concentration-signal intensity curve graph, the relationship between concentration and signal intensity can be identified, which is helpful to more accurately analyze and interpret spectral data. The concentration-signal intensity curve graph can clearly show the trend of signal intensity changing with concentration. By drawing the concentration-signal intensity curve graph, the change of signal intensity at different concentrations can be evaluated. The curve graph can be used for quantitative analysis. By fitting the curve and determining the concentration-signal intensity The concentration of elements in the sample can be accurately calculated by the relationship formula of the concentration-signal intensity curve. The actual signal intensity is obtained by multiplying the slope of the curve and the actual wavelength. The actual concentration value of each element is obtained by matching the actual signal intensity with the concentration-signal intensity curve. The actual signal intensity is obtained by multiplying the slope of the curve and the actual wavelength. Matching with the concentration-signal intensity curve can accurately determine the actual concentration of the element and improve the accuracy of quantitative analysis. Calculating the actual signal intensity using the slope of the curve helps to improve the accuracy of the measurement method and ensure the reliability of the results. By calculating the slope and the actual wavelength and matching the spectral signal intensity with the concentration graph, the relationship between the signal intensity and the actual concentration can be clearly explained, which enhances the interpretability of the data. In addition, calculating the actual signal intensity using the slope of the curve can reduce the error caused by spectral noise or interference and improve the accuracy of concentration measurement.

[0123] In one embodiment, the step S6 of predicting the performance characteristic evaluation value of the mold steel according to the actual concentration values ​​of the multiple elements and classifying the mold steel for use according to the performance characteristic evaluation value includes:

[0124] S61, obtaining a weight coefficient of the actual concentration value of each element, and performing weighted calculation according to the actual concentration value of each element and the corresponding weight coefficient to obtain a total performance score of the mold steel;

[0125] S62, determining whether the total performance score is less than a preset performance score;

[0126] If the total performance score is less than the preset performance score, it is determined that the performance of the die steel is poor;

[0127] If the total performance score is not less than the preset performance score, obtaining the standard concentration range of each element;

[0128] S63, determining whether the number of actual concentration values ​​of the multiple elements that are not within the corresponding standard concentration range is greater than a preset number;

[0129] If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is greater than a preset number, it is determined that the performance of the mold steel is poor;

[0130] If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is not greater than a preset number, the performance of the mold steel is determined to be good, and the actual concentration values ​​of carbon, chromium, molybdenum, nickel and manganese in the mold steel are extracted;

[0131] S64, calculating the wear resistance evaluation value according to the actual concentration values ​​of the carbon element, the chromium element, and the molybdenum element and their corresponding weight coefficients, wherein the calculation formula is:

[0132] N(X)=C*α+Cr*β+Mo*γ;

[0133] Wherein, N(X) represents the wear resistance evaluation value, C represents the carbon element, α represents the weight coefficient of the carbon element, Cr represents the chromium element, β represents the weight coefficient of the chromium element, Mo represents the molybdenum element, and γ represents the weight coefficient of the molybdenum element;

[0134] S65, determining whether the wear resistance evaluation value is greater than a first preset value;

[0135] If the wear resistance evaluation value is greater than the first preset value, it is determined that the mold steel is suitable for manufacturing a die-casting mold:

[0136] S66. Calculate the toughness performance evaluation value according to the actual concentration values ​​of the nickel element and the manganese element and their corresponding weight coefficients, wherein the calculation formula is:

[0137] R(X)=Ni*δ+Mn*ε;

[0138] Wherein, R(X) represents the toughness performance evaluation value, Ni represents the nickel element, δ represents the weight coefficient of the nickel element, Mn represents the manganese element, and ε represents the weight coefficient of the manganese element;

[0139] S67, determining whether the toughness performance evaluation value is greater than a second preset value;

[0140] If the wear resistance evaluation value is greater than the second preset value, it is determined that the die steel is suitable for manufacturing cold stamping dies.

[0141] As described in the above steps S61-S67, the present invention performs weighted calculation according to the actual concentration value of each element and the corresponding weight coefficient to obtain the total performance score of the mold steel, and determines whether the total performance score is less than the preset performance score. If the total performance score is less than the preset performance score, it is determined that the performance of the mold steel is poor. Otherwise, further judgment and prediction are made by judging the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range. The score is calculated by a specific mathematical formula, which can provide a quantitative evaluation index, which is more operational than relying solely on whether the element is within the standard range. The total performance score can be used to more accurately predict the performance of the mold steel. The performance of mold steel in actual application can be measured by comparing it with the preset performance score to directly determine whether the mold steel meets specific performance requirements. When the total performance score is qualified, the quality of the mold steel can be further verified by checking whether the elements are within the standard concentration range. This helps to analyze whether the mold steel is suitable for manufacturing cold stamping molds or die-casting molds. If the actual concentration values ​​of multiple elements are not within the corresponding standard concentration range and the number is greater than the preset number, the performance of the mold steel is judged to be poor, otherwise it is judged that the performance of the mold steel is good, and the actual concentrations of carbon, chromium, molybdenum, nickel and manganese in the mold steel are extracted. The wear resistance evaluation value is calculated according to the actual concentration values ​​of carbon, chromium and molybdenum and their corresponding weight coefficients, and the toughness performance evaluation value is calculated according to the actual concentration values ​​of nickel and manganese and their corresponding weight coefficients, and then by judging whether the wear resistance evaluation value is greater than a first preset value and whether the toughness performance evaluation value is greater than a second preset value, if the wear resistance evaluation value is greater than the first preset value, it is determined that the mold steel is suitable for manufacturing a die casting mold, and if the wear resistance evaluation value is greater than the second preset value, it is determined that the mold steel is suitable for manufacturing a cold stamping mold, and the wear resistance and toughness performance evaluation values ​​are calculated respectively, and the preset wear resistance and toughness performance evaluation values ​​are used. Taking the toughness performance value as a standard, it is possible to clearly determine whether the mold steel meets the specific performance requirements. The applicable type of mold steel (such as die-casting mold or cold stamping mold) can be determined based on the wear resistance performance evaluation value and the toughness performance evaluation value. This can ensure that the steel performs well in a specific application environment and improve the targeted use of mold steel. A detailed performance evaluation can be conducted before deciding to use it, so that potential problems can be discovered in advance. If the actual concentration values ​​of multiple elements are not within the corresponding standard concentration range and the number is greater than the preset number, it indicates that there may be a risk of poor performance, which helps to avoid selecting mold steel with insufficient performance and reduce the risks caused by insufficient mold steel performance.

[0142] The present application also provides an intelligent system for chemical composition analysis and performance prediction of mold steel, including:

[0143] A processing module, used for exciting the mold steel by laser to obtain plasma;

[0144] A first acquisition module, used for acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals;

[0145] A second acquisition module, used to acquire a plurality of characteristic spectral lines according to the spectrum diagram, and acquire a corresponding actual wavelength according to each of the characteristic spectral lines;

[0146] A comparison module, used to compare each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength;

[0147] A third acquisition module is used to obtain a concentration-signal intensity curve graph, and obtain an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph;

[0148] A prediction module is used to predict performance characteristic evaluation values ​​of mold steel according to actual concentration values ​​of multiple elements, and classify the mold steel for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include wear resistance performance evaluation values ​​and toughness performance evaluation values.

[0149] In one embodiment, the first acquisition module includes:

[0150] The first acquisition module includes:

[0151] A conversion unit, used to convert each of the spectral signals into an initial electrical signal using a spectrometer, and amplify each of the initial electrical signals to obtain a corresponding analog electrical signal;

[0152] An extraction unit, used to obtain the voltage value of each analog electrical signal at a plurality of preset time points by using an analog-to-digital converter, and extract the maximum voltage value as the maximum input voltage;

[0153] A first calculation unit, used for obtaining the number of quantization levels of the analog-to-digital converter, and calculating the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels;

[0154] A second calculation unit, configured to calculate a corresponding discrete quantization level index according to a ratio of each voltage value to a quantization step size;

[0155] The drawing unit is used for drawing the plurality of discrete quantization level indexes using a spectrometer to obtain a spectrum diagram.

[0156] The present invention also provides a computer device, including a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of the intelligent method for chemical composition analysis and performance prediction of mold steel when executing the computer program.

[0157] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of the intelligent method for chemical composition analysis and performance prediction of mold steel are implemented.

[0158] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided in this application and used in the embodiments may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0159] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0160] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. An intelligent method for chemical composition analysis and performance prediction of mold steel, characterized in that: include: The mold steel is excited by laser to obtain plasma; Acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals; Acquire a plurality of characteristic spectral lines according to the spectrum diagram, and acquire a corresponding actual wavelength according to each of the characteristic spectral lines; Compare each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength; Obtaining a concentration-signal intensity curve graph, and obtaining an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph; The performance characteristic evaluation values ​​of the mold steel are predicted according to the actual concentration values ​​of the multiple elements, and the mold steel is classified for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include a wear resistance performance evaluation value and a toughness performance evaluation value.

2. The intelligent method for chemical composition analysis and performance prediction of mold steel according to claim 1 is characterized in that: The step of obtaining a spectrum graph according to the plurality of spectrum signals comprises: Using a spectrometer to convert each of the spectral signals into an initial electrical signal, and amplifying each of the initial electrical signals to obtain a corresponding analog electrical signal; An analog-to-digital converter is used to obtain the voltage value of each analog electrical signal at multiple preset time points, and the maximum voltage value is extracted as the maximum input voltage; Obtaining the number of quantization levels of the analog-to-digital converter, and calculating the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels; Calculate the corresponding discrete quantization level index according to the ratio of each voltage value to the quantization step length; A spectrometer is used to plot the plurality of discrete quantization level indexes to obtain a spectrum graph.

3. The intelligent method for chemical composition analysis and performance prediction of mold steel according to claim 2 is characterized in that: The step of using a spectrometer to draw a plurality of discrete quantization level indexes to obtain a spectrum diagram comprises: The minimum wavelength and maximum wavelength of the spectrometer are obtained, and the wavelength step is calculated according to the minimum wavelength, the maximum wavelength and the discrete quantization level index, wherein the calculation formula is: Among them, B(C) represents the wavelength step, Z(D) represents the maximum wavelength, Z(X) represents the minimum wavelength, and L(J) represents the number of quantization levels; The corresponding wavelength is calculated according to the wavelength step, the minimum wavelength and a plurality of discrete quantization level indexes, wherein the calculation formula is: Where A represents the wavelength, B(C) represents the wavelength step, Z(X) represents the minimum wavelength, L(S) represents the wavelength step size, n represents the nth discrete quantization level index, n represents the sequence number of the discrete quantization level index, and m represents the number of discrete quantization level indexes; Convert each of the discrete quantization level indexes into a corresponding signal strength; The spectrum graph coordinate axis is established with wavelength as the X-axis and signal intensity as the Y-axis, and each signal intensity and corresponding wavelength of each spectral signal are plotted on the spectrum graph coordinate axis through a broken line to obtain a spectrum graph.

4. The intelligent method for chemical composition analysis and performance prediction of mold steel according to claim 1, characterized in that: The step of obtaining a plurality of characteristic spectral lines according to the spectrum diagram, and obtaining a corresponding actual wavelength according to each of the characteristic spectral lines comprises: Extracting multiple peaks of each broken line in the spectrum graph to obtain multiple characteristic spectrum lines; Sorting the plurality of characteristic spectral lines in order of magnitude to obtain a spectral line sorting table; Selecting the first characteristic spectral line from the spectral line ranking table as the detection spectral line; The corresponding actual wavelength is obtained from the spectrum diagram according to the detected spectrum line.

5. The intelligent method for chemical composition analysis and performance prediction of mold steel according to claim 1, characterized in that: The step of obtaining a concentration-signal intensity curve graph, and obtaining an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph, comprises: Obtaining the spectral signal intensity of the element corresponding to the actual wavelength at multiple preset concentrations; A concentration-signal intensity coordinate axis is established with the preset concentration as the X-axis and the spectral signal intensity as the Y-axis; Mark each preset concentration and the corresponding spectral signal intensity as a connection point on the concentration-signal intensity coordinate axis; Connecting the plurality of connection points through a curve to obtain a concentration-signal intensity curve graph; Obtaining the slope of a concentration-signal intensity curve, and obtaining the actual signal intensity according to the product of the slope of the curve and the actual wavelength; The actual signal intensity is matched with the concentration-signal intensity curve to obtain the actual concentration value of each element.

6. The intelligent method for chemical composition analysis and performance prediction of mold steel according to claim 1, characterized in that: The step of predicting the performance characteristic evaluation value of the mold steel according to the actual concentration values ​​of the multiple elements, and classifying the mold steel for use according to the performance characteristic evaluation value comprises: Obtain the weight coefficient of the actual concentration value of each element, and perform weighted calculation based on the actual concentration value of each element and the corresponding weight coefficient to obtain the overall performance score of the mold steel; Determining whether the total performance score is less than a preset performance score; If the total performance score is less than the preset performance score, it is determined that the performance of the die steel is poor; If the total performance score is not less than the preset performance score, obtaining the standard concentration range of each element; Determine whether the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is greater than a preset number; If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is greater than a preset number, it is determined that the performance of the mold steel is poor; If the number of actual concentration values ​​of multiple elements that are not within the corresponding standard concentration range is not greater than a preset number, the performance of the mold steel is determined to be good, and the actual concentration values ​​of carbon, chromium, molybdenum, nickel and manganese in the mold steel are extracted; The wear resistance evaluation value is calculated according to the actual concentration values ​​of the carbon element, the chromium element, and the molybdenum element and their corresponding weight coefficients, wherein the calculation formula is: N(X)=C*α+Cr*β+Mo*γ; Wherein, N(X) represents the wear resistance evaluation value, C represents the carbon element, α represents the weight coefficient of the carbon element, Cr represents the chromium element, β represents the weight coefficient of the chromium element, Mo represents the molybdenum element, and γ represents the weight coefficient of the molybdenum element; Determining whether the wear resistance evaluation value is greater than a first preset value; If the wear resistance evaluation value is greater than the first preset value, it is determined that the die steel is suitable for manufacturing a die-casting die; The toughness performance evaluation value is calculated according to the actual concentration values ​​of the nickel element and the manganese element and their corresponding weight coefficients, wherein the calculation formula is: R(X)=Ni*δ+Mn*ε; Wherein, R(X) represents the toughness performance evaluation value, Ni represents the nickel element, δ represents the weight coefficient of the nickel element, Mn represents the manganese element, and ε represents the weight coefficient of the manganese element; Determining whether the toughness performance evaluation value is greater than a second preset value; If the wear resistance evaluation value is greater than the second preset value, it is determined that the die steel is suitable for manufacturing cold stamping dies.

7. An intelligent system for chemical composition analysis and performance prediction of mold steel, characterized in that: include: A processing module, used for exciting the mold steel by laser to obtain plasma; A first acquisition module, used for acquiring a plurality of spectral signals of the plasma, and obtaining a spectral graph according to the plurality of spectral signals; A second acquisition module, used to acquire a plurality of characteristic spectral lines according to the spectrum diagram, and acquire a corresponding actual wavelength according to each of the characteristic spectral lines; A comparison module, used to compare each actual wavelength with an element characteristic spectrum database to obtain the element corresponding to the actual wavelength; A third acquisition module is used to obtain a concentration-signal intensity curve graph, and obtain an actual concentration value corresponding to each element according to the actual wavelength and the concentration-signal intensity curve graph; A prediction module is used to predict performance characteristic evaluation values ​​of mold steel according to actual concentration values ​​of multiple elements, and classify the mold steel for use according to the performance characteristic evaluation values, wherein the performance characteristic evaluation values ​​include wear resistance performance evaluation values ​​and toughness performance evaluation values.

8. The intelligent system for chemical composition analysis and performance prediction of mold steel according to claim 7, characterized in that: The first acquisition module includes: A conversion unit, used to convert each of the spectral signals into an initial electrical signal using a spectrometer, and amplify each of the initial electrical signals to obtain a corresponding analog electrical signal; An extraction unit, used to obtain the voltage value of each analog electrical signal at a plurality of preset time points by using an analog-to-digital converter, and extract the maximum voltage value as the maximum input voltage; A first calculation unit, used for obtaining the number of quantization levels of the analog-to-digital converter, and calculating the quantization step length according to the ratio of the maximum input voltage to the number of quantization levels; A second calculation unit, configured to calculate a corresponding discrete quantization level index according to a ratio of each voltage value to a quantization step size; The drawing unit is used for drawing the plurality of discrete quantization level indexes using a spectrometer to obtain a spectrum diagram.

9. A computer device comprising a memory and a processor, wherein the memory stores a computer program, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images