Coating component consistency analysis method and system based on infrared spectrum and multiple levels

Abstract

The invention belongs to the technical field of coating component analysis, and provides a coating component consistency analysis method and system based on an infrared spectrum and multiple levels. The method comprises the following steps: preprocessing an infrared spectrum of a to-be-detected coating sample, calculating the Pearson's correlation coefficient matching degree of the infrared spectrum and a standard spectrum, and judging whether a preliminary judgment result is passing, not passing or suspicious; acquiring the infrared spectrum of a non-passing or suspicious coating sample, and calculating the Hotelling Tstatistic and Q residual error of the infrared spectrum of the non-passing or suspicious coating sample by utilizing a corresponding class qualified principal component analysis model in the SIMCA model, so as to judge the analysis result of the coating sample; and for the coating sample which is judged to be not passed by the SIMCA model, calling the relative position of the coating sample and the qualified sample cluster on the principal component analysis score graph analyzed by the principal component analysis model, and judging the abnormal type. The coating quality control device can achieve the purpose of non-leakage, good and rapid quality control, and guarantees the reliability of coating quality.

Description

Technical Field

[0001] This invention belongs to the field of coating component analysis technology, and in particular relates to a method and system for analyzing the consistency of coating components based on infrared spectroscopy and multi-level analysis. Background Technology

[0002] The statements in this section are merely background information related to the present invention and do not necessarily constitute prior art.

[0003] In fields with high requirements for coating quality, such as the quality control of rail vehicle coatings, batch consistency of coating composition is the lifeline for ensuring key indicators such as corrosion resistance, weather resistance, and mechanical properties of the coating. Rail vehicle coatings are complex multi-component systems. In addition to the main film-forming materials (such as resins) and pigments, they also contain a variety of additives used in very small quantities but with critical effects (such as leveling agents, defoamers, and catalysts). The tiny fluctuations of these trace components (such as ±5%), although weak in the overall spectrum, are enough to cause coating defects or performance degradation.

[0004] The current methods for analyzing the consistency of coating components have the following problems: (1) The single Pearson correlation coefficient (PCC) method commonly used in the industry determines the consistency by calculating the overall similarity between the spectrum to be tested and the standard spectrum. It is sensitive to changes in the overall shape of the spectrum, but not sensitive to changes in specific trace components. It cannot effectively capture the absence or content deviation of key additives, resulting in the missed detection of quality risks. (2) The same PCC method is easily affected by non-component factors, such as the absorption of trace amounts of water in the coating sample, baseline drift during testing, or fluctuations in instrument status. These interferences can cause slight distortions in the spectrum, resulting in a significant reduction in the similarity calculation results, which can lead to the misjudgment of qualified products as unqualified products ("false detection"), resulting in unnecessary waste and production interruption. To accurately analyze trace components, it is usually necessary to use laboratory offline analysis techniques such as chromatography and mass spectrometry. These methods have complex pretreatment, long analysis cycles, and high costs, which cannot meet the needs of rapid and large-scale screening of incoming coating materials and online quality in the production site. Summary of the Invention

[0005] To address the technical problems existing in the background art, the present invention provides a method and system for analyzing the consistency of coating components based on infrared spectroscopy and multi-level analysis, which can achieve the goal of no omissions, no errors and rapid quality control, and ensure the reliability of coating quality.

[0006] To achieve the above objectives, the present invention adopts the following technical solution: The first aspect of the present invention provides a method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level analysis.

[0007] A method for analyzing the consistency of coating composition based on infrared spectroscopy and multi-level analysis includes: After preprocessing the infrared spectrum of the coating sample to be tested, the Pearson correlation coefficient matching degree between it and the standard spectrum is calculated, and the preliminary judgment result is determined as pass, fail or doubtful. The infrared spectra of unqualified or questionable paint samples are obtained. The corresponding qualified principal component analysis model in the SIMCA model is used to calculate the Hotelling T² statistic and Q residual of the infrared spectra of unqualified or questionable paint samples, and then the analysis results of the paint samples are judged. For paint samples that are deemed unqualified by the SIMCA model, their relative positions to the qualified sample clusters on the principal component analysis score map are retrieved to determine the anomaly type for root cause analysis.

[0008] As one implementation method, after the paint sample to be tested passes the Pearson correlation coefficient matching degree judgment, the paint sample that has passed the Pearson correlation coefficient matching degree judgment is analyzed again using the SIMCA model. If the analysis results of the paint samples all pass, it is determined that the paint composition is consistent.

[0009] As one implementation method, if the coating sample to be tested passes the Pearson correlation coefficient matching degree judgment, and the result of the re-analysis of the coating sample that passed the Pearson correlation coefficient matching degree judgment using the SIMCA model is not passed, the characteristic peak comparison is used for final determination. The key functional group characteristic peaks are checked to see if they are within the allowable range. If they are, the coating sample is judged to pass; otherwise, it is not passed.

[0010] As one implementation method, if the Pearson correlation coefficient matching degree is greater than or equal to the first matching degree threshold, the preliminary judgment result is considered to be passed.

[0011] As one implementation method, if the Pearson correlation coefficient matching degree is less than the second matching degree threshold, the preliminary judgment result is determined to be unsuccessful.

[0012] As one implementation method, if the Pearson correlation coefficient matching degree is between the second matching degree threshold and the first matching degree threshold, the preliminary judgment result is marked as suspicious; wherein, the first matching degree threshold is greater than the second matching degree threshold.

[0013] As one implementation method, during the SIMCA model analysis, if the Hotling T² statistic and the Q residual simultaneously satisfy: T² ≤ T²_limit and Q ≤ Q_limit, then the analysis result of the coating sample is judged to be passed; otherwise, it is judged to be failed. Here, T²_limit and Q_limit are both preset thresholds.

[0014] As one implementation method, the anomaly types include raw material deviation, foreign matter contamination, and process deviation.

[0015] A second aspect of the present invention provides a coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis.

[0016] A coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis includes: The preliminary judgment module is used to preprocess the infrared spectrum of the coating sample to be tested, calculate the matching degree of its Pearson correlation coefficient with the standard spectrum, and judge the preliminary judgment result as pass, fail or doubtful. The precise judgment module is used to obtain the infrared spectra of unqualified or questionable paint samples. Using the corresponding qualified principal component analysis model in the SIMCA model, it calculates the Hotelling T² statistic and Q residual of the infrared spectra of unqualified or questionable paint samples, and then judges the analysis results of the paint samples. The root cause analysis module is used to retrieve the relative position of the principal component analysis score plot of the principal component analysis model to the cluster of qualified samples for paint samples that are deemed unqualified by the SIMCA model, and to determine the anomaly type for root cause analysis.

[0017] As one implementation method, the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis also includes: The final decision module is used to re-analyze the paint samples that have passed the Pearson correlation coefficient matching test after the paint samples have passed the Pearson correlation coefficient matching test. If the analysis results of the paint samples all pass, it is determined that the paint composition is consistent.

[0018] As one implementation method, the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis also includes: The final adjudication module is used to make a final adjudication when the paint sample that passed the Pearson correlation coefficient matching test fails the re-analysis of the paint sample using the SIMCA model. The module uses characteristic peak comparison to check whether the characteristic peaks of key functional groups are within the allowable range. If they are, the paint sample is judged to have passed; otherwise, it fails.

[0019] A third aspect of the present invention provides a computer-readable storage medium.

[0020] A computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level composition.

[0021] A fourth aspect of the present invention provides a computer program product.

[0022] A computer program product includes a computer program / instructions that, when executed by a processor, implement the steps in the above-described method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level composition.

[0023] A fifth aspect of the present invention provides an electronic device.

[0024] An electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the steps in the above-described method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level composition.

[0025] Compared with the prior art, the beneficial effects of the present invention are: (1) This invention provides a method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level analysis. It combines the Pearson correlation coefficient method, SIMCA model analysis method and principal component analysis method using the infrared spectrum of the coating sample to be tested. It makes a preliminary judgment by using the matching degree of the Pearson correlation coefficient between the infrared spectrum of the coating sample to be tested and the standard spectrum. Then, it uses the SIMCA model to make a precise judgment on the infrared spectrum of the coating sample that is initially judged as failing or suspicious. For the coating sample that is judged as failing by the SIMCA model, it retrieves the relative position of the principal component analysis score map of the principal component analysis model with the qualified sample cluster, judges the anomaly type and performs root cause analysis, thus achieving the goal of no omissions, no errors and rapid quality control, and ensuring the reliability of coating quality.

[0026] (2) After the coating sample to be tested passes the Pearson correlation coefficient matching degree judgment, the coating sample that has passed the Pearson correlation coefficient matching degree judgment is analyzed again using the SIMCA model. When the two results are inconsistent, the comparison of the characteristic peaks of key functional groups is used as the final decision rule, which improves the accuracy of the coating composition consistency analysis results.

[0027] Advantages of additional aspects of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. Attached Figure Description

[0028] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an improper limitation of the invention.

[0029] Figure 1 This is a flowchart of the coating composition consistency analysis method based on infrared spectroscopy and multi-level analysis according to an embodiment of the present invention. Figure 2 This is a schematic diagram of the structure of the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis according to an embodiment of the present invention; Figure 3 This is a schematic diagram of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0030] The present invention will be further described below with reference to the accompanying drawings and embodiments.

[0031] It should be noted that the following detailed description is illustrative and intended to provide further explanation of the invention. Unless otherwise specified, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention pertains.

[0032] It should be noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit the scope of exemplary embodiments according to the invention. As used herein, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. Furthermore, it should be understood that when the terms "comprising" and / or "including" are used in this specification, they indicate the presence of features, steps, operations, devices, components, and / or combinations thereof.

[0033] Terminology Explanation: SIMCA (Soft Independent Modeling of Class Analogy) is a classification modeling method based on multivariate statistical analysis. Its core idea is to build a principal component model for each class and achieve classification by comparing the goodness of fit of new samples in each model.

[0034] The core principle and process of the SIMCA model: This model is based on principal component analysis (PCA). It constructs a separate principal component model for each known category to capture the inherent variation pattern of samples in that category. For a new sample, it calculates the DModX statistic (distance model) in each category model, which is the deviation between the sample and the model space. If the DModX value exceeds the preset confidence interval (such as 95%), it is determined that the sample does not belong to that category.

[0035] Figure 1 A schematic diagram of the principle of the coating composition consistency analysis method based on infrared spectroscopy and multi-level analysis according to an embodiment of the present invention is provided. Figure 1 The method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level layers in this embodiment may include the following steps S101 to S103.

[0036] The specific implementation process of steps S101 to S103 is as follows: Step S101: After preprocessing the infrared spectrum of the coating sample to be tested, calculate its Pearson correlation coefficient matching degree with the standard spectrum, and determine the preliminary judgment result as pass, fail or doubtful.

[0037] The preprocessing here includes interference or noise preprocessing, and the processes are all existing methods, which will not be described in detail here.

[0038] The Pearson correlation coefficient matching degree can be calculated by comparing the infrared spectrum of the pretreated coating sample with the standard spectrum using the formula for calculating the Pearson correlation coefficient.

[0039] If the Pearson correlation coefficient matching degree is greater than or equal to the first matching degree threshold (such as 95%, which can be set according to the actual situation), then the preliminary judgment result is considered to be passed.

[0040] If the Pearson correlation coefficient matching degree is less than the second matching degree threshold (e.g., 85%, which can be set according to the actual situation), then the preliminary judgment result is not passed.

[0041] If the Pearson correlation coefficient matches between the second matching threshold (e.g., 85%, which can be set according to the actual situation) and the first matching threshold (e.g., 95%, which can be set according to the actual situation), the preliminary judgment result is marked as suspicious; where the first matching threshold is greater than the second matching threshold.

[0042] The Pearson correlation coefficient can be used to quickly screen paint samples for testing. Paint samples that pass the preliminary judgment can be released directly, which can improve the efficiency of paint sample analysis.

[0043] Step S102: Obtain the infrared spectrum of the failed or questionable paint sample, and use the corresponding qualified principal component analysis model in the SIMCA model to calculate the Hotelling T² statistic and Q residual of the infrared spectrum of the failed or questionable paint sample, and then judge the analysis result of the paint sample.

[0044] Specifically, in the SIMCA model analysis process, if the Hotling T² statistic and Q residual simultaneously satisfy: T² ≤ T²_limit and Q ≤ Q_limit, then the analysis result of the coating sample is judged to be passed; otherwise, it is judged to be failed. Here, T²_limit and Q_limit are both preset thresholds.

[0045] The T²_limit and Q_limit here can be set according to the actual situation or the corresponding coating sample type, which will not be described in detail here.

[0046] It should be noted that the SIMCA model and principal component analysis model are existing models, and the process of calculating the Hotelling T² statistic and Q residuals of the infrared spectrum is a current technique.

[0047] Step S103: For paint samples that are deemed unqualified by the SIMCA model, retrieve the relative position of the principal component analysis score plot with the qualified sample cluster from the principal component analysis model to determine the anomaly type for root cause analysis. This provides direct clues for quality problem investigation.

[0048] Among these, abnormal types include, but are not limited to, raw material deviation, foreign matter contamination, and process deviation.

[0049] In other embodiments, after the paint sample to be tested passes the Pearson correlation coefficient matching degree judgment, the paint sample that passed the Pearson correlation coefficient matching degree judgment is analyzed again using the SIMCA model. If the analysis results of the paint sample are all passed, it is determined that the paint composition is consistent.

[0050] In other embodiments, if the paint sample to be tested passes the Pearson correlation coefficient matching degree test, and the result of the re-analysis of the paint sample that passed the Pearson correlation coefficient matching degree test using the SIMCA model is not passing, the characteristic peak comparison is used for final decision-making. The key functional group characteristic peaks are checked to see if they are within the allowable range. If they are, the paint sample is judged to pass; otherwise, it is not passed.

[0051] This approach improves the accuracy of coating composition consistency analysis results by using the comparison of key functional group characteristic peaks as the final decision when the Pearson correlation coefficient matching result of the tested coating sample is inconsistent with the SIMCA model analysis result.

[0052] It should be noted that the database stores the standard spectra, principal component analysis models, and statistical control limits of various qualified coatings.

[0053] This invention employs the SIMCA classification method to establish an independent statistical fingerprint model for each type of qualified coating. This model is insensitive to normal fluctuations between qualified batches, but is extremely sensitive to abnormal chemical components (such as the absence or imbalance of key additives) that exceed the model's range. It can reliably detect trace component deviations that traditional PCC methods cannot detect, intercepting potential quality risks caused by minor component changes at the source and significantly reducing the false negative rate.

[0054] This invention employs a dual-judgment logic of "rapid initial screening using PCC (Pearson correlation coefficient) + validation using the SIMCA model" to effectively distinguish between actual changes in composition and interference from testing conditions. The SIMCA model focuses on the structural assignment of the spectrum in chemical space, rather than the overall amplitude, thus avoiding misleading information from common interferences such as moisture peaks and baseline drift. This significantly reduces misjudgments caused by non-compositional factors, preventing production delays and economic losses due to the unwarranted rejection of qualified raw materials.

[0055] This invention innovatively implements intelligent resource allocation in a three-tiered process. The vast majority (approximately 85%) of clearly qualified samples are released within seconds using PCC (Precision Process Control); precise SIMCA analysis is initiated only for a small number (approximately 10%-15%) of boundary samples; and PCA root cause diagnosis is performed only on samples confirmed to be abnormal. In this way, without sacrificing accuracy, and even significantly improving accuracy, the overall analytical efficiency is raised to a level that supports online quality control, resolving the inherent contradiction of high-precision methods being inherently high-cost.

[0056] The infrared spectroscopy-based, multi-level coating composition consistency analysis method of this invention achieves the quality control goal of "no omissions, no errors, and rapid" for the first time in the field of coating composition consistency determination, providing unprecedented technical assurance for the reliability of coating quality in high-requirement industries such as rail vehicles.

[0057] like Figure 2 As shown, the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis provided in this embodiment of the invention can be implemented in software. The coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis includes the following software modules: preliminary judgment module 201, precise judgment module 202, and root cause analysis module 203.

[0058] The functions of each software module in the infrared spectroscopy-based, multi-level coating composition consistency analysis system are described below: The preliminary judgment module 201 is used to preprocess the infrared spectrum of the coating sample to be tested, calculate the matching degree of its Pearson correlation coefficient with the standard spectrum, and judge the preliminary judgment result as pass, fail or doubtful. The precise judgment module 202 is used to obtain the infrared spectrum of the unqualified or suspicious paint samples, and use the principal component analysis model of the corresponding category in the SIMCA model to calculate the Hotelling T² statistic and Q residual of the infrared spectrum of the unqualified or suspicious paint samples, and then judge the analysis results of the paint samples. The root cause analysis module 203 is used to retrieve the relative position of the principal component analysis score map of the principal component analysis model to the qualified sample cluster for paint samples that are determined to fail by the SIMCA model, and to determine the anomaly type for root cause analysis.

[0059] In other embodiments, the infrared spectroscopy-based, multi-level coating composition consistency analysis system further includes: The final decision module is used to re-analyze the paint samples that have passed the Pearson correlation coefficient matching test after the paint samples have passed the Pearson correlation coefficient matching test. If the analysis results of the paint samples all pass, it is determined that the paint composition is consistent.

[0060] In other embodiments, the infrared spectroscopy-based, multi-level coating composition consistency analysis system further includes: The final adjudication module is used to make a final adjudication when the paint sample that passed the Pearson correlation coefficient matching test fails the re-analysis of the paint sample using the SIMCA model. The module uses characteristic peak comparison to check whether the characteristic peaks of key functional groups are within the allowable range. If they are, the paint sample is judged to have passed; otherwise, it fails.

[0061] It should be noted that each module in the infrared spectroscopy-based multi-level coating composition consistency analysis system of the present invention corresponds one-to-one with each step in the infrared spectroscopy-based multi-level coating composition consistency analysis method in the above embodiments, and their specific implementation processes are the same, so they will not be repeated here.

[0062] The structure of the electronic device according to an embodiment of the present invention will be described in detail below. Figure 3 This is a schematic diagram of the composition structure of an electronic device provided in an embodiment of the present invention. It can be understood that... Figure 3 The diagram shows only an exemplary structure of the electronic device, not the entire structure. Some or all of the structures shown may be implemented as needed.

[0063] The electronic device provided in this embodiment of the invention includes: at least one processor 301, a memory 302, a user interface 303, and at least one network interface 304. The various components in the infrared spectroscopy-based multi-level coating composition consistency analysis system are coupled together via a bus system 305. It can be understood that the bus system 305 is used to realize the connection and communication between these components. In addition to a data bus, the bus system 305 also includes a power bus, a control bus, and a status signal bus. However, for clarity, in... Figure 3 The general designated all buses as Bus System 305.

[0064] The user interface 303 may include a monitor, keyboard, mouse, trackball, click wheel, buttons, touchpad, or touch screen.

[0065] It is understood that memory 302 can be volatile memory or non-volatile memory, or both. In this embodiment of the invention, memory 302 is capable of storing data to support the operation of the terminal. Examples of this data include any computer programs used to operate on the terminal, such as operating systems and applications. The operating system includes various system programs, such as framework layers, core library layers, driver layers, etc., used to implement various basic services and handle hardware-based tasks. Applications can include various applications.

[0066] In some embodiments, the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis provided in this invention can be implemented using a combination of hardware and software. For example, the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis provided in this invention can be a processor in the form of a hardware decoding processor, programmed to execute the coating composition consistency analysis method based on infrared spectroscopy and multi-level analysis provided in this invention. For instance, the processor in the form of a hardware decoding processor can employ one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components.

[0067] As an example, processor 301 can be an integrated circuit chip with signal processing capabilities, such as a general-purpose processor, a digital signal processor (DSP), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc., wherein the general-purpose processor can be a microprocessor or any conventional processor, etc.

[0068] As an example of the hardware implementation of the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis provided in this embodiment of the invention, the device provided in this embodiment of the invention can be directly executed by a processor 301 in the form of a hardware decoding processor. For example, it can be executed by one or more application-specific integrated circuits (ASICs), DSPs, programmable logic devices (PLDs), complex programmable logic devices (CPLDs), field-programmable gate arrays (FPGAs), or other electronic components to implement the coating composition consistency analysis method based on infrared spectroscopy and multi-level analysis provided in this embodiment of the invention.

[0069] The memory 302 in this embodiment of the invention is used to store various types of data to support the operation of the coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis, or to store data for execution. Figure 1The program code for the method shown. Examples of this data include: any executable instructions for operation on an infrared spectroscopy-based and multi-level coating composition consistency analysis system, such as executable instructions that can be included in the executable instructions to implement the infrared spectroscopy-based and multi-level coating composition consistency analysis method of the embodiments of the present invention.

[0070] Specifically, according to embodiments of this application, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of this application include a computer program product comprising a computer program carried on a computer-readable medium, the computer program including functions for executing... Figure 1 The program code for the method shown. In such an embodiment, the computer program can be downloaded and installed from a network via a communication component, and / or installed from a removable medium. When the computer program is executed by the central processing unit, it performs the various functions defined in the apparatus of this application.

[0071] This invention is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, as well as combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart. Figure 1 One or more processes and / or boxes Figure 1 Figure 1 A device that provides the functions specified in one or more boxes.

[0072] The above are merely preferred embodiments of the present invention and are not intended to limit the present invention. Various modifications and variations can be made to the present invention by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. A method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level analysis, characterized in that, include: After preprocessing the infrared spectrum of the coating sample to be tested, the Pearson correlation coefficient matching degree between it and the standard spectrum is calculated, and the preliminary judgment result is determined as pass, fail or doubtful. Infrared spectra of failed or questionable paint samples are obtained. Principal component analysis models of the corresponding categories in the SIMCA model are used to calculate the Hotelling T² statistic and Q residual of the infrared spectra of failed or questionable paint samples, thereby determining the analysis results of the paint samples. For paint samples that are deemed unqualified by the SIMCA model, their relative positions to the qualified sample clusters on the principal component analysis score map are retrieved to determine the anomaly type for root cause analysis.

2. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, After the paint sample to be tested passes the Pearson correlation coefficient matching degree judgment, the paint sample that passed the Pearson correlation coefficient matching degree judgment is analyzed again using the SIMCA model. If the analysis results of the paint sample all pass, it is determined that the paint composition is consistent.

3. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, If a coating sample passes the Pearson correlation coefficient matching test, and the result of a re-analysis of the coating sample that passed the Pearson correlation coefficient matching test using the SIMCA model is negative, then a final decision is made by comparing characteristic peaks. The key functional group characteristic peaks are checked to see if they are within the allowable range. If they are, the coating sample is judged to have passed; otherwise, it is judged to have failed.

4. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, If the Pearson correlation coefficient matching degree is greater than or equal to the first matching degree threshold, then the preliminary judgment result is considered as passing.

5. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, If the Pearson correlation coefficient matching degree is less than the second matching degree threshold, the preliminary judgment result is "not passed".

6. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, If the Pearson correlation coefficient matches between the second matching threshold and the first matching threshold, the preliminary judgment result is marked as suspicious; where the first matching threshold is greater than the second matching threshold.

7. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, During the SIMCA model analysis, if the Hotling T² statistic and Q residual simultaneously satisfy: T² ≤ T²_limit and Q ≤ Q_limit, then the analysis result of the coating sample is considered to be passed; otherwise, it is considered to be failed. Here, T²_limit and Q_limit are both preset thresholds.

8. The method for detecting the cross-sectional dimensions of a material as described in claim 1, characterized in that, The types of anomalies include raw material deviation, foreign matter contamination, and process deviation.

9. A coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis, characterized in that, include: The preliminary judgment module is used to preprocess the infrared spectrum of the coating sample to be tested, calculate the matching degree of its Pearson correlation coefficient with the standard spectrum, and judge the preliminary judgment result as pass, fail or doubtful. The precise judgment module is used to obtain the infrared spectra of unqualified or questionable paint samples. Using the corresponding qualified principal component analysis model in the SIMCA model, it calculates the Hotelling T² statistic and Q residual of the infrared spectra of unqualified or questionable paint samples, and then judges the analysis results of the paint samples. The root cause analysis module is used to retrieve the relative position of the principal component analysis score plot of the principal component analysis model to the cluster of qualified samples for paint samples that are deemed unqualified by the SIMCA model, and to determine the anomaly type for root cause analysis.

10. The coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis as described in claim 9, characterized in that, Also includes: The final decision module is used to re-analyze the paint samples that have passed the Pearson correlation coefficient matching test after the paint samples have passed the Pearson correlation coefficient matching test. If the analysis results of the paint samples all pass, it is determined that the paint composition is consistent.

11. The coating composition consistency analysis system based on infrared spectroscopy and multi-level analysis as described in claim 9, characterized in that, Also includes: The final adjudication module is used to make a final adjudication when the paint sample that passed the Pearson correlation coefficient matching test fails the re-analysis of the paint sample using the SIMCA model. The module uses characteristic peak comparison to check whether the characteristic peaks of key functional groups are within the allowable range. If they are, the paint sample is judged to have passed; otherwise, it fails.

12. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the steps in the method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level as described in any one of claims 1-8.

13. A computer program product comprising a computer program / instructions, characterized in that, When the computer program / instructions are executed by the processor, they implement the steps in the method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level as described in any one of claims 1-8.

14. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the steps in the method for analyzing the consistency of coating components based on infrared spectroscopy and multi-level as described in any one of claims 1-8.

Images