An asphalt homology recognition method and device based on infrared spectrum, an electronic device, and a storage medium

Abstract

The present application relates to a kind of based on infrared spectrum's asphalt homology identification method, including the infrared spectrum curve of collection parent sample asphalt and the asphalt to be identified, division full wave number spectral interval, fingerprint area spectral interval, characteristic peak spectral interval, calculate similarity judgment parameter and similarity score, judge the homology of the asphalt to be identified.The present application also relates to a kind of based on infrared spectrum's asphalt homology identification device, including acquisition, processing, calculation, first judgment, second judgment module.The present application also relates to an electronic device and storage medium.Using the present application design a kind of based on infrared spectrum's asphalt homology identification method, device, electronic device and storage medium, can solve the problem that the existing asphalt homology identification method is often difficult to give consideration to the comprehensive analysis of whole spectrum characteristics and local characteristics when processing complex asphalt sample, leading to insufficient recognition accuracy, or rely on complex element content determination process, difficult to meet the actual needs of rapid detection.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of material evaluation, and in particular to an asphalt homology recognition method and device based on infrared spectroscopy, an electronic device, and a storage medium. BACKGROUND

[0002] As an important building material, the homology recognition of asphalt is of great significance in product quality control, brand traceability, and performance evaluation. Infrared spectroscopy technology is widely used in asphalt analysis due to its efficiency and non-destructive characteristics. However, with the rapid development of asphalt production technology, existing asphalt homology recognition methods often fail to balance the comprehensive analysis of full-spectrum characteristics and local characteristics when dealing with complex asphalt samples, resulting in insufficient recognition accuracy or reliance on complex element content determination processes, making it difficult to meet the actual needs of rapid detection.

[0003] Therefore, the prior art has defects and needs to be improved and developed. SUMMARY

[0004] The present application provides an asphalt homology recognition method and device based on infrared spectroscopy, an electronic device, and a storage medium, which solves the problem that the existing asphalt homology recognition method often fails to balance the comprehensive analysis of full-spectrum characteristics and local characteristics when dealing with complex asphalt samples, resulting in insufficient recognition accuracy or reliance on complex element content determination processes, making it difficult to meet the actual needs of rapid detection.

[0005] In a first aspect of the present application, an asphalt homology recognition method based on infrared spectroscopy is provided, comprising:

[0006] Collecting a first infrared spectrum curve of a parent asphalt sample and a second infrared spectrum curve of an asphalt sample to be identified;

[0007] According to the wave number range of the infrared spectrum, the first infrared spectrum curve and the second infrared spectrum curve are divided to obtain a full-wave number spectrum interval, a fingerprint region spectrum interval, and a characteristic peak spectrum interval;

[0008] According to the full-wave number spectrum interval, the fingerprint region spectrum interval, and the characteristic peak spectrum interval, a similarity judgment parameter is calculated, which at least includes a Pearson correlation coefficient of the full-wave number spectrum interval , a Pearson correlation coefficient of the fingerprint region spectrum interval , a Pearson correlation coefficient of the Mth characteristic peak spectrum interval in the M characteristic peak spectrum intervals , a Euclidean distance of the full-wave number spectrum interval , a normalized root mean square error of the fingerprint region spectrum interval , and the Mth characteristic peak spectrum interval in the M characteristic peak spectrum intervals ​Normalized root mean square error of the characteristic peak spectral interval , the number of unqualified characteristic peaks; wherein, =1, 2, …, M;

[0009] According to the similarity judgment parameter, it is judged whether the to-be-identified asphalt is qualified or not, and if it is qualified, the similarity score is calculated according to the similarity judgment parameter ; otherwise, it is determined that the to-be-identified asphalt is not of the same source as the parent sample asphalt, and the judgment method comprises: >0.99, <1, <0.05, and the number of unqualified characteristic peaks is ≤ , the asphalt represented by the infrared spectrum curve is qualified, and the similarity score is calculated ; when >0.99, <1, <0.05, and the number of unqualified characteristic peaks is ≤ , any one of the conditions is not met, and it is determined that the unqualified asphalt is not of the same source as the parent sample asphalt; wherein, when the asphalt is base asphalt, the value of is 1, and when the asphalt is modified asphalt, the value of is 2; the similarity score is calculated according to the similarity judgment parameter , and the calculation formula of the similarity score is ; wherein, , , , is a weight coefficient;

[0010] According to the similarity score and the similarity threshold , the homogeneity of the to-be-identified asphalt is judged, and if > , the to-be-identified asphalt is of the same source as the parent sample asphalt; otherwise, it is not of the same source.

[0011] Further, the first infrared spectrum curve and the second infrared spectrum curve are divided according to the wave number range of the infrared spectrum, and the full wave number spectral interval, the fingerprint region spectral interval, and the characteristic peak spectral interval are obtained, which comprises:

[0012] The interval with an effective wave number range of 4000~600cm -1 is divided into the full wave number spectral interval;

[0013] The interval with an effective wave number range of 1500~600cm -1 is divided into the fingerprint region spectral interval;

[0014] The effective wavenumber range is set at 25 cm to the left and right of the characteristic peak. -1 The interval is divided into the characteristic peak spectral interval.

[0015] Furthermore, the similarity judgment parameters are calculated based on the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range. These similarity judgment parameters include at least the Pearson correlation coefficient for the full wavenumber spectral range. Pearson correlation coefficient of fingerprint spectral range The first of the M characteristic peak spectral intervals Pearson correlation coefficient for each characteristic peak spectral interval Euclidean distance across the entire wavenumber spectral range Normalized root mean square error of the fingerprint region spectral range The first of the M characteristic peak spectral intervals Normalized root mean square error of the spectral range of each characteristic peak The number of unqualified characteristic peaks; among which, =1,2,...,M, including:

[0016] Pearson correlation coefficient The calculation formula is ;in, To calculate the x-coordinate within the interval The vertical axis value corresponding to the first infrared spectrum curve at that time. To calculate the x-coordinate within the interval The value of the ordinate corresponding to the second infrared spectrum curve at that time. To calculate the average value of all ordinate values ​​in the first infrared spectrum curve within the interval, To calculate the average of all ordinate values ​​in the second infrared spectrum within the interval; based on the Pearson correlation coefficient... The calculation formulas are used to calculate the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range, respectively. , , ;

[0017] Euclidean distance across the entire wavenumber spectral range The calculation formula is ;

[0018] Normalized root mean square error The calculation formula is ;in, , The sample size; based on the normalized root mean square error The calculation formula is used to calculate the fingerprint region spectral range. Calculate the first characteristic peak spectral range. Characteristic peaks Wherein, when calculating in the spectral range of the fingerprint region hour, The total number of coordinate points selected in the spectral range of the fingerprint region, when calculating the first point in the spectral range of the characteristic peak. Characteristic peaks hour, This represents the total number of coordinate points within the spectral range of the characteristic peak.

[0019] The number of unqualified characteristic peaks in the characteristic peak spectral range is calculated by subtracting the total number of qualified characteristic peaks from the total number of characteristic peaks, where the total number of qualified characteristic peaks is the number of peaks that satisfy the condition... >0.99 and The sum of the number of characteristic peaks under the condition <0.15.

[0020] Furthermore, , , , The values ​​are 0.35, 0.15, 0.25, and 0.25, respectively.

[0021] Furthermore, the method based on similarity scores... and similarity threshold To determine the homology of the asphalt to be identified, if > If the asphalt to be identified is of the same origin as the parent sample asphalt, then it is of different origin, including:

[0022] When the asphalt is base asphalt The value is 0.97 when the asphalt is modified asphalt. The value is 0.96.

[0023] A second aspect of the present invention provides a device for identifying the homology of asphalt based on infrared spectroscopy, comprising:

[0024] The acquisition module is used to acquire the first infrared spectrum curve of the parent sample asphalt and the second infrared spectrum curve of the asphalt to be identified;

[0025] The processing module is used to divide the first infrared spectrum curve and the second infrared spectrum curve according to the wavenumber range of the infrared spectrum to obtain the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range.

[0026] The calculation module is used to calculate similarity judgment parameters based on the full wavenumber spectral interval, the fingerprint region spectral interval, and the characteristic peak spectral interval. The similarity judgment parameters include at least the Pearson correlation coefficient for the full wavenumber spectral interval. Pearson correlation coefficient of the fingerprint region spectral interval Pearson correlation coefficient of the M characteristic peak spectral interval Pearson correlation coefficient of the M characteristic peak spectral interval Euclidean distance of the full-wave spectral interval Normalized root mean square error of the fingerprint region spectral interval Normalized root mean square error of the M characteristic peak spectral interval Normalized root mean square error of the M characteristic peak spectral interval Number of unqualified characteristic peaks; wherein, =1, 2, …, M;

[0027] The first judging module is configured to determine whether the to-be-identified asphalt is qualified according to the similarity judgment parameters, and if so, to calculate a similarity score according to the similarity judgment parameters ; otherwise, it is determined that the to-be-identified asphalt is not of the same source as the parent sample asphalt, and the determination method comprises: when >0.99, <1, <0.05, and the number of unqualified characteristic peaks is ≤ , the asphalt represented by the infrared spectrum curve is qualified, and the similarity score is calculated ; when >0.99, <1, <0.05, and the number of unqualified characteristic peaks is ≤ , it is determined that the unqualified asphalt is not of the same source as the parent sample asphalt; wherein, when the asphalt is base asphalt, the value of is 1, and when the asphalt is modified asphalt, the value of is 2; the similarity score is calculated according to the similarity judgment parameters , and the calculation formula of the similarity score is ; wherein, , , , is a weight coefficient;

[0028] The second judging module is configured to determine the homogeneity of the to-be-identified asphalt according to the similarity score and a similarity threshold ; if > , the to-be-identified asphalt is of the same source as the parent sample asphalt; otherwise, it is not of the same source.

[0029] In a third aspect, the present invention provides an electronic device, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the electronic device implements the aforementioned method for identifying asphalt homology based on infrared spectroscopy.

[0030] In a fourth aspect, the present invention provides a computer-readable storage medium for storing a computer program that, when run on a computer, causes the computer to execute the aforementioned method for identifying asphalt homology based on infrared spectroscopy.

[0031] Beneficial effects:

[0032] As can be seen from the above technical solutions, the present invention provides a method for identifying the homology of asphalt based on infrared spectroscopy, which has the following beneficial effects:

[0033] 1. Improve the speed and stability of asphalt homology identification: Divide the infrared spectrum into intervals according to the effective wavenumber range and calculate similarity judgment parameters. By performing multi-level division of the infrared spectrum of asphalt and selecting multiple indicators, it is possible to identify the similarity based on the Pearson correlation coefficient across the entire wavenumber spectral range. Euclidean distance across the entire wavenumber spectral range Simultaneously capturing the consistency of baseline shape and amplitude within the same judgment process enables the use of Pearson correlation coefficients based on the spectral range of the fingerprint region. Normalized root mean square error of the fingerprint region spectral range The ability to identify sensitive differences in fingerprint region spectral shape is based on the characteristic peak spectral interval. Normalized root mean square error of each characteristic peak The number of unqualified characteristic peaks in the characteristic peak spectral range is used to identify the changes in common high wavenumber key peaks in modified asphalt systems. By using interval division and similarity judgment parameters, information loss caused by relying on a single region or single indicator is avoided, thereby maintaining rapid identification and stability of asphalt under complex formulations or different process batches.

[0034] 2. Improve the accuracy of asphalt homology judgment: Design a multi-level judgment process, including judging the compliance status of the asphalt to be identified and the comparison of similarity scores. The judgment is based on the similarity judgment parameters obtained by infrared spectral curves. It can perform multi-level judgment in a short time, speed up the judgment process, reduce the risk of misjudgment, and improve the accuracy of the judgment results.

[0035] 3. Improve the applicability of asphalt homology assessment: Considering both base asphalt and modified asphalt, by... The value, The numerical values are distinguished to provide a basis for judging different bitumens while maintaining the strictness of the judgment process. By setting different parameter values, the fault tolerance of the judgment is improved, avoiding being mistakenly rejected, thus better meeting the homogeneity judgment needs in actual production and formula fluctuation scenarios, and improving the applicability of bitumen homogeneity judgment.

[0036] 4. Improved implementability of bitumen homogeneity identification: By selecting the to-be-identified bitumen and the parent sample bitumen for judgment, each new bitumen is identified separately and sequentially by running the method, which can be directly embedded in the on-site screening process and production quality control system. Compared with the prior art, the dependence on complex element content determination and high complexity model training is reduced, the response speed of identification is improved, and the maintenance controllability is improved, which is suitable for actual engineering needs.

[0037] It should be understood that all combinations of the aforementioned concepts and additional concepts described in greater detail below can be seen as part of the subject matter of the present disclosure as long as such concepts are not mutually contradictory in terms of their meaning.

[0038] The foregoing and other aspects, embodiments and features of the present teachings can be more fully understood from the following description taken in conjunction with the accompanying drawings. Other aspects, embodiments and features of the present teachings will be apparent from the description that follows, and from the claims. BRIEF DESCRIPTION OF DRAWINGS

[0039] The drawings are not drawn to true scale. In the drawings, like reference numerals can be used to denote like parts throughout the various views. For the sake of clarity, not every component can be labeled in every drawing. There will now be described, by way of example only, embodiments of various aspects of the application with reference to the accompanying drawings in which:

[0040] Figure 1 A general flowchart of a bitumen homogeneity identification method based on infrared spectroscopy in an embodiment of the present application.

[0041] Figure 2 A table of characteristic peak positions (center wave numbers) and corresponding components of matrix bitumen in an embodiment of the present application.

[0042] Figure 3 A table of characteristic peak positions (center wave numbers) and corresponding components of modified bitumen in an embodiment of the present application.

[0043] Figure 4 A distribution graph of infrared spectroscopy and identification results of Experiment 1 in an embodiment of the present application.

[0044] Figure 5 A distribution graph of infrared spectroscopy and identification results of Experiment 2 in an embodiment of the present application.

[0045] Figure 6 The distribution diagram and identification result of the infrared spectrum of Experiment 3 in the embodiment of the present application.

[0046] Figure 7 The distribution diagram and identification result of the infrared spectrum of Experiment 4 in the embodiment of the present application.

[0047] Figure 8 The schematic diagram of the electronic device of the embodiment of the present application. DETAILED DESCRIPTION

[0048] In order to make the purpose, technical scheme and advantages of the embodiments of the present application clearer, the technical scheme of the embodiments of the present application will be described clearly and completely below with reference to the drawings of the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, rather than all the embodiments of the present application. Based on the described embodiments of the present application, all other embodiments obtained by those of ordinary skill in the art without any creative effort belong to the scope of protection of the present application. Unless otherwise defined, the technical terms or scientific terms used herein should have the usual meaning understood by those of ordinary skill in the art to which the present application belongs.

[0049] The terms “first”, “second”, and similar terms used in the patent application specification and claims of the present application do not represent any order, quantity, or importance, but are only used to distinguish different components. Similarly, unless the context clearly indicates otherwise, the singular forms “one”, “an”, or “the” and the like do not represent a quantity limitation, but represent the existence of at least one. The terms “include” or “contain” and the like mean that the elements or objects appearing before “include” or “contain” cover the features, whole, steps, operations, elements, and / or components listed after “include” or “contain”, and do not exclude the existence or addition of one or more other features, whole, steps, operations, elements, components, and / or sets thereof. “Up”, “down”, “left”, “right”, and the like are only used to represent relative positional relationships, and when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0050] In the prior art, due to the fact that the existing asphalt homogeneity identification method is difficult to comprehensively analyze the global features and local features when processing complex asphalt samples, the identification accuracy is insufficient, or it relies on a complex element content determination process, and it is difficult to meet the actual needs of rapid detection.

[0051] In view of this, the embodiments of the present application provide an asphalt homogeneity identification method based on infrared spectrum, with reference to Figure 1 , comprising:

[0052] Step S102: Collect the first infrared spectrum curve of the parent sample asphalt and the second infrared spectrum curve of the asphalt to be identified.

[0053] Step S104: Divide the first infrared spectrum curve and the second infrared spectrum curve according to the wavenumber range of the infrared spectrum to obtain the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range.

[0054] Step S106: Calculate similarity judgment parameters based on the full wavenumber spectral range, fingerprint region spectral range, and characteristic peak spectral range. The similarity judgment parameters shall include at least the Pearson correlation coefficient for the full wavenumber spectral range. Pearson correlation coefficient of fingerprint spectral range The first of the M characteristic peak spectral intervals Pearson correlation coefficient for each characteristic peak spectral interval Euclidean distance across the entire wavenumber spectral range Normalized root mean square error of the fingerprint region spectral range The first of the M characteristic peak spectral intervals Normalized root mean square error of the spectral range of each characteristic peak The number of unqualified characteristic peaks; among which, =1,2,…,M.

[0055] Step S108: Determine whether the asphalt to be identified meets the standard based on the similarity judgment parameters. If it meets the standard, calculate the similarity score based on the similarity judgment parameters. Otherwise, the asphalt to be identified is determined to be from a different source than the parent sample asphalt.

[0056] Step S110: Based on similarity score and similarity threshold To determine the homology of the asphalt to be identified, if > If the asphalt to be identified is of the same origin as the parent sample asphalt, then it is of different origin; otherwise, it is of different origin.

[0057] By dividing the infrared spectrum into intervals, calculating similarity judgment parameters, and using these parameters for judgment, rapid homology determination is achieved, balancing accuracy and timeliness in homology identification. Interval division and unified sampling ensure that the infrared spectra comparison between the asphalt to be identified and the parent asphalt sample have the same metric basis. Parallel calculation of multiple indicators characterizes differences in shape, amplitude, and local peaks within the same framework. Finally, identification is performed using a two-level judgment, which is beneficial for batch testing in practical engineering and maintaining judgment stability because each step has traceable intermediate values. It also facilitates traceability and verification within the quality system.

[0058] In some embodiments, the first infrared spectral curve and the second infrared spectral curve are divided according to the wavenumber range of the infrared spectrum to obtain the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range, including:

[0059] The effective wavenumber range is 4000~600cm. -1 The effective wavenumber range is divided into the full wavenumber spectral range. The effective wavenumber range is 1500–600 cm⁻¹. -1 The spectral range is divided into fingerprint region ranges. The effective wavenumber range is defined as 25 cm to the left and right of the characteristic peak position. -1 The interval is divided into the characteristic peak spectral interval.

[0060] The fingerprint region is a low-frequency area in infrared spectroscopy, where the absorption peak intensity of most chemical bonds varies with the compound content. The characteristic peak region refers to the infrared spectrum of asphalt exhibiting characteristic absorption peaks corresponding to the vibrations of specific molecules or functional groups within the wavenumber range. Given the differences in molecular configuration and chemical composition between base asphalt and modified asphalt, this method constructs differentiated characteristic peak sets for modeling and analysis. The peak positions (center wavenumbers) and corresponding composition tables for base asphalt are shown in [reference needed]. Figure 2 The base asphalt has five characteristic peaks. The figures show the median values ​​of the spectral ranges of these five peaks, with values ​​25 cm to the left and right of each median. -1 The radius length is used as the characteristic peak spectral range for calculating the characteristic index of this characteristic peak. See the table for the characteristic peak positions (center wavenumbers) and corresponding components of modified asphalt. Figure 3 It also utilizes the middle value of 25cm on both sides. -1 The radius length is used as the spectral range of the characteristic peak for calculating the characteristic index of the characteristic peak. The characteristic peak set enables the classification and processing of asphalt from different sources, facilitating individual maintenance as needed in engineering, thereby maintaining the adaptability and transferability of the method under different raw materials and formulation systems.

[0061] In some embodiments, similarity judgment parameters are calculated based on the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range. These similarity judgment parameters include at least the Pearson correlation coefficient for the full wavenumber spectral range. Pearson correlation coefficient of fingerprint spectral range The first of the M characteristic peak spectral intervals Pearson correlation coefficient for each characteristic peak spectral interval Euclidean distance across the entire wavenumber spectral range Normalized root mean square error of the fingerprint region spectral range The first of the M characteristic peak spectral intervals Normalized root mean square error of the spectral range of each characteristic peak The number of unqualified characteristic peaks; among which, = 1, 2, …, M, including:

[0062] Pearson correlation coefficient The calculation formula is ; wherein, is the vertical coordinate value corresponding to the first infrared spectrum curve when the horizontal coordinate is in the calculation interval, is the vertical coordinate value corresponding to the second infrared spectrum curve when the horizontal coordinate is in the calculation interval, is the average of all vertical coordinate values in the first infrared spectrum curve in the calculation interval, is the average of all vertical coordinate values in the second infrared spectrum curve in the calculation interval; according to the calculation formula of the Pearson correlation coefficient , , , are calculated in the full-wave spectral interval, the fingerprint spectral interval, and the characteristic peak spectral interval, respectively.

[0063] Pearson correlation coefficient, used to describe the linear shape synchronization of two infrared spectrum curves in the same window, the value range is [-1, 1].

[0064] The calculation formula of the Euclidean distance of the full-wave spectral interval is .

[0065] Euclidean distance, used to calculate the geometric distance of two infrared spectrum curves at the wave number point.

[0066] The calculation formula of the normalized root mean square error is ; wherein, , is the sample number; according to the calculation formula of the normalized root mean square error , is calculated in the fingerprint spectral interval, and the th characteristic peak of is calculated in the characteristic peak spectral interval, wherein, when is calculated in the fingerprint spectral interval, is the total number of coordinate points selected in the fingerprint spectral interval, and when the th characteristic peak of is calculated in the characteristic peak spectral interval, is the total number of coordinate points in the characteristic peak spectral interval.

[0067] Normalized root mean square error, used to calculate the average error of two infrared spectrum curves in the relative dynamic range.

[0068] The calculation method of the number of unqualified characteristic peaks in the characteristic peak spectral range is the total number of characteristic peaks minus the total number of qualified characteristic peaks, wherein the total number of qualified characteristic peaks is the sum of the number of characteristic peaks under the conditions that > 0.99 and < 0.15 are met.

[0069] In some embodiments, according to the similarity judgment parameter, it is judged whether the to-be-identified asphalt is qualified, and if so, the similarity score is calculated according to the similarity judgment parameter ; otherwise, it is determined that the to-be-identified asphalt is not of the same source as the parent sample asphalt, including:

[0070] When > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ , the asphalt represented by the infrared spectrum curve is qualified, and the similarity score is calculated ; when > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ , any of the conditions is not met, and it is determined that the unqualified asphalt is not of the same source as the parent sample asphalt; wherein when the asphalt is base asphalt, the value of is 1, and when the asphalt is modified asphalt, the value of is 2.

[0071] The similarity score is calculated according to the similarity judgment parameter , and the calculation formula of the similarity score is ; wherein , , , are weight coefficients.

[0072] After the multi-index selection of the asphalt infrared spectrum is performed, the multi-index is analyzed to determine whether the to-be-identified asphalt is of the same source as the parent sample asphalt. When there are several to-be-identified asphalts to be identified, the judgment with the parent sample asphalt is sequentially completed in order to screen out the asphalts of the same source to meet the needs of subsequent engineering.

[0073] In some embodiments, , , , The values of

[0074] In some embodiments, according to the similarity score and the similarity threshold , judge the homology of the asphalt to be identified, if , the asphalt to be identified is homologous to the parent sample asphalt; otherwise, it is not homologous, including:

[0075] When the asphalt is base asphalt, the value of is 0.97, and when the asphalt is modified asphalt, the value of is 0.96.

[0076] The following experiments are carried out using the asphalt homology identification method based on infrared spectrum provided in the embodiments of the present application:

[0077] Experiment 1: Two homologous base asphalts.

[0078] The similarity value calculated by the existing OPUS infrared spectrum software is 0.9962, which is greater than the software set threshold value 0.98, and the two base asphalts can be identified as homologous. The similarity value of the two base asphalts obtained by the asphalt homology identification method based on infrared spectrum provided in the present application is 0.9828, which is greater than the algorithm set threshold value 0.97, and the two base asphalts can also be identified as homologous. The distribution graph of infrared spectrum and the identification result are shown in Figure 4 , wherein the abscissa represents the wave number, and decreases from left to right, and the ordinate represents the absorbance; in order to distinguish, the graph is illustrated using colors, the blue area on the left represents the characteristic peak spectral interval, and the green area on the right represents the fingerprint spectral interval, and the blue curve and the orange curve in the graph represent the first and second infrared spectrum curves. The subsequent Figures 5 to 7 is also illustrated using the above case, and will not be described in detail.

[0079] Experiment 2: Two different source base asphalts.

[0080] The similarity value calculated by the existing OPUS infrared spectrum software is 0.9903, which is still greater than the software set threshold value 0.98, but the two base asphalts are actually selected as different sources, and the existing OPUS infrared spectrum software cannot identify that the two base asphalts are different sources.

[0081] The homology of the two base asphalts is identified using the asphalt homology identification method based on infrared spectrum provided in the present application.

[0082] Step 1: Threshold determination.

[0083] Index 1: The Euclidean distance of the whole curve is 0.4907<1, which meets the requirement.

[0084] Index 2: The Pearson correlation coefficient of the fingerprint area is 0.9886<0.99, which does not meet the requirement.

[0085] ​Index 3: the normalized root mean square error of the fingerprint region is 0.0419 < 0.05, which meets the requirement.

[0086] Index 4: the number of unqualified characteristic peaks is 0 < 1, which meets the requirement. The wave numbers corresponding to the peak positions (center wave numbers) of the qualified characteristic peaks include 2920 cm -1 , 2850 cm -1 , 1450 cm -1 , 1375 cm -1 , and 720 cm -1 .

[0087] Step 2: Similarity score calculation verification.

[0088] The similarity of the two asphalt infrared spectrum curves is calculated, and the calculation formula is as follows: .

[0089] Step 3: Homology discrimination.

[0090] The two kinds of matrix asphalt infrared spectrum do not meet the threshold, and the verification similarity score is less than the similarity threshold, so it is determined that the two kinds of matrix asphalt are different sources, and the two kinds of matrix asphalt can be distinguished from different sources.

[0091] The infrared spectrum distribution diagram and the homology identification result obtained based on the method of the present application are shown in Figure 5 .

[0092] Experiment 3: Two kinds of modified asphalt with the same source.

[0093] The similarity value calculated by the existing OPUS infrared spectrum software is 0.9989, which is greater than the threshold value 0.98 set by the software, and the two kinds of modified asphalt can be identified as the same source. The similarity value of the two kinds of modified asphalt obtained by the asphalt homology identification method based on infrared spectrum proposed in the present application is 0.9887, which is greater than the threshold value 0.96 set by the algorithm, and the two kinds of modified asphalt can be identified as the same source. The infrared spectrum distribution diagram and the identification result are shown in Figure 6 .

[0094] Experiment 4: Two kinds of modified asphalt with different sources.

[0095] The similarity value calculated by the existing OPUS infrared spectrum software is 0.9922, which is greater than the threshold value 0.98 set by the software, but the two kinds of modified asphalt actually selected are different sources, and the existing OPUS infrared spectrum software cannot identify that the two kinds of modified asphalt are different sources.

[0096] The homology of the two kinds of modified asphalt is identified by using the asphalt homology identification method based on infrared spectrum proposed in the present application.

[0097] Step 1: Threshold determination.

[0098] Indicator 1: The Euclidean distance of the entire curve is 1.2075 > 1, which is not satisfied.

[0099] Indicator 2: The Pearson correlation coefficient of the fingerprint area is 0.9783 < 0.99, which is not met.

[0100] Indicator 3: The normalized root mean square error of the fingerprint area is 0.0886 > 0.05, which is not met.

[0101] Indicator 4: The number of non-compliant characteristic peaks (6 > 2) is not met. Specifically, all characteristic peaks are non-compliant.

[0102] Step 2: Similarity score calculation and verification.

[0103] The similarity between two asphalt infrared spectrum curves is calculated using the following formula: .

[0104] Step 3: Homology determination.

[0105] The infrared spectra of both modified asphalts failed to meet the threshold, and their similarity scores were lower than the similarity threshold. Therefore, the two modified asphalts were determined to belong to different sources, and their different sources could be distinguished. The infrared spectral distribution and homology identification results are shown below. Figure 7 As shown.

[0106] Another embodiment of the present invention also provides an asphalt homology identification device based on infrared spectroscopy, comprising:

[0107] The acquisition module is used to acquire the first infrared spectrum curve of the parent sample asphalt and the second infrared spectrum curve of the asphalt to be identified.

[0108] The processing module is used to divide the first infrared spectrum curve and the second infrared spectrum curve according to the wavenumber range of the infrared spectrum to obtain the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range.

[0109] The calculation module is used to calculate similarity judgment parameters based on the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range. The similarity judgment parameters include at least the Pearson correlation coefficient for the full wavenumber spectral range. Pearson correlation coefficient of fingerprint spectral range The first of the M characteristic peak spectral intervals Pearson correlation coefficient for each characteristic peak spectral interval Euclidean distance across the entire wavenumber spectral range Normalized root mean square error of the fingerprint region spectral range The first of the M characteristic peak spectral intervals Normalized root mean square error of the spectral range of each characteristic peak , the number of unqualified characteristic peaks; wherein = 1, 2, …, M.

[0110] The first judging module is configured to judge whether the to-be-identified asphalt is qualified according to the similarity judgment parameter, and if so, calculate the similarity score according to the similarity judgment parameter ; otherwise, determine that the to-be-identified asphalt is not from the same source as the master sample asphalt.

[0111] The second judging module is configured to judge the homology of the to-be-identified asphalt according to the similarity score and the similarity threshold , if > similarity threshold , then the to-be-identified asphalt is from the same source as the master sample asphalt; otherwise, is not from the same source.

[0112] It should be noted that although several units or sub-units of the apparatus are mentioned in the foregoing detailed description, such division is merely exemplary and not mandatory. In fact, according to the embodiments of the present application, the features and functions of two or more units described above can be embodied in one unit. Conversely, the features and functions of one unit described above can be further divided into units embodied by multiple units.

[0113] Based on the same inventive concept as the method embodiments described above, the embodiments of the present application also provide an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the electronic device implements the control method in the above embodiments.

[0114] In an embodiment, the electronic device can be a server, and in this embodiment, the structure of the electronic device can be as shown in Figure 8 , which includes a memory, a communication module, and one or more processors.

[0115] The memory is configured to store the computer program executed by the processor. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and programs required for running instant messaging functions, etc.; and the data storage area can store various instant messaging information and operation instruction sets, etc.

[0116] Memory can be volatile memory, such as random access memory (RAM); memory can also be non-volatile memory, such as read-only memory, flash memory, hard disk drive (HDD), or solid-state drive (SSD); or memory can be any other medium capable of carrying or storing a desired computer program having the form of instructions or data structures and accessible by a computer, but is not limited thereto. Memory can be a combination of the above-mentioned types of memory.

[0117] A processor may include one or more central processing units (CPUs) or digital processing units, etc. The processor is used to implement the aforementioned audio data processing methods when it invokes computer programs stored in memory.

[0118] The communication module is used to communicate with terminal devices and other servers.

[0119] This application embodiment does not limit the specific connection medium between the above-described memory, communication module, and processor. This application embodiment... Figure 8 The memory and processor are connected via a bus, and the bus is in... Figure 8 The connections between other components are illustrated with arrows and are for illustrative purposes only, not as limiting information. Buses can be categorized as address buses, data buses, control buses, etc. For ease of description, Figure 8 The text uses only one arrow to describe it, but does not indicate that there is only one bus or one type of bus.

[0120] Based on the same inventive concept as the above-described method embodiments, embodiments of the present invention also provide a computer-readable storage medium for storing a computer program. When the computer program is run on a computer, it enables an electronic device to implement the control methods described in the above embodiments. The computer-readable storage medium can be a readable signal medium or a readable storage medium. A readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof.

[0121] Based on the same inventive concept as the method embodiments described above, embodiments of the present application also provide a computer program product including a computer program for causing an electronic device to perform the steps of the control method according to various exemplary embodiments of the present application described above in the specification when the program product is run on the electronic device. The program product can take any combination of one or more of a readable medium. These computer program commands can be provided to the processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing devices to produce a machine, so that the commands executed by the processor of the computer or other programmable data processing devices produce a device that implements the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks. Figure 1 one flow or multiple flows and / or the functions specified in one block or multiple blocks.

[0122] Although the present application has been disclosed in connection with the preferred embodiments shown, it should be understood that many modifications, substitutions, and changes can be made by those skilled in the art to the preferred embodiments without departing from the spirit and the scope of the present application. Therefore, the present application should not be limited to the precisely formulated embodiments.

Claims

1. An infrared spectroscopy-based asphalt homogeneity recognition method, characterized by, The method comprises the following steps: collecting a first infrared spectrum curve of a mother sample asphalt and a second infrared spectrum curve of an asphalt to be identified; dividing the first infrared spectrum curve and the second infrared spectrum curve according to a wave number range of the infrared spectrum to obtain a full wave number spectrum interval, a fingerprint region spectrum interval and a characteristic peak spectrum interval; According to the full-wave number spectral interval, the fingerprint region spectral interval, the characteristic peak spectral interval, a similarity judgment parameter is calculated, and the similarity judgment parameter at least includes a Pearson correlation coefficient of the full-wave number spectral interval , a Pearson correlation coefficient of the fingerprint region spectral interval , a Pearson correlation coefficient of the M characteristic peak spectral intervals , a Pearson correlation coefficient of the M characteristic peak spectral intervals , a Euclidean distance of the full-wave number spectral interval , a normalized root mean square error of the fingerprint region spectral interval , a normalized root mean square error of the M characteristic peak spectral intervals , a normalized root mean square error of the M characteristic peak spectral intervals , and a number of unqualified characteristic peaks; wherein, =1, 2, …, M; According to the similarity judgment parameter, it is judged whether the to-be-identified asphalt is qualified or not, and if yes, a similarity score is calculated according to the similarity judgment parameter ; otherwise, it is determined that the to-be-identified asphalt is not from the same source as the parent sample asphalt, and the judgment method comprises: when > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ , the asphalt represented by the infrared spectrum curve is qualified, and the similarity score is calculated ; when any of the conditions of > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ is not met, it is determined that the unqualified asphalt is not from the same source as the parent sample asphalt; wherein when the asphalt is base asphalt, the value of is 1, and when the asphalt is modified asphalt, the value of is 2; the similarity score is calculated according to the similarity judgment parameter , and the calculation formula of the similarity score is ; wherein , , are weight coefficients According to the similarity score and the similarity threshold , judging the homology of the asphalt to be identified, if > the asphalt to be identified is homologous to the parent asphalt; otherwise, it is not homologous.

2. The method for identifying the homogeneity of asphalt based on infrared spectrum according to claim 1, characterized in that, the step of dividing the first infrared spectrum curve and the second infrared spectrum curve according to the wave number range of the infrared spectrum to obtain the full wave number spectrum interval, the fingerprint region spectrum interval and the characteristic peak spectrum interval comprises the following steps: dividing an effective wave number range in an interval of 4000~600 cm -1 of the total wave number spectrum interval; The effective wave number range in the interval of 1500~600 cm -1 is divided into the fingerprint region spectral interval; The effective wave number range is divided into the characteristic peak spectral interval by 25 cm -1 on both sides of the peak position of the characteristic peak.

3. The method for identifying the homogeneity of asphalt based on infrared spectrum according to claim 2, characterized in that, The similarity judgment parameters are calculated based on the full wavenumber spectral interval, the fingerprint region spectral interval, and the characteristic peak spectral interval. These similarity judgment parameters include at least the Pearson correlation coefficient for the full wavenumber spectral interval. Pearson correlation coefficient of fingerprint spectral range The first of the M characteristic peak spectral intervals Pearson correlation coefficient for each characteristic peak spectral interval Euclidean distance across the entire wavenumber spectral range Normalized root mean square error of the fingerprint region spectral range The first of the M characteristic peak spectral intervals Normalized root mean square error of the spectral range of each characteristic peak The number of unqualified characteristic peaks; among which, =1,2,...,M, including: Pearson correlation coefficient The calculation formula is ;in, To calculate the x-coordinate within the interval The vertical axis value corresponding to the first infrared spectrum curve at that time. To calculate the x-coordinate within the interval The value of the ordinate corresponding to the second infrared spectrum curve at that time. To calculate the average value of all ordinate values ​​in the first infrared spectrum curve within the interval, To calculate the average of all ordinate values ​​in the second infrared spectrum within the interval; based on the Pearson correlation coefficient... The calculation formulas are used to calculate the full wavenumber spectral range, the fingerprint region spectral range, and the characteristic peak spectral range, respectively. , , ; Euclidean distance of full-wave number spectral interval The calculation formula is ; Normalized root mean square error The calculation formula is ;in, , The sample size; based on the normalized root mean square error The calculation formula is used to calculate the fingerprint region spectral range. Calculate the first characteristic peak spectral range. Characteristic peaks Wherein, when calculating in the spectral range of the fingerprint region hour, The total number of coordinate points selected in the spectral range of the fingerprint region, when calculating the first number in the spectral range of the characteristic peak. Characteristic peaks hour, This represents the total number of coordinate points within the spectral range of the characteristic peak. The calculation method of the number of the unqualified characteristic peaks in the characteristic peak spectral range is the total number of characteristic peaks minus the total number of qualified characteristic peaks, wherein the total number of qualified characteristic peaks is the sum of the number of characteristic peaks under the condition that the relative intensity of the characteristic peak is greater than 0.99 and the relative intensity of the characteristic peak is less than 0.

15. The total number of qualified characteristic peaks is the sum of the number of characteristic peaks under the condition that the relative intensity of the characteristic peak is greater than 0.99 and the relative intensity of the characteristic peak is less than 0.

15. The total number of qualified characteristic peaks is the sum of the number of characteristic 4. The method for identifying the homogeneity of asphalt based on infrared spectrum according to claim 1, characterized in that, , , , the values of the numbers are 0.35, 0.15, 0.25, 0.25, respectively.

5. The method for identifying the homogeneity of asphalt based on infrared spectrum according to claim 1, characterized in that, The similarity score and a similarity threshold , judging the homology of the asphalt to be identified, if > the asphalt to be identified is homologous to the parent asphalt otherwise, different sources, comprising: When the bitumen is a base bitumen has a value of 0.97, when the bitumen is a modified bitumen has a value of 0.

96.

6. An infrared spectroscopy-based asphalt homogeneity recognition device, characterized by, The method comprises the following steps: a collecting module configured to collect a first infrared spectrum curve of a mother sample asphalt and a second infrared spectrum curve of an asphalt to be identified; a processing module configured to divide the first infrared spectrum curve and the second infrared spectrum curve according to a wave number range of the infrared spectrum to obtain a full wave number spectrum interval, a fingerprint region spectrum interval and a characteristic peak spectrum interval; The computing module is configured to calculate similarity judgment parameters according to the full-wave number spectral interval, the fingerprint region spectral interval and the characteristic peak spectral interval, and the similarity judgment parameters at least include a Pearson correlation coefficient of the full-wave number spectral interval , a Pearson correlation coefficient of the fingerprint region spectral interval , a Pearson correlation coefficient of the M characteristic peak spectral intervals , a Pearson correlation coefficient of the M characteristic peak spectral intervals , a Euclidean distance of the full-wave number spectral interval , a normalized root mean square error of the fingerprint region spectral interval , a normalized root mean square error of the M characteristic peak spectral intervals , a normalized root mean square error of the M characteristic peak spectral intervals , and a number of unqualified characteristic peaks; wherein, =1, 2, …, M. The first judging module is configured to judge whether the to-be-identified asphalt is up to standard according to the similarity judgment parameter, and if so, calculate a similarity score according to the similarity judgment parameter ; otherwise, determine that the to-be-identified asphalt is not from the same source as the parent sample asphalt, and the judging method comprises: when > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ , the asphalt represented by the infrared spectrum curve is up to standard, and the similarity score is calculated ; when any of the following conditions is not met: > 0.99, < 1, < 0.05, and the number of unqualified characteristic peaks is ≤ , it is determined that the asphalt that does not meet the standard is not from the same source as the parent sample asphalt; wherein when the asphalt is base asphalt, the value of is 1, and when the asphalt is modified asphalt, the value of is 2; the similarity score is calculated according to the similarity judgment parameter , and the calculation formula of the similarity score is ; wherein , , are weight coefficients The second judgment module is used to determine the similarity score. and similarity threshold To determine the homology of the asphalt to be identified, if > If the asphalt to be identified is of the same origin as the parent sample asphalt, then it is of different origin; otherwise, it is of different origin.

7. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, The processor executes the computer program, so that the electronic device implements the asphalt source identification method based on infrared spectrum as claimed in any one of claims 1-5.

8. A computer-readable storage medium, characterized in that, The computer readable storage medium is used for storing a computer program, when the computer program runs on a computer, so that the computer executes the asphalt source identification method based on infrared spectrum as claimed in any one of claims 1-5.

Images