Bitumen melting furnace internal temperature data analysis method and system

Abstract

The application discloses a kind of asphalt melting furnace internal temperature data analysis method and system, it is related to asphalt melting furnace temperature analysis technical field, specifically discloses that virtual three-dimensional cavity is constructed, and temperature acquisition point corresponding with temperature sensing device is set in it;The temperature distribution characteristics of asphalt melting furnace side are acquired, and it is mapped to virtual three-dimensional cavity;Temperature distribution parameter characteristic array is constructed, including temperature value and point distance, and the position of each parameter in array is determined;Parameter characteristic array is sorted based on time series relationship, establishes the association of parameter characteristic array sequence and asphalt melting quality, forms asphalt melting quality relationship library;Characteristic factor configuration is carried out to temperature distribution parameter characteristic array using characteristic analysis model, and the index relationship of asphalt melting quality relationship library is established, which provides strong support for the accurate control and optimization of asphalt melting quality.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of asphalt melting furnace temperature analysis, and particularly relates to an asphalt melting furnace internal temperature data analysis method and system. BACKGROUND

[0002] In the field of asphalt processing, the asphalt melting furnace as a key production equipment, its internal temperature control has a decisive influence on the melting quality of asphalt. However, the traditional asphalt melting furnace temperature data analysis method faces many challenges and limitations. These methods often cannot accurately and comprehensively obtain the temperature distribution characteristics in the furnace, resulting in insufficient precision of temperature control; at the same time, the traditional method is also difficult to effectively associate the temperature collection points and the temperature distribution center points, and cannot establish the quantitative relationship between the temperature data and the asphalt melting quality. SUMMARY

[0003] The purpose of the present application is to provide an asphalt melting furnace internal temperature data analysis method which can accurately establish the corresponding relationship between the temperature distribution characteristics in the furnace and the asphalt melting quality, and thus provide data support for the internal temperature control optimization of the asphalt melting furnace.

[0004] In order to achieve the above purpose, the present application adopts the following technical scheme:

[0005] An asphalt melting furnace internal temperature data analysis method, comprising:

[0006] The cavity structure of the asphalt melting furnace is determined, and a virtual three-dimensional cavity is constructed based on the cavity structure. Based on the relative position of the temperature sensing device in the cavity structure of the asphalt melting furnace, corresponding temperature collection points are set in the virtual three-dimensional cavity;

[0007] The temperature distribution characteristics of the side part of the asphalt melting furnace are determined by using thermal imaging detection technology, and the determined temperature distribution characteristics are mapped on the virtual three-dimensional cavity. Combined with the temperature values collected by different temperature collection points, the point distance between each temperature collection point and the temperature distribution center point to which it belongs is determined;

[0008] For the relative position of different temperature collection points, a temperature distribution parameter characteristic array is constructed. The temperature distribution parameters include the temperature values collected by the temperature collection points and the point distance. Based on the position of the temperature collection points in the virtual three-dimensional cavity, the corresponding temperature distribution parameters in the temperature distribution parameter characteristic array are determined;

[0009] Based on the time sequence relationship, the temperature distribution parameter characteristic array is sorted to obtain the parameter characteristic array sequence, and the correlation between the parameter characteristic array sequence and the asphalt melting quality is established. The correlation relationships are integrated to obtain the asphalt melting quality relationship library;

[0010] The characteristic analysis model is used to configure characteristic factors for the characteristic array of the temperature distribution parameter, and an index relationship of the asphalt melting quality relationship database is established based on the characteristic factors.

[0011] In some embodiments of the present disclosure, the method for determining the point distance of each temperature collection point of the virtual three-dimensional cavity from the temperature distribution center point to which the temperature collection point belongs includes:

[0012] The thermal imaging detection technology is used to form a thermal imaging image of the side of the asphalt melting furnace, and a threshold value is determined based on the gray level change gradient in the thermal imaging image and a preset gray level boundary, and a plurality of temperature center blocks are divided in the thermal imaging image;

[0013] Based on the temperature center blocks in the thermal imaging images in different directions, a three-dimensional temperature center block is divided in the virtual three-dimensional cavity;

[0014] The block boundary of each three-dimensional temperature center block is determined, a plurality of boundary mapping points are randomly selected on the block boundary, the boundary coordinates of each boundary mapping point are obtained, and the average coordinates of all boundary coordinates are calculated, and the mapping point corresponding to the average coordinates is identified as the temperature distribution center point;

[0015] The temperature collection points within the same three-dimensional temperature center block range are determined, and the distance between each temperature collection point and the temperature distribution center point, i.e., the point distance, is calculated.

[0016] In some embodiments of the present disclosure, the method for establishing the correlation between the parameter characteristic array sequence and the asphalt melting quality includes:

[0017] The penetration test, softening point test, and viscosity test are used to judge the melting quality of the asphalt, and the judgment results are quantified to obtain the melting quality parameter;

[0018] The method for quantifying the judgment results includes:

[0019] The penetration test is set to have a penetration interval corresponding group, wherein each penetration interval is set to have a first preset melting quality parameter, the softening point test is set to have a softening point interval corresponding group, wherein each softening point interval is set to have a second preset melting quality parameter, and the viscosity test is set to have a viscosity interval corresponding group, wherein each annual interval is set to have a third preset melting quality parameter;

[0020] Based on the belonging relationship of the penetration test results, the softening point test results, and the viscosity test results in the respective interval corresponding groups, the corresponding first preset melting quality parameter, the second preset melting quality parameter, and the third preset melting quality parameter are called to perform comprehensive comparison and calculation to obtain the melting quality parameter.

[0021] In some embodiments of the present application, the expression for calculating the melting quality parameter is:

[0022]

[0023] wherein H is the melting quality parameter, is a weight coefficient of the first preset melting quality parameter, is the first preset melting quality parameter, is a weight coefficient of the second preset melting quality parameter, is the second preset melting quality parameter, is a weight coefficient of the third preset melting quality parameter, is the third preset melting quality parameter.

[0024] In some embodiments of the present application, the method for configuring a characteristic factor for a temperature distribution parameter characteristic array using a characteristic analysis model includes:

[0025] For a preset difference interval, the classified melting quality parameters are classified, and based on the classification of the melting quality parameters, the parameter characteristic array sequence is classified to obtain a plurality of parameter characteristic array sequence sets;

[0026] Each temperature distribution parameter characteristic array sequence in the parameter characteristic array sequence set is aligned, and the temperature distribution parameter characteristic arrays in the temperature distribution parameter characteristic array sequence are compared in sequence. If the difference characteristics between the temperature distribution parameter characteristic arrays of the same sequence meet the equivalence standard, the temperature distribution parameter characteristic array of the sequence is marked as a weak characteristic temperature distribution parameter characteristic array, and the remaining other temperature distribution characteristic arrays are marked as moderate characteristic temperature distribution parameter characteristic arrays;

[0027] The difference characteristics of the moderate characteristic temperature distribution parameter characteristic arrays of the equivalent sequence between the parameter characteristic array sequences are analyzed to determine the difference characteristic parameter of each sequence, and the difference characteristic parameters are continuously analyzed. If the continuous difference characteristic parameters show a monotonic change trend, the temperature distribution parameter characteristic array corresponding to the difference characteristic parameter is identified as a strong characteristic temperature distribution parameter characteristic array;

[0028] The sequence of the strong characteristic temperature distribution parameter characteristic array in the parameter characteristic array sequence is identified as a first characteristic factor.

[0029] In some embodiments of the present application, the temperature values of different points in the strong characteristic temperature distribution parameter characteristic array are identified as a second characteristic factor.

[0030] In some embodiments disclosed in the present application, the method for analyzing the difference characteristics of the moderate characteristic temperature distribution parameter characteristic arrays of the equivalent sequence between the parameter characteristic array sequences includes:

[0031] Randomly selected equivalent ordinal medium characteristic temperature distribution parameter characteristic array is combined in pairs, and is recorded as a parameter characteristic array random group, the temperature values and the point distance between the equivalent points of the medium characteristic temperature distribution parameter characteristic array in the parameter characteristic array random group are compared, the temperature value difference of the equivalent points and the point distance are determined, and the average temperature value difference and the average point distance between the parameter characteristic array random groups are determined;

[0032] The first difference characteristic operator is constructed based on the average temperature value difference of the equivalent points, and the second difference characteristic operator is constructed based on the average point distance between the equivalent points, and the difference characteristic parameter is determined based on the first difference characteristic operator and the second difference characteristic operator.

[0033] In some embodiments disclosed in the present application, the difference characteristic parameter expression is:

[0034]

[0035] Wherein, T is the difference characteristic parameter, is the average temperature value difference of the i th equivalent point between the medium characteristic temperature distribution parameter characteristic arrays, is the average point distance of the i th equivalent point between the medium characteristic temperature distribution parameter characteristic arrays, and n is the total number of points in the medium characteristic temperature distribution parameter characteristic array, is the average point distance ratio adjustment coefficient, is the average point distance ratio adjustment constant.

[0036] In some embodiments disclosed in the present application, an asphalt melting furnace internal temperature data analysis system is also disclosed, comprising:

[0037] The first module is used for determining the cavity structure of the asphalt melting furnace, and constructing a virtual three-dimensional cavity based on the cavity structure, and setting corresponding temperature collection points in the virtual three-dimensional cavity based on the relative position of the temperature sensing device in the cavity structure of the asphalt melting furnace;

[0038] The second module is used for determining the temperature distribution characteristics of the side part of the asphalt melting furnace by using thermal imaging detection technology, mapping the determined temperature distribution characteristics on the virtual three-dimensional cavity, and combining the temperature values collected by different temperature collection points to determine the point distance between each temperature collection point of the virtual three-dimensional cavity and the temperature distribution center point to which the temperature collection point belongs;

[0039] The third module is configured to construct a temperature distribution parameter characteristic array for the relative positions of different temperature collection points, wherein the temperature distribution parameters include temperature values collected by the temperature collection points and point-to-point distances, and the corresponding temperature distribution parameters in the temperature distribution parameter characteristic array are determined based on the positions of the temperature collection points in the virtual three-dimensional cavity;

[0040] The fourth module is configured to sort the temperature distribution parameter characteristic array based on time sequence relationships, obtain a parameter characteristic array sequence, and establish an association between the parameter characteristic array sequence and the asphalt melting quality.

[0041] The fifth module is configured to configure characteristic factors for the temperature distribution parameter characteristic array by using a characteristic analysis model, and establish an index relationship of the asphalt melting quality relationship library based on the characteristic factors.

[0042] The present application discloses a kind of asphalt melting furnace internal temperature data analysis method and system, it is related to asphalt melting furnace temperature analysis technical field, specifically discloses that virtual three-dimensional cavity is constructed, and temperature collection point corresponding with temperature sensing device is set in it;Temperature distribution characteristics of asphalt melting furnace side are obtained, and it is mapped to virtual three-dimensional cavity;Temperature distribution parameter characteristic array is constructed, including temperature value and point-to-point distance, and the position of each parameter in array is determined;Parameter characteristic array is sorted based on time sequence relationship, parameter characteristic array sequence and the association between asphalt melting quality are established, and asphalt melting quality relationship library is formed;Characteristic factor configuration is carried out to temperature distribution parameter characteristic array by using characteristic analysis model, and the index relationship of asphalt melting quality relationship library is established, for the precise control and optimization of asphalt melting quality provides strong support. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 The method steps of the asphalt melting furnace internal temperature data analysis method proposed in the present application are shown in the figure. DETAILED DESCRIPTION

[0044] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all the embodiments.

[0045] The purpose of the present application is to provide an asphalt melting furnace internal temperature data analysis method capable of accurately establishing the corresponding relationship between temperature distribution characteristics in the furnace and asphalt melting quality, thereby providing data support for the optimization of furnace temperature control of asphalt melting furnace.

[0046] To achieve the above-mentioned purpose, the present application adopts the following technical solutions:

[0047] ReferenceFigure 1 A method for analyzing internal temperature data of an asphalt melting furnace, comprising:

[0048] In step S100, the internal structure of the cavity of the asphalt melting furnace is determined, and a virtual three-dimensional cavity is constructed based on the internal structure. Based on the relative positions of the temperature sensing devices in the internal structure of the cavity of the asphalt melting furnace, corresponding temperature collection points are set in the virtual three-dimensional cavity.

[0049] The core principle of this step is to convert the actual internal structure of the cavity of the asphalt melting furnace into a virtual three-dimensional cavity through accurate measurement and modeling. This conversion process relies on advanced measurement technology and three-dimensional modeling software, which can ensure high consistency between the virtual cavity and the real furnace cavity in structure and size. At the same time, according to the actual position of the temperature sensing device in the furnace cavity, the corresponding temperature collection points are set in the virtual cavity, providing accurate coordinate basis for subsequent temperature data collection and analysis.

[0050] In step S200, the temperature distribution characteristics of the side of the asphalt melting furnace are determined using thermal imaging detection technology, and the determined temperature distribution characteristics are mapped onto the virtual three-dimensional cavity. In combination with the temperature values collected by different temperature collection points, the point-to-point distance of each temperature collection point from the temperature distribution center point to which it belongs in the virtual three-dimensional cavity is determined.

[0051] This step uses thermal imaging detection technology to capture the temperature distribution characteristics of the side of the asphalt melting furnace. Thermal imaging technology can accurately measure the temperature distribution of the surface of an object in real time and present it in the form of an image. By mapping these temperature distribution characteristics onto the virtual three-dimensional cavity, the organic combination of temperature data and furnace cavity structure can be achieved. At the same time, in combination with the temperature values collected by different temperature collection points, mathematical algorithms are used to calculate the point-to-point distance of each temperature collection point from the temperature distribution center point to which it belongs, providing key data for subsequent temperature analysis and quality control.

[0052] In some embodiments disclosed in the present application, the method for determining the point-to-point distance of each temperature collection point in the virtual three-dimensional cavity from the temperature distribution center point to which it belongs includes:

[0053] In step S201, a thermal imaging image of the side of the asphalt melting furnace is formed using thermal imaging detection technology, and a threshold value is determined based on the gray scale change gradient in the thermal imaging image and the preset gray scale boundary. A number of temperature center blocks are divided in the thermal imaging image.

[0054] This step utilizes thermal imaging detection technology to capture the infrared radiation emitted from the side of the asphalt melting furnace and convert it into a thermal image of visible light. Since objects at different temperatures emit different intensities of infrared radiation, in the thermal image, areas with higher temperatures will appear brighter in grayscale, while areas with lower temperatures will appear darker in grayscale. By analyzing the grayscale gradient in the thermal image and combining the preset grayscale boundary threshold, the temperature center blocks representing different temperature distributions can be accurately divided.

[0055] Step S202, based on the temperature center blocks in the thermal images of different orientations, the three-dimensional temperature center blocks are divided in the virtual three-dimensional cavity.

[0056] The core of this step is to map the temperature center block information in the thermal image to the virtual three-dimensional cavity. Since the virtual three-dimensional cavity is constructed according to the actual cavity structure of the asphalt melting furnace, the temperature center blocks in the thermal image can be converted to three-dimensional temperature center blocks in the virtual cavity through precise mathematical transformation and coordinate mapping. This mapping process ensures the consistency of the spatial position of the temperature data with the actual furnace cavity structure, providing accurate spatial reference for subsequent temperature analysis and calculation.

[0057] Step S203, determine the block boundary of each three-dimensional temperature center block, and randomly select several boundary mapping points on the block boundary, obtain the boundary coordinates of each boundary mapping point, and calculate the average coordinates of all boundary coordinates, and the mapping point corresponding to the average coordinates is identified as the temperature distribution center point.

[0058] The purpose of this step is to determine the precise range of each three-dimensional temperature center block and find its temperature distribution center point. By defining the block boundary and randomly selecting several boundary mapping points, the specific coordinates of these points can be obtained. Then, the average coordinates of all boundary coordinates are calculated using mathematical algorithms, and the mapping point corresponding to the average coordinates is identified as the temperature distribution center point. This process is based on statistical principles and estimates the center position of the block by calculating the average value of the boundary coordinates, providing an accurate reference point for subsequent calculation of point distance.

[0059] Step S204, determine the temperature collection points within the same three-dimensional temperature center block range, and calculate the distance between each temperature collection point and the temperature distribution center point, denoted as point distance.

[0060] The core of this step is to calculate the distance between each temperature collection point and the center point of the temperature distribution to which it belongs. Since the temperature collection points represent the actual temperature measurement positions in the furnace cavity, by calculating the distance between them and the center point of the temperature distribution, a detailed point distance data set can be obtained. This data set reflects the temperature distribution at different positions in the furnace cavity, providing important data support for subsequent temperature analysis, quality control and optimization of the melting process. At the same time, by comparing the point distance data sets at different time points, the change law of the temperature distribution with time can be revealed, providing a strong basis for further melting process control.

[0061] In step S300, a temperature distribution parameter feature array is constructed for the relative positions of different temperature collection points. The temperature distribution parameters include the temperature values collected by the temperature collection points and the point distances. Based on the positions of the temperature collection points in the virtual three-dimensional cavity, the corresponding temperature distribution parameters in the temperature distribution parameter feature array are determined.

[0062] The principle of this step is to construct an ordered and structured temperature distribution parameter feature array to better organize and process a large amount of temperature data. By considering the relative positions of different temperature collection points, key parameters such as temperature values and point distances can be organically integrated. At the same time, based on the positions of the temperature collection points in the virtual three-dimensional cavity, the belonging point position of each temperature distribution parameter in the feature array can be determined, so as to realize accurate positioning and rapid retrieval of data.

[0063] In step S400, the temperature distribution parameter feature array is sorted based on the time sequence relationship to obtain a parameter feature array sequence, and the association between the parameter feature array sequence and the asphalt melting quality is established. By integrating several association relationships, an asphalt melting quality relationship library is obtained.

[0064] The principle of this step is to sort and organize the temperature distribution parameter feature array using the time sequence relationship to better reveal the internal relationship between the temperature data and the asphalt melting quality. By sorting based on the time sequence, an ordered parameter feature array sequence can be obtained, reflecting the change of the temperature distribution parameters with time. At the same time, by establishing the association between the parameter feature array sequence and the asphalt melting quality, the corresponding relationship between the temperature distribution parameters at different time points and the asphalt melting quality can be found, providing strong support for subsequent quality control and prediction.

[0065] In some embodiments disclosed in the present application, the method for establishing the association between the parameter feature array sequence and the asphalt melting quality includes:

[0066] In step S401, the melting quality of the asphalt is judged by using the penetration test, the softening point test and the viscosity test, and the judgment result is quantified to obtain the melting quality parameter.

[0067] The method for quantifying the judgment result comprises:

[0068] In step S4011, a penetration interval corresponding group is set for the penetration test, wherein each penetration interval is provided with a first preset melting quality parameter; a softening point interval corresponding group is set for the softening point test, wherein each softening point interval is provided with a second preset melting quality parameter; and a viscosity interval corresponding group is set for the viscosity test, wherein each annual interval is provided with a third preset melting quality parameter.

[0069] In step S4012, the corresponding first preset melting quality parameter, the second preset melting quality parameter and the third preset melting quality parameter are called and comprehensively compared and calculated based on the belonging relationship of the penetration test result, the softening point test result and the viscosity test result in the respective interval corresponding group to obtain the melting quality parameter.

[0070] In some embodiments of the present application, the expression for calculating the melting quality parameter is:

[0071]

[0072] H is the melting quality parameter, is a weight coefficient of the first preset melting quality parameter, is the first preset melting quality parameter, is a weight coefficient of the second preset melting quality parameter, is the second preset melting quality parameter, is a weight coefficient of the third preset melting quality parameter, is the third preset melting quality parameter.

[0073] In step S500, the characteristic analysis model is used to configure characteristic factors for the temperature distribution parameter characteristic array, and an index relationship of the asphalt melting quality relationship library is established based on the characteristic factors.

[0074] The principle of this step is to use the characteristic analysis model to deeply mine and analyze the temperature distribution parameter characteristic array, so as to extract key characteristic factors which have important influence on the asphalt melting quality. These characteristic factors can reflect the core characteristics and properties of the temperature distribution parameter, and have important significance for understanding and controlling the asphalt melting process. At the same time, based on these characteristic factors, the index relationship of the asphalt melting quality relationship library is established, which can realize fast retrieval and efficient utilization of data, and provide strong technical support for precise control and optimization of the asphalt melting quality.

[0075] In some embodiments of the present application, the method for configuring characteristic factors for a temperature distribution parameter characteristic array using a characteristic analysis model comprises:

[0076] In step S501, the quantized melting quality parameters are classified according to a preset difference interval, and the parameter characteristic array sequences are classified based on the classification of the melting quality parameters, thereby obtaining a plurality of parameter characteristic array sequence sets.

[0077] The core of this step is to classify the quantized melting quality parameters and group the parameter characteristic array sequences based on the classification. The preset difference interval is used to determine different categories of melting quality parameters, thereby ensuring the accuracy and effectiveness of the classification. By classifying the parameter characteristic array sequences, a plurality of parameter characteristic array sequence sets with similar characteristics can be obtained, providing a basis for subsequent characteristic analysis and factor configuration.

[0078] In step S502, each temperature distribution parameter characteristic array sequence in the parameter characteristic array sequence set is aligned, and the temperature distribution parameter characteristic arrays in the temperature distribution parameter characteristic array sequence are compared one by one. If the difference characteristics between the temperature distribution parameter characteristic arrays of the same sequence meet the equivalence standard, the temperature distribution parameter characteristic arrays of the same sequence are marked as weak characteristic temperature distribution parameter characteristic arrays, and the remaining other temperature distribution characteristic arrays are marked as medium characteristic temperature distribution parameter characteristic arrays.

[0079] In this step, the temperature distribution parameter characteristic arrays in each parameter characteristic array sequence set are aligned and compared, with the purpose of identifying arrays with similar characteristics. If the difference characteristics between the temperature distribution parameter characteristic arrays of the same sequence meet the equivalence standard, these arrays are marked as weak characteristic temperature distribution parameter characteristic arrays, indicating that they are relatively weak in characteristics and may have a smaller impact on the melting quality. The remaining other temperature distribution characteristic arrays are marked as medium characteristic temperature distribution parameter characteristic arrays, indicating that they are relatively strong in characteristics and may have a certain impact on the melting quality.

[0080] In step S503, the difference characteristics of the medium characteristic temperature distribution parameter characteristic arrays of the equivalent sequences between the parameter characteristic array sequences are analyzed, the difference characteristic parameters of each sequence are determined, and the difference characteristic parameters are continuously analyzed. If the continuous difference characteristic parameters show a monotonic change trend, the temperature distribution parameter characteristic array corresponding to the difference characteristic parameter is identified as a strong characteristic temperature distribution parameter characteristic array.

[0081] This step further analyzes the difference features of the medium characteristic temperature distribution parameter characteristic array, and aims to find out the array with significant features. By continuously analyzing the difference feature parameters, if the continuous difference feature parameters show a monotonic change trend, it indicates that the temperature distribution parameter characteristic array corresponding to these feature parameters has strong performance in characteristics, and therefore they are identified as strong characteristic temperature distribution parameter characteristic arrays. This step helps to identify the key characteristic factors that have important influence on the melting quality, and provides strong support for subsequent quality control and optimization.

[0082] In some embodiments disclosed in the present application, the method for analyzing the difference features of the medium characteristic temperature distribution parameter characteristic array between the equivalent order of the parameter characteristic array sequence comprises:

[0083] Step S5031, randomly select the medium characteristic temperature distribution parameter characteristic array of the equivalent order for pair combination, and record it as the parameter characteristic array random group. By comparing the temperature values and the distance between points of the equivalent points between the medium characteristic temperature distribution parameter characteristic arrays in the parameter characteristic array random group, the temperature value difference and the distance between points of the equivalent points are determined, and the average temperature value difference and the average distance between points between the parameter characteristic array random groups are determined.

[0084] The purpose of this step is to compare the temperature value and the distance between points of the equivalent points between the medium characteristic temperature distribution parameter characteristic arrays by randomly combining the medium characteristic temperature distribution parameter characteristic arrays of the equivalent order. By comparison, the temperature value difference and the distance between points of the equivalent points of each pair of parameter characteristic arrays can be determined. Further, by calculating the average temperature value difference and the average distance between points between all parameter characteristic array random groups, a quantitative difference measure can be obtained, which provides a basis for subsequent difference feature analysis.

[0085] Step S5032, a first difference feature operator is constructed based on the average temperature value difference of the equivalent points, and a second difference feature operator is constructed based on the average distance between points of the equivalent points. Based on the first difference feature operator and the second difference feature operator, the difference feature parameter is determined.

[0086] In some embodiments disclosed in the present application, the difference feature parameter expression is:

[0087]

[0088] Wherein, T is the difference feature parameter, is the average temperature value difference of the i th equivalent point between the medium characteristic temperature distribution parameter characteristic arrays, is the average distance between points of the i th equivalent point between the medium characteristic temperature distribution parameter characteristic arrays, and n is the total number of points in the medium characteristic temperature distribution parameter characteristic array. is an average inter-point distance ratio adjustment coefficient, is an average inter-point distance ratio adjustment constant.

[0089] In step S504, the sequence of the strong feature temperature distribution parameter feature array in the parameter feature array sequence is identified as a first feature factor.

[0090] In some embodiments of the present application, the temperature values of different point positions in the strong feature temperature distribution parameter feature array are identified as a second feature factor.

[0091] In some embodiments disclosed in the present application, an asphalt melting furnace internal temperature data analysis system is also disclosed, comprising:

[0092] The first module is configured to determine the internal structure of the cavity of the asphalt melting furnace, construct a virtual three-dimensional cavity based on the internal structure, and set corresponding temperature collection points in the virtual three-dimensional cavity based on the relative positions of the temperature sensing devices in the internal structure of the cavity of the asphalt melting furnace.

[0093] The second module is configured to determine the temperature distribution characteristics of the side part of the asphalt melting furnace by using thermal imaging detection technology, map the determined temperature distribution characteristics on the virtual three-dimensional cavity, and determine the inter-point distance of each temperature collection point of the virtual three-dimensional cavity from the temperature distribution center point to which the temperature collection point belongs, in combination with the temperature values collected by different temperature collection points.

[0094] The third module is configured to construct a temperature distribution parameter feature array for the relative positions of different temperature collection points, wherein the temperature distribution parameters include the temperature values collected by the temperature collection points and the inter-point distances, and determine the corresponding temperature distribution parameters in the temperature distribution parameter feature array based on the positions of the temperature collection points in the virtual three-dimensional cavity.

[0095] The fourth module is configured to sort the temperature distribution parameter feature array based on the time sequence relationship, obtain a parameter feature array sequence, and establish the association between the parameter feature array sequence and the asphalt melting quality, integrate a plurality of association relationships, and obtain an asphalt melting quality relationship library.

[0096] The fifth module is configured to configure feature factors for the temperature distribution parameter feature array by using a feature analysis model, and establish an index relationship of the asphalt melting quality relationship library based on the feature factors.

[0097] The application discloses a kind of asphalt melting furnace internal temperature data analysis method and system, it is related to asphalt melting furnace temperature analysis technical field, specifically disclose that virtual three-dimensional cavity is constructed, and temperature acquisition point corresponding with temperature sensing device is set in it;The temperature distribution characteristics of asphalt melting furnace side are acquired, and it is mapped to virtual three-dimensional cavity;Temperature distribution parameter characteristic array is constructed, including temperature value and point distance, and the position of each parameter in array is determined;Parameter characteristic array is sorted based on time series relationship, establishes the association of parameter characteristic array sequence and asphalt melting quality, forms asphalt melting quality relationship library;Characteristic factor configuration is carried out to temperature distribution parameter characteristic array using characteristic analysis model, and the index relationship of asphalt melting quality relationship library is established, provide strong support for the accurate control and optimization of asphalt melting quality.

[0098] The above is only the preferred specific embodiment of the present application, but the protection scope of the present application is not limited to this, any skilled person in the art can replace or change according to the technical range disclosed in the present application and the inventive concept of the present application, which should be covered in the protection scope of the present application.

Claims

1. A method for analyzing temperature data inside an asphalt melting furnace, characterized in that: include: The cavity structure of the asphalt melting furnace is determined, and a virtual three-dimensional cavity is constructed based on the cavity structure. Based on the relative position of the temperature sensor device in the cavity structure of the asphalt melting furnace, corresponding temperature collection points are set in the virtual three-dimensional cavity; Using thermal imaging technology, the temperature distribution characteristics of the side of the asphalt melting furnace are determined and mapped onto a virtual three-dimensional cavity. The temperature values ​​collected at different temperature collection points are combined to determine the distance between each temperature collection point in the virtual three-dimensional cavity and the center point of the temperature distribution to which it belongs. Based on the relative positions of different temperature collection points, a temperature distribution parameter feature array is constructed. The temperature distribution parameters include the temperature values ​​collected by the temperature collection points and the distances between the points. Based on the positions of the temperature collection points in the virtual three-dimensional cavity, the corresponding temperature distribution parameters are determined in the temperature distribution parameter feature array. Based on the time series relationship, the temperature distribution parameter feature array is sorted to obtain the parameter feature array sequence, and the association between the parameter feature array sequence and the asphalt melting quality is established. Several association relationships are integrated to obtain the asphalt melting quality relationship library; By using the characteristic analysis model, characteristic factors are configured for the characteristic array of temperature distribution parameters, and the index relationship of the asphalt melting quality relationship library is established based on the characteristic factors.

2. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 1, characterized in that: The method for determining the distance between each temperature collection point of the virtual three-dimensional cavity and the center point of the temperature distribution to which it belongs includes: Using thermal imaging detection technology, a thermal image of the side of the asphalt melting furnace is formed. Based on the grayscale gradient and the preset grayscale boundary in the thermal image, a threshold is determined to divide the thermal image into several temperature center blocks. Based on the temperature center blocks in the thermal imaging images at different orientations, three-dimensional temperature center blocks are divided in the virtual three-dimensional cavity; Determine the block boundary of each 3D temperature center block, randomly select several boundary mapping points on the block boundary, obtain the boundary coordinates of each boundary mapping point, and calculate the average coordinates of all boundary coordinates. The mapping point corresponding to the average coordinate is identified as the center point of the temperature distribution; The temperature collection points within the same three-dimensional temperature center block are determined, and the distance between each temperature collection point and the temperature distribution center point is calculated and recorded as the inter-point distance.

3. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 1, characterized in that: The method for establishing the association between the parameter feature array sequence and the asphalt melting quality includes: Use needle penetration test, softening point test and viscosity test to judge the melting quality of asphalt, and quantify the judgment results to obtain melting quality parameters; The methods for quantifying the judgment results include: For the needle penetration test, a corresponding group of needle penetration intervals is set, wherein each needle penetration interval is set with a first preset melting quality parameter; for the softening point test, a corresponding group of softening point intervals is set, wherein each softening point interval is set with a second preset melting quality parameter; for the viscosity test, a corresponding group of viscosity intervals is set, wherein each annual interval is set with a third preset melting quality parameter; Based on the relationship between the needle penetration test results, softening point test results and viscosity test results in the corresponding groups of their respective intervals, the corresponding first preset melting mass parameter, second preset melting mass parameter and third preset melting mass parameter are called for comprehensive comparison and calculation to obtain the melting mass parameter.

4. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 3, characterized in that: The expression for calculating the melting mass parameter is: Among them, H is the melting mass parameter, is the weight coefficient of the first preset melting quality parameter, is the first preset melting quality parameter, is the weight coefficient of the second preset melting quality parameter, is the second preset melting quality parameter, is the weight coefficient of the third preset melting quality parameter, The third preset melting quality parameter.

5. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 1, characterized in that: The method of configuring characteristic factors for the characteristic array of temperature distribution parameters using the characteristic analysis model includes: Classifying the quantized melting quality parameters for the preset difference intervals, and classifying the parameter feature array sequences based on the classification of the melting quality parameters to obtain a plurality of parameter feature array sequence sets; Aligning each temperature distribution parameter feature array sequence in the parameter feature array sequence set, and comparing the temperature distribution parameter feature arrays in the temperature distribution parameter feature array sequence one by one, if the difference features between the temperature distribution parameter feature arrays of the same sequence meet the equivalent standard, then marking the temperature distribution parameter feature array of the sequence as a weak characteristic temperature distribution parameter feature array, and marking the remaining other temperature distribution feature arrays as medium characteristic temperature distribution parameter feature arrays; Analyze the difference characteristics of the medium characteristic temperature distribution parameter characteristic arrays of the same order between the parameter characteristic array sequences, determine the difference characteristic parameters of each order, and continuously analyze the difference characteristic parameters. If the continuous difference characteristic parameters show a monotonic change trend, the temperature distribution parameter characteristic array corresponding to the difference characteristic parameter is identified as a strong characteristic temperature distribution parameter characteristic array; The order of the strong characteristic temperature distribution parameter characteristic array in the parameter characteristic array sequence is identified as the first characteristic factor.

6. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 5, characterized in that: The temperature values ​​at different points in the characteristic array of the strong characteristic temperature distribution parameter are identified as the second characteristic factor.

7. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 5, characterized in that: The method for analyzing the difference characteristics of medium characteristic temperature distribution parameter characteristic arrays of equal order between parameter characteristic array sequences includes: Randomly selecting medium characteristic temperature distribution parameter feature arrays of equal order for pairwise combination, recorded as parameter feature array random group, comparing temperature values ​​and inter-point distances of equal points between medium characteristic temperature distribution parameter feature arrays of the parameter feature array random group, determining temperature value differences and inter-point distances of equal points, and determining average temperature value differences and average inter-point distances between the parameter feature array random groups; A first difference characteristic operator is constructed based on the difference in average temperature values ​​of equivalent points, and a second difference characteristic operator is constructed based on the average distance between equivalent points. Based on the first difference characteristic operator and the second difference characteristic operator, a difference characteristic parameter is determined.

8. The method for analyzing internal temperature data of an asphalt melting furnace according to claim 7, characterized in that: The expression of the difference characteristic parameter is: Among them, T is the difference characteristic parameter, is the average temperature difference of the i-th equivalent point between the characteristic arrays of the medium characteristic temperature distribution parameter, is the average distance between the i-th equivalent points in the characteristic array of the medium characteristic temperature distribution parameter, n is the total number of points in the characteristic array of the medium characteristic temperature distribution parameter, is the average point distance magnification adjustment coefficient, is the average point distance multiplication adjustment constant.

9. An analysis system based on the asphalt melting furnace internal temperature data analysis method according to claim 1, characterized in that: include: The first module is used to determine the cavity structure of the asphalt melting furnace and construct a virtual three-dimensional cavity based on the cavity structure. Based on the relative position of the temperature sensor device in the cavity structure of the asphalt melting furnace, corresponding temperature collection points are set in the virtual three-dimensional cavity; The second module is used to determine the temperature distribution characteristics of the side of the asphalt melting furnace using thermal imaging detection technology, and map the determined temperature distribution characteristics onto the virtual three-dimensional cavity. The temperature values ​​collected at different temperature collection points are combined to determine the distance between each temperature collection point in the virtual three-dimensional cavity and the center point of the temperature distribution to which it belongs; The third module is used to construct a temperature distribution parameter feature array based on the relative positions of different temperature collection points. The temperature distribution parameters include the temperature values ​​collected by the temperature collection points and the distances between the points. Based on the positions of the temperature collection points in the virtual three-dimensional cavity, the corresponding temperature distribution parameters are determined in the temperature distribution parameter feature array. The fourth module is used to sort the temperature distribution parameter feature array based on the time series relationship to obtain a parameter feature array sequence, establish an association between the parameter feature array sequence and the asphalt melting quality, and integrate several association relationships to obtain an asphalt melting quality relationship library; The fifth module is used to configure characteristic factors for the temperature distribution parameter characteristic array using the characteristic analysis model, and to establish an index relationship of the asphalt melting quality relationship library based on the characteristic factors.

Images