Method, device and equipment for testing working performance of asphalt mixture and storage medium

Abstract

The invention discloses an asphalt mixture working performance testing method, device and equipment and a storage medium, relates to the technical field of mixture performance testing, and aims to solve the problem that the testing precision of the working performance of an asphalt mixture is low. The method comprises the following steps: firstly, setting a test temperature range according to a material formula and a construction environment; then, torque, temperature and visual signals are collected through a multi-mode sensor array, and the height of a stirring paddle is adjusted in a self-adaptive mode based on the abnormal signal type so as to ensure the testing stability; after the signal is normal, acquiring multi-source time sequence data including torque, temperature and visual data, calculating a torque median reference line by adopting a dynamic sliding time window with a self-adaptive window size, and generating a target confidence interval for dynamically adjusting a boundary; and finally, judging a lower limit critical temperature point and an upper limit critical temperature point by comprehensively judging the trend of the glossiness attenuation coefficient and the torque median or the torque median datum line in the visual data, so as to determine the construction performance window.

Description

Technical Field

[0001] This application relates to the field of mixture performance testing technology, and in particular to a method, apparatus, equipment and storage medium for testing the workability of asphalt mixtures. Background Technology

[0002] The key to the construction quality of asphalt mixture pavement lies in the precise control of the temperature-sensitive characteristics of the asphalt mixture. The core of the entire process is to deliver the mixture to the site within the optimal temperature window and complete the paving.

[0003] In traditional construction scenarios, asphalt-based mixtures are relatively insensitive to variables such as temperature and transportation time. Experienced construction workers can rely on subjective experience, such as visual observation and touch, to cope with temperature fluctuations on site, thereby ensuring the final compaction quality. However, with the development of road engineering, to meet different structural performance (such as heavy load capacity) and non-structural performance (such as aesthetics and noise reduction) requirements, new types of mixtures such as modified asphalt, porous asphalt, and colored asphalt are widely used. The construction characteristics of these new materials differ significantly from those of traditional base asphalt. Their suitable temperature windows are narrower and more unpredictable, making it impossible for construction workers to rely on traditional experience to accurately judge the workability of asphalt mixtures.

[0004] Therefore, there is an urgent need for a testing method that can improve testing accuracy and scientifically define the construction performance window. Summary of the Invention

[0005] The purpose of this application is to provide a method, apparatus, equipment and storage medium for testing the workability of asphalt mixtures, aiming to solve the problem of low testing accuracy of asphalt mixture workability.

[0006] To achieve the above objectives, this application adopts the following technical solution: This application provides a method for testing the workability of asphalt mixtures. The method includes: setting a starting temperature and an ending temperature based on the material formulation and target construction environment of the asphalt mixture to form a test temperature reference range; acquiring multi-source signals based on a multi-modal sensor array, including torque signals, multi-point temperature signals, and visual signals, with the multi-point temperature signals acquired with reference to the test temperature reference range; assigning weights to the multi-source signals according to the type of abnormal signals in the multi-source signals and a preset weighting rule, and calculating a height adjustment coefficient for the mixing paddle based on the weights, driving the mixing paddle to adjust its height vertically in preset steps until the multi-source signals meet preset normal conditions; acquiring multi-source time-series data, including torque data, temperature data, and visual data, when the multi-source signals meet the preset normal conditions; and using a dynamic sliding time window... The median torque of the torque data is calculated to form a torque median baseline. A target confidence interval is generated based on the torque median baseline. The size of the dynamic sliding time window is adaptively adjusted according to the temperature change rate of the asphalt mixture, and the boundary of the target confidence interval is dynamically adjusted according to the dispersion of the torque data. When the gloss decay coefficient in the visual data is greater than or equal to the preset lower limit coefficient, the temperature point corresponding to the first time the median torque exceeds the lower boundary of the target confidence interval for the first time is determined as the lower limit critical temperature point. When the gloss decay coefficient is less than or equal to the preset upper limit coefficient, the temperature point corresponding to the first time the torque median baseline decreases for the first time for the second preset number of windows is determined as the upper limit critical temperature point. The workability window of the asphalt mixture is the temperature range between the upper limit critical temperature point and the lower limit critical temperature point.

[0007] The asphalt mixture workability testing method provided in this application provides an accurate initial framework for testing by setting a personalized test temperature reference range based on material formulation and construction environment. Then, a multi-modal sensor array is used to simultaneously collect torque, temperature, and visual signals, achieving multi-dimensional perception of the mixture's working state. Furthermore, by dynamically allocating weights according to the type of abnormal signals and adaptively adjusting the mixing paddle height, shear surface interference caused by uneven loading or local resistance is effectively suppressed, ensuring the stability of the data acquisition process. Based on this, a dynamic sliding time window is used to analyze torque data, with the window size adaptively adjusted according to the rate of temperature change. A target confidence interval with dynamically adjusted boundaries based on data dispersion is generated, making the capture of the median torque trend more accurately reflect the essential changes in the mixture's viscosity. Finally, by fusing the gloss attenuation coefficient in the visual signal with the trends of the median torque and the median torque baseline, the upper and lower critical temperature points are accurately determined, thereby improving the testing accuracy of the asphalt mixture workability window.

[0008] In some embodiments, the above-mentioned setting of the starting temperature and ending temperature for testing based on the material formulation of the asphalt mixture and the target construction environment to form a test temperature reference range includes: determining the starting temperature based on the design mixing temperature of the asphalt mixture and the expected temperature loss under the target construction environment; determining the ending temperature based on the softening point temperature of the asphalt mixture and the failure temperature of similar mixtures in historical construction performance data, wherein the failure temperature is the temperature point at which the mixture loses its working performance; and determining the test temperature reference range based on the starting temperature and the ending temperature.

[0009] Based on this, this application sets the starting temperature by combining the design mixing temperature and the temperature loss of the construction environment, and sets the termination temperature by combining the softening point and historical failure data. This allows the test range to not only realistically simulate the on-site working conditions, but also focus on the range where the material properties undergo key changes, laying a reasonable foundation for subsequent accurate analysis.

[0010] In some embodiments, before acquiring multi-source signals based on the multimodal sensor array, the mixing shaft and mixing container can be preheated to the initial temperature and maintained for a preset time; the mixed asphalt mixture is transferred to the mixing container, and a surface image of the asphalt mixture is acquired through a vision sensing unit; if no gaps are shown in the surface image, the mixing paddle is inserted into the asphalt mixture at a constant speed until the asphalt mixture completely covers the mixing blades of the mixing paddle.

[0011] Based on this, this application effectively avoids interference such as torque signal abrupt changes caused by uneven initial temperature or shear surface of the loading by standardizing the operation of inserting the stirring paddle after preheating the components and visually confirming that there are no gaps, thus ensuring the accuracy and consistency of data acquisition in the initial stage of the test.

[0012] In some embodiments, the types of the above-mentioned abnormal signals include at least one of the following: the instantaneous fluctuation of the torque signal exceeds the normal fluctuation threshold, the local temperature gradient of the multi-point temperature signal is abnormal, and there are abnormal visual signal points in the visual signal, wherein the abnormal visual signal points are signal points corresponding to the shear surface in the asphalt mixture.

[0013] Based on this, this application specifically defines torque fluctuation, abnormal temperature gradient, and visual shear surface as abnormality types, so that the weighted impeller height adjustment strategy has a clear judgment basis, thereby eliminating various local interferences in a more targeted manner and improving the stability of the test process.

[0014] In some embodiments, the acquisition of multi-source time-series data includes: directly measuring the rotational torque on the mixing impeller through a torque measurement unit to obtain torque data; acquiring the internal temperature, surface temperature, and ambient temperature of the asphalt mixture through a multi-point temperature acquisition unit to obtain temperature data; capturing the appearance texture video stream of the asphalt mixture during the mixing process through a visual sensing unit to obtain visual data; performing filtering and noise reduction processing on the rotational torque to separate the low-frequency torque signal and high-frequency torque noise, where the low-frequency torque signal represents the overall viscosity of the asphalt mixture and the high-frequency torque noise represents the instantaneous jamming of the asphalt mixture; performing image processing on the appearance texture video stream to extract the gloss attenuation coefficient, particle segregation index, and agglomeration area ratio as visual features; calibrating the surface temperature and ambient temperature based on the internal temperature to obtain standard temperature values, and using the standard temperature values ​​to time-align the low-frequency torque signal and visual features to form multi-source time-series data.

[0015] Based on this, this application separates the intrinsic and noise components of the torque signal by filtering, extracts key visual features, and then performs temperature calibration and time alignment to obtain fused data that accurately reflects the viscosity, texture evolution and temperature correlation of the mixture, providing a reliable data foundation for subsequent accurate determination of critical points.

[0016] In some embodiments, the asphalt mixture workability testing method provided in this application may further include: generating a fusion characteristic curve based on a standard temperature value and a low-frequency torque signal, wherein the fusion characteristic curve characterizes the relationship between temperature, torque and time; marking the workability window, upper limit critical temperature point and lower limit critical temperature point on the fusion characteristic curve; and forming a workability test report based on the marked fusion characteristic curve and key state images collected by the visual sensing unit, wherein the key state images include at least the mixing start time image and the mixing end time image.

[0017] Based on this, this application generates fusion feature curves and labels key parameters, and then combines key state images to present the test results in a visualized and integrated report, intuitively demonstrating the evolution of working performance with temperature.

[0018] In some embodiments, the asphalt mixture workability testing method provided in this application may further include: comparing the workability window with the temperature of the target construction environment to generate operation suggestions for mixing equipment, transportation process or compaction equipment; generating temperature control accuracy suggestions when the slope of the torque median baseline within the workability window exceeds a preset slope; and integrating the operation suggestions and temperature control accuracy suggestions based on preset equipment parameter adjustment rules to output workability adaptation suggestions, wherein the workability adaptation suggestions include specific parameter adjustment values.

[0019] Based on this, this application compares the measured performance window with the field environment and analyzes the slope of torque change within the window to directly generate parameterized suggestions for specific equipment and processes, thereby achieving precise control from laboratory testing to the construction site to ensure construction quality.

[0020] This application provides an asphalt mixture workability testing device, comprising: a setting unit for setting the starting and ending temperatures of the test based on the material formulation of the asphalt mixture and the target construction environment, forming a test temperature reference range; an acquisition unit for acquiring multi-source signals based on a multi-modal sensor array, the multi-source signals including torque signals, multi-point temperature signals, and visual signals, the multi-point temperature signals being acquired with reference to the test temperature reference range; an execution unit for assigning weights to the multi-source signals according to the type of abnormal signals in the multi-source signals and a preset weighting rule, and calculating the height adjustment coefficient of the mixing paddle based on the weights, driving the mixing paddle to adjust its height vertically in preset steps until the multi-source signals meet preset normal conditions; the acquisition unit is further configured to acquire multi-source time-series data, including torque data, temperature data, and visual data, when the multi-source signals meet the preset normal conditions; and generate... The unit is used to calculate the median torque of the torque data based on a dynamic sliding time window, form a torque median baseline, and generate a target confidence interval based on the torque median baseline. The window size of the dynamic sliding time window is adaptively adjusted according to the temperature change rate of the asphalt mixture, and the boundary of the target confidence interval is dynamically adjusted according to the dispersion of the torque data. The judgment unit is used to: determine the temperature point corresponding to the first time that the median torque exceeds the lower boundary of the target confidence interval when the gloss decay coefficient in the visual data is greater than or equal to a preset lower decay limit coefficient, and determine the temperature point corresponding to the first time that the median torque exceeds the lower boundary of the target confidence interval when the gloss decay coefficient is less than or equal to a preset upper decay limit coefficient, as the upper limit critical temperature point when the median torque baseline decreases for the first time. The workability window of the asphalt mixture is the temperature range between the upper limit critical temperature point and the lower limit critical temperature point.

[0021] In some embodiments, the setting unit is specifically used to: determine the starting temperature based on the design mixing temperature of the asphalt mixture and the expected temperature loss under the target construction environment; determine the ending temperature based on the softening point temperature of the asphalt mixture and the failure temperature of similar mixtures in historical construction performance data, wherein the failure temperature is the temperature point at which the mixture loses its working performance; and determine the test temperature reference range based on the starting temperature and the ending temperature.

[0022] In some embodiments, the execution unit is further configured to preheat the mixing shaft and the mixing container to the initial temperature and maintain it for a preset time, and transfer the mixed asphalt mixture to the mixing container; the acquisition unit is further configured to acquire a surface image of the asphalt mixture through a visual sensing unit; the execution unit is further configured to insert the mixing paddle into the asphalt mixture at a constant rotation speed when the surface image shows no gaps, until the asphalt mixture completely covers the mixing blades of the mixing paddle.

[0023] In some embodiments, the types of the above-mentioned abnormal signals include at least one of the following: the instantaneous fluctuation of the torque signal exceeds the normal fluctuation threshold, the local temperature gradient of the multi-point temperature signal is abnormal, and there are abnormal visual signal points in the visual signal, wherein the abnormal visual signal points are signal points corresponding to the shear surface in the asphalt mixture.

[0024] In some embodiments, the acquisition unit is specifically used for: directly measuring the rotational torque on the mixing blade through the torque measurement unit to obtain torque data; acquiring the internal temperature, surface temperature, and ambient temperature of the asphalt mixture through the multi-point temperature acquisition unit to obtain temperature data; capturing the appearance texture video stream of the asphalt mixture during the mixing process through the visual sensing unit to obtain visual data; performing filtering and noise reduction processing on the rotational torque to separate the low-frequency torque signal and the high-frequency torque noise, where the low-frequency torque signal represents the overall viscosity of the asphalt mixture and the high-frequency torque noise represents the instantaneous jamming of the asphalt mixture; performing image processing on the appearance texture video stream to extract the gloss attenuation coefficient, particle segregation index, and agglomeration area ratio as visual features; calibrating the surface temperature and ambient temperature based on the internal temperature to obtain a standard temperature value, and using the standard temperature value to time-align the low-frequency torque signal and visual features to form multi-source time-series data.

[0025] In some embodiments, the above-mentioned generation unit is further configured to: generate a fusion characteristic curve based on the standard temperature value and the low-frequency torque signal, wherein the fusion characteristic curve characterizes the relationship between temperature, torque and time; mark the construction performance window, the upper limit critical temperature point and the lower limit critical temperature point on the fusion characteristic curve; and form a work performance test report based on the marked fusion characteristic curve and the key state images collected by the visual sensing unit, wherein the key state images include at least the image at the start of mixing and the image at the end of mixing.

[0026] In some embodiments, the above-mentioned generation unit is further configured to: compare the construction performance window with the temperature of the target construction environment to generate operation suggestions for mixing equipment, transportation process or compaction equipment; generate temperature control accuracy suggestions when the slope of the torque median baseline within the construction performance window exceeds a preset slope; and integrate the operation suggestions and temperature control accuracy suggestions based on preset equipment parameter adjustment rules to output working performance adaptation suggestions, wherein the working performance adaptation suggestions include specific parameter adjustment values.

[0027] This application provides an electronic device, including: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute instructions to implement the asphalt mixture workability testing method described above.

[0028] This application provides a computer-readable storage medium storing instructions that, when executed on a terminal, cause the terminal to perform the asphalt mixture workability test method described above.

[0029] This application provides a computer program product containing instructions that, when executed by a computer, cause the computer to perform the asphalt mixture workability test method described above.

[0030] This application provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled together. The processor is used to run computer programs or instructions to implement the asphalt mixture performance testing method described above.

[0031] Specifically, the chip provided in this application embodiment also includes a memory for storing computer programs or instructions. Attached Figure Description

[0032] To more clearly illustrate the technical solutions of the embodiments of this application, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0033] Figure 1 A flowchart illustrating a method for testing the workability of asphalt mixtures, as provided in this application embodiment; Figure 2 A flowchart illustrating another method for testing the workability of asphalt mixtures provided in this application embodiment; Figure 3 This is a fusion characteristic curve diagram corresponding to a method for testing the workability of asphalt mixtures provided in an embodiment of this application; Figure 4 A structural diagram of an asphalt mixture workability testing device provided in an embodiment of this application; Figure 5 This is a structural diagram of an electronic device provided in an embodiment of this application. Detailed Implementation

[0034] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0035] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "rear," "inner," and "outer," etc., indicate the orientation or positional relationship based on the orientation or relative positional relationship shown in the accompanying drawings. They are used only for the convenience of describing this application and for simplification, and do not indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned orientational descriptions can be flexibly set in practical applications, provided that the relative positional relationships shown in the accompanying drawings are satisfied.

[0036] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Therefore, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this application, unless otherwise stated, "a plurality of" means two or more.

[0037] In the description of this application, it should be noted that, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," and "communication" should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection. They can refer to a direct connection or an indirect connection through an intermediate medium, or a connection within two components. Those skilled in the art can understand the specific meaning of the above terms in this application according to the specific circumstances.

[0038] In some embodiments, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, article, or apparatus. Without further limitation, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, article, or apparatus that includes that element.

[0039] In some embodiments, the words "exemplary" or "for example" are used to indicate that something is an example, illustration, or illustration. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being more preferred or advantageous than other embodiments or designs. Specifically, the use of the words "exemplary" or "for example" is intended to present the relevant concepts in a specific manner.

[0040] In the description of this specification, specific features, structures, materials, or characteristics may be combined in any suitable manner in one or more embodiments or examples.

[0041] The construction of asphalt pavement is a complex systems engineering project involving materials science, logistics management, and on-site processes. Excessively high or low paving and compaction temperatures can directly lead to pavement defects such as insufficient compaction.

[0042] In traditional construction scenarios, asphalt-based mixtures are less sensitive to variables such as temperature and transportation time. However, with the upgrading of performance requirements in road engineering, asphalt mixture technology is developing in multiple dimensions.

[0043] On the one hand, the types of mixtures are becoming increasingly diverse, expanding from traditional dense types to porous types, color-customized types, and other special functional mixtures. On the other hand, different application scenarios, such as heavy-duty road surface layers and secondary road base layers, place differentiated requirements on the performance of mixtures.

[0044] On the other hand, the promotion of integrated design and construction projects has driven the application of new types of asphalt (such as modified asphalt) to extend road life. At the same time, the mixture also needs to meet non-structural performance requirements such as aesthetics, driving comfort, and noise reduction.

[0045] Therefore, the traditional experience-based operating model can no longer meet the construction control requirements of new asphalt mixtures, and it is difficult to accurately measure the working performance of asphalt mixtures.

[0046] Against this backdrop, to address the issue of low accuracy in testing the workability of asphalt mixtures in related technologies, this application provides a method, apparatus, equipment, and storage medium for testing the workability of asphalt mixtures. The method involves acquiring signals using a multimodal sensor array and adaptively adjusting the mixing paddle height to ensure test stability. Then, a dynamic sliding time window is used to analyze torque data to form an adaptive confidence interval. Finally, the visual gloss decay coefficient and torque characteristics are fused to accurately and automatically determine the upper and lower critical temperature points of the workability window.

[0047] The following is a reference. Figures 1 to 3 The method for testing the workability of asphalt mixtures provided in the embodiments of this application is described.

[0048] Figure 1This is a flowchart of the method for testing the workability of asphalt mixtures provided in the embodiments of this application. The main body executing this method can be an electronic device or various devices / modules of the electronic device, such as integrated circuits or chips. The embodiments of this application do not specifically limit this.

[0049] For example, such as Figure 1 As shown, the asphalt mixture workability testing method provided in this application embodiment may include the following S101 to S108: S101. Based on the material formulation of asphalt mixture and the target construction environment, set the starting temperature and ending temperature of the test to form a test temperature reference range.

[0050] In some embodiments, the initial temperature can be determined based on the design mixing temperature of the asphalt mixture and the expected temperature loss under the target construction environment.

[0051] In the embodiments of this application, the design mixing temperature refers to the optimal temperature at which the various components of the asphalt mixture (aggregate and asphalt binder) are fully mixed in the mixing mill and the uniformity of the mixture is guaranteed. For example, the design mixing temperature for 40 / 60 penetration asphalt is 160°C; the design mixing temperature for polymer-modified bitumen-styrene-butadiene-styrene (PMB-SBS) is 185°C.

[0052] In this embodiment, the expected temperature loss refers to the temperature drop of the asphalt mixture after it is discharged from the mixing plant, during transportation, and while waiting to be paved, due to environmental factors (wind speed, humidity, transportation distance). For example, if the target construction environment has a wind speed of 3 m / s, humidity of 65%, and a transportation distance of 2 km, then the expected temperature loss can be calculated as (1 + 5% + 3%) × (2 × 2) = 4.32℃ according to the formula: "Temperature loss = (1 + additional loss 5% (wind speed > 3 m / s) + additional loss 3% (humidity > 60%)) × base loss (2℃ loss per 1 km of transportation)".

[0053] For example, the starting temperature can be determined by superimposing the design mixing temperature and the expected temperature loss on the specific mixture type.

[0054] For example, take asphalt mixture with a penetration of 70 / 100 asphalt. Its design mixing temperature is 160℃. If the expected temperature loss is calculated to be 4℃, then the initial temperature is set to 160℃ + 4℃ = 164℃.

[0055] For example, consider PMB-SBS modified asphalt as an example. Its design mixing temperature is 185℃. If the expected temperature loss is calculated to be 3.5℃, then the initial temperature is set to 188.5℃.

[0056] In some embodiments, the termination temperature can be determined based on the softening point temperature of the asphalt mixture and the failure temperature of similar mixtures in historical construction performance data.

[0057] In the embodiments of this application, the softening point temperature refers to the critical temperature at which the asphalt binder changes from a viscoelastic state to a viscous state. For example, the softening point temperature of 40 / 60 penetration asphalt is approximately 70°C, the softening point temperature of 70 / 100 penetration asphalt is approximately 60°C, and the softening point temperature of PMB-SBS modified asphalt is approximately 80°C.

[0058] In this embodiment, the failure temperature is the temperature at which the mixture loses its workability. For example, the historical failure temperature of 40 / 60 penetration asphalt is 68°C.

[0059] For example, the termination temperature can be determined by taking the minimum value between the historical failure temperature of similar mixtures and the softening point temperature of the asphalt used in the current mixture.

[0060] For example, taking asphalt mixture with a penetration of 70 / 100 asphalt as an example. Its historical failure temperature is 58℃ and its softening point temperature is 60℃, so the termination temperature is set to 58℃.

[0061] For example, consider a high-modulus asphalt mixture. Its historical failure temperature is 78℃ and its softening point temperature is 80℃, so the termination temperature is set to 78℃.

[0062] Furthermore, the test temperature reference range can be determined based on the starting temperature and the ending temperature.

[0063] For example, a continuous temperature range can be formed by setting the starting temperature as the upper limit and the ending temperature as the lower limit, which can be used as the test temperature reference range. For instance, if the starting temperature of PMB-SBS modified asphalt is 188.5℃ and the ending temperature is 78℃, then the test temperature reference range is 78℃-188.5℃.

[0064] Thus, by combining the design mixing temperature with the temperature loss of the construction environment to set the starting temperature, and by comprehensively considering the softening point and historical failure data to set the ending temperature, the test range can not only realistically simulate the on-site working conditions, but also focus on the range where the material properties undergo key changes, laying a reasonable foundation for subsequent accurate analysis.

[0065] S102. Acquire multi-source signals based on a multi-modal sensor array.

[0066] In this embodiment, the multi-source signals may include torque signals, multi-point temperature signals, and visual signals. The multi-point temperature signals are acquired with reference to a test temperature reference range.

[0067] Specifically, the test temperature reference range will serve as the reference for multi-point temperature signal acquisition. For example, when the temperature is at the upper limit of the reference range (188.5℃), the temperature acquisition frequency is set to 1 time / 5s; when the temperature is in the middle of the reference range (around 130℃), the temperature acquisition frequency is set to 1 time / 10s; and when the temperature is at the lower limit of the reference range (78℃), the temperature acquisition frequency is set to 1 time / 3s.

[0068] Optionally, the multimodal sensor array may include a torque sensing unit, a multi-point temperature sensing unit, and a vision sensing unit.

[0069] For example, the torque signal refers to the real-time measurement signal of the flow resistance torque of the asphalt mixture experienced by the rotating mixing paddle through a torque sensing unit. The torque sensing unit can be a shaft-to-shaft rotary torque sensor or an integrated encoder.

[0070] Specifically, when the agitator rotates at 15 rpm, the rotational torque sensor can output continuous torque values ​​such as 20 Nm, 20.1 Nm, and 19.9 Nm in real time.

[0071] For example, the multi-point temperature signal refers to the temperature signals of the asphalt mixture and the environment collected at different locations in the mixer by the multi-point temperature sensing unit. The multi-point temperature signal may include three sets of sensors: sensor 1 is an infrared thermometer, aimed at the surface of the mixture inside the mixing container; sensor 2 is a contact temperature sensor, installed in the middle of the side wall of the mixing container; sensor 3 is an embedded temperature sensor, inserted into the center of the mixing shaft.

[0072] Specifically, within the test temperature reference range of 163.5℃-58℃, when the temperature is 160℃, sensor 1 measures a surface temperature of 158℃, sensor 2 measures a sidewall temperature of 159℃, and sensor 3 measures an internal shaft temperature of 160℃.

[0073] For example, the visual signal refers to the video stream signal of the apparent texture of the asphalt mixture during the mixing process, obtained through a visual sensing unit. The visual sensing unit can be a high-definition industrial camera, installed 1.5m directly above the mixing container, to capture in real time the presence of voids, segregation, shear surfaces, and other conditions on the surface of the mixture.

[0074] Specifically, when the high-definition industrial camera captures images of a mixture surface without obvious voids, it outputs a normal visual signal; when the captured image shows a sheared area with abrupt changes in grayscale values, it outputs an abnormal visual signal.

[0075] Optionally, before acquiring multi-source signals, the stirring shaft and stirring container can be preheated to the starting temperature and maintained for a preset time.

[0076] For example, the preset time can be determined according to the volume of the mixing container: when the container volume is <100L, the preset time is 30 minutes; when the container volume is ≥100L, the preset time is 60 minutes.

[0077] Specifically, taking a stirring container with a volume of 80L as an example (its effective capacity is 0.0150m³, corresponding to a sample mass of 20-30kg), the stirring shaft and the stirring container can be preheated to an oven with an initial temperature of 164℃ and kept there for 30 minutes to ensure that the temperature of the stirring shaft (including the stirring blades) and the inner wall of the stirring container both reach 164℃.

[0078] Further, the mixed asphalt mixture is transferred to a mixing container, and a surface image of the asphalt mixture is acquired through a vision sensing unit.

[0079] For example, the prepared asphalt mixture can be quickly poured from the 30L horizontal mixer into the preheated mixing container. Then, the vision sensing unit (industrial camera) is activated to take three images of the surface of the mixture in the container. The shooting angles are directly above, 45° to the upper left, and 45° to the upper right, respectively, to ensure that the entire surface area is covered. If the surface of the mixture is free of depressions and holes and the particles are evenly distributed in the captured images, it is preliminarily determined that the loading is qualified.

[0080] Specifically, voids in surface images can be identified using image processing algorithms: set a grayscale threshold of 120 (0-255 grayscale range), and when the area of ​​regions with grayscale values ​​> 120 (representing voids) in the image accounts for less than 1%, the surface is determined to be void-free; if the proportion is ≥ 1%, the surface of the mixture needs to be gently compacted with a scraper to eliminate voids, and the image is retaken until the void-free requirement is met.

[0081] Furthermore, when the surface image shows no voids, the mixing paddle is inserted into the asphalt mixture at a constant speed until the asphalt mixture completely covers the mixing blades of the mixing paddle.

[0082] For example, the constant rotation speed of the agitator can be set to 15 rpm (comparative tests have verified that 15 rpm can effectively reduce segregation and agglomeration of the mixture, with minimal data fluctuation). The drive motor is started, and the agitator is controlled to slowly insert into the mixture at a speed of 5 mm / s. The agitator has 4 blades arranged at a 90° angle, with a blade height of 21 cm. When the visual sensing unit captures that the top of the blade (21 cm from the bottom of the blade) is completely covered by the mixture, the insertion is stopped.

[0083] Specifically, during the insertion process, the position of the stirring blade can be monitored in real time by the height sensor on the stirring shaft (e.g., the initial servo position is set to -65mm, and the final position after insertion is set to 290mm). At the same time, the torque sensing unit monitors the torque value in real time. If the torque value suddenly exceeds 30Nm (initial torque threshold), the insertion is immediately paused to check for blade jamming (e.g., agglomeration of the mixture). After troubleshooting, the insertion continues.

[0084] Thus, this application, through the standardized operation of preheating the components and visually confirming the absence of gaps before inserting the stirring paddle, effectively avoids interference such as sudden changes in torque signals caused by uneven initial temperature or shear surface of the loading, ensuring the accuracy and consistency of data acquisition in the initial stage of testing.

[0085] S103. Based on the type of abnormal signal in the multi-source signal, assign weights to the multi-source signal according to the preset weight allocation rules.

[0086] In this application embodiment, the type of abnormal signal includes at least one of the following A, B, and C: A. The instantaneous fluctuation of the torque signal exceeds the normal fluctuation threshold.

[0087] For example, the normal fluctuation threshold can be set to ±10% of the current median torque. For instance, if the median torque during a certain testing phase is 50 Nm, then the normal fluctuation range is 45 Nm-55 Nm.

[0088] Specifically, if the torque sensing unit measures a torque value of 61 Nm (exceeding 55 Nm) or 38 Nm (below 45 Nm) at a certain moment, the torque signal is determined to be an abnormal signal.

[0089] B. Local temperature gradient anomalies appear in multiple temperature signals.

[0090] For example, the criterion for judging local temperature gradient anomalies can be "the temperature difference measured by any two adjacent temperature sensors ÷ the distance between the sensors > 3℃ / cm".

[0091] Specifically, if sensor 2 (side wall) measures a temperature of 155℃ and sensor 3 (stirring shaft) measures a temperature of 161℃, and the horizontal distance between the two sensors is 2cm, then the temperature gradient = (161-155)℃ ÷ 2cm = 3℃ / cm. When the gradient > 3℃ / cm (e.g., a temperature difference of 7℃ and a distance of 2cm, resulting in a gradient of 3.5℃ / cm), it is determined to be an abnormal temperature gradient.

[0092] C. Abnormal visual signal points exist in the visual signal. These abnormal visual signal points are signal points corresponding to the shear surfaces in the asphalt mixture.

[0093] For example, image analysis using a visual sensing unit can identify abnormal visual signal points when a region with abrupt changes in grayscale values ​​(such as a shearing plane) appears in the image, and the area of ​​this region is greater than 5 cm². Specifically, if a rectangular area of ​​6cm×2cm appears in the image of the surface of the mixture, and the gray value suddenly changes from 100 to 180, and the area of ​​the area is 12cm²>5cm², then the area is the shear plane (relative sliding occurs inside the mixture), which corresponds to an abnormal visual signal.

[0094] In actual testing, if visual anomalies, torque fluctuation anomalies, and temperature gradient anomalies exist simultaneously, preset weights are assigned according to the degree of influence of the anomaly signals on the test data: visual shear plane has the greatest influence, with a weight of 0.6; torque fluctuation has the second greatest influence, with a weight of 0.3; and temperature gradient has the least influence, with a weight of 0.1. The comprehensive anomaly coefficient is calculated as (visual anomaly judgment value × 0.6) + (torque anomaly judgment value × 0.3) + (temperature anomaly judgment value × 0.1).

[0095] Specifically, an anomaly determination value of 1 indicates the presence of an anomaly, and an anomaly determination value of 0 indicates the absence of an anomaly. The calculated comprehensive anomaly coefficient = 1 × 0.6 + 1 × 0.3 + 1 × 0.1 = 1.0. Therefore, it is necessary to prioritize adjusting the height of the stirring paddle based on visual anomalies to eliminate the shear plane.

[0096] Thus, by specifically defining torque fluctuation, abnormal temperature gradient, and visual shear surface as abnormality types, this application provides a clear basis for the weighted impeller height adjustment strategy, thereby more effectively eliminating various local interferences and improving the stability of the testing process.

[0097] S104. Calculate the height adjustment coefficient of the agitator based on the weight, and drive the agitator to adjust its height in the vertical direction in a preset step size until the multi-source signals meet the preset normal conditions.

[0098] In this embodiment, the preset step size is a value set manually, which can be flexibly adjusted according to the actual scenario.

[0099] In one example, the preset step size can be set according to the total height of the mixing container, such as a preset step size of 0.1 cm.

[0100] In another example, the preset step size can also be set according to the height of the stirring blade. For example, if the blade height is 15cm, the preset step size is set to 0.15cm (1 / 100 of the blade height).

[0101] In this embodiment of the application, the preset normal conditions refer to the torque signal fluctuation being within the normal fluctuation threshold, the multi-point temperature signal not having an abnormal temperature gradient, and the visual signal not having any abnormal visual signal points.

[0102] Specifically, the stirring paddle can be adjusted vertically using the equipment's servo control system. The servo motor has an accuracy of 0.01cm. During the adjustment process, multi-source signals are monitored in real time. A 10-second pause is taken after every 0.1cm adjustment to collect torque, temperature, and visual signals, determining whether the abnormality has been alleviated. For example, after adjusting by 0.42cm, a new visual image is captured. If the shear area decreases from 12cm² to 3cm² (<5cm²), the torque fluctuation range recovers to 45Nm-55Nm, and the temperature gradient decreases to 2.5℃ / cm, it indicates that the multi-source signals meet the preset normal conditions, and the height adjustment is stopped.

[0103] S105. Under the condition that the multi-source signals meet the preset normal conditions, acquire multi-source time-series data.

[0104] In this embodiment of the application, multi-source time-series data may include torque data, temperature data, and visual data.

[0105] In some embodiments, the rotational torque on the agitator can be directly measured by a torque measuring unit to obtain torque data.

[0106] For example, the sampling frequency of the torque measurement unit, i.e., the shaft-to-shaft rotation torque sensor, can be set to 1Hz, and the measurement data can be stored in the form of "time-torque value". For example, the torque measured on April 25, 2025 at 10:44:13 is 64Nm, the torque measured at 10:44:14 is 64Nm, and the torque measured at 10:44:15 is 64Nm.

[0107] Furthermore, the rotational torque can be filtered and noise-reduced to separate the low-frequency torque signal and the high-frequency torque noise.

[0108] Among them, the low-frequency torque signal represents the overall viscosity of the asphalt mixture, while the high-frequency torque noise represents the instantaneous jamming of the asphalt mixture.

[0109] For example, wavelet denoising (WD) can be used, selecting the db4 wavelet basis and decomposing it into 3 layers to decompose the original torque data (such as 64 Nm, 65.2 Nm, 63.8 Nm, 66.5 Nm, 62.1 Nm).

[0110] Specifically, the first layer decomposition yields high-frequency coefficient d1 (representing high-frequency torque noise) and low-frequency coefficient a1; the second layer decomposition of a1 yields high-frequency coefficients d2 and a2; the third layer decomposition of a2 yields high-frequency coefficients d3 and a3; then, the high-frequency coefficients d1, d2, and d3 are processed with a soft threshold (e.g., the threshold is set to 1.5 × root mean square noise), and then the denoised low-frequency torque signal (e.g., 64.0 Nm, 64.2 Nm, 64.1 Nm, 64.3 Nm, 64.0 Nm) is obtained through wavelet reconstruction, and the high-frequency torque noise (e.g., 1.2 Nm, -1.0 Nm, 2.4 Nm, -2.2 Nm) is removed.

[0111] Optionally, to ensure data accuracy, the shaft-to-shaft rotation torque sensor can be calibrated before actual measurement by applying a standard torque (such as 50 Nm or 100 Nm) and adjusting the sensor output value so that the error between the sensor output value and the standard torque is ≤0.5%. For example, when applying a standard torque of 50 Nm, a sensor output of 49.8 Nm-50.2 Nm is considered acceptable.

[0112] In some embodiments, the internal temperature, surface temperature, and ambient temperature of the asphalt mixture can be collected by a multi-point temperature acquisition unit to obtain temperature data.

[0113] For example, the surface temperature can be measured by sensor 1 (infrared thermometer), the temperature of the mixture near the side wall of the container can be measured by sensor 2 (side wall contact sensor), and the internal temperature of the mixture can be measured by sensor 3 (stirring shaft embedded sensor), with the sampling frequency set to 1Hz. For instance, at 10:44:13, sensor 1 measured a surface temperature of 77.3℃, sensor 2 measured a side wall temperature of 45.1℃, and sensor 3 measured an internal temperature of 35.3℃.

[0114] Furthermore, the surface temperature and ambient temperature can be calibrated using the internal temperature as a reference to obtain a standard temperature value.

[0115] For example, the collected temperature data can be calibrated using the internal temperature collected by sensor 3 as a reference to obtain a standard temperature value. The calibration formula is as follows: The surface temperature calibration value T1' = T1 + (T3 - T1) × 0.8.

[0116] The sidewall temperature calibration value T2' = T2 + (T3 - T2) × 0.5.

[0117] Standard temperature value T std = (T1' + T2' + 2 × T3) / 4.

[0118] Where T1 is the raw value collected by sensor 1, T2 is the raw value collected by sensor 2, and T3 is the raw value collected by sensor 3.

[0119] Specifically, if T1 = 77.3℃, T2 = 45.1℃, and T3 = 35.3℃, then the calculated values ​​are: T1' = 77.3 + (35.3 - 77.3) × 0.8 = 43.7℃, T2' = 45.1 + (35.3 - 45.1) × 0.5 = 40.2℃, T... std = (43.7 + 40.2 + 2 × 35.3) / 4 = 38.625℃.

[0120] Optionally, to ensure the accuracy of temperature data, each sensor can be calibrated with a standard thermometer (accuracy ±0.1℃) before testing. The sensors are placed in constant temperature oil baths at 50℃, 100℃, and 150℃. If the error between the sensor reading and the standard temperature is ≤±0.5℃, it is considered qualified.

[0121] In some embodiments, visual data can be obtained by capturing a video stream of the apparent texture of asphalt mixture during the mixing process using a visual sensing unit.

[0122] For example, a high-definition industrial camera can capture one frame of image every 10 seconds as a visual data sample, and the sample contains "time-image-standard temperature value" correlation information.

[0123] Furthermore, image processing can be performed on the apparent texture video stream to extract gloss attenuation coefficient, particle segregation index, and agglomeration area ratio as visual features.

[0124] For example, with 10:44:13 (T std Taking an image captured at 38.625℃ as an example, the following visual features can be extracted through image processing: 1) Gloss attenuation coefficient G: G = Current gloss G t / Initial gloss G0. Wherein, the initial gloss G0 is the gloss of the mixture surface at the start of the test (temperature 164℃) (calculated from the average grayscale value of the image, G0=80). If the current gloss G is the average grayscale value of this frame of image (e.g., G... t =60), then G=60 / 80=0.75.

[0125] 2) Particle segregation index S: S = (Segregation area / Total image area) × 100%. The segregation area is defined as the region where the particle size > 5 mm accounts for > 30% of the total area. If the analyzed image shows a segregation area of ​​9.6 cm² and a total image area of ​​282.7 cm² (container diameter 30 cm), then S = (9.6 / 282.7) × 100% ≈ 3.4%.

[0126] 3) Aggregate area percentage C: C = (aggregate area / total image area) × 100%. Aggregates are regions >1 cm² formed by particle aggregation. If the area of ​​the aggregates in the image is 5.7 cm², then C = (5.7 / 282.7) × 100% ≈ 2.0%.

[0127] Furthermore, standard temperature values ​​can be used to time-align low-frequency torque signals and visual features to form multi-source time-series data.

[0128] In some embodiments, the acquisition time of different signals can be uniformly mapped to the "standard temperature-time" axis.

[0129] For example, since temperature acquisition, torque acquisition, and visual acquisition are all 1Hz, but temperature changes have a lag (cooling rate < 0.1℃ / s), multiple time points may correspond to the same standard temperature value. For instance, the standard temperature value of 78.75℃ corresponds to three time points (e.g., 3598 seconds, 3599 seconds, and 3600 seconds), and the measured low-frequency torque signals are 68.3Nm, 68.5Nm, and 68.4Nm, respectively, with gloss attenuation coefficients of 0.602, 0.600, and 0.598. Then, the average value at this temperature is taken as the aligned data: low-frequency torque 68.4Nm, gloss attenuation coefficient 0.600, forming a correlated data point of "standard temperature 78.75℃ - torque 68.4Nm - gloss 0.6".

[0130] Specifically, the extracted visual features can be stored synchronously with the low-frequency torque signal and standard temperature value to form a multi-dimensional data table of "time (s) - standard temperature (°C) - low-frequency torque (Nm) - gloss decay coefficient - segregation index - agglomeration area ratio".

[0131] Table 1 shows the multi-dimensional data for 30-minute and 60-minute intervals. In real-world scenarios, more or fewer multi-dimensional data may be included, which are not listed here.

[0132] Table 1

[0133] Thus, this application separates the intrinsic and noise components of the torque signal by filtering, extracts key visual features, and then obtains fused data that accurately reflects the viscosity, texture evolution and temperature correlation of the mixture after temperature calibration and time alignment, providing a reliable data foundation for subsequent accurate determination of critical points.

[0134] S106. Calculate the median torque of the torque data based on the dynamic sliding time window, form a torque median baseline, and generate a target confidence interval based on the torque median baseline.

[0135] Optionally, the size of the dynamic sliding time window can be adaptively adjusted according to the rate of temperature change of the asphalt mixture.

[0136] For example, the rate of temperature change v = (current standard temperature T) k -The previous standard temperature T k-1 ) / (current time t) k -Previous moment time t k-1 (), the unit is ℃ / min.

[0137] Specifically, the rules for adjusting the window size can be as follows: When v > 5℃ / min (temperature drops rapidly, such as in the early stage of testing), the window size can be set to 10 seconds (corresponding to 10 data points).

[0138] When 2℃ / min < v ≤ 5℃ / min (temperature decreases at a moderate rate), the window size can be set to 30 seconds (30 data points).

[0139] When v ≤ 2℃ / min (temperature decreases slowly, approaching the termination temperature), the window size can be set to 180 seconds (180 data points).

[0140] For example, in the initial stage of the test (standard temperature 160℃), v = 6℃ / min, and the window size is 10 seconds. The median value of the 10 torque data points (e.g., 20Nm, 20.2Nm, 19.8Nm, etc.) within this window is 20.1Nm. In the middle stage of the test (standard temperature 100℃), v = 3℃ / min, and the window size is 30 seconds. The median value of the 30 torque data points is 45.3Nm. In the later stage of the test (standard temperature 80℃), v = 1.5℃ / min, and the window size is 180 seconds. The median value of the 180 torque data points is 68.5Nm.

[0141] For example, the moving step of the dynamic sliding window can be fixed at 10 seconds, that is, the median torque within the window is recalculated every 10 seconds, and the continuous median torque values ​​are connected in chronological order to form a torque median baseline.

[0142] For example, if the median value for 3590-3600 seconds (10-second window) is 68.3 Nm, the median value for 3600-3610 seconds is 68.5 Nm, and the median value for 3610-3620 seconds is 68.7 Nm, then we can obtain an ascending line segment from 68.3 Nm to 68.7 Nm, reflecting the increasing trend of torque as temperature decreases.

[0143] Optionally, the boundaries of the target confidence interval can be dynamically adjusted based on the dispersion of the torque data.

[0144] For example, the dispersion can be represented by the standard deviation σ of the torque data within the window, and the target confidence interval can be set as: median torque M ± k × σ.

[0145] Where k is the confidence coefficient, which can be determined according to the test accuracy requirements (e.g., 2 corresponds to a 95% confidence level).

[0146] Specifically, if the median torque data M = 45.3 Nm and the standard deviation σ = 2.5 Nm within a certain window (30 seconds) during the test, then the confidence interval = 45.3 ± 2 × 2.5 = (40.3 Nm - 50.3 Nm); if the median torque data M = 46.0 Nm and the standard deviation σ = 3.0 Nm in the next window (i.e., the data dispersion increases), then the confidence interval = 46.0 ± 2 × 3.0 = (40.0 Nm - 52.0 Nm), and the interval width expands from 10 Nm to 12 Nm.

[0147] S107. When the gloss attenuation coefficient in the visual data is greater than or equal to the preset attenuation lower limit coefficient, the temperature point corresponding to the first time when the median torque is greater than the lower boundary of the target confidence interval for the first time is determined as the lower limit critical temperature point.

[0148] In this embodiment, both the preset attenuation lower limit coefficient and the first preset window are manually set values ​​that can be flexibly adjusted according to the actual scenario. For example, the preset attenuation lower limit coefficient can be 0.6; the first preset window can be 5.

[0149] For example, the preset lower limit of attenuation coefficient G for 70 / 100 penetration bitumen. min =0.6, taking the first preset window number n1=5 as an example. When the test has been running for 1.5 hours (5400 seconds), if the gloss decay coefficient G=0.62≥0.6, then the judgment premise is met, and the relationship between the median torque and the lower boundary of the confidence interval is monitored.

[0150] Specifically: Window 1 (5400-5410 seconds): Median torque 70.2 Nm, lower boundary of confidence interval 65.0 Nm, 70.2 > 65.0 (satisfied for the first time); Window 2 (5410-5420 seconds): Median torque 70.5 Nm, lower boundary of confidence interval 65.2 Nm, 70.5 > 65.2 (satisfied for the second time); Window 3 (5420-5430 seconds): Median torque 70.8 Nm, lower boundary of confidence interval 65.5 Nm, 70.8 > 65.5 (satisfied for the third time). ); Window 4 (5430-5440 seconds): median torque 71.0 Nm, lower boundary of confidence interval 65.8 Nm, 71.0 > 65.8 (4th time satisfied); Window 5 (5440-5450 seconds): median torque 71.2 Nm, lower boundary of confidence interval 66.0 Nm, 71.2 > 66.0 (5th time satisfied), indicating that the condition is satisfied for the first time for 5 consecutive windows. The standard temperature value corresponding to this window is 60℃, so 60℃ is determined to be the lower limit critical temperature point (i.e., the lowest temperature at which the mixture can be applied).

[0151] S108. When the gloss attenuation coefficient is less than or equal to the preset attenuation upper limit coefficient, the temperature point corresponding to the first continuous decrease of the torque median baseline for the second preset window number is determined as the upper limit critical temperature point.

[0152] In this embodiment, both the preset attenuation upper limit coefficient and the second preset window are manually set values ​​that can be flexibly adjusted according to the actual scenario. For example, the preset attenuation upper limit coefficient can be 0.9; the second preset window can be 3.

[0153] For example, the preset attenuation upper limit coefficient G of 40 / 60 penetration bitumen. max =0.9, taking the second preset window number n2=3 as an example. At the beginning of the test (600 seconds), the gloss decay coefficient G=0.85≤0.9, which meets the judgment premise. At this time, the trend of the torque median baseline is monitored.

[0154] Specifically: Window 1 (600-630 seconds): Median torque baseline 22.5 Nm, previous window median torque baseline 23.0 Nm, 22.5 < 23.0 (first decrease); Window 2 (630-660 seconds): Median torque baseline 22.0 Nm, previous window median torque baseline 22.5 Nm, 22.0 < 22.5 (second decrease); Window 3 (660-690 seconds): Median torque baseline 21.5 Nm, previous window median torque baseline 22.0 Nm, 21.5 < 22.0 (third decrease), indicating the first continuous decrease for 3 windows. The standard temperature value corresponding to this window is 160℃, so 160℃ is determined to be the upper limit critical temperature point (i.e., the highest temperature at which the mixture can be applied).

[0155] Optionally, the workability window of the asphalt mixture is the temperature range between the upper critical temperature point and the lower critical temperature point.

[0156] For example, the upper critical temperature point of 40 / 60 penetration asphalt is 160℃ and the lower critical temperature point is 60℃, so the workability window is 60℃-160℃; the upper critical temperature point of 70 / 100 penetration asphalt is 155℃ and the lower critical temperature point is 58℃, so the workability window is 58℃-155℃.

[0157] Optionally, the number of the first preset window and the number of the second preset window can be the same or different, and this application does not make a specific limitation in this regard.

[0158] In the asphalt mixture workability testing method provided in this application embodiment, a personalized test temperature reference range is set based on the material formulation and construction environment, providing an accurate starting framework for the test. Then, a multi-modal sensor array is used to synchronously collect torque, temperature, and visual signals, realizing multi-dimensional perception of the mixture's working state. Furthermore, weights are dynamically allocated according to the type of abnormal signals, and the height of the mixing paddle is adaptively adjusted, effectively suppressing shear surface interference caused by uneven loading or local resistance, ensuring the stability of the data acquisition process. On this basis, torque data is analyzed by using a dynamic sliding time window with the window size adaptively adjusted according to the rate of temperature change, and a target confidence interval with dynamically adjusted boundaries based on data dispersion is generated, making the capture of the median torque trend more accurately reflect the essential changes in the mixture's viscosity. Finally, by fusing the gloss attenuation coefficient in the visual signal with the trends of the median torque and the median torque baseline, the upper and lower critical temperature points are accurately determined, thereby improving the testing accuracy of the asphalt mixture workability window.

[0159] Optionally, such as Figure 2 As shown, the asphalt mixture workability testing method provided in this application embodiment may further include the following steps S201 to S203: S201. Generate a fusion characteristic curve based on the standard temperature value and the low-frequency torque signal.

[0160] In the embodiments of this application, the fusion characteristic curve represents the relationship between temperature, torque and time.

[0161] For example, using standard temperature values ​​(x-axis, unit °C) as the X-axis, low-frequency torque signal (y-axis, unit Nm) as the Y-axis, and time (labeled on the curve, unit min) as the auxiliary dimension, multi-source time-series data points (e.g., (160℃, 21.5 Nm, 11.5 min), (100℃, 45.3 Nm, 60 min), (60℃, 71.2 Nm, 90 min)) after time alignment can be connected to generate a fused feature curve.

[0162] Specifically, such as Figure 3 As shown, curve S is the generated fusion characteristic curve. In the high-temperature stage (160℃-120℃), the torque increases slowly (from 21.5Nm to 35.2Nm), in the medium-temperature stage (120℃-80℃), the torque increases rapidly (from 35.2Nm to 68.5Nm), and in the low-temperature stage (80℃-60℃), the torque growth rate slows down (from 68.5Nm to 71.2Nm).

[0163] S202. Mark the construction performance window, upper limit critical temperature point, and lower limit critical temperature point on the fusion characteristic curve.

[0164] For example, combined Figure 3 The construction performance window (e.g., 160℃-60℃) can be marked with a shaded area on curve S, the upper limit critical temperature point (e.g., 160℃, 21.5Nm) can be marked with a dot A, and the lower limit critical temperature point (e.g., 60℃, 71.2Nm) can be marked with a dot B.

[0165] Optionally, combined Figure 3 You can also use point C to mark local minimum points (e.g., 140℃, 20.0Nm) and point D to mark inflection points (e.g., 120℃, 35.2Nm).

[0166] S203. Based on the labeled fusion feature curves and key state images collected by the visual sensing unit, generate a performance test report.

[0167] In this embodiment of the application, the key state images include at least the image at the start of stirring and the image at the end of stirring.

[0168] For example, the image at the start of stirring is an image of the surface of the mixture taken at the start of the test (0 seconds, standard temperature 164°C); the image at the end of stirring is an image taken at the end of the test (5400 seconds, standard temperature 60°C).

[0169] Specifically, the image at the start of mixing shows that the surface of the mixture is free of voids and the particles are evenly distributed, with the caption "Start image: Temperature 164℃, no voids, excellent processability"; the image at the end of mixing shows that the surface of the mixture is agglomerated, with the caption "End image: Temperature 60℃, agglomeration, critical processability".

[0170] Optionally, the performance test report may be in portable document format (PDF) and may include the following specific content: 1) Basic test information: Mixture type (e.g., 40 / 60 penetration asphalt), sample mass (e.g., 20kg), stirring speed (15rpm), test duration (90min).

[0171] 2) Test data summary: statistical tables of standard temperature, low-frequency torque signal, and visual characteristics (such as average, maximum, and minimum values).

[0172] 3) Performance analysis conclusions: construction performance window (e.g., 60℃-160℃), key temperature points (e.g., upper limit critical temperature point 160℃, lower limit critical temperature point 60℃, optimal temperature point 140℃); 4) Raw data files: raw torque, temperature, and visual data.

[0173] Thus, by generating fusion feature curves and labeling key parameters, and combining them with key state images, this application presents the test results in a visualized and integrated report format, intuitively demonstrating the evolution of working performance with temperature.

[0174] Optionally, after determining the workability window of the asphalt mixture, the workability window can be compared with the temperature of the target construction environment to generate operational recommendations for mixing equipment, transportation processes, or compaction equipment.

[0175] In this embodiment, the operation suggestions can be generated based on a preset "environmental parameter-device parameter association table". As shown in Table 2, some environmental parameter-device parameter associations are illustrated. In actual scenarios, there may be more or fewer environmental parameter-device parameter associations, which will not be listed here.

[0176] Table 2

[0177] For example, consider asphalt mixture with a penetration degree of 40 / 60. Its workability window is 60℃-160℃. If the on-site temperature of the target construction environment is 55℃, which is lower than the lower limit of the window of 60℃, and the transportation distance is 3km, with a temperature loss of 2℃ per 1km, then operation suggestions can be generated based on the temperature loss during transportation.

[0178] Specifically, for the mixing equipment: the original design mixing temperature of 160℃ can be increased to 166℃ to compensate for the 6℃ temperature loss during 3km transportation, ensuring that the temperature at the site is ≥60℃; for the transportation process: insulated tank trucks can be used, with the insulation layer thickness increased from 20mm to 35mm, and the temperature inside the tank monitored every 30 minutes during transportation to ensure that the temperature at the site is ≥65℃ (with a 5℃ margin); for the compaction equipment: a high-frequency vibratory roller (e.g., a vibration frequency of 30Hz, 5Hz higher than the conventional one) can be selected, and the number of compaction passes increased from 6 to 8 to ensure that compaction is completed before the temperature drops to 60℃.

[0179] Furthermore, if the slope of the torque median baseline within the construction performance window exceeds a preset slope, a temperature control accuracy recommendation can be generated.

[0180] In this embodiment, the preset slope is a manually set value that can be flexibly adjusted according to the actual scenario. For example, the preset slope can be 0.5 Nm / ℃, that is, a slope > 0.5 Nm / ℃ indicates that the torque is sensitive to temperature and requires higher temperature control accuracy.

[0181] In one example, taking a preset slope of 0.5 Nm / ℃ as an example, the slope of the median torque baseline within the working performance window of 60℃-160℃ for 40 / 60 penetration asphalt can be calculated: taking the two endpoints within the window (60℃, 71.2 Nm) and (160℃, 21.5 Nm), the slope k is calculated as k = (71.2-21.5) / (60-160) = -0.497 Nm / ℃. Since the absolute value 0.497 Nm / ℃ ≈ 0.5 Nm / ℃, which is close to the preset slope, the current control accuracy is maintained.

[0182] In another example, if the absolute value of the slope of another PMB-SBS modified asphalt mixture is 0.6 Nm / ℃ > 0.5 Nm / ℃, a new temperature control accuracy recommendation is generated, increasing the original temperature control accuracy from ±2℃ to ±1℃.

[0183] Specifically, recommendations for temperature control accuracy may include: For mixing equipment: a proportional-integral-derivative (PID) temperature controller can be used, adjusting the proportional coefficient P=2.0, the integral coefficient I=0.5, and the derivative coefficient D=0.1 to reduce temperature fluctuations; For transport tank trucks: a real-time temperature feedback device can be installed, which automatically starts auxiliary heating (e.g., heating power 5kW) when the temperature fluctuation inside the tank exceeds ±1℃; For on-site paving: an infrared temperature monitor can be installed at the paver hopper, providing temperature feedback every 10 seconds, and reducing the paving speed from 3m / min to 2.5m / min when the fluctuation exceeds the limit (e.g., ±5℃).

[0184] Furthermore, based on preset equipment parameter adjustment rules, operation suggestions and temperature control accuracy suggestions can be integrated to output performance adaptation suggestions.

[0185] In this application embodiment, the performance adaptation suggestion includes specific parameter adjustment values.

[0186] Optionally, the preset equipment parameter adjustment rules may include: ① Mixing temperature adjustment rule: Mixing temperature = Design mixing temperature + Transportation distance × 2℃; ② Insulation layer thickness adjustment rule: Insulation layer thickness = 20mm + (Transportation distance - 1km) × 5mm; ③ Temperature control accuracy adjustment rule: When the absolute value of the slope is > 0.5Nm / ℃, the control accuracy is adjusted to ±1℃, otherwise it is ±2℃.

[0187] For example, taking asphalt mixture with a penetration of 40 / 60 asphalt as an example. After obtaining the above operation suggestions and temperature control accuracy suggestions, the final performance adaptation suggestions can be integrated, and the specific parameter adjustment values ​​include: 1) Mixing equipment: mixing temperature is 166℃, temperature control accuracy is ±1℃; 2) Transportation process: insulation layer thickness is 35mm, auxiliary heating power is 5kW; 3) Compaction equipment: number of compaction passes is 8, vibration frequency is 30Hz.

[0188] Thus, by comparing the measured performance window with the field environment and analyzing the slope of torque change within the window, this application directly generates parameterized suggestions for specific equipment and processes, achieving precise control from laboratory testing to the construction site to ensure construction quality.

[0189] The above primarily describes the solutions provided in the embodiments of this application from a methodological perspective. To achieve the above functions, the asphalt mixture workability testing device or electronic device includes corresponding hardware structures and / or software modules for performing each function. Those skilled in the art should readily recognize that, based on the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein, this application can be implemented in hardware or a combination of hardware and computer software. Whether a function is executed in hardware or by computer software driving hardware depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.

[0190] This application embodiment can, based on the above method, exemplarily divide the asphalt mixture workability testing device or electronic device into functional modules. For example, the asphalt mixture workability testing device or electronic device may include functional modules corresponding to each functional division, or two or more functions may be integrated into one processing module. The integrated module can be implemented in hardware or as a software functional module. It should be noted that the module division in this application embodiment is illustrative and only represents one logical functional division; in actual implementation, there may be other division methods.

[0191] Figure 4 This is a structural diagram of an asphalt mixture workability testing device provided in an embodiment of this application. The asphalt mixture workability testing device 400 includes: a setting unit 401, an acquisition unit 402, an execution unit 403, a generation unit 404, and a judgment unit 405.

[0192] The system includes: a setting unit 401, used to set the starting and ending temperatures of the test based on the material formulation of the asphalt mixture and the target construction environment, forming a test temperature reference range; an acquisition unit 402, used to acquire multi-source signals based on a multi-modal sensor array, including torque signals, multi-point temperature signals, and visual signals, with the multi-point temperature signals acquired with reference to the test temperature reference range; an execution unit 403, used to assign weights to the multi-source signals according to the type of abnormal signals in the multi-source signals and according to a preset weight allocation rule, and calculate the height adjustment coefficient of the mixing paddle based on the weights, driving the mixing paddle to adjust its height vertically in preset steps until the multi-source signals meet preset normal conditions; the acquisition unit 402 is also used to acquire multi-source time-series data, including torque data, temperature data, and visual data, when the multi-source signals meet the preset normal conditions; and a generation unit 404, used for... The median torque of the torque data is calculated within a dynamic sliding time window to form a torque median baseline. A target confidence interval is generated based on the torque median baseline. The window size of the dynamic sliding time window is adaptively adjusted according to the temperature change rate of the asphalt mixture, and the boundary of the target confidence interval is dynamically adjusted according to the dispersion of the torque data. The judgment unit 405 is used to: determine the temperature point corresponding to the first time the median torque exceeds the lower boundary of the target confidence interval when the gloss decay coefficient in the visual data is greater than or equal to a preset lower decay limit coefficient; determine the temperature point corresponding to the first time the median torque baseline decreases when the gloss decay coefficient is less than or equal to a preset upper decay limit coefficient when the median torque baseline decreases when the second preset window number of decreases; wherein, the workability window of the asphalt mixture is the temperature range between the upper and lower critical temperature points.

[0193] In some embodiments, the setting unit 401 is specifically used to: determine the starting temperature based on the design mixing temperature of the asphalt mixture and the expected temperature loss under the target construction environment; determine the ending temperature based on the softening point temperature of the asphalt mixture and the failure temperature of similar mixtures in historical construction performance data, wherein the failure temperature is the temperature point at which the mixture loses its working performance; and determine the test temperature reference range based on the starting temperature and the ending temperature.

[0194] In some embodiments, the execution unit 403 is further configured to preheat the mixing shaft and the mixing container to the initial temperature and maintain it for a preset time, and transfer the mixed asphalt mixture to the mixing container; the acquisition unit 402 is further configured to acquire a surface image of the asphalt mixture through a visual sensing unit; the execution unit 403 is further configured to insert the mixing paddle into the asphalt mixture at a constant speed when the surface image shows no gaps, until the asphalt mixture completely covers the mixing blades of the mixing paddle.

[0195] In some embodiments, the types of the above-mentioned abnormal signals include at least one of the following: the instantaneous fluctuation of the torque signal exceeds the normal fluctuation threshold, the local temperature gradient of the multi-point temperature signal is abnormal, and there are abnormal visual signal points in the visual signal, wherein the abnormal visual signal points are signal points corresponding to the shear surface in the asphalt mixture.

[0196] In some embodiments, the acquisition unit 402 is specifically used for: directly measuring the rotational torque of the mixing blade through the torque measurement unit to obtain torque data; acquiring the internal temperature, surface temperature, and ambient temperature of the asphalt mixture through the multi-point temperature acquisition unit to obtain temperature data; capturing the appearance texture video stream of the asphalt mixture during the mixing process through the visual sensing unit to obtain visual data; performing filtering and noise reduction processing on the rotational torque to separate the low-frequency torque signal and the high-frequency torque noise, where the low-frequency torque signal represents the overall viscosity of the asphalt mixture and the high-frequency torque noise represents the instantaneous jamming of the asphalt mixture; performing image processing on the appearance texture video stream to extract the gloss attenuation coefficient, particle segregation index, and agglomeration area ratio as visual features; calibrating the surface temperature and ambient temperature based on the internal temperature to obtain a standard temperature value, and using the standard temperature value to time-align the low-frequency torque signal and visual features to form multi-source time-series data.

[0197] In some embodiments, the generation unit 404 is further configured to: generate a fusion characteristic curve based on the standard temperature value and the low-frequency torque signal, wherein the fusion characteristic curve characterizes the relationship between temperature, torque and time; mark the construction performance window, the upper limit critical temperature point and the lower limit critical temperature point on the fusion characteristic curve; and form a work performance test report based on the marked fusion characteristic curve and the key state images collected by the visual sensing unit, wherein the key state images include at least the image at the start of mixing and the image at the end of mixing.

[0198] In some embodiments, the generation unit 404 is further configured to: compare the construction performance window with the temperature of the target construction environment to generate operation suggestions for mixing equipment, transportation process or compaction equipment; generate temperature control accuracy suggestions when the slope of the torque median baseline within the construction performance window exceeds a preset slope; and integrate the operation suggestions and temperature control accuracy suggestions based on preset equipment parameter adjustment rules to output working performance adaptation suggestions, which include specific parameter adjustment values.

[0199] In the asphalt mixture workability testing device provided in this application embodiment, a personalized test temperature reference range is set based on the material formulation and construction environment, providing an accurate starting framework for the test. Then, a multi-modal sensor array is used to synchronously collect torque, temperature, and visual signals, realizing multi-dimensional perception of the working state of the mixture. Furthermore, weights are dynamically allocated according to the type of abnormal signals and the height of the mixing paddle is adaptively adjusted, effectively suppressing shear surface interference caused by uneven loading or local resistance, ensuring the stability of the data acquisition process. On this basis, torque data is analyzed by using a dynamic sliding time window with the window size adaptively adjusted according to the rate of temperature change, and a target confidence interval with dynamically adjusted boundaries based on data dispersion is generated, so that the capture of the median torque trend can more realistically reflect the essential changes in the viscosity of the mixture. Finally, by fusing the gloss attenuation coefficient in the visual signal with the trend of the median torque and the median torque baseline, the upper and lower critical temperature points are accurately determined, thereby improving the testing accuracy of the asphalt mixture workability window.

[0200] Regarding the apparatus in the above embodiments, the specific manner in which each module performs its operation has been described in detail in the embodiments related to the method, and will not be elaborated upon here.

[0201] Figure 5 This is a structural diagram of an electronic device provided in an embodiment of this application. Figure 5 As shown, the electronic device 500 includes, but is not limited to, a processor 501 and a memory 502.

[0202] The aforementioned memory 502 is used to store the executable instructions of the aforementioned processor 501. It is understood that the processor 501 is configured to execute instructions to implement the asphalt mixture workability testing method in the above embodiments.

[0203] It should be noted that those skilled in the art will understand that Figure 5 The electronic device structure shown does not constitute a limitation on the electronic device; the electronic device may include, but is not limited to, other electronic devices. Figure 5 This may indicate more or fewer components, or combinations of certain components, or different component arrangements.

[0204] Processor 501 is the control center of the electronic device. It connects various parts of the electronic device via various interfaces and lines. By running or executing software programs and / or modules stored in memory 502, and by calling data stored in memory 502, it performs various functions and processes data, thereby providing overall monitoring of the electronic device. Processor 501 may include one or more processing units. Optionally, processor 501 may integrate an application processor and a modem processor. The application processor mainly handles the operating system, user interface, and applications, while the modem processor mainly handles wireless communication. It is understood that the modem processor may not be integrated into processor 501.

[0205] The memory 502 can be used to store software programs and various data. The memory 502 may primarily include a program storage area and a data storage area. The program storage area may store the operating system, application programs required by at least one functional module (such as a determination unit, processing unit, etc.), etc. Furthermore, the memory 502 may include high-speed random access memory, and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other volatile solid-state storage device.

[0206] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 502 including instructions, which can be executed by a processor 501 of an electronic device 500 to implement the asphalt mixture workability testing method in the above embodiments.

[0207] In actual implementation, Figure 4 The steps performed by the setting unit 401, obtaining unit 402, execution unit 403, generation unit 404, and determination unit 405 can all be performed by... Figure 5 The processor 501 calls the computer program stored in the memory 502 to implement the process. The specific execution process can be found in the description of the method section in the previous embodiment, and will not be repeated here.

[0208] Optionally, the computer-readable storage medium may be a non-transitory computer-readable storage medium, such as a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device.

[0209] In an exemplary embodiment, this application also provides a computer program product including one or more instructions, which can be executed by a processor 501 of an electronic device to complete the asphalt mixture workability test method in the above embodiments.

[0210] It should be noted that when one or more instructions in the computer-readable storage medium or computer program product are executed by the processor of an electronic device, they implement the various processes of the above method embodiments and achieve the same technical effect as the above method. To avoid repetition, they will not be described again here.

[0211] Through the above description of the embodiments, those skilled in the art can clearly understand that, for the sake of convenience and brevity, only the division of the above functional modules is used as an example. In actual applications, the above functions can be assigned to different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete all or part of the functions described above.

[0212] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of modules or units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another apparatus, or some features may be ignored or not executed. Furthermore, the mutual coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0213] The units described as separate components may or may not be physically separate. A component shown as a unit can be one or more physical units; that is, it can be located in one place or distributed in multiple different locations. Some or all of the classified units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0214] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0215] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiments of this application, essentially, or the part that contributes to the prior art, or a complete or partial classification of the technical solution, can be embodied in the form of a software product. This software product is stored in a storage medium and includes several instructions to cause a device (which may be a microcontroller, chip, etc.) or processor to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0216] The above are merely specific embodiments of this application, but the scope of protection of this application is not limited thereto. Any variations or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application. Therefore, the scope of protection of this application should be determined by the scope of the claims.

Claims

1. A method of testing the workability of an asphalt mixture, characterized in that, The method comprises: setting a starting temperature and an ending temperature of the test based on a material formula of the asphalt mixture and a target construction environment, forming a test temperature reference range; acquiring multi-source signals based on a multi-modal sensor array, the multi-source signals comprising torque signals, multi-point temperature signals, and visual signals, the multi-point temperature signals being acquired with reference to the test temperature reference range; according to the type of abnormal signals in the multi-source signals, assigning weights to the multi-source signals according to a preset weight distribution rule, and calculating a height adjustment coefficient of the stirring paddle based on the weights, and driving the stirring paddle to adjust the height in the vertical direction by a preset step size until the multi-source signals meet a preset normal condition; in the case where the multi-source signals meet the preset normal condition, acquiring multi-source time series data, the multi-source time series data comprising torque data, temperature data, and visual data; calculating a torque median value of the torque data based on a dynamic sliding time window, forming a torque median value reference line, and generating a target confidence interval based on the torque median value reference line, the window size of the dynamic sliding time window being adaptively adjusted according to the temperature change rate of the asphalt mixture, and the boundary of the target confidence interval being dynamically adjusted according to the dispersion of the torque data; in the case where the gloss attenuation coefficient in the visual data is greater than or equal to a preset lower attenuation coefficient, determining the temperature point corresponding to the first time when the torque median value continuously exceeds the lower boundary of the target confidence interval for a first preset window number as a lower limit critical temperature point; in the case where the gloss attenuation coefficient is less than or equal to a preset upper attenuation coefficient, determining the temperature point corresponding to the first time when the torque median value reference line continuously decreases for a second preset window number as an upper limit critical temperature point; wherein the construction performance window of the asphalt mixture is a temperature range between the upper limit critical temperature point and the lower limit critical temperature point.

2. The method of testing the workability of an asphalt mixture according to claim 1, wherein, The method comprises: determining the starting temperature according to the design mixing temperature of the asphalt mixture and the expected temperature loss under the target construction environment; determining the ending temperature according to the softening point temperature of the asphalt mixture and the failure temperature of the same type of mixture in the historical construction performance data, the failure temperature being the temperature point at which the mixture loses working performance; determining the test temperature reference range according to the starting temperature and the ending temperature.

3. The method of testing the workability of an asphalt mixture of claim 1 wherein, Before the multi-modal sensor array acquires the multi-source signals, the method further comprises: preheating the stirring shaft and the stirring container to the starting temperature for a preset time length; transferring the mixed asphalt mixture to the stirring container and acquiring a surface image of the asphalt mixture through a visual sensing unit; in the case where the surface image shows no voids, inserting the stirring paddle into the asphalt mixture at a constant rotating speed until the asphalt mixture completely covers the stirring blades of the stirring paddle.

4. The method of testing the performance of asphalt mixtures of claim 1 wherein, The type of abnormal signals comprises at least one of the following: the instantaneous fluctuation of the torque signal exceeds the normal fluctuation threshold; The multi-point temperature signal appears a local temperature gradient anomaly; The visual signal has an abnormal visual signal point, and the abnormal visual signal point is a signal point corresponding to a shear surface in the asphalt mixture.

5. The method of testing the workability of an asphalt mixture according to claim 3, wherein, The multi-source time-series data is acquired, including: The torque data is obtained by directly measuring the rotational torque suffered by the stirring paddle through a torque measurement unit; The temperature data is obtained by collecting the internal temperature, surface temperature and environmental temperature of the asphalt mixture through a multi-point temperature acquisition unit; The visual data is obtained by capturing the apparent texture video stream of the asphalt mixture during the stirring process through the visual sensing unit; The rotational torque is filtered and denoised to separate a torque low-frequency signal and a torque high-frequency noise, the torque low-frequency signal representing the overall viscosity of the asphalt mixture, and the torque high-frequency noise representing the instantaneous jamming of the asphalt mixture; The apparent texture video stream is image-processed to extract the glossiness decay coefficient, particle segregation index and agglomeration area proportion as visual features; The standard temperature value is obtained by calibrating the surface temperature and the environmental temperature based on the internal temperature, and the torque low-frequency signal and the visual features are time-aligned using the standard temperature value to form the multi-source time-series data.

6. The method of testing the workability of an asphalt mixture according to claim 5, wherein, The method further includes: A fusion feature curve is generated according to the standard temperature value and the torque low-frequency signal, the fusion feature curve representing the correlation between temperature, torque and time; The construction performance window, the upper limit critical temperature point and the lower limit critical temperature point are labeled on the fusion feature curve, and a working performance test report is formed according to the labeled fusion feature curve and key state images collected by the visual sensing unit, the key state images at least including a stirring start time point image and a stirring end time point image.

7. The method of testing the workability of an asphalt mixture of claim 1 wherein, The method further includes: The construction performance window is compared with the temperature of the target construction environment to generate operation suggestions for the mixing equipment, transportation process or compaction equipment; A temperature control precision suggestion is generated in a case where the slope of the torque median reference line in the construction performance window exceeds a preset slope; Based on a preset device parameter adjustment rule, the operation suggestion and the temperature control precision suggestion are integrated to output a working performance adaptation suggestion, the working performance adaptation suggestion including a specific parameter adjustment value.

8. An asphalt mixture workability testing device characterized by, The device includes: A setting unit configured to set a starting temperature and an ending temperature of a test based on a material formula of the asphalt mixture and a target construction environment to form a test temperature reference range; An acquisition unit configured to acquire multi-source signals based on a multi-modal sensor array, the multi-source signals including torque signals, multi-point temperature signals and visual signals, the multi-point temperature signals being collected with reference to the test temperature reference range; An execution unit configured to assign weights to the multi-source signals according to a preset weight distribution rule based on the types of abnormal signals in the multi-source signals, and calculate a height adjustment coefficient of a stirring paddle based on the weights, and drive the stirring paddle to adjust the height in a vertical direction by a preset step size until the multi-source signals meet a preset normal condition. The acquisition unit is further configured to acquire multi-source timing data including torque data, temperature data, and visual data when the multi-source signal meets the preset normal condition; The generation unit is configured to calculate a torque median of the torque data based on a dynamic sliding time window, form a torque median reference line, and generate a target confidence interval based on the torque median reference line, wherein a window size of the dynamic sliding time window is adaptively adjusted according to a temperature variation rate of the asphalt mixture, and a boundary of the target confidence interval is dynamically adjusted according to a dispersion of the torque data; The determination unit is configured to: determine, when a glossiness attenuation coefficient in the visual data is greater than or equal to a preset lower attenuation coefficient, a temperature point corresponding to a time when the torque median first continuously exceeds a lower boundary of the target confidence interval for a first preset window number as a lower limit critical temperature point; determine, when the glossiness attenuation coefficient is less than or equal to a preset upper attenuation coefficient, a temperature point corresponding to a time when the torque median reference line first continuously decreases for a second preset window number as an upper limit critical temperature point; wherein a construction performance window of the asphalt mixture is a temperature range between the upper limit critical temperature point and the lower limit critical temperature point.

9. An electronic device, comprising: comprise: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement the asphalt mixture work performance test method of any one of claims 1 to 7.

10. A computer-readable storage medium having stored therein instructions, the computer-readable storage medium comprising: When a computer executes the instructions, the computer executes the asphalt mixture work performance test method of any one of claims 1 to 7.

Images