Bituminous concrete production material mixing monitoring system based on internet of things

Abstract

The application discloses an asphalt concrete production material mixing monitoring system based on an internet of things, and relates to the technical field of asphalt production control. The system comprises the following modules: an internet of things sensing module, which is used for collecting environmental parameters of an asphalt concrete production area and process parameters in a production process in real time; a data storage and management module, which stores real-time environmental parameters collected by the internet of things sensing module, historical environmental data, real-time process parameters and historical production effect data, and supports data calling and backup; the internet of things sensing module is used for collecting multi-dimensional environmental and process parameters in real time; an intelligent compensation model module generates a process parameter compensation amount dynamically based on the correlation between environmental parameters and process parameters, realizes flexible adjustment of parameters such as aggregate proportioning and mixing time; and a model iteration optimization module continuously optimizes the compensation algorithm by using historical data, so that the system can better adapt to different environmental changes.

Description

Technical Field

[0001] This invention relates to the field of asphalt production control technology, specifically to an Internet of Things-based asphalt concrete production material mixing monitoring system. Background Technology

[0002] As a core material for road construction, the production quality of asphalt concrete directly determines the load-bearing capacity and service life of roads. In the production process of asphalt concrete, the material mixing stage is extremely sensitive to environmental factors. Atmospheric humidity, wind speed, temperature, and sudden weather conditions can all significantly affect the physical properties and chemical reaction processes of materials, thus having a significant impact on production quality. Therefore, how to effectively control environmental factors in the production process and ensure the stability of asphalt concrete quality has become a key issue that the industry urgently needs to address.

[0003] Existing asphalt concrete production systems have significant shortcomings in environmental factor control. They primarily employ a fixed threshold triggering mode, where fixed parameter adjustment commands are triggered when environmental parameters reach a certain threshold. However, this control method has two major drawbacks. First, the impact of environmental factors on asphalt concrete production is continuous and dynamic. Different degrees of environmental change have varying degrees of impact on the production process, and fixed thresholds cannot fully cover this complex environmental change, making it difficult to accurately control based on actual environmental conditions, resulting in unstable production quality. Second, existing systems lack correlation analysis between historical environmental data and production results. In actual production, there is a complex intrinsic relationship between environmental factors and production quality. In-depth analysis of historical data can uncover this correlation pattern and optimize control strategies. However, traditional systems fail to fully utilize this data and cannot dynamically adjust and optimize control strategies based on production feedback, making it difficult to continuously improve production quality and meet increasingly stringent road construction quality requirements. Summary of the Invention

[0004] The purpose of this invention is to overcome the shortcomings of existing technologies and provide an Internet of Things (IoT)-based monitoring system for the mixing of asphalt concrete production materials. This system can collect environmental parameters of the production area and process parameters in real time through an IoT sensing module. It uses a data storage and management module to store, retrieve, and back up the data. An intelligent compensation model module generates compensation amounts for process parameters based on a preset compensation algorithm. A production control execution module dynamically adjusts the operating parameters of the production equipment. Finally, a model iteration and optimization module continuously optimizes the compensation algorithm based on historical data, effectively improving the system's adaptability to different environments and ensuring the stability of asphalt concrete production quality.

[0005] To solve the above-mentioned technical problems, the present invention provides the following technical solution: an Internet of Things-based asphalt concrete production material mixing monitoring system, the system comprising:

[0006] IoT sensing module: used to collect environmental parameters and process parameters in the asphalt concrete production area in real time;

[0007] Data storage and management module: Stores real-time environmental parameters, historical environmental data, real-time process parameters, and historical production effect data collected by the IoT sensing module, and also supports data retrieval and backup;

[0008] Intelligent compensation model module: It has a preset compensation algorithm based on the relationship between environmental parameters and process parameters. It calls the real-time environmental parameters in the data storage and management module to calculate and generate the compensation amount of process parameters, and supports the manual correction of the compensation amount of process parameters by the staff.

[0009] Production control execution module: Receives the process parameter compensation amount output by the intelligent compensation model module, and automatically adjusts the operating parameters of the asphalt concrete production equipment to achieve dynamic adjustment of aggregate ratio, mixing time, asphalt heating temperature and heat preservation time;

[0010] Model Iterative Optimization Module: Based on historical environmental data and historical production effect data in the data storage and management module, an iterative optimization algorithm is used to iteratively optimize the compensation algorithm in the intelligent compensation model module.

[0011] Furthermore, the environmental parameters in the IoT sensing module include atmospheric humidity, wind speed, diurnal temperature range, rainfall status, and high temperature status, while the process parameters include aggregate moisture content, aggregate ratio, mixing time, asphalt heating temperature, and heat preservation time.

[0012] Furthermore, the intelligent compensation model module is pre-set with compensation algorithms based on the correlation between environmental parameters and process parameters, including a rainy day humidity compensation algorithm and a high temperature compensation algorithm: the rainy day humidity compensation algorithm presets a reference humidity. When the real-time humidity is higher than the reference humidity, it calculates the increase in aggregate moisture content based on the correlation between the humidity increment and the increase in aggregate moisture content, determines the increase in dry aggregate dosage based on the increase in aggregate moisture content, and extends the mixing time; the high temperature compensation algorithm presets a reference temperature. When the real-time temperature is higher than the reference temperature, it calculates the decrease in asphalt viscosity based on the correlation between the temperature increment and the decrease in asphalt viscosity, determines the decrease in asphalt heating temperature based on the decrease in asphalt viscosity, and shortens the heat preservation time; it also has a parameter display function, allowing staff to view real-time environmental parameters, process parameters, compensation amounts, and production equipment operating status through a touch screen or host computer software, and allowing staff to manually correct the process parameter compensation amount, with manual correction commands having higher priority than automatic output commands.

[0013] Furthermore, in the intelligent compensation model module, the increase in aggregate moisture content is calculated based on the correlation between the increase in humidity and the increase in aggregate moisture content. The calculation formula is as follows: ,in, It refers to the increase in aggregate moisture content, specifically the difference between the actual moisture content of the aggregate and the reference moisture content caused by changes in ambient humidity. It is the humidity influence coefficient, determined by the type of aggregate, reflecting the sensitivity of different aggregates to humidity adsorption. It is the increase in atmospheric humidity, that is, the difference between the real-time atmospheric humidity and the reference humidity. This is a wind speed correction factor, used to correct for the effect of wind speed on the moisture content of aggregates (the higher the wind speed, the faster the moisture on the aggregate surface evaporates). The value decreases as wind speed increases. For real-time wind speed, It is the correction value for the basic moisture content of aggregates, which refers to the inherent moisture content of aggregates under the reference environment.

[0014] Furthermore, in the intelligent compensation model module, the increase in dry aggregate usage is determined based on the increase in aggregate moisture content, and the mixing time is extended. The formula for calculating the increase in dry aggregate usage is as follows: ,in, This refers to the increase in the amount of dry aggregate used, i.e., the additional mass of dry aggregate that needs to be added to ensure that the total moisture content of the mixture meets the process requirements. This refers to the baseline dry aggregate dosage, which indicates the mass of dry aggregate required to produce a unit mass of asphalt concrete under baseline conditions. This refers to the target moisture content of the mixture, i.e., the optimum moisture content required by the asphalt concrete production process; the formula for calculating the mixing time is: ,in, This is the extended mixing time, used to compensate for the time required for uniform mixing of the mixture due to increased moisture content. It is the correlation coefficient between moisture content and stirring time. It is the aggregate gradation correction factor. The coefficient for non-uniform aggregate gradation.

[0015] Furthermore, in the intelligent compensation model module, when the real-time temperature is higher than the reference temperature, the reduction in asphalt viscosity is calculated based on the correlation between the temperature increment and the reduction in asphalt viscosity. The calculation formula is as follows: ,in, This refers to the decrease in asphalt viscosity, specifically the difference between the actual viscosity of asphalt and the reference viscosity under high-temperature conditions. This is the reference viscosity of asphalt, which refers to the kinematic viscosity of asphalt under reference conditions. It is the temperature sensitivity coefficient, reflecting the degree to which the viscosity of asphalt is sensitive to temperature. It is the ambient temperature increment, that is, the difference between the real-time ambient temperature and the reference temperature. It is the atmospheric humidity correction factor. This is the real-time atmospheric humidity.

[0016] Furthermore, in the intelligent compensation model module, the amount of temperature reduction in asphalt heating is determined based on the decrease in asphalt viscosity, and the heat preservation time is shortened. The decrease in heating temperature is: ,in, This refers to the reduction in asphalt heating temperature to prevent asphalt aging caused by high temperatures. It is the viscosity-temperature compensation coefficient, which is determined by the type of asphalt. It is a heating time correction factor. This represents the total heating time for the day; the formula for calculating the heat preservation time is: ,in, This refers to the reduction in asphalt insulation time. It is the viscosity-holding time correlation coefficient. For the real-time power of the insulation device, It is the insulation power correction factor.

[0017] Furthermore, the production control execution module receives the process parameter compensation amount output by the intelligent compensation model module, and adjusts the production parameters through various controllers: the aggregate batching controller adjusts the dry aggregate usage by adjusting the rotation speed of the batching screw conveyor; the mixing motor controller adjusts the mixing speed by changing the motor frequency, thereby extending or shortening the mixing time; the asphalt heating controller uses pulse width modulation technology to adjust the asphalt heating temperature by adjusting the power of the heating tube; and the insulation device controller adjusts the insulation time by controlling the on / off duration of the heating wire in the insulation layer.

[0018] Furthermore, the model iterative optimization module employs an iterative optimization algorithm to iteratively optimize the compensation algorithm in the intelligent compensation model module. The iterative formula is as follows: ,in, It is the first The compensation coefficient after the next iteration. It is the first Initial values ​​of the compensation coefficients in the next iteration It's the learning rate, which controls the update step size in each iteration. It is the error compensation function, and the calculation formula is: ,in For actual production results data, For the production performance data predicted by the model, For the target value of production effect, It is the error function on the first iteration coefficients The partial derivatives reflect the degree to which changes in the coefficients affect the error. It is a decay coefficient, used to reduce the update magnitude as the number of iterations increases. It is the current iteration number. It represents the total number of iterations.

[0019] Compared with existing technologies, this IoT-based asphalt concrete production material mixing monitoring system has the following advantages:

[0020] I. This invention uses an IoT sensing module to collect multi-dimensional environmental and process parameters in real time. The intelligent compensation model module dynamically generates process parameter compensation based on the correlation between environmental and process parameters, enabling flexible adjustment of parameters such as aggregate ratio and mixing time. At the same time, the model iteration optimization module continuously optimizes the compensation algorithm using historical data, enabling the system to better adapt to different environmental changes. This effectively solves the problem of production quality fluctuations caused by dynamic changes in environmental factors and significantly improves the stability of asphalt concrete production quality.

[0021] Second, this invention automatically adjusts key process parameters such as aggregate ratio, mixing time, asphalt heating temperature, and heat preservation time according to environmental changes such as different atmospheric humidity, temperature, wind speed, and sudden weather. Furthermore, the intelligent compensation model module supports manual correction of compensation amounts by staff, and manual commands have high priority, increasing operational flexibility. In addition, the system adopts an edge + cloud collaborative storage architecture to ensure data security and accessibility, meeting the needs of different production scenarios and providing reliable protection for the industrial production of asphalt concrete.

[0022] Other advantages, objectives and features of the invention will be set forth in part in the description which follows, and in part will be apparent to those skilled in the art from the following examination or study, or may be learned from the practice of the invention. Attached Figure Description

[0023] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0024] Figure 1 This is a structural block diagram of an IoT-based asphalt concrete production material mixing monitoring system.

[0025] Figure 2 This is a flowchart of an IoT-based asphalt concrete production material mixing monitoring system. Detailed Implementation

[0026] To further illustrate the technical means and effects of the present invention in achieving its intended purpose, the following detailed description of the specific implementation methods, structures, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided below.

[0027] This invention provides an Internet of Things-based monitoring system for the mixing of materials in asphalt concrete production, such as... Figure 1 As shown, the system includes an IoT sensing module, a data storage and management module, an intelligent compensation model module, a production control execution module, and a model iteration and optimization module. The IoT sensing module collects environmental parameters of the production area and process parameters during production in real time. The data storage and management module stores, retrieves, and backs up the data. The intelligent compensation model module generates compensation amounts for process parameters based on a preset compensation algorithm. The production control execution module dynamically adjusts the operating parameters of the production equipment. Finally, the model iteration and optimization module continuously optimizes the compensation algorithm based on historical data, effectively improving the system's adaptability to different environments and ensuring the stability of asphalt concrete production quality.

[0028] Example 1

[0029] An asphalt concrete mixing plant operates during the rainy season in spring. The production goal is to prepare asphalt concrete for the base course of urban main roads. It is necessary to ensure that the moisture content and mixing uniformity of the mixture meet the process requirements, while also dealing with the problem of frequent humidity fluctuations during rainfall.

[0030] One hour before production, staff initiated system preheating via the human-machine interface module. The IoT sensing module entered the parameter acquisition preheating phase: sensor nodes distributed across the aggregate stockpile, mixing workshop, and asphalt storage tank area completed self-checks in sequence. Environmental sensors such as humidity sensors, wind speed sensors, and rainfall sensors began collecting initial environmental data, confirming that the current atmospheric humidity was 58%RH (close to the preset baseline humidity of 60%RH), and that thickening cloud cover indicated a possible rainfall. Simultaneously, the process parameter acquisition components started up, the weight sensor at the aggregate batching bin outlet calibrated to zero, and the humidity sensor inside the mixing tank collected the moisture content of the aggregate foundation. The value is 0.8%. The mixer motor encoder is reset to ensure accurate recording of the baseline mixing time (180 seconds / batch). After all sensors pass self-test, the data storage and management module establishes a data synchronization link between the edge gateway and the cloud server, the real-time parameter transmission channel is activated, and historical rainy day production data (including the moisture influence coefficient for the current limestone aggregate) is displayed. Wind speed correction factor Retrieve data from the cloud to the local cache to provide a reference for subsequent compensation calculations.

[0031] After the rainfall begins, such as Figure 2 As shown, the IoT sensing module captures environmental changes in real time: the humidity sensor detects that the atmospheric humidity has rapidly risen to 72%RH, exceeding the preset benchmark humidity of 60%RH, and this is confirmed by the formula... Real-time atmospheric humidity - reference humidity = 12%RH, calculate the increase in atmospheric humidity. With a RH of 12%, the wind speed sensor recorded gusts of wind accompanying the rainfall, and the real-time wind speed was [data missing]. The rainfall speed was 3.5 m / s. The rainfall sensor confirmed that the rainfall intensity was stable (moderate rain). The process parameter acquisition component found that as humidity increased, the moisture content of the aggregate in the mixing tank showed a slow upward trend. This real-time data was transmitted to the data storage and management module via industrial Ethernet. The edge gateway prioritized processing the humidity and moisture content correlation data to avoid delays. After receiving the real-time data, the intelligent compensation model module automatically triggered the rainy weather humidity compensation algorithm: first, it combined the historically calibrated humidity influence coefficient... Wind speed correction factor and the moisture content of the collected aggregate foundation Through formula The increase in aggregate moisture content under the current environment was calculated. Then, based on the target moisture content required by the mixture process... Compared with the standard dry aggregate dosage Through formula Determine the additional amount of dry aggregate required. To avoid reducing the strength of the mixture due to excessive moisture content; at the same time, the impact of aggregate gradation differences on mixing uniformity should be considered, combined with the aggregate gradation non-uniformity coefficient. Correlation coefficients corresponding to mixing equipment =12、 =0.03, through the formula The required extended stirring time was calculated. After seconds, once the compensation calculation results are generated, the module displays real-time environmental parameters in partitions on the touchscreen. RH m / s), process adjustment amount ( 34kg By comparing the compensation effect (=14 seconds) with that of similar historical scenarios, staff can quickly confirm the rationality of the compensation logic. If no abnormalities are found, the compensation instruction will automatically enter the execution queue.

[0032] After receiving the compensation command, the production control execution module performs adjustments according to priority: the aggregate batching controller responds first, gradually increasing the amount of dry aggregate by fine-tuning the speed of the batching screw conveyor. This avoids aggregate metering deviations caused by sudden changes in rotation speed; simultaneously, the mixer motor controller adjusts the mixing time based on the amount of time extension. Gradually reduce the motor frequency and extend the mixing time to the baseline mixing time + =194 seconds, during which the stirring speed and actual stirring time are fed back in real time for staff monitoring. During production, the system is equipped with multiple monitoring mechanisms: if the humidity sensor detects... If the RH level suddenly rises from 12% to 18% within 5 minutes, the intelligent compensation model module will temporarily pause the current compensation command and recalculate. With the corresponding , To avoid frequent adjustments that could affect production stability; if the humidity sensor inside the mixing tank detects that the actual moisture content of the aggregate is different from the expected value... If the calculated value deviates by more than 0.1%, the system will automatically prompt the staff to check the rain protection measures of the aggregate stockpile. After inspection, it was found that the rainproof cloth at the edge of the stockpile was damaged. After repair, the moisture content gradually dropped to 1.85%, which is in line with the calculation expectation. Since the current temperature (28℃) has not reached the high temperature threshold (35℃), the asphalt heating and insulation system maintains the normal operating parameters (heating temperature 165℃, insulation time 10 minutes), but the temperature sensor continues to collect data to ensure that there is no abnormal temperature rise.

[0033] After the batch is completed, staff enter records of any abnormal situations encountered during the production process (such as handling brief humidity fluctuations) through the human-machine interface module. The data storage and management module then stores the complete data chain of this production process. =12%RH =3.5m / s =1.84%, =34kg =14 seconds and the final mixture production effect data) are linked and archived to the cloud server and marked as typical rainy and gusty weather scenario data. At the same time, the model iteration and optimization module automatically marks the key features of this batch of data. After accumulating a certain amount of similar data, it will be included in the training dataset, and the compensation coefficient will be used to iteratively update the formula. , Optimize coefficients to improve the system's adaptability to complex rainy environments.

[0034] Example 2

[0035] An asphalt concrete mixing plant produces modified asphalt concrete for highway surface layers during the high-temperature period in summer. It needs to avoid the asphalt's bonding performance from aging due to high temperatures, and also needs to cope with the differences between the midday temperature peak and the morning and evening temperature fluctuations.

[0036] To address the temperature fluctuation patterns during the hot summer months, the system employs a time-segmented parameter acquisition strategy: Before morning production, the IoT sensing module collects environmental data at a normal frequency (1 time / minute) to confirm the current ambient temperature is 32℃ (lower than the preset baseline temperature of 35℃) and the atmospheric humidity is 30%RH (relatively low). As sunlight intensifies, approaching midday, the module automatically increases the acquisition frequency of the temperature and asphalt temperature sensors to 1 time / 10 seconds, shortening the data transmission interval and ensuring timely capture of rising temperature trends, which are then analyzed using formulas. The increase in atmospheric humidity is calculated by subtracting the baseline humidity from the real-time atmospheric humidity. In the process parameter acquisition component, the temperature sensors of the asphalt heating tank and the insulation tank are additionally equipped with temperature gradient monitoring function to record the rate of temperature rise and provide dynamic basis for compensation calculation.

[0037] Before production, the data storage and management module retrieves recent high-temperature production data from the cloud, focusing on analyzing the compensation patterns during the midday temperature peak period (including temperature sensitivity coefficient). =0.04, viscosity-temperature compensation coefficient =55), while also setting the reference viscosity of the modified asphalt. =0.35Pa・s is imported into the intelligent compensation model module as a constraint condition for compensation calculation (emergency cooling is initiated when the asphalt viscosity is below 0.28Pa・s) to prevent the asphalt temperature from exceeding the performance limit.

[0038] After the midday temperature reached its peak and exceeded the preset baseline temperature, the IoT sensing module detected a real-time ambient temperature of 41℃ and calculated the temperature increment using a formula. 6℃; the temperature inside the asphalt heating tank has risen to 167℃ (2℃ higher than the reference heating temperature), and the atmospheric humidity remains at 30%RH (real-time atmospheric humidity is obtained). RH), wind speed sensor collects real-time wind speed m / s (a light breeze with limited auxiliary effect on asphalt cooling), after real-time data transmission to the data storage and management module, the edge gateway quickly filters out... =6℃ The correlation data between RH and asphalt temperature of 167℃ is pushed to the intelligent compensation model module, which triggers the high-temperature compensation algorithm: first, it combines the temperature sensitivity coefficient calibrated in the historical calibration. =0.04, Atmospheric humidity correction factor =0.008 and modified asphalt reference viscosity =0.35 Pa·s, according to the formula The reduction in asphalt viscosity under the current environment was calculated. =0.0903, then according to Total heating time of the day =4.2 hours, combined with viscosity-temperature compensation coefficient =55, Heating time correction factor =0.003, through the formula =13.97℃ determines the asphalt heating temperature that needs to be reduced. =14℃, (adjusted target heating temperature = 165℃ - 14℃ = 151℃); Simultaneously considering the increased fluidity of asphalt after viscosity reduction, combined with the correlation coefficient corresponding to the insulation device (vacuum insulation). =0.002 and real-time power of the insulation device kW, through the formula =7.5 seconds, take the heat preservation time =8 seconds (adjusted target insulation time = 12 minutes - 8 seconds = 11 minutes 52 seconds). After the compensation result is generated, the module generates a visual report on the host computer software, comparing it with the current compensation scheme. =14℃ (seconds) and historical midday high temperature scheme (same) C-hour average =13-15℃,), indicating the modified asphalt for , Due to the special calibration requirements, after the staff confirms that there are no abnormalities, the compensation instruction is issued to the production control execution module.

[0039] When the production control execution module executes compensation commands, it adopts a step-by-step adjustment strategy: the asphalt heating controller uses pulse width modulation technology to gradually reduce the heating tube power in three stages (from 80% to 45% of the original power). The first stage reduces the power to 65%, lowering the temperature from 167℃ to 158℃ (approximately 5 minutes); the second stage reduces it to 55%, lowering the temperature to 154℃ (approximately 4 minutes); the third stage reduces it to 45%, stabilizing the temperature at 151℃ (the target temperature). Each adjustment is followed by a preset time pause to allow the asphalt temperature to stabilize before the next adjustment, preventing sudden temperature drops from affecting asphalt fluidity (temperature fluctuations are controlled within ±2℃). The insulation device controller, according to... =8 seconds, by reducing the energizing time of the heating wires inside the insulation layer (adjusting the energizing interval from 10 seconds / time to 12 seconds / time), the insulation time is shortened to 11 minutes and 52 seconds. At the same time, the auxiliary heat dissipation ventilation vents are opened (opening at 20%), and the temperature change inside the insulation tank is monitored in real time. If the temperature drops sharply from 151℃ to 148℃, the ventilation vent opening is automatically reduced to 10% to maintain the temperature stable in the range of 149-151℃. If any abnormal situation occurs during the process, such as a sudden failure of the asphalt temperature sensor, the system automatically switches to the backup sensor (error ±0.5℃) to collect data, and at the same time recalls the most recent data. The temperature trend (0.5℃ / 10 minutes) estimates the current asphalt temperature to be approximately 150.5℃. The actual viscosity is approximately 0.088 Pa·s, ensuring uninterrupted compensation calculations. If staff discover through the human-computer interaction module that the actual asphalt viscosity is 0.085 Pa·s (slightly lower than the calculated value of 0.09 Pa·s), they can manually adjust the value. Fine-tuning was performed to 14.5℃ (target temperature 150.5℃). Manual commands had higher priority than automatic commands. After adjustment, the system recorded the reason for manual intervention (viscosity detection deviation) and its effect (viscosity recovered to 0.088 Pa·s after temperature stabilization), which will be used for correction during subsequent model optimization. , Reference basis for equal coefficients.

[0040] After this batch of production is completed, the data storage and management module will store the complete data for the midday temperature peak period. 6℃ RH , =14℃ The bond strength test results of the modified asphalt (after 8 seconds) were compared with the production data during the low-temperature periods in the morning and evening to analyze the different temperature ranges. The model iterative optimization module extracts key data features (the effect of modified asphalt on the process adjustment amount) to match the process adjustment amount. Sensitivity = 0.04 =30%RH The influence weights are updated in the training dataset, and in subsequent iterations, the formula is updated iteratively using the compensation coefficient. (Pick right By iteratively updating coefficients, the system can more accurately adapt to the dynamic temperature changes during the high-temperature period in summer, thereby improving the production quality stability of modified asphalt concrete.

[0041] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. An Internet of Things-based material mixing monitoring system for asphalt concrete production, characterized in that, The system includes: IoT sensing module: used to collect environmental parameters and process parameters in the asphalt concrete production area in real time; Data storage and management module: Stores real-time environmental parameters, historical environmental data, real-time process parameters, and historical production effect data collected by the IoT sensing module, and also supports data retrieval and backup; Intelligent compensation model module: It has a preset compensation algorithm based on the relationship between environmental parameters and process parameters. It calls the real-time environmental parameters in the data storage and management module to calculate and generate the compensation amount of process parameters, and supports the manual correction of the compensation amount of process parameters by the staff. Production control execution module: Receives the process parameter compensation amount output by the intelligent compensation model module, and automatically adjusts the operating parameters of the asphalt concrete production equipment to achieve dynamic adjustment of aggregate ratio, mixing time, asphalt heating temperature and heat preservation time; Model Iterative Optimization Module: Based on historical environmental data and historical production effect data in the data storage and management module, an iterative optimization algorithm is used to iteratively optimize the compensation algorithm in the intelligent compensation model module.

2. The Internet of Things-based asphalt concrete production material mixing monitoring system according to claim 1, characterized in that, The environmental parameters in the IoT sensing module include atmospheric humidity, wind speed, diurnal temperature range, rainfall status, and high temperature status, while the process parameters include aggregate moisture content, aggregate ratio, mixing time, asphalt heating temperature, and heat preservation time.

3. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 1, characterized in that, The intelligent compensation model module is pre-programmed with compensation algorithms based on the correlation between environmental parameters and process parameters, including a rainy day humidity compensation algorithm and a high temperature compensation algorithm. The rainy day humidity compensation algorithm pre-sets a baseline humidity. When the real-time humidity is higher than the baseline humidity, it calculates the increase in aggregate moisture content based on the correlation between the humidity increment and the increase in aggregate moisture content, determines the increase in dry aggregate dosage based on the increase in aggregate moisture content, and extends the mixing time. The high temperature compensation algorithm pre-sets a baseline temperature. When the real-time temperature is higher than the baseline temperature, it calculates the decrease in asphalt viscosity based on the correlation between the temperature increment and the decrease in asphalt viscosity, determines the decrease in asphalt heating temperature based on the decrease in asphalt viscosity, and shortens the heat preservation time. It also has a parameter display function, allowing staff to view real-time environmental parameters, process parameters, compensation amounts, and production equipment operating status via a touch screen or host computer software. It also allows staff to manually correct the process parameter compensation amount, with manual correction commands having higher priority than automatic output commands.

4. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 3, characterized in that, In the intelligent compensation model module, the increase in aggregate moisture content is calculated based on the correlation between the increase in humidity and the increase in aggregate moisture content. The calculation formula is as follows: ,in, It refers to the increase in aggregate moisture content, specifically the difference between the actual moisture content of the aggregate and the reference moisture content caused by changes in ambient humidity. It is the humidity influence coefficient. It is an increase in atmospheric humidity. It is the wind speed correction factor. For real-time wind speed, This is the correction value for the moisture content of the aggregate foundation.

5. The Internet of Things-based asphalt concrete production material mixing monitoring system according to claim 4, characterized in that, In the intelligent compensation model module, the increase in dry aggregate usage is determined based on the increase in aggregate moisture content, and the mixing time is extended. The formula for calculating the increase in dry aggregate usage is as follows: ,in, It is an increase in the amount of dry aggregate used. This is the baseline dry aggregate dosage. This refers to the target moisture content of the mixture; the formula for calculating the mixing time is: ,in, It is the amount of time the stirring is extended. It is the correlation coefficient between moisture content and stirring time. It is the aggregate gradation correction factor. The coefficient for non-uniform aggregate gradation.

6. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 3, characterized in that, In the intelligent compensation model module, when the real-time temperature is higher than the reference temperature, the reduction in asphalt viscosity is calculated based on the correlation between the temperature increment and the reduction in asphalt viscosity. The calculation formula is as follows: ,in, This refers to the decrease in asphalt viscosity. It is the reference viscosity of asphalt. It is the temperature sensitivity coefficient. It is the increase in ambient temperature. It is the atmospheric humidity correction factor. This is the real-time atmospheric humidity.

7. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 6, characterized in that, In the intelligent compensation model module, the reduction in asphalt heating temperature is determined based on the reduction in asphalt viscosity, and the heat preservation time is shortened accordingly. The reduction in heating temperature is as follows: ,in, It is the decrease in the heating temperature of asphalt. It is the viscosity-temperature compensation coefficient. It is a heating time correction factor. This represents the total heating time for the day; the formula for calculating the heat preservation time is: ,in, This refers to the reduction in asphalt insulation time. It is the viscosity-holding time correlation coefficient. For the real-time power of the insulation device, It is the insulation power correction factor.

8. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 1, characterized in that, The production control execution module receives the process parameter compensation amount output by the intelligent compensation model module, and adjusts the production parameters through various controllers: the aggregate batching controller adjusts the dry aggregate usage by adjusting the speed of the batching screw conveyor; the mixing motor controller adjusts the mixing speed by changing the motor frequency, thereby extending or shortening the mixing time; the asphalt heating controller uses pulse width modulation technology to adjust the asphalt heating temperature by adjusting the power of the heating tube; and the insulation device controller adjusts the insulation time by controlling the on / off duration of the heating wire in the insulation layer.

9. The Internet of Things-based material mixing monitoring system for asphalt concrete production according to claim 1, characterized in that, The model iterative optimization module uses an iterative optimization algorithm to iteratively optimize the compensation algorithm in the intelligent compensation model module. The iterative formula is as follows: ,in, It is the first The compensation coefficient after the next iteration. It is the first Initial values ​​of the compensation coefficients in the next iteration It's the learning rate, which controls the update step size in each iteration. It is the error compensation function, and the calculation formula is: ,in For actual production results data, For the production performance data predicted by the model, For the target value of production effect, It is the error function on the first iteration coefficients The partial derivatives reflect the degree to which changes in the coefficients affect the error. It is a decay coefficient, used to reduce the update magnitude as the number of iterations increases. It is the current iteration number. It represents the total number of iterations.

Images