An asphalt pavement paving quality management system

Abstract

The application relates to the technical field of measurement and monitoring of road engineering variables, and a bituminous pavement paving quality management system, which comprises a data acquisition module configured to acquire real-time meteorological data, mixture temperature parameters and pavement quality monitoring data; a viscosity analysis module configured to determine a dynamic viscosity adjustment range of bituminous material based on the real-time meteorological data and the mixture temperature parameters; a temperature control module configured to regulate and control mixing temperature according to bituminous material viscosity change and generate a target paving temperature curve; and a power optimization module configured to match a dynamic adjustment strategy of a paving machine screed heating power based on the target paving temperature curve. Through the system, meteorological and construction data are monitored in real time, bituminous viscosity, screed power and other parameters are dynamically regulated and controlled, closed-loop optimization is realized, paving quality is improved, and intelligent construction is realized.

Description

Technical Field

[0001] This application relates to the field of measurement and monitoring technology of road engineering variables, and in particular to an asphalt pavement paving quality management system. Background Technology

[0002] The asphalt pavement paving quality management system mainly involves ensuring the consistency and stability of paving quality by precisely controlling key parameters during the construction process.

[0003] This system combines real-time data monitoring and dynamic adjustment technology to monitor changes in the temperature, compaction, and viscosity of the mixture during paving, and optimizes equipment operation and material performance based on this data.

[0004] However, the system still faces several challenges: firstly, how to precisely control the heating power of the paver screed based on the temperature change curve of the asphalt mixture to avoid uneven pavement compaction caused by temperature differences; secondly, in high-temperature construction, how to utilize real-time meteorological data to adjust the viscosity of the asphalt material, thereby reducing wheel tracks and ensuring paving smoothness. Solving these problems will contribute to further improving the quality control level of paving construction. Summary of the Invention

[0005] To address the problems mentioned in the background art, this application provides an asphalt pavement paving quality management system.

[0006] This application provides an asphalt pavement paving quality management system, which adopts the following technical solution: An asphalt pavement paving quality management system, comprising:

[0007] Data acquisition module: configured to acquire real-time meteorological data, mixture temperature parameters, and pavement quality monitoring data;

[0008] The viscosity analysis module includes: a parameter calculation unit configured to use formulas... Calculate the viscosity adjustment coefficient of the asphalt material, where and These are empirical parameters set for regression analysis based on historical data. The current relative temperature is calculated as the ratio of ambient temperature to reference temperature. The current relative humidity;

[0009] Viscosity prediction unit: configured to update the target mixing temperature based on the viscosity adjustment coefficient. And combined with wind speed parameters Generate viscosity prediction models. As the reference mixing temperature, This is the viscosity-temperature conversion factor. This indicates the viscosity adjustment coefficient of the asphalt material;

[0010] Deviation determination unit: configured to compare the viscosity value measured in real time. With the preset target viscosity To determine whether there is a deviation , This is the viscosity deviation threshold;

[0011] The temperature control module includes:

[0012] Temperature curve generation unit: configured to plot the temperature decay curve of the mixture. , This indicates the predicted temperature of the mixture at paving time t. The initial temperature of the mixture. For the paving time, The temperature decay constant of the mixture;

[0013] Warning judgment unit: configured to be based on formula Determine whether the mixture has reached the warning temperature condition. Current temperature of the mixture;

[0014] Temperature compensation unit: configured to generate a temperature compensation command and adjust the sample temperature when the mixture temperature is lower than the warning value. ,in This is the temperature regulation coefficient. For the required adjustment of the mixing temperature increment, The target mixture temperature;

[0015] The power optimization module includes:

[0016] Temperature distribution acquisition unit: configured to acquire the actual temperature distribution of multiple measuring points in real time through a temperature sensor array. Calculate the average value of the measurements , where n represents the number of temperature sensor measurement points; and based on the mixture temperature decay curve of the temperature control module. Generate a temperature prediction sequence for the future control period;

[0017] Power adjustment unit: configured to adjust power based on target temperature value in each control cycle. Based on the predicted temperature sequence, the objective function is optimized as follows:

[0018]

[0019] Solving the Future Step power adjustment command, only the first command is executed. ,in This is the proportional gain factor. Here, k is the power smoothing weighting coefficient; k is the current control period, and m is the prediction step number. The target ironing plate temperature;

[0020] Global optimization unit: configured to handle temperature deviations exceeding a threshold The measuring points are compensated independently:

[0021]

[0022] Generate local compensation power and generate a global paving power adjustment table based on two-dimensional coordinates. To achieve regionally differentiated power collaborative optimization;

[0023] The execution feedback module applies the adjusted heating power to the paving operation, while monitoring the road surface compaction and wheel track conditions and feeding back the results to the temperature control module and power optimization module to optimize the parameters.

[0024] In one specific embodiment, the data acquisition module further includes:

[0025] Meteorological sensor unit: configured to acquire the current ambient temperature and relative humidity Mixture temperature sensor unit: configured to record the initial mixture temperature And collect the temperature of the mixture in real time. Wind speed monitoring unit: configured to acquire real-time wind speed parameters. Road surface quality testing unit: configured to collect road surface compaction data. Wheel track depth and surface flatness data.

[0026] In one specific implementation, the execution feedback module further includes:

[0027] Power execution unit: configured to apply the adjusted heating power to the paver screed; Quality monitoring unit: configured to collect pavement compaction data. Wheel track depth and surface flatness Data; Feedback optimization unit: configured to calculate compaction deviation based on the quality monitoring data. Smoothness deviation , To achieve the target compaction degree, To achieve the target flatness, parameter optimization suggestions are generated and fed back to the temperature control module and power optimization module.

[0028] In one specific implementation, a special high-temperature environment control module is also included, configured to: identify when the outside temperature is higher than a critical high-temperature value. It enters a special control state at times;

[0029] Using the modified power adjustment model Accounting is carried out, among which Adjust parameters for sensitivity. The current ambient temperature. Based on heating power, The asphalt viscosity is measured in real time. As the reference viscosity, High-temperature reference temperature.

[0030] In one specific implementation, a wheel track correction control module is also included, configured as follows:

[0031] When the length of continuous wheel tracks is found to exceed the predetermined length In this case, an alarm signal is triggered; the working angle of the ironing board is reset. ,in As the initial angle, This is the path sensitivity coefficient. Adjustment cycle for paving.

[0032] In one specific implementation, a microstructure detection module is also included, configured as follows:

[0033] Collect data on the microscopic particle shape distribution of asphalt surface and calculate surface roughness. ,in The height by which the surface profile deviates from the average line, and n represents the number of road surface smoothness detection points;

[0034] Using formula The determination of whether particle irregularity exceeds the standard is as follows: To allow the maximum roughness, Sampling length;

[0035] When the limit is exceeded, an early warning procedure is triggered, and a local enhanced thermal compensation command is generated. , For local thermal compensation power to address surface roughness deviations, Surface roughness adjustment coefficient, Target surface roughness.

[0036] In one specific implementation, an intelligent decision support module is also included, configured to: establish a comprehensive rating index system. ,in These are the weighting coefficients. Let n represent the various quality indicators, and n be the quality indicator constituting the comprehensive rating index system I. The number of items; generating an intelligent recommendation strategy database based on historical data; continuously iteratively optimizing key system parameters through machine learning algorithms. Generate and archive complete construction parameter documents.

[0037] In summary, this application includes at least one of the following beneficial technical effects:

[0038] The embodiments disclosed in this application provide an asphalt pavement paving quality management system that integrates real-time data monitoring and dynamic adjustment technology, overcomes the limitations of traditional processes, significantly improves construction quality and reduces maintenance costs. In response to the problem of the mixture temperature affecting compaction, the heating power of the screed is precisely controlled through sensors and a three-dimensional mapping relationship database to avoid local temperature anomalies and effectively improve the compaction quality of the pavement.

[0039] During high-temperature construction, the dynamic viscosity adjustment range of asphalt is calculated based on meteorological data, and the mixing temperature is adjusted accordingly. Combined with the power adjustment of the screed, the viscosity and plasticity of the mixture are improved, and wheel tracks are suppressed. At the same time, high-frequency detection instruments are used to collect data, and machine learning and digital twin technology are used for analysis and deduction to establish a closed-loop feedback optimization mechanism, automatically optimize key construction parameters, improve parameter adjustment efficiency, and ensure construction quality. In addition, the integration of multiple technologies such as blockchain, ZigBee, and BIM ensures data security, enables real-time transmission and intelligent decision-making, reduces reliance on manual experience, and promotes the intelligent and refined development of paving construction. Attached Figure Description

[0040] Figure 1 This is a flowchart of the modules of the asphalt pavement paving quality management system. Detailed Implementation

[0041] The embodiments of this application are described in detail below, and examples of the embodiments are shown in the accompanying drawings.

[0042] In the description of this specification, the references to "certain embodiments," "one embodiment," "some embodiments," "illustrative embodiment," "example," "specific example," or "some examples" refer to specific features, structures, materials, or characteristics described in connection with the described embodiment or example, which are included in at least one embodiment or example of this application. In this specification, the illustrative expressions of the above terms do not necessarily refer to the same embodiment or example. Furthermore, the specific features, structures, materials, or characteristics described may be combined in any suitable manner in one or more embodiments or examples.

[0043] Next, referring to the accompanying drawings, a quality management system for asphalt pavement paving according to the present invention is described, which addresses the problems of uneven compaction and frequent wheel tracks under high-temperature conditions during asphalt paving. The system first determines the dynamic viscosity adjustment range of the asphalt material, then adjusts the mixing temperature based on the viscosity, outputs a target paving temperature curve, and combines this curve with a dynamic adjustment strategy for matching the heating power of the screed. Finally, it is applied to the paving operation and provides feedback optimization on the actual compaction and wheel track conditions during the operation.

[0044] The first step involves acquiring real-time meteorological data such as ambient temperature and wind speed, and combining this with the initial asphalt mixture's factory outlet temperature data to calculate the dynamic viscosity adjustment range of the asphalt material under different construction conditions. Specifically, a sensor network is deployed at the construction site to collect meteorological elements such as ambient temperature and humidity, which are then transmitted to a central controller for analysis. These meteorological factors affect the cooling rate and viscosity characteristics of asphalt, and their fluctuation patterns must be accurately understood. For example, sunny and hot weather will cause the mixture to cool down faster, resulting in a shorter working window; humid air after rain may slow down the temperature drop and increase residual moisture, affecting the internal bonding force of the material, thereby causing changes in viscosity.

[0045] The second step involves further adjusting the mixing temperature based on the understanding of the viscosity variation range to generate a suitable target paving temperature curve. This step requires setting a reasonable discharge temperature range based on the newly derived viscosity standard. This involves controlling the raw material characteristics at the factory stage to ensure they meet the expected design specifications as closely as possible, and reserving a buffer margin for subsequent construction to prevent quality defects caused by excessive cooling or heating. In one embodiment, if a high risk of rapid heat loss due to strong sunlight is anticipated during an operation, the initial discharge setting point is appropriately increased to a few degrees Celsius above the usual standard to ensure that the desired range is still achieved upon arrival at the site. Simultaneously, a continuous monitoring and control model is established to predict the entire trajectory to verify feasibility and adaptability, and timely fine-tuning is performed to avoid over-correction that could cause problems.

[0046] The third step, based on the aforementioned results, further explores how to dynamically match the heating power of the paver screed to ensure excellent smoothness. This mainly involves flexibly switching power supply modes for different paving conditions to maintain a sufficiently soft and hard interface in specific situations, enhancing the ability to meet connection requirements. The research content covers a multi-dimensional linkage mechanism, including a sensing feedback unit receiving signals from the front to determine whether the local pressure difference deviates from the normal threshold, and then directing the rear device to increase or decrease the energy input accordingly until it returns to the equilibrium track. The entire process is a closed-loop operation, reducing human error, improving automation efficiency, reducing operation and maintenance costs, and maximizing benefits. For example, when certain road sections have significant differences in foundation bearing capacity due to insufficient preliminary preparation or unstable geological structures, the surface preheating function can be temporarily enhanced to compensate for inherent defects and achieve a good fit, avoiding separation gaps that damage the overall appearance and durability.

[0047] The fourth and final step emphasizes the evaluation and verification of the effectiveness of the above-mentioned theoretical solutions during practical application. This requires continuously collecting ground-based measured data to compare with theoretical deductions for any deviations, summarizing experiences and lessons learned, and continuously improving technical parameter settings to ensure the final product better meets actual user satisfaction standards. Specifically, this involves installing several sets of high-frequency detection instruments to record every millimeter of change across the entire area without blind spots. This data is then uploaded to a database via wireless communication for in-depth analysis and statistical processing, generating graphical reports for technical personnel to review and make decisions. These reports guide the next steps in optimizing action plans, clarifying responsibilities, and accelerating progress until perfect completion, acceptance, and delivery. For example, during the construction of a new cross-city main road, it was discovered that the drastic temperature difference between day and night in the mountainous area caused significant elevation differences at joints during night shift changes. The newly developed intelligent temperature control system was quickly implemented to resolve the problem, restoring a smooth and uniform appearance, earning praise and recognition from all parties, and becoming a model project.

[0048] This invention discloses an asphalt pavement paving quality management system, comprising real-time monitoring and control of temperature, meteorological conditions, and equipment parameters throughout the paving operation to ensure optimal quality management of asphalt pavement paving. Specifically, the system collects and analyzes asphalt mixture temperature parameters and real-time meteorological data to first assess the dynamic viscosity adjustment range of the asphalt material during the paving process. Based on this result, a corresponding mixing temperature adjustment scheme is formulated, thereby generating a target paving temperature curve. Further, based on this target temperature curve, a dynamic adjustment strategy for the screed heating power is designed and matched, and the adjusted power parameters are applied to the actual construction during the paving process.

[0049] To address the issue of uneven pavement compaction, this system employs dynamic adjustment technology for the heating power of the paver screed. By accurately calculating and predicting the temperature changes of the mixture, it ensures that the screed can adapt to changes in the mixture's state under different working conditions. For example, when the mixture experiences significant temperature differences due to environmental or transportation conditions, dynamically adjusting the screed's heating power can effectively reduce insufficient or excessive compaction caused by localized low-temperature areas, thereby improving overall smoothness and compaction quality.

[0050] To address the issue of wheel tracks easily appearing during paving under high-temperature conditions, this invention combines real-time meteorological data (such as air temperature, humidity, and solar radiation) to accurately assess the impact of these factors on the viscosity of asphalt mixtures. Subsequently, by adjusting the mixing temperature, the risk of excessive viscosity due to overly soft asphalt material is preemptively suppressed. Finally, under the target paving temperature curve, a feedback mechanism for compaction and wheel tracks is introduced to dynamically optimize relevant parameters, further reducing the incidence of quality problems under high-temperature conditions. This method not only improves work efficiency but also ensures the stability of paving construction quality.

[0051] The data acquisition module further includes: a meteorological sensor unit configured to acquire the current ambient temperature. and relative humidity Mixture temperature sensor unit: configured to record the initial mixture temperature And collect the temperature of the mixture in real time. Wind speed monitoring unit: configured to acquire real-time wind speed parameters. Road surface quality testing unit: configured to collect road surface compaction data. Wheel track depth and surface flatness data.

[0052] Based on the calculated dynamic viscosity adjustment range, an intelligent temperature control system is used in the asphalt mixing plant to regulate the mixing temperature. This system, centered on a PLC controller, uses a PID control algorithm to adjust the gas flow rate in the heating furnace, achieving precise control of the mixing temperature. For example, if a higher dynamic viscosity is required, necessitating improved mixture flowability, the mixing temperature is increased from the conventional 170℃ to 175℃. Simultaneously, a paving construction simulation model is established using BIM technology. Parameters such as the adjusted mixing temperature, transportation time, and environmental meteorological data are input into the model to simulate temperature changes in the mixture during transportation and paving, generating a target paving temperature curve. Assuming a paving length of 1000 meters, the target paving temperature curve generated by the model shows that the temperature of the mixture should be 165℃ when it reaches the starting point of paving and no lower than 140℃ when it reaches the end point. A temperature control point is set every 50 meters to ensure that temperature changes meet expectations.

[0053] The viscosity analysis module further includes: a parameter calculation unit configured to calculate parameters using formulas. Calculate the viscosity adjustment coefficient of the asphalt material, where and These are empirical parameters set for regression analysis based on historical data. The current relative temperature is calculated as the ratio of ambient temperature to reference temperature. The current relative humidity;

[0054] Viscosity prediction unit: configured to update the target mixing temperature based on the viscosity adjustment coefficient. And combined with wind speed parameters Generate viscosity prediction models. As the reference mixing temperature, This is the viscosity-temperature conversion factor. Indicates the viscosity adjustment coefficient of the asphalt material; Deviation judgment unit: configured to compare the viscosity value measured in real time. With the preset target viscosity To determine whether there is a deviation , The viscosity deviation threshold is used; based on the target paving temperature curve, a dynamic adjustment strategy for the heating power of the screed is matched; the viscosity is predicted by combining wind speed; and the target mixing temperature is obtained. Then, combined with wind speed parameters Viscosity prediction model To calculate the predicted viscosity. For example, assuming the viscosity prediction model is... (in , , , (coefficients obtained by fitting experimental data), and Substituting the value into the model, we can obtain the predicted viscosity. It comprehensively considers the influence of factors such as ambient temperature and humidity, viscosity adjustment coefficient, and wind speed on asphalt viscosity.

[0055] Temperature and pressure sensors are installed on the paver. The temperature sensor monitors the surface temperature of the paved mixture in real time, while the pressure sensor detects pressure changes beneath the screed. A three-dimensional mapping database of temperature, pressure, and heating power is established, and the target paving temperature curve and real-time monitoring data are input into the paver's control system. When the temperature sensor detects that the mixture temperature in a certain area is 10°C lower than the target temperature curve, and the pressure sensor shows that the pressure value in that area is 15% lower than the normal value, the control system automatically increases the screed's heating power in that area from 60% to 80% of the rated power, based on the mapping database. Simultaneously, by adjusting the on / off time ratio of the heating pipes, dynamic fine-tuning of the heating power is achieved, with an adjustment accuracy of ±2%. For example, in a continuous paving operation, as the ambient temperature gradually decreases, the system automatically increases the screed's heating power from the initial 50% to 70%, ensuring that the paved mixture remains in a suitable softened state and guaranteeing paving smoothness.

[0056] The temperature control module further includes: a temperature curve generation unit configured to plot the temperature decay curve of the mixture. , This indicates the predicted temperature of the mixture at paving time t;

[0057] Warning judgment unit: configured to be based on formula The temperature compensation unit is configured to determine whether the mixture has reached the warning temperature condition. When the mixture temperature is below the warning value, it generates a temperature compensation command and adjusts the sample temperature. ,in This is the temperature regulation coefficient. The temperature decay constant of the mixture, where For the paving time, Current temperature of the mixture The initial temperature of the mixture. For ambient temperature, For the required adjustment of the mixing temperature increment, The target mixture temperature;

[0058] During the paving operation, actual compaction and wheel track data are collected in real time. Based on the collected data, the dynamic viscosity adjustment range, mixing temperature, and screed heating power are optimized. At the paving site, a detection section is set up every 20 meters along the paving direction. Each section is equipped with three nuclear density meters and one laser leveling meter to collect real-time compaction and wheel track depth data. The data is transmitted to the server in the quality monitoring center via a 4G network. The server analyzes the data using machine learning algorithms. If a detection section detects a compaction degree lower than the design standard (96%) for three consecutive times and a wheel track depth exceeding 3mm, the server will trigger the feedback optimization mechanism. First, the actual viscosity of the asphalt material was inferred from the compaction and wheel track data, and compared with the calculated dynamic viscosity adjustment range. If the actual viscosity was too high, the lower limit of the dynamic viscosity adjustment range was lowered by 0.1 Pa·s. Second, the mixing temperature was recalculated based on the inferred results and increased by 3-5℃. Finally, the dynamic adjustment strategy for the heating power of the screed was adjusted, reducing the adjustment threshold of the heating power from ±10% to ±5%. Through continuous feedback and optimization, in a highway paving project, the pavement compaction qualification rate increased from the initial 85% to 98%, and the average wheel track depth decreased from 5 mm to 1.5 mm, significantly improving the paving quality of the asphalt pavement.

[0059] During asphalt pavement paving, co-optimizing the heating power of the screed in each zone to avoid localized overheating or underheating can be achieved through a Model Predictive Control (MPC) framework and a regionally differentiated adjustment strategy. The following describes a rolling optimization mechanism built based on a temperature prediction model, incorporating the power optimization module:

[0060] I. Temperature Prediction Model and Control Cycle Design

[0061] 1) The internal prediction model is constructed using the mixture temperature decay model of the temperature control module as the prediction basis:

[0062]

[0063] This model describes the decay of the mixture temperature with paving time t, where The initial temperature. For ambient temperature, This is the temperature decay constant. By inputting environmental data (such as wind speed, temperature, and humidity) and mixture parameters (such as initial temperature and viscosity) in real time, the temperature evolution of different regions during future control cycles can be predicted.

[0064] 2. Control cycle and rolling optimization

[0065] Period setting: Define the control period as... (e.g., once per second), perform the following steps within each cycle: ① Collect the current temperature distribution at each measuring point. (k is the current period number); ② Generate a temperature prediction sequence for the next m periods based on the prediction model. ③ Solve the open-loop optimization problem to obtain the power adjustment command for the next m steps. Only step 1 is executed. ;

[0066] Rolling characteristics: Through a cycle of "prediction-optimization-execution-feedback", the model error is dynamically corrected to adapt to environmental changes (such as sudden changes in wind speed and fluctuations in mixture temperature).

[0067] II. Multi-region power collaborative optimization algorithm

[0068] 1. Objective Function and Constraints - Optimization Objective: Minimize the costs of temperature deviation and power fluctuation, while avoiding local overheating / insufficiency.

[0069] Where: n represents the number of measuring points on the temperature sensor. To predict the number of steps; The power smoothing weighting coefficient is used to avoid frequent adjustments. The target ironing plate temperature;

[0070] Constraints: ① Power physical limit: ② Temperature safety threshold: (Core constraints of the global optimization unit); ③ Regional differentiation constraints: Set higher priority for key areas (such as the easily heat-dissipating areas at the edge of the paver) to ensure their power adjustment. Prioritize meeting temperature requirements;

[0071] 2) Distributed solution and region compensation

[0072] Measurement point grouping and coordination: The ironing plate is divided into several regions (e.g., left, center, and right regions). Measurement points within each group share a power adjustment strategy, reducing computational complexity. For example, the left region, being exposed to the elements, dissipates heat faster, allowing for the setting of a power adjustment gain. Based on formula For high-temperature areas Reduce power consumption and increase power consumption in low-temperature regions.

[0073] Local overheating / underheating handling: When the temperature deviation at a certain measuring point exceeds the threshold... At that time, an independent compensation mechanism is triggered:

[0074] in , The abnormality can be quickly corrected by increasing the adjustment gain.

[0075] 3. Generation of Global Power Adjustment Table

[0076] Based on the optimization results, a global power adjustment table in two-dimensional coordinates is generated. ,in Corresponding positions on the ironing board: Direction (paving width) is divided into equal parts, The direction (the direction of paving) is divided into Divide equally; each cell The power value is calculated from the deviation between the average temperature of the measuring points in the area and the target value, thus achieving precise spatial control.

[0077] III. Implementation Process and Key Technologies

[0078] 1. Data Acquisition and Transmission: Real-time data acquisition via temperature sensor array (e.g., infrared thermal imager + thermocouple). Temperature distribution at each measuring point, with an accuracy of [missing information]. After data is preprocessed by edge computing nodes, it is transmitted to the central controller, with latency controlled within [a certain range]. within;

[0079] 2. Model Prediction and Optimization Solution: The temperature decay constant is updated online using the recursive least squares method. It adapts to different asphalt mixture characteristics; the optimization problem is solved using a quadratic programming (QP) algorithm, accelerated by parallel computing, ensuring that... The calculation is completed within the time limit;

[0080] 3. Execution and Feedback: The power adjustment command is sent to each heating unit through the distributed control system (DCS), driving the solid-state relay to adjust the heating power with a resolution of 1% of the rated power; in the next cycle, the predicted temperature is compared with the measured temperature, the model error is calculated and the prediction parameters are corrected to form a closed-loop feedback.

[0081] IV. Application Effects and Advantages

[0082] Improved temperature uniformity: Through synergistic optimization, the standard deviation of ironing plate surface temperature is reduced from ±8°C in traditional control to ±3°C, and the incidence of local overheating / underheating is reduced by 70%;

[0083] Construction quality optimization: uneven road surface compaction was reduced by 50%, and the average wheel track depth was reduced from 5mm to 1.5mm;

[0084] Intelligent upgrade: Continuously optimize model parameters by combining machine learning (e.g.) The system's adaptive capability continuously improves with the accumulation of construction data, forming an intelligent closed loop of "prediction-control-learning".

[0085] The execution feedback module further includes:

[0086] Power execution unit: configured to apply the adjusted heating power to the paver screed; Quality monitoring unit: configured to collect pavement compaction data. Wheel track depth and surface flatness Data; Feedback optimization unit: configured to calculate compaction deviation based on the quality monitoring data. Smoothness deviation , To achieve the target compaction degree, To achieve the target flatness, parameter optimization suggestions are generated and fed back to the temperature control module and power optimization module; the central controller builds a data storage and sharing platform based on blockchain technology to realize distributed storage and encrypted transmission of meteorological data, temperature data and calculation results, ensuring data integrity and traceability.

[0087] In practical implementation, the central controller is equipped with the Hyperledger Fabric blockchain framework, establishing a consortium blockchain network among multiple nodes, including the construction company headquarters, supervision units, and material suppliers. Meteorological data, temperature data, and dynamic viscosity calculation results collected by sensors are encrypted using a hash algorithm and stored as blocks on each node. For example, when the temperature data of a batch of asphalt mixture is uploaded to the blockchain, the system automatically generates a unique hash value and establishes a chain-like association with the preceding and following blocks. If the data is tampered with, the hash value will change, and the system will immediately trigger an alarm. Regarding data sharing, if the supervision unit needs to retrieve meteorological data for a specific period for quality verification, it can initiate a request to each node through a smart contract. After multi-party consensus verification, the encrypted data can be obtained, decrypted, and viewed, achieving transparency and immutability of construction data throughout the entire process and providing a reliable basis for quality traceability.

[0088] It also includes a special high-temperature environment control module, configured to: identify when the outside temperature exceeds the critical high-temperature value. It enters a special control state at times;

[0089] Using the modified power adjustment model Accounting is carried out, among which Adjust parameters for sensitivity. The current ambient temperature. Based on heating power, The asphalt viscosity is measured in real time. As the reference viscosity, High-temperature reference temperature;

[0090] Prioritize ensuring constant working conditions in key areas; assess the impact of additional costs under special conditions and generate a cost-quality optimization report. The screed heating system of the paver adopts zoned independent heating control, dividing the screed into multiple heating units. Each heating unit is equipped with an independent temperature sensor and heating power adjustment device to adapt to the differentiated heating needs under different paving widths and thicknesses.

[0091] In practice, the paver screed is divided into five heating units along its width, each unit being 1.2 meters long. A K-type thermocouple temperature sensor is installed at the center of each unit's surface. Each heating unit is controlled by an independent solid-state relay to turn the heating element on and off, and the heating power is adjusted using PWM (Pulse Width Modulation) technology. For example, during operations where the paving width is expanded from 3 meters to 6 meters, if the system detects a 5°C temperature drop in the outer heating unit due to increased heat dissipation area, it automatically increases the heating power of that unit from 70% to 85%, while maintaining the original power of the inner units. This ensures that the temperature uniformity error of the entire screed working surface is controlled within ±3°C, avoiding paving quality defects caused by localized overheating or undercooling.

[0092] This also includes a wheel track correction control module, configured to: when a continuous wheel track length exceeds a predetermined length... In this case, an alarm signal is triggered; the working angle of the ironing board is reset. ,in As the initial angle, For path sensitivity coefficient, sensitivity coefficient The screed angle needs to be determined and adjusted reasonably based on factors such as the specific characteristics of the paver, construction materials, and construction environment to ensure that the adjustment can effectively address road surface unevenness. For paving adjustment cycle;

[0093] The impact trend of the new scheme on the overall flatness of the road surface is predicted by finite element simulation, and adjustment suggestions are generated. In the feedback optimization process, digital twin technology is introduced to construct a virtual model of asphalt pavement paving. Real-time collected data is input into the virtual model for simulation and deduction to predict the impact of different parameter adjustment schemes on the final paving quality and help determine the optimal optimization strategy.

[0094] During the implementation phase, a 1:1 digital twin model of the actual construction site was built using the Unity3D platform, digitally modeling elements such as pavers, rollers, and weather conditions. When the quality monitoring center server received abnormal data on compaction and wheel track depth, it synchronized the data to the digital twin model. Based on preset physics engines and material property parameters, the model simulated adjustments to parameters such as dynamic viscosity, mixing temperature, and screed power using 10 different schemes. For example, in the feedback optimization of insufficient compaction in a certain section, the model simulation showed that increasing the mixing temperature by 4°C and the screed heating power by 12% could increase the compaction to 97%, while maintaining the wheel track depth below 2mm. Based on this, technicians adjusted the construction parameters to ensure the actual paving quality met expectations, reducing trial-and-error costs and construction delays.

[0095] It also includes a microstructure detection module, configured to: collect data on the shape distribution of microparticles on the asphalt surface and calculate the surface roughness. ,in The height by which the surface profile deviates from the average line, and n represents the number of road surface smoothness detection points;

[0096] Using formula The determination of whether particle irregularity exceeds the standard is as follows: To allow the maximum roughness, Sampling length;

[0097] When the limit is exceeded, an early warning procedure is triggered, and a local enhanced thermal compensation command is generated. , For local thermal compensation power to address surface roughness deviations, Surface roughness adjustment coefficient, The target surface roughness is achieved by using intelligent transport vehicles equipped with temperature control devices during the transportation of asphalt mixtures. These vehicles communicate with the central controller via the onboard control system to adjust the insulation measures of the transport vehicles in real time, ensuring that the temperature fluctuation range of the mixture is controlled within ±5℃ when it arrives at the construction site.

[0098] In practical applications, an electric heating insulation blanket and a circulating hot air system are equipped for the transport vehicle, and the vehicle-mounted control system is equipped with a 4G communication module to interact with the central controller in real time. When the vehicle is in transit, the central controller calculates the target temperature that the mixture should maintain based on the real-time meteorological data and the remaining transport time, and sends an instruction to the vehicle-mounted control system. For example, in case of a sudden drop in temperature and a remaining transport time of 30 minutes, if the central controller predicts that the temperature of the mixture will drop by 8°C, it will send an instruction to the vehicle to start the electric heating insulation blanket and increase the circulating hot air temperature from 50°C to 65°C. At the same time, the vehicle-mounted control system monitors the temperature of the mixture in real time and dynamically adjusts the heating power through the PID adjustment algorithm, so that the temperature of the mixture is stable within the range of the target temperature ±5°C when it arrives at the site, ensuring the continuity and quality stability of the paving operation.

[0099] Furthermore, it also includes an intelligent decision support module, configured to: establish a comprehensive rating index system , where is the weight coefficient, are the quality indicators, and n represents the number of quality indicators that make up the comprehensive rating index system I; generate an intelligent recommendation strategy database based on historical data; continuously iterate and optimize the key parameters of the system through machine learning algorithms , generate a complete construction parameter document and file it. By establishing an early warning mechanism for the paving quality of asphalt pavement, when the deviation between the real-time collected data and the preset threshold exceeds a certain range, the system automatically generates a warning message and notifies relevant construction management personnel through means such as text messages and APP push, so as to take intervention measures in a timely manner.

[0100] In the implementation process, warning thresholds for key indicators such as compaction degree, temperature, and rut depth are set in the quality monitoring center server. For example, a warning is triggered when the compaction degree is lower than 95%, the paving temperature is lower than 135°C, or the rut depth exceeds 4 mm. When the data collected by the sensor triggers the threshold, the server sends a text message containing abnormal data, location information, and preliminary processing suggestions to the project manager, technical person in charge, etc. through Alibaba Cloud SMS service; at the same time, a warning pop-up window is pushed in the construction management APP, showing a detailed quality anomaly analysis chart. For example, when the compaction degree of a certain detection section is detected as 94% twice consecutively, the system immediately issues a warning, and the construction management personnel can quickly rush to the site according to the warning information, call the digital twin model to analyze the reason, arrange for the roller to re-compact and adjust the subsequent paving parameters, and eliminate the quality problem at the budding stage.

[0101] Although the embodiments of the present application have been shown and described above, it can be understood that the above embodiments are exemplary and should not be construed as limitations of the present application. Those of ordinary skill in the art can make changes, modifications, substitutions, and variations to the above embodiments within the scope of the present application.​​

Claims

1. An asphalt pavement paving quality management system, characterized in that, include: Data acquisition module: configured to acquire real-time meteorological data, mixture temperature parameters, and pavement quality monitoring data; The viscosity analysis module includes: a parameter calculation unit configured to use formulas... Calculate the viscosity adjustment coefficient of the asphalt material, where and These are empirical parameters set for regression analysis based on historical data. The current relative temperature is calculated as the ratio of ambient temperature to reference temperature. The current relative humidity; Viscosity prediction unit: configured to update the target mixing temperature based on the viscosity adjustment coefficient. And combined with wind speed parameters Generate viscosity prediction models. As the reference mixing temperature, This is the viscosity-temperature conversion factor. This indicates the viscosity adjustment coefficient of the asphalt material; Deviation determination unit: configured to compare the viscosity value measured in real time. With the preset target viscosity To determine whether there is a deviation , This is the viscosity deviation threshold; The temperature control module includes: Temperature curve generation unit: configured to plot the temperature decay curve of the mixture. , This indicates the predicted temperature of the mixture at paving time t. The initial temperature of the mixture. For the paving time, The temperature decay constant of the mixture; Warning judgment unit: configured to be based on formula Determine whether the mixture has reached the warning temperature condition. Current temperature of the mixture; Temperature compensation unit: configured to generate a temperature compensation command and adjust the sample temperature when the mixture temperature is lower than the warning value. ,in This is the temperature regulation coefficient. For the required adjustment of the mixing temperature increment, The target mixture temperature; The power optimization module includes: Temperature distribution acquisition unit: configured to acquire the actual temperature distribution of multiple measuring points in real time through a temperature sensor array. Calculate the average value of the measurements , where n represents the number of temperature sensor measurement points; and based on the mixture temperature decay curve of the temperature control module. Generate a temperature prediction sequence for the future control period; Power adjustment unit: configured to adjust power based on target temperature value in each control cycle. Based on the predicted temperature sequence, the objective function is optimized as follows: Solving the Future Step power adjustment command, only the first command is executed. ,in This is the proportional gain factor. Here, k is the power smoothing weighting coefficient; k is the current control period, and m is the prediction step number. The target ironing plate temperature; Global optimization unit: configured to handle temperature deviations exceeding a threshold The measuring points are compensated independently: Generate local compensation power and generate a global paving power adjustment table based on two-dimensional coordinates. To achieve regionally differentiated power collaborative optimization; The execution feedback module applies the adjusted heating power to the paving operation, while monitoring the road surface compaction and wheel track conditions and feeding back the results to the temperature control module and power optimization module to optimize the parameters.

2. The asphalt pavement paving quality management system according to claim 1, characterized in that, The data acquisition module includes: Meteorological sensor unit: configured to acquire the current ambient temperature and relative humidity ; Mixture temperature sensor unit: configured to record the initial mixture temperature And collect the temperature of the mixture in real time. ; Wind speed monitoring unit: configured to acquire real-time wind speed parameters ; Road surface quality testing unit: configured to collect road surface compaction data. Wheel track depth and surface flatness data.

3. The asphalt pavement paving quality management system according to claim 2, characterized in that, The execution feedback module includes: Power execution unit: configured to apply the adjusted heating power to the paver screed; Quality monitoring unit: configured to collect pavement compaction data. Wheel track depth and surface flatness data; Feedback optimization unit: configured to calculate compaction deviation based on quality monitoring data. Smoothness deviation , To achieve the target compaction degree, To achieve the target flatness, parameter optimization suggestions are generated and fed back to the temperature control module and power optimization module.

4. The asphalt pavement paving quality management system according to claim 3, characterized in that, It also includes a special control module for high-temperature environments, configured as follows: Identify when the outside temperature is higher than the critical high temperature value It enters a special control state at times; Using the modified power adjustment model Accounting is carried out, among which Adjust parameters for sensitivity. The current ambient temperature. Based on heating power, The asphalt viscosity is measured in real time. As the reference viscosity, High-temperature reference temperature.

5. The asphalt pavement paving quality management system according to claim 4, characterized in that, It also includes a wheel track correction control module, configured as follows: When the length of continuous wheel tracks is found to exceed the predetermined length In the event of this, an alarm signal is triggered; Reset the working angle of the ironing board ,in As the initial angle, This is the path sensitivity coefficient. Adjustment cycle for paving.

6. The asphalt pavement paving quality management system according to claim 5, characterized in that, It also includes a microstructure detection module, configured as follows: Collect data on the shape distribution of micro-particles on the asphalt surface and calculate the surface roughness. ,in The height by which the surface profile deviates from the average line, and n represents the number of road surface smoothness detection points; Using formula The determination of whether particle irregularity exceeds the standard is as follows: To allow the maximum roughness, Sampling length; When the limit is exceeded, an early warning procedure is triggered, and a local enhanced thermal compensation command is generated. , For local thermal compensation power to address surface roughness deviations, Surface roughness adjustment coefficient, Target surface roughness.

7. The asphalt pavement paving quality management system according to claim 6, characterized in that, It also includes an intelligent decision support module, configured as follows: Establish a comprehensive rating index system ,in These are the weighting coefficients. Let n represent the various quality indicators, and n be the quality indicator constituting the comprehensive rating index system I. Quantity; Generate an intelligent recommendation strategy database based on historical data; Continuously optimize key system parameters through machine learning algorithms. Generate and archive complete construction parameter documents.

Images