Intelligent asphalt proportion optimization and dynamic adjustment method and system

Abstract

The invention discloses an intelligent asphalt proportion optimization and dynamic adjustment system and a method thereof. A data acquisition module of the system is used for acquiring key parameters of asphalt in real time and transmitting the parameters to a controller. The controller is provided with a high-performance central processing unit and an optimization control algorithm, receives and processes data from the data acquisition module, analyzes the matching state of asphalt and generates a dynamic adjustment instruction. And the execution mechanism automatically adjusts the asphalt proportion after receiving the control instruction. The database is used for storing historical and real-time data and supporting data management and analysis. The system automatically updates and optimizes model parameters through a self-adaptive learning mechanism according to real-time data and feedback generated in the production process, improves the stability of asphalt proportioning and the product quality, has automatic fault detection and emergency shutdown functions, and ensures the production safety. According to the invention, intelligent optimization, dynamic adjustment and stable production of the asphalt proportion can be realized, and the production efficiency and the product quality are obviously improved.

Description

Technical Field

[0001] The present invention relates to the field of asphalt, and in particular to an intelligent asphalt mix ratio optimization and dynamic adjustment method and system thereof. Background Art

[0002] In the asphalt production industry, the traditional asphalt ratio adjustment method mainly relies on manual experience and regular testing, which has many shortcomings. First, manual adjustment of the ratio is easily affected by human factors, such as the operator's experience level and fatigue level, resulting in low ratio accuracy, which in turn affects product quality. Secondly, the regular testing method has a lag and cannot reflect the changes in the production process in real time, making it difficult to adjust the ratio in time to adapt to changes in production needs and environmental conditions. In addition, the traditional method lacks intelligent and automated means, resulting in low production efficiency and high costs. In response to the above problems, the idea of ​​intelligent asphalt ratio optimization and dynamic adjustment has been proposed. However, in the prior art, although some similar systems have been proposed, they still have shortcomings in terms of intelligence, response speed, adaptability and reliability. For example, some systems lack adaptive learning algorithms and cannot automatically optimize the ratio according to real-time data in the production process; the actuators of some systems are not accurate enough to meet the requirements of high-precision ratios; and some systems have hidden dangers in terms of safety and reliability and cannot ensure the continuity and stability of the production process. Summary of the invention

[0003] In order to solve the above technical problems, the present invention provides an intelligent asphalt mix ratio optimization and dynamic adjustment method and system.

[0004] The present invention is achieved through the following technical solutions: The present invention provides an intelligent asphalt mix ratio optimization and dynamic adjustment method, the method comprising the following steps: Data acquisition: Through the data acquisition module integrating temperature sensor, pressure sensor, flow sensor and liquid level sensor, the key parameters of asphalt temperature, pressure, flow and liquid level are collected in real time, and the parameter data are transmitted to the controller; Data processing and analysis: The controller is equipped with a high-performance central processing unit and a pre-installed ratio optimization control algorithm. It performs data preprocessing and feature extraction based on the asphalt parameter data collected by the data acquisition module, and analyzes the current asphalt ratio status and quality characteristics; Model building and optimization: Establish an asphalt mix model based on historical data and real-time data, and use genetic algorithms or particle swarm optimization algorithms to optimize the mix to obtain the optimal asphalt mix parameters; Dynamic adjustment: Real-time monitoring of changes in production demand, construction environment and material properties, generating dynamic adjustment instructions based on the asphalt mix ratio model and control algorithm, and controlling the opening of the electric valve through the electric actuator to automatically adjust the asphalt mix ratio; Execution and feedback: The actuator includes an electric actuator and an electric valve, which responds quickly after receiving the control command and feeds back the adjusted ratio data to the controller for closed-loop control; Data storage and display: All data in the adjustment process are stored in the database, which is used to manage historical data and real-time data, and the production parameters and ratio status are displayed in a graphical form through the user interface; Adaptive learning: The control algorithm supports an adaptive learning mechanism, which automatically updates and optimizes model parameters based on real-time data and feedback generated during the production process to improve the stability of the ratio and product quality; Safety assurance: The system has automatic fault detection and emergency shutdown functions. When an abnormal situation is detected, it automatically stops production and provides guidance on resuming production after the abnormality is resolved.

[0005] Furthermore, the data processing and analysis includes the following steps: Data collection and transmission: The key parameters such as temperature, pressure, flow, liquid level, etc. are collected in real time through sensors in the data acquisition module and transmitted to the input of the controller in the form of digital signals. These data are collected regularly or in real time to ensure that the changes in the environment and raw materials during the production process can be accurately recorded.

[0006] Data cleaning: The controller first cleans the received raw data to remove outliers and noise that may be caused by sensor failure, communication errors, etc.

[0007] Filtering: Smoothing the data through filtering algorithms (such as Kalman filtering, sliding average filtering, etc.) to reduce short-term fluctuations caused by environmental interference, thereby improving data accuracy.

[0008] Data normalization: To ensure that all parameters can be analyzed at the same scale, the controller normalizes the data of each sensor, usually using zero-mean normalization or minimum-maximum normalization methods.

[0009] Time series analysis: Based on historical data and real-time data, time series analysis methods are used to extract trend information in asphalt mix ratios, such as temperature change trends, pressure fluctuation patterns, etc. This information can help determine changes in current production conditions.

[0010] Parameter interaction analysis: Interactive analysis of the relationship between different parameters (such as temperature and flow, pressure and liquid level) is carried out to explore potential correlations and extract feature combinations that have a greater impact on asphalt quality. This step can use methods such as Pearson correlation coefficient and regression analysis.

[0011] Furthermore, the model building includes the following steps: Historical data collection and analysis: Including: historical data collation, storing the production data collected in the asphalt mixing process in the database. These data include key parameters in the production process (such as temperature, pressure, flow, liquid level, etc.) and the corresponding finished product quality characteristics (such as viscosity, anti-aging, stability, etc.).

[0012] Feature selection and extraction: Analyze historical data and use data mining technology to extract the parameters that have the greatest impact on asphalt mix, such as the impact of temperature on viscosity, the impact of flow on mixing uniformity, etc. Use correlation analysis (such as Pearson correlation coefficient, principal component analysis) to select the most representative parameters.

[0013] Establish an asphalt mix ratio model and a mathematical model. Use the key parameters in the historical data to build an asphalt mix ratio mathematical model based on physical or empirical formulas. This model outputs an expected asphalt mix ratio and quality characteristic value based on the input parameters such as temperature, pressure, flow, etc.

[0014] The prediction model based on machine learning inputs historical data into the machine learning algorithm (such as linear regression, support vector machine, neural network, etc.), and trains the model through supervised learning so that it can predict the relationship between the ratio parameters and the quality of the finished product. The model forms a prediction model by learning the impact of different combinations of parameters on the quality of the final product.

[0015] Model verification and tuning: Use new historical data to verify the constructed model, adjust model parameters by comparing the output values ​​predicted by the model with the actual quality of the finished products produced, and improve the accuracy and robustness of the model.

[0016] The model optimization comprises the following steps: Real-time data input and correction: Real-time data collection: During the operation of the system, the key parameters such as temperature, pressure, flow rate, etc. in the current production are collected in real time and used as the input of the model.

[0017] Real-time data correction: Since external factors such as production environment and raw material characteristics may cause deviations in real-time data, the system performs data correction by real-time monitoring of production environment changes. For example, changes in ambient temperature will affect the viscosity of asphalt, and the system will make appropriate adjustments to the model input data based on actual environmental conditions.

[0018] Ratio optimization process: Objective function setting. In the optimization process, an objective function is first set, which is usually set according to production requirements, such as maximizing product quality stability, minimizing production costs, and improving material utilization. The objective function can be multi-objective, with different weights set according to different requirements. Then use genetic algorithms or particle swarm optimization algorithms for optimization.

[0019] Genetic algorithm optimization includes the following steps: Initial population generation: The system first generates a set of initial asphalt mix parameters (populations), which represent different mix schemes. Each individual is a potential mix scheme, including multiple variables such as temperature, pressure, flow, etc.

[0020] Fitness function calculation: Calculate the fitness of each individual based on the objective function (such as product quality, cost, etc.). The higher the fitness of the individual, the better the corresponding matching scheme.

[0021] Genetic operations: Genetic operations such as crossover and mutation are performed to generate new populations. The crossover operation combines two excellent individuals to generate a new matching scheme; the mutation operation randomly changes some parameters of the individual to introduce new characteristics and increase the diversity of exploration.

[0022] Selection and iteration: Select individuals with higher fitness to enter the next generation, and continue to perform genetic operations, iterating repeatedly until the stopping condition is met (such as reaching the set number of generations, or the fitness is no longer significantly improved).

[0023] The particle swarm optimization algorithm includes the following steps: Initialize the particle swarm: Each particle represents a ratio scheme. The initial particle swarm is randomly distributed in the parameter space. Each particle has a speed and a position, and the position represents the ratio parameter.

[0024] Update speed and position: Update the speed and position of the particle according to its current fitness. The position of the particle is adjusted by following the individual best position and the global best position, so that the particle gradually approaches the optimal ratio.

[0025] Iterative optimization: The particle swarm continuously adjusts its position according to the feedback of the objective function. After multiple iterations, the entire particle swarm will converge to the global optimal solution, that is, the optimal ratio solution.

[0026] Optimal mix parameters acquisition: Optimal mix selection: After multiple iterations of genetic algorithm or particle swarm optimization algorithm, the system will select the mix scheme with the highest fitness. This scheme is the optimal asphalt mix parameters under the current conditions.

[0027] Parameter application: The optimal mix ratio parameters are output to the actuator, which automatically adjusts the asphalt mix ratio to meet production needs. At the same time, the parameters will be stored in the database for future reference or further optimization.

[0028] Continuous optimization and updating: The system will continuously collect real-time production data, input it into the model, and update the model and ratio parameters through adaptive learning algorithms to ensure that the ratio is always in the optimal state during the production process.

[0029] Feedback after ratio optimization: After the optimized ratio parameters are applied to production, the system monitors the production effect in real time and verifies the optimization effect by comparing the difference between the predicted finished product quality and the actual finished product quality.

[0030] Feedback adjustment: If the optimization result is not ideal, the system will record the specific situation of the optimization and input the feedback information into the model to further improve the model and optimization algorithm to ensure that the next optimization is more accurate.

[0031] Furthermore, the dynamic adjustment includes the following steps: Real-time monitoring of production demand, construction environment and material characteristics; Includes: real-time monitoring of production demand, through the sensors and production management modules in the system, real-time acquisition of current production demand data, such as production progress, target output, production cycle, etc.

[0032] Construction environment parameter monitoring, real-time monitoring of external environmental factors that affect asphalt performance, such as temperature, humidity, air pressure, etc. at the construction site. These parameters are collected by environmental sensors and transmitted to the controller.

[0033] Material property monitoring: continuously monitors the properties of asphalt materials to ensure that their viscosity, fluidity, etc. meet the expected requirements. For different batches of raw materials or changes in raw materials during the production process, the system will automatically detect and record changes in material properties.

[0034] Dynamic adjustment based on the model; Includes: model input and calculation. The controller inputs the real-time collected environmental parameters, material properties and production demand data into the pre-established asphalt mix model. The model will generate a new mix recommendation based on the current production conditions.

[0035] Adjustment demand analysis: The model will compare with the current production status and calculate the deviation between the asphalt mix ratio in the current production process and the optimal mix ratio. If there is a significant difference between the mix ratio parameters and the optimal value recommended by the model, the system will generate a mix ratio adjustment demand.

[0036] Dynamic adjustment of the control algorithm: the controller dynamically analyzes the current mix status by running the control algorithm (such as PID control, fuzzy control, etc.), and generates corresponding adjustment instructions to indicate the specific parameters that need to be changed, such as asphalt flow, temperature, mixing ratio, etc.

[0037] Generate dynamic adjustment instructions: Including: parameter optimization and command generation, the system automatically generates ratio adjustment commands based on the model analysis results. The adjustment commands contain specific ratio parameters, such as asphalt flow, aggregate ratio, temperature setting, etc. that need to be adjusted.

[0038] Multi-objective optimization: When generating adjustment instructions, the system not only considers production efficiency and quality, but also production costs and energy consumption. Through comprehensive optimization, it generates the most economical adjustment plan.

[0039] Furthermore, the execution and feedback include the following steps: Automatic adjustment via actuator: Including: the actuator responds, the adjustment command is sent to the actuator through the controller, and the actuator includes an electric actuator and an electric valve. The electric actuator quickly adjusts the opening of the electric valve according to the command, thereby changing the ratio and flow of asphalt.

[0040] The electric valve is precisely controlled and adjusted according to the slight changes in the controller instructions to ensure a smooth adjustment process. The opening of the electric valve is controlled by PWM (pulse width modulation) signal or digital control signal to adjust the asphalt flow, aggregate addition and other related materials.

[0041] During the mixing and blending control, the system will automatically adjust the mixing speed and mixing time during the ratio adjustment process to ensure that all adjusted materials can be fully mixed and evenly mixed to prevent the product quality from being affected by insufficient material mixing due to ratio adjustment.

[0042] Real-time feedback and monitoring after adjustment: Including: closed-loop control, the adjusted asphalt ratio data is collected again by sensors and fed back to the controller. The controller compares it with the model prediction value to verify whether the adjustment effect meets expectations.

[0043] Dynamically adjusted optimization iterations: If the real-time feedback data still deviates from the expected matching results, the system will further fine-tune based on the new feedback data until the best matching effect is achieved.

[0044] Fault detection and safety assurance: Including: Fault self-checking function. During the dynamic adjustment process, the system has a fault self-checking function, which can monitor the operating status of the actuator (such as electric valves, agitators). If the equipment is abnormal or there is a jam during the adjustment process, the system will automatically stop the adjustment and issue an alarm.

[0045] Emergency shutdown and recovery mechanism: if safety hazards are detected in production or the adjustment process does not meet expectations, the system will automatically trigger the emergency shutdown function to prevent the problem from further deteriorating, and save the data before and after the adjustment for reference when resuming production.

[0046] Data logging and trend analysis: Including: data storage, the specific parameters and production environment data of each dynamic adjustment will be recorded and stored in the database for subsequent production analysis and optimization.

[0047] Trend prediction and optimization: through the analysis of historical adjustment data, the system can summarize the best adjustment strategies under different environments. In the future, it can make preliminary adjustments in similar environmental conditions to improve production efficiency.

[0048] Furthermore, the adaptive learning includes the following steps: Real-time data input and model updating: Including: real-time data input, the system continuously monitors and records real-time data during the production process, and the real-time data is directly input into the controller through the sensor network. The data will be input into the adaptive learning algorithm to adjust and optimize the existing ratio model.

[0049] Adaptive learning mechanism: Including: Machine learning model training, the system uses adaptive learning algorithms (such as online learning, recursive neural networks or reinforcement learning) to automatically adjust model parameters based on feedback data. The algorithm continuously adjusts its weights and parameters with each new data input, so that the model gradually adapts to the new production environment and needs.

[0050] Online learning: After each new data input, the algorithm will immediately update the model so that it gradually adapts to the current production conditions, without having to wait until a large amount of data is accumulated before batch training.

[0051] Reinforcement learning: Based on the feedback results of current production conditions, the system regards each optimization operation as a "decision" and gives the system positive or negative feedback based on the effectiveness of the decision (i.e. the difference between the actual ratio and the expected value), thereby adjusting future decision-making strategies.

[0052] Multi-objective optimization: During the adaptive learning process, the system not only optimizes a single objective (such as product quality), but also considers multiple production objectives, such as production cost, raw material utilization, production efficiency, etc. The system comprehensively optimizes these objectives according to the set weights.

[0053] Model parameter update: After each data collection, the adaptive learning algorithm in the controller updates the existing model parameters in real time. These parameters include: Material characteristic parameters: such as viscosity, fluidity, etc.

[0054] Production environment parameters: such as construction temperature, humidity, etc.

[0055] Production efficiency parameters: such as flow adjustment time, valve response speed, etc.

[0056] Data weight adjustment: Based on new data, the algorithm automatically adjusts the weight of each parameter. For example, if the ambient temperature changes significantly, the system may give the temperature parameter a higher weight to ensure that the optimization algorithm pays more attention to the impact of temperature on the ratio.

[0057] Dynamic adjustment of the model: Including: updating the ratio optimization algorithm. According to the new data and the results learned, the system will dynamically adjust the optimization algorithm. For example, if it is found through learning that the temperature fluctuation has a greater impact on the ratio result, the system will automatically increase the sensitivity to temperature changes and include it in the key variable.

[0058] Adjust the control parameters. The system dynamically adjusts the controller parameters, such as the gain of the PID controller and the setting range of the threshold controller, based on the results of adaptive learning to ensure the accuracy of the adjustment.

[0059] Furthermore, the abnormal conditions include: 1. Equipment failure exception: Temperature sensor failure: The temperature sensor fails to measure the asphalt or ambient temperature normally, resulting in the controller being unable to obtain accurate temperature data, which may cause production risks of excessively high or low temperatures.

[0060] Pressure sensor failure: Inaccurate or faulty pressure sensors cannot detect changes in actual pressure in the production line, which may cause equipment overload or unstable production.

[0061] Flow sensor failure: Failure of the flow sensor to accurately monitor the asphalt flow may result in uneven raw material supply or ratio deviation.

[0062] Electric actuator stuck or delayed response: The electric actuator fails to adjust the opening of the electric valve according to the control command, which may cause the asphalt flow rate to be unable to be adjusted in time and affect the accuracy of the mix ratio.

[0063] Valve failure: Failure of the electric valve to open and close as instructed or the inability to adjust the opening may result in excessive or insufficient flow of asphalt or aggregate, affecting product quality.

[0064] Agitator Failure: Failure of the mixing equipment to function properly results in uneven mixing of materials, which in turn affects the uniformity and quality of the final product.

[0065] Failure of conveyor belts or pumps in the production line: Equipment damage may result in the inability to transport or supply materials as required, causing the entire production process to stagnate.

[0066] 2. Parameter exception class exception: Temperature is too high or too low: During the production process, the temperature of the environment or materials suddenly exceeds the preset safety range, which may cause problems such as deterioration of material quality or overheating of production equipment.

[0067] Too much or too little pressure: If the pressure in the pipeline or reaction vessel in the production line exceeds the set range, it may cause equipment damage or safety hazards.

[0068] Unstable or abnormal flow: If the sensor detects that the flow of materials (such as asphalt, aggregate) exceeds the set value or is seriously unstable, it may affect the proportioning accuracy and product quality.

[0069] Liquid level is too low or too high: If the liquid level in the storage tank exceeds the safe range, it may affect the normal production process and even cause insufficient material supply or overflow.

[0070] 3. System operation abnormality: Data transmission failure: Due to failure of the network, communication module or control system, the data collected by the sensor cannot be transmitted to the controller in time, resulting in the control system being unable to adjust the ratio parameters in time, which may affect the continuity of production.

[0071] System crash or freeze: Due to hardware failure or software program error, the controller loses control of the system and cannot issue adjustment instructions. This type of failure may cause the equipment to lose control or fail to adjust the ratio on time.

[0072] The optimization algorithm fails to converge: When the ratio optimization algorithm within the system fails to converge due to data anomalies or overly complex calculations, the system may be unable to generate effective ratio adjustment instructions, affecting production continuity.

[0073] 4. Abnormal material properties: Deviations in raw material properties: For example, if the viscosity, density and other properties of the supplied asphalt deviate from the standard range, the system may not be able to achieve the expected ratio effect through conventional adjustment strategies, thus affecting the quality of the product.

[0074] Poor mixing uniformity: Uneven mixing of materials before entering the mixing stage may lead to unstable material supply in certain parts, affecting the overall performance of the final asphalt.

[0075] 5. Abnormal environmental conditions: Sudden changes in ambient temperature: The ambient temperature at the production site may change dramatically, especially in outdoor production or in scenarios with large temperature fluctuations. This may affect the operating efficiency of the equipment and the physical properties of the materials, thereby affecting the production results.

[0076] Humidity affects material properties: Excessive humidity may lead to increased water absorption of materials (such as aggregates), affecting the moisture content in the mix and, in turn, affecting the performance and quality of asphalt.

[0077] 6. Security and emergency: Emergency stop button trigger: When the on-site operator manually presses the emergency stop button, the system will immediately interrupt production and enter safety mode.

[0078] Equipment overload: If a device (such as a pump, agitator, electric valve, etc.) is overloaded, causing the motor to overheat or the equipment to vibrate abnormally, the system will detect this condition and trigger an emergency shutdown.

[0079] Solutions to abnormal situations: Automatic detection and alarm, the system monitors the above abnormal conditions in real time through the built-in fault detection module. Once a problem is detected, the system immediately triggers an alarm signal to notify the operator.

[0080] Emergency shutdown: when an abnormal situation may cause equipment damage or affect safety, the system will automatically trigger the emergency shutdown procedure, immediately stop all production activities, and protect the safety of equipment and operators.

[0081] The system will provide a production resumption guidance plan after the abnormality is resolved. The plan includes step-by-step instructions, such as restarting equipment step by step, checking the status of raw materials and equipment, adjusting production parameters, etc., to ensure that production can be resumed smoothly and avoid new problems caused by direct restart.

[0082] An intelligent asphalt mix ratio optimization and dynamic adjustment system, characterized by comprising: The data acquisition module integrates a temperature sensor, a pressure sensor, a flow sensor and a liquid level sensor, and is used to collect key parameters of the temperature, pressure, flow and liquid level of the asphalt in real time, and transmit the parameters to the controller; A controller, equipped with a high-performance central processing unit and a large-capacity memory, pre-installed with a control algorithm, for receiving and processing real-time data from the data acquisition module, and generating optimized ratio adjustment instructions based on the data; The actuator, including an electric actuator and an electric valve, can receive adjustment instructions from the controller and adjust the asphalt ratio parameters according to the instructions to ensure the accuracy of the ratio; Database, used to store asphalt parameter data, including historical data and real-time data, as well as control algorithms, to support efficient management and analysis of asphalt mix data; The user interface integrates a display and input devices to display real-time system data, query historical data, and provide an intuitive operating interface for adjusting ratio parameters.

[0083] The beneficial effects of the present invention are: The present invention realizes the automation and intelligent adjustment of asphalt mix ratio through real-time data collection, intelligent algorithm analysis and precise actuator control. This avoids the errors and delays caused by human factors in traditional methods, and significantly improves production efficiency and product quality stability. The system can quickly respond to production needs and environmental changes, ensuring that the asphalt mix ratio is always in the optimal state, thereby improving the overall quality and market competitiveness of the product.

[0084] The adaptive learning algorithm used in the present invention can continuously learn from production data and optimize its own parameters to adapt to different production conditions and requirements. This flexibility enables the system to easily cope with various changes and challenges in the production process, such as fluctuations in raw material quality and changes in market demand. At the same time, users can also easily adjust control parameters and view real-time data through the user interface, further enhancing the controllability and predictability of the production process.

[0085] The present invention takes a number of measures to ensure the stability and safety of the production process. For example, the regular automatic calibration and fault self-checking functions can detect and solve potential problems in a timely manner, reducing the risk of equipment failure; the emergency shutdown and recovery mechanism can quickly cut off the power supply of related equipment and save key data when an abnormal situation is detected to prevent the situation from further deteriorating. These measures together improve the safety and reliability of the system and ensure the continuity and stability of the production process. BRIEF DESCRIPTION OF THE DRAWINGS

[0086] Figure 1 : Schematic diagram of the process of the present invention; Figure 2 : A schematic diagram of the system structure of the present invention; DETAILED DESCRIPTION

[0087] The present invention will be further described below in conjunction with the accompanying drawings and specific embodiments: Example: Figure 1-2As shown, the present invention relates to an intelligent asphalt ratio optimization and dynamic adjustment system and method thereof, aiming to realize automatic optimization and dynamic adjustment of asphalt ratio through intelligent data collection, analysis and control. The specific implementation of the present invention will be described in detail below in combination with each module.

[0088] 1. System overall structure and working principle The intelligent asphalt ratio optimization and dynamic adjustment system of the present invention includes a data acquisition module, a controller, an actuator, a database and a user interface. The modules communicate and cooperate in a wired or wireless manner to achieve the optimization and adjustment of the asphalt ratio.

[0089] The data acquisition module integrates a variety of sensors, including temperature sensors, pressure sensors, flow sensors and liquid level sensors, which are used to collect key parameters of asphalt during the production process in real time.

[0090] Temperature sensors are used to monitor temperature changes of asphalt and the external environment; pressure sensors monitor pressure changes in pipelines or storage tanks; flow sensors measure the flow of asphalt and aggregate to ensure the accuracy of the ratio; liquid level sensors are used to monitor the asphalt liquid level in the raw material storage tank to ensure a stable supply of raw materials.

[0091] These data are transmitted to the controller for processing via signal transmission lines, and the data collection frequency can be dynamically adjusted according to production needs to ensure the accuracy and real-time performance of key parameters.

[0092] The controller is the core processing unit of the system. It is equipped with a high-performance central processing unit (CPU) and a large-capacity memory. It can efficiently process real-time data from the data acquisition module and analyze the data using built-in control algorithms.

[0093] The controller uses intelligent algorithms (such as genetic algorithms or particle swarm optimization algorithms) to establish an asphalt mix model and optimize the mix parameters based on the model. After real-time data is input, the controller generates optimized mix adjustment instructions based on current production conditions (including temperature, flow, pressure, etc.).

[0094] The controller has an adaptive learning function that can automatically update model parameters based on data feedback from the production process, continuously optimize the asphalt mix ratio, and improve the stability of the production process and product quality.

[0095] The actuator includes an electric actuator and an electric valve. After receiving the instruction from the controller, the electric actuator controls the opening of the electric valve to adjust the flow of asphalt and aggregate to achieve dynamic adjustment of asphalt ratio.

[0096] When the controller generates new ratio parameters, the actuator will respond immediately and adjust the relevant parameters according to the instructions. The actuator can accurately control the opening and closing degree of the valve to ensure the accuracy and fast response of flow adjustment.

[0097] The actuator also has a fault detection function, which can monitor the operating status of the equipment in real time. If an abnormal situation is detected (such as electric actuator stuck, valve failure, etc.), the system will automatically stop production and send out an alarm signal.

[0098] The database is used to store all historical and real-time data in the asphalt mix process, supporting large-capacity data management. The database not only stores the parameter data generated during the production process, but also includes the model parameters of the system's internal control algorithm.

[0099] The historical data in the database can be used for subsequent trend analysis and optimization strategy adjustment, providing data support for adaptive learning. The database also allows users to query historical production data to evaluate the system's production performance and adjustment effects.

[0100] The database supports regular backup to prevent data loss and has fast retrieval capabilities to meet the needs of efficient access to real-time data during the production process.

[0101] The user interface adopts a graphical design and integrates a display and input devices for operators to monitor the real-time status of the system and adjust control parameters. The user interface can display key data such as asphalt temperature, pressure, flow, liquid level in real time, and supports query and comparative analysis of historical data.

[0102] The user interface allows users to manually adjust system parameters (such as temperature, flow, etc.) and dynamically optimize the production process according to production needs. The interface also supports an alarm function. When a system abnormality or failure is detected, the interface will automatically pop up an alarm prompt to prompt the operator to handle it.

[0103] The intelligent asphalt mix ratio optimization and dynamic adjustment method provided by the present invention has the following specific implementation process: Data acquisition: The temperature sensor, pressure sensor, flow sensor and liquid level sensor integrated in the data acquisition module can collect key parameters in the asphalt production process in real time, including temperature, pressure, flow and liquid level.

[0104] These data are immediately transmitted to the controller after collection, and the controller will monitor all parameters in real time to ensure the accuracy and timeliness of the data.

[0105] Data processing and analysis: The controller is equipped with a high-performance central processing unit (CPU) and a pre-installed ratio optimization control algorithm. After receiving the parameters from the data acquisition module, the controller first pre-processes the data to remove noise and outliers to ensure data reliability.

[0106] After data preprocessing, the controller extracts key feature data and analyzes the current asphalt mix status, including the physical properties of the material (such as viscosity, density, etc.) and current production conditions (such as temperature, pressure, etc.), thereby ensuring the system's precise control of the production process.

[0107] Model building and optimization: The controller builds an asphalt mix model based on historical production data and current real-time data in the database. The model is used to predict the optimal mix parameters to ensure the efficiency of material use and product quality during the production process.

[0108] The system uses genetic algorithms or particle swarm optimization algorithms to optimize the ratio model so as to quickly adjust the ratio according to different environmental conditions and production needs to obtain the optimal ratio solution.

[0109] Dynamic adjustment: The system will generate dynamic adjustment instructions based on real-time monitoring of production needs, construction environment and changes in material properties.

[0110] The controller controls the opening of the electric valve through the electric actuator to automatically adjust the flow of asphalt and aggregate to ensure the accuracy of the mix ratio. Real-time adjustment enables the production process to quickly respond to changes in the environment and production conditions, ensuring the continuity and stability of production.

[0111] Execution and feedback: The above-mentioned actuators include electric actuators and electric valves. When receiving dynamic adjustment instructions generated by the controller, the actuators will immediately respond, adjust the opening of the valve, and change the flow of asphalt and other materials.

[0112] After the actuator completes its action, the system will collect the adjusted production parameters again through sensors and feed these data back to the controller. The controller performs closed-loop control based on the feedback data to ensure that the adjustment effect meets expectations.

[0113] Data storage and display: During the entire ratio adjustment process, the system stores real-time and historical data in the database. The database not only stores the real-time parameters of the current production, but also includes all historical records of past production cycles.

[0114] Users can view this data through the integrated user interface, and the system will intuitively display production parameters, ratio status and historical trends in a graphical form. At the same time, users can manually adjust parameters in the interface to intervene in or optimize the production process.

[0115] Adaptive learning: The control algorithm in the controller supports an adaptive learning mechanism. The system automatically updates the parameters of the optimization model by analyzing the real-time data and feedback generated during the production process, thereby improving the stability of the ratio and product quality.

[0116] The adaptive learning mechanism can continuously adjust the control strategy based on historical data and current production conditions, so that the system can maintain efficient operation under different production conditions.

[0117] Safety assurance: The system has an automatic fault detection function and can monitor the operating status of the equipment in real time. When a device failure or abnormal parameter (such as excessive temperature, abnormal pressure, etc.) is detected, the system will automatically trigger the emergency shutdown function to stop production and protect the safety of equipment and personnel.

[0118] When the abnormal situation is resolved, the system will provide guidance on resuming production, prompting operators to gradually resume equipment operation to ensure that the production process can be restarted safely and orderly.

[0119] Finally, it should be noted that the above is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, it is still possible for those skilled in the art to modify the technical solutions described in the aforementioned embodiments or to make equivalent substitutions for some of the technical features therein. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. An intelligent asphalt mix ratio optimization and dynamic adjustment method, characterized in that: The method comprises the following steps: Data acquisition: Through the data acquisition module integrating temperature sensor, pressure sensor, flow sensor and liquid level sensor, the key parameters of asphalt temperature, pressure, flow and liquid level are collected in real time, and the parameter data are transmitted to the controller; Data processing and analysis: The controller is equipped with a high-performance central processing unit and a pre-installed ratio optimization control algorithm. It performs data preprocessing and feature extraction based on the asphalt parameter data collected by the data acquisition module, and analyzes the current asphalt ratio status and quality characteristics; Model building and optimization: Establish an asphalt mix model based on historical data and real-time data, and use genetic algorithms or particle swarm optimization algorithms to optimize the mix to obtain the optimal asphalt mix parameters; Dynamic adjustment: Real-time monitoring of changes in production demand, construction environment and material properties, generating dynamic adjustment instructions based on the asphalt mix ratio model and control algorithm, and controlling the opening of the electric valve through the electric actuator to automatically adjust the asphalt mix ratio; Execution and feedback: The actuator includes an electric actuator and an electric valve, which responds quickly after receiving the control command and feeds back the adjusted ratio data to the controller for closed-loop control; Data storage and display: All data in the adjustment process are stored in the database, which is used to manage historical data and real-time data, and the production parameters and ratio status are displayed in a graphical form through the user interface; Adaptive learning: The control algorithm supports an adaptive learning mechanism, which automatically updates and optimizes model parameters based on real-time data and feedback generated during the production process to improve the stability of the ratio and product quality; Safety assurance: The system has automatic fault detection and emergency shutdown functions. When an abnormal situation is detected, it automatically stops production and provides guidance on resuming production after the abnormality is resolved.

2. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The data processing and analysis includes the following steps: Data cleaning: The controller cleans the received parameter data to remove abnormal values ​​and noise; Filtering: Smoothing the data through filtering algorithms to reduce short-term fluctuations caused by environmental interference, thereby improving data accuracy; the algorithms include Kalman filtering and sliding average filtering; Data standardization: To ensure that all parameters can be analyzed at the same scale, the controller standardizes the data of each sensor using zero mean standardization or minimum-maximum normalization method; Time series analysis: Based on historical data and real-time data, the time series analysis method is used to extract trend information in asphalt mix ratio, including temperature change trend and pressure fluctuation law; Parameter interaction analysis: Interactive analysis is performed on the relationship between different parameters to explore potential correlations and extract feature combinations that have a greater impact on asphalt quality. This step uses the Pearson correlation coefficient method or regression analysis method.

3. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The model establishment includes the following steps: Historical data collation: The production data collected over a long period of time during the asphalt mixing process is stored in the database; the data includes key parameters in the production process, including temperature, pressure, flow, liquid level, and the corresponding finished product quality characteristics, including viscosity, anti-aging, and stability; Feature selection and extraction: Analyze historical data and use data mining technology to extract the parameters that have the greatest impact on asphalt mix ratio; use correlation analysis to select the most representative parameters; Establish asphalt mix ratio model: Use key parameters in historical data to build a mathematical model of asphalt mix ratio based on physical or empirical formulas; this model outputs an expected asphalt mix ratio and quality characteristic value based on the input parameter data; Prediction model based on machine learning: historical data is input into the machine learning algorithm, and the model is trained through supervised learning to enable it to predict the relationship between parameter data and finished product quality. The model forms a prediction model by learning the impact of different parameter combinations on the quality of the final product; Model verification and tuning: Use new historical data to verify the built model, adjust model parameters by comparing the output value predicted by the model with the actual quality of the finished product, and improve the accuracy and robustness of the model; The model optimization comprises the following steps: Objective function setting: In the optimization process, first set an objective function, which is set according to production requirements, including maximizing product quality stability, minimizing production costs, and improving material utilization; the objective function can be multi-objective, with different weights set according to different requirements; then use genetic algorithms or particle swarm optimization algorithms for optimization; Optimal mix ratio selection: After multiple iterations of the genetic algorithm or particle swarm optimization algorithm, the system will select the mix ratio scheme with the highest fitness; this scheme is the optimal asphalt mix ratio parameter under the current conditions; Parameter application: The optimal mix ratio parameters are output to the actuator, which automatically adjusts the asphalt mix ratio to meet production needs; at the same time, the parameters will be stored in the database for future reference or further optimization; Continuous optimization and updating: The system will continuously collect real-time production data, input it into the model, and update the model and ratio parameters through adaptive learning algorithms to ensure that the ratio is always in the optimal state during the production process; Result verification: After the optimized ratio parameters are applied to production, the system monitors the production effect in real time and verifies the optimization effect by comparing the difference between the predicted finished product quality and the actual finished product quality; Feedback adjustment: If the optimization result is not ideal, the system will record the specific situation of the optimization and input the feedback information into the model to further improve the model and optimization algorithm to ensure that the next optimization is more accurate.

4. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The dynamic adjustment comprises the following steps: Real-time monitoring of production demand: Through the sensors and production management modules in the system, the current production demand data, including production progress, target output, and production cycle, can be obtained in real time; Construction environment parameter monitoring: Real-time monitoring of external environmental factors that affect asphalt performance, including temperature, humidity, and air pressure at the construction site; these parameters are collected through environmental sensors and transmitted to the controller; Material property monitoring: Continuously monitor the properties of asphalt materials to ensure that their viscosity and fluidity meet the expected requirements; for different batches of raw materials or changes in raw materials during the production process, the system will automatically detect and record changes in material properties; Model input and calculation: The controller inputs the real-time collected environmental parameters, material properties and production demand data into the pre-established asphalt mix model, and the model generates a new mix recommendation based on the current production conditions; Adjustment demand analysis: The model will compare with the current production status and calculate the deviation between the asphalt mix ratio in the current production process and the optimal mix ratio; if there is a significant difference between the mix ratio parameters and the optimal value recommended by the model, the system will generate a mix ratio adjustment demand; Dynamic adjustment of control algorithm: The controller dynamically analyzes the current mix ratio by running the control algorithm and generates corresponding adjustment instructions to indicate the specific parameters that need to be changed, including asphalt flow, temperature, and mixing ratio; Parameter optimization and instruction generation: The system automatically generates mix ratio adjustment instructions based on the model analysis results; the adjustment instructions contain specific mix ratio parameters, including the asphalt flow, aggregate ratio, and temperature setting that need to be adjusted; when generating adjustment instructions, the system not only considers production efficiency and quality, but also production costs and energy consumption, and generates the most economical adjustment plan through comprehensive optimization.

5. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The execution and feedback include the following steps: Actuator response: The adjustment command is sent to the actuator through the controller. The actuator includes an electric actuator and an electric valve. The electric actuator quickly adjusts the opening of the electric valve according to the command, thereby changing the asphalt ratio and flow rate. Precise control of electric valves: Electric valves are precisely adjusted according to slight changes in controller instructions to ensure a smooth adjustment process; the opening of electric valves is controlled by pulse width modulation signals or digital control signals to adjust the asphalt flow, aggregate addition, and other related material additions; Stirring and mixing control: During the ratio adjustment process, the system will automatically adjust the stirring speed and mixing time to ensure that all adjusted materials can be fully mixed and evenly mixed to prevent the product quality from being affected by insufficient material mixing due to ratio adjustment; Closed-loop control: The adjusted asphalt ratio data is collected again by sensors and fed back to the controller; the controller compares it with the model prediction value to verify whether the adjustment effect meets expectations; Dynamically adjusted optimization iteration: If the real-time feedback data still deviates from the expected ratio result, the system will further fine-tune according to the new feedback data until the optimal ratio effect is achieved; Fault self-checking function: During the dynamic adjustment process, the system has a fault self-checking function that can monitor the operating status of the actuator; if the equipment is found to be abnormal or a jam occurs during the adjustment process, the system will automatically stop the adjustment and issue an alarm; Emergency shutdown and recovery mechanism: If a safety hazard is detected in production or the adjustment process does not meet expectations, the system will automatically trigger the emergency shutdown function to prevent the problem from further deteriorating, and save the data before and after the adjustment for reference when resuming production.

6. Data storage: The specific parameters and production environment data of each dynamic adjustment will be recorded and stored in the database for subsequent production analysis and optimization; Trend prediction and optimization: By analyzing historical adjustment data, the system can summarize the best adjustment strategies under different environments. In the future, it can make pre-adjustments in advance under similar environmental conditions to improve production efficiency.

7. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The adaptive learning and optimization comprises the following steps: Real-time data input: The system continuously monitors and records real-time data during the production process, and the real-time data is directly input into the controller through the sensor network; this data will be input into the adaptive learning algorithm to adjust and optimize the existing ratio model; Machine learning model training: The system uses an adaptive learning algorithm to automatically adjust model parameters based on feedback data. The algorithm continuously adjusts its weights and parameters with each new data input, so that the model gradually adapts to the new production environment and needs. Model parameter update: The adaptive learning algorithm in the controller updates the existing model parameters in real time. The parameters include: Material characteristic parameters: including viscosity and fluidity; Production environment parameters: including construction temperature and humidity; Production efficiency parameters: including flow adjustment time and valve response speed; Data weight adjustment: Based on new data, the algorithm automatically adjusts the weight of each parameter; Update the ratio optimization algorithm: The adaptive learning algorithm in the controller dynamically adjusts the optimization algorithm according to new data and learned results; Adjust control parameters: The system dynamically adjusts the controller parameters, including the gain of the PID controller and the setting range of the threshold controller, based on the results of adaptive learning to ensure the accuracy of the adjustment.

8. The intelligent asphalt mix ratio optimization and dynamic adjustment method according to claim 1, characterized in that: The abnormal situations include: Equipment failure anomalies: temperature sensor failure, pressure sensor failure, flow sensor failure, electric actuator stuck or delayed response, valve failure, agitator failure, conveyor belt or pump failure in the production line; Parameter abnormality: temperature is too high or too low, pressure is too high or too low, flow rate is abnormal, liquid level is too low or too high; System operation abnormalities: data transmission failure, system crash or freeze, optimization algorithm failure to converge; Abnormal material properties: deviation in raw material properties and poor mixing uniformity; Abnormal environmental conditions: sudden temperature changes and excessive humidity in the external environment; Safety and emergency conditions: safety device triggered, equipment overloaded or overheated.

9. An intelligent asphalt mix ratio optimization and dynamic adjustment system according to any one of claims 1 to 7, characterized in that: include: The data acquisition module integrates a temperature sensor, a pressure sensor, a flow sensor and a liquid level sensor, and is used to collect key parameters of the temperature, pressure, flow and liquid level of the asphalt in real time, and transmit the parameters to the controller; A controller, equipped with a high-performance central processing unit and a large-capacity memory, pre-installed with a control algorithm, for receiving and processing real-time data from the data acquisition module, and generating optimized ratio adjustment instructions based on the data; The actuator, including an electric actuator and an electric valve, can receive adjustment instructions from the controller and adjust the asphalt ratio parameters according to the instructions to ensure the accuracy of the ratio; Database, used to store asphalt parameter data, including historical data and real-time data, as well as control algorithms, to support efficient management and analysis of asphalt mix data; The user interface integrates a display and input devices to display real-time system data, query historical data, and provide an intuitive operating interface for adjusting ratio parameters.

Images