Microwave penetration type on-line monitoring and feeding compensation method and system for water content of gravel in concrete mixing plant

Abstract

The invention discloses a microwave penetration type online monitoring and feeding compensation method and system for the water content of gravel in a concrete mixing plant, and relates to the technical field of concrete production process control. According to the method, real-time monitoring of the water content of the gravel is achieved, the problems of hysteresis and insufficient precision of traditional off-line detection are solved, data processing and prediction modeling are carried out in combination with the sliding window algorithm and the Kalman filtering algorithm, the timeliness and accuracy of water content monitoring are remarkably improved, and real-time monitoring of the water content is achieved through a time synchronization mechanism and accurate time compensation parameters. By combining feedforward control and a PID control algorithm, accurate feeding of gravel and water is realized, the problem of proportion deviation caused by moisture content fluctuation in a traditional feeding mode is solved, the refinement level of production is improved, abnormity can be quickly identified and processed, the control performance can be continuously optimized, stable operation of the system and production continuity are ensured, and the production efficiency is improved. And the intelligent level of concrete production and the product quality consistency are obviously improved.

Description

Technical Field

[0001] This invention relates to the field of underwater vision technology, specifically to a microwave-guided online monitoring method and system for the moisture content of sand and gravel in concrete mixing plants, as well as a method and system for material feeding compensation. Background Technology

[0002] Concrete, as a core material in modern construction engineering, directly affects the structural safety and durability of buildings. Precise control of the moisture content of sand and gravel is crucial for ensuring the accuracy of concrete mix proportions. In the production process of concrete mixing plants, real-time monitoring and dynamic control of sand and gravel moisture content have become decisive factors affecting product quality consistency. Traditional methods for detecting sand and gravel moisture content mainly rely on manual sampling and drying and weighing. This offline testing method is not only time-consuming but also cannot reflect real-time changes in moisture content during production. Although some mixing plants use resistive or capacitive sensors for online monitoring, these methods are easily affected by the size, density, and impurity content of sand and gravel particles, making it difficult to meet the requirements of refined production. Summary of the Invention

[0003] The purpose of this invention is to provide a microwave-guided online monitoring method and system for the moisture content of sand and gravel in concrete mixing plants, as well as a feeding compensation method and system. This improves the level of intelligence in concrete production and the consistency of product quality, and solves the problems of monitoring lag, inaccurate feeding, and insufficient system stability in traditional methods.

[0004] The objective of this invention can be achieved through the following technical solutions: This application provides a microwave penetration-based online monitoring method for the moisture content of sand and gravel in concrete mixing plants and a method for material feeding compensation, including the following steps: The moisture content signal is collected at different locations in the sand and gravel silo by a multi-point array of capacitive sensors. Real-time moisture content data is obtained by high-frequency scanning mode and a continuous moisture content data stream is generated according to the preset sampling frequency. A sliding window algorithm is used to filter out noise and smooth the water content data stream. By setting the time window length and weighting coefficient, a moving average is calculated to obtain a stable water content benchmark value. Based on historical moisture content change patterns and current monitoring data, a moisture content prediction model is established using the Kalman filter algorithm. The predicted moisture content for future moments is calculated using the state transition matrix and the observation matrix, thereby obtaining the moisture content change trend and prediction error range. By using a time synchronization mechanism, the trend of moisture content change is linked to the sand and gravel batch management system. The time delay of sand and gravel arriving at the mixing point is calculated based on the conveyor belt speed and the location of the silo, thus obtaining accurate time compensation parameters. The predicted moisture content is corrected by using time compensation parameters. The feedforward control algorithm is used to calculate the feed compensation amount of sand and water. The specific compensation coefficient is determined according to the mix ratio requirements and moisture content deviation to obtain real-time feed adjustment instructions. The feeding adjustment command is refined by using a PID control algorithm. The control output value is calculated based on the proportional gain, integral time and derivative time parameters. A closed-loop feedback mechanism is used to monitor the deviation between the actual feeding amount and the target value to obtain a stable feeding control signal. The feeding control signal drives the sand and gravel feeder and water metering system to perform compensation and adjustment. The servo motor and solenoid valve control the precise feeding of materials. The weight sensor and flow meter monitor the actual feeding effect. When the deviation between the actual ratio and the target ratio exceeds the allowable range, the secondary compensation program is activated.

[0005] Furthermore, a multi-point array of capacitive sensors is used to collect moisture content signals at different locations within the sand and gravel silo, specifically including: The moisture content signal is collected at different locations in the sand and gravel bin by multiple capacitive sensors. A real-time data stream is generated by high-frequency scanning mode. Based on the real-time data stream, the moisture content signal is processed continuously by a preset sampling frequency to obtain a continuous sequence of moisture content information. Calculate the fluctuation amplitude between adjacent time points, determine the abnormal time period, obtain the moisture content information sequence within the abnormal time period, call the data processing module to perform priority analysis on the abnormally marked data, and extract the fluctuation characteristics. By analyzing the fluctuation characteristics, the support vector machine algorithm is used to classify the abnormal data and determine whether the abnormality belongs to negligible noise or a real abnormality. According to the classification results, if it is determined to be a real abnormality, the abnormal data and the corresponding time period information are transmitted to the subsequent processing unit to obtain the detailed abnormality distribution. By combining the location information of sensors arranged at multiple points within the sand and gravel silo, an anomaly location map is generated to determine the specific area where the anomaly occurred.

[0006] Furthermore, a sliding window algorithm is used to perform noise filtering and data smoothing on the moisture content data stream, specifically including: By collecting moisture content data streams in real time, the data flow direction is segmented using a sliding window method, and the distribution of data points within each time window is calculated. For each data point within a time window, the calculation method is adjusted by applying a weighting coefficient, and the data is smoothed using a moving average method to obtain a smoothed moisture content data sequence. Combined with the preset time window length, the moving average is continuously updated to determine a stable moisture content benchmark value. The current moisture content detection value is compared with the benchmark value. When the deviation between the detection value and the benchmark value exceeds the preset tolerance range, a corresponding abnormal signal mark is generated. The generated abnormal signal mark is classified and processed, and combined with the characteristics of data flow and detection value difference, the abnormal signal is transmitted to the prediction module for analysis. Based on the abnormal signals transmitted to the prediction module, combined with the noise filtering results and data smoothing characteristics in historical data, an abnormal trend analysis model is constructed to determine the persistence and potential impact of the abnormal signals. Based on the output of the abnormal trend analysis model, corresponding early warning information is generated for the persistence characteristics of the abnormal signals.

[0007] Furthermore, a water content prediction model is established using the Kalman filter algorithm, specifically including: By combining historical data and current monitoring information, an analytical basis for the initial moisture content change is constructed. The Kalman filter algorithm is used to process the data, and the state transition matrix and observation matrix are used to extrapolate the moisture content change trend to obtain the predicted value data for future moments. For the acquired predicted data, the prediction error and error range are calculated, and it is determined whether the error exceeds the preset threshold. By marking the state to be adjusted, the parameter adjustment mechanism is triggered to update the key parameters in the prediction model and recalculate the moisture content change trend and predicted value. Based on the updated predicted values, the prediction error and error range are reassessed to determine whether the preset threshold conditions are met. The predicted values ​​and trends that finally meet the conditions are obtained, and a complete dataset of moisture content prediction is generated. By continuously monitoring the moisture content change trend, historical data and current detection information are updated regularly.

[0008] Furthermore, a time synchronization mechanism is used to link the moisture content change trend with the sand and gravel batch management system, specifically including: The data on moisture content change trends are obtained through a time synchronization mechanism, and the correlation information between the data and the sand and gravel batch management system is obtained. The moisture content change trend corresponding to each batch is determined. Based on the moisture content change trend, conveyor belt speed, and silo location information, the time delay from the sand and gravel to the mixing point is calculated, and the time delay value is obtained. The time delay value is compared with a preset range threshold to determine whether the time delay value exceeds the preset range threshold, and the comparison result is obtained to obtain the adjusted sensor position data. By adjusting the sensor position data and conveyor belt speed parameters, the time delay is recalculated to obtain the calibrated time delay value. The calibrated time delay value is then used to update the time compensation parameters, which are then used to adjust the scheduling logic of the sand and gravel batch management system and determine the optimized batch scheduling scheme.

[0009] Furthermore, time compensation parameters are used to correct the predicted moisture content over time, and the feed compensation amounts for sand, gravel, and water are calculated using a feedforward control algorithm, specifically including: The predicted moisture content is corrected by time compensation parameters. A preset correction model is used to obtain the corrected predicted moisture content. Based on the corrected predicted moisture content and the proportioning requirements, a feedforward control algorithm is used to calculate the initial compensation amount of sand and gravel feed and water feed, and to determine the initial compensation coefficient. For the initial compensation coefficient and moisture content deviation, a linear regression model is used to generate real-time feeding adjustment instructions to obtain the adjusted feeding amount. When the adjusted feeding amount exceeds the equipment adjustment range, the compensation amount is decomposed into multiple sub-compensation actions through a graded compensation algorithm to obtain a graded compensation sequence. According to the graded compensation sequence, the corresponding feeding adjustment actions are executed, the actual feeding data after each adjustment is obtained, the adjustment process is recorded, and the deviation trend of feeding adjustment is analyzed. A time series analysis model is used to obtain the dynamic change trend of feeding deviation. Based on the dynamic trend of the feeding deviation, the time compensation parameters and the input parameters of the feedforward control algorithm are updated to generate an optimized correction model and obtain a new moisture content prediction value.

[0010] Furthermore, the feeding adjustment command is refined using a PID control algorithm, and the control output value is calculated based on the proportional gain, integral time, and derivative time parameters. Specifically, this includes: The actual feeding amount data is collected in real time by sensors, the deviation between the actual feeding amount and the target value is calculated, the initial deviation value is obtained, and the control output value is calculated by using the PID control algorithm combined with the preset proportional gain, integral time and derivative time parameters to generate feeding adjustment command. The actuator sends the feeding adjustment command to the feeding equipment to adjust the feeding rate and obtain the actual feeding amount after adjustment. A closed-loop feedback mechanism is adopted to monitor the deviation between the actual feeding amount after adjustment and the target value in real time and obtain the current deviation value. When the current deviation value exceeds the preset threshold, the proportional gain, integral time and derivative time parameters are automatically adjusted by the gradient descent algorithm to obtain the optimized PID parameters, and then the control output value is recalculated to generate a new feeding adjustment command. The updated feeding rate is obtained, the deviation between the updated feeding rate and the target value is continuously monitored, a stable feeding control signal is generated, and the final feeding control response is obtained.

[0011] Furthermore, based on the feeding control signal, the sand and gravel feeder and water metering system are driven to perform compensation adjustments, and precise material feeding is achieved through servo motors and solenoid valves, specifically including: The operation command data of the sand and gravel feeder and water metering system are obtained through the feeding control signal generation device. The command data is compared with the preset operation parameters to obtain the control signal after initial adjustment. Based on the control signal after initial adjustment, the servo motor and solenoid valve control module are driven to perform material feeding operations and record the material quantity change data in real time during the feeding process. The system uses weight sensors and flow meters to monitor changes in material quantity in real time, obtains the deviation between the actual amount and the target ratio, and determines whether the deviation is within the preset threshold range. If the deviation exceeds the preset threshold range, a deviation correction signal is generated through the ratio feedback module. The operating parameters of the sand and gravel feeder and water metering system are adjusted according to the correction signal to obtain the corrected feeding control data. Then, the secondary compensation process is triggered, and the material feeding adjustment is performed again using the servo motor and solenoid valve control module. The material quantity distribution data after the secondary feeding is collected to determine the execution effect of the secondary compensation. Data is processed by a pre-established regression analysis model to obtain stability indicators for ratio adjustment. It is then determined whether the stability indicators meet the preset standards. The signal data drives the sand and gravel feeder and water metering system to make fine adjustments, and the final ratio control result is obtained.

[0012] Furthermore, after secondary compensation, the process also includes: updating the moisture content prediction model and control parameters using ratio control feedback data, optimizing prediction accuracy and control effect through machine learning algorithms, and establishing an adaptive adjustment mechanism based on historical production data to obtain continuously improved control performance.

[0013] This application provides a microwave-guided online monitoring and feeding compensation system for the moisture content of sand and gravel in concrete mixing plants, including: The moisture content signal acquisition module uses a multi-point array of capacitive sensors to perform high-frequency scanning of different locations in the sand and gravel silo, acquires moisture content signals in real time and generates a continuous data stream, and combines a support vector machine algorithm to classify abnormal data and generate anomaly location mappings. The data smoothing and anomaly detection module uses a sliding window algorithm to filter out noise and smooth the moisture content data stream. It obtains a stable moisture content benchmark value by calculating the moving average value, generates moisture content anomaly signals, and transmits them to the prediction module. The moisture content prediction module, based on historical moisture content change patterns and current monitoring data, uses the Kalman filter algorithm to establish a prediction model, calculates the predicted moisture content value and error range for future times, and automatically adjusts the model parameters and recalculates when the prediction error exceeds the set threshold. The time synchronization and compensation module uses a time synchronization mechanism to associate the moisture content change trend with the sand and gravel batch management system, calculates the time delay of sand and gravel arriving at the mixing point, and obtains accurate time compensation parameters. The feeding compensation calculation module uses time compensation parameters to correct the predicted moisture content value, calculates the feeding compensation amount of sand and water through a feedforward control algorithm, determines the compensation coefficient based on the moisture content deviation, executes compensation actions in stages, and records the adjustment process. The feeding control module uses a PID control algorithm to refine the feeding adjustment command, calculates the control output value based on proportional, integral and derivative parameters, and uses a closed-loop feedback mechanism to monitor the deviation between the actual feeding amount and the target value, automatically adjusts the PID parameters and optimizes the control response. The actual feeding and feedback module drives the sand and gravel feeder and water metering system to perform compensation and adjustment based on the feeding control signal. It controls the precise feeding of materials through servo motors and solenoid valves, and uses weight sensors and flow meters to monitor the actual feeding effect. When the actual ratio deviates too much from the target ratio, a secondary compensation program is initiated, and the prediction model and control parameters are updated using feedback data to optimize system performance.

[0014] The beneficial effects of this invention are as follows: By using a multi-point array of capacitive sensors and a high-frequency scanning mode, this invention can collect moisture content signals from different locations in the sand and gravel bins in real time, generating a continuous moisture content data stream. This real-time monitoring method effectively solves the problems of long detection time and inability to reflect real-time changes in traditional offline detection, ensuring the timeliness and accuracy of moisture content data. By combining the sliding window algorithm and Kalman filter algorithm to filter out noise, smooth the data, and perform predictive modeling, it can accurately obtain the trend and predicted value of moisture content changes, providing reliable data support for subsequent dynamic control, thereby significantly improving the accuracy of concrete mix proportions and the consistency of product quality. By adopting a time synchronization mechanism to link the moisture content change trend with the sand and gravel batch management system, and by accurately calculating the time delay and time compensation parameters, the problem of moisture content deviation caused by time delay during sand and gravel transportation is solved. By using feedforward control algorithm and PID control algorithm to finely calculate and adjust the feeding compensation amount, the precise feeding of sand, gravel and water is achieved. This precise feeding compensation method can not only effectively solve the problem of proportion deviation caused by moisture content fluctuation in traditional feeding methods, but also monitor and adjust the feeding amount in real time through a closed-loop feedback mechanism during the actual feeding process, ensuring the stability and accuracy of feeding, and further improving the level of precision in concrete production. To address potential anomalies during monitoring, this invention employs a support vector machine algorithm for classification and processing. Combined with anomaly location mapping and a secondary compensation procedure, it can quickly identify and handle genuine anomalies, ensuring stable system operation. Furthermore, by analyzing the proportion control feedback data using machine learning algorithms, the moisture content prediction model and control parameters are dynamically updated, establishing an adaptive adjustment mechanism. This anomaly handling and system optimization approach not only effectively solves the problem of insufficient monitoring accuracy caused by interference factors in traditional monitoring methods but also continuously improves control performance based on historical production data, enhancing system reliability and intelligence. Simultaneously, when equipment failure or sensor malfunction is detected, it can automatically switch to a backup channel and send a maintenance reminder signal, further ensuring the continuity and stability of production. Attached Figure Description

[0015] To better understand and implement this application, the technical solution is described in detail below with reference to the accompanying drawings.

[0016] Figure 1 This is a schematic flowchart of the microwave penetration-type online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant provided in Embodiment 1 of this application; Figure 2 The flowchart of the microwave penetration online monitoring and feeding compensation method for the moisture content of sand and gravel in concrete mixing plants provided in Embodiment 1 of this application is a schematic diagram of the process of establishing a moisture content prediction model using the Kalman filter algorithm. Figure 3 The flowchart of the microwave penetration online monitoring and feeding compensation method for the moisture content of sand and gravel in concrete mixing plants provided in Embodiment 1 of this application calculates the feeding compensation amount of sand, gravel and water through a feedforward control algorithm. Figure 4 This is a schematic diagram of the structure of the microwave penetration-type online monitoring and feeding compensation system for the moisture content of sand and gravel in a concrete mixing plant provided in Embodiment 2 of this application. Detailed Implementation

[0017] To further illustrate the technical means and effects adopted by the present invention to achieve its intended purpose, exemplary embodiments will be described in detail below, examples of which are illustrated in the accompanying drawings. In the following description relating to the drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with this application. Rather, they are merely examples of methods and systems consistent with some aspects of this application as detailed in the appended claims.

[0018] The terminology used in this application is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. The singular forms “a,” “the,” and “the” used in this application and the appended claims are also intended to include the plural forms unless the context clearly indicates otherwise. It should also be understood that the term “and / or” as used herein refers to and includes any and all possible combinations of one or more of the associated listed items.

[0019] The following detailed description of the specific implementation methods, features, and effects of the present invention, in conjunction with the accompanying drawings and preferred embodiments, is provided in detail.

[0020] Example 1

[0021] Please see Figures 1-3 This embodiment provides a microwave penetration-based online monitoring method for the moisture content of sand and gravel in concrete mixing plants and a method for material feeding compensation, including the following steps: S1. The moisture content signal of different locations in the sand and gravel silo is collected by a multi-point array of capacitive sensors. The real-time moisture content data is obtained by high-frequency scanning mode. A continuous moisture content data stream is generated according to the preset sampling frequency. When the moisture content fluctuation exceeds the preset threshold, the data processing module is triggered to mark the anomaly and process it with priority. Furthermore, a multi-point array of capacitive sensors is used to collect moisture content signals at different locations within the sand and gravel silo, specifically including: The moisture content signal is collected at different locations in the sand and gravel bin by multiple capacitive sensors. A real-time data stream is generated by high-frequency scanning mode to complete the initial information acquisition. Based on the real-time data stream, the moisture content signal is processed continuously by a preset sampling frequency to obtain a continuous moisture content information sequence. Calculate the fluctuation amplitude between adjacent time points. When the fluctuation amplitude exceeds the preset fluctuation threshold, the anomaly marking mechanism is triggered to determine the abnormal time period, obtain the water content information sequence within the abnormal time period, and call the data processing module to perform priority analysis on the anomaly-marked data to extract fluctuation characteristics. By analyzing the fluctuation characteristics, the support vector machine algorithm is used to classify the abnormal data and determine whether the abnormality belongs to negligible noise or a real abnormality. According to the classification results, if it is determined to be a real abnormality, the abnormal data and the corresponding time period information are transmitted to the subsequent processing unit to obtain the detailed abnormality distribution. By combining the location information of sensors arranged at multiple points within the sand and gravel silo, an anomaly location map is generated to determine the specific area where the anomaly occurred.

[0022] Specifically, by employing a multi-point array of capacitive sensors and a high-frequency scanning mode, this invention achieves real-time and continuous monitoring of the moisture content at different locations in sand and gravel silos. This solves the problem that traditional methods cannot reflect changes in moisture content in real time. Furthermore, by utilizing fluctuation amplitude analysis and anomaly labeling mechanisms, combined with a support vector machine algorithm, abnormal data is classified and processed, enabling rapid differentiation between noise and genuine anomalies and generating anomaly location maps. This technology not only improves the accuracy and reliability of moisture content monitoring but also precisely locates abnormal areas, providing accurate data support for subsequent dynamic control and material feeding compensation, effectively ensuring the accuracy of concrete mix design and the consistency of product quality.

[0023] S2. The sliding window algorithm is used to filter out noise and smooth the data stream of moisture content. By setting the time window length and weight coefficient, the moving average is calculated to obtain a stable moisture content benchmark value. When the deviation between the current detection value and the benchmark value exceeds the tolerance range, an abnormal moisture content signal is generated and transmitted to the prediction module. Furthermore, a sliding window algorithm is used to perform noise filtering and data smoothing on the moisture content data stream, specifically including: By collecting moisture content data stream in real time, the data flow direction is segmented using the sliding window method, and the distribution of data points within each time window is calculated to obtain preliminary noise distribution characteristics. For each data point within a time window, the calculation method is adjusted by applying a weighting coefficient, and the data is smoothed using a moving average method to obtain a smoothed moisture content data sequence. Combined with the preset time window length, the moving average is continuously updated to determine a stable moisture content benchmark value. The current moisture content detection value is compared with the benchmark value. When the deviation between the detection value and the benchmark value exceeds the preset tolerance range, a corresponding abnormal signal mark is generated. The generated abnormal signal mark is classified and processed, and combined with the characteristics of data flow and detection value difference, the abnormal signal is transmitted to the prediction module for subsequent analysis. Based on the abnormal signals transmitted to the prediction module, and combined with the noise filtering results and data smoothing characteristics in historical data, an abnormal trend analysis model is constructed to determine the persistence and potential impact of the abnormal signals. Based on the output of the abnormal trend analysis model, corresponding early warning information is generated for the persistence characteristics of the abnormal signals and transmitted to the relevant processing units for subsequent response.

[0024] Specifically, by using a sliding window algorithm to filter noise and smooth the moisture content data stream, this invention effectively removes random fluctuations and noise interference from the data, generating a stable moisture content benchmark value. Simultaneously, by comparing the current detected value with the benchmark value, abnormal deviations are promptly detected and abnormal signals are generated. Combined with an abnormal trend analysis model, early warnings are issued, enabling early detection and accurate warnings of moisture content anomalies. This provides a reliable basis for the dynamic control of concrete production, significantly improving production stability and reliability.

[0025] S3. Based on historical moisture content change patterns and current detection data, a moisture content prediction model is established using the Kalman filter algorithm. The predicted moisture content for future moments is calculated using the state transition matrix and observation matrix to obtain the moisture content change trend and prediction error range. When the prediction error exceeds the set threshold, the model parameters are adjusted and the prediction results are recalculated.

[0026] Furthermore, a water content prediction model is established using the Kalman filter algorithm, specifically including: S31. Based on historical data and current detection information, construct the analytical basis for the initial moisture content change, process the data using the Kalman filter algorithm to obtain a preliminary prediction model framework, and use the state transition matrix and observation matrix to extrapolate the moisture content change trend and obtain the predicted value data for future times. S32. For the acquired predicted value data, calculate the prediction error and error range, determine whether the error exceeds the preset threshold, and if it does, record the current error value and mark it as a state to be adjusted. By marking the state to be adjusted, trigger the parameter adjustment mechanism to update the key parameters in the prediction model and recalculate the moisture content change trend and predicted value. S33. Based on the updated predicted value, re-evaluate the prediction error and error range, and determine whether the preset threshold condition is met. If it is still not met, iteratively execute the parameter adjustment and recalculation process to obtain the final predicted value and change trend that meet the condition, and generate a complete dataset of moisture content prediction for subsequent business analysis and decision support. By continuously monitoring the moisture content change trend, regularly updating historical data and current detection information, the optimization process of the prediction model is executed cyclically.

[0027] Specifically, by employing a Kalman filter algorithm to establish a moisture content prediction model, this invention can accurately predict the future moisture content change trend and predicted value based on historical data and current monitoring information, and calculate the prediction error range. When the prediction error exceeds a set threshold, the model automatically adjusts its parameters and recalculates to ensure prediction accuracy. This dynamically optimized prediction method effectively solves the problem of insufficient prediction of moisture content change trends in traditional monitoring, achieving accurate prediction and real-time correction of moisture content. This provides reliable forward-looking data support for concrete production, further improving the level of refined control in the production process and the stability of product quality.

[0028] S4. The moisture content change trend is linked with the sand and gravel batch management system through a time synchronization mechanism. The time delay of sand and gravel reaching the mixing point is calculated based on the conveyor belt speed and the silo position to obtain accurate time compensation parameters. If the time delay calculation result does not match the preset range, the sensor position and conveying speed parameters are recalibrated.

[0029] Furthermore, a time synchronization mechanism is used to link the moisture content change trend with the sand and gravel batch management system, specifically including: The data on moisture content change trends are obtained through a time synchronization mechanism, and the correlation information between the data and the sand and gravel batch management system is obtained. The moisture content change trend corresponding to each batch is determined. Based on the moisture content change trend, conveyor belt speed, and silo location information, the time delay from the sand and gravel to the mixing point is calculated, and the time delay value is obtained. The time delay value is compared with a preset range threshold to determine whether the time delay value exceeds the preset range threshold. The comparison result is obtained. If the comparison result shows that the time delay value exceeds the preset range threshold, the sensor position is adjusted according to the sensor position information, and the adjusted sensor position data is obtained. By adjusting the sensor position data and conveyor belt speed parameters, the time delay is recalculated to obtain the calibrated time delay value. The calibrated time delay value is then used to update the time compensation parameters, which are then used to adjust the scheduling logic of the sand and gravel batch management system and determine the optimized batch scheduling scheme.

[0030] Specifically, by linking the moisture content change trend with the sand and gravel batch management system through a time synchronization mechanism, and calculating the time delay of sand and gravel arriving at the mixing point based on conveyor belt speed and silo position, this invention can obtain accurate time compensation parameters, thereby achieving precise optimization of sand and gravel batch scheduling. When the calculated time delay exceeds the preset range, the system automatically recalibrates the sensor position and conveyor speed parameters to ensure the accuracy of time compensation. This time synchronization and calibration mechanism effectively solves the problem of mismatch between moisture content and batch management caused by time delay, significantly improving the coordination and efficiency of concrete production, and ensuring the continuity and stability of the production process.

[0031] S5. Time compensation parameters are used to correct the predicted moisture content value. The feed compensation amount of sand and water is calculated through the feedforward control algorithm. The specific compensation coefficient is determined according to the ratio requirements and moisture content deviation. Real-time feed adjustment instructions are obtained. When the compensation amount exceeds the equipment adjustment range, the compensation action is executed in stages and the adjustment process is recorded.

[0032] Furthermore, time compensation parameters are used to correct the predicted moisture content over time, and the feed compensation amounts for sand, gravel, and water are calculated using a feedforward control algorithm, specifically including: S51. The predicted moisture content is corrected by time compensation parameters. A preset correction model is used to obtain the corrected predicted moisture content. Based on the corrected predicted moisture content and the proportioning requirements, a feedforward control algorithm is used to calculate the initial compensation amount of sand and gravel feed and water feed, and to determine the initial compensation coefficient. S52. For the initial compensation coefficient and moisture content deviation, a linear regression model is used to generate a real-time feeding adjustment command to obtain the adjusted feeding amount. When the adjusted feeding amount exceeds the equipment adjustment range, the compensation amount is decomposed into multiple sub-compensation actions through a graded compensation algorithm to obtain a graded compensation sequence. S53. According to the graded compensation sequence, execute the corresponding feeding adjustment action, obtain the actual feeding data after each adjustment, record the adjustment process, analyze the deviation trend of feeding adjustment, and use a time series analysis model to obtain the dynamic change trend of feeding deviation. S54. Based on the dynamic trend of the feeding deviation, update the time compensation parameters and the input parameters of the feedforward control algorithm, generate the optimized correction model, and obtain the new moisture content prediction value.

[0033] Specifically, by correcting the predicted moisture content value through time compensation parameters and calculating the material feeding compensation amount using a feedforward control algorithm, this invention can generate precise material feeding adjustment instructions in real time based on moisture content deviations, ensuring the accuracy of concrete mix proportions. When the compensation amount exceeds the equipment adjustment range, a tiered compensation strategy is adopted and the adjustment process is recorded, solving the problem of equipment adjustment limitations. Simultaneously, based on dynamically updated parameters and optimized correction models according to material feeding deviations, refined control and dynamic optimization of the material feeding process are achieved, significantly improving the stability of concrete production and the consistency of product quality.

[0034] S6. The feeding adjustment command is refined through PID control algorithm. The control output value is calculated based on the proportional gain, integral time and derivative time parameters. A closed-loop feedback mechanism is used to monitor the deviation between the actual feeding amount and the target value to obtain a stable feeding control signal. When the control deviation persists, the PID parameters are automatically adjusted and the control response is optimized.

[0035] Furthermore, the feeding adjustment command is refined using a PID control algorithm, and the control output value is calculated based on the proportional gain, integral time, and derivative time parameters. Specifically, this includes: The actual feeding amount data is collected in real time by sensors, the deviation between the actual feeding amount and the target value is calculated, the initial deviation value is obtained, and the control output value is calculated by using the PID control algorithm combined with the preset proportional gain, integral time and derivative time parameters to generate feeding adjustment command. The actuator sends the feeding adjustment command to the feeding equipment to adjust the feeding rate and obtain the actual feeding amount after adjustment. A closed-loop feedback mechanism is adopted to monitor the deviation between the actual feeding amount after adjustment and the target value in real time and obtain the current deviation value. When the current deviation value exceeds the preset threshold, the proportional gain, integral time and derivative time parameters are automatically adjusted by the gradient descent algorithm to obtain the optimized PID parameters, and then the control output value is recalculated to generate a new feeding adjustment command. The updated feeding rate is obtained, the deviation between the updated feeding rate and the target value is continuously monitored, a stable feeding control signal is generated, and the final feeding control response is obtained.

[0036] Specifically, by employing a PID control algorithm to refine the material feeding adjustment command, and combining proportional gain, integral time, and derivative time parameters to calculate the control output value, this invention utilizes a closed-loop feedback mechanism to monitor the deviation between the actual material feeding amount and the target value in real time. This allows for rapid adjustment of the feeding rate, ensuring the stability of the feeding control signal. When control deviation persists, the system automatically adjusts the PID parameters and optimizes the control response, effectively solving the problems of insufficient accuracy and lag in traditional feeding control. This further improves feeding accuracy and stability, ensuring high quality and high efficiency in concrete production.

[0037] S7. Drive the sand and gravel feeder and water metering system to perform compensation adjustment according to the feeding control signal. Use servo motors and solenoid valves to control the precise feeding of materials. Use weight sensors and flow meters to monitor the actual feeding effect and obtain proportion control feedback data. When the deviation between the actual proportion and the target proportion exceeds the allowable range, start the secondary compensation program.

[0038] Furthermore, based on the feeding control signal, the sand and gravel feeder and water metering system are driven to perform compensation adjustments, and precise material feeding is achieved through servo motors and solenoid valves, specifically including: The feeding control signal generation device acquires the operation command data of the sand and gravel feeder and the water metering system. The command data is compared with the preset operation parameters. When the command data deviates from the preset parameter range, the signal output intensity is adjusted to obtain the initial adjusted control signal. Based on the control signal after initial adjustment, the servo motor and solenoid valve control module are driven to perform material feeding operations, record material quantity changes in real time during the feeding process, and determine the preliminary execution results of the feeding operation. The system uses weight sensors and flow meters to monitor changes in material quantity in real time, obtains the deviation between the actual amount and the target ratio, and determines whether the deviation is within the preset threshold range. If the deviation exceeds the preset threshold range, a deviation correction signal is generated through the ratio feedback module. The operating parameters of the sand and gravel feeder and water metering system are adjusted according to the correction signal to obtain the corrected feeding control data. Then, the secondary compensation process is triggered, and the material feeding adjustment is performed again using the servo motor and solenoid valve control module. The material quantity distribution data after the secondary feeding is collected to determine the execution effect of the secondary compensation. The material quantity distribution data after secondary compensation is processed by a pre-established regression analysis model to obtain the stability index of the proportion adjustment. It is then determined whether the stability index meets the preset standard. If the stability index does not meet the preset standard, a further adjustment signal is generated through the proportion feedback module. The signal data drives the sand and gravel feeder and water metering system to make fine adjustments, and the final proportion control result is obtained.

[0039] Specifically, by driving the sand and gravel feeder and water metering system through feeding control signals, and using servo motors and solenoid valves for precise material feeding, and employing weight sensors and flow meters to monitor the actual feeding effect in real time, this invention achieves precise control over material feeding. When the actual mix proportion deviates from the target mix proportion beyond the allowable range, the system initiates a secondary compensation program to further adjust the feeding parameters, ensuring the accuracy of the mix proportion. This dual compensation mechanism effectively solves the mix proportion deviation problem caused by insufficient equipment precision or dynamic changes in traditional feeding systems, significantly improving the quality and stability of concrete production, and ensuring high efficiency and precision in the production process.

[0040] Furthermore, after secondary compensation, the system also includes: updating the moisture content prediction model and control parameters using ratio control feedback data; optimizing prediction accuracy and control effect through machine learning algorithms; establishing an adaptive adjustment mechanism based on historical production data to obtain continuously improved control performance; and switching to the backup monitoring channel and sending a maintenance reminder signal when the system detects abnormal equipment status or sensor failure.

[0041] Specifically, updating the moisture content prediction model and control parameters using ratio control feedback data includes: obtaining feedback data from the production process, performing preliminary cleaning and formatting on the data to obtain a structured first dataset, and using a support vector machine algorithm to update the parameters of the moisture content prediction model to determine the latest weights and deviation values ​​of the prediction model. By using the updated prediction model and combining historical data for feature extraction and pattern analysis, the prediction results of the moisture content change trend are obtained. By adjusting the control parameters and combining them with the adaptive adjustment mechanism, the optimal control scheme in the current production environment is calculated. It is then determined whether the control effect has reached the preset threshold. If not, the adjustment mechanism is iteratively optimized to obtain the optimized control command. When an abnormal equipment status or sensor failure is detected during the execution of control commands, the system switches to the backup monitoring channel to obtain alternative data, determines the continuity of system operation, and re-verifies the output results of the prediction model based on the data from the backup monitoring channel. If there is a deviation, the model is locally corrected to obtain the corrected prediction value. Then, combined with the optimized control commands, the system continuously monitors the equipment status and control effect to determine whether it has returned to the normal operating mode and obtains the final stable state of the system.

[0042] Specifically, by updating the moisture content prediction model and control parameters using feedback data from the proportioning control, and combining this with machine learning algorithms for optimization, this invention can establish an adaptive adjustment mechanism based on historical production data, continuously improving control performance and ensuring the system's intelligence and efficiency. When equipment malfunctions or sensor failures are detected, the system automatically switches to a backup monitoring channel and sends a maintenance reminder signal, ensuring the continuity and stability of the production process. This adaptive optimization and fault-switching mechanism effectively solves the problems of production interruptions and reduced control accuracy caused by equipment failures in traditional systems, significantly improving system reliability and production efficiency.

[0043] Example 2

[0044] Please see Figure 4 This embodiment provides a microwave penetration-type online monitoring and feeding compensation system for the moisture content of sand and gravel in a concrete mixing plant, including: The moisture content signal acquisition module uses a multi-point array of capacitive sensors to perform high-frequency scanning of different locations in the sand and gravel silo, collects moisture content signals in real time and generates a continuous data stream. When the moisture content fluctuation exceeds the preset threshold, an anomaly marking mechanism is triggered. The abnormal data is then classified and processed using a support vector machine algorithm to generate an anomaly location mapping. The data smoothing and anomaly detection module uses a sliding window algorithm to filter out noise and smooth the moisture content data stream. It obtains a stable moisture content benchmark value by calculating the moving average. When the deviation between the current detected value and the benchmark value exceeds the tolerance range, a moisture content anomaly signal is generated and transmitted to the prediction module for further analysis of the persistence and potential impact of the anomaly signal. The moisture content prediction module, based on historical moisture content change patterns and current detection data, uses the Kalman filter algorithm to establish a prediction model, calculates the predicted moisture content value and error range for future times, and automatically adjusts the model parameters and recalculates when the prediction error exceeds the set threshold to ensure that the prediction accuracy meets the requirements. The time synchronization and compensation module uses a time synchronization mechanism to associate the moisture content change trend with the sand and gravel batch management system, calculates the time delay of sand and gravel arriving at the mixing point, and obtains accurate time compensation parameters. When the time delay does not match the preset range, the sensor position and conveying speed parameters are recalibrated to ensure the accuracy of time compensation. The feeding compensation calculation module uses time compensation parameters to correct the predicted moisture content value, calculates the feeding compensation amount of sand and water through a feedforward control algorithm, determines the compensation coefficient based on the moisture content deviation, and executes compensation actions in stages and records the adjustment process when the compensation amount exceeds the equipment adjustment range to ensure feeding accuracy. The feeding control module uses a PID control algorithm to refine the feeding adjustment command, calculates the control output value based on proportional, integral and derivative parameters, and uses a closed-loop feedback mechanism to monitor the deviation between the actual feeding amount and the target value. When the control deviation persists, the PID parameters are automatically adjusted and the control response is optimized to ensure the stability of feeding. The actual feeding and feedback module drives the sand and gravel feeder and water metering system to perform compensation and adjustment based on the feeding control signal. It controls the precise feeding of materials through servo motors and solenoid valves, and uses weight sensors and flow meters to monitor the actual feeding effect. When the actual ratio deviates too much from the target ratio, a secondary compensation program is initiated, and the prediction model and control parameters are updated using feedback data to optimize system performance. When an equipment failure is detected, it switches to the backup channel and sends a maintenance reminder signal.

[0045] The above description is merely a preferred embodiment of the present invention and is not intended to limit the present invention in any way. Although the present invention has been disclosed above with reference to preferred embodiments, it is not intended to limit the present invention. Any person skilled in the art can make some modifications or alterations to the above-disclosed technical content to create equivalent embodiments without departing from the scope of the present invention. Any simple modifications, equivalent changes and alterations made to the above embodiments based on the technical essence of the present invention without departing from the scope of the present invention shall still fall within the scope of the present invention.

Claims

1. A microwave-guided online monitoring method for the moisture content of sand and gravel in a concrete mixing plant and a method for compensation during material feeding, characterized in that: Includes the following steps: The moisture content signal is collected at different locations in the sand and gravel silo by a multi-point array of capacitive sensors. Real-time moisture content data is obtained by high-frequency scanning mode and a continuous moisture content data stream is generated according to the preset sampling frequency. A sliding window algorithm is used to filter out noise and smooth the water content data stream. By setting the time window length and weighting coefficient, a moving average is calculated to obtain a stable water content benchmark value. Based on historical moisture content change patterns and current monitoring data, a moisture content prediction model is established using the Kalman filter algorithm. The predicted moisture content for future moments is calculated using the state transition matrix and the observation matrix, thereby obtaining the moisture content change trend and prediction error range. By using a time synchronization mechanism, the trend of moisture content change is linked to the sand and gravel batch management system. The time delay of sand and gravel arriving at the mixing point is calculated based on the conveyor belt speed and the location of the silo, thus obtaining accurate time compensation parameters. The predicted moisture content is corrected by using time compensation parameters. The feedforward control algorithm is used to calculate the feed compensation amount of sand and water. The specific compensation coefficient is determined according to the mix ratio requirements and moisture content deviation to obtain real-time feed adjustment instructions. The feeding adjustment command is refined by using a PID control algorithm. The control output value is calculated based on the proportional gain, integral time and derivative time parameters. A closed-loop feedback mechanism is used to monitor the deviation between the actual feeding amount and the target value to obtain a stable feeding control signal. The feeding control signal drives the sand and gravel feeder and water metering system to perform compensation and adjustment. The servo motor and solenoid valve control the precise feeding of materials. The weight sensor and flow meter monitor the actual feeding effect. When the deviation between the actual ratio and the target ratio exceeds the allowable range, the secondary compensation program is activated.

2. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: A multi-point array of capacitive sensors is used to collect moisture content signals at different locations in the sand and gravel silo, specifically including: The moisture content signal is collected at different locations in the sand and gravel bin by multiple capacitive sensors. A real-time data stream is generated by high-frequency scanning mode. Based on the real-time data stream, the moisture content signal is processed continuously by a preset sampling frequency to obtain a continuous sequence of moisture content information. Calculate the fluctuation amplitude between adjacent time points, determine the abnormal time period, obtain the moisture content information sequence within the abnormal time period, call the data processing module to perform priority analysis on the abnormally marked data, and extract the fluctuation characteristics. By analyzing the fluctuation characteristics, the support vector machine algorithm is used to classify the abnormal data and determine whether the abnormality belongs to negligible noise or a real abnormality. According to the classification results, if it is determined to be a real abnormality, the abnormal data and the corresponding time period information are transmitted to the subsequent processing unit to obtain the detailed abnormality distribution. By combining the location information of sensors arranged at multiple points within the sand and gravel silo, an anomaly location map is generated to determine the specific area where the anomaly occurred.

3. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: The sliding window algorithm is used to perform noise filtering and data smoothing on the moisture content data stream, specifically including: By collecting moisture content data streams in real time, the data flow direction is segmented using a sliding window method, and the distribution of data points within each time window is calculated. For each data point within a time window, the calculation method is adjusted by applying a weighting coefficient, and the data is smoothed using a moving average method to obtain a smoothed moisture content data sequence. Combined with the preset time window length, the moving average is continuously updated to determine a stable moisture content benchmark value. The current moisture content detection value is compared with the benchmark value. When the deviation between the detection value and the benchmark value exceeds the preset tolerance range, a corresponding abnormal signal mark is generated. The generated abnormal signal mark is classified and processed, and combined with the characteristics of data flow and detection value difference, the abnormal signal is transmitted to the prediction module for analysis. Based on the abnormal signals transmitted to the prediction module, combined with the noise filtering results and data smoothing characteristics in historical data, an abnormal trend analysis model is constructed to determine the persistence and potential impact of the abnormal signals. Based on the output of the abnormal trend analysis model, corresponding early warning information is generated for the persistence characteristics of the abnormal signals.

4. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: A water content prediction model is established using the Kalman filter algorithm, specifically including: By combining historical data and current monitoring information, an analytical basis for the initial moisture content change is constructed. The Kalman filter algorithm is used to process the data, and the state transition matrix and observation matrix are used to extrapolate the moisture content change trend to obtain the predicted value data for future moments. For the acquired predicted data, the prediction error and error range are calculated, and it is determined whether the error exceeds the preset threshold. By marking the state to be adjusted, the parameter adjustment mechanism is triggered to update the key parameters in the prediction model and recalculate the moisture content change trend and predicted value. Based on the updated predicted values, the prediction error and error range are reassessed to determine whether the preset threshold conditions are met. The predicted values ​​and trends that finally meet the conditions are obtained, and a complete dataset of moisture content prediction is generated. By continuously monitoring the moisture content change trend, historical data and current detection information are updated regularly.

5. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: The moisture content change trend is linked to the sand and gravel batch management system through a time synchronization mechanism, specifically including: The data on moisture content change trends are obtained through a time synchronization mechanism, and the correlation information between the data and the sand and gravel batch management system is obtained. The moisture content change trend corresponding to each batch is determined. Based on the moisture content change trend, conveyor belt speed, and silo location information, the time delay from the sand and gravel to the mixing point is calculated, and the time delay value is obtained. The time delay value is compared with a preset range threshold to determine whether the time delay value exceeds the preset range threshold, and the comparison result is obtained to obtain the adjusted sensor position data. By adjusting the sensor position data and conveyor belt speed parameters, the time delay is recalculated to obtain the calibrated time delay value. The calibrated time delay value is then used to update the time compensation parameters, which are then used to adjust the scheduling logic of the sand and gravel batch management system and determine the optimized batch scheduling scheme.

6. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: The predicted moisture content is corrected using a time compensation parameter, and the feed compensation amounts for sand, gravel, and water are calculated using a feedforward control algorithm. Specifically, this includes: The predicted moisture content is corrected by time compensation parameters. A preset correction model is used to obtain the corrected predicted moisture content. Based on the corrected predicted moisture content and the proportioning requirements, a feedforward control algorithm is used to calculate the initial compensation amount of sand and gravel feed and water feed, and to determine the initial compensation coefficient. For the initial compensation coefficient and moisture content deviation, a linear regression model is used to generate real-time feeding adjustment instructions to obtain the adjusted feeding amount. When the adjusted feeding amount exceeds the equipment adjustment range, the compensation amount is decomposed into multiple sub-compensation actions through a graded compensation algorithm to obtain a graded compensation sequence. According to the graded compensation sequence, the corresponding feeding adjustment actions are executed, the actual feeding data after each adjustment is obtained, the adjustment process is recorded, and the deviation trend of feeding adjustment is analyzed. A time series analysis model is used to obtain the dynamic change trend of feeding deviation. Based on the dynamic trend of the feeding deviation, the time compensation parameters and the input parameters of the feedforward control algorithm are updated to generate an optimized correction model and obtain a new moisture content prediction value.

7. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: The feeding adjustment command is refined through a PID control algorithm. The control output value is calculated based on the proportional gain, integral time, and derivative time parameters, specifically including: The actual feeding amount data is collected in real time by sensors, the deviation between the actual feeding amount and the target value is calculated, the initial deviation value is obtained, and the control output value is calculated by using the PID control algorithm combined with the preset proportional gain, integral time and derivative time parameters to generate feeding adjustment command. The actuator sends the feeding adjustment command to the feeding equipment to adjust the feeding rate and obtain the actual feeding amount after adjustment. A closed-loop feedback mechanism is adopted to monitor the deviation between the actual feeding amount after adjustment and the target value in real time and obtain the current deviation value. When the current deviation value exceeds the preset threshold, the proportional gain, integral time and derivative time parameters are automatically adjusted by the gradient descent algorithm to obtain the optimized PID parameters, and then the control output value is recalculated to generate a new feeding adjustment command. The updated feeding rate is obtained, the deviation between the updated feeding rate and the target value is continuously monitored, and a stable feeding control signal is generated.

8. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 1, characterized in that: The feeding control signal drives the sand and gravel feeder and water metering system to perform compensation and adjustment. Precise material feeding is achieved through servo motors and solenoid valves, specifically including: The operation command data of the sand and gravel feeder and water metering system are obtained through the feeding control signal generation device. The command data is compared with the preset operation parameters to obtain the control signal after initial adjustment. Based on the control signal after initial adjustment, the servo motor and solenoid valve control module are driven to perform material feeding operations and record the material quantity change data in real time during the feeding process. Weight sensors and flow meters are used to monitor material quantity changes in real time, obtain the deviation between the actual amount and the target ratio, and generate a deviation correction signal through the ratio feedback module. The operating parameters of the sand and gravel feeder and water metering system are adjusted according to the correction signal, and then the secondary compensation process is triggered. The material feeding adjustment is performed again using the servo motor and solenoid valve control module. The material quantity distribution data after the secondary feeding is collected to determine the execution effect of the secondary compensation. Data is processed by a pre-established regression analysis model to obtain stability indicators for mix ratio adjustment. The signal data drives the sand and gravel feeder and water metering system to make fine adjustments, and the final mix ratio control result is obtained.

9. The microwave penetration-based online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant according to claim 8, characterized in that: After secondary compensation, the following steps are also included: updating the moisture content prediction model and control parameters using ratio control feedback data, optimizing prediction accuracy and control effect through machine learning algorithms, and establishing an adaptive adjustment mechanism based on historical production data to obtain continuously improved control performance.

10. A microwave-guided online monitoring and feeding compensation system for the moisture content of sand and gravel in a concrete mixing plant, applied to the microwave-guided online monitoring and feeding compensation method for the moisture content of sand and gravel in a concrete mixing plant as described in any one of claims 1-9, characterized in that: include: The moisture content signal acquisition module uses a multi-point array of capacitive sensors to perform high-frequency scanning of different locations in the sand and gravel silo, acquires moisture content signals in real time and generates a continuous data stream, and combines a support vector machine algorithm to classify abnormal data and generate anomaly location mappings. The data smoothing and anomaly detection module uses a sliding window algorithm to filter out noise and smooth the moisture content data stream. It obtains a stable moisture content benchmark value by calculating the moving average value, generates moisture content anomaly signals, and transmits them to the prediction module. The moisture content prediction module, based on historical moisture content change patterns and current monitoring data, uses the Kalman filter algorithm to establish a prediction model, calculates the predicted moisture content value and error range for future times, and automatically adjusts the model parameters and recalculates when the prediction error exceeds the set threshold. The time synchronization and compensation module uses a time synchronization mechanism to associate the moisture content change trend with the sand and gravel batch management system, calculates the time delay of sand and gravel arriving at the mixing point, and obtains accurate time compensation parameters. The feeding compensation calculation module uses time compensation parameters to correct the predicted moisture content value, calculates the feeding compensation amount of sand and water through a feedforward control algorithm, determines the compensation coefficient based on the moisture content deviation, executes compensation actions in stages, and records the adjustment process. The feeding control module uses a PID control algorithm to refine the feeding adjustment command, calculates the control output value based on proportional, integral and derivative parameters, and uses a closed-loop feedback mechanism to monitor the deviation between the actual feeding amount and the target value, automatically adjusts the PID parameters and optimizes the control response. The actual feeding and feedback module drives the sand and gravel feeder and water metering system to perform compensation and adjustment based on the feeding control signal. It controls the precise feeding of materials through servo motors and solenoid valves, and uses weight sensors and flow meters to monitor the actual feeding effect. When the actual ratio deviates too much from the target ratio, a secondary compensation program is initiated, and the prediction model and control parameters are updated using feedback data to optimize system performance.

Images