Desert environment C60 high-strength concrete production control method

Abstract

The invention relates to a desert environment C60 high-strength concrete production control method which comprises the following steps: establishing an intelligent temperature control system, stably maintaining the water temperature in summer at 25 DEG C or below through algorithm prediction and dynamic adjustment of the intelligent temperature control system, and monitoring and adjusting pre-cooling measures of aggregate and sand; a raw material temperature monitoring network is established, the raw material temperature monitoring network is deployed in a cement storage area, an aggregate storage yard and a water treatment area, data are collected in real time through the raw material temperature monitoring network, and an accurate basis is provided for a temperature control strategy; establishing a mix proportion dynamic adjustment algorithm: based on the collected temperature and humidity data, combining with a concrete performance model, automatically adjusting the proportion of cement, water, an additive and aggregate, and optimizing the performance of the concrete under different environmental conditions; a quality monitoring system of the whole process from mixing to pouring is established, concrete performance data are collected and fed back to the algorithm model, and the production process and the mix proportion design are continuously optimized.

Description

Technical Field

[0001] The present application relates to the technical field of concrete production, and in particular to a method for controlling the production of C60 high-strength concrete in a desert environment. Background Art

[0002] When constructing infrastructure in desert areas, it is necessary to build a mixing plant to produce high-performance concrete. Especially under extreme climatic conditions, ensuring the quality of concrete, especially the quality of C60 high-strength concrete, faces many challenges. In high temperature environments, the temperature and humidity management of cement, water and raw materials has a significant impact on the final performance of concrete. In the traditional concrete production process, due to poor temperature control of raw materials, problems such as poor early strength development of concrete, shrinkage cracking, etc. are usually caused. Especially in summer, the water temperature is difficult to effectively control within the ideal range (such as below 25°C), which affects the mixing efficiency of concrete and the quality of the finished product. Summary of the invention

[0003] The embodiment of the present application provides a method for controlling the production of C60 high-strength concrete in a desert environment. The method for controlling the production of C60 high-strength concrete in a desert environment can solve the temperature and humidity problems faced in concrete production in desert areas to a certain extent, thereby improving the quality and performance of concrete.

[0004] The method for controlling the production of C60 high-strength concrete in a desert environment provided in the embodiment of the present application comprises the following steps:

[0005] 1) Establish an intelligent temperature control system, through the algorithm prediction and dynamic adjustment of the intelligent temperature control system, combined with a refrigerator and / or an ice cube delivery device, so that the water temperature in summer is stably maintained at 25°C or below, and at the same time monitor and adjust the pre-cooling measures of aggregates and sand to achieve the preset temperature and humidity state of the raw materials;

[0006] 2) Establishing a raw material temperature monitoring network, which is deployed at least in cement storage, aggregate yard and water treatment area, and collecting data in real time through the raw material temperature monitoring network to provide an accurate basis for temperature control strategy;

[0007] 3) Establish a dynamic mix ratio adjustment algorithm: Based on the collected temperature and humidity data and combined with the concrete performance model, the mix ratio of cement, water, admixtures and aggregates is automatically adjusted to optimize the performance of concrete under different environmental conditions;

[0008] 4) Conduct quality feedback and optimization cycles: Establish a quality monitoring system for the entire process from mixing to pouring, collect concrete performance data, feed it back to the algorithm model, and continuously optimize the production process and mix design.

[0009] In an optional solution, the intelligent temperature control system adopts a temperature control optimization algorithm, the goal of which is to predict and maintain the preset temperature and humidity state of water and raw materials under given external environmental conditions. The algorithm framework is as follows:

[0010] 1.1) Data input: current water temperature T w ; Target water temperature T wtarget =25℃; external environment temperature T env ; Actual temperature and humidity of aggregate and sand T agg ,T sand ,H agg ,H sand ; Expected ambient temperature change trend in the next few hours T envforecast ;

[0011] 1.2) Historical data analysis: Learn the temperature and humidity change patterns based on historical data and use time series analysis to predict future temperature fluctuations;

[0012] 1.3) Temperature control model establishment: For water temperature control, a dynamic model is constructed to describe the refrigerator power P cool , Ice cube quantity Q ice Relationship with water temperature changes;

[0013] 1.4) Optimization algorithm: adopt model predictive control strategy, based on the prediction model, find the control strategy that minimizes the temperature difference in the future period;

[0014] 1.5) Instruction output and execution: The CPU outputs at least one of a refrigerator power adjustment instruction, an ice cube placement instruction, and an aggregate sand precooling equipment start-stop instruction according to the optimization algorithm result;

[0015] 1.6) Feedback and adjustment: Monitor the deviation between actual temperature and humidity and target values ​​in real time, and continuously fine-tune control parameters through closed-loop control to ensure that the system is stable in the optimal state.

[0016] In an optional solution, the step 1.3) needs to consider the heat exchange principle and energy balance equation when constructing the dynamic model:

[0017]

[0018] Where k is the system cooling efficiency coefficient, c is the environmental influence coefficient on water temperature; the precooling of aggregate and sand is achieved by controlling air cooling and spray water volume W spray To adjust, calculate the precooling rate based on the material specific heat capacity and mass flow rate;

[0019] The step 1.4) also includes setting a cost function, which includes minimizing energy consumption and the sum of squares of temperature differences:

[0020]

[0021] In the formula, w 1 ,w 2 is the weight coefficient, N p is the prediction step length.

[0022] In an optional solution, the raw material temperature monitoring network realizes accurate data fusion through extended Kalman filtering, isolates the forest algorithm to efficiently identify data anomalies, and optimizes resource allocation through genetic algorithm. The establishment of the raw material temperature monitoring network includes:

[0023] 2.1) Time synchronization algorithm: The network time protocol is used to ensure the time synchronization of all sensors and data collection nodes, ensuring the timing accuracy of the data;

[0024] 2.2) Data fusion algorithm: At the CCU level, the Kalman filter algorithm is used to fuse the temperature and humidity data from different sensors to reduce noise and improve the credibility of the data;

[0025] 2.3) Anomaly detection algorithm refinement: The anomaly detection algorithm based on machine learning isolation forest estimates the degree of isolation of data points by constructing random trees;

[0026] 2.4) Genetic algorithms are used in resource optimization and scheduling. For the optimization of the intelligent temperature control system, the goal is to find the optimal control strategy, which includes the power of the refrigerator, the amount of ice cubes put in, and the operating time of the pre-cooling equipment, so as to minimize energy consumption while ensuring the temperature and humidity control effect.

[0027] In an optional solution, the following steps are included when the Kalman filter algorithm is used to fuse the temperature and humidity data:

[0028] For raw material temperature monitoring, assume that the state vector of each monitoring point is Include temperature Its rate of change over time T k , measurement vector z k Only the temperature T k Direct observation, the prediction and update steps of the extended Kalman filter are as follows:

[0029] Prediction Steps:

[0030]

[0031] Where f is the nonlinear state transfer function, u k-1 is the control input, such as external environmental influence, F k is the Jacobian matrix, Q k is the process noise covariance matrix;

[0032] Update steps:

[0033]

[0034] P k|k =(IK k H k ) k|k-1 ;

[0035] Where h is the nonlinear observation function, H k Its Jacobian matrix, R k is the observation noise covariance matrix.

[0036] In an optional solution, the following steps are included when refining the anomaly detection algorithm:

[0037] Given a set of training data, the isolation forest algorithm calculates the average path length or path length score of each data point. For a new data point, its MHL or PLF is calculated. If it is significantly higher than the average value of the training data set, the point is considered to be abnormal. Let H(x) be the average path length of data point x, and the anomaly score is defined as:

[0038]

[0039] Where E(H(x)) is the expected value of the average path length of x, c(n) is a constant calculated based on the size of the data set n, and the closer s(x) is to 1, the more likely x is a normal data point; the closer it is to 0, the more likely it is an outlier.

[0040] The following steps are included when using genetic algorithms for resource optimization scheduling:

[0041] Let the decoded code be X = [P cool ,Q ice ,W spray ] T , where P cool is the refrigerator power, Q ice is the amount of ice cubes put in, W spray For the precooling spray water volume, the objective function (i.e. the minimization target) is defined as:

[0042]

[0043] In the formula, E total is the total energy consumption, w 1 ,w 2 is the weight coefficient, N is the number of monitoring points, T i and are the actual temperature and target temperature of the i-th monitoring point respectively.

[0044] In an optional solution, the step 3) specifically includes the following steps:

[0045] 3.1) Data collection and preprocessing: The real-time temperature and humidity data of cement, water, aggregate and sand are collected through the raw material temperature monitoring network. After cleaning and correction, the data is converted into key parameters that have a direct impact on concrete performance, including the effective water-binder ratio. Aggregate moisture content correction;

[0046]

[0047] In the formula, is the nominal water-binder ratio, k is the temperature influence coefficient, T cement is the actual temperature of cement, T ref As the reference temperature, the formula can be fitted with historical data to obtain the k value, and its accuracy can be verified by data;

[0048] 3.2) Establish a concrete performance prediction model based on regression analysis;

[0049] 3.3) Using the particle swarm optimization algorithm as the basic framework, combined with the concrete performance model, automatically find the optimal mix ratio under the current environmental conditions. The particle swarm optimization algorithm simulates the foraging behavior of bird flocks to find the global optimal solution;

[0050] 3.4) Implementation and feedback; including implementation adjustment, performance verification and feedback loop. Implementation adjustment: adjust the raw material ratio in actual production according to the optimal mix ratio obtained by the particle swarm optimization algorithm; Performance verification: perform performance tests on the adjusted concrete to verify the consistency between the model prediction and the actual performance; Feedback loop: continuously incorporate new data into model training to form a data-driven closed-loop iterative optimization process, and continuously improve the generalization ability of the model and the accuracy of mix ratio adjustment.

[0051] In an optional solution, the step 3.2) specifically includes the following steps:

[0052] Considering the influence of main raw material ratio and environmental temperature and humidity on concrete performance, including compressive strength, workability and shrinkage, the model is expressed as:

[0053] Y=f(C,W,A,S,T env ,H env )+∈;

[0054] In the formula, (Y) represents a performance index of concrete, such as 28-day compressive strength, C, W, A, S represent the proportion of cement, water, aggregate, and sand, respectively, and T env ,H env is the ambient temperature and humidity, ∈ is the random error term;

[0055] Based on multiple linear regression analysis, the 28-day compressive strength of concrete is expressed as:

[0056]

[0057] In the formula, β i is the regression coefficient, is the sand ratio, T env and H env are the ambient temperature and humidity respectively, and the coefficient β i It can be determined by the least squares estimation of historical test data;

[0058] The step 3.3) specifically comprises the following steps:

[0059] Let the particle's position vector be X i =[C i ,W i ,A i ,S i ], the velocity vector is (V i ), the optimization goal is to maximize the concrete performance index (Y);

[0060] Initialization: Randomly generate an initial particle group, each particle represents a possible mix ratio;

[0061] Iteration Update: V i,t+1 =wV i,t +c 1 r 1 (X pbesti -X i,t )+c 2 r 2 (X gbest,t -X i,t );

[0062] X i,t+1 =X i,t +V i,t+1 ;

[0063] Where w is the inertia weight, c 1 ,c 2 is the acceleration constant, r 1 ,r 2 is a random number between [0,1], and X gbest,t Represent the historical optimal position and current global optimal position of the i-th particle respectively;

[0064] Mix ratio constraint processing: After each iteration, the constraint processing mechanism is applied to ensure the mix ratio of all particles, such as water-binder ratio Sand rate Fall within the permitted range of the specification;

[0065] Algorithm termination condition: set the maximum number of iterations or reach a predetermined performance improvement threshold.

[0066] In an optional solution, the step 4) comprises the following steps:

[0067] 4.1) Sample selection and testing: After each batch of concrete is produced, samples are taken from different parts according to standard procedures, and 28-day compressive strength tests and 7-day shrinkage rate evaluations are carried out under standard curing to ensure the representativeness and accuracy of the data;

[0068] 4.2) Data standardization: pre-process the collected test data, including outlier removal and standardization, to ensure data availability;

[0069] 4.3) Performance index deviation calculation: Calculate the deviation between the actual test results and the expected performance index as the basis for feedback adjustment;

[0070] 4.4) Feedback adjustment model: Proportional integral differential control algorithm is used to dynamically adjust production parameters according to the deviation and change trend of performance indicators. For mix ratio adjustment, the compressive strength deviation is mapped to the adjustment amount of cement amount and water-binder ratio;

[0071] 4.5) Parameter optimization and adjustment: Based on the adjustment amount calculated by the proportional-integral-differential algorithm and combined with the production experience limitations, fine-tune the mix ratio of the next production batch; based on the shrinkage rate evaluation results, adjust the type or amount of admixtures through similar methods to control the shrinkage rate.

[0072] In an optional solution, when preprocessing the collected test data, the compressive strength f c,28 and shrinkage rate ε 7 , the standardized formula is expressed as:

[0073]

[0074] Where μ and σ are the historical mean and standard deviation of compressive strength and shrinkage, respectively;

[0075] The expected performance indicators include the designed compressive strength and the maximum allowable shrinkage rate; assuming that the expected compressive strength is f c,28_target , then the deviation Δf c,28 for:

[0076] Δf c,28 =f c,28_target -f c,28 ;

[0077] The proportional-integral-differential control algorithm formula used in step 4.4) is:

[0078]

[0079] In the formula, X represents the production parameters that need to be adjusted, such as cement dosage, K P ,K I ,K D They are proportional, integral and differential coefficients, which need to be adjusted according to system characteristics and historical data.

[0080] The beneficial effects of the embodiments of the present application are:

[0081] The desert environment C60 high-strength concrete production control method provided in the embodiment of the present application improves the efficiency and stability of concrete production and reduces production costs through an intelligent temperature control system and a dynamic mix ratio adjustment algorithm. The production process and mix ratio design are continuously improved through quality feedback and optimization cycles, thereby further improving the quality and reliability of concrete. It effectively solves the temperature and humidity control problems in concrete production in desert environments, ensures the quality and performance of concrete to a certain extent, is suitable for various concrete projects in desert areas, and has broad application prospects and market value.

[0082] It should be understood that the foregoing general description and the following detailed description are exemplary only and are not restrictive of the present application. BRIEF DESCRIPTION OF THE DRAWINGS

[0083] Figure 1 A schematic diagram of the steps of the production control method of C60 high-strength concrete in a desert environment provided in this application;

[0084] Figure 2 for Figure 1 A flowchart showing the detailed implementation steps of the production control method in each step.

[0085] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application. DETAILED DESCRIPTION

[0086] In order to better understand the technical solution of the present application, the embodiments of the present application are described in detail below with reference to the accompanying drawings.

[0087] It should be clear that the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in the field without creative work are within the scope of protection of the present application.

[0088] The terms used in the embodiments of the present application are only for the purpose of describing specific embodiments, and are not intended to limit the present application. The singular forms "a", "said" and "the" used in the embodiments of the present application and the appended claims are also intended to include plural forms, unless the context clearly indicates other meanings.

[0089] It should be understood that the term "and / or" used in this article is only a description of the association relationship of associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist at the same time, and B exists alone. In addition, the character " / " in this article generally indicates that the associated objects before and after are in an "or" relationship.

[0090] like Figure 1-2 As shown, the embodiment of the present application provides a method for controlling the production of C60 high-strength concrete in a desert environment, and the method mainly includes the following steps:

[0091] 1) Intelligent temperature control system: The integrated refrigerator and ice delivery device ensure that the water temperature is maintained at 25°C or below in summer through algorithm prediction and dynamic adjustment. At the same time, the pre-cooling measures of aggregates and sand are monitored and adjusted to achieve the ideal temperature and humidity state of raw materials.

[0092] The intelligent temperature control system uses a temperature control optimization algorithm (TCA) whose goal is to predict and maintain the ideal temperature and humidity state of water and other raw materials under given external environmental conditions. The algorithm framework is as follows:

[0093] 1.1 Data input: current water temperature T w ; Target water temperature External environment temperature T env ; Actual temperature and humidity of aggregate and sand T agg ,T sand ,H agg ,H sand ; Expected ambient temperature change trend in the next few hours T envforecast

[0094] 1.2 Historical data analysis: Learn the temperature and humidity change patterns based on historical data, and use time series analysis (such as ARIMA model) to predict future temperature fluctuations.

[0095] 1.3 Temperature control model establishment: For water temperature control, a dynamic model is constructed to describe the refrigerator power P cool , Ice cube quantity Q ice Relationship with water temperature change. For example, consider the heat exchange principle and energy balance equation:

[0096]

[0097] In the formula, k is the system cooling efficiency coefficient, and c is the coefficient of environmental influence on water temperature. The precooling of aggregate and sand is achieved by controlling air cooling and spray water volume W. spray To adjust, the precooling rate is calculated based on the material specific heat capacity and mass flow rate.

[0098] 1.4 Optimization algorithm: Use the model predictive control (MPC) strategy to find a control strategy that minimizes the temperature difference in the future period based on the prediction model. Set the cost function, such as minimizing energy consumption and the sum of squares of temperature differences:

[0099]

[0100] In the formula, w 1 ,w 2 is the weight coefficient, N p is the prediction step length.

[0101] 1.5 Instruction output and execution: Based on the results of the optimization algorithm, the CPU outputs refrigerator power adjustment instructions, ice cube placement instructions, and start and stop instructions for aggregate sand precooling equipment.

[0102] 1.6 Feedback and adjustment: Real-time monitoring of the deviation between actual temperature and humidity and target values, and continuous fine-tuning of control parameters through closed-loop control to ensure that the system is stable in the optimal state.

[0103] 2) Raw material temperature monitoring network: deployed in cement storage, aggregate yards and water treatment areas, collecting data in real time to provide an accurate basis for temperature control strategies.

[0104] By using extended Kalman filtering to achieve precise data fusion, the isolation forest algorithm to efficiently identify data anomalies, and the genetic algorithm to optimize resource allocation, this intelligent raw material temperature monitoring network can provide strong support for the temperature control strategy of the desert mixing plant, ensuring that the temperature control in the production process of C60 high-strength concrete is both efficient and accurate.

[0105] 2.1 Time synchronization algorithm: The Network Time Protocol (NTP) is used to ensure the time synchronization of all sensors and data acquisition nodes to ensure the timing accuracy of the data.

[0106] 2.2 Data fusion algorithm: At the CCU level, the Kalman filter algorithm is used to fuse the temperature and humidity data from different sensors to reduce noise and improve the credibility of the data. In order to better handle nonlinear problems, the extended Kalman filter (EKF) is used here. For raw material temperature monitoring, it is assumed that the state vector of each monitoring point is Include temperature Its rate of change over time T k . Measurement vector z kOnly the temperature T k Direct observation of . The prediction and update steps of the extended Kalman filter are as follows:

[0107] Prediction Steps:

[0108]

[0109] Where f is the nonlinear state transfer function, u k-1 is the control input (such as external environmental influence), F k is the Jacobian matrix, Q k is the process noise covariance matrix.

[0110] Update steps:

[0111]

[0112] P k|k =(IK k H k ) k|k-1

[0113] h is the nonlinear observation function, H k Its Jacobian matrix, R k is the observation noise covariance matrix.

[0114] 2.3 Anomaly detection algorithm refinement: Isolation Forest based on machine learning is an efficient anomaly detection algorithm that estimates the degree of isolation of data points by constructing random trees. Given a set of training data, the Isolation Forest algorithm calculates the mean path length (MHL) or path length fraction (PLF) of each data point. For new data points, their MHL or PLF is calculated. If it is significantly higher than the mean value of the training data set, the point is considered to be anomaly.

[0115] Let H(x) be the average path length of data point x, and the anomaly score is defined as:

[0116]

[0117] Where E(H(x)) is the expected value of the average path length of x, c(n) is a constant calculated based on the size of the data set n, and the closer s(x) is to 1, the more likely x is a normal data point; conversely, the closer it is to 0, the more likely it is an outlier.

[0118] 2.4 Genetic Algorithm (GA) is used in resource optimization and scheduling. It is a heuristic optimization method suitable for solving complex combinatorial optimization problems. For the optimization of the temperature control system, the goal is to find the optimal control strategy (such as refrigerator power, ice cube delivery, pre-cooling equipment operation time, etc.) to minimize energy consumption while ensuring temperature and humidity control effects.

[0119] Let the decoded code be X = [P cool ,Q ice ,W spray ] T , where P cool is the refrigerator power, Q ice is the amount of ice cubes put in, W spray is the amount of precooling spray water. The objective function (i.e. the minimization target) can be defined as:

[0120]

[0121] In the formula, E total is the total energy consumption, w 1 ,w 2 is the weight coefficient, N is the number of monitoring points, T i and are the actual temperature and target temperature of the i-th monitoring point respectively.

[0122] The basic operations of genetic algorithms include selection, crossover (hybridization), mutation, and elite retention. Through multiple generations of iterations, the optimal solution is gradually approached, and finally functions such as real-time temperature control strategy support are achieved.

[0123] Dynamic threshold setting: Based on historical data and current environmental conditions, the temperature and humidity thresholds are dynamically set. Once the monitoring data exceeds the threshold, an alarm is immediately triggered and corresponding temperature control measures are initiated.

[0124] Predictive maintenance: Use time series analysis or machine learning models to predict future temperature and humidity trends, adjust the working status of refrigeration and pre-cooling equipment in advance, and avoid passive response of the temperature control system.

[0125] Resource optimization scheduling: Based on real-time monitoring data, the operation strategies of refrigerators, ice delivery and pre-cooling equipment are adjusted through optimization algorithms (such as genetic algorithms or particle swarm optimization) to minimize energy consumption and maximize temperature control effects.

[0126] 3) Dynamic adjustment algorithm of mix ratio: Based on the collected temperature and humidity data and combined with the concrete performance model, the mix ratio of cement, water, admixtures and aggregates is automatically adjusted to ensure the optimal performance of concrete under different environmental conditions.

[0127] In desert environments, with the dramatic fluctuations in temperature and humidity, the traditional fixed mix ratio may not be able to ensure the stability of concrete performance. Therefore, this section proposes a dynamic mix ratio adjustment algorithm based on temperature and humidity data and concrete performance model, aiming to optimize the performance of C60 high-strength concrete under different environmental conditions by adjusting the ratio of cement, water, admixtures and aggregates in real time.

[0128] 3.1 Data collection and preprocessing: First, the real-time temperature and humidity data of cement, water, aggregate and sand are collected through the raw material temperature monitoring network. After cleaning and correction, the data is converted into key parameters that have a direct impact on the performance of concrete, such as the effective water-binder ratio. (considering the influence of actual water temperature on the hydration reaction rate), aggregate moisture content correction, etc.

[0129]

[0130] here, is the nominal water-binder ratio, k is the temperature influence coefficient, T cement is the actual temperature of cement, T ref is the reference temperature. The formula can be fitted with historical data to obtain the k value, and its accuracy can be verified by data.

[0131] 3.2 Establish a concrete performance prediction model based on regression analysis, considering the influence of the main raw material ratio and environmental temperature and humidity on concrete performance, such as compressive strength, workability (slump) and shrinkage. The model can be expressed as:

[0132] Y=f(C,W,A,S,T env ,H env )+∈

[0133] In the formula, (Y) represents a certain performance index of concrete (such as 28-day compressive strength), C, W, A, S represent the proportion of cement, water, aggregate, and sand, respectively, and T env ,H env is the ambient temperature and humidity, and ∈ is the random error term.

[0134] Based on multiple linear regression analysis, the 28-day compressive strength of concrete can be expressed as:

[0135]

[0136] In the formula, β i is the regression coefficient, is the sand ratio, T env and H env are the ambient temperature and humidity respectively. Coefficient β i It can be determined by the least squares estimation of historical test data, and the effectiveness of the model can be proven by statistical significance tests (such as t-tests).

[0137] 3.3 Particle Swarm Optimization (PSO) is used as the basic framework, combined with the concrete performance model, to automatically find the optimal mix ratio under the current environmental conditions. The PSO algorithm simulates the foraging behavior of bird flocks to find the global optimal solution. Let the position vector of the particle be X i =[C i ,W i ,A i ,S i ], the velocity vector is (V i ), the optimization goal is to maximize the concrete performance index (Y).

[0138] Initialization: Randomly generate an initial particle group, each particle represents a possible mix ratio.

[0139] Iterative updates:

[0140]

[0141] X i,t+1 =X i,t +V i,t+1

[0142] Where w is the inertia weight, c 1 ,c 2 is the acceleration constant, r 1 ,r 2 is a random number between [0,1], and X gbest,t Represent the historical optimal position and the current global optimal position of the i-th particle respectively.

[0143] Mix ratio constraint processing: After each iteration, the constraint processing mechanism is applied to ensure the mix ratio of all particles, such as water-binder ratio Sand rate etc. fall within the permitted range of the specification.

[0144] Algorithm termination condition: set the maximum number of iterations or reach a predetermined performance improvement threshold.

[0145] 3.4 Implementation and feedback;

[0146] Implementation adjustment: Adjust the raw material ratio in actual production according to the optimal mix ratio obtained by the PSO algorithm.

[0147] Performance verification: The adjusted concrete is subjected to performance tests to verify the consistency between the model prediction and the actual performance.

[0148] Feedback loop: Continuously incorporate new data into model training to form a data-driven closed-loop iterative optimization process, continuously improving the generalization ability of the model and the accuracy of mix ratio adjustment.

[0149] Of course, the specific mathematical models and formulas of the dynamic adjustment algorithm of the mix ratio are explored in depth, and it is clearly pointed out which parts can be verified and optimized through the actual collected data.

[0150] Through the above algorithm design, the dynamic adjustment algorithm of mix ratio can not only respond to the temperature and humidity changes of raw materials in real time, but also ensure the continuous optimization of concrete performance in the extreme environment of the desert. This method combines advanced data processing, concrete performance prediction model and intelligent optimization algorithm, providing strong technical support for the high-quality production of C60 high-strength concrete in desert areas.

[0151] 4) Quality feedback and optimization loop: Establish a quality monitoring system for the entire process from mixing to pouring, collect concrete performance data, feed it back to the algorithm model, and continuously optimize the production process and mix design.

[0152] The quality monitoring and feedback system is a key link in ensuring the quality of concrete production. It integrates real-time data collection, performance evaluation, and feedback adjustment, and continuously optimizes the concrete production process through automation and intelligent means. The following is the specific design of the system and related algorithm details.

[0153] 4.1 Sample selection and testing: After each batch of concrete is produced, samples are taken from different parts according to standard procedures, and 28-day compressive strength tests and 7-day shrinkage rate assessments are carried out under standard curing to ensure the representativeness and accuracy of the data.

[0154] 4.2 Data standardization: Preprocess the collected test data, including outlier removal and standardization, to ensure data availability. c,28 and shrinkage rate ε 7 , the standardized formula can be expressed as:

[0155]

[0156] Where μ and σ are the historical mean and standard deviation of compressive strength and shrinkage, respectively.

[0157] 4.3 Calculation of performance index deviation: Calculate the deviation between the actual test results and the expected performance index (such as designed compressive strength, maximum allowable shrinkage, etc.) as the basis for feedback adjustment. Assume that the expected compressive strength is f c,28_target , then the deviation Δf c,28 for:

[0158] Δf c,28 =f c,28_target -fc,28

[0159] 4.4 Feedback adjustment model: Proportional integral differential (PID) control algorithm is used to dynamically adjust production parameters according to the deviation and change trend of performance indicators. For mix ratio adjustment, the compressive strength deviation can be mapped to the adjustment amount of cement amount, water-binder ratio, etc. The specific formula is as follows:

[0160]

[0161] In the formula, X represents the production parameters that need to be adjusted (such as cement dosage), K P ,K I ,K D They are proportional, integral and differential coefficients, which need to be adjusted according to system characteristics and historical data.

[0162] 4.5 Parameter optimization and adjustment: According to the adjustment amount calculated by the PID algorithm, combined with the production experience limit (such as the upper and lower limits of the mix ratio), the mix ratio of the next production batch is fine-tuned. In addition, according to the shrinkage evaluation results, the type or amount of admixture is adjusted by a similar method to control the shrinkage.

[0163] Through the above design, the quality monitoring and feedback system can monitor the concrete performance in real time, quickly respond to deviations in production, and ensure that each batch of concrete can meet the design requirements. The application of PID algorithm makes the adjustment strategy more flexible and close to the actual production needs. The whole system is based on data-driven and continuously optimizes production parameters, effectively improving the production quality and efficiency of C60 high-strength concrete in desert environment.

[0164] The production control method of C60 high-strength concrete in desert environment provided by this application overcomes the temperature and humidity management problems caused by high temperatures in desert areas, thereby improving the quality and performance of concrete. The intelligent temperature control system dynamically adjusts the water temperature and pre-cools aggregates through refrigeration and ice cube placement combined with an algorithm; the raw material temperature monitoring network accurately monitors temperature and humidity through the fusion of sensors and algorithms; the dynamic adjustment algorithm of the mix ratio uses the concrete performance model and particle swarm optimization algorithm to automatically optimize the mix ratio under different environments; the quality feedback and optimization cycle system adjusts the production parameters in real time through the PID control algorithm to continuously improve the quality of concrete and production efficiency. This method ensures the quality and performance of high-strength concrete in desert environments and has broad application prospects and market value.

[0165] The above are only preferred embodiments of the present application and are not intended to limit the present application. For those skilled in the art, the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A method for controlling the production of C60 high-strength concrete in a desert environment, characterized in that: The following steps are involved: 1) Establish an intelligent temperature control system, through the algorithm prediction and dynamic adjustment of the intelligent temperature control system, combined with a refrigerator and / or an ice cube delivery device, so that the water temperature in summer is stably maintained at 25°C or below, and at the same time monitor and adjust the pre-cooling measures of aggregates and sand to achieve the preset temperature and humidity state of the raw materials; 2) Establishing a raw material temperature monitoring network, which is deployed at least in cement storage, aggregate yard and water treatment area, and collecting data in real time through the raw material temperature monitoring network to provide an accurate basis for temperature control strategy; 3) Establish a dynamic mix ratio adjustment algorithm: Based on the collected temperature and humidity data and combined with the concrete performance model, the mix ratio of cement, water, admixtures and aggregates is automatically adjusted to optimize the performance of concrete under different environmental conditions; 4) Conduct quality feedback and optimization cycles: Establish a quality monitoring system for the entire process from mixing to pouring, collect concrete performance data, feed it back to the algorithm model, and continuously optimize the production process and mix design.

2. The production control method of C60 high-strength concrete in desert environment according to claim 1 is characterized in that: The intelligent temperature control system adopts a temperature control optimization algorithm, the goal of which is to predict and maintain the preset temperature and humidity state of water and raw materials under given external environmental conditions. The algorithm framework is as follows: 1.1) Data input: current water temperature T w ; Target water temperature T wtarget =25℃; external environment temperature T env ; Actual temperature and humidity of aggregate and sand T agg ,T sand ,H agg ,H sand ; Expected ambient temperature change trend in the next few hours T envforecast ; 1.2) Historical data analysis: Learn the temperature and humidity change patterns based on historical data and use time series analysis to predict future temperature fluctuations; 1.3) Temperature control model establishment: For water temperature control, a dynamic model is constructed to describe the refrigerator power P cool , Ice cube quantity Q ice Relationship with water temperature changes; 1.4) Optimization algorithm: adopt model predictive control strategy, based on the prediction model, find the control strategy that minimizes the temperature difference in the future period; 1.5) Instruction output and execution: The CPU outputs at least one of a refrigerator power adjustment instruction, an ice cube placement instruction, and an aggregate sand precooling equipment start-stop instruction according to the optimization algorithm result; 1.6) Feedback and adjustment: Monitor the deviation between actual temperature and humidity and target values ​​in real time, and continuously fine-tune control parameters through closed-loop control to ensure that the system is stable in the optimal state.

3. The production control method of C60 high-strength concrete in desert environment according to claim 2 is characterized in that: The step 1.3) needs to consider the heat exchange principle and energy balance equation when constructing the dynamic model: Where k is the system cooling efficiency coefficient, c is the environmental influence coefficient on water temperature; the precooling of aggregate and sand is achieved by controlling air cooling and spray water volume W spray To adjust, calculate the precooling rate based on the material specific heat capacity and mass flow rate; The step 1.4) also includes setting a cost function, which includes minimizing energy consumption and the sum of squares of temperature differences: In the formula, w1, w2 are weight coefficients, N p is the prediction step length.

4. The method for controlling the production of C60 high-strength concrete in a desert environment according to any one of claims 1 to 3, characterized in that: The raw material temperature monitoring network achieves accurate data fusion through extended Kalman filtering, the isolation forest algorithm efficiently identifies data anomalies, and the genetic algorithm optimizes resource allocation. The establishment of the raw material temperature monitoring network includes: 2.1) Time synchronization algorithm: The network time protocol is used to ensure the time synchronization of all sensors and data collection nodes, ensuring the timing accuracy of the data; 2.2) Data fusion algorithm: At the CCU level, the Kalman filter algorithm is used to fuse the temperature and humidity data from different sensors to reduce noise and improve the credibility of the data; 2.3) Anomaly detection algorithm refinement: The anomaly detection algorithm based on machine learning isolation forest estimates the degree of isolation of data points by constructing random trees; 2.4) Genetic algorithms are used in resource optimization and scheduling. For the optimization of the intelligent temperature control system, the goal is to find the optimal control strategy, which includes the power of the refrigerator, the amount of ice cubes put in, and the operating time of the pre-cooling equipment, so as to minimize energy consumption while ensuring the temperature and humidity control effect.

5. The production control method of C60 high-strength concrete in desert environment according to claim 4 is characterized in that: The following steps are included when using the Kalman filter algorithm to fuse temperature and humidity data: For raw material temperature monitoring, assume that the state vector of each monitoring point is Include temperature Its rate of change over time T k , measurement vector z k Only the temperature T k Direct observation, the prediction and update steps of the extended Kalman filter are as follows: Prediction Steps: Where f is the nonlinear state transfer function, u k-1 is the control input, such as external environmental influences, F k is the Jacobian matrix, Q k is the process noise covariance matrix; Update steps: P k|k =(I-K k H k )P k|k-1 ; Where h is the nonlinear observation function, H k Its Jacobian matrix, R k is the observation noise covariance matrix.

6. The production control method of C60 high-strength concrete in desert environment according to claim 4, characterized in that: The following steps are included when refining the anomaly detection algorithm: Given a set of training data, the isolation forest algorithm calculates the average path length or path length score of each data point. For a new data point, its MHL or PLF is calculated. If it is significantly higher than the average value of the training data set, the point is considered to be abnormal. Let H(x) be the average path length of data point x, and the anomaly score is defined as: Where E(H(x)) is the expected value of the average path length of x, c(n) is a constant calculated based on the size of the data set n, and the closer s(x) is to 1, the more likely x is to be a normal data point; The closer it is to 0, the more likely it is an outlier; The following steps are included when using genetic algorithms for resource optimization scheduling: Let the decoded code be X = [P cool , Q ice , W spray ] T , where P cool is the refrigerator power, Q ice is the amount of ice cubes put in, W spray For the precooling spray water volume, the objective function (i.e. the minimization target) is defined as: In the formula, E total is the total energy consumption, w1, w2 are weight coefficients, N is the number of monitoring points, T i and are the actual temperature and target temperature of the i-th monitoring point respectively.

7. The method for controlling the production of C60 high-strength concrete in a desert environment according to any one of claims 1-3 or 5-6, characterized in that: The step 3) specifically comprises the following steps: 3.1) Data collection and preprocessing: The real-time temperature and humidity data of cement, water, aggregate and sand are collected through the raw material temperature monitoring network. After cleaning and correction, the data is converted into key parameters that have a direct impact on the performance of concrete, including the effective water-binder ratio. Aggregate moisture content correction; In the formula, is the nominal water-binder ratio, k is the temperature influence coefficient, T cement is the actual temperature of cement, T ref As the reference temperature, the formula can be fitted with historical data to obtain the k value, and its accuracy can be verified by data; 3.2) Establish a concrete performance prediction model based on regression analysis; 3.3) Using the particle swarm optimization algorithm as the basic framework, combined with the concrete performance model, automatically find the optimal mix ratio under the current environmental conditions. The particle swarm optimization algorithm simulates the foraging behavior of bird flocks to find the global optimal solution; 3.4) Implementation and feedback; including implementation adjustment, performance verification and feedback loop. Implementation adjustment: adjust the raw material ratio in actual production according to the optimal mix ratio obtained by the particle swarm optimization algorithm; Performance verification: perform performance tests on the adjusted concrete to verify the consistency between the model prediction and the actual performance; Feedback loop: continuously incorporate new data into model training to form a data-driven closed-loop iterative optimization process, and continuously improve the generalization ability of the model and the accuracy of mix ratio adjustment.

8. The production control method of C60 high-strength concrete in desert environment according to claim 7, characterized in that: The step 3.2) specifically includes the following steps: Considering the influence of main raw material ratio and environmental temperature and humidity on concrete performance, including compressive strength, workability and shrinkage, the model is expressed as: Y=f(C,W,A,S,T env ,H env )+∈; In the formula, (Y) represents a performance index of concrete, such as 28-day compressive strength, C, W, A, S represent the proportion of cement, water, aggregate, and sand, respectively, and T env , H env is the ambient temperature and humidity, ∈ is the random error term; Based on multiple linear regression analysis, the 28-day compressive strength of concrete is expressed as: In the formula, β i is the regression coefficient, is the sand ratio, T env and H env are the ambient temperature and humidity respectively, and the coefficient β i It can be determined by the least squares estimation of historical test data; The step 3.3) specifically comprises the following steps: Let the particle's position vector be X i =[C i , W i , A i , S i ], the velocity vector is (V i ), the optimization goal is to maximize the concrete performance index (Y); Initialization: Randomly generate an initial particle group, each particle represents a possible mix ratio; Iterative updates: X i，t+1 =X i，t +V i，t+1 ; In the formula, w is the inertia weight, c1, c2 are acceleration constants, r1, r2 are random numbers between [0, 1], and X gbest，t Represent the historical optimal position and current global optimal position of the i-th particle respectively; Mix ratio constraint processing: After each iteration, the constraint processing mechanism is applied to ensure the mix ratio of all particles, such as water-binder ratio Sand rate Fall within the permitted range of the specification; Algorithm termination condition: set the maximum number of iterations or reach a predetermined performance improvement threshold.

9. The method for controlling the production of C60 high-strength concrete in a desert environment according to any one of claims 1-3 or 5-6 or 8, characterized in that: The step 4) comprises the following steps: 4.1) Sample selection and testing: After each batch of concrete is produced, samples are taken from different parts according to standard procedures, and 28-day compressive strength tests and 7-day shrinkage rate evaluations are carried out under standard curing to ensure the representativeness and accuracy of the data; 4.2) Data standardization: pre-process the collected test data, including outlier removal and standardization, to ensure data availability; 4.3) Performance index deviation calculation: Calculate the deviation between the actual test results and the expected performance index as the basis for feedback adjustment; 4.4) Feedback adjustment model: Proportional integral differential control algorithm is used to dynamically adjust production parameters according to the deviation and change trend of performance indicators. For mix ratio adjustment, the compressive strength deviation is mapped to the adjustment amount of cement amount and water-binder ratio; 4.5) Parameter optimization and adjustment: Based on the adjustment amount calculated by the proportional-integral-differential algorithm and combined with the production experience limitations, fine-tune the mix ratio of the next production batch; based on the shrinkage rate evaluation results, adjust the type or amount of admixtures through similar methods to control the shrinkage rate.

10. The production control method of C60 high-strength concrete in desert environment according to claim 9, characterized in that: When preprocessing the collected test data, the compressive strength f c,28 And the shrinkage rate ε7, the standardized formula is expressed as: Where μ and σ are the historical mean and standard deviation of compressive strength and shrinkage, respectively; The expected performance indicators include the designed compressive strength and the maximum allowable shrinkage rate; assuming that the expected compressive strength is f c,28_target , then the deviation Δf c,28 for: Δf c,28 =f c,28_target -f c,28 ; The proportional-integral-differential control algorithm formula used in step 4.4) is: In the formula, X represents the production parameters that need to be adjusted, such as cement dosage, K P ,K I ,K D They are proportional, integral and differential coefficients, which need to be adjusted according to system characteristics and historical data.

Images