Artificial intelligence-based low-carbon solid waste cementitious material production control method and system

Abstract

The present invention discloses a production control method and system for low-carbon solid waste cementitious materials based on artificial intelligence, which relates to the field of production control technology. The method obtains historical production data and uses a machine learning algorithm to train a quality prediction model and a production process control variable data relationship prediction model respectively. By collecting target variable data that affects the production process in real time and inputting it into the two models, the corresponding prediction results are obtained respectively. The variable data is corrected in combination with the model output, and the optimal correction parameters are obtained according to the correction strategy database. The optimal correction parameters are converted into production equipment control parameters to achieve intelligent regulation of the production process. The method solves the problem of insufficient control accuracy in the production process of low-carbon solid waste cementitious materials, realizes accurate prediction and dynamic optimization of the production process, and effectively improves the quality stability and production efficiency of low-carbon solid waste cementitious materials.

Description

Technical Field

[0001] The present application relates to the field of production control technology, and in particular to a method and system for controlling the production of low-carbon solid waste cementitious materials based on artificial intelligence. Background Art

[0002] Low-carbon solid waste cementitious materials are widely used in fields such as construction and environmental protection, playing a particularly important role in solid waste treatment. A similar prior art technique is the Chinese patent publication number CN118192456A, which proposes an automatic glue addition method for film production. This method monitors and analyzes the production demand status parameters during the forage film production process to obtain a glue addition value, dynamically adjusting the glue addition parameters based on the glue addition value. Simultaneously, the glue quality status parameters, glue addition equipment status parameters, and ambient temperature during the current monitoring period during the forage film production process are analyzed to obtain a glue addition influence coefficient, which is then used to analyze the calibrated glue addition value. This ensures that the glue addition effect during the production process is consistent with actual demand, reducing over- or under-addition. Furthermore, it helps to promptly detect and correct glue addition value deviations caused by factors such as glue quality, glue addition equipment, and ambient temperature, thereby automatically adjusting glue addition parameters, improving production efficiency and product quality, and achieving intelligent production. In addition, similar prior art includes a Chinese patent with publication number CN107291039A, which proposes a method for automatic batching control of rubber powder. The method is implemented by hardware and software. The software is installed in a PLC controller system. The hardware includes several powder feeding devices, several colloid feeding devices and an air compressor. The discharge ports of each device are concentrated together, and a container cup is provided at the lower end of the discharge port, and the container cup is placed on a precision weighing instrument; the powder feeding device is connected to the PLC controller, and the PLC controller controls the feeding speed, vibration frequency, motor speed, and operating voltage of the powder feeding device through the weight feedback information measured by the precision weighing instrument, and achieves precise proportioning, thereby improving the accuracy and repeatability of the batching, and can be mechanically operated in a closed environment, which can effectively ensure that the raw materials will not cause product quality problems due to the humid environment. Although the technical solutions in the above two patent documents solve the problem of adding or mixing materials during the production process, they do not take into account that when liquid admixtures are directly added to the cementitious material, problems such as uneven dispersion and agglomeration are likely to occur, resulting in unstable material properties during the production process, which can easily cause quality problems. Summary of the Invention

[0003] The present application provides an artificial intelligence-based low-carbon solid waste cementitious material production control method and system, which is used to achieve precise adjustment of various control variables during the production process of low-carbon solid waste cementitious materials, effectively improving production efficiency, reducing errors and substandard products in the production process, and ensuring the quality stability and sustainable production of cementitious materials through intelligent control and correction schemes. The method includes:

[0004] Obtaining historical production data, training a first model based on historical target variable data and corresponding quality data in the historical production data using a machine learning algorithm, and training a second model based on the historical target variable data;

[0005] collecting target variable data that affects production quality in real time, inputting the target variable data into the first model and the second model, and obtaining a first prediction result and a second prediction result respectively;

[0006] Obtaining the number of difference variables from the second prediction result and the target variable data, determining whether the second model needs secondary training based on the number, and training the second model if necessary;

[0007] Correcting the target variable data according to the second prediction result and the second model, obtaining and inputting the correction data into the first model, obtaining a third prediction result, and obtaining optimal correction parameters according to the third prediction result, the correction data, and a correction strategy database;

[0008] The output information of the production equipment is adjusted based on the optimal correction parameters.

[0009] As a preferred technical solution of the present invention, the training of the second model includes:

[0010] The historical target variable data is used as the second sample data, and the second model is trained by the second sample data. The second model learns the correlation between the historical target variable data through a machine learning algorithm, extracts key information from the historical target variable data, encodes the key information, and restores the historical target variable data based on the encoded key information and the learned correlation between the historical target variable data.

[0011] As a preferred technical solution of the present invention, the correction of the target variable data includes:

[0012] Comparing the second prediction result with the input target variable data one by one, obtaining the variable difference corresponding to each variable data, taking the variables whose variable difference is greater than a set threshold as difference variables, and counting the number of the difference variables;

[0013] When the difference variable does not exist in the target variable data, the target variable data does not need to be corrected. When the number of the difference variables is less than the first set number, the target variable data excluding the difference variables is input into the second model to obtain a prediction variable data group. The numerical value of the difference variable in the target variable data is replaced by the numerical value corresponding to the difference variable in the prediction variable data group, and the target variable data after replacement is used as the correction data.

[0014] As a preferred technical solution of the present invention, determining whether the second model needs secondary training includes:

[0015] When the number of difference variables is greater than the second set number and the first prediction result is normal, the target variable data is used as the data to be learned, multiple groups of the data to be learned are continuously collected and added to the second sample data corresponding to the second model, and the second model is retrained based on the second sample data.

[0016] As a preferred technical solution of the present invention, the acquisition of the optimal correction parameters includes:

[0017] If there is no difference variable in the target variable data or the target variable data has been corrected, input the first model to obtain the first prediction result, and compare the first prediction result with the quality standard to obtain a comparison result;

[0018] When the comparison result is less than or equal to the set value, the quality is qualified; when the comparison result is greater than the set value, the quality is unqualified, and based on the input data of the first prediction result, a variable data set whose similarity with the target variable data and the first prediction result is greater than a preset similarity is searched in the correction strategy database, and the control parameters corresponding to the target variable data are corrected according to the correction strategy corresponding to each variable combination in the variable data set to obtain the correction parameters, and the correction parameters are input into the first model to obtain a third prediction result, and the correction parameters corresponding to the third prediction result closest to the quality standard are used as the optimal correction parameters.

[0019] As a preferred technical solution of the present invention, the target variable data at least includes the spray amount and spray speed of the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment.

[0020] As a preferred technical solution of the present invention, the quality data at least includes the compressive strength and stability of the low-carbon solid waste cementitious material.

[0021] The present invention also provides an artificial intelligence-based production control system for low-carbon solid waste cementitious materials, which is used to implement the above method. The system includes:

[0022] a training unit, configured to obtain historical production data, train a first model based on historical target variable data and corresponding quality data in the historical production data through a machine learning algorithm, and train a second model based on the historical target variable data;

[0023] a prediction unit, configured to collect target variable data affecting production quality in real time, input the target variable data into the first model and the second model, and obtain a first prediction result and a second prediction result, respectively;

[0024] a judging unit, configured to obtain a number of difference variables from the second prediction result and the target variable data, determine whether the second model needs secondary training based on the number, and train the second model if necessary;

[0025] a correction unit, configured to correct the target variable data according to the second prediction result and the second model, obtain and input the correction data into the first model, obtain a third prediction result, and obtain an optimal correction parameter according to the third prediction result, the correction data, and a correction strategy database;

[0026] A control unit is used to control output information of the production equipment based on the optimal correction parameters.

[0027] The present invention also provides a computer-readable storage medium having instructions stored thereon, and the above-mentioned method is implemented when the instructions are executed by a processor.

[0028] The present invention provides accurate prediction capabilities for the production process through a quality prediction model trained by a machine learning algorithm and a production process control variable data relationship prediction model. These models can analyze and predict the relationship between multiple variable data that affect production quality, enabling real-time adjustments to the production process to ensure that the final product quality meets the predetermined standards. This technical solution avoids quality fluctuations caused by fluctuations in dependent variables through multiple predictions and optimization control, thereby improving production stability. Secondly, the system collects target variable data that affects production quality in real time and inputs this data into the trained prediction model to obtain prediction results. By comparing the predicted results with the actual data, the system can promptly detect deviations and make corrections. The corrected data is re-input into the model to further improve the prediction accuracy, thereby achieving dynamic optimization and precise control in the production process. This closed-loop control mechanism effectively avoids quality fluctuations caused by equipment performance aging or environmental changes, improving production consistency and stability. In addition, the present invention dynamically adjusts variable data through a correction strategy database. When the predicted results do not meet the quality standards, the system can automatically select the optimal correction parameters based on similar situations in historical data and make real-time adjustments to the production equipment. Through this automated adjustment process, the complexity of human intervention is reduced, and the efficiency of the production process and the response speed of quality control are improved. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0030] Figure 1 Flowchart of the artificial intelligence-based low-carbon solid waste cementitious material production control method in the embodiment;

[0031] Figure 2 Flowchart of the method for correcting target variable data in the embodiment;

[0032] Figure 3 Flowchart of a method for obtaining the optimal correction parameters in an embodiment;

[0033] Figure 4 This is a structural diagram of the artificial intelligence-based low-carbon solid waste cementitious material production control system in the embodiment. DETAILED DESCRIPTION

[0034] The embodiments of the present application provide a method and system for controlling the production of low-carbon solid waste cementitious materials based on artificial intelligence. The terms "first", "second", "third", "fourth", etc. (if any) in the specification and claims of this application and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms "including" or "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or apparatus that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or that are inherent to these processes, methods, products or apparatus.

[0035] For ease of understanding, the specific process of the embodiment of the present application is described below. An embodiment of the production control method of low-carbon solid waste cementitious materials based on artificial intelligence in the embodiment of the present application is as follows: Figure 1 Shown, including:

[0036] Step S1: Acquire historical production data, train a first model based on historical target variable data and corresponding quality data in the historical production data through a machine learning algorithm, and train a second model based on the historical target variable data;

[0037] Specifically, in the production process of low-carbon solid waste cementitious materials, when liquid admixtures are directly added to cementitious materials, problems such as uneven dispersion and agglomeration are prone to occur, resulting in unstable material properties during the production process, which can easily cause quality problems. Therefore, in order to ensure its uniform distribution and thus improve the quality and production stability of cementitious materials, atomizing devices are widely used in the dispersion of liquid admixtures, and the spray volume and spray speed of the atomizing device corresponding to the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment are used as target variables, and the compressive strength and stability of the cementitious materials are used as quality data. ， By obtaining historical target variable data and corresponding quality data, the first model and the second model are trained using a machine learning algorithm. The first model is a quality prediction model, which learns the relationship between quality data and historical target variables in the production process based on historical data. The second model: a historical target variable data relationship prediction model for the production process, establishes the correlation between target variables by learning historical target variable data in historical production data. By training these two models, accurate first and second models can be established based on historical data, providing reference and basis for subsequent production control, and ensuring accurate modeling of the relationship between target variables in the production process and the quality of the final product.

[0038] Step S2: collecting target variable data that affects production quality in real time, inputting the target variable data into the first model and the second model, and obtaining a first prediction result and a second prediction result respectively;

[0039] Specifically, by real-time monitoring of multiple target variable data in the production process, these real-time data are automatically input into the first and second models to obtain the first prediction result, i.e., the production quality predicted based on the quality prediction model, and the second prediction result, i.e., the historical target variable relationship predicted based on the historical control variable data relationship model. The above technical solution can reflect the changes in target variables in the production process in real time, and the real-time prediction can provide effective information for subsequent data correction and adjustment, thereby improving the intelligence level of the production process.

[0040] Step S3: obtaining the number of difference variables from the second prediction result and the target variable data, determining whether the second model needs secondary training based on the number, and training the second model if necessary;

[0041] Specifically, based on the second prediction result and the actual collected target variable data, the system will compare the data difference of each variable to determine whether there are significant differences: Difference variables: If the data difference of a variable exceeds the set threshold, it is considered a difference variable. Number of difference variables: The number of difference variables is counted, and based on the number, it is determined whether the second model needs to be trained again. The above technical solution ensures the accuracy of the target variable data. When there are large deviations in the target variable data, they can be discovered and corrected in a timely manner. When the number of difference variables is large, it is determined whether the model needs to be updated, that is, retrained, to ensure that the model always adapts to changes in production and further improves the accuracy of prediction and control.

[0042] Step S4: Correcting the target variable data according to the second prediction result and the second model, obtaining and inputting the correction data into the first model, obtaining a third prediction result, and obtaining optimal correction parameters according to the third prediction result, the correction data, and the correction strategy database;

[0043] Specifically, the system will re-input the corrected target variable data into the first model to obtain the third prediction result. At the same time, the system will retrieve historical correction data similar to the third prediction result from the correction strategy database and extract the best correction parameters from it. The correction strategy database contains historical data of different production variables and correction measures. It can find a suitable adjustment strategy for the current production process based on similarity. It can also select the optimal correction parameters based on the quality prediction results and the correction strategy database and input them into the production equipment to adjust the actual production process. Through the above technical solution, the output information of the production equipment can be accurately adjusted to ensure that each variable in the production process can be as close to the predetermined target as possible. Automated adjustment optimizes the production process, reduces human intervention, and improves production efficiency and product quality stability.

[0044] Step S5: adjusting the output information of the production equipment based on the optimal correction parameters.

[0045] Specifically, based on the optimal correction parameters obtained in step S4, the system transmits the corrected control parameters to the production equipment to adjust the operations in the production process, such as the dispersion of the liquid admixture, and the spray amount and spray speed of the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment to ensure that the production quality meets the target requirements. The above technical solution ensures that the quality control in the production process is always in the best state by adjusting the control parameters of the production equipment in real time. By automatically obtaining the optimal correction parameters and controlling the equipment, manual intervention is reduced, and production efficiency and quality consistency are improved.

[0046] Furthermore, the training of the second model includes:

[0047] The historical target variable data is used as the second sample data, and the second model is trained by the second sample data. The second model learns the correlation between the historical target variable data through a machine learning algorithm, extracts key information from the historical target variable data, encodes the key information, and decodes the key information based on the encoded key information and the learned correlation between the historical target variable data to reconstruct the historical target variable data.

[0048] Specifically, in the production process of low-carbon solid waste cementitious materials, when liquid admixtures are directly added to cementitious materials, problems such as uneven dispersion and agglomeration are likely to occur, resulting in unstable material properties during the production process, which can easily cause quality problems. Therefore, in order to be able to timely adjust the above-mentioned related variables that affect quality problems, that is, the above-mentioned historical target variable data, the correlation between the quality data and the related variable data in the historical production data is learned based on the machine learning algorithm to establish a first model for predicting quality, wherein the above-mentioned quality data at least includes the compressive strength and stability of the low-carbon solid waste cementitious materials, and the above-mentioned related variable data at least includes the spray amount and spray speed of the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment, effectively realizing the accurate prediction and dynamic optimization of the quality in the production process, and ensuring the quality stability of the cementitious material production. Under the premise of the stable production quality of the above-mentioned low-carbon solid waste cementitious materials, there is also a certain correlation between the above-mentioned historical target variable data. The production quality is guaranteed by the mutual adaptation between the above-mentioned historical target variable data. Therefore, the historical target variable data in the above-mentioned historical production data is analyzed by the above-mentioned second model. The relationship between the quantity data is learned, and the correlation rules between the target variables are learned. In the training process of the above-mentioned second model, key information is first extracted from the above-mentioned historical target variable data. The above-mentioned key information is the N data ranked top in terms of the impact on the above-mentioned production quality. They are encoded and decoded based on the encoded key information and the correlation between the learned historical target variable data. The decoded data is used as the output data of the above-mentioned second model. By comparing the input data and output data of the above-mentioned second model, it can be judged whether the input data is accurate. When the input data of the above-mentioned second model does not completely include the above-mentioned target variable data, the missing variables in the input data are predicted by the learned correlation between the above-mentioned variables, and the complete predicted target variable data is output. Through the above-mentioned technical solution, it is possible to judge whether the target variable data input by the above-mentioned first model is accurate through the second model, thereby avoiding the deterioration of quality prediction accuracy due to inaccurate collection of the above-mentioned target variable data in the production process, improving the accurate prediction and dynamic optimization of production quality in the production process, ensuring the quality stability of cementitious material production, and also laying the foundation for optimizing the above-mentioned target variable data.

[0049] Furthermore, the correction of the target variable data, such as Figure 2 Shown, including:

[0050] Comparing the second prediction result with the input target variable data one by one, obtaining the variable difference corresponding to each variable data, taking the variables whose variable difference is greater than a set threshold as difference variables, and counting the number of the difference variables;

[0051] When the difference variable does not exist in the target variable data, the target variable data does not need to be corrected. When the number of the difference variables is less than the first set number, the target variable data excluding the difference variables is input into the second model to obtain a prediction variable data group. The numerical value of the difference variable in the target variable data is replaced by the numerical value corresponding to the difference variable in the prediction variable data group, and the target variable data after replacement is used as the correction data.

[0052] Specifically, during the production of low-carbon solid waste cementitious materials, as equipment performance is lost or aged, resulting in performance changes or changes in the production environment, the control parameters, i.e., the output of the equipment corresponding to the above-mentioned target variable data, may deviate from the preset standards, resulting in unstable or unpredictable production quality. Traditional control methods are difficult to accurately adjust multiple variables in real time, especially when the production quality is about to become abnormal. Failure to make effective corrections in time will lead to fluctuations in production quality. For example, when the spray volume and spray speed of the liquid admixture by the atomizing device do not match the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment, the production quality will be unqualified. Therefore, by inputting the above-mentioned target variable data collected in real time into the above-mentioned first model and the second model respectively, and obtaining the above-mentioned first prediction result and the above-mentioned second prediction result respectively, wherein the data type of the above-mentioned target variable data is the same as that of the above-mentioned historical target variable data, each variable data in the above-mentioned second prediction result is compared with each variable data corresponding to the above-mentioned multiple variables, and the variable data corresponding to each variable is obtained. When the difference between the variables corresponding to each of the above variables is less than or equal to the set threshold, that is, the above does not exist, indicating that the correlation relationship between the above target variable data is satisfied and no correction is required; the variables in the above target variables whose corresponding difference between the variables is greater than the set threshold are taken as the above difference variables, that is, the variables with deviations. When the number of the above difference variables is less than the first set number, the first set number is 2, that is, when there is a deviation in the above target variable data, the second model can output the prediction variable data group with the highest similarity based on the remaining variable data after eliminating the difference variables in the target variable data, and replace the difference variable values ​​in the above target variable data with the values ​​corresponding to the above abnormal variables in the above prediction variable data group, and use the replaced target variable data as the above correction data. The above technical solution, through the mutual cooperation of the first model and the second model, can not only verify the accuracy of the above target variable data, but also correct the above target variable data, thereby further improving the accuracy of the prediction results of the above second model.

[0053] Furthermore, determining whether the second model needs secondary training includes:

[0054] When the number of difference variables is greater than or equal to the second set number and the first prediction result is normal, the target variable data is used as the data to be learned, multiple groups of the data to be learned are continuously collected and added to the second sample data corresponding to the second model, and the second model is retrained based on the second sample data.

[0055] Specifically, when the above-mentioned difference variable data is greater than or equal to the above-mentioned first set number and less than the above-mentioned second set number, it is possible that the data collected by the above-mentioned sensor acquisition unit is erroneous. At this time, the first prediction result output by inputting the above-mentioned target variable data into the first model cannot be guaranteed to be accurate, and due to the large number of variables, it cannot be accurately corrected by the above-mentioned second model. Therefore, it is possible to send a fault code or early warning information to the user terminal to conduct timely maintenance or stop production to prevent quality problems from occurring. However, when the above-mentioned difference variable number is greater than or equal to the above-mentioned second set number, wherein the above-mentioned second set number is 50% of the total number of the above-mentioned target variable data types and is rounded, and when the above-mentioned first prediction result is normal, it is possible that with the changes in the environment and the fluctuations in equipment performance during the production process, the above-mentioned target variable data may have large The difference between the first model and the second model is not updated synchronously or the second model is not updated in time during the production process, resulting in some production modes or production parameter combinations in the production not being learned by the second model, making the reconstruction result of the input target variable data in the second model quite different from the input data. Therefore, the target variable data is used as the data to be learned, and multiple groups of the data to be learned are collected and added to the second sample data corresponding to the second model, and the second model is trained for the second time. The model after the second training will be able to better learn the relationship between the new control variables and better cooperate with the first model, thereby improving the prediction ability of production quality. Through more accurate prediction, more precise control parameters can be provided for the production process to ensure the achievement of quality standards.

[0056] Furthermore, the acquisition of the optimal correction parameters is as follows: Figure 3 Shown, including:

[0057] If there is no difference variable in the target variable data or the target variable data has been corrected, input the first model to obtain the first prediction result, and compare the first prediction result with the quality standard to obtain a comparison result;

[0058] When the comparison result is less than or equal to the set value, the quality is qualified; when the comparison result is greater than the set value, the quality is unqualified, and based on the first prediction result and the corresponding input target variable data, a variable data set with a similarity greater than a preset similarity is searched in the correction strategy database, and the target variable data is corrected according to the correction strategy corresponding to each variable combination in the variable data set to obtain correction parameters, and the correction parameters are input into the first model to obtain a third prediction result, and the correction parameters corresponding to the third prediction result closest to the quality standard are used as the optimal correction parameters.

[0059] Specifically, since the target variable data or correction data without difference variables conform to the correlation between variables, when the first model is input, the accurate first prediction result can be obtained. By comparing the first prediction result with the quality standard, it is determined whether the current production quality is qualified. If there is a large difference between the first prediction result and the quality standard, that is, the prediction result does not meet the set quality standard, since multiple variables are interrelated, the unqualified production quality is the result of the interaction between multiple variables. It is difficult to determine which specific control parameter of the equipment to adjust to improve the production quality. Therefore, historical data with a high similarity to the current prediction result is searched from the database, and the corresponding correction strategy is extracted. The correction strategy database contains the target variable data set, corresponding quality data and correction strategy in the historical production process. These data sets are associated with various quality deviations, control strategies and correction parameters in the production process. , according to the correction strategy corresponding to the variable group with a high similarity to the current target variable data and the first prediction result, i.e., the predicted quality data in the database, the control parameters of the current equipment are corrected, and the correction parameters, i.e., the above-mentioned target variable data output by the production equipment after correction, are simulated and re-input into the above-mentioned first model to obtain the above-mentioned third prediction result. The above-mentioned correction strategy at least includes adjusting the spray volume, spray speed, stirring speed, stirring time, mixing uniformity and material temperature, and the above-mentioned correction parameters corresponding to the third prediction result closest to the above-mentioned quality standard are used as the above-mentioned optimal correction parameters. The above-mentioned technical solution can automatically select the most appropriate correction parameters through the correction strategy database, reduce the tedious steps of manual adjustment, improve production efficiency and the response speed and accuracy of quality control, ensure that the quality of the cementitious material meets the quality standards, reduce quality fluctuations, production downtime and the occurrence of unqualified products, and improve overall production efficiency.

[0060] Furthermore, the target variable data at least include the spray amount and spray speed of the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment.

[0061] Furthermore, the quality data at least includes the compressive strength and stability of the low-carbon solid waste cementitious material.

[0062] Specifically, the above-mentioned compressive strength and stability are both measured and quantified data. For example, the compressive strength and stability can be divided into multiple levels respectively to quantify the compressive strength and stability of the low-carbon solid waste cementitious material.

[0063] The present invention also provides a production control system for low-carbon solid waste cementitious materials based on artificial intelligence, which is used to implement the above method, such as Figure 4 As shown, the system includes:

[0064] a training unit, configured to obtain historical production data, train a first model based on historical target variable data and corresponding quality data in the historical production data through a machine learning algorithm, and train a second model based on the historical target variable data;

[0065] a prediction unit, configured to collect target variable data affecting production quality in real time, input the target variable data into the first model and the second model, and obtain a first prediction result and a second prediction result, respectively;

[0066] a judging unit, configured to obtain a number of difference variables from the second prediction result and the target variable data, determine whether the second model needs secondary training based on the number, and train the second model if necessary;

[0067] a correction unit, configured to correct the target variable data according to the second prediction result and the second model, obtain and input the correction data into the first model, obtain a third prediction result, and obtain an optimal correction parameter according to the third prediction result, the correction data, and a correction strategy database;

[0068] A control unit is used to control output information of the production equipment based on the optimal correction parameters.

[0069] The present invention also provides a computer-readable storage medium having instructions stored thereon, and the above-mentioned method is implemented when the instructions are executed by a processor.

[0070] In summary, the present invention provides accurate prediction capabilities for the production process through the quality prediction model trained by the machine learning algorithm and the production process control variable data relationship prediction model. These models can analyze and predict the relationship between multiple variable data that affect production quality, so that the production process can be adjusted in real time, thereby ensuring that the final product quality meets the predetermined standards. This technical solution avoids quality fluctuations caused by dependent variable fluctuations through multiple predictions and optimization control, thereby improving production stability. Secondly, the system collects target variable data that affect production quality in real time and inputs these data into the trained prediction model to obtain prediction results. By comparing the predicted results with the actual data, the system can promptly detect deviations and make corrections. The corrected data will be re-input into the model to further improve the accuracy of the prediction, thereby achieving dynamic optimization and precise control in the production process. This closed-loop control mechanism effectively avoids quality fluctuations caused by equipment performance aging or environmental changes, and improves production consistency and stability. In addition, the present invention dynamically adjusts variable data through a correction strategy database. When the predicted results do not meet the quality standards, the system can automatically select the optimal correction parameters based on similar situations in historical data and make real-time adjustments to the production equipment. Through this automated adjustment process, the complexity of human intervention is reduced, and the efficiency of the production process and the response speed of quality control are improved.

[0071] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the above-described systems, systems and units can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0072] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk, and other media that can store program code.

[0073] As described above, the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A production control method for low-carbon solid waste cementitious materials based on artificial intelligence, characterized in that: The method comprises: Obtain historical production data, train a first model based on historical target variable data and corresponding quality data in the historical production data through a machine learning algorithm, and train a second model based on the historical target variable data, wherein the training of the second model includes: analyzing the mutual relationship between the historical target variable data in the historical production data, learning the association rules between the target variables, and in the training process of the second model, first extracting key information from the historical target variable data, where the key information is N data ranked top in terms of production quality impact, and encoding the key information, decoding the encoded key information based on the correlation between the learned historical target variable data, and using the decoded data as output data of the second model; collecting target variable data that affects production quality in real time, inputting the target variable data into the first model and the second model, and obtaining a first prediction result and a second prediction result respectively; Comparing the second prediction result with the input target variable data one by one, obtaining the variable difference corresponding to each variable data, taking the variables whose variable difference is greater than a set threshold as difference variables, and counting the number of the difference variables; When the difference variable does not exist in the target variable data, the target variable data does not need to be corrected; when the number of the difference variables is less than a first set number, the remaining variable data of the target variable data excluding the difference variables is input into the second model to obtain a prediction variable data group, and the values ​​corresponding to the difference variables in the prediction variable data group are replaced with the values ​​of the difference variables in the target variable data, and the target variable data after replacement is used as correction data; When the number of difference variables is greater than the second set number and the first prediction result is normal, the target variable data is used as the data to be learned, multiple groups of data to be learned are continuously collected and added to the second sample data corresponding to the second model, and the second model is retrained based on the second sample data; If there is no difference variable in the target variable data or the target variable data has been corrected, input the first model to obtain a first prediction result, and compare the first prediction result with the quality standard to obtain a comparison result; When the comparison result is less than or equal to the set value, the quality is qualified; when the comparison result is greater than the set value, the quality is unqualified, and based on the input data of the first prediction result, a variable data set having a similarity greater than a preset similarity with the target variable data and the first prediction result is searched in the correction strategy database, and the control parameters corresponding to the target variable data are corrected according to the correction strategy corresponding to each variable combination in the variable data set to obtain the correction parameters, and the correction parameters are input into the first model to obtain a third prediction result, and the correction parameters corresponding to the third prediction result closest to the quality standard are used as the optimal correction parameters; The output information of the production equipment is adjusted based on the optimal correction parameters.

2. The method according to claim 1, characterized in that The training of the second model includes: The historical target variable data is used as the second sample data, and the second model is trained by the second sample data. The second model learns the correlation between the historical target variable data through a machine learning algorithm, extracts key information from the historical target variable data, encodes the key information, and restores the historical target variable data based on the encoded key information and the learned correlation between the historical target variable data.

3. The method according to claim 1, characterized in that The target variable data at least include the spray amount and spray speed of the liquid admixture and the stirring speed, stirring time, mixing uniformity and material temperature of the stirring equipment.

4. The method according to claim 1, wherein The quality data at least include the compressive strength and stability of the low-carbon solid waste cementitious material.

5. A production control system for low-carbon solid waste cementitious materials based on artificial intelligence, used to implement the method according to any one of claims 1 to 4, characterized in that: The system comprises: a training unit, configured to obtain historical production data, train a first model based on historical target variable data and corresponding quality data in the historical production data through a machine learning algorithm, and train a second model based on the historical target variable data; a prediction unit, configured to collect target variable data affecting production quality in real time, input the target variable data into the first model and the second model, and obtain a first prediction result and a second prediction result, respectively; a judging unit, configured to obtain the number of difference variables from the second prediction result and the target variable data, determine whether the second model needs secondary training based on the number, and train the second model if necessary; a correction unit, configured to correct the target variable data according to the second prediction result and the second model, obtain and input the correction data into the first model, obtain a third prediction result, and obtain an optimal correction parameter according to the third prediction result, the correction data, and a correction strategy database; A control unit is used to control output information of the production equipment based on the optimal correction parameters.

6. A computer-readable storage medium having instructions stored thereon, characterized in that: When the instructions are executed by a processor, the method according to any one of claims 1 to 4 is implemented.

Images