A concrete whole-process production management method, system, terminal and storage medium

Abstract

The application belongs to the technical field of concrete production, and particularly relates to a concrete whole-process production management method, system, terminal and storage medium, wherein the method comprises the following steps: collecting temperature time series data of concrete in a mixing process by using a temperature sensor; based on the temperature time series data and basic data, a digital twin of a concrete hydration reaction is constructed, and the digital twin is used to predict the hydration degree, compressive strength and slump change trend of the concrete in real time; in the process of transporting the concrete, the digital twin is used to dynamically predict the slump of the concrete when the concrete reaches a construction site, in combination with the real-time acquired transportation duration and environmental temperature data. The concrete whole-process production management method, system, terminal and storage medium of the application construct a concrete production management system capable of real-time sensing, accurate prediction, intelligent decision-making and closed-loop optimization by deeply fusing a physical and chemical mechanism model and an advanced data-driven model.

Description

Technical Field

[0001] This invention belongs to the field of concrete production technology, and in particular relates to a method, system, terminal and storage medium for the whole process of concrete production management. Background Technology

[0002] As the world's most widely used building material, concrete's production and quality control directly impact the safety, durability, and economic benefits of construction projects. Traditional concrete production management relies heavily on manual experience and paper records, resulting in problems such as delayed information transmission, severe data silos, and passive quality control. In recent years, with the rapid development of information technology, the construction industry has begun to introduce various production management systems (such as ERP and MES) in an attempt to improve the shortcomings of traditional concrete production management through electronic and networked means. These systems have, to some extent, achieved the recording of production processes, the collection of data, and the generation of reports, improving management efficiency. However, in-depth analysis of existing technical solutions reveals a core technical bottleneck: most of these systems remain at the level of "process digitization" and "data visualization," lacking a deep understanding of the core physicochemical processes of concrete, a complex material system, and the ability to make intelligent decisions.

[0003] The strength development and temperature changes of concrete are key indicators for measuring its internal hydration process. However, existing systems cannot acquire this data in real time and still rely on later laboratory testing. Especially during the concrete transportation and pouring stages, the slump loss (a core indicator of concrete workability) is a complex process influenced by various factors such as transportation time, ambient temperature, humidity, and mixing conditions. In related technologies, existing systems lack effective predictive models and cannot anticipate the combined impact of these factors on slump loss. This often results in concrete mixer trucks arriving at the construction site with workability that does not meet pouring requirements, severely impacting construction quality and efficiency, and causing significant material waste. Summary of the Invention

[0004] In view of this, the present invention aims to propose a method, system, terminal and storage medium for the whole process production management of concrete, so as to solve the problem that the existing concrete production management lacks in-depth perception and intelligent decision-making ability of the core physical and chemical processes of concrete, which affects the quality of concrete.

[0005] To achieve the above objectives, the technical solution of the present invention is implemented as follows: In a first aspect, the present invention provides a method for managing the entire process of concrete production, comprising: Configure the basic data required for concrete production, and generate a concrete production plan based on the basic data, including the pouring location, planned volume, and mix proportion; wherein, the basic data includes engineering structure information, concrete design strength and mix proportion, raw material information, and construction environment parameters; Concrete mixing and production are carried out according to the concrete production plan, and temperature sensors are pre-embedded in the concrete mixture to collect temperature time-series data of the concrete during the mixing process. Based on the temperature time series data and the basic data, a digital twin of the concrete hydration reaction is constructed, and the digital twin is used to predict the changes in the degree of hydration, compressive strength and slump of concrete in real time. During concrete transportation, real-time transportation time and ambient temperature data are acquired. Using the digital twin, combined with the real-time transportation time and ambient temperature data, the slump of the concrete upon arrival at the construction site is dynamically predicted. If the predicted slump is lower than the preset lower limit of the pouring requirement, based on the prediction results of the digital twin, process parameter adjustment instructions are dynamically generated. These instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. The process parameter adjustment command is fed back to the concrete transportation system to execute the adjustment operation; After the concrete is poured, the compressive strength data of the standard curing specimens are collected, compared and analyzed with the prediction results of the digital twin, a prediction error report is generated, and the error report is fed back to the digital twin to optimize the model parameters.

[0006] Furthermore, the step of constructing a digital twin of the concrete hydration reaction based on the temperature time-series data and the basic data, and using the digital twin to predict the changes in the degree of hydration, compressive strength, and slump of concrete in real time, includes: Based on the physicochemical principles of cement hydration reaction, a mechanistic model describing the relationship between hydration degree, strength development, and temperature is established; wherein, the mechanistic model includes a temperature-hydration rate relationship model based on the Arrhenius equation and a maturity method strength prediction model based on the hydration degree-strength relationship model. A data-driven model for predicting slump loss over time was established using machine learning algorithms, based on historical production data, experimental data, and real-time temperature time-series data. The mechanistic model and the data-driven model are fused to form a hybrid digital twin; wherein the mechanistic model is used to predict hydration degree and compressive strength, the data-driven model is used to predict slump change trend, and real-time collected temperature time series data is used as a bridge connecting the two models to achieve collaborative prediction and correction.

[0007] Furthermore, during concrete transportation, real-time data on transportation time and ambient temperature are acquired. Using the digital twin, combined with this data, the slump of the concrete upon arrival at the construction site is dynamically predicted. If the predicted slump is lower than the preset lower limit for pouring requirements, based on the prediction results of the digital twin, dynamic adjustments to process parameters are generated. These adjustments include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. During the concrete transportation process, real-time data on transportation time and ambient temperature are acquired. The real-time acquired transportation time and ambient temperature data are input into the data-driven model of the digital twin; The data-driven model, based on the input real-time data and combined with the initial slump and mix proportion information of the concrete, predicts the slump value of the concrete at any future time. The estimated arrival time of concrete at the construction site is determined, and the predicted slump of the concrete upon arrival is calculated based on the estimated arrival time. If the predicted slump is lower than the preset lower limit of the pouring requirement, the process parameter adjustment instructions are dynamically generated based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transport speed.

[0008] Furthermore, the dynamically generated process parameter adjustment instructions include: Construct an intelligent decision-making model based on preset rules or optimization algorithms to determine the optimal process parameter adjustment strategy; When the predicted slump is lower than the preset lower limit of the pouring requirement, the decision model calculates the optimal combination of adjustment strategies based on the current concrete state, remaining transportation time, ambient temperature, and a preset adjustment rule library. The combination of adjustment strategies includes adjustments to the dosage of retarder, water-reducing agent, mixing speed, and transportation speed. The optimal adjustment strategy is then converted into specific, executable process parameter adjustment instructions.

[0009] Furthermore, the step of feeding back the process parameter adjustment command to the concrete transportation system and executing the adjustment operation includes: The process parameter adjustment command is sent to the concrete transport vehicle in the concrete transport system via a wireless communication network; wherein, after receiving the process parameter adjustment command, the on-board terminal on the concrete transport vehicle controls the admixture addition device, the mixing drum drive motor or the vehicle power system to perform the corresponding adjustment operation.

[0010] Furthermore, after the concrete pouring is completed, the compressive strength data of the standard curing specimens are collected, compared and analyzed with the prediction results of the digital twin, a prediction error report is generated, and the error report is fed back to the digital twin for optimizing the model parameters, including: After the concrete is poured, standard specimens are made and cured according to national standard methods, and compressive strength tests are conducted at the specified age to obtain actual compressive strength data. The actual compressive strength data is compared with the predicted strength values ​​of the digital twin at the corresponding age, and the prediction error is calculated. Perform statistical analysis on the prediction error to generate a prediction error report that includes the magnitude, distribution, and trend of the error; The prediction error report is used as a feedback signal and input into the model training algorithm of the digital twin. The undetermined coefficients in the mechanistic model or the network weights in the data-driven model are adjusted by optimization methods to achieve online self-learning and continuous optimization of the model.

[0011] Secondly, the present invention also provides a concrete full-process production management system, comprising: The data configuration planning module is used to configure the basic data required for concrete production and generate a concrete production plan based on the basic data, which includes the pouring location, planned volume, and mix proportion. The basic data includes engineering structure information, concrete design strength and mix proportion, raw material information, and construction environment parameters. The data acquisition module is used to execute concrete mixing and production according to the concrete production plan, and to embed temperature sensors in the concrete mixture to collect temperature time-series data of the concrete during the mixing process. The digital twin module is used to construct a digital twin of the concrete hydration reaction based on the temperature time series data and the basic data, and to use the digital twin to predict the changes in the degree of hydration, compressive strength and slump of concrete in real time. The decision control module is used to acquire real-time transportation time and ambient temperature data during concrete transportation, and dynamically predict the slump of the concrete when it arrives at the construction site using the digital twin and the real-time transportation time and ambient temperature data. If the predicted slump is lower than the preset lower limit of the pouring requirement, the module dynamically generates process parameter adjustment instructions based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. The execution control module is used to feed back the process parameter adjustment instructions to the concrete transportation system and execute the adjustment operation; The feedback optimization module is used to collect the compressive strength data of standard curing specimens after the concrete is poured, compare and analyze it with the prediction results of the digital twin, generate a prediction error report, and feed the error report back to the digital twin to optimize the model parameters.

[0012] Thirdly, the present invention also provides an electronic terminal, comprising: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the concrete full-process production management method described above.

[0013] Fourthly, the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the concrete whole-process production management method described above.

[0014] Compared with existing technologies, the concrete whole-process production management method, system, terminal and storage medium described in this invention have the following advantages: The present invention discloses a concrete production management method, system, terminal, and storage medium for the entire process. By deeply integrating physical and chemical mechanism models with advanced data-driven models, a concrete production management system capable of real-time perception, accurate prediction, intelligent decision-making, and closed-loop optimization is constructed. The core objective of this system is to achieve dynamic and precise control over key performance parameters of concrete throughout the entire process from mixing and transportation to pouring, thereby proactively and forward-lookingly solving quality control problems in concrete production and ultimately improving the quality and reliability of construction projects. Attached Figure Description

[0015] The accompanying drawings, which form part of this invention, are used to provide a further understanding of the invention. The illustrative embodiments of the invention and their descriptions are used to explain the invention and do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a schematic diagram of the concrete full-process production management method according to Embodiment 1 of the present invention; Figure 2 This is a schematic diagram of the structure of a concrete full-process production management system according to Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of an electronic terminal according to Embodiment 3 of the present invention. Detailed Implementation

[0016] The present invention will now be described in further detail with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and not intended to limit it. Furthermore, it should be noted that, for ease of description, the accompanying drawings show only the parts relevant to the present invention, and not all of the structures.

[0017] Example 1 Figure 1 This is a schematic diagram of the concrete production management method according to Embodiment 1 of the present invention. See also... Figure 1 This invention provides a method for managing the entire concrete production process, specifically including the following steps: Step 101: Configure the basic data required for concrete production, and generate a concrete production plan based on the basic data, including the pouring location, planned volume, and mix proportion; wherein, the basic data includes engineering structure information, concrete design strength and mix proportion, raw material information, and construction environment parameters.

[0018] For example, basic data such as project information, mix proportions, raw materials and environmental parameters can be configured in the concrete production management system, and a detailed production plan can be generated.

[0019] This step is the starting point of the entire intelligent management process, aiming to provide a comprehensive and accurate data foundation for subsequent model predictions and intelligent decision-making. For example, a concrete production management system can provide a user interface that allows operators to input and manage the basic data required for production, either directly or by interfacing with upstream design systems (such as BIM).

[0020] In practical applications, operators need to enter detailed structural information into the system. This information includes not only standard details such as project name and construction unit, but more importantly, detailed information specific to each pouring section. For example, for a high-rise building, it is necessary to enter the floor number, structural component types such as columns / beams / slabs, component dimensions (length, width, height), and reinforcement density. This structural information directly relates to the concrete pouring method, vibration difficulty, and specific requirements for workability (such as slump). Furthermore, densely reinforced beam-column joints require concrete with better fluidity; this information will serve as a crucial basis for subsequent production planning and quality control.

[0021] Furthermore, based on engineering design drawings and construction specifications, the system can set the required concrete design strength grade (e.g., C30, C40) and corresponding mix proportion for each pouring section. The mix proportion information should be detailed down to the specific amounts of cement, water, sand, aggregate, and various admixtures (e.g., water-reducing agents, retarders) per cubic meter of concrete. For example, the system can include a built-in mix proportion design module that automatically calculates and recommends an initial mix proportion based on national standards such as the "Specifications for Concrete Construction of Waterway Engineering" (JTS 257-2008) and the performance of raw materials.

[0022] In addition, the system needs to input detailed information on various raw materials used in the current batch of production. For example, for cement, key indicators such as its type (e.g., PO 42.5), manufacturer, specific surface area, and C3A content need to be recorded, as these indicators directly affect the hydration rate and the adsorption capacity of admixtures, thus affecting slump loss. For aggregates, their type (crushed stone / pebbles), maximum nominal particle size, mud content, and mud lump content need to be recorded, especially since mud content significantly affects the effectiveness of polycarboxylate superplasticizers. In actual use, the system can also access meteorological service APIs or on-site sensors to acquire and record environmental parameters during construction in real time, such as temperature, humidity, and wind speed. These parameters have a significant impact on the setting time and slump loss of concrete.

[0023] After completing the basic data configuration, the system will automatically generate a detailed concrete production plan based on the engineering structure information and construction schedule. This plan will specify the required concrete volume, strength grade, slump requirement, and planned pouring time for each pouring section. Subsequently, the system can optimize the production sequence and dispatch intervals based on transportation distance and vehicle scheduling to ensure a continuous supply of concrete and avoid quality degradation due to excessive waiting time. Using this method, this automatically generated production plan will serve as the core instruction for all subsequent production, transportation, and monitoring activities.

[0024] Step 102: Perform concrete mixing and production according to the concrete production plan, and pre-embed temperature sensors in the concrete mixture to collect temperature time-series data of the concrete during the mixing process using the temperature sensors.

[0025] Specifically, during the concrete mixing process, temperature time-series data reflecting the intensity of the hydration reaction can be collected in real time by pre-embedded temperature sensors in the mixture.

[0026] This step is a crucial link connecting the physical world and the digital twin. By embedding sensing devices during the physical production process, it enables real-time sensing of changes in the internal state of the concrete. Specifically, the raw temperature data collected is transmitted in real time to a cloud server or a local edge computing gateway via the wireless communication modules (such as LoRa or NB-IoT) built into the sensors.

[0027] During data transmission, the system performs preliminary processing on the raw data, including data cleaning (removing anomalous jump values), timestamp synchronization, and data compression, to ensure data accuracy and transmission efficiency. The processed temperature time-series data stream can be stored in a time-series database and bound to a unique identifier for that batch of concrete (such as production batch number and transport vehicle number), providing a continuous and reliable data source for real-time calculation of the digital twin.

[0028] Step 103: Based on the temperature time series data and the basic data, construct a digital twin of the concrete hydration reaction, and use the digital twin to predict the changes in the degree of hydration, compressive strength and slump of the concrete in real time.

[0029] In practical applications, while mechanistic models are powerful, pure mechanistic modeling is very difficult for macroscopic properties like slump, which are affected by a variety of complex factors (such as the interaction between admixtures and cement, and aggregate surface properties). Therefore, this embodiment introduces a data-driven model to accurately predict the time-dependent loss of slump.

[0030] Specifically, various machine learning algorithms can be employed, such as backpropagation neural networks (BPNN), genetic expression programming (GEP), or multivariate adaptive regression splines (MARS). These models can learn complex nonlinear mapping relationships between inputs (such as time, temperature, mix proportions, admixture types and dosages) and outputs (slump) from high-dimensional historical data. The training data for these models comes from a large amount of historical production records and laboratory experimental data. Data preprocessing is a crucial step, including data cleaning, outlier handling (such as using box plots to identify and remove outlier data points), data standardization (such as Z-score standardization to ensure a mean of 0 and a variance of 1), and dataset partitioning (typically 70% training set and 30% test set). The trained model then uses real-time collected information such as temperature, time, and initial mix proportions as input to output real-time predictions of slump values ​​for the current and any future time.

[0031] Using the above method, by inputting real-time collected temperature data along with basic data into a digital twin, which integrates a mechanism model based on physicochemical principles such as the Arrhenius equation and a prediction model based on machine learning, it can calculate and predict the degree of hydration, compressive strength development curve, and slump loss trend of concrete over time in real time.

[0032] Optionally, the digital twin architecture is divided into three layers: the first is the data layer, which is responsible for receiving and storing real-time data (such as temperature and environmental parameters) and static data (such as mix proportions and raw material information) from the physical world; the second is the model layer, which contains two types of core models, namely mechanistic models and data-driven models. Mechanistic models are responsible for describing the physicochemical evolution of concrete performance, while data-driven models use historical data to learn complex nonlinear relationships; the third is the application layer, which provides application services such as real-time monitoring, early warning, and optimization decision-making based on the prediction results of the model layer.

[0033] Specifically, step 103 includes the following steps: Step 1031: Based on the physicochemical principles of cement hydration reaction, establish a mechanistic model describing the relationship between hydration degree, strength development, and temperature; wherein, the mechanistic model includes a temperature-hydration rate relationship model based on the Arrhenius equation and a maturity method strength prediction model based on the hydration degree-strength relationship model.

[0034] For example, the temperature-hydration rate relationship model based on the Arrhenius equation: the hydration reaction rate of cement is closely related to temperature and can usually be described by the Arrhenius equation. This embodiment uses the Maturity Method to quantify this relationship. The core idea is that concrete cured at different temperatures will have the same strength development level as long as its "maturity" (i.e., the integral of temperature and time) is the same. Equivalent age The calculation formula is: In the above formula, For the equivalent age increment, It is the activation energy of cement hydration (e.g., 33,000 kW). ), It is the ideal gas constant (e.g., 8.314). This is a reference temperature (e.g., 293K). Is it concrete at any time? The measured temperature (provided in real time by the sensor). It refers to the time interval. By calculating the equivalent age, the curing time at non-standard temperatures can be converted into the equivalent time at standard temperatures, thereby accurately predicting the hydration process.

[0035] Computerized water hydration (Equivalent age → hydration reaction), the formula is as follows: In the above formula, the initial = 0; = 1; , Determined by the cement test report (e.g.: , = 0.95), This is the reaction rate constant in the hydration reaction kinetic model, determined by experimental calorimetric curves or inversion of early-age temperature history in the field. For ordinary Portland cement, its value ranges from 0.008 to 0.020 within the 20–40 °C range. n is the order of cement hydration reaction, dimensionless, and related to The values ​​were determined by inversion from the early-age hydration heat curves, with a range of 0.8–1.2.

[0036] Computer maturity (Hydration degree → Mechanical maturity, both can be the same value), the formula is: .

[0037] For example, a maturity-based strength prediction model based on the hydration degree-strength relationship model: Based on the relationship between hydration degree and strength, this invention uses the maturity method to predict compressive strength. A commonly used model formula is as follows: In the above formula, yes Intensity at any moment It is the final strength. It is the reaction rate constant, determined by inversion from the laboratory intensity-age curve, and its value generally ranges from 0.012 to 0.025. , Is to Maturity at any given moment. Maturity is calculated in real time. This allows for dynamic prediction of the intensity development curve.

[0038] Step 1032: Using machine learning algorithms, based on historical production data, experimental data, and real-time collected temperature time-series data, establish a data-driven model for predicting slump loss over time; wherein, the machine learning algorithms include, but are not limited to, BP neural network, genetic expression programming (GEP), or multivariate adaptive regression splines (MARS).

[0039] Specifically, historical production data can be collected first, such as temperature time series. Equivalent age Water-to-glue ratio Water-reducing agent dosage Mud content, ambient temperature, initial slump As input, the measured slump is used as a label, and after normalization, a sample library is formed. Then, a BP-NN (or GEP, MARS) is used with 7 input nodes, 1 hidden layer, 12 nodes, and 1 output node (…). The loss function is the mean squared error. The Adam optimizer is trained for 300 epochs with an early stopping patience of 30, resulting in the weight matrix. With bias Finally, the real-time prediction thread (executed every 30 seconds) obtains the current... and .

[0040] The formula for assembling the input vector is as follows: Secondly, the forward calculation formula is as follows: Secondly, timeline extrapolation: using the same network structure... The step size is used to predict forward, resulting in 0→ The entire slump-time curve is used for judgment in the subsequent transportation stage.

[0041] Step 1033: The mechanistic model and the data-driven model are fused to form a hybrid digital twin; wherein the mechanistic model is used to predict the degree of hydration and compressive strength, the data-driven model is used to predict the slump change trend, and real-time collected temperature time series data is used as a bridge to connect the two models to achieve collaborative prediction and correction.

[0042] This embodiment constructs a hybrid digital twin by organically integrating a mechanistic model and a data-driven model. The implementation involves the mechanistic model (such as a maturity model) calculating real-time hydration and maturity levels. These physical quantities, as important feature variables, are input along with raw data such as temperature and time into the data-driven model (such as a backpropagation neural network). This integration leverages both the physical interpretability of the mechanistic model and the powerful fitting ability of the data-driven model to complex relationships, making the entire prediction system more robust and accurate.

[0043] In practical applications, temperature sensors embedded in the concrete mix generate a continuous temperature time-series curve over time. The digital twin, triggered by real-time temperature data, performs a complete calculation iteration at a preset time step (e.g., every 5 minutes). In each iteration, the system updates the predicted curves for hydration degree, compressive strength, and slump. These predictions are displayed visually on the monitoring interface (e.g., dynamic graphs), allowing managers to intuitively see the future evolution trend of concrete performance and providing a basis for advance decision-making.

[0044] Real-time temperature serves as both a common input variable for the two models and a benchmark for verifying the consistency of their outputs. Through the common link of temperature and performance, the mechanistic side provides interpretable physical states, while the data-driven side provides the ability to fit complex nonlinearities. The two complement and correct each other, thus forming a closed-loop hybrid digital twin. Therefore, temperature is the shared raw data for both models, ensuring that the two models can interact with the same physical object in the same time frame.

[0045] Step 104: During concrete transportation, real-time transportation time and ambient temperature data are acquired. Using the digital twin, combined with the real-time transportation time and ambient temperature data, the slump of the concrete upon arrival at the construction site is dynamically predicted. If the predicted slump is lower than the preset lower limit of the pouring requirement, based on the prediction result of the digital twin, process parameter adjustment instructions are dynamically generated. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed.

[0046] Specifically, step 104 includes the following steps: Step 1041: During the concrete transportation process, acquire real-time data on transportation time and ambient temperature.

[0047] Step 1042: Input the real-time acquired transportation time and ambient temperature data into the data-driven model of the digital twin.

[0048] Step 1043: The data-driven model, based on the input real-time data and combined with the initial slump and mix proportion information of the concrete, predicts the slump value of the concrete at any future time.

[0049] Step 1044: Estimate the time it takes for the concrete to arrive at the construction site, and calculate the predicted slump of the concrete upon arrival based on the estimated arrival time. If the predicted slump is lower than the preset lower limit of the pouring requirement, dynamically generate process parameter adjustment instructions based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transport speed.

[0050] For example, once a concrete truck leaves the mixing plant, its location can be tracked in real time via GPS positioning and combined with electronic map data to dynamically calculate the remaining transportation time from its current location to the construction site. Simultaneously, real-time ambient temperature data along the route is obtained through onboard temperature sensors or by connecting to a third-party meteorological service API. This dynamically changing data is continuously input into the digital twin. Upon receiving the latest transportation time and ambient temperature data, the data-driven model within the digital twin (such as a backpropagation neural network) immediately performs a rapid prediction calculation to determine the slump of the concrete at the expected arrival time at the construction site. This prediction is dynamically updated, becoming increasingly accurate as the transportation process progresses.

[0051] By comparing the predicted slump value at the arrival point with the preset lower limit of the slump requirement for that part of the project, it is possible to determine whether the slump meets the requirements. It should be understood that the lower limit is preset based on construction requirements (such as pumping or pouring methods). For example, if pumping is used on site, the slump requirement might be 160mm, and its lower limit could be set at 140mm. If the predicted value is lower than 140mm, the system will automatically trigger an alarm and initiate the next intelligent decision-making process.

[0052] Optionally, the specific steps for dynamically generating process parameter adjustment instructions are as follows: First, an intelligent decision-making model based on preset rules or optimization algorithms is constructed to determine the optimal process parameter adjustment strategy; second, when the predicted slump is lower than the preset lower limit of the pouring requirement, the decision-making model calculates the optimal combination of adjustment strategies based on the current concrete state, remaining transportation time, ambient temperature, and a preset adjustment rule library; the combination of adjustment strategies includes adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed; finally, the optimal adjustment strategy is converted into specific, executable process parameter adjustment instructions.

[0053] Intelligent decision-making models can employ two main approaches: One approach is an expert system based on pre-defined rules: This involves pre-establishing a knowledge base containing numerous "if-then" pre-defined rules. For example, "If the transportation time exceeds 60 minutes and the ambient temperature is above 30°C, it is recommended to increase the retarder dosage by 0.1%." This method is simple and fast, but lacks flexibility.

[0054] Second, a decision-making model based on optimization algorithms: the problem is defined as a multi-objective optimization problem. The objective function can be to minimize the cost of admixtures, minimize the impact on the final strength, and maximize the slump recovery effect. Constraints include the maximum allowable dosage of admixtures and the range of stirring speeds. Specifically, intelligent optimization algorithms such as genetic algorithms and particle swarm optimization can be used to search for the optimal combination of adjustment strategies in the vast solution space. This method is more intelligent and flexible and can find the global or near-global optimal solution.

[0055] Taking the optimization algorithm as an example, the decision-making process is as follows: When an adjustment command is triggered, the optimization algorithm starts. It takes the current concrete state (provided by a digital twin), remaining transport time, ambient temperature, and available adjustment methods (admixture inventory, vehicle performance) as input. The algorithm generates a series of possible adjustment schemes (e.g., Scheme A: add 0.05% water-reducing agent; Scheme B: add 0.1% retarder and increase the mixing speed to 5 rpm; Scheme C: ...), and uses the digital twin to quickly simulate the effect of each scheme after implementation (i.e., predict the adjusted slump at the arrival point). Then, through iterative calculations, the algorithm ultimately finds one or more optimal schemes that meet the slump requirements, have the lowest cost, and have the least impact on performance.

[0056] Step 105: Feed back the process parameter adjustment command to the concrete transportation system and execute the adjustment operation.

[0057] Specifically, the process parameter adjustment command can be sent to the concrete transport vehicle in the concrete transport system via a wireless communication network; wherein, after receiving the process parameter adjustment command, the on-board terminal on the concrete transport vehicle controls the admixture addition device, the mixing drum drive motor or the vehicle power system to perform the corresponding adjustment operation.

[0058] For example, a vehicle-mounted terminal can be installed on a concrete transport truck and connected to a wireless communication network. The terminal receives and parses instructions, then automatically controls the corresponding actuators: first, admixture addition: the terminal controls the start, stop, and flow rate of the admixture pump, injecting the specified amount of retarder or water-reducing agent into the mixing drum; second, mixing speed adjustment: the terminal sends instructions to the drive motor controller of the mixing drum to adjust the speed to a specified value. In this way, the entire process requires no manual intervention, achieving a high degree of automation.

[0059] It should be noted that if the concrete transport truck is an autonomous driverless vehicle, the speed of the concrete transport truck can be adjusted by controlling the vehicle's power system, thereby shortening the transportation time and adjusting the process parameters.

[0060] In practical applications, after the actuator completes the adjustment, it can also feed back the execution results (such as the actual added dosage and the actual achieved mixing speed) to the vehicle terminal and upload them to the cloud system. At the same time, the temperature sensor continues to monitor the temperature change of the concrete, and the digital twin continues to predict the slump recovery based on the new status data, so as to obtain real-time assessment of whether the adjustment measures are effective and make secondary adjustments when necessary, forming a dynamic feedback control loop.

[0061] Step 106: After the concrete pouring is completed, collect the compressive strength data of the standard curing specimens, compare and analyze them with the prediction results of the digital twin, generate a prediction error report, and feed the error report back to the digital twin for optimization of model parameters.

[0062] Specifically, this step includes the following steps: Step 1061: After the concrete is poured, standard specimens are made and cured according to national standard methods, and compressive strength tests are conducted at the specified age to obtain actual compressive strength data.

[0063] For example, at the concrete pouring site, quality inspectors can prepare standard curing specimens according to national standards (such as GB / T 50081) and conduct compressive strength tests at specified ages (such as 7 days or 28 days) to obtain the actual strength data of the batch of concrete.

[0064] Step 1062: Compare the actual compressive strength data with the predicted strength values ​​of the digital twin at the corresponding age, and calculate the prediction error. For example, the collected actual compressive strength data can be precisely compared with the predicted values ​​of the digital twin at the corresponding age to calculate the prediction error. Statistical indicators such as root mean square error (RMSE) or mean absolute percentage error (MAPE) can be calculated to quantify the model's prediction accuracy.

[0065] Step 1063: Perform statistical analysis on the prediction error and generate a prediction error report that includes the error magnitude, distribution, and trend.

[0066] For example, a detailed prediction error report can be automatically generated based on the results of the comparative analysis. This report not only includes the specific numerical value of the error, but also analyzes the possible sources of the error, such as fluctuations in raw material batches, deviations in model parameters, and abnormal environmental conditions, providing direction for subsequent model optimization.

[0067] Step 1064: The prediction error report is used as a feedback signal and input into the model training algorithm of the digital twin. The undetermined coefficients in the mechanistic model or the network weights in the data-driven model are adjusted by optimization methods to realize the online self-learning and continuous optimization of the model.

[0068] The prediction error report serves as a valuable feedback signal, inputting into the model training module of the digital twin. The system employs online or incremental learning algorithms, utilizing this new batch of data containing "correct answers" to fine-tune the weights and biases of the data-driven model (such as a neural network). Simultaneously, optimization algorithms (such as genetic algorithms) can be used to correct key parameters (such as activation energy) in the mechanistic model, thereby continuously improving the predictive ability of the entire digital twin and achieving a virtuous cycle of "becoming more accurate with use."

[0069] This embodiment describes a concrete full-process production management method that synchronously drives the maturity-strength mechanism chain and the temperature-slump data chain with temperature as the sole driving line. Throughout the mixing, transportation, and pouring processes, the equivalent age is calculated first, followed by the degree of hydration and maturity, and two curves, strength and slump, are output in real time. Once the predicted slump value is lower than the pouring lower limit, the admixture or rotation speed is immediately adjusted based on the same temperature benchmark. After pouring, the measured strength is fed back to the fine-tuning model, forming a prediction-intervention-verification-self-evolution closed loop. This transforms traditional post-event testing into process pre-control and changes from experience-based release to temperature-data dual-bridge decision-making, taking into account both strength compliance and on-site pumping performance, and achieving forward-looking, precise, and adaptive management of concrete production quality.

[0070] Example 2 Figure 2 This is a schematic diagram of the structure of a concrete full-process production management system according to Embodiment 2 of the present invention. See also... Figure 2 This system includes: The data configuration planning module 201 is used to configure the basic data required for concrete production and generate a concrete production plan based on the basic data, which includes the pouring location, planned volume and mix proportion; wherein, the basic data includes engineering structure information, concrete design strength and mix proportion, raw material information and construction environment parameters; Data acquisition module 202 is used to execute concrete mixing production according to the concrete production plan, and to embed temperature sensors in the concrete mixture to collect temperature time-series data of the concrete during the mixing process using the temperature sensors. The digital twin module 203 is used to construct a digital twin of the concrete hydration reaction based on the temperature time series data and the basic data, and to use the digital twin to predict the changes in the degree of hydration, compressive strength and slump of concrete in real time. The decision control module 204 is used to acquire real-time transportation time and ambient temperature data during concrete transportation, and dynamically predict the slump of the concrete when it arrives at the construction site using the digital twin and the real-time transportation time and ambient temperature data. If the predicted slump is lower than the preset lower limit of the pouring requirement, the module dynamically generates process parameter adjustment instructions based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. The execution control module 205 is used to feed back the process parameter adjustment command to the concrete transportation system and perform the adjustment operation. The feedback optimization module 206 is used to collect the compressive strength data of standard curing specimens after the concrete is poured, compare and analyze it with the prediction results of the digital twin, generate a prediction error report, and feed the error report back to the digital twin for optimization of model parameters.

[0071] The concrete full-process production management system provided in this embodiment of the invention can execute the concrete full-process production management method provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0072] Example 3 Figure 3 This is a schematic diagram of the structure of an electronic terminal according to Embodiment 3 of the present invention; Figure 3 A block diagram of an exemplary terminal system suitable for implementing embodiments of the present invention is shown. Figure 3 The terminal system shown is merely an example and should not impose any limitations on the functionality and scope of use of the embodiments of the present invention.

[0073] like Figure 3 As shown, terminal 12 is presented in the form of a general-purpose computing device. The components of terminal 12 may include, but are not limited to: one or more processors or processing units 16, system memory 28, and bus 18 connecting different system components (including system memory 28 and processing unit 16).

[0074] Bus 18 represents one or more of several bus architectures, including a memory bus or memory controller, a peripheral bus, a graphics acceleration port, a processor, or a local bus using any of the various bus architectures. For example, these architectures include, but are not limited to, the Industry Standard Architecture (ISA) bus, the Micro Channel Architecture (MAC) bus, the Enhanced ISA bus, the Video Electronics Standards Association (VESA) local bus, and the Peripheral Component Interconnect (PCI) bus.

[0075] Terminal 12 typically includes a variety of computer system readable media. These media can be any available media that can be accessed by terminal 12, including volatile and non-volatile media, removable and non-removable media.

[0076] System memory 28 may include computer system readable media in the form of volatile memory, such as random access memory (RAM) 30 and / or cache memory 32. Terminal 12 may further include other removable / non-removable, volatile / non-volatile computer system storage media. By way of example only, storage system 34 may be used to read and write non-removable, non-volatile magnetic media (… Figure 3 Not shown; usually referred to as a "hard drive"). Although Figure 3 Not shown, a disk drive for reading and writing to a removable non-volatile disk (e.g., a "floppy disk") and an optical disk drive for reading and writing to a removable non-volatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 via one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules configured to perform the functions of the embodiments of the present invention.

[0077] A program / utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28. Such program modules 42 include, but are not limited to, an operating system, one or more application programs, other program modules, and program data. Each or some combination of these examples may include an implementation of a network environment. Program modules 42 typically perform the functions and / or methods described in the embodiments of the present invention.

[0078] Terminal 12 can also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), and with one or more devices that enable a user to interact with terminal 12, and / or with any device that enables terminal 12 to communicate with one or more other computing devices (e.g., network card, modem, etc.). This communication can be performed via input / output (I / O) interface 22. Furthermore, terminal 12 can also communicate with one or more networks (e.g., local area network (LAN), wide area network (WAN), and / or public networks, such as the Internet) via network adapter 20. As shown, network adapter 20 communicates with other modules of terminal 12 via bus 18. It should be understood that, although not shown in the figures, other hardware and / or software modules can be used in conjunction with terminal 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems.

[0079] The processing unit 16 executes various functional applications and data processing by running programs stored in the system memory 28, such as implementing the concrete full-process production management method provided in the embodiments of the present invention.

[0080] Example 4 Embodiment 4 of the present invention also provides a storage medium containing computer-executable instructions, which, when executed by a computer processor, are used to perform the concrete full-process production management method as described in any of the above embodiments.

[0081] The computer storage medium of this invention can be any combination of one or more computer-readable media. A computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium can be, for example,—but not limited to—an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination thereof. More specific examples of computer-readable storage media (a non-exhaustive list) include: an electrical connection having one or more wires, a portable computer disk, a hard disk, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fiber, portable compact disk read-only memory (CD-ROM), optical storage device, magnetic storage device, or any suitable combination thereof. In this document, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device.

[0082] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, carrying computer-readable program code. Such propagated data signals may take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination thereof. Computer-readable signal media may also be any computer-readable medium other than computer-readable storage media, capable of sending, propagating, or transmitting programs for use by or in connection with an instruction execution system, apparatus, or device.

[0083] Program code contained on a computer-readable medium may be transmitted using any suitable medium, including—but not limited to—wireless, wire, optical fiber, RF, etc., or any suitable combination thereof.

[0084] Computer program code for performing the operations of this invention can be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, and C++, as well as conventional procedural programming languages ​​such as "C" or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as a standalone software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In cases involving remote computers, the remote computer can be connected to the user's computer via any type of network—including a local area network (LAN) or a wide area network (WAN)—or can be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0085] Note that the above description is merely a preferred embodiment of the present invention and the technical principles employed. Those skilled in the art will understand that the present invention is not limited to the specific embodiments described herein, and various obvious changes, readjustments, and substitutions can be made without departing from the scope of protection of the present invention. Therefore, although the present invention has been described in detail through the above embodiments, the present invention is not limited to the above embodiments, and may include many other equivalent embodiments without departing from the concept of the present invention, the scope of which is determined by the scope of the appended claims.

Claims

1. A method for managing the entire production process of concrete, characterized in that, include: Configure the basic data required for concrete production, and generate a concrete production plan based on the basic data, including the pouring location, planned volume, and mix proportion; wherein, the basic data includes engineering structure information, concrete design strength and mix proportion, raw material information, and construction environment parameters; Concrete mixing and production are carried out according to the concrete production plan, and temperature sensors are pre-embedded in the concrete mixture to collect temperature time-series data of the concrete during the mixing process. Based on the temperature time series data and the basic data, a digital twin of the concrete hydration reaction is constructed, and the digital twin is used to predict the changes in the degree of hydration, compressive strength and slump of concrete in real time. During concrete transportation, real-time transportation time and ambient temperature data are acquired. Using the digital twin, combined with the real-time transportation time and ambient temperature data, the slump of the concrete upon arrival at the construction site is dynamically predicted. If the predicted slump is lower than the preset lower limit of the pouring requirement, based on the prediction results of the digital twin, process parameter adjustment instructions are dynamically generated. These instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. The process parameter adjustment command is fed back to the concrete transportation system to execute the adjustment operation; After the concrete is poured, the compressive strength data of the standard curing specimens are collected, compared and analyzed with the prediction results of the digital twin, a prediction error report is generated, and the error report is fed back to the digital twin to optimize the model parameters.

2. The method according to claim 1, characterized in that, The process of constructing a digital twin of the concrete hydration reaction based on the temperature time-series data and the basic data, and using the digital twin to predict the real-time trends of concrete hydration degree, compressive strength, and slump, includes: Based on the physicochemical principles of cement hydration reaction, a mechanistic model describing the relationship between hydration degree, strength development, and temperature is established; wherein, the mechanistic model includes a temperature-hydration rate relationship model based on the Arrhenius equation and a maturity method strength prediction model based on the hydration degree-strength relationship model. A data-driven model for predicting slump loss over time was established using machine learning algorithms, based on historical production data, experimental data, and real-time temperature time-series data. The mechanistic model and the data-driven model are fused to form a hybrid digital twin; wherein the mechanistic model is used to predict hydration degree and compressive strength, the data-driven model is used to predict slump change trend, and real-time collected temperature time series data is used as a bridge connecting the two models to achieve collaborative prediction and correction.

3. The method according to claim 1, characterized in that, During concrete transportation, real-time data on transportation time and ambient temperature are acquired. Using the digital twin, combined with this data, the slump of the concrete upon arrival at the construction site is dynamically predicted. If the predicted slump is lower than a preset lower limit for pouring requirements, based on the prediction results from the digital twin, dynamic adjustments to process parameters are generated. These adjustments include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. During the concrete transportation process, real-time data on transportation time and ambient temperature are acquired. The real-time acquired transportation time and ambient temperature data are input into the data-driven model of the digital twin; The data-driven model, based on the input real-time data and combined with the initial slump and mix proportion information of the concrete, predicts the slump value of the concrete at any future time. The estimated arrival time of concrete at the construction site is determined, and the predicted slump of the concrete upon arrival is calculated based on the estimated arrival time. If the predicted slump is lower than the preset lower limit of the pouring requirement, the process parameter adjustment instructions are dynamically generated based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transport speed.

4. The method according to claim 3, characterized in that, The dynamically generated process parameter adjustment instructions include: Construct an intelligent decision-making model based on preset rules or optimization algorithms to determine the optimal process parameter adjustment strategy; When the predicted slump is lower than the preset lower limit of the pouring requirement, the decision model calculates the optimal combination of adjustment strategies based on the current concrete state, remaining transportation time, ambient temperature, and a preset adjustment rule library. The combination of adjustment strategies includes adjustments to the dosage of retarder, water-reducing agent, mixing speed, and transportation speed. The optimal adjustment strategy is then converted into specific, executable process parameter adjustment instructions.

5. The method according to claim 1, characterized in that, The step of feeding back the process parameter adjustment command to the concrete transportation system and executing the adjustment operation includes: The process parameter adjustment command is sent to the concrete transport vehicle in the concrete transport system via a wireless communication network; wherein, after receiving the process parameter adjustment command, the on-board terminal on the concrete transport vehicle controls the admixture addition device, the mixing drum drive motor or the vehicle power system to perform the corresponding adjustment operation.

6. The method according to claim 1, characterized in that, After the concrete pouring is completed, the compressive strength data of standard curing specimens are collected and compared with the prediction results of the digital twin. A prediction error report is generated and fed back to the digital twin for optimization of model parameters, including: After the concrete is poured, standard specimens are made and cured according to national standard methods, and compressive strength tests are conducted at the specified age to obtain actual compressive strength data. The actual compressive strength data is compared with the predicted strength values ​​of the digital twin at the corresponding age, and the prediction error is calculated. Perform statistical analysis on the prediction error to generate a prediction error report that includes the magnitude, distribution, and trend of the error; The prediction error report is used as a feedback signal and input into the model training algorithm of the digital twin. The undetermined coefficients in the mechanistic model or the network weights in the data-driven model are adjusted by optimization methods to achieve online self-learning and continuous optimization of the model.

7. A concrete full-process production management system, characterized in that, include: The data configuration planning module is used to configure the basic data required for concrete production and generate a concrete production plan based on the basic data, which includes the pouring location, planned volume, and mix proportion. The basic data includes engineering structure information, concrete design strength and mix proportion, raw material information, and construction environment parameters. The data acquisition module is used to execute concrete mixing and production according to the concrete production plan, and to embed temperature sensors in the concrete mixture to collect temperature time-series data of the concrete during the mixing process. The digital twin module is used to construct a digital twin of the concrete hydration reaction based on the temperature time series data and the basic data, and to use the digital twin to predict the changes in the degree of hydration, compressive strength and slump of concrete in real time. The decision control module is used to acquire real-time transportation time and ambient temperature data during concrete transportation, and dynamically predict the slump of the concrete when it arrives at the construction site using the digital twin and the real-time transportation time and ambient temperature data. If the predicted slump is lower than the preset lower limit of the pouring requirement, the module dynamically generates process parameter adjustment instructions based on the prediction results of the digital twin. The instructions include adjustments to the retarder dosage, water-reducing agent dosage, mixing speed, and transportation speed. The execution control module is used to feed back the process parameter adjustment instructions to the concrete transportation system and execute the adjustment operation; The feedback optimization module is used to collect the compressive strength data of standard curing specimens after the concrete is poured, compare and analyze it with the prediction results of the digital twin, generate a prediction error report, and feed the error report back to the digital twin to optimize the model parameters.

8. An electronic terminal, characterized in that, include: One or more processors; Storage device for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the concrete full-process production management method as described in any one of claims 1-6.

9. A storage medium containing computer-executable instructions, characterized in that: The computer-executable instructions, when executed by a computer processor, are used to perform the concrete full-process production management method as described in any one of claims 1-6.

Images