Intelligent pouring system and method for basement concrete

Abstract

The invention discloses an intelligent pouring system and method for basement concrete, and relates to the technical field of constructional engineering. A basement pouring area is divided into a plurality of sub-areas; collecting multi-source process parameters of the sub-regions and the sub-region joints in real time; according to preset evaluation indexes and weight factors, on the basis of the processed data, pouring quality evaluation indexes of all the sub-regions and the sub-region connecting positions are calculated; based on the historical construction data and the real-time monitoring data, constructing a construction quality prediction model, and predicting the pouring quality of each sub-region and the connection part of the sub-regions; according to the pouring quality evaluation result and the prediction result, in combination with a construction target and constraint conditions, an optimization algorithm is applied to generate construction optimization suggestions including adjustment of all technological parameters; and the construction optimization suggestions are fed back to an automatic control system or a manual operation interface of a construction site in real time, dynamic adjustment of construction parameters is achieved, the adjusted construction effect is continuously monitored, and closed-loop feedback control is formed.

Description

Technical Field

[0001] This invention relates to the field of building engineering technology, and in particular to an intelligent concrete pouring system and method for basements. Background Technology

[0002] Concrete pouring is a crucial step in building construction, especially in basement structures, where its quality directly affects the structural safety and durability of the entire building. Traditional concrete pouring methods rely heavily on manual labor and experience-based judgment, leading to several problems, primarily in the following aspects: 1) Unstable construction quality Human factors have a significant impact: differences in the technical skills and experience of construction workers lead to inconsistent pouring quality. For example, inaccurate control of vibration time may cause quality problems such as honeycomb and pitting inside the concrete; uneven pouring speed can easily cause concrete segregation and bleeding.

[0003] Delayed quality inspection: Traditional quality inspection methods are usually carried out after pouring, such as testing concrete strength by taking samples. This method cannot reflect the quality status during the pouring process in real time. Once a problem is discovered, it has often caused irreparable damage, requiring large-scale rework and repair, which not only increases construction costs but also delays the construction period.

[0004] 2) Low construction efficiency Construction progress is difficult to control precisely: In the construction of large-area basements, multiple work surfaces are operating simultaneously, making it difficult to coordinate the construction progress of each area. For example, the connection between concrete supply, vibration, troweling and other processes in different areas is not tight, which can easily lead to idle work or waiting, resulting in delays in the construction progress.

[0005] Unreasonable resource allocation: Traditional construction management methods make it difficult to monitor the construction progress and resource needs of each sub-area in real time, resulting in an uneven distribution of human, material, and equipment resources. For example, some areas may experience delays due to insufficient equipment, while equipment may be idle in other areas, leading to resource waste.

[0006] 3) Complex construction environment Basement space is limited: Basement construction spaces are relatively small, poorly ventilated, and create a harsh working environment. This not only inconveniences construction workers but also increases safety risks. For example, when performing vibration compaction in a confined space, the operating space for the vibrator is limited, which can easily lead to insufficient compaction.

[0007] Multiple overlapping operations: Basement construction typically involves multiple overlapping operations, such as rebar tying, formwork erection, and concrete pouring. Coordination between these operations is challenging and prone to interference, affecting construction quality and efficiency.

[0008] 4) Lack of real-time monitoring and feedback Data acquisition is difficult: In traditional construction processes, there is a lack of real-time and accurate monitoring methods for key parameters during the pouring process (such as pouring speed, pouring thickness, and pouring temperature). Even if some monitoring equipment exists, it often operates independently, and the data cannot be shared and integrated in real time, making it difficult to form a complete construction process data chain.

[0009] Lack of feedback control: Due to the lack of real-time monitoring data, quality control and parameter adjustment during construction rely mainly on manual experience, lacking scientific basis. Once construction parameters deviate from the reasonable range, they cannot be detected and adjusted in time, leading to quality problems.

[0010] With the continuous development of the construction industry and technological advancements, higher demands are being placed on the quality and efficiency of concrete pouring construction. In recent years, emerging technologies such as the Internet of Things (IoT), big data, and artificial intelligence (AI) have gradually gained traction in the construction field, providing new ideas and methods for solving problems in traditional concrete pouring construction. For example, by deploying IoT sensor networks at the construction site, various data during the construction process can be collected in real time; big data analytics can be used to deeply mine and analyze the collected data, providing decision support for construction quality control; and AI algorithms can be used to achieve intelligent optimization and dynamic adjustment of construction parameters.

[0011] However, currently, there is no intelligent control method or system on the market that can comprehensively and systematically solve the quality, efficiency, and complex construction environment problems in basement concrete pouring. Existing technical solutions mostly focus on the monitoring and control of specific links or parameters, lacking global optimization and collaborative management of the entire pouring process. Therefore, there is an urgent need for an intelligent control method and system for basement concrete pouring that can comprehensively utilize technologies such as the Internet of Things, big data, and artificial intelligence to achieve real-time monitoring, intelligent analysis, dynamic optimization, and balanced control of the basement concrete pouring process, improve construction quality and efficiency, reduce construction costs, improve the construction environment, and promote the intelligent development of the construction industry. To this end, an intelligent basement concrete pouring system and method are proposed. Summary of the Invention

[0012] The main objective of this invention is to provide an intelligent concrete pouring system and method for basements. This system aims to utilize technologies such as the Internet of Things, big data, and artificial intelligence to achieve real-time monitoring, intelligent analysis, dynamic optimization, and balanced control of the basement concrete pouring process, thereby improving construction quality and efficiency, reducing costs, and improving the construction environment. It can effectively solve the problems in the background technology.

[0013] To achieve the above objectives, the technical solution adopted by the present invention is as follows: A method for intelligent pouring of basement concrete includes the following steps: a) Divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between them; b) Install multiple sensors in each sub-region and at the junctions between sub-regions to collect process parameters in real time, including pouring speed, pouring thickness, pouring temperature and vibration parameters. c) The collected process parameter data are preprocessed, and based on the preset evaluation indicators and weighting factors, the pouring quality evaluation indicators of each sub-region and the sub-region connection are calculated. d) Based on historical construction data and real-time monitoring data, construct a construction quality prediction model to predict the pouring quality of each sub-area and the connection between sub-areas; e) Based on the evaluation and prediction results of the pouring quality, and in combination with the construction objectives and constraints, use optimization algorithms to generate construction optimization suggestions, including adjustments to each of the aforementioned process parameters; f) Feedback construction optimization suggestions to the automated control system or manual operation interface at the construction site in real time to achieve dynamic adjustment of construction parameters and continuous monitoring of the adjusted construction effect, forming a closed-loop feedback control.

[0014] Also includes: g) Evaluate the uniformity of pouring quality among sub-regions. When the evaluation parameters of the uniformity of pouring quality among sub-regions exceed the preset threshold, regenerate construction optimization suggestions to ensure the uniformity of pouring quality among sub-regions.

[0015] A smart concrete pouring system for basements includes: The pouring area division module is used to divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between sub-areas. The real-time monitoring module includes multiple sensors for real-time acquisition of process parameters, including pouring speed, pouring thickness, pouring temperature, and vibration parameters, for each sub-region and the connection between sub-regions, and transmits the acquired data to the data processing module. The data processing module is used to receive process parameter data transmitted by the real-time monitoring module, preprocess, fuse and integrate the data, and store the processed data in the database. The quality evaluation module calculates the pouring quality evaluation indicators for each sub-region and the connection between sub-regions based on the preset evaluation indicators and weighting factors and the data provided by the data processing module. These indicators include the pouring quality evaluation indicators for the sub-regions and the pouring quality evaluation indicators for the connection. The prediction model module uses machine learning or deep learning algorithms to build a construction quality prediction model based on historical construction data and real-time monitoring data, which is used to predict the pouring quality of each sub-area and the connection between sub-areas. The optimization control module, based on the evaluation results of the quality evaluation module and the prediction results of the prediction model module, combined with the construction objectives and constraints, uses optimization algorithms to generate construction optimization suggestions, including optimization suggestions for construction parameters such as pouring speed, pouring thickness, pouring temperature, and vibration parameters. The dynamic adjustment module is used to feed back the optimization suggestions generated by the optimization control module to the automated control system or manual operation interface at the construction site in real time, so as to realize the dynamic adjustment of construction parameters and continuously monitor the construction effect after adjustment, forming a closed-loop feedback control. The balance assessment module is used to evaluate the balance of pouring quality among sub-regions. When the evaluation parameters of the balance of pouring quality among sub-regions exceed the preset threshold, construction optimization suggestions are regenerated to ensure the balance of pouring quality among sub-regions. The data storage and management module is used to store real-time monitoring data, data processing results, quality evaluation results, prediction model parameters, optimization suggestions, and other relevant information during the construction process, and provides data query, backup, and recovery functions. The user interaction module provides a user interface for displaying real-time monitoring data, pouring quality evaluation results, prediction model output, and optimization suggestions. It also allows users to input construction goals, constraints, and evaluation index weights, as well as configure and operate the system.

[0016] The system also includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor.

[0017] Furthermore, the evaluation indicators for pouring quality include sub-indicators for pouring speed per unit time, pouring thickness, pouring temperature, and vibration parameters.

[0018] Furthermore, the calculation method for the casting quality evaluation index is as follows: = + + + ;in, The quantitative values ​​of the evaluation indicators for pouring quality; The first influence function of the sub-index of pouring speed on pouring quality; This is the second influence function of the sub-index for evaluating pouring thickness on pouring quality. This is the third influence function of the sub-index of pouring temperature on pouring quality; This is the fourth influence function of the vibration parameter evaluation sub-index on the pouring quality; , , , These are the weighting coefficients for the evaluation sub-indices of pouring speed, pouring thickness, pouring temperature, and vibration parameters, respectively. + + + =1; ∈ (0,1); =1,2,3,4; These are the standardized process parameters.

[0019] Furthermore, the first influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are the first fitted parameters, used to reflect the intensity of the influence of pouring speed on pouring quality.

[0020] The second influence function is determined in the following way: = ;in, It is a natural exponential function; , These are all second fitting parameters, used to reflect the strength of the influence of the pouring thickness on the pouring quality.

[0021] The third influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are third-order fitting parameters, used to reflect the intensity of the influence of pouring temperature on pouring quality.

[0022] The fourth influence function is determined in the following way: = ;in, It is a natural exponential function; , All are fourth fitting parameters, used to reflect the intensity of the influence of vibration parameters on the pouring quality.

[0023] Furthermore, the construction quality prediction model is constructed using a neural network or support vector machine, wherein: When using a neural network for construction, the expression is: = ;in, This refers to the quantified value of the predicted pouring quality evaluation index; This is the standardized process parameter data matrix. = ; , This is the weight matrix; , For bias terms; For activation functions; This refers to the activation function of the output layer of the neural network. When using support vector machines for construction, the expression is: = ;in, Number the sub-regions; For the first Lagrange multipliers of the subregion; For the first Target value for the sub-region; This is the kernel function.

[0024] Furthermore, the uniformity of pouring quality among the sub-regions is determined by the coefficient of variation of the pouring quality in the sub-regions. To conduct an evaluation, when the coefficient of variation > At that time, construction optimization suggestions are regenerated, among which, The coefficient of variation is the preset threshold. The calculation method is as follows: = ;in, The coefficient of variation for the pouring quality of the sub-region; The standard deviation of the pouring quality in the sub-region. = ; This represents the average pouring quality of the sub-region. = .

[0025] Furthermore, construction optimization suggestions are generated using the following optimization model: = ;in, To optimize the objective function of the model; , These are all weighting coefficients used to balance the impact of construction objectives and constraints on optimization, and + =1; ∈ (0,1); ∈ (0,1); These are the target parameters for construction. These are construction constraint parameters; The quantitative values ​​of the evaluation indicators for pouring quality; This refers to the quantitative value of the predicted pouring quality evaluation index.

[0026] The present invention has the following beneficial effects: Compared with existing technologies, this solution uses real-time monitoring and intelligent analysis to promptly identify and correct quality problems during construction, reduce rework caused by quality issues, and improve the overall quality of concrete pouring.

[0027] Compared with existing technologies, this solution optimizes construction parameters to achieve dynamic adjustment of the construction process, reducing downtime and waiting time, improving construction efficiency, and shortening the construction cycle.

[0028] Compared with existing technologies, this solution can reduce rework and resource waste caused by quality problems, optimize resource allocation, and reduce construction costs through intelligent construction process optimization.

[0029] Compared with existing technologies, this solution reduces the labor intensity of construction workers, improves the construction environment, and enhances construction safety and comfort through real-time monitoring and feedback control mechanisms.

[0030] Compared with existing technologies, this solution comprehensively considers the construction quality of each sub-area and connection point, achieving global optimization and balanced control, and ensuring the efficiency and quality of the entire basement concrete pouring process.

[0031] Compared with existing technologies, this solution can provide rich real-time data and intelligent analysis results, providing scientific basis for construction managers, supporting data-driven decision-making, and improving management level. Attached Figure Description

[0032] Figure 1 This is a schematic flowchart of an intelligent concrete pouring method for basements according to the present invention. Figure 2 This is a structural schematic diagram of an intelligent concrete pouring system for basements according to the present invention. Detailed Implementation

[0033] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0034] Example 1: See Figure 1 The flowchart shown is a schematic diagram of an intelligent concrete pouring method for basements according to the present invention, which includes the following steps: a) Divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between them; It should be noted that: The following considerations should be taken into account when dividing sub-regions: Note 1. Ease of construction: The division of sub-areas should take into account the movement and operating space of construction equipment to ensure a smooth construction process.

[0035] Avoid dividing the area into too small sub-areas, as this will increase the frequency of moving construction equipment and the difficulty of operation.

[0036] Note 2. Quality Control: The size of the sub-regions should facilitate quality monitoring and control to ensure that the pouring quality of each sub-region is uniform and consistent.

[0037] Considering factors such as pouring thickness and vibration effect, sub-areas should be reasonably divided to avoid uneven quality due to excessively large areas.

[0038] Note 3. Structural Features: The basement is divided according to its structural characteristics (such as column grid and wall location) to ensure that the pouring operation of each sub-area meets the structural requirements.

[0039] Avoid dividing the structure into excessively large sub-areas in critical structural locations (such as column bases and wall corners) to prevent affecting structural quality.

[0040] Note 4. Sensor Layout: The division of sub-regions should facilitate the installation and layout of sensors, ensuring that sensors can cover the entire pouring area and effectively monitor the junctions between sub-regions.

[0041] Considering the monitoring range and accuracy of the sensors, sub-regions should be rationally divided to avoid signal interference between sensors.

[0042] Note 5. Construction Schedule: The division of sub-regions should be aligned with the construction schedule to ensure a reasonable arrangement of the construction progress.

[0043] Avoid construction delays or resource waste caused by unreasonable division of factor areas.

[0044] In one possible implementation, a meshing method based on structured mesh generation is provided, specifically as follows: Based on the column grid and wall locations in the basement, the pouring area is divided into regular grid-like sub-areas. The size of each sub-area can be determined according to the column spacing and wall location.

[0045] Example: Assuming the basement column grid spacing is 6 meters × 6 meters, the pouring area can be divided into 6-meter × 6-meter square sub-areas. Sensors are installed at the center and junctions of each sub-area to ensure comprehensive monitoring coverage.

[0046] In another possible implementation, a method for dividing the operating range of construction equipment is provided, specifically as follows: The pouring area is divided into several sub-areas based on the operating range of the construction equipment (such as concrete pump trucks, vibrators, etc.). The size of each sub-area should match the operating radius of the equipment.

[0047] Example: Assuming the concrete pump truck has an operating radius of 15 meters, the pouring area can be divided into circular sub-areas with a diameter of 15 meters. Sensors are installed at the center and junctions of each sub-area to ensure effective monitoring within the equipment's operating range.

[0048] In another possible implementation, a method for dividing the construction schedule is given, specifically: According to the construction schedule, the pouring area is divided into several sub-areas, and the pouring time for each sub-area should match the construction schedule.

[0049] Example: Suppose the construction schedule requires 100 square meters of pouring work to be completed each day. The pouring area can be divided into sub-areas of 100 square meters each. Sensors are installed at the center and connection points of each sub-area to ensure the reasonable arrangement of the construction schedule.

[0050] In another possible implementation, a classification method based on quality control requirements is provided, specifically as follows: According to the requirements for pouring quality control, the pouring area is divided into several sub-areas, and the size of each sub-area should facilitate quality monitoring and control.

[0051] Example: Assuming quality control requires uniform pouring thickness in each sub-area, the pouring area can be divided into 3m x 3m sub-areas. Sensors are installed at the center and junctions of each sub-area to ensure uniform pouring thickness.

[0052] Additionally, it should be noted that the location information at the junction of sub-regions is determined as follows: Connection definition: A sub-region connection refers to the boundary area between two or more sub-regions. The location information of the connection includes boundary coordinates, connection method (such as overlapping, docking, etc.), and sensor layout.

[0053] Method for determining the location information of the connection point: Boundary coordinate determination: The specific coordinates of the boundary of each sub-region are determined through measurement and marking. Precise measurements can be taken using surveying tools such as total stations or GPS.

[0054] Connection method: Determine the connection method between sub-areas based on construction requirements. For example, when using an overlapping method, the width of the connection should be determined according to the operational requirements and quality control requirements of the construction equipment.

[0055] Sensor placement: Install sensors at the connection points to ensure effective monitoring of the pouring quality at these points. The sensor installation locations should cover the entire area of ​​the connection point to avoid blind spots.

[0056] b) Install multiple sensors in each sub-region and at the junctions between sub-regions to collect process parameters in real time, including pouring speed, pouring thickness, pouring temperature and vibration parameters. Specifically, the sensors include: A pouring speed sensor is used to measure the pouring speed of concrete. A pouring thickness sensor is used to measure the pouring thickness of concrete. A pouring temperature sensor is used to measure the pouring temperature of concrete. Vibration parameter sensor (taking vibration time as an example) is used to measure the working time of the vibrator; A dedicated sensor for the connection point is used to measure the pouring thickness, pouring temperature, and vibration time parameters at the connection point of the sub-area.

[0057] c) The collected process parameter data are preprocessed, and based on the preset evaluation indicators and weighting factors, the pouring quality evaluation indicators of each sub-region and the sub-region connection are calculated. The calculation method for the pouring quality evaluation index is as follows: = + + + ;in, The quantitative values ​​of the evaluation indicators for pouring quality; The first influence function of the sub-index of pouring speed on pouring quality; This is the second influence function of the sub-index for evaluating pouring thickness on pouring quality. This is the third influence function of the sub-index of pouring temperature on pouring quality; This is the fourth influence function of the vibration time evaluation sub-index on the pouring quality; , , , These are the weighting coefficients for the evaluation sub-indices of pouring speed, pouring thickness, pouring temperature, and vibration time, respectively. + + + =1; ∈ (0,1); =1,2,3,4; These are the standardized process parameters.

[0058] The first influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are the first fitted parameters, used to reflect the intensity of the influence of pouring speed on pouring quality.

[0059] The second influence function is determined in the following way: = ;in, It is a natural exponential function; , These are all second fitting parameters, used to reflect the strength of the influence of the pouring thickness on the pouring quality.

[0060] The third influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are third-order fitting parameters, used to reflect the intensity of the influence of pouring temperature on pouring quality.

[0061] The fourth influence function is determined in the following way: = ;in, It is a natural exponential function; , All are fourth fitting parameters, used to reflect the intensity of the influence of vibration time on the pouring quality.

[0062] d) Based on historical construction data and real-time monitoring data, a construction quality prediction model is constructed to predict the pouring quality of each sub-area and the connection between sub-areas; the construction quality prediction model is constructed using neural networks or support vector machines; In one possible implementation, when a neural network is used for construction, the expression is: = ;in, This is the standardized process parameter data matrix. = ; , This is the weight matrix; , For bias terms; For activation functions; This refers to the activation function of the output layer of the neural network. In another possible implementation, when constructed using a support vector machine, the expression is: = ;in, Number the sub-regions; For the first Lagrange multipliers of the subregion; For the first Target value for the sub-region; This is the kernel function.

[0063] e) Based on the evaluation and prediction results of the pouring quality, and in combination with the construction objectives and constraints, use optimization algorithms to generate construction optimization suggestions, including adjustments to various process parameters; The construction optimization suggestions are generated using the following optimization model: = ;in, To optimize the objective function of the model; , These are all weighting coefficients used to balance the impact of construction objectives and constraints on optimization, and + =1; ∈ (0,1); ∈ (0,1); These are the target parameters for construction. These are the parameters for construction constraints.

[0064] It should be noted that during the optimization process, the construction parameter constraints for each sub-region and connection point need to be considered. For example, for the first... Sub-region: Pouring speed per unit time Within a reasonable range, it should be expressed as: ≤ ≤ ;in, , These are the lower and upper limits of the pouring speed per unit time, respectively; Casting thickness Within a reasonable range, it should be expressed as: ≤ ≤ ;in, , These are the lower and upper limits of the pouring thickness, respectively; Pouring temperature Within a reasonable range, it should be expressed as: ≤ ≤ ;in, , These are the lower and upper limits of the pouring temperature, respectively. Vibration time Within a reasonable range, it should be expressed as: ≤ ≤ ;in, , These are the lower and upper limits of the vibration time, respectively; f) Feedback construction optimization suggestions to the automated control system or manual operation interface at the construction site in real time to achieve dynamic adjustment of construction parameters and continuous monitoring of the adjusted construction effect, forming a closed-loop feedback control.

[0065] Real-time feedback and closed-loop control are key aspects of ensuring construction quality. This can be achieved through the following steps: Data acquisition: Real-time acquisition of sensor data.

[0066] Data preprocessing: Standardize the collected data, detect outliers, and impute them.

[0067] Quality assessment: Calculate the current pouring quality evaluation indicators.

[0068] Quality prediction: Using predictive models to predict the quality of subsequent construction.

[0069] Optimization suggestions: Based on the current pouring quality evaluation indicators and the predicted quality of subsequent construction, optimization suggestions are generated.

[0070] Feedback control: Optimization suggestions are fed back to the automated control system or manual operation interface in real time to adjust construction parameters.

[0071] Continuous monitoring: Continuously monitor the construction effect after adjustments to form a closed-loop feedback.

[0072] Through the above mathematical model and implementation steps, the automation and optimization of intelligent concrete pouring in basements can be achieved, improving construction quality and efficiency.

[0073] g) Evaluate the uniformity of pouring quality among sub-regions. When the evaluation parameters of the uniformity of pouring quality among sub-regions exceed the preset threshold, regenerate construction optimization suggestions to ensure the uniformity of pouring quality among sub-regions.

[0074] The uniformity of pouring quality among sub-regions is determined by the coefficient of variation of pouring quality in each sub-region. To conduct an evaluation, when the coefficient of variation > At that time, construction optimization suggestions are regenerated, among which, The coefficient of variation is the preset threshold. The calculation method is as follows: = ;in, The coefficient of variation for the pouring quality of the sub-region; The standard deviation of the pouring quality in the sub-region. = ; This represents the average pouring quality of the sub-region. = .

[0075] Example 2: See Figure 2 The schematic diagram shown below illustrates the structure of an intelligent concrete pouring system for basements according to the present invention, comprising: The pouring area division module is used to divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between sub-areas. The real-time monitoring module includes multiple sensors for real-time acquisition of process parameters, including pouring speed, pouring thickness, pouring temperature, and vibration parameters, for each sub-region and the connection between sub-regions, and transmits the acquired data to the data processing module. The data processing module is used to receive process parameter data transmitted by the real-time monitoring module, preprocess, fuse and integrate the data, and store the processed data in the database. The quality evaluation module calculates the pouring quality evaluation indicators for each sub-region and the connection between sub-regions based on the preset evaluation indicators and weighting factors and the data provided by the data processing module. These indicators include the pouring quality evaluation indicators for the sub-regions and the pouring quality evaluation indicators for the connection. The prediction model module uses machine learning or deep learning algorithms to build a construction quality prediction model based on historical construction data and real-time monitoring data, which is used to predict the pouring quality of each sub-area and the connection between sub-areas. The optimization control module, based on the evaluation results of the quality evaluation module and the prediction results of the prediction model module, combined with the construction objectives and constraints, uses optimization algorithms to generate construction optimization suggestions, including optimization suggestions for construction parameters such as pouring speed, pouring thickness, pouring temperature, and vibration parameters. The dynamic adjustment module is used to feed back the optimization suggestions generated by the optimization control module to the automated control system or manual operation interface at the construction site in real time, so as to realize the dynamic adjustment of construction parameters and continuously monitor the construction effect after adjustment, forming a closed-loop feedback control. The balance assessment module is used to evaluate the balance of pouring quality among sub-regions. When the evaluation parameters of the balance of pouring quality among sub-regions exceed the preset threshold, construction optimization suggestions are regenerated to ensure the balance of pouring quality among sub-regions. The data storage and management module is used to store real-time monitoring data, data processing results, quality evaluation results, prediction model parameters, optimization suggestions, and other relevant information during the construction process, and provides data query, backup, and recovery functions. The user interaction module provides a user interface for displaying real-time monitoring data, pouring quality evaluation results, prediction model output, and optimization suggestions. It also allows users to input construction goals, constraints, and evaluation index weights, as well as configure and operate the system.

[0076] The system also includes a memory, a processor, and an electronic program stored in the memory that can run on the processor during vibration time.

[0077] The foregoing has shown and described the basic principles, main features, and advantages of the present invention. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The embodiments and descriptions in the specification are merely illustrative of the principles of the invention. Various changes and modifications can be made to the invention without departing from its spirit and scope, and all such changes and modifications fall within the scope of the present invention as claimed. The scope of protection of this invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligent pouring of basement concrete, characterized in that, Includes the following steps: a) Divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between them; b) Install multiple sensors in each sub-region and at the junctions between sub-regions to collect process parameters in real time, including pouring speed, pouring thickness, pouring temperature and vibration parameters. c) The collected process parameter data are preprocessed, and based on the preset evaluation indicators and weighting factors, the pouring quality evaluation indicators of each sub-region and the sub-region connection are calculated. d) Based on historical construction data and real-time monitoring data, construct a construction quality prediction model to predict the pouring quality of each sub-area and the connection between sub-areas; e) Based on the evaluation and prediction results of the pouring quality, and in combination with the construction objectives and constraints, use optimization algorithms to generate construction optimization suggestions, including adjustments to each of the aforementioned process parameters; f) Feedback construction optimization suggestions to the automated control system or manual operation interface at the construction site in real time to achieve dynamic adjustment of construction parameters and continuous monitoring of the adjusted construction effect, forming a closed-loop feedback control.

2. The intelligent concrete pouring method for basements according to claim 1, characterized in that, Also includes: g) Evaluate the uniformity of pouring quality among sub-regions. When the evaluation parameters of the uniformity of pouring quality among sub-regions exceed the preset threshold, regenerate construction optimization suggestions to ensure the uniformity of pouring quality among sub-regions.

3. The intelligent concrete pouring method for basements according to claim 1, characterized in that, The evaluation indicators for pouring quality include sub-indicators for pouring speed per unit time, pouring thickness, pouring temperature, and vibration parameters.

4. The intelligent concrete pouring method for basements according to claim 3, characterized in that, The calculation method for the casting quality evaluation index is as follows: = + + + ;in, The quantitative values ​​of the evaluation indicators for pouring quality; The first influence function of the sub-index of pouring speed on pouring quality; This is the second influence function of the sub-index for evaluating pouring thickness on pouring quality. This is the third influence function of the sub-index of pouring temperature on pouring quality; This is the fourth influence function of the vibration parameter evaluation sub-index on the pouring quality; , , , These are the weighting coefficients for the evaluation sub-indices of pouring speed, pouring thickness, pouring temperature, and vibration parameters, respectively. + + + =1; ∈ (0,1); =1,2,3,4; These are the standardized process parameters.

5. The intelligent concrete pouring method for basements according to claim 4, characterized in that, The first influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are the first fitted parameters, used to reflect the intensity of the influence of pouring speed on pouring quality; The second influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are second fitting parameters, used to reflect the intensity of the influence of the pouring thickness on the pouring quality; The third influence function is determined in the following way: = ;in, It is a natural exponential function; , All of these are third-fit parameters, used to reflect the intensity of the influence of pouring temperature on pouring quality; The fourth influence function is determined in the following way: = ;in, It is a natural exponential function; , All are fourth fitting parameters, used to reflect the intensity of the influence of vibration parameters on the pouring quality.

6. The intelligent concrete pouring method for basements according to claim 1, characterized in that, The construction quality prediction model is constructed using a neural network or support vector machine, wherein: When using a neural network for construction, the expression is: = ;in, This refers to the quantified value of the predicted pouring quality evaluation index; This is the standardized process parameter data matrix. = ; , This is the weight matrix; , For bias terms; For activation functions; This refers to the activation function of the output layer of the neural network. When using support vector machines for construction, the expression is: = ;in, Number the sub-regions; For the first Lagrange multipliers of the subregion; For the first Target value for the sub-region; This is the kernel function.

7. The intelligent concrete pouring method for basements according to claim 2, characterized in that, The uniformity of pouring quality among the sub-regions is measured by the coefficient of variation of the pouring quality of the sub-regions. To conduct an evaluation, when the coefficient of variation > At that time, construction optimization suggestions are regenerated, among which, The coefficient of variation is the preset threshold. The calculation method is as follows: = ;in, The coefficient of variation for the pouring quality of the sub-region; The standard deviation of the pouring quality in the sub-region. = ; This represents the average pouring quality of the sub-region. = ; For the first The quantitative values ​​of the pouring quality evaluation indicators for sub-regions.

8. The intelligent concrete pouring method for basements according to claim 1, characterized in that, Construction optimization suggestions are generated using the following optimization model: = ;in, To optimize the objective function of the model; , These are all weighting coefficients used to balance the impact of construction objectives and constraints on optimization, and + =1; ∈ (0,1); ∈ (0,1); These are the target parameters for construction. These are construction constraint parameters; The quantitative values ​​of the evaluation indicators for pouring quality; This refers to the quantitative value of the predicted pouring quality evaluation index.

9. A smart concrete pouring system for basements, characterized in that, include: The pouring area division module is used to divide the basement pouring area into several sub-areas and determine the location information of each sub-area and the connection points between sub-areas. The real-time monitoring module includes multiple sensors for real-time acquisition of process parameters, including pouring speed, pouring thickness, pouring temperature, and vibration parameters, for each sub-region and the connection between sub-regions, and transmits the acquired data to the data processing module. The data processing module is used to receive process parameter data transmitted by the real-time monitoring module, preprocess, fuse and integrate the data, and store the processed data in the database. The quality evaluation module calculates the pouring quality evaluation indicators for each sub-region and the connection between sub-regions based on the preset evaluation indicators and weighting factors and the data provided by the data processing module. These indicators include the pouring quality evaluation indicators for the sub-regions and the pouring quality evaluation indicators for the connection. The prediction model module uses machine learning or deep learning algorithms to build a construction quality prediction model based on historical construction data and real-time monitoring data, which is used to predict the pouring quality of each sub-area and the connection between sub-areas. The optimization control module, based on the evaluation results of the quality evaluation module and the prediction results of the prediction model module, combined with the construction objectives and constraints, uses optimization algorithms to generate construction optimization suggestions, including optimization suggestions for construction parameters such as pouring speed, pouring thickness, pouring temperature, and vibration parameters. The dynamic adjustment module is used to feed back the optimization suggestions generated by the optimization control module to the automated control system or manual operation interface at the construction site in real time, so as to realize the dynamic adjustment of construction parameters and continuously monitor the construction effect after adjustment, forming a closed-loop feedback control. The balance assessment module is used to evaluate the balance of pouring quality among sub-regions. When the evaluation parameters of the balance of pouring quality among sub-regions exceed the preset threshold, construction optimization suggestions are regenerated to ensure the balance of pouring quality among sub-regions. The data storage and management module is used to store real-time monitoring data, data processing results, quality evaluation results, prediction model parameters, optimization suggestions, and other relevant information during the construction process, and provides data query, backup, and recovery functions. The user interaction module provides a user interface for displaying real-time monitoring data, pouring quality evaluation results, prediction model output, and optimization suggestions. It also allows users to input construction goals, constraints, and evaluation index weights, as well as configure and operate the system.

10. A smart concrete pouring system for basements according to claim 9, characterized in that, The system further includes a memory, a processor, and an electronic program stored in the memory and capable of running on the processor, wherein the processor, when running the electronic program, is capable of implementing the steps of the intelligent concrete pouring method for basements according to any one of claims 1-8.

Images