Concrete pouring monitoring system and method

Abstract

The invention relates to a concrete pouring monitoring system and method. The system comprises an acquisition unit, an analysis unit and an execution unit, the analysis unit can predict a concrete quality range based on initial data information acquired by the acquisition unit, and sends corresponding pouring construction parameters as a construction strategy to the execution unit when the predicted concrete quality meets a preset standard, when the execution unit executes the pouring operation, the analysis unit can calculate the corresponding evaluation indexes according to the partial monitoring data acquired by the acquisition unit for the pouring operation in different stages of the current pouring link, so as to realize the real-time prediction of the concrete quality. The method comprises the following steps: collecting initial data information; predicting a concrete quality range to determine a pouring strategy to be executed; and when the pouring operation is executed, corresponding evaluation indexes are calculated according to different stages in the current pouring link, so that the real-time prediction of the concrete quality is realized.

Description

Technical Field

[0001] The present invention relates to the technical field of concrete structure construction, and particularly to a concrete pouring monitoring system and method. Background Art

[0002] In modern construction projects, concrete, as a composite material, is formed by mixing cement, water, fine aggregates (such as sand), coarse aggregates (such as gravel or crushed bricks), and additives and admixtures added when necessary in a certain proportion, and through processes such as uniform mixing, shaping, and hardening. It is widely used in projects such as buildings, bridges, roads, and tunnels, and is an indispensable structural material in modern construction projects. The quality of concrete directly determines the safety, durability, and functionality of buildings. High-quality concrete has good workability, that is, it is easy to operate during pouring and does not segregate; at the same time, it should also have appropriate strength, good durability and crack resistance, and excellent long-term performance. These characteristics not only affect the load-bearing capacity and stability of buildings, but also relate to the service life and maintenance cost of buildings.

[0003] Concrete pouring is a key link in construction, involving multiple processes such as raw material proportioning, mixing, transportation, and pouring. During this process, the quality of concrete is affected by various factors, including the quality of raw materials, environmental conditions, and construction techniques. Accurately monitoring and controlling these factors is crucial for ensuring the quality of concrete. Traditional methods for controlling the quality of concrete pouring mainly rely on the empirical judgment of on-site technicians and discrete detection means, lacking systematic and real-time monitoring. For example, the quality inspection of raw materials is usually carried out in the laboratory, and it is difficult to obtain timely feedback on the real-time changes during on-site pouring. In addition, changes in environmental conditions such as temperature and humidity and unexpected situations during the construction process are often difficult to detect and adjust in a timely manner through manual inspection, resulting in fluctuations in the quality of concrete pouring and even quality defects.

[0004] CN118191283A discloses a method and related device for detecting the quality of concrete pouring, which relates to the technical field of concrete construction. It includes collecting the concrete vibration frequency data, concrete vibration time data, and concrete vibration force data of a target concrete component through a receiver of an induction wire, and obtaining the vibration effect after analyzing the above data; after obtaining, inputting the vibration effect into a preset BIM model for visualization; since the induction wire is used to replace the manual measurement method to measure concrete parameters, and then the computer is used to replace the manual method to calculate and analyze the above data, the problem that the obtained vibration effect is not accurate enough is solved.

[0005] With the rapid development of the construction industry, the requirements for the quality of concrete construction are getting higher and higher. However, the existing concrete pouring monitoring technologies have the following technical problems: First, the prediction accuracy of concrete quality is insufficient because traditional methods rely on empirical judgment and limited experimental data, lacking real-time data support and dynamic adjustment mechanisms. Second, construction strategies are often set based on fixed parameters and cannot be dynamically adjusted according to real-time changing environmental conditions and material properties, resulting in low construction efficiency and resource waste. In addition, existing technologies often ignore the complex interactions between environmental factors and material properties during the concrete pouring process and lack in-depth analysis and understanding of these interactions. Finally, the assessment of concrete quality often focuses on the inspection after pouring and lacks the assessment of quality changes at different stages during the pouring process, making the construction quality control lack timeliness and pertinence.

[0006] In addition, on the one hand, there are differences in the understanding of those skilled in the art; on the other hand, although the applicant has studied a large number of documents and patents when making this invention, all details and content are not listed in detail due to space limitations. However, this does not mean that this invention does not possess the features of these prior arts. On the contrary, this invention already possesses all the features of the prior arts, and the applicant reserves the right to add relevant prior arts in the background art. Summary of the Invention

[0007] Aiming at the deficiencies of the prior art, the present invention provides a concrete pouring monitoring system and method to solve at least some of the above technical problems.

[0008] The present invention discloses a concrete pouring monitoring system, which is characterized in that it includes: a collection unit for collecting relevant data information during the concrete pouring process; an analysis unit for analyzing and processing the data information obtained by the collection unit and generating or adjusting construction strategies based on this; an execution unit for executing the construction strategies issued by the analysis unit or communicating with other devices. The analysis unit can predict the range of concrete quality obtained after concrete pouring under the current initial conditions based on the initial data information obtained by the collection unit in multiple process links before concrete pouring, and when the predicted concrete quality meets the preset concrete quality standard, send the corresponding pouring construction parameters as construction strategies to the execution unit. Among them, when the execution unit performs the pouring operation, the analysis unit can calculate the corresponding evaluation indicators using some monitoring data obtained by the collection unit for the pouring operation according to the different stages currently in the pouring link to achieve real-time prediction of concrete quality.

[0009] The concrete pouring monitoring system of the present invention realizes high-precision prediction and real-time monitoring of concrete quality by integrating a collection unit, an analysis unit, and an execution unit. The system collects initial data information through multiple process links before concrete pouring. Combining with the built-in AI model and machine learning algorithms, it can not only make predictions based on historical data and statistical models, but also significantly improve the controllability of construction quality and the accuracy of prediction through the dynamic feedback of real-time monitoring data. This comprehensive prediction ability not only relies on traditional data analysis, but also fundamentally realizes an in-depth analysis of the complex interaction between environmental factors and material properties, such as the influence of temperature and humidity on the concrete curing process, thereby providing scientific guidance for the optimization of construction parameters. In addition, the analysis unit dynamically generates or adjusts construction strategies according to the real-time collected data, enabling the construction process to flexibly respond to environmental changes and fluctuations in material properties. This ability not only optimizes the construction process, reduces resource waste, but also significantly improves construction efficiency. The system applies different evaluation indicators at different stages of concrete pouring, realizing multi-dimensional evaluation of concrete quality, more comprehensively capturing the characteristic changes of concrete at different curing stages, and providing a more detailed scientific basis for construction quality control. The integration and data-driven characteristics of this entire system significantly improve the scientific nature and accuracy of construction management, reflecting the unique value and non-obvious technical effects of this technical solution in the field of concrete construction.

[0010] According to a preferred embodiment, the analysis unit can be respectively built-in with a first evaluation indicator and a second evaluation indicator calculated based on different monitoring data for the initial stage and the later stage of the concrete pouring link. Among them, the analysis unit can determine the timing of switching from calculating the first evaluation indicator to calculating the second evaluation indicator by judging the switching node.

[0011] The present invention realizes multi-stage and differential evaluation of concrete quality by building different evaluation indicators for the initial stage and the later stage of the concrete pouring link in the analysis unit. The evaluation indicator in the initial stage focuses on quickly reflecting the basic condition of the concrete, while the evaluation indicator in the later stage pays more attention to evaluating the density and internal structural integrity of the concrete. This differential evaluation strategy not only improves the accuracy of concrete quality prediction, but also provides a more detailed scientific basis for construction personnel, making the adjustment of construction strategies more accurate and timely. Through the built-in switching mechanism, the system can intelligently judge the conversion timing from the initial stage to the later stage, realizing seamless switching of evaluation indicators, thereby ensuring continuous and consistent monitoring of concrete quality throughout the pouring process, and greatly improving the intelligent level of the construction process and the scientific nature of quality control.

[0012] According to a preferred embodiment, in the initial stage of the concrete pouring process, the analysis unit can calculate the first evaluation index in real time based on the monitoring data obtained by the acquisition unit, including external environmental temperature, internal concrete temperature, external environmental humidity, internal concrete humidity, fluidity data, and pressure.

[0013] In the initial stage of the concrete pouring process, the monitoring system of the present invention can calculate the first evaluation index in real time. This process involves key parameters such as external environmental temperature, internal concrete temperature, external environmental humidity, internal concrete humidity, fluidity data, and pressure obtained by the acquisition unit. The real-time monitoring and calculation of these parameters provide a scientific basis for the rapid evaluation of the early concrete quality, enabling construction personnel to promptly capture the basic conditions of the concrete in the initial pouring stage, and thus quickly respond to possible problems. This real-time monitoring and evaluation mechanism not only improves the response speed of the construction process but also provides strong technical support for early warning and quality control, ensuring the quality and safety of concrete construction.

[0014] According to a preferred embodiment, in the later stage of the concrete pouring process, the analysis unit can calculate the second evaluation index in real time based on the monitoring data obtained by the acquisition unit, including external environmental temperature, internal concrete temperature, external environmental humidity, internal concrete humidity, acoustic wave propagation speed, vibration frequency, conductivity, and pressure.

[0015] In the later stage of the concrete pouring process, the monitoring system of the present invention can calculate the second evaluation index in real time. This process involves key parameters such as external environmental temperature, internal concrete temperature, external environmental humidity, internal concrete humidity, acoustic wave propagation speed, vibration frequency, conductivity, and pressure obtained by the acquisition unit. The real-time monitoring and calculation of these parameters provide a scientific basis for the in-depth evaluation of the later concrete quality, enabling construction personnel to comprehensively evaluate the compactness and internal structural integrity of the concrete. This in-depth evaluation mechanism not only improves the accuracy of concrete quality prediction but also provides a more detailed scientific basis for construction personnel, making the adjustment of construction strategies more precise and timely, and greatly enhancing the intelligent level of the construction process and the scientific nature of quality control.

[0016] According to a preferred embodiment, the switching node can be determined through the switching mechanism built into the analysis unit. Among them, the switching mechanism is based on the stability of some of the monitoring data related to the first evaluation index obtained by the acquisition unit, starts the acquisition of some of the monitoring data related to the second evaluation index, and if the selected multiple monitoring data all meet the switching conditions within the same time period, it is determined that the switching node is reached.

[0017] Through the built-in switching mechanism, the present invention realizes the intelligent switching from the evaluation indicators in the initial stage to those in the later stage. This mechanism is based on the stability of part of the monitoring data related to the first evaluation indicator obtained by the acquisition unit, starts the acquisition of part of the monitoring data related to the second evaluation indicator, and determines that the switching node is reached when multiple monitoring data all meet the switching conditions. This intelligent switching mechanism not only improves the accuracy of concrete quality prediction, but also provides more detailed scientific basis for construction personnel, making the adjustment of construction strategies more accurate and timely. Through this mechanism, the system can achieve seamless switching of evaluation indicators, ensuring continuous and consistent monitoring of concrete quality throughout the pouring process, and greatly improving the intelligent level of the construction process and the scientific nature of quality control.

[0018] According to a preferred embodiment, the acquisition unit can collect only the monitoring data related to the first evaluation indicator in the initial stage of the concrete pouring link, and after the stability of at least one selected monitoring data meets the standard, start the acquisition of part of the monitoring data related to the second evaluation indicator until the switching node is reached, and then make the acquisition unit collect only the monitoring data related to the second evaluation indicator.

[0019] The monitoring system of the present invention collects only the monitoring data related to the first evaluation indicator in the initial stage of the concrete pouring link, and after the stability of at least one selected monitoring data meets the standard, starts the acquisition of part of the monitoring data related to the second evaluation indicator until the switching node is reached. This differential data acquisition strategy not only improves the efficiency of data acquisition, but also reduces unnecessary data redundancy, making resource allocation more reasonable. After reaching the switching node, the acquisition unit collects only the monitoring data related to the second evaluation indicator. This strategy ensures in-depth evaluation of concrete quality in the later stage, provides more detailed scientific basis for construction personnel, makes the adjustment of construction strategies more accurate and timely, and greatly improves the intelligent level of the construction process and the scientific nature of quality control.

[0020] According to a preferred embodiment, the analysis unit can input the initial data information obtained by the acquisition unit into the established AI model to obtain the predicted concrete quality range. The analysis unit compares the built-in or user-terminal uploaded concrete quality standard with the above predicted concrete quality range to determine whether to continue the pouring operation or adjust some influencing factors in one or more process links before concrete pouring and then re-obtain the predicted concrete quality range, so as to determine the construction strategy for the pouring link.

[0021] The monitoring system of the present invention inputs the initial data information obtained by the acquisition unit into the established AI model, realizes the prediction of the concrete quality range, and compares the concrete quality standard built-in or uploaded by the user terminal with the predicted concrete quality range to determine whether to continue the pouring operation or adjust some influencing factors of one or more process links before concrete pouring. This construction strategy determination mechanism based on prediction and comparison not only improves the accuracy of concrete quality prediction, but also provides more detailed scientific basis for construction personnel, making the adjustment of construction strategy more accurate and timely. Through this mechanism, the system can realize the real-time prediction and dynamic adjustment of concrete quality, greatly improving the intelligent level of the construction process and the scientific nature of quality control.

[0022] According to a preferred embodiment, the analysis unit can generate a quantitative index of the influence degree of each influencing factor on the concrete quality based on the built-in AI model, and classify each influencing factor into a strong control factor and a weak control factor based on the quantitative index, so as to distinguish the strong control factor from the weak control factor by prominently displaying the strong control factor in the systematic causal diagram. Among them, the AI model of the analysis unit can be established by artificial neural network and random forest, and sensitivity analysis is carried out through the established machine learning model to quantify the influence degree of each influencing factor on the concrete quality.

[0023] The monitoring system of the present invention generates a quantitative index of the influence degree of each influencing factor on the concrete quality based on the built-in AI model, and classifies each influencing factor into a strong control factor and a weak control factor based on the quantitative index. This quantification and classification mechanism not only improves the accuracy of concrete quality prediction, but also provides more detailed scientific basis for construction personnel, making the adjustment of construction strategy more accurate and timely. By prominently displaying the strong control factor in the systematic causal diagram, the system can intuitively indicate the factors that have the greatest influence on the concrete quality, so that construction personnel can quickly identify and respond to key influencing factors, greatly improving the intelligent level of the construction process and the scientific nature of quality control. The AI model is established by artificial neural network and random forest, and sensitivity analysis is carried out to further quantify the influence degree of each influencing factor on the concrete quality, making this quantification and classification more accurate and reliable.

[0024] According to a preferred embodiment, the analysis unit can compare the initial data information obtained by the acquisition unit with the design parameters to perform difference display according to the relationship between the deviation degree corresponding to the deviation situation of different data information and the preset threshold. Among them, the way of difference display is different from the way of prominent display, and the preset threshold of the strong control factor can be set to be lower than the preset threshold of the weak control factor.

[0025] The monitoring system of the present invention can compare the initial data information obtained by the acquisition unit with the design parameters, and perform differential display according to the relationship between the deviation degree corresponding to the deviation conditions of different data information and the preset threshold. This differential display mechanism not only improves the accuracy of concrete quality prediction, but also provides more detailed scientific basis for construction personnel, making the adjustment of construction strategies more accurate and timely. By setting different preset thresholds, the system can distinguish between strong control factors and weak control factors, enabling construction personnel to quickly identify and respond to key influencing factors, greatly improving the intelligent level of the construction process and the scientific nature of quality control. This mechanism enables construction personnel to intuitively see which factors have a large deviation degree in data information, so as to take corresponding adjustment measures to ensure the quality and efficiency of concrete construction.

[0026] The present invention also discloses a concrete pouring monitoring method, which is characterized in that it includes:

[0027] Collect the initial data information of one or more process links before concrete pouring;

[0028] Based on the prediction of the AI model, determine the range of concrete quality obtained after concrete pouring under the current initial conditions, so as to determine the pouring strategy to be executed;

[0029] When performing the pouring operation according to the pouring strategy, calculate the corresponding evaluation index using part of the monitoring data obtained for the pouring operation according to the different stages currently in the pouring link, so as to realize the real-time prediction of the concrete quality.

[0030] Preferably, the evaluation index includes a first evaluation index and a second evaluation index respectively for the initial stage and the later stage of the concrete pouring link, and the timing of switching from calculating the first evaluation index to calculating the second evaluation index is determined by judging the switching node.

[0031] The concrete pouring monitoring method of the present invention determines the pouring strategy to be executed by collecting the initial data information of one or more process links before concrete pouring and predicting the range of concrete quality obtained after concrete pouring based on the current initial conditions using an AI model. When performing the pouring operation according to the pouring strategy, the system can calculate the corresponding evaluation indexes using partial monitoring data obtained for the pouring operation according to the different stages currently in the pouring link to achieve real-time prediction of the concrete quality. This method based on prediction and real-time monitoring not only improves the accuracy of concrete quality prediction but also provides a more detailed scientific basis for construction personnel, making the adjustment of construction strategies more accurate and timely. By judging the switching node to determine the timing of switching from calculating the first evaluation index to calculating the second evaluation index, the system can achieve seamless switching of evaluation indexes, ensuring continuous and consistent monitoring of concrete quality throughout the pouring process, and greatly improving the intelligent level of the construction process and the scientific nature of quality control. BRIEF DESCRIPTION OF THE DRAWINGS

[0032] Figure 1 is the hardware connection diagram of the monitoring system provided by the present invention;

[0033] Figure 2 is the schematic diagram of the concrete pouring link provided by the present invention;

[0034] Figure 3 is the working schematic diagram of the analysis unit provided by the present invention;

[0035] Figure 4 is the logical diagram for special display of the systematic causal diagram provided by the present invention;

[0036] Figure 5 is the schematic diagram of the systematic causal diagram provided by the present invention;

[0037] Figure 6 is the step flow chart of the monitoring method provided by the present invention.

[0038] LIST OF REFERENCE NUMERALS

[0039] 100: Acquisition unit; 200: Analysis unit; 300: Execution unit; 400: User terminal. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The following is a detailed description with reference to the drawings.

[0041] Embodiment 1

[0042] The present invention discloses a concrete pouring monitoring system, which includes: a collection unit 100 for collecting relevant data information during the concrete pouring process; an analysis unit 200 for analyzing and processing the data information obtained by the collection unit 100 and generating or adjusting a construction strategy based thereon; and an execution unit 300 for executing the construction strategy issued by the analysis unit 200. Figure 1 It is the hardware connection diagram of the monitoring system.

[0043] Preferably, the analysis unit 200 can generate a systematic causal diagram with the concrete quality (or quality) as the target, as Figure 5 shown. In the systematic causal diagram, the horizontal line extending from the target is used as the "main backbone", so that the diagonal lines extending from the "main backbone" represent the links to which the influencing factors belong in the form of the first branch, the diagonal lines extending again from the first branch represent the categories to which the influencing factors belong in the form of the second branch, and the diagonal lines extending again from the second branch represent the specific influencing factors in the form of the third branch. Among them, the second branch and the third branch are not necessary structures of the systematic causal diagram, and some of the first branches may not extend the second branch and / or the third branch.

[0044] Furthermore, the analysis unit 200 can fill the initial data information collected by the collection unit 100 before the concrete pouring into the associated box of the corresponding influencing factor in the systematic causal diagram. Preferably, the initial data information can be the data information corresponding to the influencing factors related to the concrete quality obtained by the collection unit 100 in one or more process links before the concrete pouring. Among them, the process links before the concrete pouring may include the raw material link, the production and installation / dismantling link, and the transportation link. Preferably, the process link after the concrete pouring may further include the curing link, but the monitoring system of the present invention may not be used for this link. Preferably, the first branch of the systematic causal diagram generated by the analysis unit 200 may include the raw material link, the production and installation / dismantling link, the transportation link, and the pouring link.

[0045] Preferably, in the raw material stage, the acquisition unit 100 can collect the data information corresponding to multiple influencing factors such as cement factors, coarse aggregate factors, fine aggregate factors, mineral admixture factors, admixture factors, and water factors. Exemplarily, for cement factors, the acquisition unit 100 can obtain data information such as setting time, soundness, mortar strength, magnesium oxide and chloride ion content; for coarse aggregate factors, the acquisition unit 100 can obtain data information such as particle size distribution, content of needle-like and flaky particles, mud content, lump content, crushing value index and soundness; for fine aggregate factors, the acquisition unit 100 can obtain data information such as particle size distribution, fineness modulus, mud content, lump content, soundness, chloride ion content and harmful substance content; for mineral admixture factors, the acquisition unit 100 can obtain data information such as fineness, water demand ratio, loss on ignition and sulfur trioxide content of fly ash, specific surface area, activity index and fluidity ratio of granulated blast furnace slag powder, and specific surface area of steel slag powder; for admixture factors, the acquisition unit 100 can obtain data information such as water reduction rate, setting time difference, compressive strength ratio, pH value, chloride ion content and alkali content; for water factors, the acquisition unit 100 can obtain data information such as pH value, insoluble content, soluble content, sulfate ion content, chloride ion content, cement setting time difference, cement mortar strength ratio and alkali content.

[0046] Preferably, in the production, installation and disassembly stage, the acquisition unit 100 can collect the data information corresponding to multiple influencing factors such as steel bar factors, formwork factors and concrete factors. Exemplarily, for steel bar factors, the acquisition unit 100 can obtain data information such as selection of cushion blocks, selection of main concrete reinforcement cover, and deviation of steel bars during processing and installation, and can also obtain data information such as steel bar displacement and spacing, cover thickness, and size of steel bar welds; for formwork factors, the acquisition unit 100 can obtain data information such as formwork selection, release agent selection and deviation of formwork during processing and installation, and can also obtain data information such as formwork surface flatness, support stiffness, release agent construction parameters (such as construction quantity, temperature, time, etc.); for concrete factors, the acquisition unit 100 can obtain data information such as mixer rotation speed and time, mix ratio, etc.

[0047] Preferably, in the transportation stage, the acquisition unit 100 can obtain the data information corresponding to multiple influencing factors such as transportation time, transportation distance, vibration condition of transportation route, transportation environment temperature, transportation environment humidity, etc.

[0048] Preferably, the acquisition unit 100 can obtain data information related to the quality of concrete in various ways such as manual entry, OCR recognition, infrared or temperature sensors, humidity sensors, vision or image recognition, radar detection, ultrasonic detection, GPS, etc. Among them, the acquisition unit 100 can send the acquired data information to the analysis unit 200 in a quantified form. Especially for data information that cannot directly obtain actual values (such as selection of cushion blocks, selection of main reinforcement protection layers of concrete, etc.), the acquisition unit 100 can convert these data information into corresponding values according to specific rules through big data look-up tables or manual entry, so as to obtain quantifiable data information.

[0049] Exemplarily, the acquisition unit 100 can obtain quality certification documents of various raw materials through OCR recognition; the acquisition unit 100 can obtain the deviation of steel bars during processing and installation through image recognition, especially obtain the bending and folding conditions of stressed steel bars, the appearance quality and dimensional deviation of formed steel bars, etc.; the acquisition unit 100 can obtain the transportation distance (or transportation path) through GPS.

[0050] Preferably, the analysis unit 200 that obtains quantifiable data information can fill these initial data information into the corresponding associated boxes to obtain a systematic causal diagram with associated data information before performing the pouring operation. Preferably, the analysis unit 200 can send the obtained systematic causal diagram to the user terminal 400 through the execution unit 300, so that the user can view and operate on the systematic causal diagram through the user terminal 400.

[0051] Preferably, as Figure 3As shown in the figure, the analysis unit 200 can be built-in with an AI model for predicting the quality of concrete. The model is established through artificial neural networks and random forests, and can perform sensitivity analysis through the established machine learning model to quantify the influence degree of each influencing factor on the quality of concrete, and thereby predict the quality of concrete obtained under different scenarios. Preferably, the establishment of the AI model can be based on the collection of a large amount of historical data, including quality index data such as concrete mix design parameters, raw material performance indicators, construction environment conditions, production control parameters, and measured concrete strength. After data preprocessing, these data will be input as the input features and target variables of the model. Preferably, the present invention can adopt two main supervised machine learning algorithms, namely artificial neural networks and random forests, to train the model through training data. Specifically, artificial neural networks can construct feedforward neural networks or convolutional neural networks, etc., and adjust the network weights and biases through training to effectively fit the non-linear relationship of concrete quality influence; random forest is an ensemble algorithm based on decision trees, which consists of multiple decision trees, can better handle high-dimensional features, and has strong robustness to outliers. Further, by learning the model with a large amount of training data, the model weights are continuously adjusted, and the predicted values will gradually approach the actual values, so as to obtain an AI model with high prediction accuracy. In practical applications, the model can perform real-time prediction on the evaluation indicators of concrete quality based on various influencing factor data collected on-site, providing important quality warnings for on-site construction personnel.

[0052] Preferably, in order to quantify the influence degree of each influencing factor on the concrete quality, the present invention conducts a sensitivity analysis through the established machine learning model. The main idea of the sensitivity analysis method is to fix other variables unchanged and only change the value of a certain independent variable, and observe the change of the target variable (such as concrete strength), so as to judge the importance of this variable. The specific analysis methods include: 1) For models such as random forest, the contribution of each feature to the model prediction result can be directly calculated to rank the feature importance; 2) For black-box models such as neural networks, through methods such as integrated gradient or Shapley value analysis, the change of the model prediction result is decomposed into each input feature to quantify the importance contribution of each feature; 3) The single-variable perturbation method can fix other variables and only change the value of a certain feature to observe the change range of the target variable, so as to measure the feature importance. On the basis of the sensitivity analysis, the present invention further designs a variety of methods to quantify the influence degree of each influencing factor on the concrete quality, including: 1) Local perturbation analysis, perturb a certain feature in the local domain of the training data to obtain the influence interval of this feature on the target variable; 2) Additive model interpretation, approximately represent the complex model as the accumulation of the influence of a single feature on the target value, so as to quantify the influence degree of each feature; 3) Prediction confidence interval estimation, estimate the confidence interval range of the prediction value through methods such as repeated sampling, and analyze the influence degree of each feature change on the confidence interval; 4) The control variable method, fix other variables unchanged, change the range of a certain feature value, and fit the functional relationship between this feature and the target variable, so as to analyze the influence degree.

[0053] Preferably, the analysis unit 200 can classify the influencing factors according to the quantification indexes of the influence degree of each influencing factor generated by the AI model. Among them, the influencing factors can be divided into strong control factors and weak control factors according to the size of the quantification indexes. Further, the strong control factors can be configured with relatively higher control priorities and have higher control accuracy requirements during control. Preferably, in the present invention, by comparing the quantification indexes of each influencing factor, the release agent selection type and mud content in the raw material link, the mix ratio in the production and installation and disassembly links, and the transportation time in the transportation link are used as strong control factors and are shown in the systematic causal diagram in a form different from that of the weak control factors.

[0054] Preferably, as Figure 4As shown, some influencing factors and / or their corresponding data information in the systematic causal diagram can be specially displayed. Preferably, strong control factors can be prominently displayed. For example, one or more of the following methods can be used for prominent display: changing the color, changing the font, changing the font size, bolding, adding an underline, etc. Moreover, the data information filled in the associated box corresponding to the strong control factor can also be prominently displayed in the same way. Preferably, the analysis unit 200 can compare the initial data information obtained by the acquisition unit 100 with the design parameters (or planned parameters) to judge the deviation situation. Among them, according to the deviation degree of the deviation situation, the display form of the data information filled in the corresponding associated box is adjusted, so that each data information is differentially displayed in the systematic causal diagram. For example, one or more of the following methods can be used for differential display: changing the color, changing the font, changing the font size, bolding, adding an underline, etc. Preferably, the deviation degree of the differentially displayed data information from the design parameters is usually greater than the preset threshold. Especially when multiple preset thresholds are set, the data information with deviation degrees in different threshold intervals can be displayed by different differential display methods. Among them, the deviation degree can be calculated by dividing the difference between the data information obtained by the acquisition unit 100 and the design parameters by the design parameters. Further, for different types of influencing factors, the analysis unit 200 can set different preset thresholds. Among them, the preset threshold of the strong control factor can be lower (even much lower) than that of the weak control factor to improve the display priority of the strong control factor. Further preferably, the differential display can adopt a different method from the prominent display. For example, the prominent display adopts the method of bolding and / or adding an underline, while the differential display can adopt the method of changing the color, changing the font, and / or changing the font size. Such a setting can enable the data information of the strong control factor to be both prominently displayed and differentially displayed, so that it is convenient for the user to intuitively see which data information of the strong control factor has a large deviation degree when operating the user terminal 400. Preferably, the data information that is neither prominently displayed nor differentially displayed can be directly hidden or avoid blocking other information in the systematic causal diagram by an active avoidance method. Among them, the hidden or avoided data information can be redisplayed by methods such as clicking, checking, and circling.

[0055] Preferably, as Figure 3As shown in the figure, the analysis unit 200 can input the initial data information of various influencing factors in multiple process links before concrete pouring into the established AI model. Based on the quantification index of the influence degree of each influencing factor on the concrete quality, the analysis unit 200 can predict the concrete quality range obtained after concrete pouring under the current initial conditions. Among them, the analysis unit 200 can predict the concrete quality obtained under different combination forms according to the combination of various pouring construction parameters, so as to sort out the above-mentioned predicted concrete quality range. Further, the analysis unit 200 can judge the above-mentioned predicted concrete quality range according to the concrete quality standard built-in or uploaded by the user terminal 400, so as to confirm whether the concrete quality standard falls within the above-mentioned predicted concrete quality range. If so, the pouring operation can be continued; if not, it is necessary to adjust some influencing factors of one or more process links before concrete pouring, and regenerate the predicted concrete quality range for judgment again. Preferably, when adjusting some influencing factors of one or more process links before concrete pouring, the analysis unit 200 can preferentially put forward corresponding adjustment suggestions for the strong control factors with a large deviation degree of data information, and send them to the user terminal 400 through the execution unit 300. Among them, the adjustment suggestions can be directly displayed on the systematic causal diagram of the user terminal 400 until the user confirms or closes them. Since the data information of the strong control factors with a large deviation degree can be prominently displayed and differentially displayed in the systematic causal diagram at the same time, so that the user can quickly open it when needing to recheck the adjustment suggestions.

[0056] Preferably, when the predicted concrete quality meets the preset concrete quality standard, the analysis unit 200 can send the corresponding pouring construction parameters to the execution unit 300, so that the execution unit 300 directly and / or indirectly through the user terminal 400 executes and controls the pouring operation.

[0057] Preferably, when the execution unit 300 executes the pouring operation, the acquisition unit 100 can obtain the external environmental temperature T e 、the internal temperature T of the concrete i 、the external environmental humidity H e 、the internal humidity H of the concrete i , measure the slump of the concrete through a slump tester or a laser scanning device to obtain the fluidity data F, and monitor the pressure change of the concrete in real time through a pressure sensor to obtain the pressure P. Further preferably, based on the above monitoring data obtained by the acquisition unit 100, the analysis unit 200 can calculate the first evaluation index for predicting the concrete quality in real time through the following formula:

[0058]

[0059] Wherein, Q1 is the first evaluation index, T i is the internal temperature of the concrete, H i is the internal humidity of the concrete, F is the fluidity data, P is the pressure, T e is the external environmental temperature, H e is the external environmental humidity, T ref is the reference temperature, w o is the (bias term) constant, w1, w2, w3, w4 are the weight coefficients of temperature, humidity, fluidity, and pressure respectively, and w5, w6, w7 are the weight coefficients of the interaction terms.

[0060] Further, in the above formula, F2 in the fourth term emphasizes the square relationship between fluidity and strength; T e ·H e represents the interaction between temperature and humidity, considering the hydration process of the concrete; in the seventh term represents the non-linear relationship between fluidity and temperature, capturing its influence on the early hydration rate; P2·log(H e +1) in the eighth term emphasizes the influence of pressure on humidity.

[0061] Preferably, when the execution unit 300 performs the pouring operation, the acquisition unit 100 can obtain the external environmental temperature T e , the internal temperature T i of the concrete, the external environmental humidity H e , the internal humidity H i of the concrete through the temperature and humidity sensor, measure the acoustic wave propagation speed S inside the concrete through the ultrasonic rangefinder to evaluate the density and crack condition, measure the vibration frequency V in the concrete structure through the vibration sensor or accelerometer to evaluate its density and curing state, measure the conductivity E in the concrete through the conductivity sensor to reflect its water content and chemical reaction degree, and monitor the pressure change of the concrete in real time through the pressure sensor to obtain the pressure P. Further preferably, based on the above monitoring data obtained by the acquisition unit 100, the analysis unit 200 can calculate in real time the second evaluation index for predicting the concrete quality through the following formula:

[0062]

[0063] Wherein, Q2 is the first evaluation index, S is the acoustic wave propagation speed, V is the vibration frequency, T i is the internal temperature of the concrete, T ref is the reference temperature, E is the conductivity, H i is the internal humidity of the concrete, H ref is the reference humidity, T e is the external environmental temperature, H e is the external environmental humidity, P is the pressure, ko is the (bias term) constant, k1, k2, k3, and k4 are the weight coefficients of sound wave, vibration, temperature, and conductivity respectively, and k5, k6, k7, and k8 are the weight coefficients of the interaction terms.

[0064] Further, in the above formula, in the fourth term represents the influence of temperature on the hydration rate; E in the fifth term 1.5 represents the influence of conductivity, emphasizing its effect on moisture and chemical reactions in a non-linear manner; in the seventh term represents the non-linear relationship between the square of the sound wave propagation speed and humidity, reflecting the complexity of the influence of density on moisture; T in the eighth term e 2 ·H e represents the non-linear interaction between temperature and humidity; P·H in the ninth term i represents the interaction between pressure and humidity, affecting the curing process of concrete.

[0065] Preferably, the analysis unit 200 of the present invention is provided with at least two different evaluation indicators because the first evaluation indicator is more suitable for scenarios of quickly evaluating macroscopic parameters such as temperature, humidity, and fluidity data. Especially in the initial stage of the concrete pouring link, it can timely reflect the basic condition of the concrete, and the calculation formula of the first evaluation indicator is relatively simpler and easier to use, with a fast calculation speed, suitable for real-time monitoring and early warning; while the second evaluation indicator is more suitable for the later stage of the concrete pouring link, especially in occasions where it is necessary to evaluate the density and internal structural integrity of the concrete, and the calculation formula of the second evaluation indicator is relatively more complex, which can fully consider the interaction between parameters, especially the unique influence of the sound wave propagation speed and vibration frequency on the quality of the concrete, providing a more accurate quality assessment. The two stages included in the concrete pouring link are as Figure 2As shown. In addition, the acquisition unit 100 can also specifically activate the monitoring devices required to calculate the corresponding evaluation indicators to obtain the corresponding monitoring data, so as to avoid data redundancy and resource waste caused by the acquisition of a large amount of monitoring data. Based on this, the analysis unit 200 can flexibly select more applicable evaluation indicators for the current scenario from a variety of evaluation indicators according to the construction progress, which is conducive to more accurately predicting the concrete quality. And the calculation of the first evaluation indicator and the second evaluation indicator of the present invention is based on the premise that after multiple process links before concrete pouring are completed, it can be predicted by the AI model to meet the preset standard. Meeting this premise enables the analysis unit 200 to avoid the influence of abnormal situations existing in one or more process links before concrete pouring on the accuracy and reliability of the evaluation indicator calculation when calculating the first evaluation indicator and the second evaluation indicator. Since the calculation formulas of the first evaluation indicator and the second evaluation indicator are comprehensively considered when established, the calculation sensitivity of these two evaluation indicators is relatively high. If there are relatively serious abnormal situations in the process links before concrete pouring, whether in the initial stage or the later stage of the concrete pouring link, it will have a greater impact on the quality of the concrete, so that the calculation results of the first evaluation indicator and the second evaluation indicator are always characterized as abnormal, thus losing the meaning of calculation and prediction. And when it is determined that the predicted concrete quality can meet the preset concrete quality standard, based on the real-time calculation of the first evaluation indicator and the second evaluation indicator, it can be intuitively seen how the predicted concrete quality fluctuates with the concrete pouring.

[0066] Preferably, the analysis unit 200 of the present invention can use the first evaluation indicator and the second evaluation indicator respectively at different stages of the concrete pouring link to represent the prediction results of the concrete quality in real time. Among them, the analysis unit 200 can ensure to switch from the first evaluation indicator to the second evaluation indicator at an appropriate time by judging the switching node. Further, the switching node can be judged by the following switching mechanism, that is, based on the stability of some monitoring data related to the first evaluation indicator obtained by the acquisition unit 100, start the acquisition of some monitoring data related to the second evaluation indicator, and if the selected multiple monitoring data all reach the switching conditions within the same time period, it is judged that the switching node is reached. Some monitoring data related to the first evaluation indicator includes one or more of the fluidity data F, the internal temperature T of the concrete i and the pressure P. Among them, the stability of these monitoring data can be set as follows: if the change rate of the fluidity data F is less than 5%, it indicates that the fluidity is relatively stable; the internal temperature T of the concrete iIf the change value is less than 2°C, it indicates that the thermal state of the concrete is stable, which is helpful for the subsequent curing process; if the change rate of the pressure P is less than 5% and reaches a preset stable value (for example, the critical compaction pressure), it indicates that the concrete has completed the basic filling. When at least one piece of monitoring data related to the first evaluation index meets the stability requirements, the acoustic wave propagation speed S is measured by an ultrasonic rangefinder. If the speed exceeds the preset reference, it means that the density of the concrete has increased significantly, indicating a good curing state. When the above-mentioned monitoring data all reach the preset stable conditions within a period of time (for example, 30 to 60 minutes), the analysis unit 200 switches from calculating the first evaluation index to calculating the second evaluation index.

[0067] Exemplarily, in one embodiment, the monitoring data obtained by the acquisition unit 100 at a certain time node in the initial stage of the concrete pouring link, the constants and weight coefficients in the calculation formula of the first evaluation index built in the analysis unit 200 are shown in Table 1. Table 1 is a data table related to the first evaluation index; the monitoring data obtained by the acquisition unit 100 at a certain time node in the later stage of the concrete pouring link, the constants and weight coefficients in the calculation formula of the second evaluation index built in the analysis unit 200 are shown in Table 2. Table 2 is a data table related to the second evaluation index.

[0068] Table 1 Data table related to the first evaluation index

[0069] Parameter Description Data Parameter Description Data <![CDATA[T i > Internal temperature of concrete (°C) 20 W Temperature weight coefficient 1.2 <![CDATA[T e > External environmental temperature (°C) 25 <![CDATA[W2]]> Humidity weight coefficient 0.8 <![CDATA[H i > Internal humidity of concrete (%) 60 <![CDATA[W3]]> Fluidity weight coefficient 0.5 <![CDATA[H e > External environmental humidity (%) 70 <![CDATA[W4]]> Pressure weight coefficient 1.0 F Fluidity (slump, cm) 10 <![CDATA[W5]]> Interaction term weight coefficient 0.3 P Pressure (MPa) 15 <![CDATA[W6]]> Interaction term weight coefficient 0.2 <![CDATA[W0]]> Constant 5 <![CDATA[W7]]> Interaction term weight coefficient 0.4

[0070] Table 2 Data table related to the second evaluation index

[0071] Parameter Description Data Parameter Description Data S Sound wave propagation velocity (m / s) 3500 <![CDATA[k2]]> Vibration weight coefficient 0.7 V Vibration frequency (Hz) 50 <![CDATA[k3]]> Temperature influence coefficient 0.9 <![CDATA[T i > Internal temperature of concrete (°C) 20 <![CDATA[k4]]> Conductivity weight coefficient 1.1 <![CDATA[H i > Internal humidity of concrete (%) 60 <![CDATA[k5]]> Interaction term weight coefficient 0.6 E Conductivity (mS / cm) 0.5 <![CDATA[k6]]> Interaction term weight coefficient 0.3 <![CDATA[k0]]> Constant 10 <![CDATA[k7]]> Interaction term weight coefficient 0.2 <![CDATA[k1]]> Sound wave weight coefficient 1.5 <![CDATA[k8]]> Interaction term weight coefficient 0.4

[0072] Preferably, after the pouring operation is completed, the analysis unit 200 can fill the data information obtained by the acquisition unit 100 in the pouring link and the calculated evaluation index in real time into the systematic causal diagram to form a comprehensive analysis diagram of the influencing factors of the current concrete construction. Further, the user can view the comprehensive analysis diagram of the influencing factors in a visual manner through the user terminal 400, and can trace the current concrete construction process based on the final concrete quality using the comprehensive analysis diagram of the influencing factors.

[0073] Example 2

[0074] This embodiment is a further improvement of Embodiment 1, and the repeated content will not be elaborated.

[0075] As Figure 6 shown, the present invention also discloses a concrete pouring monitoring method, which can adopt the monitoring system described in Embodiment 1. Among them, the monitoring method may include the following steps:

[0076] Collect the initial data information of one or more process steps before concrete pouring;

[0077] Based on the prediction of the AI model, determine the range of concrete quality obtained after concrete pouring under the current initial conditions, so as to determine the pouring strategy to be executed;

[0078] When performing the pouring operation according to the pouring strategy, calculate the corresponding evaluation indicators by using some of the monitoring data obtained for the pouring operation at different stages in the current pouring link, so as to realize the real-time prediction of the concrete quality.

[0079] The evaluation indicators include a first evaluation indicator and a second evaluation indicator respectively for the initial stage and the later stage of the concrete pouring link, and determine the timing of switching from calculating the first evaluation indicator to calculating the second evaluation indicator by judging the switching node.

[0080] It should be noted that the above specific embodiments are exemplary. Those skilled in the art can come up with various solutions inspired by the disclosure of the present invention, and these solutions also belong to the disclosure scope of the present invention and fall within the protection scope of the present invention. Those skilled in the art should understand that the description and drawings of the present invention are illustrative and do not constitute a limitation on the claims. The protection scope of the present invention is defined by the claims and their equivalents. The description of the present invention contains multiple inventive concepts. For example, "preferably" or "according to a preferred embodiment" indicates that a separate inventive concept is disclosed in the corresponding paragraph. The applicant reserves the right to file divisional applications according to each inventive concept. Throughout the text, the features guided by "preferably" are only optional ways and should not be understood as must be set. Therefore, the applicant reserves the right to abandon or delete the relevant preferred features at any time.

Claims

1. A concrete pouring monitoring system, characterized in that, It includes: A collection unit (100) for collecting relevant data information during the concrete pouring process; An analysis unit (200) for analyzing and processing the data information obtained by the collection unit (100) and generating or adjusting a construction strategy based on this; An execution unit (300) for executing the construction strategy issued by the analysis unit (200) or communicating and connecting with other devices, The analysis unit (200) can predict the range of concrete quality obtained after concrete pouring under the current initial conditions based on the initial data information obtained by the collection unit (100) in multiple process links before concrete pouring. When the predicted concrete quality meets the preset concrete quality standard, the corresponding pouring construction parameters are sent to the execution unit (300) as a construction strategy. Among them, when the execution unit (300) performs the pouring operation, the analysis unit (200) can calculate the corresponding evaluation index using part of the monitoring data obtained by the collection unit (100) for the pouring operation according to the different stages currently in the pouring link to achieve real-time prediction of the concrete quality.

2. The monitoring system according to claim 1, wherein The analysis unit (200) can be internally provided with a first evaluation index and a second evaluation index calculated based on different monitoring data for the initial stage and the later stage of the concrete pouring link respectively. Among them, the analysis unit (200) can determine the timing of switching from calculating the first evaluation index to calculating the second evaluation index by judging the switching node.

3. The monitoring system according to claim 1 or 2, characterized in that, In the initial stage of the concrete pouring link, the analysis unit (200) can calculate the first evaluation index in real time based on the monitoring data obtained by the collection unit (100), including external environmental temperature, concrete internal temperature, external environmental humidity, concrete internal humidity, fluidity data, and pressure.

4. The monitoring system according to any one of claims 1 to 3, characterized in that, In the later stage of the concrete pouring link, the analysis unit (200) can calculate the second evaluation index in real time based on the monitoring data obtained by the collection unit (100), including external environmental temperature, concrete internal temperature, external environmental humidity, concrete internal humidity, acoustic wave propagation speed, vibration frequency, conductivity, and pressure.

5. The monitoring system according to any one of claims 1 to 4, characterized in that, The switching node can be judged by the switching mechanism built in the analysis unit (200). Among them, the switching mechanism is based on the stability of part of the monitoring data related to the first evaluation index obtained by the collection unit (100), starts the collection of part of the monitoring data related to the second evaluation index, and if the selected multiple monitoring data all meet the switching conditions within the same time period, it is judged that the switching node is reached.

6. The monitoring system according to any one of claims 1 to 5, characterized in that, The collection unit (100) can only collect the monitoring data related to the first evaluation index in the initial stage of the concrete pouring link, and after the stability of at least one selected monitoring data meets the standard, start the collection of part of the monitoring data related to the second evaluation index until the switching node is reached, and then make the collection unit (100) only collect the monitoring data related to the second evaluation index.

7. The monitoring system according to any one of claims 1 to 6, characterized in that The analysis unit (200) can input the initial data information obtained by the acquisition unit (100) into the established AI model to obtain the predicted range of concrete quality. The analysis unit (200) compares the built-in or user terminal (400) uploaded concrete quality standard with the above predicted range of concrete quality to determine whether to continue the pouring operation or adjust some influencing factors in one or more process links before concrete pouring and then re-obtain the predicted range of concrete quality, so as to determine the construction strategy for the pouring link.

8. The monitoring system according to any one of claims 1 to 7, characterized in that, The analysis unit (200) can generate a quantitative index of the influence degree of each influencing factor on the concrete quality based on the built-in AI model, and classify each influencing factor into a strong control factor and a weak control factor based on the quantitative index, so as to distinguish the strong control factor from the weak control factor by highlighting it in the systematic causal diagram. Among them, the AI model of the analysis unit (200) can be established through artificial neural network and random forest, and sensitivity analysis can be carried out through the established machine learning model to quantify the influence degree of each influencing factor on the concrete quality.

9. The monitoring system according to any one of claims 1 to 8, characterized in that The analysis unit (200) can compare the initial data information obtained by the acquisition unit (100) with the design parameters, and perform differential display according to the relationship between the deviation degree corresponding to the deviation of different data information and the preset threshold. Among them, the differential display method is different from the highlighting display method, and the preset threshold of the strong control factor can be set to be lower than that of the weak control factor.

10. A method for monitoring concrete pouring, characterized in that, It includes: Collect the initial data information of one or more process links before concrete pouring; Predict the range of concrete quality obtained after concrete pouring under the current initial conditions based on the AI model to determine the pouring strategy to be executed; When performing the pouring operation according to the pouring strategy, calculate the corresponding evaluation index by using part of the monitoring data obtained for the pouring operation according to the different stages currently in the pouring link, so as to realize the real-time prediction of the concrete quality. Among them, The evaluation indexes include a first evaluation index and a second evaluation index respectively for the initial stage and the later stage of the concrete pouring link, and the switching node is judged to determine the timing of switching from calculating the first evaluation index to calculating the second evaluation index.

Images