Intelligent management system for premixed concrete pouring on construction site

Abstract

The invention, which relates to the technical field of intelligent management, discloses an intelligent management system for premixed concrete pouring at a construction site, comprising a premixed concrete data acquisition module, a premixed concrete quality detection module and a premixed concrete quality early warning module. The concrete data acquisition module inputs raw material information by scanning a two-dimensional code, and monitors concrete hardening, drying, fluidity, stirring pressure and pouring vibration conditions in real time by using temperature and humidity, slump, pressure and vibration sensors; the premixed concrete quality detection module applies a neural network algorithm, establishes a CNN model, accurately judges the concrete quality, reduces false report and missing report, visualizes an analysis result, and generates a quality report; and the premixed concrete quality early warning module triggers alarm information in time based on prediction of the CNN model, and the system realizes comprehensive intelligent monitoring of the premixed concrete pouring process, improves the construction quality and efficiency, and brings intelligent and automatic innovation for construction site management.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent management, and in particular to an intelligent management system for pouring ready-mixed concrete at a construction site. Background Art

[0002] Concrete is a building material made of a mixture of cement, aggregate, water and admixtures. It has the characteristics of strong plasticity, high strength and good durability. It is widely used in construction projects, infrastructure construction and other fields.

[0003] Ready-mixed concrete refers to concrete that is directly used in engineering construction, in which raw materials such as cement, aggregates, fly ash and admixtures are mixed in advance according to a certain ratio in a concrete mixing station or precast concrete plant, and then transported to the construction site by a mixer truck. The intelligent management system for pouring ready-mixed concrete on the construction site can monitor and analyze data in the concrete construction process in real time by integrating sensors and machine learning technology, thereby improving the accuracy and efficiency of quality inspection.

[0004] In the quality inspection of the intelligent management system for premixed concrete pouring at the construction site, the intelligent management system often faces severe challenges in the face of complex and changeable on-site environments. Environmental noise, equipment vibration, and slight changes in material properties may interfere with the system, leading to false positives and missed quality problems, which in turn affect the construction progress and overall quality. In order to overcome this problem, we introduced machine learning algorithms to conduct deep learning and analysis of historical data, identify abnormal patterns and potential risks in the construction process, and thus improve the data processing capabilities and accuracy of the system. At the same time, high-precision sensor technology can monitor the quality parameters of concrete, such as compressive strength, slump, and workability, in real time, providing more comprehensive and accurate data support for the system. By combining advanced machine learning algorithms and sensor technology, the intelligent management system can more accurately judge the quality status of concrete and effectively reduce false positives and missed reports. This not only improves construction efficiency, but also ensures the stability and reliability of construction quality, providing strong support for the digital transformation and intelligent upgrading of the construction industry. Summary of the invention

[0005] In view of the deficiencies in the prior art, the present invention provides an intelligent management system for pouring ready-mixed concrete at a construction site, which solves the problems in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: an intelligent management system for pouring ready-mixed concrete at a construction site, comprising a ready-mixed concrete data acquisition module, a ready-mixed concrete quality detection module and a ready-mixed concrete quality early warning module; The ready-mixed concrete data acquisition module includes scanning the QR code on the raw materials, temperature and humidity sensors, slump sensors, pressure sensors and vibration sensors, collecting the types and proportions of raw materials, measuring the concrete hardening process and water evaporation, calculating the slump value, and monitoring the pressure changes and vibrations during the concrete pouring process; The ready-mixed concrete quality detection module uses a neural network algorithm to determine the quality of concrete, reduce false positives and false negatives, visualize the CNN model analysis results, and generate a quality report; The ready-mixed concrete quality early warning module determines whether to trigger an alarm message based on the prediction results of the CNN model.

[0007] Furthermore, the process of the ready-mixed concrete data collection module collecting the type and proportion information of the raw materials by scanning the barcode on the raw material packaging includes: The staff at the mixing station uses a barcode scanner to scan the barcode on the raw material packaging. The barcode scanner reads the information in the barcode through optical principles and converts it into a digital signal that can be recognized by a computer. When the scanner contacts the barcode, it emits light and receives the reflected light. The raw material information in the barcode is identified based on the reflection intensity and distribution pattern of the light. The received raw material information is analyzed and processed to generate the type and ratio information of the raw materials.

[0008] Furthermore, the process of the ready-mixed concrete data acquisition module measuring the hardening process and water evaporation of concrete through the temperature and humidity sensor includes: Before pouring concrete, the temperature and humidity sensor is arranged in a position that is in close contact with the concrete. The resistance of the thermistor of the temperature sensor changes with the change of temperature. When the temperature rises, the resistance of the thermistor decreases, and when the temperature decreases, the resistance increases. By measuring the change in the resistance of the thermistor, the temperature of the concrete can be inferred. The resistance of the humidity sensor's internal humidity-sensitive element changes with the change in humidity. In an environment with low humidity, the humidity-sensitive material loses moisture, and the movement of its internal charge becomes difficult, the resistance value increases, and the conductivity decreases. In an environment with high humidity, the humidity-sensitive material absorbs moisture, and the presence of water molecules makes it easier for the internal charge of the humidity-sensitive material to move, the resistance value becomes smaller, and the conductivity increases. By measuring the change in the resistance of the humidity-sensitive resistor, the humidity of the concrete can be inferred.

[0009] Furthermore, the process of calculating the slump value by the ready-mixed concrete data acquisition module through the slump sensor includes: The slump sensor consists of a sensing element, a signal processing circuit and an output device. When concrete is poured into the container where the sensor is located, the sensing element is squeezed by the concrete and deformed. When the slump of concrete increases, the concrete is easily deformed, resulting in an increase in the deformation degree of the sensing element. When the slump of concrete decreases, the deformation capacity of concrete weakens, and the deformation degree of the sensing element also decreases accordingly. The sensing element converts the deformation degree into a proportional electrical signal output, which is then amplified and filtered by the signal processing circuit to remove noise and interference. The processed signal is converted into a digital signal and transmitted to the intelligent management system in real time.

[0010] Furthermore, the process of the ready-mixed concrete data acquisition module monitoring the pressure change and vibration of concrete during the pouring process through the pressure sensor and the vibration sensor includes: During the concrete mixing process, pressure changes are generated as the mixer rotates and the concrete is mixed. These pressure changes are closely related to the consistency, component ratio and operating status of the concrete. The pressure sensor works based on the strain effect, monitors and converts the pressure signal generated during the concrete mixing process into an electrical signal for output; When concrete is poured into the formwork, vibration and impact are generated due to the fluidity and gravity of the concrete. These vibration signals are closely related to the cohesion, fluidity and pouring speed of the concrete. The vibration sensor uses internal piezoelectric crystals to monitor the vibration signals during the concrete pouring process and convert them into electrical signals for output.

[0011] Furthermore, the process of the ready-mixed concrete quality detection module using a neural network algorithm to judge the quality of concrete and reduce false positives and false negatives includes: The collected raw data is cleaned to remove noise, outliers and duplicate data, and then the data is integrated and formatted to meet the input requirements of the neural network algorithm. A neural network model for judging the quality status of concrete is constructed. In the forward propagation stage, features related to concrete quality are extracted from the preprocessed data and transmitted through the input layer. The features include the type and proportion information of raw materials, the compressive strength, slump and workability of concrete. After being processed layer by layer by the hidden layer, they finally reach the output layer and output the predicted result of the concrete quality status. If the predicted result of the output layer does not match the actual quality status, the error back propagation stage is entered. In this stage, the error signal is transmitted back to the input layer layer by layer through the hidden layer, and the weights and thresholds of the network are adjusted according to the error signal, so that the predicted output of the network continues to approach the expected output. Through a large amount of training data and learning iterations, the neural network establishes an implicit mathematical model between the input sensor data and the output concrete quality status, thereby realizing accurate judgment of the concrete quality status.

[0012] Furthermore, the ready-mixed concrete quality detection module visualizes the CNN model analysis results, and the process of generating a quality report includes: Extract analysis results related to raw material types and proportions, concrete compressive strength, slump and workability from the neural network model, ensure that the analysis result data is in database format, use Tableau as a visualization tool to generate charts, use bar charts to display the types and proportions of raw materials and the changing trends of concrete compressive strength, use line charts to display the changing trends of slump in real time, use radar charts to intuitively display the performance of workability in different aspects, and embed the generated charts into the interface of the intelligent management system to facilitate construction personnel and managers to quickly understand the quality status of concrete.

[0013] Furthermore, the process of determining whether to trigger an alarm message based on the raw material ratio information, compressive strength and slump prediction results of the ready-mixed concrete quality early warning module of the CNN model includes: Compare the collected raw material types and proportion information with the preset standard proportion, wherein the standard proportion includes that the cement content accounts for 10% to 15% of the total concrete volume, the aggregate content accounts for 60% to 75% of the total concrete volume, and the water and admixture content fluctuation range does not exceed ±1%. If the actual proportion exceeds the allowable fluctuation range, an alarm message is triggered. If the actual proportion is within the allowable fluctuation range, the concrete can be used. The CNN model is used to predict the compressive strength of concrete, and the prediction result is compared with the set minimum compressive strength requirement value. Different concrete strength grades have different minimum compressive strength requirements. In a standard curing environment, C30 is a commonly used concrete strength grade in ordinary construction projects, and the corresponding concrete compressive strength must reach 30MPa or more. If the prediction result is 30MPa or less, an alarm message is triggered. If the prediction result is greater than 30MPa, the concrete can be used. The CNN model is used to calculate and output the slump value in real time. Since the suitable slump range of C30 grade ready-mixed concrete is between 80mm and 180mm, the actual slump value is compared with the suitable range. If the actual slump value exceeds 80mm to 180mm, an alarm message is triggered. If the actual slump value is between 80mm and 180mm, the concrete can be used.

[0014] Furthermore, the process of determining whether to trigger an alarm message by the ready-mixed concrete quality warning module based on the ready-mixed concrete workability analysis result of the CNN model includes: For C30 grade concrete, during the mixing process, its internal pressure will change as the mixing progresses. At the initial stage of mixing, the internal pressure of the concrete is P0. If the internal pressure of the concrete exceeds 1.2P0, is lower than 0.9P0, and lasts for more than 5 seconds, it is considered that the pressure change during the concrete mixing process is abnormal and the concrete fluidity does not meet the standard. During normal pouring, if the vibration frequency of the concrete is between 20 and 50Hz, the vibration amplitude is between 0.2 and 0.5mm, and the vibration time is between 15 and 30 seconds, it is considered that the concrete cohesion and water retention are good. If the vibration frequency of the concrete is not between 20 and 50Hz, the vibration amplitude is not between 0.2 and 0.5mm, and the vibration time is not between 15 and 30 seconds, it is considered that the concrete cohesion and water retention do not meet the standard. Taking into account the fluidity, cohesion and water retention of the concrete, the workability of the concrete is comprehensively evaluated to determine whether the actual workability meets the standard. If the actual workability does not meet the standard, an alarm message is triggered. If the actual workability meets the standard, the concrete can be used.

[0015] The present invention provides an intelligent management system for pouring premixed concrete at a construction site. It has the following beneficial effects: By introducing advanced neural network algorithms and sensor technology, the problem of false alarms and missed alarms of quality issues in the intelligent management system for premixed concrete pouring on construction sites has been significantly solved. First, it improves the quality stability of concrete production. Sensor technology can monitor various parameters in the concrete mixing process in real time, such as raw material ratio, compressive strength, slump and workability, to ensure that production is under strict control, thereby reducing the occurrence of quality problems. Secondly, the application of neural network algorithms has significantly improved the accuracy and reliability of the system. Through the analysis and learning of a large amount of production data, the neural network can identify potential quality problems and accurately issue early warnings, effectively avoiding false alarms and missed alarms. Finally, this intelligent management system also improves production efficiency. The automated management and intelligent control functions reduce the time and cost of manual operations, making concrete production more efficient and economical. At the same time, the system records the entire production process data of each batch of concrete, realizes the traceability of the entire production process, and improves the transparency and credibility of project quality. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 This is a block diagram of an intelligent management system for pouring ready-mixed concrete at a construction site according to an embodiment of the present application. DETAILED DESCRIPTION

[0017] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0018] like Figure 1 As shown, the present invention provides a technical solution: an intelligent management system for pouring ready-mixed concrete at a construction site, comprising a ready-mixed concrete data acquisition module, a ready-mixed concrete quality detection module and a ready-mixed concrete quality early warning module; The ready-mixed concrete data acquisition module includes scanning the QR code on the raw materials, temperature and humidity sensors, slump sensors, pressure sensors and vibration sensors, collecting the types and proportions of raw materials, measuring the concrete hardening process and water evaporation, calculating the slump value, and monitoring the pressure changes and vibrations during the concrete pouring process; The ready-mixed concrete quality detection module uses a neural network algorithm to determine the quality of concrete, reduce false positives and false negatives, visualize the CNN model analysis results, and generate a quality report; The ready-mixed concrete quality early warning module determines whether to trigger an alarm message based on the prediction results of the CNN model.

[0019] The process of the ready-mixed concrete data collection module collecting the type and proportion information of the raw materials by scanning the barcode on the raw material packaging includes: The staff at the mixing station uses a barcode scanner to scan the barcode on the raw material packaging. The barcode scanner reads the information in the barcode through optical principles and converts it into a digital signal that can be recognized by a computer. When the scanner contacts the barcode, it emits light and receives the reflected light. The raw material information in the barcode is identified based on the reflection intensity and distribution pattern of the light. The received raw material information is analyzed and processed to generate the type and ratio information of the raw materials.

[0020] The process of the ready-mixed concrete data acquisition module measuring the hardening process and water evaporation of concrete through the temperature and humidity sensor includes: Before pouring concrete, the temperature and humidity sensor is arranged in a position that is in close contact with the concrete. The resistance of the thermistor of the temperature sensor changes with the change of temperature. When the temperature rises, the resistance of the thermistor decreases, and when the temperature decreases, the resistance increases. By measuring the change in the resistance of the thermistor, the temperature of the concrete can be inferred. The resistance of the humidity sensor's internal humidity-sensitive element changes with the change in humidity. In an environment with low humidity, the humidity-sensitive material loses moisture, and the movement of its internal charge becomes difficult, the resistance value increases, and the conductivity decreases. In an environment with high humidity, the humidity-sensitive material absorbs moisture, and the presence of water molecules makes it easier for the internal charge of the humidity-sensitive material to move, the resistance value becomes smaller, and the conductivity increases. By measuring the change in the resistance of the humidity-sensitive resistor, the humidity of the concrete can be inferred.

[0021] The process of calculating the slump value by the ready-mixed concrete data acquisition module through the slump sensor includes: The slump sensor consists of a sensing element, a signal processing circuit and an output device. When concrete is poured into the container where the sensor is located, the sensing element is squeezed by the concrete and deformed. When the slump of concrete increases, the concrete is easily deformed, resulting in an increase in the deformation degree of the sensing element. When the slump of concrete decreases, the deformation capacity of concrete weakens, and the deformation degree of the sensing element also decreases accordingly. The sensing element converts the deformation degree into a proportional electrical signal output, which is then amplified and filtered by the signal processing circuit to remove noise and interference. The processed signal is converted into a digital signal and transmitted to the intelligent management system in real time.

[0022] The process of the ready-mixed concrete data acquisition module monitoring the pressure change and vibration of concrete during the pouring process through the pressure sensor and the vibration sensor includes: During the concrete mixing process, pressure changes are generated as the mixer rotates and the concrete is mixed. These pressure changes are closely related to the consistency, component ratio and operating status of the concrete. The pressure sensor works based on the strain effect, monitors and converts the pressure signal generated during the concrete mixing process into an electrical signal for output; When concrete is poured into the formwork, vibration and impact are generated due to the fluidity and gravity of the concrete. These vibration signals are closely related to the cohesion, fluidity and pouring speed of the concrete. The vibration sensor uses internal piezoelectric crystals to monitor the vibration signals during the concrete pouring process and convert them into electrical signals for output.

[0023] The process of using a neural network algorithm to determine the quality of concrete and reduce false positives and false negatives in the ready-mixed concrete quality detection module includes: The collected raw data is cleaned to remove noise, outliers and duplicate data, and then the data is integrated and formatted to meet the input requirements of the neural network algorithm. A neural network model for judging the quality status of concrete is constructed. In the forward propagation stage, features related to concrete quality are extracted from the preprocessed data and transmitted through the input layer. The features include the type and proportion information of raw materials, the compressive strength, slump and workability of concrete. After being processed layer by layer by the hidden layer, they finally reach the output layer and output the predicted result of the concrete quality status. If the predicted result of the output layer does not match the actual quality status, the error back propagation stage is entered. In this stage, the error signal is transmitted back to the input layer layer by layer through the hidden layer, and the weights and thresholds of the network are adjusted according to the error signal, so that the predicted output of the network continues to approach the expected output. Through a large amount of training data and learning iterations, the neural network establishes an implicit mathematical model between the input sensor data and the output concrete quality status, thereby realizing accurate judgment of the concrete quality status.

[0024] The ready-mixed concrete quality detection module visualizes the CNN model analysis results, and the process of generating a quality report includes: Extract analysis results related to raw material types and proportions, concrete compressive strength, slump and workability from the neural network model, ensure that the analysis result data is in database format, use Tableau as a visualization tool to generate charts, use bar charts to display the types and proportions of raw materials and the changing trends of concrete compressive strength, use line charts to display the changing trends of slump in real time, use radar charts to intuitively display the performance of workability in different aspects, and embed the generated charts into the interface of the intelligent management system to facilitate construction personnel and managers to quickly understand the quality status of concrete.

[0025] The process of the ready-mixed concrete quality early warning module judging whether to trigger an alarm message based on the raw material ratio information, compressive strength and slump prediction results of the CNN model includes: Compare the collected raw material types and proportion information with the preset standard proportion, wherein the standard proportion includes that the cement content accounts for 10% to 15% of the total concrete volume, the aggregate content accounts for 60% to 75% of the total concrete volume, and the water and admixture content fluctuation range does not exceed ±1%. If the actual proportion exceeds the allowable fluctuation range, an alarm message is triggered. If the actual proportion is within the allowable fluctuation range, the concrete can be used. The CNN model is used to predict the compressive strength of concrete, and the prediction result is compared with the set minimum compressive strength requirement value. Different concrete strength grades have different minimum compressive strength requirements. In a standard curing environment, C30 is a commonly used concrete strength grade in ordinary construction projects, and the corresponding concrete compressive strength must reach 30MPa or more. If the prediction result is 30MPa or less, an alarm message is triggered. If the prediction result is greater than 30MPa, the concrete can be used. The CNN model is used to calculate and output the slump value in real time. Since the suitable slump range of C30 grade ready-mixed concrete is between 80mm and 180mm, the actual slump value is compared with the suitable range. If the actual slump value exceeds 80mm to 180mm, an alarm message is triggered. If the actual slump value is between 80mm and 180mm, the concrete can be used.

[0026] The process of determining whether to trigger an alarm message by the ready-mixed concrete quality early warning module based on the ready-mixed concrete workability analysis result of the CNN model includes: For C30 grade concrete, during the mixing process, its internal pressure will change as the mixing progresses. At the initial stage of mixing, the internal pressure of the concrete is P0. If the internal pressure of the concrete exceeds 1.2P0, is lower than 0.9P0, and lasts for more than 5 seconds, it is considered that the pressure change during the concrete mixing process is abnormal and the concrete fluidity does not meet the standard. During normal pouring, if the vibration frequency of the concrete is between 20 and 50Hz, the vibration amplitude is between 0.2 and 0.5mm, and the vibration time is between 15 and 30 seconds, it is considered that the concrete cohesion and water retention are good. If the vibration frequency of the concrete is not between 20 and 50Hz, the vibration amplitude is not between 0.2 and 0.5mm, and the vibration time is not between 15 and 30 seconds, it is considered that the concrete cohesion and water retention do not meet the standard. Taking into account the fluidity, cohesion and water retention of the concrete, the workability of the concrete is comprehensively evaluated to determine whether the actual workability meets the standard. If the actual workability does not meet the standard, an alarm message is triggered. If the actual workability meets the standard, the concrete can be used.

[0027] How to use this system: First, the data acquisition module uses the QR code scanning function to input raw material information to ensure that the information is accurate. At the same time, the temperature, humidity, slump, pressure and vibration sensors integrated in the module will monitor the concrete hardening, dryness, fluidity, mixing pressure and vibration during the pouring process in real time, providing detailed data for subsequent analysis. Then, the data processing module uses advanced CNN neural network algorithms to accurately analyze these data to judge the quality of concrete, significantly reduce false positives and false negatives, and display the analysis results in a visual form, automatically generate quality reports, and facilitate managers to intuitively understand the quality of concrete. Finally, based on the prediction results of the CNN model, the data analysis module will immediately trigger an alarm message once an abnormality and potential quality problems are detected, reminding managers to take timely measures. The entire system realizes comprehensive intelligent monitoring of the ready-mixed concrete pouring process, significantly improves construction quality and efficiency, and brings an intelligent and automated innovation experience to construction site management.

[0028] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the statement "includes an element defined by..." does not exclude the presence of other identical elements in the process, method, article or device including the element.

[0029] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. An intelligent management system for pouring ready-mixed concrete at a construction site, characterized in that: It includes ready-mixed concrete data acquisition module, ready-mixed concrete quality detection module and ready-mixed concrete quality early warning module; The ready-mixed concrete data acquisition module includes scanning the QR code on the raw materials, temperature and humidity sensors, slump sensors, pressure sensors and vibration sensors, collecting the types and proportions of raw materials, measuring the concrete hardening process and water evaporation, calculating the slump value, and monitoring the pressure changes and vibrations during the concrete pouring process; The ready-mixed concrete quality detection module uses a neural network algorithm to determine the quality of concrete, reduce false positives and false negatives, visualize the CNN model analysis results, and generate a quality report; The ready-mixed concrete quality early warning module determines whether to trigger an alarm message based on the prediction results of the CNN model.

2. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 1, characterized in that: The process of the ready-mixed concrete data collection module collecting the type and proportion information of the raw materials by scanning the barcode on the raw material packaging includes: The staff at the mixing station uses a barcode scanner to scan the barcode on the raw material packaging. The barcode scanner reads the information in the barcode through optical principles and converts it into a digital signal that can be recognized by a computer. When the scanner contacts the barcode, it emits light and receives the reflected light. The raw material information in the barcode is identified based on the reflection intensity and distribution pattern of the light. The received raw material information is analyzed and processed to generate the type and ratio information of the raw materials.

3. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 2, characterized in that: The process of the ready-mixed concrete data acquisition module measuring the hardening process and water evaporation of concrete through the temperature and humidity sensor includes: Before pouring concrete, the temperature and humidity sensor is arranged in a position that is in close contact with the concrete. The resistance of the thermistor of the temperature sensor changes with the change of temperature. When the temperature rises, the resistance of the thermistor decreases, and when the temperature decreases, the resistance increases. By measuring the change in the resistance of the thermistor, the temperature of the concrete can be inferred. The resistance of the humidity sensor's internal humidity-sensitive element changes with the change in humidity. In an environment with low humidity, the humidity-sensitive material loses moisture, and the movement of its internal charge becomes difficult, the resistance value increases, and the conductivity decreases. In an environment with high humidity, the humidity-sensitive material absorbs moisture, and the presence of water molecules makes it easier for the internal charge of the humidity-sensitive material to move, the resistance value becomes smaller, and the conductivity increases. By measuring the change in the resistance of the humidity-sensitive resistor, the humidity of the concrete can be inferred.

4. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 3, characterized in that: The process of calculating the slump value by the ready-mixed concrete data acquisition module through the slump sensor includes: The slump sensor consists of a sensing element, a signal processing circuit and an output device. When concrete is poured into the container where the sensor is located, the sensing element is squeezed by the concrete and deformed. When the slump of concrete increases, the concrete is easily deformed, resulting in an increase in the deformation degree of the sensing element. When the slump of concrete decreases, the deformation capacity of concrete weakens, and the deformation degree of the sensing element also decreases accordingly. The sensing element converts the deformation degree into a proportional electrical signal output, which is then amplified and filtered by the signal processing circuit to remove noise and interference. The processed signal is converted into a digital signal and transmitted to the intelligent management system in real time.

5. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 4, characterized in that: The process of the ready-mixed concrete data acquisition module monitoring the pressure change and vibration of concrete during the pouring process through the pressure sensor and the vibration sensor includes: During the concrete mixing process, pressure changes are generated as the mixer rotates and the concrete is mixed. These pressure changes are closely related to the consistency, component ratio and operating status of the concrete. The pressure sensor works based on the strain effect, monitors and converts the pressure signal generated during the concrete mixing process into an electrical signal for output; When concrete is poured into the formwork, vibration and impact are generated due to the fluidity and gravity of the concrete. These vibration signals are closely related to the cohesion, fluidity and pouring speed of the concrete. The vibration sensor uses internal piezoelectric crystals to monitor the vibration signals during the concrete pouring process and convert them into electrical signals for output.

6. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 5, characterized in that: The process of using a neural network algorithm to determine the quality of concrete and reduce false positives and false negatives in the ready-mixed concrete quality detection module includes: The collected raw data is cleaned to remove noise, outliers and duplicate data, and then the data is integrated and formatted to meet the input requirements of the neural network algorithm. A neural network model for judging the quality status of concrete is constructed. In the forward propagation stage, features related to concrete quality are extracted from the preprocessed data and transmitted through the input layer. The features include the type and proportion information of raw materials, the compressive strength, slump and workability of concrete. After being processed layer by layer by the hidden layer, they finally reach the output layer and output the predicted result of the concrete quality status. If the predicted result of the output layer does not match the actual quality status, the error back propagation stage is entered. In this stage, the error signal is transmitted back to the input layer layer by layer through the hidden layer, and the weights and thresholds of the network are adjusted according to the error signal, so that the predicted output of the network continues to approach the expected output. Through a large amount of training data and learning iterations, the neural network establishes an implicit mathematical model between the input sensor data and the output concrete quality status, thereby realizing accurate judgment of the concrete quality status.

7. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 6, characterized in that: The ready-mixed concrete quality detection module visualizes the CNN model analysis results, and the process of generating a quality report includes: Extract analysis results related to raw material types and proportions, concrete compressive strength, slump and workability from the neural network model, ensure that the analysis result data is in database format, use Tableau as a visualization tool to generate charts, use bar charts to display the types and proportions of raw materials and the changing trends of concrete compressive strength, use line charts to display the changing trends of slump in real time, use radar charts to intuitively display the performance of workability in different aspects, and embed the generated charts into the interface of the intelligent management system to facilitate construction personnel and managers to quickly understand the quality status of concrete.

8. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 7, characterized in that: The process of the ready-mixed concrete quality early warning module judging whether to trigger an alarm message based on the raw material ratio information, compressive strength and slump prediction results of the CNN model includes: Compare the collected raw material types and proportion information with the preset standard proportion, wherein the standard proportion includes that the cement content accounts for 10% to 15% of the total concrete volume, the aggregate content accounts for 60% to 75% of the total concrete volume, and the water and admixture content fluctuation range does not exceed ±1%. If the actual proportion exceeds the allowable fluctuation range, an alarm message is triggered. If the actual proportion is within the allowable fluctuation range, the concrete can be used. The CNN model is used to predict the compressive strength of concrete, and the prediction result is compared with the set minimum compressive strength requirement value. Different concrete strength grades have different minimum compressive strength requirements. In a standard curing environment, C30 is a commonly used concrete strength grade in ordinary construction projects, and the corresponding concrete compressive strength must reach 30MPa or more. If the prediction result is 30MPa or less, an alarm message is triggered. If the prediction result is greater than 30MPa, the concrete can be used. The CNN model is used to calculate and output the slump value in real time. Since the suitable slump range of C30 grade ready-mixed concrete is between 80mm and 180mm, the actual slump value is compared with the suitable range. If the actual slump value exceeds 80mm to 180mm, an alarm message is triggered. If the actual slump value is between 80mm and 180mm, the concrete can be used.

9. The intelligent management system for pouring ready-mixed concrete at a construction site according to claim 8, characterized in that: The process of determining whether to trigger an alarm message by the ready-mixed concrete quality early warning module based on the ready-mixed concrete workability analysis result of the CNN model includes: For C30 grade concrete, during the mixing process, its internal pressure will change as the mixing progresses. At the initial stage of mixing, the internal pressure of the concrete is P0. If the internal pressure of the concrete exceeds 1.2P0, is lower than 0.9P0, and lasts for more than 5 seconds, it is considered that the pressure change during the concrete mixing process is abnormal and the concrete fluidity does not meet the standard. During normal pouring, if the vibration frequency of the concrete is between 20 and 50Hz, the vibration amplitude is between 0.2 and 0.5mm, and the vibration time is between 15 and 30 seconds, it is considered that the concrete cohesion and water retention are good. If the vibration frequency of the concrete is not between 20 and 50Hz, the vibration amplitude is not between 0.2 and 0.5mm, and the vibration time is not between 15 and 30 seconds, it is considered that the concrete cohesion and water retention do not meet the standard. Taking into account the fluidity, cohesion and water retention of the concrete, the workability of the concrete is comprehensively evaluated to determine whether the actual workability meets the standard. If the actual workability does not meet the standard, an alarm message is triggered. If the actual workability meets the standard, the concrete can be used.

Images