Concrete construction quality monitoring platform based on Internet of Things

Abstract

A concrete construction quality monitoring platform based on Internet of Things relates to the technical field of Internet of Things and is composed of a data acquisition module, a data processing module, a data analysis module and a data interaction module. The data acquisition module is used for monitoring various parameters in concrete construction in real time through various sensors and transmitting data through a wireless sensing network. The data processing module is used for preprocessing the collected data through an edge computing device and extracting feature data by using a principal component analysis method; the data analysis module is used for generating a detailed pouring plan by using a neural network algorithm and monitoring and controlling the concrete quality in real time by using a machine vision technology; storing the processed data through cloud storage; the data interaction module displays monitoring data and analysis results through a Web terminal and a mobile terminal; through the steps, the system can solve the problems of inaccurate data acquisition and limited monitoring range in existing concrete construction.

Description

Technical Field

[0001] The present invention relates to the technical field of Internet of Things, and in particular to a concrete construction quality monitoring platform based on the Internet of Things. Background Art

[0002] The safe construction and monitoring of various large-scale projects are long-term concerns of architectural design and construction units. There are relatively mature theories for pouring large-volume concrete, but there are many factors in the pouring of large-volume concrete, including the geometric shape of the concrete structure, constraints, and changes in parameters such as elastic modulus, hydration heat, and thermal expansion coefficient during the concrete hardening process, which will cause temperature cracks in the poured large-volume concrete, which affects the quality of the project to a certain extent.

[0003] Concrete construction quality monitoring is an important part of ensuring the quality and safety of construction projects. Traditional concrete construction quality monitoring methods mainly rely on manual inspection and experience judgment, which has many shortcomings. First, data collection is inaccurate, and traditional methods are difficult to obtain various parameters in the concrete construction process in real time and accurately; second, the monitoring range is limited, and traditional methods can usually only cover local areas and cannot achieve comprehensive monitoring; third, the real-time performance is poor, and traditional methods are difficult to detect and deal with potential quality problems in a timely manner. In recent years, with the development of Internet of Things technology, concrete construction quality monitoring technology based on the Internet of Things has gradually become a research hotspot. Through the Internet of Things technology, all-round monitoring and management of concrete projects from pouring, maintenance, quality inspection to component installation can be achieved, thereby effectively improving the level of project quality management. However, although some existing monitoring systems can achieve a certain degree of automated monitoring, they lack the integration of Internet of Things technology, data transmission and sharing are inconvenient, and monitoring data cannot be fed back to relevant personnel for analysis and decision-making in a timely manner. In addition, the construction process has high requirements for personnel, and abnormal situations rely on manual experience, which is highly subjective and uncertain. Summary of the invention

[0004] In order to solve the above problems, the object of the present invention is to provide a concrete construction quality monitoring platform based on the Internet of Things, which is composed of a data acquisition module, a data processing module, a data analysis module and a data interaction module; The data acquisition module is used to monitor various parameters in concrete construction in real time through a variety of sensors, arrange detection points according to construction progress and structural characteristics, and transmit data using a wireless sensor network; The data processing module is used to pre-process the collected data through the edge computing device, remove noise and outliers, and convert the data format; extract feature data using the principal component analysis method; The data analysis module: generates a detailed pouring plan using a neural network algorithm, monitors and controls concrete quality in real time using machine vision technology, and stores processed data via cloud storage; The data interaction module displays monitoring data and analysis results and command input in real time through the Web terminal and mobile terminal; Furthermore, the process of the data acquisition module monitoring various parameters in concrete construction in real time through a variety of sensors includes: Sensors including temperature sensors, humidity sensors, stress sensors, and strain sensors are used to collect various parameters during the concrete construction process in real time; Temperature sensors are used to monitor temperature changes during concrete pouring and curing; humidity sensors are used to monitor humidity changes during concrete pouring and curing; stress sensors are used to monitor stress changes in concrete components during construction; strain sensors are used to monitor strain changes in concrete components during construction.

[0005] Furthermore, the process of arranging sensor detection points according to the construction progress and structural characteristics of the data acquisition module includes: Sensors are embedded in the test piece in advance to measure temperature and stress changes. The data of each measuring point is collected and processed using a wireless sensor network. The base station set up by the computer collects the data of wireless sensors in each area. In beam structures, sensors are installed at the mid-span and key parts of the supports of beams; in column structures, sensors are installed at the bottom, top and middle parts of the columns; 1 to 2 measuring positions are arranged on the pouring operation surface every day and night according to the construction progress; measuring positions can be arranged at the edges, corners, middle parts of concrete, water pits, and elevator shaft edges; when the thickness of the concrete casting is uniform, the measuring position spacing is 10m to 15m, and the number of measuring positions can be increased at the parts with variable cross-sections; on the facade of the wall, the horizontal spacing of the measuring positions is 5m to 10m, and the vertical spacing is 3m to 5m; According to the thickness of concrete, 3 to 5 measuring points are arranged at each measuring position, which are located at the surface, center, bottom layer, middle upper part and middle lower part of the concrete respectively; when water cooling is carried out, the measuring position is arranged in the middle position of two adjacent cooling water pipes, and temperature measuring points are arranged at the inlet and outlet of the cooling water pipe respectively; The temperature measuring point of the concrete surface should be arranged at 50mm from the concrete surface; the temperature measuring point of the bottom layer should be arranged at 50mm to 100mm above the bottom surface of the concrete casting; When the temperature sensor is directly buried in concrete, protective measures should be taken for the sensor and transmission wire to prevent damage to the sensor and wire during construction; the temperature sensor should be placed in a metal protective tube with a diameter of 20mm to 30mm for protection. The bottom of the metal tube should be sealed in advance, preferably 300mm exposed from the concrete surface, and the metal tube should be fixed; after the temperature sensor is placed, the upper end of the metal tube should be sealed and protected.

[0006] Furthermore, the process of the data acquisition module transmitting the data collected by the sensor to the data processing platform by using the wireless sensor network to transmit data includes: Data transmission supports multiple communication protocols and adopts low-power wide area network technology to realize remote transmission of sensor data. NB-IoT module data transmission is used to realize data transmission of narrowband Internet of Things. NB-IoT technology has the characteristics of low power consumption, wide coverage and low cost, and can stably transmit data in complex construction environments.

[0007] Furthermore, the data processing module is used to pre-process the collected data through the edge computing device, remove noise and outliers, and convert the data format; the process of extracting feature data using the principal component analysis method includes: The edge computing device pre-processes the collected data to remove noise and outliers; the pre-processed data is transmitted to the cloud platform server via the Internet; Preprocess the received data, including data cleaning and format conversion operations; use statistical methods to determine data outliers based on the mean and standard deviation of the data; use high-pass filtering to remove noise from the data; Remove outliers from collected data and convert data in different formats into a unified format; Finally, data features are extracted from the preprocessed data; features that can reflect the state of the concrete construction process, the stress fluctuation range, and the changing trends of temperature and humidity are extracted from the historical data of the concrete pouring process; and the principal component analysis method is used to convert multiple related variables into unrelated variables, thereby reducing the dimension of the data while retaining the main features of the data.

[0008] Furthermore, the data analysis module generates a detailed pouring plan using a neural network algorithm, and the process of using machine vision technology to monitor and control concrete quality in real time includes: Before concrete construction, the neural network algorithm of the machine learning algorithm is used to learn historical data, and according to the amount of concrete required for the building and the raw material quality inspection report input by the data interaction module, the amount of cement, sand, gravel, water, and admixture is analyzed, and a pouring plan is generated, including partial pouring, formwork installation, steel bar binding, uniform pouring and vibration of concrete, and maintenance plan after pouring. The number of neural network layers and the number of neurons in each layer are determined based on the input and output features. The number of neurons in the input layer will correspond to the number of input features, the amount of concrete required for the building, and the number of key parameters in the quality inspection report of cement, sand, gravel, water, and admixtures. The number of neurons in the output layer will correspond to the output results, i.e. the amount of cement, sand, gravel, water, and admixtures, as well as the various contents of the pouring plan, including the order of partial pouring, formwork installation details, steel bar binding requirements, parameters for uniform concrete pouring and vibration, and post-pouring maintenance plans. The number of layers and neurons in the hidden layer can be determined by experiments or empirical rules. Try fewer hidden layers and neurons first, and then adjust according to the performance of the model. Number of neurons in the hidden layer Determined by the following formula:

[0009] is the number of neurons in the input layer; is the number of neurons in the output layer; Collect relevant data from historical concrete construction projects, including building scale, raw material quality inspection reports, and corresponding construction plans, as the basis for neural network learning; divide the collected data into training set, validation set, and test set; the training set is used to train the neural network model, the validation set is used to adjust the model's hyperparameters during the training process, and the test set is used to evaluate the performance of the final model; During the training process, the neural network uses the back propagation algorithm to adjust the connection weights between neurons based on the input data, i.e., the amount of concrete required for construction and the raw material quality inspection report, and the expected output, which includes the error between the amount of raw materials used and the construction plan. The training process is iterated continuously until the model reaches the preset number of iterations. The mean square error is used to evaluate the performance of the model on the test set. If the model has a large error, the cause is analyzed and the number of hidden layers of the network structure is adjusted until the error meets the "Concrete Structure Engineering Construction Quality Acceptance Code"; During concrete construction, moisture sensors are installed in the pouring pipes to monitor the moisture content of concrete. Combined with pre-buried sensors, the IoT platform uses a curve chart to visually describe temperature changes based on the on-site temperature measurement data table. The temperature measurement curve trend chart automatically generates a scientific data query basis for the temperature rise and fall trends of large-volume concrete. The temperature difference between the inside and outside of large-volume concrete is monitored to be controlled within 25°C, and an alarm is automatically sounded when the temperature reaches the warning value, reminding relevant personnel. When the temperature reaches the warning value, the temperature of the cooling circulating water is reduced and the water flow rate is increased to take away the internal heat of the concrete. In the concrete vibration construction quality monitoring based on machine vision, the collected videos of workers' behavior and actions and video image data of concrete vibration surface status are processed to monitor the vibration construction quality and the wearing of safety helmets in real time. When quality problems are found, timely feedback is given to the construction site managers so that the construction process and parameters can be adjusted in time to ensure the quality of concrete construction.

[0010] Furthermore, the process of storing the processed data by the data analysis module through cloud storage includes: Users transfer data to the cloud service provider's server through the network; cloud storage usually adopts a distributed storage architecture, and data is stored in multiple copies in different physical locations; During data storage, cloud services use redundant backup and disaster recovery technologies to ensure data security and reliability; cloud storage provides multi-level security controls, including identity authentication, access control, and data encryption technology; Users manage data through the management tools and API interfaces provided by the cloud storage platform, including data organization, retrieval, and processing; The cloud storage platform sets permissions and access control functions so that only authorized users can access data; user identities are verified through usernames and passwords; users set different access permissions, including read, write, and delete permissions, and permissions are allocated based on user roles or user groups.

[0011] Furthermore, the data interaction module displays monitoring data and analysis results in real time and inputs commands through the Web terminal and the mobile terminal, including: Monitoring data and analysis results are displayed in real time through the Web and mobile terminals, supporting a variety of chart formats; the data display terminal supports multi-user access and permission management; Construction managers can view monitoring data through the Web and mobile terminals. The data display terminal supports multi-language interface. Before concrete construction, supervisors upload the raw material types and quality inspection reports. The data analysis module can extract quality information and concrete construction plans based on the quality inspection reports. The construction plans are sent to the data interaction module, and construction personnel implement them according to the plans. After concrete construction, operators input control instructions through the data interaction interface to view the operating status and data of the maintenance equipment; the interactive interface displays real-time data, alarm information and processing methods obtained from data analysis.

[0012] The beneficial effects of the present invention are: A concrete construction quality monitoring platform based on the Internet of Things is provided. It uses various types of high-precision sensors to collect various parameters in the concrete construction process in real time, adopts wireless communication technology to realize remote data transmission, and displays monitoring data and analysis results in real time through the Web and mobile terminals.

[0013] The neural network algorithm of the machine learning algorithm is used to analyze the dosage of cement, sand, gravel, water, and admixtures, and generate a pouring plan; this includes partial pouring, formwork installation, steel bar binding, uniform pouring and vibration of concrete, and maintenance plan after pouring; it has low requirements on the level of construction personnel.

[0014] The present invention can monitor various parameters in the process of concrete pouring and curing in real time to ensure the quality of the project. The monitoring platform can provide real-time feedback on the state of concrete, helping construction managers to adjust the construction plan in time to avoid quality problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0015] Figure 1 This is a block diagram of a concrete construction quality monitoring platform based on the Internet of Things according to an embodiment of the present application. DETAILED DESCRIPTION

[0016] The following is a clear and complete description of the technical solutions in the embodiments of the present application in conjunction with the drawings in the embodiments of the present application. Obviously, the described embodiments are part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present application.

[0017] like Figure 1 As shown, a concrete construction quality monitoring platform based on the Internet of Things is composed of a data acquisition module, a data processing module, a data analysis module and a data interaction module; The data acquisition module is used to monitor various parameters in concrete construction in real time through a variety of sensors, arrange detection points according to the construction progress and structural characteristics, and transmit data using a wireless sensor network; The data processing module is used to pre-process the collected data through edge computing devices, remove noise and outliers, and convert data formats; and extract feature data using the principal component analysis method; Data analysis module: Generate detailed pouring plans using neural network algorithms, monitor and control concrete quality in real time using machine vision technology; store processed data through cloud storage; The data interaction module displays monitoring data and analysis results in real time as well as command input through the Web and mobile terminals; The process of real-time monitoring of various parameters in concrete construction by the data acquisition module through a variety of sensors includes: Sensors including temperature sensors, humidity sensors, stress sensors, and strain sensors are used to collect various parameters during the concrete construction process in real time; Temperature sensors are used to monitor temperature changes during concrete pouring and curing; humidity sensors are used to monitor humidity changes during concrete pouring and curing; stress sensors are used to monitor stress changes in concrete components during construction; strain sensors are used to monitor strain changes in concrete components during construction.

[0018] The process of arranging sensor detection points for the data acquisition module according to the construction progress and structural characteristics includes: Sensors are embedded in the test piece in advance to measure temperature and stress changes. The data of each measuring point is collected and processed using a wireless sensor network. The base station set up by the computer collects the data of wireless sensors in each area. In beam structures, sensors are installed at the mid-span and key parts of the supports of beams; in column structures, sensors are installed at the bottom, top and middle parts of the columns; 1 to 2 measuring positions are arranged on the pouring operation surface every day and night according to the construction progress; measuring positions can be arranged at the edges, corners, middle parts of concrete, water pits, and elevator shaft edges; when the thickness of the concrete casting is uniform, the measuring position spacing is 10m to 15m, and the number of measuring positions can be increased at the parts with variable cross-sections; on the facade of the wall, the horizontal spacing of the measuring positions is 5m to 10m, and the vertical spacing is 3m to 5m; According to the thickness of concrete, 3 to 5 measuring points are arranged at each measuring position, which are located at the surface, center, bottom layer, middle upper part and middle lower part of the concrete respectively; when water cooling is carried out, the measuring position is arranged in the middle position of two adjacent cooling water pipes, and temperature measuring points are arranged at the inlet and outlet of the cooling water pipe respectively; The temperature measuring point of the concrete surface should be arranged at 50mm from the concrete surface; the temperature measuring point of the bottom layer should be arranged at 50mm to 100mm above the bottom surface of the concrete casting; When the temperature sensor is directly buried in concrete, protective measures should be taken for the sensor and transmission wire to prevent damage to the sensor and wire during construction; the temperature sensor should be placed in a metal protective tube with a diameter of 20mm to 30mm for protection. The bottom of the metal tube should be sealed in advance, preferably 300mm exposed from the concrete surface, and the metal tube should be fixed; after the temperature sensor is placed, the upper end of the metal tube should be sealed and protected.

[0019] The process of transmitting the data collected by the sensor to the data processing platform by using the wireless sensor network to transmit the data acquisition module includes: Data transmission supports multiple communication protocols and adopts low-power wide area network technology to realize remote transmission of sensor data. NB-IoT module data transmission is used to realize data transmission of narrowband Internet of Things. NB-IoT technology has the characteristics of low power consumption, wide coverage and low cost, and can stably transmit data in complex construction environments.

[0020] The data processing module is used to pre-process the collected data through the edge computing device, remove noise and outliers, and convert the data format; the process of extracting feature data using the principal component analysis method includes: The edge computing device pre-processes the collected data to remove noise and outliers; the pre-processed data is transmitted to the cloud platform server via the Internet; Preprocess the received data, including data cleaning and format conversion operations; use statistical methods to determine data outliers based on the mean and standard deviation of the data; use high-pass filtering to remove noise from the data; Remove outliers from collected data and convert data in different formats into a unified format; Finally, data features are extracted from the preprocessed data; features that can reflect the state of the concrete construction process, the stress fluctuation range, and the changing trends of temperature and humidity are extracted from the historical data of the concrete pouring process; and the principal component analysis method is used to convert multiple related variables into unrelated variables, thereby reducing the dimension of the data while retaining the main features of the data.

[0021] The process of using a neural network algorithm to generate a detailed pouring plan for the data analysis module and using machine vision technology to monitor and control concrete quality in real time includes: Before concrete construction, the neural network algorithm of the machine learning algorithm is used to learn historical data, and according to the amount of concrete required for the building and the raw material quality inspection report input by the data interaction module, the amount of cement, sand, gravel, water, and admixture is analyzed, and a pouring plan is generated, including partial pouring, formwork installation, steel bar binding, uniform pouring and vibration of concrete, and maintenance plan after pouring. The number of neural network layers and the number of neurons in each layer are determined based on the input and output features. The number of neurons in the input layer will correspond to the number of input features, the amount of concrete required for the building, and the number of key parameters in the quality inspection report of cement, sand, gravel, water, and admixtures. The number of neurons in the output layer will correspond to the output results, i.e. the amount of cement, sand, gravel, water, and admixtures, as well as the various contents of the pouring plan, including the order of partial pouring, formwork installation details, steel bar binding requirements, parameters for uniform concrete pouring and vibration, and post-pouring maintenance plans. The number of layers and neurons in the hidden layer can be determined by experiments or empirical rules. Try fewer hidden layers and neurons first, and then adjust according to the performance of the model. Number of neurons in the hidden layer Determined by the following formula:

[0022] is the number of neurons in the input layer; is the number of neurons in the output layer; Collect relevant data from historical concrete construction projects, including building scale, raw material quality inspection reports, and corresponding construction plans, as the basis for neural network learning; divide the collected data into training set, validation set, and test set; the training set is used to train the neural network model, the validation set is used to adjust the model's hyperparameters during the training process, and the test set is used to evaluate the performance of the final model; During the training process, the neural network uses the back propagation algorithm to adjust the connection weights between neurons based on the input data, i.e., the amount of concrete required for construction and the raw material quality inspection report, and the expected output, which includes the error between the amount of raw materials used and the construction plan. The training process is iterated continuously until the model reaches the preset number of iterations. The mean square error is used to evaluate the performance of the model on the test set. If the model has a large error, the cause is analyzed and the number of hidden layers of the network structure is adjusted until the error meets the "Concrete Structure Engineering Construction Quality Acceptance Code"; During concrete construction, moisture sensors are installed in the pouring pipes to monitor the moisture content of concrete. Combined with pre-buried sensors, the IoT platform uses a curve chart to visually describe temperature changes based on the on-site temperature measurement data table. The temperature measurement curve trend chart automatically generates a scientific data query basis for the temperature rise and fall trends of large-volume concrete. The temperature difference between the inside and outside of large-volume concrete is monitored to be controlled within 25°C, and an alarm is automatically sounded when the temperature reaches the warning value, reminding relevant personnel. When the temperature reaches the warning value, the temperature of the cooling circulating water is reduced and the water flow rate is increased to take away the internal heat of the concrete. In the concrete vibration construction quality monitoring based on machine vision, the collected videos of workers' behavior and actions and video image data of concrete vibration surface status are processed to monitor the vibration construction quality and the wearing of safety helmets in real time. When quality problems are found, timely feedback is given to the construction site managers so that the construction process and parameters can be adjusted in time to ensure the quality of concrete construction.

[0023] The process of storing the processed data by the data analysis module through cloud storage includes: Users transfer data to the cloud service provider's server through the network; cloud storage usually adopts a distributed storage architecture, and data is stored in multiple copies in different physical locations; During data storage, cloud services use redundant backup and disaster recovery technologies to ensure data security and reliability; cloud storage provides multi-level security controls, including identity authentication, access control, and data encryption technology; Users manage data through the management tools and API interfaces provided by the cloud storage platform, including data organization, retrieval, and processing; The cloud storage platform sets permissions and access control functions so that only authorized users can access data; user identities are verified through usernames and passwords; users set different access permissions, including read, write, and delete permissions, and permissions are allocated based on user roles or user groups.

[0024] The process of real-time display of monitoring data and analysis results and command input for the data interaction module through the Web terminal and the mobile terminal includes: Monitoring data and analysis results are displayed in real time through the Web and mobile terminals, supporting a variety of chart formats; the data display terminal supports multi-user access and permission management; Construction managers can view monitoring data through the Web and mobile terminals. The data display terminal supports multi-language interface. Before concrete construction, supervisors upload the raw material types and quality inspection reports. The data analysis module can extract quality information and concrete construction plans based on the quality inspection reports. The construction plans are sent to the data interaction module, and construction personnel implement them according to the plans. After concrete construction, operators input control instructions through the data interaction interface to view the operating status and data of the maintenance equipment; the interactive interface displays real-time data, alarm information and processing methods obtained from data analysis.

[0025] The concrete construction quality monitoring platform based on the Internet of Things described in this embodiment includes the following steps: Step 1: During the concrete construction process, various sensors are installed inside the specimen or at key locations in advance to monitor various parameters during the concrete construction process in real time; Step 2: Transmit data to the central data processing system via low-power wide area network technology; Step 3: The edge computing device pre-processes the data, removes noise and outliers, performs data cleaning and format conversion; uses principal component analysis technology to reduce data dimensions and extract the most important feature data; Step 4: Use machine learning algorithms to conduct in-depth analysis to determine the amount of cement, sand, gravel, water, and admixtures, and generate a pouring plan; use machine vision to monitor the quality of concrete vibration construction during the construction process; Step 5: Store all data in the cloud platform and authorize users to access the data through identity authentication; Step 6: Through the visual interface, construction managers can intuitively view the changing trends and analysis results of various parameters; The above embodiments are only used to illustrate the technical method of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical method of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical method of the present invention.

Claims

1. A concrete construction quality monitoring platform based on the Internet of Things, relating to the technical field of the Internet of Things, characterized in that: It consists of data acquisition module, data processing module, data analysis module and data interaction module; The data acquisition module is used to monitor various parameters in concrete construction in real time through a variety of sensors, arrange detection points according to construction progress and structural characteristics, and transmit data using a wireless sensor network; The data processing module is used to pre-process the collected data through the edge computing device, remove noise and outliers, and convert the data format; and extract feature data using the principal component analysis method; The data analysis module: generates a detailed pouring plan using a neural network algorithm, monitors and controls concrete quality in real time using machine vision technology, and stores processed data via cloud storage; The data interaction module displays monitoring data and analysis results as well as command input in real time through the Web terminal and mobile terminal.

2. According to the Internet of Things-based concrete construction quality monitoring platform of claim 1, it is characterized in that: The process of the data acquisition module monitoring various parameters in concrete construction in real time through a variety of sensors includes: Sensors including temperature sensors, humidity sensors, stress sensors, and strain sensors are used to collect various parameters during the concrete construction process in real time; Temperature sensors are used to monitor temperature changes during concrete pouring and curing; humidity sensors are used to monitor humidity changes during concrete pouring and curing; stress sensors are used to monitor stress changes in concrete components during construction; strain sensors are used to monitor strain changes in concrete components during construction.

3. The concrete construction quality monitoring platform based on the Internet of Things according to claim 1 is characterized in that: The process of arranging sensor detection points according to the construction progress and structural characteristics of the data acquisition module includes: Sensors are embedded in the test piece in advance to measure temperature and stress changes. The data of each measuring point is collected and processed using a wireless sensor network. The base station set up by the computer collects the data of wireless sensors in each area. In beam structures, sensors are installed at the mid-span and key parts of the supports of beams; in column structures, sensors are installed at the bottom, top and middle parts of the columns; 1 to 2 measuring positions are arranged on the pouring operation surface every day and night according to the construction progress; measuring positions can be arranged at the edges, corners, middle parts of concrete, water pits, and elevator shaft edges; when the thickness of the concrete casting is uniform, the measuring position spacing is 10m to 15m, and the number of measuring positions can be increased at the parts with variable cross-sections; on the facade of the wall, the horizontal spacing of the measuring positions is 5m to 10m, and the vertical spacing is 3m to 5m; According to the thickness of concrete, 3 to 5 measuring points are arranged at each measuring position, which are located at the surface, center, bottom layer, middle upper part and middle lower part of the concrete respectively; when water cooling is carried out, the measuring position is arranged in the middle position of two adjacent cooling water pipes, and temperature measuring points are arranged at the inlet and outlet of the cooling water pipe respectively; The temperature measuring point of the concrete surface should be arranged at 50mm from the concrete surface; the temperature measuring point of the bottom layer should be arranged at 50mm to 100mm above the bottom surface of the concrete casting; When the temperature sensor is directly buried in concrete, protective measures should be taken for the sensor and transmission wire to prevent damage to the sensor and wire during construction; the temperature sensor should be placed in a metal protective tube with a diameter of 20mm to 30mm for protection. The bottom of the metal tube should be sealed in advance, preferably 300mm exposed from the concrete surface, and the metal tube should be fixed; after the temperature sensor is placed, the upper end of the metal tube should be sealed and protected.

4. The concrete construction quality monitoring platform based on the Internet of Things according to claim 1 is characterized in that: The process of the data acquisition module using the wireless sensor network to transmit the data collected by the sensor to the data processing platform includes: Data transmission supports multiple communication protocols and adopts low-power wide area network technology to realize remote transmission of sensor data. NB-IoT module data transmission is used to realize data transmission of narrowband Internet of Things. NB-IoT technology has the characteristics of low power consumption, wide coverage and low cost, and can stably transmit data in complex construction environments.

5. The concrete construction quality monitoring platform based on the Internet of Things according to claim 1 is characterized in that: The data processing module is used to pre-process the collected data through the edge computing device, remove noise and outliers, and perform data format conversion; The process of extracting feature data using principal component analysis includes: The edge computing device pre-processes the collected data to remove noise and outliers; the pre-processed data is transmitted to the cloud platform server via the Internet; Preprocess the received data, including data cleaning and format conversion operations; use statistical methods to determine data outliers based on the mean and standard deviation of the data; use high-pass filtering to remove noise from the data; Remove outliers from collected data and convert data in different formats into a unified format; Finally, data features are extracted from the preprocessed data; features that can reflect the state of the concrete construction process, the stress fluctuation range, and the changing trends of temperature and humidity are extracted from the historical data of the concrete pouring process; and the principal component analysis method is used to convert multiple related variables into unrelated variables, thereby reducing the dimension of the data while retaining the main features of the data.

6. The concrete construction quality monitoring platform based on the Internet of Things according to claim 1 is characterized in that: The data analysis module generates a detailed pouring plan using a neural network algorithm, and the process of using machine vision technology to monitor and control concrete quality in real time includes: Before concrete construction, the neural network algorithm of the machine learning algorithm is used to learn historical data, and according to the amount of concrete required for the building and the raw material quality inspection report input by the data interaction module, the amount of cement, sand, gravel, water, and admixture is analyzed, and a pouring plan is generated, including partial pouring, formwork installation, steel bar binding, uniform pouring and vibration of concrete, and maintenance plan after pouring. The number of neural network layers and the number of neurons in each layer are determined based on the input and output features. The number of neurons in the input layer will correspond to the number of input features, the amount of concrete required for the building, and the number of key parameters in the quality inspection report of cement, sand, gravel, water, and admixtures. The number of neurons in the output layer will correspond to the output results, i.e. the amount of cement, sand, gravel, water, and admixtures, as well as the various contents of the pouring plan, including the order of partial pouring, formwork installation details, steel bar binding requirements, parameters for uniform concrete pouring and vibration, and post-pouring maintenance plans. The number of layers and neurons in the hidden layer can be determined by experiments or empirical rules. Try fewer hidden layers and neurons first, and then adjust according to the performance of the model. Number of neurons in the hidden layer Determined by the following formula: ， is the number of neurons in the input layer; is the number of neurons in the output layer; Collect relevant data from historical concrete construction projects, including building scale, raw material quality inspection reports, and corresponding construction plans, as the basis for neural network learning; divide the collected data into training set, validation set, and test set; the training set is used to train the neural network model, the validation set is used to adjust the model's hyperparameters during the training process, and the test set is used to evaluate the performance of the final model; During the training process, the neural network uses the back propagation algorithm to adjust the connection weights between neurons based on the input data, i.e., the amount of concrete required for construction and the raw material quality inspection report, and the expected output, which includes the error between the amount of raw materials used and the construction plan. The training process is iterated continuously until the model reaches the preset number of iterations. The mean square error is used to evaluate the performance of the model on the test set. If the model has a large error, the cause is analyzed and the number of hidden layers of the network structure is adjusted until the error meets the "Concrete Structure Engineering Construction Quality Acceptance Code"; During concrete construction, moisture sensors are installed in the pouring pipes to monitor the moisture content of concrete. Combined with pre-buried sensors, the IoT platform uses a curve chart to visually describe temperature changes based on the on-site temperature measurement data table. The temperature measurement curve trend chart automatically generates a scientific data query basis for the temperature rise and fall trends of large-volume concrete. The temperature difference between the inside and outside of large-volume concrete is monitored to be controlled within 25°C, and an alarm is automatically sounded when the temperature reaches the warning value, reminding relevant personnel. When the temperature reaches the warning value, the temperature of the cooling circulating water is reduced and the water flow rate is increased to take away the internal heat of the concrete. In the concrete vibration construction quality monitoring based on machine vision, the collected videos of workers' behavior and actions and video image data of concrete vibration surface status are processed to monitor the vibration construction quality and the wearing of safety helmets in real time. When quality problems are found, timely feedback is given to the construction site managers so that the construction process and parameters can be adjusted in time to ensure the quality of concrete construction.

7. The Internet of Things-based concrete construction quality monitoring platform according to claim 1 is characterized in that: The process of storing the processed data by the data analysis module through cloud storage includes: Users transfer data to the cloud service provider's server through the network; cloud storage usually adopts a distributed storage architecture, and data is stored in multiple copies in different physical locations; During data storage, cloud services use redundant backup and disaster recovery technologies to ensure data security and reliability; cloud storage provides multi-level security controls, including identity authentication, access control, and data encryption technology; Users manage data through the management tools and API interfaces provided by the cloud storage platform, including data organization, retrieval, and processing; The cloud storage platform sets permissions and access control functions so that only authorized users can access data; user identities are verified through usernames and passwords; users set different access permissions, including read, write, and delete permissions, and permissions are allocated based on user roles or user groups.

8. The Internet of Things-based concrete construction quality monitoring platform according to claim 1 is characterized in that: The process of real-time display of monitoring data and analysis results and command input by the data interaction module through the Web terminal and the mobile terminal includes: Monitoring data and analysis results are displayed in real time through the Web and mobile terminals, supporting a variety of chart formats; the data display terminal supports multi-user access and permission management; Construction managers can view monitoring data through the Web and mobile terminals. The data display terminal supports multi-language interface. Before concrete construction, supervisors upload the raw material types and quality inspection reports. The data analysis module can extract quality information and concrete construction plans based on the quality inspection reports. The construction plans are sent to the data interaction module, and construction personnel implement them according to the plans. After concrete construction, operators input control instructions through the data interaction interface to view the operating status and data of the maintenance equipment; the interactive interface displays real-time data, alarm information and processing methods obtained from data analysis.

Images