Cloud-based building construction site quality monitoring system and method

Abstract

The invention belongs to the technical field of ocean engineering new energy, and particularly relates to a cloud-based building construction site quality monitoring system and method.The cloud processing module is provided with a database, an AI analysis engine and an early warning prompt unit, and the AI analysis engine comprises a monitoring unit and a prediction unit; a monitoring unit of the AI analysis engine directly calls the analyzed real-time sensor data in the database and compares the analyzed real-time sensor data with the parameter interval table to judge whether abnormal items occur or not, if yes, an early warning prompt unit of the cloud processing module gives out real-time early warning, and if not, an early warning prompt unit of the cloud processing module gives out real-time early warning; and the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and judges whether abnormity occurs or not through a neural network model, if abnormity occurs, an early warning prompt unit of the cloud processing module sends out an early warning prompt, and otherwise, the cloud processing module continues to process the sensor data. The engineering quality of the building construction site can be monitored in real time.

Description

Technical Field

[0001] The present invention belongs to the technical field of new energy for ocean engineering, and particularly relates to a cloud-based quality monitoring system and method for construction sites. Background Art

[0002] Ocean engineering refers to the application of engineering technology to solve various engineering problems related to the marine environment, resources, energy, transportation, etc. It covers multiple fields, including but not limited to offshore oil and gas exploitation, offshore wind power, port construction, offshore platforms, subsea pipelines, and marine environmental protection. Ocean engineering is a national key project. It is not only an important field for promoting economic development but also an important part of enhancing the country's comprehensive competitiveness and strategic security. Ocean engineering is one of the key areas for national development, and the projects involved cover multiple aspects such as energy development, marine resource utilization, maritime transportation, environmental protection, and national defense security.

[0003] During the construction process of ocean engineering, especially during the foundation pit construction of infrastructure in new energy fields such as wind power generation, it is necessary to monitor the quality of construction sites in real time. With the continuous expansion of the scale of construction projects, the traditional manual quality inspection method can no longer meet the requirements of real-time, comprehensiveness, and efficiency at the construction site. In construction, quality problems are often related to multiple factors such as the construction operations of workers, the use of materials, and environmental changes, and long-term monitoring is required to determine the construction quality. Therefore, the traditional quality monitoring method not only has problems such as large workload, low efficiency, and data lag, but also lacks real-time and systematicness.

[0004] Although the existing building quality monitoring systems can partially monitor the construction site through various sensors, most of them use a single hardware device for data collection, lacking an efficient data processing platform and integrated management system. Moreover, the analysis and feedback of data often rely on manual operations, resulting in slow information flow and unable to achieve real-time feedback and automatic warning. Therefore, the present invention proposes a cloud-based quality monitoring system and method for construction sites. Summary of the Invention

[0005] The purpose of the present invention is to provide a cloud-based quality monitoring system and method for construction sites to monitor the engineering quality of construction sites in real time.

[0006] The technical solutions adopted by the present invention are specifically as follows: A cloud-based quality monitoring system for construction sites includes: a multi-sensor module, a communication module, and a cloud processing module. The multi-sensor module is communicatively connected to the cloud processing module through the communication module; Multi-sensor module: At the construction site, multiple sensors are set up to monitor the quality indicators of the environment, materials, and structure during the construction process in real time, and the sensor data collected is sent to the communication module; The communication module directly sends the sensor data to the cloud processing module. The cloud processing module is equipped with a database, an AI analysis engine, and a warning and prompting unit. The database is used to store the sensor data sent by the communication module. A parameter range table is built inside the database. The AI analysis engine includes a monitoring unit and a prediction unit. The monitoring unit of the AI analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter range table to determine whether there are abnormal items. If there are abnormalities, the warning and prompting unit of the cloud processing module issues a real-time warning. If there are no abnormalities, the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and judges whether abnormalities will occur through a neural network model. If abnormalities will occur, the warning and prompting unit of the cloud processing module issues a warning and prompting. Otherwise, the cloud processing module continues to process the sensor data.

[0007] Preferably, the multiple sensors set by the multi-sensor module include: temperature and humidity sensors, pressure sensors, vibration sensors, tilt sensors, and air quality sensors.

[0008] Preferably, the communication module dynamically switches the transmission mode according to the network status. The transmission modes include: 4G network transmission, 5G network transmission, Wi-Fi transmission, and offline caching. The 4G network transmission, 5G network transmission, and Wi-Fi transmission can all resume transmission after network interruption.

[0009] Preferably, when the AI analysis engine retrieves the real-time sensor data in the database, it first conducts finite element simulation analysis. During the analysis process, the analysis objective is first determined. The analysis objective is the mechanical response during the construction process, and the design requirements and standards are defined: according to relevant building design codes and standards, and the requirements of the analysis are clarified; for example, requirements in terms of bearing capacity, stability, safety, etc. Then, structural modeling and mesh generation are carried out. According to the design drawings or construction drawings of the construction site, a geometric model of the building is established; the shape, size, material properties, etc. of the building need to be considered during this process; the building model is discretized into finite element meshes; then, the material properties are defined. The mechanical properties of the structural materials are defined, including elastic modulus, Poisson's ratio, density, yield strength, etc.; the physical properties of different materials, such as steel bars, concrete, wood, etc., will directly affect the simulation results; in some cases, the non-linear behavior of the materials, such as plasticity, fracture, fatigue, etc., needs to be considered, especially for some complex load conditions or structures, the non-linear behavior of the materials may need to be emphasized; then, the support and constraint conditions of the model are defined. For example, boundary conditions such as fixed supports, hinged supports, and roller supports will affect the deformation and force of the structure; different load types are defined; such as static loads, dynamic loads, wind loads, seismic loads, etc.; a suitable finite element solver is selected according to the characteristics of the analysis problem; for example, a linear static analysis solver can be used for linear problems, and a non-linear solver may need to be selected for non-linear problems. Calculation process: Use finite element analysis software for solution; during the solution process, the stress, strain, displacement, temperature change, etc. of the structure will be calculated according to the given boundary conditions, load conditions, and material properties; corresponding monitoring results are generated according to the calculation results, and the monitoring results, which are the analyzed sensor data, are digitized again.

[0010] Preferably, the neural network model set in the prediction unit of the AI analysis engine adopts the error back propagation (BP) neural network. The AI analysis engine first trains the error back propagation (BP) neural network, and then uses the error back propagation (BP) neural network to perform intelligent prediction on the analyzed sensor data.

[0011] Preferably, the cloud processing module further includes an application unit, which is used to output a visual quality dashboard based on the mobile terminal in real time, and the application unit automatically generates a quality report regularly; the automatically generated quality report (complies with the GB / T 50375 standard); the cloud processing module further includes a permission login unit and a data traceability unit. After passing the identity authentication, the permission login unit can view and obtain the quality report, and the data traceability unit traces the real-time sensor data in the database based on blockchain technology.

[0012] Preferably, the cloud processing module is further used to monitor whether the communication module obtains all the real-time sensor data of the multi-sensor module. After preprocessing the obtained real-time sensor data, the communication module sends it to the cloud processing module. The preprocessing process of the real-time sensor data by the communication module includes: data cleaning: removing noise and invalid data to ensure data quality; data filtering: screening specific data according to requirements, such as removing outliers; data compression: compressing the data to be transmitted to reduce the bandwidth consumption of data transmission.

[0013] A quality monitoring method for a building construction site based on the cloud, the quality monitoring method includes the following steps: Step 1: Set up a multi-sensor module, and complete the setting of temperature and humidity sensors, pressure sensors, vibration sensors, tilt sensors, and air quality sensors at the construction site. Step 2: Build a communication module and a cloud processing module, and build in the cloud processing module: a database, an AI analysis engine, a warning prompt unit, and an application unit. Step 3: The multi-sensor module monitors the quality indicators of the environment, materials, and structure during the construction process through various sensors, and sends the collected sensor data to the communication module. Step 4: The communication module preprocesses the sensor data and sends the preprocessed sensor data to the cloud processing module. Step 5: The database first stores the sensor data sent by the communication module. The AI analysis engine performs finite element analysis on the sensor data and stores the monitoring results of the sensor data after analysis in the database again. Step 6: The monitoring unit of the AI analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter interval table to determine whether there are abnormal items. If there are abnormalities, the warning prompt unit of the cloud processing module issues a real-time warning. Step 7: If there is no abnormality, the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and determines whether an abnormality will occur through the neural network model. If an abnormality will occur, the warning prompt unit of the cloud processing module issues a warning prompt. Otherwise, the cloud processing module continues to process the sensor data.

[0014] The technical effects achieved by the present invention are as follows: In the present invention, by setting up a multi-sensor module, a communication module, and a cloud processing module, the multi-sensor module is arranged at the construction site of a building construction project, and a variety of sensors are set to monitor the quality indicators of the environment, materials, and structure during the construction process in real time. The collected sensor data is sent to the communication module; the communication module directly sends the sensor data to the cloud processing module. The cloud processing module is equipped with a database, an AI analysis engine, and a warning prompt unit. The database is used to store the sensor data sent by the communication module, and a parameter range table is built inside the database. The AI analysis engine includes a monitoring unit and a prediction unit. The monitoring unit of the AI analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter range table to determine whether there are abnormal items. If there is an abnormality, the warning prompt unit of the cloud processing module issues a real-time warning. If there is no abnormality, the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and determines whether an abnormality will occur through the neural network model. If an abnormality will occur, the warning prompt unit of the cloud processing module issues a warning prompt. Otherwise, the cloud processing module continues to process the sensor data. Finally, the present invention can monitor the project quality of a building construction site in real time and ensure the accuracy of the monitoring results. Description of the Drawings

[0015] Figure 1 is a system block diagram of the cloud-based building construction site quality monitoring system of the present invention; Figure 2 is a flowchart of the cloud-based building construction site quality monitoring method of the present invention. Detailed Embodiments

[0016] In order to make the purpose and advantages of the present invention clearer, the present invention will be specifically described below in conjunction with embodiments. It should be understood that the following text is only used to describe one or several specific implementation manners of the present invention, and does not strictly limit the scope of protection specifically claimed by the present invention. Embodiment 1

[0017] As Figure 1 - shown in FIG. 2, the cloud-based building construction site quality monitoring system includes: a multi-sensor module, a communication module, and a cloud processing module. The multi-sensor module is communicatively connected to the cloud processing module through the communication module; Multi-sensor module: At the construction site, multiple sensors are set to monitor the quality indicators of the environment, materials, and structures during the construction process in real time, and the sensor data collected is sent to the communication module; The communication module directly sends the sensor data to the cloud processing module. The cloud processing module is equipped with a database, an AI analysis engine, and an early warning prompt unit. The database is used to store the sensor data sent by the communication module. A parameter range table is built inside the database. The AI analysis engine includes a monitoring unit and a prediction unit. The monitoring unit of the AI analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter range table to determine whether there are abnormal items. If there are abnormalities, the early warning prompt unit of the cloud processing module issues a real-time warning. If there are no abnormalities, the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and judges whether abnormalities will occur through a neural network model. If abnormalities will occur, the early warning prompt unit of the cloud processing module issues a warning prompt. Otherwise, the cloud processing module continues to process the sensor data.

[0018] In the present invention, the cloud-based construction site quality monitoring system provided by the present invention utilizes advanced Internet of Things technology, cloud computing platform, and intelligent analysis methods, and can effectively conduct comprehensive monitoring and quality management of the construction site, solving problems such as low efficiency, slow response, and inaccurate data in traditional quality monitoring methods, and has high practicality and promotion value.

[0019] Preferably, the multiple sensors set by the multi-sensor module include: temperature and humidity sensors, pressure sensors, vibration sensors, tilt sensors, and air quality sensors.

[0020] Preferably, the communication module dynamically switches the transmission mode according to the network status. The transmission modes include: 4G network transmission, 5G network transmission, Wi-Fi transmission, and offline caching. 4G network transmission, 5G network transmission, and Wi-Fi transmission can all resume transmission after network interruption.

[0021] By setting the communication module in the present invention, the data transmission is made more secure.

[0022] Preferably, when the AI analysis engine retrieves real-time sensor data from the database, it first conducts finite element simulation analysis. During the analysis process, the analysis target is first determined. The analysis target is the mechanical response during the construction process, and the design requirements and standards are defined: according to relevant building design codes and standards, and the requirements of the analysis are clarified; for example, the requirements in terms of bearing capacity, stability, safety, etc. Then, structural modeling and mesh generation are carried out. According to the design drawings or construction drawings of the construction site, a geometric model of the building is established; in this process, the shape, size, material properties, etc. of the building need to be considered; the building model is discretized into finite element meshes; then, the material properties are defined, and the mechanical properties of the structural materials are defined, including elastic modulus, Poisson's ratio, density, yield strength, etc.; the physical properties of different materials, such as steel bars, concrete, wood, etc., will directly affect the simulation results; in some cases, the nonlinear behavior of the materials needs to be considered, such as plasticity, fracture, fatigue, etc., especially for some complex load conditions or structures, the nonlinear behavior of the materials may need to be considered emphatically; then, the support and constraint conditions of the model are defined. For example, boundary conditions such as fixed supports, hinged supports, and roller supports will affect the deformation and force of the structure; different load types are defined; such as static loads, dynamic loads, wind loads, seismic loads, etc.; a suitable finite element solver is selected according to the characteristics of the analysis problem; for example, a linear static analysis solver can be used for linear problems, and a nonlinear solver may need to be selected for nonlinear problems. Calculation process: Use finite element analysis software for solution; during the solution process, the stress, strain, displacement, temperature change, etc. of the structure will be calculated according to the given boundary conditions, load conditions, and material properties; corresponding monitoring results are generated based on the calculation results, and the monitoring results, which are the analyzed sensor data, are digitalized again.

[0023] Preferably, the neural network model set in the prediction unit of the AI analysis engine adopts the error backpropagation (BP) neural network. The AI analysis engine first trains the error backpropagation (BP) neural network, and then uses the error backpropagation (BP) neural network to perform intelligent prediction on the analyzed sensor data.

[0024] Preferably, the cloud processing module further includes an application unit, which is used to output a visual quality dashboard based on the mobile terminal in real time, and the application unit automatically generates a quality report regularly; the automatically generated quality report (complies with the GB / T 50375 standard); the cloud processing module further includes a permission login unit and a data traceability unit. After passing the identity verification through the permission login unit, the quality report can be viewed and obtained, and the data traceability unit traces the real-time sensor data in the database based on blockchain technology.

[0025] Preferably, the cloud processing module is further configured to monitor whether the communication module obtains all the real-time sensor data of the multi-sensor module. After the communication module preprocesses the obtained real-time sensor data, it is sent to the cloud processing module. The preprocessing process of the real-time sensor data by the communication module includes: data cleaning: removing noise and invalid data to ensure data quality; data filtering: screening specific data according to requirements, such as removing outliers; data compression: compressing the data to be transmitted to reduce the bandwidth consumption of data transmission. Embodiment 2

[0026] As Figure 1 shown in - FIG. 2, the cloud-based construction site quality monitoring method includes the following steps: Step 1: Set up a multi-sensor module, and complete the setting of temperature and humidity sensors, pressure sensors, vibration sensors, tilt sensors, and air quality sensors at the construction site. Step 2: Build a communication module and a cloud processing module, and build in the cloud processing module: a database, an AI analysis engine, a warning prompt unit, and an application unit. Step 3: The multi-sensor module monitors the quality indicators of the environment, materials, and structures during the construction process through various sensors, and the collected sensor data is sent to the communication module. Step 4: The communication module preprocesses the sensor data and sends the preprocessed sensor data to the cloud processing module. Step 5: The database first stores the sensor data sent by the communication module. The AI analysis engine performs finite element analysis on the sensor data and stores the monitoring results of the analyzed sensor data in the database again. Step 6: The monitoring unit of the AI analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter interval table to determine whether there are abnormal items. If there are abnormalities, the warning prompt unit of the cloud processing module issues a real-time warning. Step 7: If there are no abnormalities, the prediction unit of the AI analysis engine retrieves the analyzed real-time sensor data in the database again and judges whether there will be abnormalities through a neural network model. If there will be abnormalities, the warning prompt unit of the cloud processing module issues a warning prompt. Otherwise, the cloud processing module continues to process the sensor data.

[0027] In the present invention, the error backpropagation (BP) neural network is the essence of neural networks. Approximately 85% of artificial neural networks use the error backpropagation neural network, namely the BP neural network. The idea of the BP neural network consists of a forward propagation and a backward propagation process through input samples and output samples. The forward process is that the input samples pass through the input layer, enter the hidden layer through the thresholds (defining the range of input samples) and weights (weighted input sample parameters) connecting the input layer and the hidden layer, and then enter the output layer after being weighted again through the processing of the hidden layer, and then the output value is obtained. The output value is compared with the expected output sample. If the output value is inconsistent with the expected output sample, it enters the error backpropagation stage, that is, the backpropagation of the error is to transmit the input-output error to the output layer through the hidden layer in a certain form, and allocate the error to the output layer, hidden layer, output layer, etc., so as to obtain the magnitude of the error information of each layer. And this error information is offset through the connection weights between the layers. The weights are continuously adjusted to obtain the connection weights between each layer that conform to the entire sample data. This is the process of network learning and training. By using the error backpropagation (BP) neural network, it is ensured that the prediction unit of the AI analysis engine can accurately identify the quality and safety of building construction projects.

[0028] The above are only the preferred embodiments of the present invention. It should be noted that for those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements and refinements can be made, and these improvements and refinements should also be regarded as the protection scope of the present invention. The structures, devices and operation methods not specifically described and explained in the present invention are implemented according to the conventional means in this field without special explanation and limitation.

Claims

1. A cloud-based construction site quality monitoring system, characterized by: include: A multi-sensor module, a communication module and a cloud processing module, wherein the multi-sensor module is communicatively connected with the cloud processing module via the communication module; Multi-sensor module: At the construction site, multiple sensors are set up to monitor the quality indicators of the environment, materials, and structures during the construction process in real time, and the collected sensor data is sent to the communication module; The communication module directly sends the sensor data to the cloud processing module. The cloud processing module is constructed with a database, an AI analysis engine and an early warning prompt unit. The database is used to store the sensor data sent by the communication module. A parameter interval table is constructed inside the database. The AI ​​analysis engine includes a monitoring unit and a prediction unit. The monitoring unit of the AI ​​analysis engine directly retrieves the real-time sensor data analyzed in the database and compares it with the parameter interval table to determine whether an abnormal item occurs. If an abnormal item occurs, the early warning prompt unit of the cloud processing module issues a real-time warning. If there is no abnormality, the prediction unit of the AI ​​analysis engine retrieves the real-time sensor data analyzed in the database again and determines whether an abnormality will occur through a neural network model. If an abnormality will occur, the early warning prompt unit of the cloud processing module issues an early warning prompt. Otherwise, the cloud processing module continues to process the sensor data.

2. The cloud-based construction site quality monitoring system according to claim 1 is characterized by: The multi-sensor module is provided with a variety of sensors including: a temperature and humidity sensor, a pressure sensor, a vibration sensor, a tilt sensor and an air quality sensor.

3. The cloud-based construction site quality monitoring system according to claim 1 is characterized by: The communication module dynamically switches the transmission mode according to the network status. The transmission modes include: 4G network transmission, 5G network transmission, Wi-Fi transmission and offline cache. The 4G network transmission, 5G network transmission and Wi-Fi transmission can all be resumed after disconnecting the network.

4. The cloud-based construction site quality monitoring system according to claim 1 is characterized by: When the AI ​​analysis engine retrieves the real-time sensor data in the database, it first performs finite element simulation analysis. During the analysis, it first determines the analysis target, which is the mechanical response during the construction process, and designs requirements and standards: and clarifies the analysis requirements; then it performs structural modeling and meshing, and establishes a geometric model of the building based on the design drawings or construction drawings of the construction site, and discretizes the building model into finite element meshes; then it defines material property definitions, and defines the mechanical properties of structural materials; Then, define the support and constraint conditions of the model; define different load types; Select the appropriate finite element solver according to the characteristics of the analysis problem; Calculation process: Use finite element analysis software for solution; the solution process will calculate the stress, strain, displacement, temperature change and other results of the structure according to the given boundary conditions, load conditions and material properties; generate corresponding monitoring results based on the calculation results, and digitize the monitoring results as analyzed sensor data again.

5. The cloud-based construction site quality monitoring system according to claim 1 is characterized in that: The neural network model set in the prediction unit of the AI ​​analysis engine adopts an error back propagation neural network. The AI ​​analysis engine first trains the error back propagation neural network, and then uses the error back propagation neural network to perform intelligent prediction on the analyzed sensor data.

6. The cloud-based construction site quality monitoring system according to claim 1 is characterized by: The cloud processing module also includes an application unit, which is used to output a visual quality dashboard based on a mobile terminal in real time, and the application unit automatically generates a quality report regularly; the cloud processing module also includes an authority login unit and a data tracing unit. After the authority login unit passes the identity authentication, it checks and obtains the quality report, and the data tracing unit traces the real-time sensor data in the database based on blockchain technology.

7. The cloud-based construction site quality monitoring system according to claim 1 is characterized by: The cloud processing module is also used to monitor whether the communication module obtains all real-time sensor data of the multi-sensor module. The communication module pre-processes the acquired real-time sensor data and then sends it to the cloud processing module. The pre-processing process of the real-time sensor data by the communication module includes: data cleaning: removing noise and invalid data; data filtering: filtering specific data according to needs; data compression: compressing the data to be transmitted.

8. A cloud-based construction site quality monitoring method, characterized in that: The quality monitoring method is a cloud-based construction site quality monitoring system according to any one of claims 1 to 7, and the quality monitoring method comprises the following steps: Step 1: Set up the multi-sensor module, and then set up temperature and humidity sensors, pressure sensors, vibration sensors, tilt sensors, and air quality sensors at the construction site; Step 2: Build the communication module and cloud processing module, and build the following in the cloud processing module: database, AI analysis engine, early warning prompt unit and application unit; Step 3: The multi-sensor module monitors the quality indicators of the environment, materials, and structures during the construction process in real time through a variety of sensors, and sends the collected sensor data to the communication module; Step 4: The communication module preprocesses the sensor data and sends the preprocessed sensor data to the cloud processing module; Step 5: The database first stores the sensor data sent by the communication module, the AI ​​analysis engine performs finite element analysis on the sensor data, and stores the monitoring results of the analyzed sensor data in the database again; Step 6: The monitoring unit of the AI ​​analysis engine directly retrieves the analyzed real-time sensor data in the database and compares it with the parameter interval table to determine whether an abnormal item occurs. If an abnormal item occurs, the early warning prompt unit of the cloud processing module issues a real-time early warning. Step 7: If there is no abnormality, the prediction unit of the AI ​​analysis engine retrieves the real-time sensor data analyzed in the database again and determines whether an abnormality will occur through the neural network model. If an abnormality will occur, the early warning prompt unit of the cloud processing module issues an early warning prompt, otherwise the cloud processing module continues to process the sensor data.

Images