Construction site on-site comprehensive data acquisition system based on Internet of Things

By adopting the Internet of Things system on construction sites, combining sensors and video surveillance modules, and using machine learning algorithms for data analysis and prediction, the problem of traditional data processing relying on manual analysis is solved, data quality and decision-making support capabilities are improved, and efficient , secure data-driven decision-making.

CN119005876APending Publication Date: 2024-11-22XIAMEN MUNICIPAL SMART CITY TECH CO LTD
View PDF 0 Cites 1 Cited by

Patent Information

Application Number
CN202410923809.5
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-22

AI Technical Summary

Technical Problem

Traditional construction site data processing methods rely on manual analysis, resulting in insufficient overall accuracy and efficiency, and errors are prone to occur in the decision-making process.

Method used

Design a comprehensive data acquisition system for construction site sites based on the Internet of Things, including sensor modules, video surveillance modules, data processing modules, display modules, storage modules, communication modules and remote server modules, and use machine learning algorithms to perform data analysis and prediction. Provide intelligent decision-making support.

Benefits of technology

It improves data quality and model prediction accuracy, enhances decision-making support capabilities, realizes data-driven decision-making, improves work efficiency and security, and brings about improvements in economic benefits.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN119005876A_ABST
    Figure CN119005876A_ABST
Patent Text Reader

Abstract

The invention discloses a construction site on-site comprehensive data acquisition system based on the Internet of Things, and belongs to the technical field of construction site data acquisition. In the construction site on-site comprehensive data acquisition system, a model training and prediction module establishes a prediction model for construction site on-site environment parameters and activity trends through a machine learning algorithm to provide support for decision making; through model training and verification, model parameters are continuously optimized, and the prediction accuracy and generalization ability of the model are improved. The intelligent decision support module generates specific decision suggestions according to the prediction result and the business logic, and helps managers to make scientific and reasonable decisions. Four modules in the data processing module cooperate with one another, so that the data quality, the prediction accuracy of the model and the decision support capability are improved together, powerful data support and intelligent decision capability are provided for comprehensive management of the construction site, the working efficiency and safety are improved, and the system is suitable for popularization and application. Decision support of data driving is achieved, and economic benefits are improved.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention belongs to the technical field of construction site data collection, and in particular relates to a construction site comprehensive data collection system based on the Internet of Things. Background Art

[0002] Data collection at construction sites is an important part of the construction industry. It involves real-time and accurate collection and collation of various data on the construction site. These data include but are not limited to project progress, staffing, material use, equipment status, safety status, etc. Through efficient data collection, it is helpful to improve the management level of construction sites, ensure project quality and safety, reduce costs, and enhance corporate competitiveness. Data collection at construction sites also needs to pay attention to material use and equipment status. By real-time collection of data such as material procurement, use, and inventory, it is possible to ensure the rational use of materials and reduce waste. By real-time monitoring of the status of equipment, equipment failures can be discovered in time, ensuring the normal use of equipment and improving project efficiency. Data collection at construction sites also needs to pay attention to project safety and quality management. By real-time monitoring of safety hazards on the construction site, accidents can be prevented. By real-time monitoring of project quality, it is possible to ensure that the project quality meets the standards and avoid quality problems in the later stage. Data collection at construction sites is an important means for the construction industry to achieve refined management. Through real-time and accurate data collection, it is possible to improve the management level of construction sites, ensure project quality and safety, reduce costs, and enhance corporate competitiveness.

[0003] However, traditional construction site data processing methods may rely on manual analysis and processing, which affects the overall accuracy and efficiency. At the same time, traditional decision support may rely on experience and intuition, which may lead to errors in the overall decision-making process. Summary of the invention

[0004] The purpose of the present invention is to provide a construction site comprehensive data acquisition system based on the Internet of Things in order to solve the above-mentioned problems.

[0005] The technical solution adopted by the present invention is as follows: a construction site comprehensive data acquisition system based on the Internet of Things, the system comprising a sensor module, a video monitoring module, a data processing module, a display module, a storage module, a communication module and a remote server module;

[0006] The data processing module is internally provided with a data preprocessing module, a feature engineering module, a model training and prediction module and an intelligent decision support module;

[0007] The sensor module monitors the environmental parameters and activities of the construction site in real time and sends the raw data to the data processing module.

[0008] The video monitoring module captures visual information of the construction site through a camera and transmits the video data to the data processing module.

[0009] The data processing module cleans, preprocesses and extracts features from the received raw data, and performs data analysis through machine learning algorithms to identify patterns and predict trends. The processed data is sent to the display module and storage module. At the same time, the data will also be sent to the remote server module through the communication module.

[0010] The display module receives statistical charts and reports from the data processing module and displays them to managers at the construction site.

[0011] The storage module is responsible for long-term storage of statistical charts, reports and raw data generated by the data processing module. At the same time, these data will also be synchronized to the remote server module to achieve redundant backup and remote access of data.

[0012] The communication module transmits the data generated by the data processing module to the remote server module;

[0013] The remote server module is a central data processing and storage center that receives data from multiple construction sites. The remote server module provides data storage services to ensure data security and accessibility. Managers can view real-time data and reports through a secure remote access interface for remote monitoring and management;

[0014] The data preprocessing module passes the preprocessed data to the feature engineering module for feature extraction and selection. The feature-engineered data generated inside the feature engineering module is used to train and verify the machine learning model. The prediction results generated by the model training and prediction module for new data using the trained model are passed to the intelligent decision support module to generate decision support information.

[0015] In a preferred embodiment, the sensor module is provided with a temperature sensor to accurately measure the temperature change at the construction site, which is crucial for the pouring and hardening process of concrete. The sensor module is provided with a humidity sensor to monitor the moisture content in the air in real time, which is very critical for the storage of wood and the prevention of material damage caused by humidity. The sensor module is provided with a light sensor to measure the light intensity at the construction site to ensure the safety and comfort of the workplace. The sensor module is provided with a noise sensor to monitor the noise level at the construction site in real time to ensure that it meets the noise standards stipulated by the government and protect the hearing of workers. The sensor module is provided with a vibration sensor to monitor the vibration of equipment or structures to prevent structural damage caused by excessive vibration. The sensor module is provided with a wind speed sensor to monitor the wind speed, which is crucial for the safety of high-altitude operations such as high-rise building construction and crane operation. The sensor module transmits the collected data to the data processing module to provide support for subsequent data analysis and decision-making.

[0016] In a preferred embodiment, the video surveillance module installs a high-definition camera to monitor the construction site in real time 24 hours a day to ensure the safety of the construction site and record all activities. The video data of the video surveillance module can be used for accident investigation, worker training, and process improvement.

[0017] In a preferred embodiment, the display module displays real-time statistics, charts and video monitoring images through a large-screen display or an interactive touch screen. Different display modes can be set to meet different management needs and decision-making scenarios. The display module enables managers to intuitively understand the situation on the construction site and take corresponding measures as needed.

[0018] In a preferred embodiment, the storage module stores the collected data and the statistical charts and reports generated by the data processing module. The storage module uses RAID configuration services to ensure data security and persistence. The storage module supports long-term storage of massive data, facilitating historical data analysis and auditing. The storage module provides a solid foundation for data traceability and future data analysis.

[0019] In a preferred embodiment, the communication module transmits the collected data and the statistical charts and reports generated by the data processing module to a remote server or cloud platform. The communication module ensures the security and integrity of data transmission through a secure network connection through a VPN or a dedicated network. The communication module supports MQTT, HTTP, and WebSocket communication protocols to meet different transmission requirements. Remote access and sharing of data are achieved, and real-time monitoring and management of multiple locations and multiple users are supported. The communication module facilitates remote monitoring and management of construction sites and achieves data sharing and remote access.

[0020] In a preferred embodiment, data cleaning in the data preprocessing module includes the following steps:

[0021] Missing value processing: Check whether there are missing values ​​in the data and process them, such as deletion or interpolation;

[0022] Outlier processing: detect and process outliers, delete or replace them;

[0023] Duplicate value processing: delete duplicate construction site comprehensive data records;

[0024] The data preprocessing module uses the minimum-maximum standardization method to perform data standardization processing, and the specific steps are as follows:

[0025] S1. Calculate the maximum and minimum values: For each feature, find the maximum value (Max) and minimum value (Min) in the comprehensive data set of the construction site;

[0026] S2. Apply transformation formula: For each feature value x in the comprehensive data set of the construction site, use the following formula for transformation:

[0027]

[0028] Among them, x norm is the transformed value;

[0029] S3. Transform the comprehensive construction site dataset: Apply the above transformation to each feature of the entire dataset; after min-max normalization, all features will be scaled to the range of 0 to 1.

[0030] In a preferred embodiment, the feature engineering module receives the preprocessed data and then performs feature extraction and selection. The feature engineering module reduces the number of features by selecting the features most relevant to the prediction target and reducing the dimension. The feature engineering module uses principal component analysis (PCA) to find the main components of the data by calculating the covariance matrix of the eigenvalues. The calculation formula is:

[0031] where Σ is the covariance matrix, x i is a data point, is the mean of the data.

[0032] In a preferred embodiment, the model training and prediction module uses 70% of the data as a training set, 15% of the data as a validation set, and 15% of the data as a test set;

[0033] The model training submodule uses the training set to train the model, optimizes the performance by adjusting the model parameters, and uses the batch gradient descent algorithm to optimize the parameters of the logistic regression model. The iterative update formula is:

[0034] Where θj is the model parameter, α is the learning rate, and J(θ) is the cross entropy loss function, which is calculated as:

[0035]

[0036] Where m is the number of training samples, y(i) is the true label of the i-th sample, and hθ(x(i)) is the prediction result of the model.

[0037] In a preferred embodiment, the intelligent decision support module receives the prediction results from the model training and prediction module and converts them into actionable insights or suggestions. This module formulates decision strategies based on the prediction results and business logic;

[0038] The decision strategy of the intelligent decision support module is formulated based on the decision rules of the model. The intelligent decision support module includes the following steps:

[0039] S1. Set a threshold and take specific actions when the predicted probability exceeds the set value;

[0040] S2. Use algorithms such as rule engines or logistic regression to combine the outputs of multiple decision tree models into a comprehensive decision;

[0041] S3. Optimize decision-making strategies to maximize profits or minimize costs, taking into account cost-benefit analysis;

[0042] S4. Execution and monitoring: Implement decision-making strategies and monitor decision results. Collect feedback data for subsequent model retraining and optimization;

[0043] S5. Report and Explanation: Generate reports to explain the model’s prediction results and decision recommendations to decision makers, and provide visualization tools to help decision makers understand the model’s prediction logic and decision basis.

[0044] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0045] 1. In the present invention, the data preprocessing module improves the overall data quality: through data cleaning, outlier processing and duplicate value processing, the integrity and accuracy of the data are improved to ensure the reliability of subsequent analysis. The data preprocessing module scales the data to the range of 0 to 1 through minimum-maximum normalization, which facilitates comparison between different features and model training. At the same time, the feature engineering module identifies the features most relevant to the target variable through feature extraction and selection, reduces data dimensions, and improves the efficiency of model training. The feature engineering module uses methods such as principal component analysis (PCA) to reduce data dimensions, remove redundant information, and make the model more concise and efficient;

[0046] 2. In the present invention, the model training and prediction module establishes a prediction model for the environmental parameters and activity trends of the construction site through a machine learning algorithm to provide support for decision-making. Through model training and verification, the model parameters are continuously optimized to improve the prediction accuracy and generalization ability of the model. The intelligent decision support module generates specific decision suggestions based on the prediction results and business logic to help managers make scientific and reasonable decisions. Implement decision-making strategies, monitor decision results, and collect feedback data for subsequent model retraining and optimization. In summary, the four modules within the data processing module cooperate with each other to jointly improve the quality of data, the prediction accuracy of the model and the decision support ability, provide powerful data support and intelligent decision-making capabilities for the comprehensive management of the construction site, help improve work efficiency and safety, realize data-driven decision support, and bring about economic benefits.

[0047] 3. In the present invention, the video monitoring module and the communication module realize 24-hour real-time monitoring of the construction site. The management personnel can view the situation of the construction site in real time through the remote server module and perform remote management. This remote monitoring and management capability greatly improves management efficiency and reduces the workload of on-site personnel. The storage module is responsible for long-term storage of statistical charts, reports and original data generated by the data processing module, and synchronizes them to the remote server module to achieve redundant backup and remote access of the data. This data storage and backup capability ensures the security and accessibility of the data, and provides a solid foundation for subsequent data analysis and decision-making. Through the massive data storage capacity of the storage module, the system can perform historical data analysis and trend prediction, help management personnel understand the historical situation of the construction site, and predict future development trends, providing a reference for decision-making. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 is the overall system block diagram of the present invention;

[0049] Figure 2 This is a system block diagram of the data processing module in the present invention. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0051] Reference Figure 1-2 ,

[0052] A construction site comprehensive data acquisition system based on the Internet of Things, the system includes a sensor module, a video monitoring module, a data processing module, a display module, a storage module, a communication module and a remote server module;

[0053] The data processing module is internally provided with a data preprocessing module, a feature engineering module, a model training and prediction module, and an intelligent decision support module;

[0054] The sensor module monitors the environmental parameters and activities on the construction site in real time and sends the raw data to the data processing module.

[0055] The video monitoring module captures visual information of the construction site through a camera and transmits the video data to the data processing module.

[0056] The data processing module cleans, preprocesses and extracts features from the received raw data, and performs data analysis through machine learning algorithms to identify patterns and predict trends. The processed data is sent to the display module and storage module. At the same time, the data will also be sent to the remote server module through the communication module.

[0057] The display module receives statistical charts and reports from the data processing module and displays them to the managers at the construction site.

[0058] The storage module is responsible for long-term storage of statistical charts, reports and raw data generated by the data processing module. At the same time, these data will also be synchronized to the remote server module to achieve redundant data backup and remote access.

[0059] The communication module transmits the data generated by the data processing module to the remote server module;

[0060] The remote server module is a central data processing and storage center that receives data from multiple construction sites. The remote server module provides data storage services to ensure data security and accessibility. Managers can view real-time data and reports through a secure remote access interface for remote monitoring and management;

[0061] The data preprocessing module passes the preprocessed data to the feature engineering module for feature extraction and selection. The feature-engineered data generated inside the feature engineering module is used to train and verify the machine learning model. The model training and prediction module uses the trained model to generate prediction results for new data, which are passed to the intelligent decision support module to generate decision support information.

[0062] The sensor module is equipped with a temperature sensor to accurately measure the temperature changes on the construction site, which is crucial for the pouring and hardening process of concrete. The sensor module is equipped with a humidity sensor to monitor the moisture content in the air in real time, which is critical for the storage of wood and preventing material damage caused by humidity. The sensor module is equipped with a light sensor to measure the light intensity on the construction site to ensure the safety and comfort of the workplace. The sensor module is equipped with a noise sensor to monitor the noise level on the construction site in real time to ensure that it meets the noise standards set by the government and protect the hearing of workers. The sensor module is equipped with a vibration sensor to monitor the vibration of equipment or structures to prevent structural damage caused by excessive vibration. The sensor module is equipped with a wind speed sensor to monitor wind speed, which is crucial for the safety of high-altitude operations such as high-rise building construction and crane operation. The sensor module transmits the collected data to the data processing module to provide support for subsequent data analysis and decision-making.

[0063] The video surveillance module installs high-definition cameras to monitor the construction site in real time 24 hours a day to ensure the safety of the construction site and record all activities. The video data of the video surveillance module can be used for accident investigation, worker training, and process improvement.

[0064] The display module displays real-time statistics, charts and video surveillance images through a large-screen display or interactive touch screen. Different display modes can be set to meet different management needs and decision-making scenarios. The display module enables managers to intuitively understand the situation on the construction site and take appropriate measures as needed.

[0065] The storage module stores the collected data and the statistical charts and reports generated by the data processing module. The storage module uses RAID configuration services to ensure data security and persistence. The storage module supports long-term storage of massive data, facilitating historical data analysis and auditing. The storage module provides a solid foundation for data traceability and future data analysis.

[0066] The communication module transmits the collected data and the statistical charts and reports generated by the data processing module to a remote server or cloud platform. The communication module ensures the security and integrity of data transmission through a secure network connection through a VPN or a dedicated network. The communication module supports MQTT, HTTP, and WebSocket communication protocols to meet different transmission requirements. It realizes remote access and sharing of data and supports real-time monitoring and management of multiple locations and multiple users. The communication module facilitates remote monitoring and management of construction sites and realizes data sharing and remote access.

[0067] Data cleaning in the data preprocessing module includes the following steps:

[0068] Missing value processing: Check whether there are missing values ​​in the data and process them by deleting or interpolating;

[0069] Outlier processing: detect and process outliers, delete or replace them;

[0070] Duplicate value processing: delete duplicate construction site comprehensive data records;

[0071] The minimum-maximum standardization method is used in the data preprocessing module to perform data standardization. The specific steps are as follows:

[0072] S1. Calculate the maximum and minimum values: For each feature, find the maximum value (Max) and minimum value (Min) in the comprehensive data set of the construction site;

[0073] S2. Apply transformation formula: For each feature value x in the comprehensive data set of the construction site, use the following formula for transformation:

[0074]

[0075] Among them, x norm is the transformed value;

[0076] S3. Transform the construction site comprehensive dataset: Apply the above transformation to each feature of the entire dataset; after min-max normalization, all features will be scaled to the range of 0 to 1

[0077] The feature engineering module receives the preprocessed data and then performs feature extraction and selection. The feature engineering module reduces the number of features by selecting the features most relevant to the prediction target and reducing the dimension. The feature engineering module uses principal component analysis (PCA) to find the main components of the data by calculating the covariance matrix of the eigenvalues. The calculation formula is:

[0078] where Σ is the covariance matrix, x i is a data point, is the mean of the data.

[0079] The model training and prediction module uses 70% of the data as a training set, 15% of the data as a validation set, and 15% of the data as a test set;

[0080] The model training submodule uses the training set to train the model, optimizes the performance by adjusting the model parameters, and uses the batch gradient descent algorithm to optimize the parameters of the logistic regression model. The iterative update formula is:

[0081] Where θj is the model parameter, α is the learning rate, and J(θ) is the cross entropy loss function, which is calculated as:

[0082]

[0083] Where m is the number of training samples, y(i) is the true label of the i-th sample, and hθ(x(i)) is the prediction result of the model.

[0084] The intelligent decision support module receives the prediction results from the model training and prediction module and converts them into actionable insights or suggestions. This module formulates decision strategies based on the prediction results and business logic.

[0085] The decision strategy of the intelligent decision support module is formulated based on the decision rules of the model. The intelligent decision support module includes the following steps:

[0086] S1. Set a threshold and take specific actions when the predicted probability exceeds the set value;

[0087] S2. Use algorithms such as rule engines or logistic regression to combine the outputs of multiple decision tree models into a comprehensive decision;

[0088] S3. Optimize decision-making strategies to maximize profits or minimize costs, taking into account cost-benefit analysis;

[0089] S4. Execution and monitoring: Implement decision-making strategies and monitor decision results. Collect feedback data for subsequent model retraining and optimization;

[0090] S5. Report and Explanation: Generate reports to explain the model’s prediction results and decision recommendations to decision makers, and provide visualization tools to help decision makers understand the model’s prediction logic and decision basis.

[0091] From the above, we can know that:

[0092] In the present invention, the data preprocessing module improves the overall data quality: by data cleaning, outlier processing and duplicate value processing, the integrity and accuracy of the data are improved to ensure the reliability of subsequent analysis. The data preprocessing module scales the data to a range of 0 to 1 through minimum-maximum normalization, which facilitates comparison between different features and model training. At the same time, the feature engineering module identifies the features most relevant to the target variable through feature extraction and selection, reduces data dimensions, and improves the efficiency of model training. The feature engineering module uses methods such as principal component analysis (PCA) to reduce data dimensions, remove redundant information, and make the model more concise and efficient;

[0093] In the present invention, the model training and prediction module establishes a prediction model for the environmental parameters and activity trends of the construction site through a machine learning algorithm to provide support for decision-making. Through model training and verification, the model parameters are continuously optimized to improve the prediction accuracy and generalization ability of the model. The intelligent decision support module generates specific decision suggestions based on the prediction results and business logic to help managers make scientific and reasonable decisions. Decision strategies are implemented, and decision results are monitored, and feedback data is collected for subsequent retraining and optimization of the model. In summary, the four modules within the data processing module cooperate with each other to jointly improve the quality of data, the prediction accuracy of the model and the decision support ability, providing powerful data support and intelligent decision-making capabilities for the comprehensive management of the construction site, helping to improve work efficiency and safety, realize data-driven decision support, and bring about economic benefits.

[0094] In the present invention, the video monitoring module and the communication module realize 24-hour real-time monitoring of the construction site, and the management personnel can view the situation of the construction site in real time through the remote server module and perform remote management. This remote monitoring and management capability greatly improves management efficiency and reduces the workload of on-site personnel. The storage module is responsible for long-term storage of statistical charts, reports and original data generated by the data processing module, and synchronizes them to the remote server module to achieve redundant backup and remote access of the data. This data storage and backup capability ensures the security and accessibility of the data, and provides a solid foundation for subsequent data analysis and decision-making. Through the massive data storage capacity of the storage module, the system can perform historical data analysis and trend prediction, help management personnel understand the historical situation of the construction site, and predict future development trends, providing a reference for decision-making.

[0095] 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 term "comprise" or any other variant thereof is 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 elements defined by the sentence "comprise a ..." do not exclude the presence of other identical elements in the process, method, article or device including the elements.

[0096] The above description enables those skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A construction site comprehensive data acquisition system based on the Internet of Things, characterized by: The system includes a sensor module, a video monitoring module, a data processing module, a display module, a storage module, a communication module and a remote server module; The data processing module is internally provided with a data preprocessing module, a feature engineering module, a model training and prediction module and an intelligent decision support module; The sensor module monitors the environmental parameters and activities of the construction site in real time and sends the raw data to the data processing module; The video monitoring module captures visual information of the construction site through a camera and transmits the video data to the data processing module; The data processing module cleans, preprocesses and extracts features from the received raw data, and performs data analysis through machine learning algorithms to identify patterns and predict trends; the processed data is sent to the display module and storage module; at the same time, the data will also be sent to the remote server module through the communication module; The display module receives statistical charts and reports from the data processing module and displays them to the management personnel at the construction site; The storage module is responsible for long-term storage of statistical charts, reports and original data generated by the data processing module; at the same time, these data will also be synchronized to the remote server module to achieve redundant backup and remote access of data; The communication module transmits the data generated by the data processing module to the remote server module; The remote server module is a central data processing and storage center that receives data from multiple construction sites; The remote server module provides data storage services to ensure data security and accessibility; Managers can view real-time data and reports through a secure remote access interface for remote monitoring and management; The data preprocessing module passes the preprocessed data to the feature engineering module for feature extraction and selection. The feature-engineered data generated inside the feature engineering module is used to train and verify the machine learning model. The prediction results generated by the model training and prediction module for new data using the trained model are passed to the intelligent decision support module to generate decision support information.

2. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The sensor module is provided with a temperature sensor to accurately measure the temperature changes at the construction site; the sensor module is provided with a humidity sensor to monitor the moisture content in the air in real time; the sensor module is provided with a light sensor to measure the light intensity at the construction site; the sensor module is provided with a noise sensor to monitor the noise level at the construction site in real time; the sensor module is provided with a vibration sensor to monitor the vibration of equipment or structure; the sensor module is provided with a wind speed sensor to monitor the wind speed; the sensor module transmits the collected data to the data processing module to provide support for subsequent data analysis and decision-making.

3. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The video monitoring module is equipped with a high-definition camera to monitor the construction site in real time 24 hours a day.

4. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The display module displays real-time statistical data, charts and video monitoring images through a large-screen display or an interactive touch screen; different display modes are set to meet different management needs and decision-making scenarios.

5. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The storage module stores the collected data and the statistical charts and reports generated by the data processing module; the storage module uses RAID configuration services to ensure the security and persistence of data.

6. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The communication module transmits the collected data and the statistical charts and reports generated by the data processing module to a remote server or cloud platform; the communication module ensures the security and integrity of data transmission through a secure network connection via a VPN or a dedicated network; The communication module supports MQTT, HTTP, and WebSocket communication protocols.

7. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The data cleaning in the data preprocessing module includes the following steps: Missing value processing: Check whether there are missing values ​​in the data and process them, such as deletion or interpolation; Outlier processing: detect and process outliers, delete or replace them; Duplicate value processing: delete duplicate construction site comprehensive data records; The data preprocessing module uses the minimum-maximum standardization method to perform data standardization processing, and the specific steps are as follows: S1. Calculate the maximum and minimum values: For each feature, find the maximum and minimum values ​​in the comprehensive dataset of the construction site; S2. Apply transformation formula: For each feature value x in the comprehensive data set of the construction site, use the following formula for transformation: Among them, x norm is the transformed value; S3. Transform the comprehensive construction site dataset: Apply the above transformation to each feature of the entire dataset; after min-max normalization, all features will be scaled to the range of 0 to 1.

8. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The feature engineering module receives the preprocessed data and then performs feature extraction and selection; the feature engineering module reduces the feature data by selecting the features most relevant to the prediction target and reducing the dimension. The feature engineering module uses principal component analysis to find the main components of the data by calculating the covariance matrix of the eigenvalues. The calculation formula is: where Σ is the covariance matrix, x i is a data point, is the mean of the data.

9. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The model training and prediction module uses 70% of the data as a training set, 15% of the data as a validation set, and 15% of the data as a test set; The model training submodule uses the training set to train the model, optimizes the performance by adjusting the model parameters, and uses the batch gradient descent algorithm to optimize the parameters of the logistic regression model. The iterative update formula is: Where θj is the model parameter, α is the learning rate, and J(θ) is the cross entropy loss function, which is calculated as: Where m is the number of training samples, y(i) is the true label of the i-th sample, and hθ(x(i)) is the prediction result of the model.

10. The construction site comprehensive data acquisition system based on the Internet of Things as claimed in claim 1, characterized in that: The intelligent decision support module receives the prediction results from the model training and prediction module and converts them into actionable insights or suggestions. This module formulates decision strategies based on the prediction results and business logic; The decision strategy of the intelligent decision support module is formulated based on the decision rules of the model; the intelligent decision support module includes the following steps: S1. Set a threshold and take specific actions when the predicted probability exceeds the set value; S2. Use algorithms such as rule engines or logistic regression to combine the outputs of multiple decision tree models into a comprehensive decision; S3. Optimize decision-making strategies to maximize profits or minimize costs, taking into account cost-benefit analysis; S4. Execution and monitoring: Implement decision-making strategies and monitor decision results; collect feedback data for subsequent model retraining and optimization; S5. Report and Explanation: Generate reports to explain the model’s prediction results and decision recommendations to decision makers, and provide visualization tools to help decision makers understand the model’s prediction logic and decision basis.

Citation Information

Cited By

  • Static pressure pile intelligent construction decision support system

    CN120373067A