CN116862199A

CN116862199A - Building construction optimizing system based on big data and cloud computing

Info

Publication number: CN116862199A
Application number: CN202311040493.7A
Authority: CN
Inventors: 马行耀; 叶佳赟; 齐琳
Original assignee: Zhejiang College of Construction
Current assignee: Zhejiang College of Construction
Priority date: 2023-08-17
Filing date: 2023-08-17
Publication date: 2023-10-10

Abstract

The invention relates to a building construction optimization system based on big data and cloud computing. Comprising the following steps: the data acquisition and storage module acquires various data of a construction site in real time through a sensor and monitoring equipment, and stores and manages the various data in real time through a cloud computing platform; the data analysis and intelligent decision module processes and analyzes the collected data through a big data analysis technology, extracts high-value information and generates a corresponding decision model; the construction plan and resource management module is used for carrying out optimization management on the construction plan and resources according to the decision model and the real-time data, adjusting the progress and sequence of the construction plan and configuring material resources and personnel resources; and the risk management and safety monitoring module predicts and manages potential safety hazards and risks in the construction process by establishing a risk model and a safety monitoring system. The system can continuously collect, analyze and build the data model, and provide real-time feedback and improvement suggestions.

Description

Building construction optimizing system based on big data and cloud computing

Technical Field

The invention relates to a building construction optimization system based on big data and cloud computing.

Background

In spite of the great data and the cloud computing technology background, the building construction optimization system has a plurality of advantages, but the following disadvantages and shortcomings still exist at present: 1. data privacy and security: the use of big data requires the collection and analysis of a large amount of sensitive data including construction progress, personnel information, equipment data, etc. This may involve privacy and security issues such as data leakage or unauthorized access. Ensuring the privacy and security of data remains a challenge. 2. Data acquisition and consistency: establishing a big data based system requires a lot of data acquisition and processing. However, due to the complexity and variety of construction sites, the collection of data may face difficulties. At the same time, ensuring consistency and accuracy of data is also a challenge, as data from different sources may have differences. 3. Accuracy and applicability of the algorithm: establishing an optimization system requires the use of appropriate algorithms and models for data analysis and decision support. However, current algorithms and models still face problems of accuracy and applicability. In application to actual construction, algorithms may be affected by factors such as data quality problems, complex construction environments, and changes in demand. 4. Technical maturity and acceptance: although the application of technologies such as big data and cloud computing in the building field is increasing, the problems of technology maturity and acceptance still exist. Some construction enterprises may face technical implementation and training challenges, and constructors and management teams also need to adapt to these new technologies and tools. 5. Cost and ROI problem: building systems based on big data and cloud computing involves corresponding investment and operating costs. The rate of Return (ROI) of a system may be a critical issue in the long term. The building enterprise needs to measure the balance between investment and return to determine the feasibility and sustainability of the system.

Disclosure of Invention

The invention aims to provide a building construction optimization system based on big data and cloud computing, so as to solve part of defects and shortcomings pointed out in the background art.

The invention solves the technical problems as follows: comprising the following steps: the data acquisition and storage module acquires various data of a construction site in real time through a sensor and monitoring equipment, and stores and manages the various data in real time through a cloud computing platform;

the data analysis and intelligent decision module processes and analyzes the collected data through a big data analysis technology, extracts high-value information and generates a corresponding decision model;

the construction plan and resource management module is used for carrying out optimization management on the construction plan and resources according to the decision model and the real-time data, adjusting the progress and sequence of the construction plan and configuring material resources and personnel resources;

and the risk management and safety monitoring module predicts and manages potential safety hazards and risks in the construction process by establishing a risk model and a safety monitoring system.

Further, wherein the data acquisition and storage module comprises an acquisition: environmental parameter data, equipment status data, and supply data; the data analysis and intelligent decision module comprises an intelligent algorithm and a rule engine;

The construction plan and resource management module comprises a step of adjusting the progress and sequence of the construction plan and a step of configuring material resources and personnel resources; the risk management and safety monitoring module comprises a safety management module, a safety monitoring module and a safety monitoring module, wherein the safety management and safety monitoring module is used for discovering and processing potential safety problems and providing emergency response and early warning functions; the risk management and safety monitoring module monitors various data of a construction site in real time, including environmental parameters, equipment states and personnel behaviors, and monitoring equipment related to safety.

Further, the system also comprises a user interface module for providing an operation interface to enable a user to view related construction data and decision results; the system further comprises a communication module for exchanging and communicating data with other devices or systems;

the construction plan and resource management module adjusts the progress and sequence of the construction plan according to the real-time data and the prediction model, and configures storage and transportation resources; and the risk management and safety monitoring module sets an early warning rule and an emergency response mechanism according to the potential safety hazard and the risk characteristics of the construction site.

Further, the data acquisition and storage module acquires environmental parameter data, equipment state data and material supply data of a construction site in real time through a sensor and monitoring equipment, and the specific acquisition mode comprises the following steps:

A. And (3) environmental parameter data acquisition:

temperature sensor: temperature sensors arranged at different positions of a construction site monitor environmental temperature changes in real time;

humidity sensor: the method comprises the steps of arranging the air humidity monitoring device in a key area of a construction site, and monitoring the air humidity in real time; the key areas comprise: the system comprises a concrete pouring area, a humidity sensitive material area, a coating area, a basement construction area, a storage area and an electrical equipment area;

a pressure sensor: the method is used for collecting the air pressure conditions of the construction site, including atmospheric pressure and oil gas pressure;

B. and (3) collecting equipment state data:

and (3) monitoring a sensor: collecting the working states of equipment, including current, voltage, power and rotating speed, through sensors arranged on mechanical equipment and electrical equipment;

and (3) detecting a switch state: detecting the switching state of the equipment by using a switching sensor, and recording the starting and stopping of the equipment and fault alarm events;

C. and (3) material supply data acquisition:

warehouse inventory monitoring: real-time monitoring the materials in the warehouse by utilizing a sensor or RFID technology, and recording the inventory and the position of the materials; integrating a material purchasing system: and integrating the material purchasing system with the building construction optimizing system.

Further, the intelligent algorithm and rule engine of the data analysis and intelligent decision module comprises the following specific core algorithm processes:

A. intelligent algorithm: the intelligent algorithm is used for comprising the following steps: analyzing the temperature, humidity and pressure environment parameter data of the construction site, and determining an optimal construction scheme under different environment conditions; predicting construction progress and optimizing resource allocation based on historical data and real-time data through a prediction and optimization algorithm;

the machine learning algorithm trains a model, learns from data and makes an automatic decision, predicts the occurrence of problems according to construction progress and resource data, and provides corresponding early warning and countermeasure;

B. rule engine: the rule engine makes and applies a series of rules and logics to make decisions and reasoning according to the collected construction data; in a building construction optimization system based on big data and cloud computing, a rule engine performs fact reasoning and rule matching according to real-time data of a construction site and preset rules, and the system comprises: judging whether potential safety hazards or quality problems exist on a construction site, and carrying out high-temperature alarm and equipment failure; and the rule engine judges whether the materials are in place or not and whether the materials are supplemented or not according to the material supply data and the construction plan data, and generates corresponding purchasing suggestions.

Further, the generating of the decision model involves the steps of:

s1, data cleaning and pretreatment: firstly, cleaning and preprocessing collected data, including data denoising, missing value filling, abnormal value detection and data normalization;

s2, feature selection and extraction:

after data cleaning and preprocessing, carrying out feature selection and extraction, and selecting the most representative and relevant features from a large amount of acquired data; this is achieved by statistical analysis, correlation analysis and feature engineering methods;

s3, model selection and training:

selecting a proper machine learning algorithm or other modeling methods according to specific decision-making requirements; the machine learning algorithm comprises a decision tree, a support vector machine, a random forest and a neural network; model training is carried out by using the selected algorithm, and model performance is optimized according to feedback of training data;

s4, model evaluation and tuning:

evaluating and verifying the trained model, and evaluating the accuracy, precision and generalization capability of the model by using a test data set; the method comprises the steps that the fruit model has problems or does not meet decision requirements, and tuning and optimizing are carried out, wherein the parameters of the model are adjusted, and the characteristics are increased or reduced;

S5, generating and applying a decision model:

the decision model with higher prediction capability and accuracy is obtained through model training and tuning; the model makes intelligent decisions according to the input new data; and generating a corresponding decision model according to the prediction result and the decision rule of the model, and taking corresponding action or suggestion.

Further, the high-value information includes: providing support and guidance for key decisions in the construction process;

the method has the capability of prediction and early warning, finds potential problems or challenges in advance, and provides corresponding prediction and early warning; monitoring and feedback are carried out on a real-time or near real-time basis, and the state and the change of the construction process are provided in time; through real-time monitoring, deviation and problems are rapidly identified; based on reliable data analysis and directly supporting decision-making process;

support the need for continued improvement; bottlenecks and opportunities for improvement in the construction process are revealed by analysis and feedback.

Further, the high-value extraction process comprises the following steps:

firstly, searching and visually analyzing the acquired data, and visually displaying the data in a mode of drawing a chart and making a data instrument panel; on the basis of exploring data, a data mining technology is applied to find hidden modes and rules in the data, and potential high-value information is extracted; the method comprises the steps of mining and exploring data by using a clustering analysis method, an association rule mining method and a classification algorithm method; meanwhile, feature engineering is carried out, and more significant features are extracted through combination, conversion and scaling modes;

Further carrying out correlation analysis to find out the correlation between the data; evaluating the correlation degree among different features through statistical analysis and a machine learning algorithm, and finding out factors with strong correlation to construction optimization; and providing information supporting the decision;

establishing a prediction model and an optimization model by utilizing historical data and real-time data; predicting and optimizing indexes in the construction process by training a machine learning model, regression analysis, time sequence analysis and an optimization algorithm method; making a corresponding solution;

applying the extracted high-value information to a decision process; converting the result of data analysis into an actual operation guide and decision support, and helping a construction manager to make an accurate and targeted decision; the method comprises the step of adjusting a work plan and resource allocation according to predicted construction progress and resource requirements.

Further, the decision model and the real-time data optimally manage the construction plan and the resources by adopting the following method:

s1, real-time plan adjustment:

according to the feedback of the real-time data, dynamically adjusting the construction plan; comparing and analyzing the construction progress and the resource use condition index with a decision model to judge whether to adjust the original plan; the method comprises the steps of carrying out real-time plan adjustment by rearranging tasks, adjusting construction periods and optimizing resource allocation modes when delay or resource shortage occurs;

S2, resource matching and optimizing:

matching and optimizing construction resources by utilizing the decision model and the real-time data; according to real-time requirements and resource availability, dynamically evaluating the use efficiency and the utilization rate of each resource; determining an optimal resource allocation scheme including manpower, equipment and materials through model analysis so as to reduce resource waste and save cost; the resource allocation can be adjusted in time to cope with emergency and change demands;

s3, risk management and decision support:

based on the decision model and real-time data, performing risk management and decision support; predicting potential risks and challenges by analyzing real-time data and historical data, and timely taking corresponding precautionary measures; based on the decision model, making a coping scheme and a decision strategy to help a construction manager make a decision with rationality and feasibility;

s4, progress monitoring and adjustment:

monitoring and adjusting the construction progress by utilizing the decision model and the real-time data; evaluating and predicting the construction progress through real-time data acquisition and analysis; the method comprises the steps of taking corresponding measures including adjusting task priority, allocating personnel and adjusting procedure sequence under the condition that the result is lagged or advanced;

S5, continuous improvement and knowledge accumulation:

performing continuous improvement and knowledge accumulation according to continuous optimization of the decision model and feedback of real-time data; by analyzing the real-time data, the bottleneck and the improvement opportunity in the construction process are found, and feedback and optimization are performed in time; accumulation of experience and training is also used to update and refine the decision model.

Further, in the construction plan and resource management module, the following method is adopted to adjust the progress and sequence of the construction plan and to configure materials and personnel resources:

s1, monitoring and analyzing real-time data:

the construction progress, the resource utilization condition and the risk condition information are known through monitoring and analyzing the real-time data; collecting various index data in the construction process by using sensor and monitoring equipment technologies, and analyzing by combining a decision model; determining whether to adjust the progress and sequence and judging whether to reconfigure the resources;

s2, priority and urgency assessment:

according to the real-time data analysis and the support of the decision model, the priorities and urgency of different tasks and activities are evaluated; determining which tasks are processed preferentially and which resources are configured preferentially by comprehensively considering construction progress, resource availability, task dependency relationship and risk degree factors;

S3, task adjustment and procedure optimization:

according to the analysis of the real-time data, the construction task is adjusted and optimized by combining with priority evaluation; the method comprises the steps of rearranging the tasks, adjusting the time window of the tasks, dividing and adjusting the tasks;

s4, resource allocation and scheduling:

optimizing distribution and scheduling of materials and personnel resources based on real-time data and support of a decision model; according to the actual and resource availability, reasonably arranging and allocating material supply, equipment and worker resources; by matching the requirements and supply of resources, the consistency and the high efficiency of construction activities are ensured;

s5, cooperative cooperation and communication:

maintaining cooperative cooperation and communication in the process of adjusting construction plans and resource allocation; each team and department are closely matched, share real-time data and information, and jointly decide and coordinate resource allocation.

Further, the process of establishing the risk management model and the safety monitoring system comprises the following steps:

s1, risk management model:

a. risk identification: firstly, carrying out comprehensive risk identification on a construction project; determining potential risk factors by carrying out risk identification on the aspects of construction process, engineering environment and personnel;

b. Risk assessment: evaluating the identified risk, including evaluating aspects of the risk's nature, severity, and scope of influence; determining the priority of risks and the emergency degree of treatment according to the evaluation result;

c. risk policies and control measures: based on the result of risk assessment, corresponding risk strategies and control measures are formulated; measures include measures in terms of risk prevention, mitigation, diversion, and emergency response;

d. risk monitoring and improvement: establishing a risk monitoring mechanism to monitor the implementation condition of the risk control measures; through continuous risk assessment and improvement measures;

s2, a safety monitoring system:

a. design requirements: determining the functional requirement and performance index of the system according to the safety monitoring target and requirement; the system comprises the functions of daily safety monitoring, anomaly detection and event early warning;

b. and (3) architecture design: designing an overall architecture of the safety monitoring system based on the requirements; determining required hardware equipment, sensors and network architecture, and designing data acquisition, transmission and processing flows;

c. data acquisition and processing: selecting a proper sensor and camera equipment, and collecting images, videos and sensor data of a construction site in real time; establishing a proper data processing flow, including the steps of data cleaning, feature extraction and anomaly detection;

d. Intelligent analysis and early warning: intelligent analysis and processing are carried out on the real-time data by utilizing machine learning and artificial intelligence technology; through image recognition, object detection and behavior analysis algorithms, potential safety hazards and abnormal conditions are recognized, and real-time early warning and alarming functions are realized;

e. visualization and reporting: the monitoring and analysis results are presented to construction managers and related personnel through data visualization and report generation; providing an intuitive interface and report;

f. continuous improvement and update: through continuous monitoring, analysis and improvement, the functions and performances of the safety monitoring system are continuously optimized; and updating and upgrading the system according to actual requirements and technical development.

The invention has the beneficial effects that:

1. real-time monitoring and decision support: the system can collect, analyze and monitor various data of a construction site in real time, such as progress, cost, quality, safety and the like. Through big data analysis and algorithm model, the system can identify problems and abnormal conditions in time and provide decision support, and help manager to make adjustment and decision quickly so as to optimize construction progress.

2. The construction efficiency and quality are improved: the system utilizes the capacity of big data, deeply analyzes construction data and finds potential work bottlenecks, low-efficiency links and hidden quality hazards. Through the data-driven optimization strategy, the system can help to improve the construction efficiency, reduce the time waste and the resource waste, and ensure that the construction quality meets the standards and requirements.

3. Resource optimization and cost control: systems based on big data and cloud computing can effectively manage the allocation and use of human resources, equipment, and materials. By means of real-time data monitoring and analysis, the system can optimize resource allocation, ensure optimal utilization of resources, reduce cost and improve benefit.

4. Risk management and security monitoring: the system can help discover and prevent potential safety risks and problems by monitoring and analyzing data of a construction site in real time. By providing the early warning and alarming functions, the system can monitor the safety condition in time and take measures to ensure the safety of the construction process and the health of workers.

5. Data visualization and collaboration: the system displays construction data to project related personnel in an intuitive manner through a data visualization technology, so that the project related personnel can better understand and analyze the data. Through cloud computing technology, the system can realize collaborative cooperation between departments and regions, promote information sharing and communication, and strengthen project management effects.

6. Continuous improvement and learning: systems based on big data and cloud computing have the advantages of data accumulation and openness. The system is capable of continuously collecting, analyzing and building data models, providing real-time feedback and improvement suggestions. The construction manager and team are prompted to continuously learn, the construction process and the management method are continuously optimized, and the working efficiency and the quality are improved.

Drawings

FIG. 1 is a flow chart of the whole building construction optimization system based on big data and cloud computing.

Detailed Description

The following describes the embodiments of the present invention in detail with reference to the drawings.

Examples:

the data acquisition and storage module is an important component of the building construction optimization system. The system collects various data of a construction site in real time through sensors and monitoring equipment, and stores and manages the data in real time through a cloud computing platform.

Various sensors and monitoring devices are arranged in key areas of a construction site, such as temperature sensors, humidity sensors, vibration sensors, pressure sensors, video monitoring and the like. These devices are capable of monitoring various physical quantities and state changes at a construction site in real time.

The sensor and the monitoring device are in data transmission with the data acquisition and storage module through wired or wireless connection. The module collects data acquired by the sensor and the monitoring equipment in real time and ensures the time sequence and the integrity of the data. The collected original data is subjected to data conversion and processing so as to adapt to the subsequent storage and analysis requirements. The process of data conversion may include data cleansing, format conversion, data fusion, etc. In some cases, real-time data processing and feature extraction may also be required. And storing and managing the acquired data in real time through a cloud computing platform. The cloud computing platform provides high availability and expandability, and can ensure the security of data. The data may be stored in a distributed database or data lake for subsequent data analysis and application.

The collected data is processed and analyzed through a big data analysis technology, and valuable information is extracted. The module utilizes technologies such as machine learning, data mining and the like to carry out deep analysis on data, generates a corresponding decision model and provides decision support for construction managers. The module optimally manages the construction plan and the resources according to the decision model and the real-time data. Through analysis and adjustment to construction progress, material demand and personnel resource, the progress and the order of construction plan can be optimized to the module, and reasonable configuration material and personnel resource improves efficiency of construction and quality. The module establishes a risk model and a safety monitoring system, and predicts and manages potential safety hazards and risks in the construction process. By analyzing the real-time data, the module can identify potential risk factors and timely take measures to perform early warning and control, so that the safety of the construction process and the health of personnel are ensured.

In this embodiment, the data acquisition and storage module includes an acquisition: environmental parameter data, equipment status data, and supply data; the data analysis and intelligent decision module comprises an intelligent algorithm and a rule engine;

And the data acquisition and storage module is used for:

environmental data of a construction site is collected in real time through monitoring equipment such as a temperature sensor, a humidity sensor and the like. In an embodiment, the temperature sensor may collect temperature data every hour and the humidity sensor may collect humidity data every 30 minutes.

And working state data of construction equipment are obtained in real time through equipment monitoring equipment such as pressure sensors, vibration sensors and the like. In an embodiment, the pressure sensor can detect the pressure change of the crane, and the vibration sensor can monitor the vibration condition of the concrete mixer.

And collecting the material supply conditions of the construction site, such as the quantity of materials entering and exiting the warehouse, supplier information and the like, in real time by means of RFID (radio frequency identification) tags or bar code scanning and the like.

Example application: and the construction site uses a temperature sensor and a humidity sensor to collect environmental parameter data. The temperature sensor collects temperature data once every hour, and the humidity sensor collects humidity data once every 30 minutes. These data will be stored and managed in real time by the cloud computing platform for subsequent data analysis and application.

And the data analysis and intelligent decision module:

the collected data is analyzed and processed by techniques such as machine learning, data mining, etc. In the embodiment, taking temperature data as an example, a time series analysis method can be used to predict the temperature trend of several hours in the future, so as to take measures for adjusting the construction plan in advance. And (3) making a set of rules and conditions, and judging and deciding according to the acquired data. In an embodiment, when the humidity exceeds a set threshold, the system may send an alarm and alert related personnel to perform the drying process to avoid construction quality problems.

The temperature data is analyzed using intelligent algorithms. The system can predict the temperature trend of the construction site for a plurality of hours in the future according to the temperature data of the past days. According to the prediction result, the system can adjust the working procedure of which the temperature needs to be considered in the construction plan in real time so as to avoid the influence of the too high or the too low temperature on the construction quality.

The construction plan and resource management module comprises the steps of adjusting the progress and sequence of the construction plan and configuring material resources and personnel resources; the risk management and safety monitoring module comprises a safety management module, a safety monitoring module and a safety monitoring module, wherein the safety management and safety monitoring module is used for discovering and processing potential safety problems and providing emergency response and early warning functions; the risk management and safety monitoring module monitors various data of a construction site in real time, including environmental parameters, equipment states and personnel behaviors, and safety-related monitoring equipment.

Construction planning and resource management module:

adjusting the progress and sequence of the construction plan: the system can dynamically adjust the construction plan through the decision model and real-time data provided by the data analysis and intelligent decision module. In embodiments, if a process delay results in a blocked overall progress, the system may shorten the construction time by optimizing the resource allocation or adjusting the process sequence.

Configuring material and personnel resources: based on data analysis and intelligent decision model, the system can arrange material and personnel resources reasonably, avoiding the condition of idle or insufficient resources. According to the embodiment, the system can predict the usage amount of required materials according to real-time material supply data and process requirements, and timely arrange material supply and distribution.

Examples: the embodiment data analysis module analyzes and obtains the progress lag of the working procedure of a certain construction stage, and the system automatically adjusts the progress and the sequence of the related working procedure in the construction plan according to the feasibility analysis and the provided decision model. Meanwhile, according to real-time collected material supply data and personnel resource conditions, the system can optimize resource allocation and ensure that needed materials and personnel can be in place in time.

Risk management and security monitoring module:

the potential security problem is found and handled: through data analysis and intelligent algorithm, the system can identify potential safety hazards of the construction site. By analyzing the equipment state data and the environment parameter data, the system can detect abnormal conditions of equipment or unsafe factors of the working environment and provide corresponding early warning and processing suggestions.

Providing emergency response and early warning functions: based on the real-time data monitoring and prediction model, the system can provide emergency response and early warning functions. In the embodiment, through the monitoring equipment (such as a flame sensor, a smoke detector and the like) related to safety, the system can timely discover dangerous situations such as fire or smoke and the like, trigger emergency measures and remind related personnel to evacuate.

Examples: the risk management and security monitoring module may use the real-time environmental parameter data and the device status data to determine whether a potential security problem exists at the job site. In the embodiment, when the pressure sensor monitors overload work of the crane, the system can detect and send out an alarm in real time to prompt related personnel to take measures so as to ensure construction safety.

By introducing actual data, the feasibility of the construction plan and resource management module and the risk management and safety monitoring module in optimizing the construction plan, managing the resources and discovering and handling the safety problems can be seen in the scheme. The modules are combined with data analysis and intelligent decision technology, so that management and guarantee are provided for the construction process, and the construction efficiency and safety are further improved.

In this embodiment, the user interface module provides an interactive interface for the construction manager, so that the construction manager can conveniently view relevant construction data and decision results. The interface can display data in the forms of charts, reports, maps and the like, and provides a visual operation interface, so that a user can conveniently perform operations such as inquiring, configuring and adjusting.

Examples: through the user interface module, construction manager can look over the chart of real-time construction temperature data and humidity data to select specific time period through drop-down menu and look over. The user can also adjust the progress of a certain procedure in the construction plan through the operation interface so as to adapt to the actual situation of the construction site.

Data exchange and communication: the communication module is responsible for data exchange and communication with other devices or systems. The system can communicate real-time data with the sensor and the monitoring equipment, and can also transmit and receive data with an external system, such as a material supply system, a human resource management system and the like of a supplier.

Examples: the communication module can exchange data with a system of the material provider, and acquire the state and progress data of material supply in real time. In an embodiment, when the supply chain of materials changes, the provider's system may send a notification to the construction management system, and the system may make corresponding adjustments to the construction plan based on the information.

The data acquisition and storage module acquires environmental parameter data, equipment state data and material supply data of a construction site in real time through the sensor and the monitoring equipment, and the specific acquisition mode comprises the following steps:

and (3) environmental parameter data acquisition:

1. temperature sensor: temperature sensors installed at different positions of a construction site monitor environmental temperature changes in real time.

The temperature sensor can be installed in key areas of a construction site, such as a concrete pouring area, a steel bar welding area and the like. The sensor continuously monitors the ambient temperature and transmits the acquired temperature data to the data acquisition and storage module in real time.

Examples: in a construction site, the temperature sensor is installed in a high temperature area, such as a concrete placement area. The sensor collects temperature data once every 15 minutes, and the data can be transmitted to the data collection and storage module for real-time storage and management. Therefore, construction managers can check temperature data through the user interface module, and timely adjust construction plans according to decision results provided by the data analysis and intelligent decision module, so that construction quality is ensured.

2. Humidity sensor: the system is arranged in a key area of a construction site, and the air humidity condition is monitored in real time.

Humidity sensors are placed in critical areas of a construction site, such as a wood work area, a plasterboard construction area, etc. The sensor monitors the air humidity in real time and sends the collected humidity data to the data collection and storage module.

Examples: at a building finishing site, the humidity sensor is disposed in the woodworking area. The sensor collects humidity data once every 30 minutes, and transmits the data to the data collection and storage module through the communication module. Construction manager can look over humidity data through user interface module, according to data analysis and intelligent decision-making module's result, arrange construction plan and safeguard measure rationally to avoid humidity to timber's influence.

The humidity sensor is arranged in a key area of a construction site; the following are some key areas:

and (3) concrete pouring areas: humidity has an important influence on the setting and strength development of concrete. Monitoring the humidity of the concrete pouring area can ensure proper water-cement ratio and construction conditions so as to ensure the concrete engineering quality.

Humidity sensitive material area: some materials, including wood, paper, etc., are very sensitive to humidity. In these areas, monitoring humidity can prevent problems such as swelling, deformation, mildew and the like of the material caused by excessive humidity, and simultaneously avoid drying and cracking of the material caused by excessive humidity.

And (3) coating areas: the coating operation requires proper humidity conditions to ensure the quality and adhesion of the coating. Too high a humidity may result in slow drying of the coating, abnormal viscosity, while too low a humidity may result in too fast drying of the coating, affecting paint quality and construction efficiency.

Basement construction area: the construction area of the basement is easily affected by groundwater, and humidity needs to be monitored to avoid infiltration of groundwater into the construction area, maintain dryness of the construction environment, and ensure construction quality.

Storage area: during construction, many materials and equipment need to be stored in a warehouse or storage area. Proper humidity control can prevent the material from absorbing moisture, rusting, or causing other potential quality problems.

Electrical equipment area: humidity has a great influence on the normal operation of electrical equipment. Too high a humidity may cause corrosion of equipment components, while too low a humidity may create static electricity problems or cause equipment failure.

and (3) collecting equipment state data:

1. and (3) monitoring a sensor: the working states of the equipment, including current, voltage, power and rotation speed, are acquired through sensors installed on the mechanical equipment and the electrical equipment.

The sensors are arranged on mechanical equipment and electrical equipment at a construction site, so that the running state parameters of the equipment can be monitored in real time, and data acquisition of the parameters is transmitted to the data acquisition and storage module.

Examples: the sensor is arranged on the crane on the site, so that the current and the rotating speed of the crane can be monitored in real time. The sensor collects data once every 5 minutes and transmits the data to the data collection and storage module. Therefore, construction manager can check real-time state data of the crane through the user interface module, know the working condition of equipment, and correspondingly adjust and maintain according to the result of the data analysis and intelligent decision module.

2. And (3) detecting a switch state: the switch state of the device is detected using a switch sensor, and the start, stop, and fault alarm events of the device are recorded. By installing the switch sensor on the switch of the equipment, the switch state of the equipment can be detected in real time, and relevant event information such as starting and stopping of the equipment, fault alarm and the like can be recorded. The data can also be transmitted to a data acquisition and storage module for storage and management.

Examples: a switch sensor is arranged on a start switch of an electric mixer to monitor the start-stop state of the mixer. If an abnormality occurs, such as a blender stopping or a malfunction alarm, the sensor immediately captures this information and records it and transmits it to the data acquisition and storage module. The construction manager can check the on-off state information of the equipment in real time through the user interface module, and timely take measures to repair or replace the equipment.

The material supply data acquisition steps are as follows:

3. warehouse inventory monitoring: and (3) monitoring the materials in the warehouse in real time by using a sensor or RFID technology, and recording the inventory and the position of the materials. By means of the sensor or RFID technology, the material condition in the warehouse can be monitored in real time, and information such as inventory quantity and position of the material can be recorded. The data can be collected and stored by a data collection and storage module.

Examples: in one building material warehouse, an RFID reader and an RFID tag are installed on each cargo. Through RFID technology, the inventory, position and warehouse entry record of each cargo can be monitored in real time. When goods enter or leave the warehouse, the RFID reader-writer can automatically read related information and transmit the related information to the data acquisition and storage module. Thus, construction manager can monitor inventory of warehouse in real time through user interface module, understand material supply condition and make corresponding adjustment and supplement in time.

4. Integrating a material purchasing system: and integrating the material purchasing system with the building construction optimizing system to automatically acquire and update the material supply information. By integrating the material purchasing system with the building construction optimizing system, the automatic acquisition and updating of the material supply information can be realized, and the material supply data in the system and the actual material purchasing situation are ensured to be kept synchronous.

Examples: after the material purchasing system is integrated with the building construction optimizing system, when a material provider supplies new materials, the material purchasing system automatically updates supply information and transmits updated data to the data acquisition and storage module. Thus, construction manager can check the latest state of material supply in real time through the user interface module, and adjust construction plan and supply chain management according to actual demands.

The steps of the intelligent algorithm in the above embodiment are as follows:

1. analyzing the environmental parameter data: and analyzing environmental parameter data such as temperature, humidity, pressure and the like of the construction site through an intelligent algorithm, and determining an optimal construction scheme under different environmental conditions.

The intelligent algorithm can analyze the relation between the environmental parameter data and the construction process by utilizing an analysis method such as statistical analysis, model establishment and the like according to the historical data and the real-time data, and find an optimal construction scheme. For example, the algorithm can deduce the optimal temperature and humidity control strategy according to the change rule of the mechanical properties of the materials under different temperature and humidity conditions, so as to ensure the construction quality and the durability of the materials.

Examples: the intelligent algorithm analyzes the change rule of the concrete strength under different temperature and humidity conditions of the construction site. Through historical data and real-time data, an algorithm can learn and establish a model, predict the strength of concrete according to current temperature and humidity data, and optimally control the pouring time and the proportion of the concrete in a real-time construction plan so as to obtain higher construction quality.

The above embodiment includes the following points:

1. the object is: an optimal construction scheme under specific environmental conditions is found to ensure construction quality and durability of materials.

2. Data sources: historical data and real-time data. The historical data is a past construction record and associated environmental parameters, while the real-time data is a current environmental parameter of the site.

3. The method comprises the following steps: and analyzing the relation between the environmental parameters and the construction process by using methods such as statistical analysis, model establishment and the like.

4. Examples: the relationship between concrete strength and temperature and humidity is considered. By analyzing the historical and real-time data, a model is established to predict the strength of the concrete, thereby optimizing the construction plan.

To understand this process more deeply, the present case may take a simplified linear regression model as an example:

examples the present example has some historical data in which the strength S of concrete versus temperature T and humidity H can be expressed as:

S＝a×T+b×H+c

here, (a), (b) and (c) are model parameters that can be determined by training through historical data.

The example history data is as follows:

temperature T	Humidity H	Intensity S
			20℃	50％	40MPa
25℃	60％	42MPa
			30℃	70％	38MPa

Using these data, the parameters (a), (b) and (c) can be determined by linear regression.

The parameters obtained in the examples are (a=0.5), (b= -0.3) and (c=35), and the model of this case is:

S＝0.5T-0.3H+35

now, if the temperature measured in the case is 28 ℃ and the humidity is 65% at the real-time construction site, the predicted strength of the concrete is:

S＝0.5×28-0.3×65+35＝38.5MPA

The construction team can decide whether to adjust the proportion or the pouring time of the concrete according to the predicted value so as to achieve ideal construction quality.

2. Prediction and optimization algorithm: and predicting the construction progress and optimizing resource allocation based on the historical data and the real-time data through a prediction and optimization algorithm so as to improve the construction efficiency and the resource utilization rate.

The prediction algorithm can predict the progress of the construction process by analyzing the historical data and the real-time data. The optimization algorithm can automatically allocate resources and plan paths according to the prediction result and the construction resource data so as to improve the construction efficiency and the resource utilization rate to the greatest extent.

Examples: and predicting the completion time of a certain engineering procedure according to the historical construction data and the real-time monitoring data by a machine learning algorithm. The algorithm can identify factors influencing the process progress, learn a model based on historical data, optimize the current construction plan through the model, and avoid potential delay and resource waste.

The above embodiment includes the following points:

1. the object is: and predicting the construction progress, and optimizing resource allocation according to the prediction result so as to improve the construction efficiency and the resource utilization efficiency. 2. Data sources: historical data and real-time data. The historical data may be past construction progress, process completion time, resource usage, etc. The real-time data may be current construction status, material use, human configuration, etc.

3. The method comprises the following steps:

prediction algorithm: the historical data and the real-time data are analyzed to predict future construction progress.

Optimization algorithm: and carrying out resource allocation and path planning according to the predicted construction progress and the current resource data.

4. Examples: and predicting the completion time of a certain engineering procedure by using a machine learning algorithm, and optimizing resources according to the prediction.

For more specific illustration, the present case may use a simplified linear regression model as an example for prediction:

completion time T of the facility process and two factors: the material supply speed M is related to the number of constructors P, and the relation is as follows:

T＝a×M+b×P+c

wherein (a), (b) and (c) are parameters that need to be determined from historical data.

The embodiment scheme has the following historical data:

material supply speed M	Number of constructors P	Completion time T
			50units/day	10	5days
60units/day	12	4days
			45units/day	8	6days

Using these data, the parameters (a), (b) and (c) can be obtained by a linear regression method.

Example the parameters obtained in this case are (a= -0.05), (b= -0.2) and (c=10), then the model in this case is:

T＝-0.05M-0.2P+10

at present, the material supply speed is 55units/day at a real-time construction site, the number of constructors is 11, and the project procedure completion time can be predicted according to the scheme:

T＝-0.05×55-0.2×11+10＝4.75days

At this point, the construction team may adjust the resource allocation based on the predicted completion time, such as increasing manpower or speeding up material supply, to further optimize the construction progress.

3. Machine learning algorithm: machine learning algorithms can train models, learn from data and automatically make decisions. For example, problems that may occur are predicted based on construction progress and resource data, and corresponding precautions and countermeasures are provided.

The machine learning algorithm can learn the historical data and the real-time data through a training model, and make automatic decisions according to learning results. For example, by monitoring construction progress and resource usage, the algorithm can predict possible problems or risks and provide corresponding pre-warning and countermeasures to assist construction managers in taking timely action.

Examples: by means of a machine learning algorithm, historical construction data and real-time sensor data are analyzed, and the possibility of material shortage is predicted. The algorithm can predict the possible material shortage situation at a certain future time point according to factors such as material consumption rate, supply chain state and the like, and inform construction managers in advance to take supplementary measures.

The above embodiment includes the following points:

1. The object is: the construction data is analyzed using machine learning algorithms, and problems that may occur, such as material shortage, are predicted and construction managers are warned in time.

2. Data sources: historical construction data and real-time sensor data such as material consumption rate, supply chain status, etc.

3. The method comprises the following steps: machine learning builds a model by training a dataset, which predicts new data (e.g., real data) and makes automatic decisions based on the prediction results.

4. Examples: predicting future shortage of materials and timely notifying related personnel.

To understand this process more intuitively, the present case can be predicted using a simplified logistic regression model as an example:

let Y be the target variable of the two categories, indicating whether the material is in shortage (1 indicates shortage, 0 indicates no shortage). M represents the material consumption rate and S represents the supply chain status (which may be a numerical indicator such as the number of supply chain delay days). The model of the present case can be expressed as:

here, p (y=1) represents the probability of material shortage, and e is the bottom of natural logarithm. Parameters a, b and c need to be trained using historical data.

Examples the present case has the following history data:

Material consumption rate M	Supply chain delay S	Whether or not the material is short of Y
			0.7	2	1
0.5	1	0
			0.9	3	1

Using these data, the parameters a, b and c can be obtained by logistic regression methods in this case.

Examples the parameters obtained in this case after training are a=2.5, b=1.2 and c= -4. Now, the example real-time data tells the case that the material consumption rate is 0.8 and the supply chain delay is 2.5 days, the probability that this case can predict the shortage of material is:

after calculating this formula, the present case can obtain a specific value of p (y=1), and if this value exceeds a certain threshold (e.g. 0.5), the present case can predict that the material will be in shortage and timely notify the construction manager to take action.

Rule engine: the rule engine makes and applies a series of rules and logics to make decisions and reasoning according to the collected construction data; in a building construction optimization system based on big data and cloud computing, a rule engine can conduct fact reasoning and rule matching according to real-time data of a construction site and preset rules;

the rule engine steps are as follows:

judging potential safety hazards and quality problems according to the environmental parameter data and the equipment state data: the rule engine makes decisions and inferences based on the collected construction data by formulating a series of rules and logic. At this step, the rule engine may determine whether a potential safety hazard or quality problem exists at the construction site, such as a high temperature alarm, an equipment failure, etc., based on the environmental parameter data and the equipment status data.

Examples: the rules engine may formulate rules to raise a high temperature alert when the temperature exceeds a certain threshold. If the real-time temperature data exceeds the set threshold, the rule engine can identify potential safety hazards according to the rules and trigger early warning notification to construction manager, so that the construction manager can take measures in time to ensure the safety of the construction manager.

The above embodiment includes the following points:

1. the object is: and identifying whether potential safety hazards or quality problems exist according to the environmental parameters and the equipment state data of the construction site.

2. The method comprises the following steps: a rules engine is used. A rule engine is a specific system that can make inferences and decisions according to predefined rules. In the context of construction management, these rules may relate to decision criteria for construction safety and construction quality.

3. Examples: if the temperature exceeds a set threshold, the rules engine will raise a high temperature alert.

To more clearly understand how to use a rule engine, consider the following simplified example:

there are two rules for embodiments:

rule 1: if the temperature T exceeds 40 ℃, a high temperature alarm is issued.

Expressed as a logical formula:

IF T>40THEN ALERT:High Temperature

rule 2: if the pressure P of the device exceeds 100psi, an overpressure alarm is issued.

Expressed as a logical formula:

IF P>100THEN ALERT:Equipment Overpressure

now, the present example receives real-time data from a construction site: temperature t=42 ℃ and device pressure p=95 psi. Matching these data with the rules described above, the case may be:

according to rule 1, the temperature exceeds 40 ℃, so the system gives a "high temperature alarm".

According to rule 2, the pressure, although high, does not exceed 100psi, so an equipment overpressure alarm is not triggered.

In this way, the rules engine can make decisions based on predefined rules and data received in real time and take corresponding actions or notifications.

Judging whether the materials are in place or not according to the material supply data and the construction plan data, and generating purchasing suggestions: the rule engine can judge whether the materials are in place or not and whether the materials need to be supplemented according to the material supply data and the construction plan data, and generate corresponding purchasing suggestions.

Examples: the rules engine may formulate rules to determine whether specific supplies need to be replenished based on the construction plan data and the supply of supplies. If a certain material is needed to be used at a certain stage in the construction plan, but the real-time material supply data shows that the stock quantity is lower than a preset threshold, the rule engine can generate corresponding purchase suggestions and remind a purchasing department of timely purchasing so as to ensure timely supply of the material.

And (3) applying an intelligent algorithm and a rule engine to perform data analysis, decision making and optimization: the data analysis and intelligent decision module is used for realizing data analysis, decision and optimization in the construction process by applying an intelligent algorithm and a rule engine.

In this step, the module can analyze historical data and real-time data by using an intelligent algorithm, perform data mining, predictive analysis and the like, and make decisions and optimize control under the support of a rule engine. By applying the intelligent algorithm and the rule engine, the module can provide efficiency and quality optimization suggestions of the construction process and provide valuable decision support and early warning functions for construction managers.

Examples: the data analysis and intelligent decision module can apply a machine learning algorithm to analyze historical construction progress data and site environment data and predict future construction progress. By combining with the rule engine, the module can generate a corresponding adjustment plan according to the prediction result and a preset rule, such as manpower allocation in advance, construction sequence adjustment and the like, so as to improve construction efficiency and resource utilization rate.

The above embodiment includes the following points:

1. a combination of intelligent algorithms and rule engines;

intelligent algorithms typically involve machine learning or other complex computational methods aimed at extracting patterns and trends from the data. Such extraction typically involves statistics and predictions.

The rule engine is used for making a decision on a specific situation according to a preset rule. These rules may be hard coded or may be adapted to the actual situation.

By combining the two technologies, intelligent decision making can be realized, and the insight that an algorithm obtains from data is utilized, and preset rules are also followed.

2. Application example:

consider a specific scenario: a machine learning algorithm is used to predict the progress of the construction.

The embodiment scheme is provided with a simplified linear regression model for predicting construction progress:

Y＝β ₀ +β ₁ X

wherein Y is the progress of construction, X is environmental data (e.g., temperature, humidity, etc.), (beta) ₀ ) Sum (beta) ₁ ) Is a model parameter.

Through historical data, the scheme can obtain estimated values of parameters: (beta) ₀ =10) and (β ₁ ＝0.5)。

Now, if the scheme receives real-time environmental data (x=20), the scheme can predict the construction progress by using a model as follows:

Y＝10+0.5×20＝20

this means that the predicted construction progress is 20 given environmental data.

Next, the rules engine enters the scene. The embodiment scheme has a simple rule:

rules: if the predicted construction progress is less than 25, the manpower is increased.

Based on the above predictions, the construction progress is 20, which is below 25, so the rules engine will decide to increase manpower.

In this way, intelligent algorithms (machine learning) in combination with the rules engine can provide data-driven, real-time decision support for construction administrators.

Generating the decision model in this embodiment involves the steps of:

s1, data cleaning and pretreatment: in the step, the scheme cleans and preprocesses the acquired data so as to ensure the quality and accuracy of the data. This includes removing noise, filling in missing values, detecting outliers, and normalizing the data.

Examples: the case is assumed to collect temperature data in the construction process, and abnormal values of some data are found. In the data cleaning and preprocessing stage, the scheme can fill up missing data by using a statistical method (such as mean value or median substitution) and identify and process abnormal values by using an abnormal value detection algorithm (such as a 3 sigma method).

S2, feature selection and extraction:

in this step, the most representative and relevant features are selected from a large number of data. Suitable features may be selected by statistical analysis, correlation analysis, feature engineering, and the like.

Examples: for the feature selection and extraction of the construction site temperature data, the correlation between the construction site temperature data and the concrete strength can be analyzed, and the temperature features closely related to the concrete strength are selected as input features of modeling, such as average temperature, highest temperature, temperature change rate and the like.

S3, model selection and training:

according to decision making requirements, a proper machine learning algorithm or other modeling methods are selected, and training data is used for training the model. Common machine learning algorithms include decision trees, support vector machines, random forests, neural networks, and the like.

Examples: a Support Vector Machine (SVM) algorithm is selected to establish a relation model between the temperature of a construction site and the strength of concrete. The scheme uses the existing training data of temperature and concrete strength to carry out model training.

S4, model evaluation and tuning:

in this step, the test dataset is used to evaluate the accuracy, precision and generalization ability of the model. If the model has problems or does not meet the decision requirement, tuning and optimization are needed in the scheme, including adjusting model parameters, adding or subtracting features and the like.

Examples: the scheme evaluates the performance of the support vector machine model by dividing the training data set into a training set and a verification set and calculating indexes such as accuracy, precision, recall rate and the like. If the model performs poorly on the validation set, an attempt may be made to adjust the hyper-parameters of the model, such as selecting a different kernel function or adjusting regularization parameters.

S5, generating and applying a decision model:

through model training and tuning, the scheme obtains a decision model with higher prediction capability and accuracy. The model makes intelligent decisions according to the input new data, generates a corresponding decision model according to the prediction result and decision rules of the model, and takes corresponding actions or provides decision suggestions.

Examples: based on the trained support vector machine model, the method can predict according to the temperature data of the current construction site and generate a corresponding decision model, such as whether to increase cooling measures of concrete or whether to adjust pouring time.

By way of example above, the present case can see the steps of generating the decision model and the workings of each step. The scheme can achieve the aim of generating a decision model with higher accuracy and prediction capability through data cleaning and preprocessing, feature selection and extraction, model selection and training, model evaluation and tuning.

The information of high value in the implementation includes: providing support and guidance for key decisions in the construction process; the information can help construction managers to make accurate and targeted decisions, so that the construction efficiency is improved, the cost is reduced, and the construction quality is improved; the method comprises the following steps:

1. Exploring and visually analyzing the acquired data:

in the step, the scheme can visually display the data by using a chart, a data panel and other modes so as to intuitively observe the distribution, trend and abnormal condition of the data and acquire key information with potential influence on construction optimization.

Examples: according to the scheme, a scatter diagram and a box diagram among temperature, humidity and concrete strength can be drawn, the influence of the temperature and the humidity on the concrete strength can be found by observing the distribution and the abnormal value of data, and the key range of the temperature and the humidity is primarily judged, so that the construction quality is potentially influenced.

2. And (3) discovering hidden modes and rules by applying a data mining technology:

after exploring the data, the present case may apply data mining techniques such as cluster analysis, association rule mining, and classification algorithms to discover hidden patterns and rules in the data and extract potentially high value information.

Examples: by applying cluster analysis, the scheme can divide the data of the construction site into different groups, and find out the temperature and humidity modes under different construction working conditions, thereby determining corresponding construction strategies and control measures.

3. Correlation analysis, namely, finding out the correlation between data:

in the step, the scheme can evaluate the correlation degree among different features by using statistical analysis and a machine learning algorithm to find out factors with strong correlation to construction optimization. This helps identify key influencing factors and provides information supporting decision making.

Examples: through correlation analysis, the relation between the temperature and the concrete strength can be evaluated, and the threshold range of the temperature is determined, so that the concrete strength is ensured to be within a reasonable range.

4. Establishing a prediction model and an optimization model:

by utilizing historical data and real-time data, the method can be used for predicting and optimizing indexes in the construction process by using a machine learning model, regression analysis, time sequence analysis, an optimization algorithm and the like. In this way, potential problems can be identified in advance, and corresponding solutions can be formulated.

Examples: by establishing a regression model of temperature and concrete strength, the scheme can predict future concrete strength according to real-time temperature data. If the predicted result shows that the concrete strength is lower than the target value, corresponding measures such as increasing the cooling measure or delaying the pouring time can be taken.

5. Applying high value information to the decision process:

converting the result of data analysis into an actual operation guide and decision support, and helping a construction manager to make an accurate and targeted decision; and according to the predicted construction progress and resource requirements, adjusting the work plan and the resource allocation to optimize the construction efficiency and quality.

Examples: according to the predicted construction progress and resource requirements, if the prediction result shows that a certain working procedure may be delayed, a construction manager can adjust a work plan in time, allocate additional resources and ensure the smooth progress of the construction progress. By way of example above, the present case can see what applies high value information to each step in the construction optimization process. The method comprises the steps of exploring, data mining, correlation analysis, prediction model establishment, optimization model establishment and the like.

In the construction plan and resource management module in the embodiment, the following methods are adopted to adjust the progress and sequence of the construction plan and to configure material and personnel resources:

s1, real-time plan adjustment:

in this step, the construction plan is dynamically adjusted based on feedback of real-time data. By monitoring the construction progress and the resource use condition index and comparing and analyzing with the decision model, whether the original plan needs to be adjusted or not is judged.

Examples: it is assumed that during the construction process, real-time data feedback shows that the progress of a certain task lags behind the plan, affecting the achievement of the overall construction period. According to the support of the decision model, a construction manager can rearrange the priority of the task according to the analysis result of the real-time data and mobilize human resources so as to achieve the acceleration completion of the task.

S2, resource matching and optimizing:

and matching and optimizing the construction resources by utilizing the decision model and the real-time data. And dynamically evaluating the use efficiency and the utilization rate of each resource according to the real-time requirements and the resource availability. And determining an optimal resource allocation scheme including manpower, equipment and materials through model analysis so as to reduce resource waste and save cost, and timely adjusting resource allocation to cope with emergency and change requirements.

Examples: through analysis of historical data and real-time data, the decision model finds that the utilization rate of some equipment in the construction project is lower, and the demand of other equipment is higher. According to the proposal of the model, a construction manager can adjust the use plan of the equipment and allocate the idle equipment to a place where the equipment is needed so as to improve the resource utilization rate and the construction efficiency.

S3, risk management and decision support:

and performing risk management and decision support based on the decision model and the real-time data. By analyzing the real-time data and the historical data, the potential risks and challenges are predicted, and corresponding precautionary measures are taken in time. Based on the decision model, a coping scheme and a decision strategy are formulated, so that a construction manager is helped to make a decision with rationality and feasibility, risks are reduced, and smooth progress of a construction process is ensured.

Examples: by analyzing the construction equipment state data monitored in real time, the decision model discovers that the failure rate of certain equipment is gradually increased, and the construction period can be delayed. Based on the prediction and decision support of the model, a construction manager can arrange maintenance and repair of equipment in advance, so that risks brought by equipment faults are reduced.

S4, progress monitoring and adjustment:

and monitoring and adjusting the construction progress by utilizing the decision model and the real-time data. And evaluating and predicting the construction progress through real-time data acquisition and analysis. If the situation of lagging or leading occurs, corresponding measures can be taken, including adjusting the priority of tasks, allocating personnel, adjusting the sequence of working procedures and the like, so as to keep the construction progress stable and reasonable.

Examples: by means of the construction completion rate data and the actual construction period data collected in real time, the decision model can predict whether a construction project can be completed as expected. If the model predicts that the construction period has high risk, the construction manager can adjust the priority of the task according to the proposal of the model and dynamically allocate resources so as to ensure the stability of the construction progress and the timely completion of the task.

S5, continuous improvement and knowledge accumulation:

and carrying out continuous improvement and knowledge accumulation according to continuous optimization of the decision model and feedback of real-time data. By analyzing the real-time data, the bottleneck and improvement opportunity in the construction process are found, and feedback and optimization are timely carried out. Experience and training accumulation can also be used to update and refine decision models to improve the accuracy and effectiveness of optimization management.

Examples: by analyzing the historical data and the real-time data, the construction management team finds that the efficiency of a certain construction process is lower. Through experience summarization and training accumulation, they cooperate with decision models to propose a series of optimization suggestions, such as adjusting the process flow, introducing new techniques, to improve the efficiency of the construction process.

S1, monitoring and analyzing real-time data:

the construction progress, the resource utilization condition and the risk condition information are known through monitoring and analyzing the real-time data; the sensor and monitoring equipment technology can be utilized to collect various index data in the construction process and analyze the index data by combining with a decision model; thus, the construction plan can be evaluated, whether the progress and the sequence need to be adjusted or not is determined, and whether resources need to be reconfigured or not is judged;

s2, priority and urgency assessment:

according to the real-time data analysis and the support of the decision model, the priorities and urgency of different tasks and activities are evaluated; determining which tasks need to be processed preferentially and which resources need to be configured preferentially by comprehensively considering construction progress, resource availability, task dependency relationship and risk degree factors; therefore, limited resources can be effectively utilized, and smooth execution of a construction plan is ensured;

s3, task adjustment and procedure optimization:

according to the analysis of the real-time data, the construction task is adjusted and optimized by combining with priority evaluation; this includes reordering of tasks, adjusting time windows of tasks, dividing and adjusting procedures; through reasonable task adjustment and procedure optimization, the flexibility and the high efficiency of a construction plan can be ensured, and the method is suitable for actual construction conditions;

S4, resource allocation and scheduling:

optimizing distribution and scheduling of materials and personnel resources based on real-time data and support of a decision model; according to actual needs and resource availability, reasonably arranging and allocating material supply, equipment and worker resources; by matching the requirements and supply of resources, the consistency and the high efficiency of construction activities are ensured;

s5, cooperative cooperation and communication:

maintaining cooperative cooperation and communication in the process of adjusting construction plans and resource allocation; each team and department need to closely cooperate, share real-time data and information, and jointly decide and coordinate resource allocation; this can ensure continuity and consistency of the construction plan, reducing conflicts and vulnerabilities.

In the embodiment step, the process of establishing the risk management model and the safety monitoring system comprises the following steps:

s1, risk management model:

a. risk identification: by comprehensively identifying risks of construction projects, potential risk factors which may exist can be determined according to historical data, expert experience, field investigation and other methods. For example, for high-rise building construction, risk factors that may be present include engineering height, weather conditions, material transport, and the like.

b. Risk assessment: the identified risk is evaluated, including in terms of likelihood, severity, and scope of impact of the risk. Risks are classified and prioritized by quantitative and qualitative methods. For example, tasks with high construction heights at the construction site, there is a risk of falling, and the corresponding likelihood and severity are high.

c. Risk policies and control measures: and based on the result of the risk assessment, corresponding risk strategies and control measures are formulated. For example, in the event of a fall risk, measures can be taken, such as providing a safety net, using safety belts, providing a guard rail, etc.

d. Risk monitoring and improvement: and establishing a risk monitoring mechanism to monitor the implementation condition of the risk control measures. By monitoring the data and feedback, potential risks are identified, and existing risk management models are improved and optimized. For example, by real-time observation and data acquisition of a monitoring camera at a construction site, a worker can be found to work at a high place without wearing a safety belt, and an alarm can be sent out and measures can be taken in time.

S2, a safety monitoring system:

a. design requirements: and determining the functional requirement and performance index of the system according to the safety monitoring target and requirement. For example, it is necessary to monitor potential safety hazards in a construction site, detect abnormal behaviors, and realize a real-time early warning function.

b. And (3) architecture design: based on the requirements, the overall architecture of the security monitoring system is designed. The required hardware equipment, sensors and network architecture are determined, and data acquisition, transmission and processing flows are designed. For example, real-time data acquisition is performed using cameras and sensor devices and transmitted to a back-end processing system over a wireless network.

c. Data acquisition and processing: and selecting a proper sensor and camera equipment, and collecting images, videos and sensor data of a construction site in real time. And establishing a proper data processing flow, including the steps of data cleaning, feature extraction, anomaly detection and the like. For example, computer vision techniques are used to image-identify real-time video, identifying potential safety hazards at the job site.

d. Intelligent analysis and early warning: and intelligent analysis and processing are carried out on the real-time data by utilizing machine learning and artificial intelligence technology. Through image recognition, object detection and behavior analysis algorithms, potential safety hazards and abnormal conditions are recognized, and real-time early warning and alarm functions are realized. For example, the behavior that the safety belt is not worn when working at high altitude is detected by an image recognition algorithm, and an alarm is given.

e. Visualization and reporting: the monitoring and analysis results are presented to construction managers and related personnel through data visualization and report generation. Visual interfaces and reports are provided to assist in understanding and taking appropriate action. For example, information such as the location, time, type, etc. of potential safety hazards and abnormal behaviors is presented to the construction manager in a chart or report form.

f. Continuous improvement and update: the function and performance of the safety monitoring system is continuously optimized through continuous monitoring, analysis and improvement. According to actual demands and technical development, the system is updated and upgraded to adapt to the continuously changing safety demands. For example, according to historical data and real-time feedback, an algorithm model is improved, and detection accuracy of potential safety hazards and abnormal behaviors is improved.

From the above examples we can see the process of building a risk management model and a security monitoring system and the content of each step. Through the steps of risk identification, risk assessment, risk strategy and control measures, risk monitoring, improvement and the like, a perfect risk management model can be established. Through the steps of design requirement, architecture design, data acquisition and processing, intelligent analysis and early warning, visualization and reporting, continuous improvement and updating and the like of the safety monitoring system, the high-efficiency safety monitoring system can be realized. While the introduction of actual data can help verify the feasibility of each step and ensure that the built model and system can be effectively applied in risk management and security monitoring at the construction site.

The foregoing has shown and described the basic principles, principal features and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and that the above embodiments and descriptions are merely illustrative of the principles of the present invention, and various changes and modifications may be made without departing from the spirit and scope of the invention, which is defined in the appended claims. The scope of the invention is defined by the appended claims and equivalents thereof.

Claims

1. Building construction optimizing system based on big data and cloud computing, characterized by comprising:

the data acquisition and storage module acquires various data of a construction site in real time through a sensor and monitoring equipment, and stores and manages the various data in real time through a cloud computing platform;

2. The building construction optimization system based on big data and cloud computing as claimed in claim 1, wherein:

wherein, the data acquisition and storage module includes the collection: environmental parameter data, equipment status data, and supply data; the data analysis and intelligent decision module comprises an intelligent algorithm and a rule engine;

3. The building construction optimization system based on big data and cloud computing as claimed in claim 1 or 2, wherein:

the system also comprises a user interface module, a control module and a control module, wherein the user interface module is used for providing an operation interface so that a user can check related construction data and decision results; the system further comprises a communication module for exchanging and communicating data with other devices or systems;

4. The building construction optimization system based on big data and cloud computing as claimed in claim 1 or 2, wherein the data acquisition and storage module acquires environmental parameter data, equipment status data and material supply data of a construction site in real time through a sensor and a monitoring device, and the specific acquisition mode comprises the following steps:

A. and (3) environmental parameter data acquisition:

B. and (3) collecting equipment state data:

C. And (3) material supply data acquisition:

5. The building construction optimization system based on big data and cloud computing as claimed in claim 1 or 2, wherein the intelligent algorithm and rule engine of the data analysis and intelligent decision module comprises the following specific core algorithm processes:

6. The building construction optimization system based on big data and cloud computing as claimed in claim 1, wherein said generating a decision model involves the steps of:

s2, feature selection and extraction:

s3, model selection and training:

s4, model evaluation and tuning:

S5, generating and applying a decision model:

the decision model with higher prediction capability and accuracy is obtained through model training and tuning; the model makes intelligent decisions according to the input new data; generating a corresponding decision model according to the prediction result and the decision rule of the model, and taking corresponding action or suggestion;

the high value information includes: providing support and guidance for key decisions in the construction process;

7. The building construction optimization system based on big data and cloud computing as claimed in claim 6, wherein the high value extraction process comprises:

8. The building construction optimization system based on big data and cloud computing as claimed in claim 1, wherein the decision model and the real-time data are used for optimizing and managing the construction plan and the resources by the following methods:

s1, real-time plan adjustment:

S2, resource matching and optimizing:

s3, risk management and decision support:

s4, progress monitoring and adjustment:

S5, continuous improvement and knowledge accumulation:

9. The building construction optimization system based on big data and cloud computing as claimed in claim 1, wherein in the construction plan and resource management module, the following methods are adopted to adjust the progress and sequence of the construction plan and to configure the material and personnel resources:

s1, monitoring and analyzing real-time data:

s2, priority and urgency assessment:

S3, task adjustment and procedure optimization:

s4, resource allocation and scheduling:

s5, cooperative cooperation and communication:

10. The building construction optimization system based on big data and cloud computing as claimed in claim 1, wherein the process of building the risk management model and the security monitoring system comprises the following steps:

s1, risk management model:

s2, a safety monitoring system: