Intelligent construction full-process digital management system based on cloud collaboration

Abstract

The invention discloses an intelligent construction full-process digital management system based on cloud collaboration, which optimizes intelligent construction full-process digital management from a single point to global collaboration by constructing integrated intelligent construction full-process closed-loop management of'intelligent pivot ', 'intelligent moment', 'intelligent joint ', 'intelligent game' and'intelligent jun '. According to the method, digital twinborn integration, cloud resource intelligentization, robot cluster collaboration, carbon emission management dynamics and Beidou-AI paying-off are taken as technical key points, BIM + Internet of Things + AI + robot cross-domain deep fusion is carried out, all method steps are linked through digital twinborn, and a full-process digital closed-loop management system of design, construction and carbon monitoring is formed.

Description

Technical Field

[0001] The present invention relates to the field of intelligent construction technology, and in particular to a cloud-based collaborative intelligent construction full-process digital management system. Background Art

[0002] Smart construction refers to the use of modern information technology, data analysis, the Internet of Things, artificial intelligence and other technologies to digitally manage and make intelligent decisions throughout the life cycle of a construction project during the construction process. It uses data to design and build construction schedules, costs, and green energy conservation, and continuously optimizes the construction process and management of buildings using data. Current construction management faces the following problems:

[0003] 1. Data silos: BIM models, equipment status, and carbon emission data are scattered and lack a unified collaborative platform.

[0004] 2. Waste of resources: Traditional construction relies on manual experience, and carbon emissions and material consumption are difficult to accurately control.

[0005] 3. Inefficiency: Robots, IoT devices, and cloud systems are not linked well, making it impossible to dynamically allocate tasks.

[0006] 4. Insufficient precision: The error rate of processes such as laying out and lifting is high and relies on manual operation.

[0007] In summary, existing technologies, such as a single BIM management platform or an independent robot control system, etc., only provide targeted solutions and optimizations to the above-mentioned problem, and cannot cover the collaborative needs of the entire design-construction-monitoring chain in the entire intelligent construction process. Summary of the Invention

[0008] In order to overcome the shortcomings of the existing technology, the technical problem to be solved by the present invention is to propose a full-process digital management system for intelligent construction based on cloud collaboration, to realize the full-process closed-loop management of design → construction → monitoring during the intelligent construction process, and to comprehensively integrate data integration, precise construction, dynamic optimization and green emission reduction.

[0009] To achieve this object, the present invention adopts the following technical solutions:

[0010] The cloud-based collaborative intelligent construction full-process digital management system provided by the present invention includes the following modules:

[0011] The Zhihu module includes a construction phase digital twin built based on BIM technology. The digital twin integrates construction progress, construction cost, and carbon emission data, and embeds an ergonomic analysis algorithm in the digital twin to evaluate the feasibility of construction plans in real time.

[0012] The Zhiju module uses visual recognition and Beidou coordinates to fully automatically lay out wall lines and column positions using an AI line drawing robot. The digital twin converts the geodetic coordinates obtained from Beidou into building coordinates in real time, enabling real-time dynamic adjustment of the AI ​​line drawing robot's path.

[0013] The intelligent integration module conducts modular standard design of the construction equipment system and stores the parameterized construction equipment system in a cloud resource library. The cloud supports the call of preset configurations and bolt tightening measurement devices according to the residential, commercial and bridge business formats, and automatically generates the construction equipment requirement list based on the calculation progress of the digital twin;

[0014] The Zhiyi module combines inspection robots, rebar tying robots, and intelligent material transport vehicles into a robot cluster. An IoT communication framework is built within the digital twin to support real-time data exchange among the robot clusters. Tasks are allocated in the cloud, enabling obstacle avoidance and collaboration among multiple devices during operations under the control of the digital twin.

[0015] The Zhijun module is used to deploy IoT sensors to collect carbon emission data in real time. Cloud-based algorithms generate dynamic carbon footprint reports and work with digital twins to issue early warnings for nodes exceeding the standard.

[0016] The beneficial effects of the present invention are:

[0017] This invention transforms the digital management of the entire intelligent construction process from single-point optimization to global coordination. Specifically, by integrating digital twins, intelligent cloud resources, collaborative robot clusters, dynamic carbon emission management, and Beidou-AI line laying as technical priorities, it deeply integrates BIM, IoT, AI, and robots across domains, and links various method steps with digital twins to form a digital closed-loop management system for the entire process of design, construction, and carbon monitoring. Specifically, it has the following characteristics:

[0018] 1. Full-process closed-loop management: Covering the entire chain from design to construction to monitoring, the construction cycle is shortened by 18% and manual intervention is reduced by 35%;

[0019] 2. Multi-format adaptation: Through the cloud resource library, it supports rapid adaptation of equipment in multiple scenarios such as residential, commercial, and infrastructure, reducing customization costs by 40%;

[0020] 3. High-precision collaboration: The error rate of robot cluster task allocation is ≤0.1%, and the Beidou-AI line laying accuracy is improved to 1mm;

[0021] 4. Green and intelligent: Carbon emissions are reduced by 12% and equipment turnover rate is increased by 60%. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1Schematic diagram of each module of the cloud-based collaborative intelligent construction full-process digital management system in a specific embodiment of the present invention DETAILED DESCRIPTION

[0023] The technical solution of the present invention will be further described below with reference to the accompanying drawings and through specific implementation methods.

[0024] To address the complex issues of construction information data silos, insufficient construction accuracy and inefficiency, and uncontrolled resource waste in traditional construction management, this invention provides a cloud-based collaborative, full-process digital management system for intelligent construction. This system builds an integrated, closed-loop management system for the entire intelligent construction process, encompassing "Zhishu," "Zhiju," "Zhihe," "Zhiyi," and "Zhijun," and includes the following modules:

[0025] The Zhihu module includes a construction phase digital twin built based on BIM technology. The digital twin integrates construction progress, construction cost, and carbon emission data, and embeds an ergonomic analysis algorithm in the digital twin to evaluate the feasibility of construction plans in real time.

[0026] This module converts the BIM model in the construction process into a digital model and digital assets, integrating multi-dimensional data such as construction progress, construction costs, and carbon emissions. Specifically, the digital twin must go through the following steps when building:

[0027] S01: Collect and standardize multi-source heterogeneous data, link the construction schedule with BIM model components based on the IFC standard; establish a unified cost coding system for construction costs, bind it to the BIM component ID, support dynamic cost accounting, and dynamically link various cost units (such as material unit price, labor rate, equipment rental cost, etc.); use life cycle assessment methods for carbon emission data, define material carbon emission coefficients and carbon emission factor libraries (such as during concrete production and transportation), and link them with BIM component attributes;

[0028] S02: Establish a digital twin foundation for multi-dimensional data fusion. Based on the traditional BIM model, embed schedule time, construction cost, and carbon emission attributes. Synchronize field data in real time through the API interface to drive dynamic adjustment of model parameters. When linking data, it is divided into schedule-cost association, schedule-carbon emission association, and cost-carbon emission association. In the schedule-cost association, define the logical relationship between processes and automatically calculate the resource waste cost caused by schedule deviation. In the schedule-carbon emission association, simulate the impact of different construction period compression strategies on carbon emissions. In the cost-carbon emission association, build an economic and environmental dual-objective optimization model to analyze the cost increment of low-carbon material alternatives. In this way, cloud-based algorithms are used to analyze carbon emission intensity and automatically recommend process adjustments.

[0029] Preferably, one of the real-time evaluation methods for the construction plan is to use the construction progress as the time axis, and the feasibility evaluation formula of the real-time construction plan can be further expressed as:

[0030] R i =α·T i +β·C i +γ·E i

[0031] R i is the feasibility evaluation parameter when the construction progress is i; α is the evaluation coefficient of the construction progress, T i is the estimated total construction period when the construction progress is i; β is the evaluation coefficient of construction cost, C i is the estimated total cost when the construction progress is i; γ is the carbon emission assessment coefficient, E i is the estimated total carbon emissions at construction progress i;

[0032] In this way, the real-time construction plan can be evaluated according to the above expression, that is, the α, β, and γ coefficients are automatically adjusted according to the project stage and node, so as to perform real-time evaluation of the construction plan. If the total construction period needs to be compressed, the evaluation coefficient α of the construction progress needs to be reduced. This is to make the feasibility evaluation parameter R i To achieve the implementation standard values, it is necessary to increase the assessment coefficient of construction costs and carbon emissions, or to increase construction costs and carbon emissions.

[0033] It should be further explained that, on the basis of the above-mentioned evaluation method, reference factors such as construction location, construction method, quality and efficiency, and material loss can also be added for comprehensive consideration, which will not be elaborated here.

[0034] S03: Embedded ergonomic analysis and dynamic optimization algorithms. Specifically, the ergonomic analysis algorithm embeds construction specifications (such as safe spacing and process intervals) and resource constraints (such as crane capacity and number of workers) to automatically verify plan compliance. A prediction model is trained based on historical project data to predict schedule risks and carbon emission peaks. Specifically, the dynamic optimization algorithm uses reinforcement learning to respond to emergencies, generating alternative processes that balance schedule, cost, and carbon emissions, and providing a multi-objective trade-off between different construction plans.

[0035] S04: Result visualization collaboration and construction decision support, creating a visualization platform that supports the overlay display of progress Gantt charts, cost curves, and carbon emission heat maps. It allows operators to drag and drop to adjust the construction sequence and view the adjusted cost and carbon emission changes in real time, enabling "what-if analysis" and sharing digital twin data to reduce information gaps.

[0036] In summary, through the "BIM + multidimensional data + embedded algorithms + visual collaboration" architecture, the digital twin not only achieves a deep integration of progress, cost, and carbon emissions, but also upgrades traditional construction management from "experience-driven" to "data-algorithm dual-driven" through dynamic optimization and interactive decision-making mechanisms. It also realizes closed-loop management of the entire process: covering the entire chain of design → construction → monitoring, that is, integrating construction progress, cost, and carbon emission data on the same digital twin platform, achieving coordinated optimization of the three goals of "quality-cost-low carbon". In actual process, the construction period is shortened by 18% and manual intervention is reduced by 35%.

[0037] The Zhiju module uses visual recognition and Beidou coordinates to fully automatically lay out wall lines and column positions using an AI line drawing robot. The digital twin converts the geodetic coordinates obtained from Beidou into building coordinates in real time, enabling real-time dynamic adjustment of the AI ​​line drawing robot's path.

[0038] In this way, geodetic coordinate data can be obtained in real time through Beidou, and the digital twin can be used to convert the geodetic coordinates obtained from Beidou into BIM building model coordinates in real time, eliminating the coordinate offset caused by cumulative construction errors, and improving the robot's layout accuracy to the millimeter level, making the positioning accuracy ≤1mm.

[0039] The intelligent integration module conducts modular standard design of the construction equipment system and stores the parameterized construction equipment system in a cloud resource library. The cloud supports calling preset configurations according to residential, commercial, and bridge business formats, and automatically generates the construction equipment requirement list based on the calculation progress of the digital twin;

[0040] The construction equipment system mentioned in this step mainly includes seven major systems: material basket, elevator operating platform, flap operating platform, edge protection device, column opening blocking hanging formwork, truss installation operating platform, and bolt tightening measuring device. In this way, these structures can be quickly adapted to multiple scenarios such as residential, commercial, and infrastructure through the cloud resource library, that is, the configuration combination is based on the needs of different scenarios, with a high fault tolerance rate, reducing customization costs by 40%, and increasing equipment turnover rate by 60%. That is, the digital twin is used to automatically generate an equipment requirement list (such as the number of baskets, installation coordinates) according to the construction progress, and send it to the site through Beidou positioning; and the above equipment can be circulated across projects. At the same time, historical usage data (such as wear rate) is included in cloud analysis to optimize maintenance cycles and scheduling paths.

[0041] The Zhiyi module combines inspection robots, rebar tying robots, and intelligent material transport vehicles into a robot cluster. An IoT communication framework is built within the digital twin to support real-time data exchange among the robot clusters. Tasks are allocated in the cloud, enabling obstacle avoidance and collaboration among multiple devices during operations under the control of the digital twin.

[0042] When the robot cluster is performing task assignments, the cloud dynamically issues instructions based on the construction progress and determines task priority. When a robot fails, the cloud reallocates tasks to backup equipment and updates the construction status through the digital twin. Specifically, the robot cluster is equipped with visual cameras and multi-task sensors, and then builds a low-latency transmission IoT communication framework to ensure end-to-end delay ≤20ms and a robot cluster task assignment error rate ≤0.1%. In practical applications, the robot cluster and the cloud can form a collaborative response mechanism and form a closed-loop control.

[0043] Through the Zhihe module and Zhiyi module, a closed-loop workflow of "modular resource library → digital twin → robot cluster execution" is formed, realizing the transformation of resource allocation from "experience-driven" to "algorithm-driven".

[0044] The Zhijun module deploys IoT sensors to collect carbon emissions data in real time. Cloud-based algorithms generate dynamic carbon footprint reports and work with digital twins to alert nodes exceeding standards.

[0045] In this way, carbon emission data (such as concrete pouring energy consumption, transportation fuel consumption, etc.) are collected in real time through the sensors carried by the inspection robot and transmitted to the cloud for processing in real time, a dynamic carbon footprint report is generated and analyzed, and then the cloud transmits the data information to the digital twin for early warning. Specifically, the cloud maps the carbon emission data to the digital twin in real time to ensure that the components in the BIM model (such as floor slabs and walls) are associated with carbon emission attributes, and supports clicking on components to view carbon emission details. The digital twin can trigger an early warning and automatically generate low-carbon alternatives, including adjusting the construction sequence or reallocating resources to form a carbon emission-progress-cost collaborative optimization. In summary, through the deep integration of "Internet of Things + dynamic carbon footprint report + digital twin feedback control", carbon emission management has been realized from passive monitoring to active intervention, and real-time carbon emission data is dynamically bound to the BIM spatial model and progress plan, making construction management more synergistic and effectively reducing carbon emissions by 12%.

[0046] The present invention is described through preferred embodiments. Those skilled in the art will appreciate that various modifications or equivalent substitutions may be made to these features and embodiments without departing from the spirit and scope of the present invention. The present invention is not limited to the specific embodiments disclosed herein; other embodiments falling within the scope of the claims of this application are intended to be protected by the present invention.

Claims

1. A cloud-based collaborative intelligent construction full-process digital management system, characterized by: include: The Zhihu module includes a construction phase digital twin built based on BIM technology. The digital twin integrates construction progress, construction cost, and carbon emission data, and embeds an ergonomic analysis algorithm in the digital twin to evaluate the feasibility of construction plans in real time. The Zhiju module uses visual recognition and Beidou coordinates to fully automatically lay out wall lines and column positions using an AI line drawing robot. The digital twin converts the geodetic coordinates obtained from Beidou into building coordinates in real time, enabling real-time dynamic adjustment of the AI ​​line drawing robot's path. The intelligent integration module conducts modular standard design of the construction equipment system and stores the parameterized construction equipment system in a cloud resource library. The cloud supports calling preset configurations according to residential, commercial, and bridge business formats, and automatically generates the construction equipment requirement list based on the calculation progress of the digital twin; The Zhiyi module combines inspection robots, rebar tying robots, and intelligent material transport vehicles into a robot cluster. An IoT communication framework is built within the digital twin to support real-time data exchange among the robot clusters. Tasks are allocated in the cloud, enabling obstacle avoidance and collaboration among multiple devices during operations under the control of the digital twin. The Zhijun module is used to deploy IoT sensors to collect carbon emission data in real time. Cloud-based algorithms generate dynamic carbon footprint reports and work with digital twins to issue early warnings for nodes exceeding the standard.

2. The cloud-based collaborative intelligent construction full-process digital management system according to claim 1 is characterized in that: The construction of the digital twin includes: collecting and standardizing multi-source heterogeneous data, establishing a digital twin base for multi-dimensional data fusion, embedded work efficiency analysis and dynamic optimization algorithms, and result visualization collaboration and construction decision support.

3. The cloud-based collaborative intelligent construction full-process digital management system according to claim 1 is characterized in that: In the intelligent module, the construction equipment is a scheduling turnover platform, which includes a material hanging basket, an elevator operating platform, a flap operating platform, an edge protection device, a column opening blocking hanging formwork, a truss installation operating platform, and a bolt tightening measuring device.

4. The cloud-based collaborative intelligent construction full-process digital management system according to claim 1 is characterized in that: In step S30, digital twins are used to achieve cross-project equipment turnover, and historical usage data is incorporated into cloud analysis to optimize maintenance cycles and scheduling paths.

5. The cloud-based collaborative intelligent construction full-process digital management system according to claim 4 is characterized in that: In the Zhiyi module, when the robot cluster is assigning tasks, the cloud dynamically issues instructions based on the construction progress and determines the task priority; when a robot fails, the cloud reallocates tasks to backup equipment and updates the construction status through the digital twin.

6. The cloud-based collaborative intelligent construction full-process digital management system according to claim 1 is characterized in that: In the Zhiyi module, the end-to-end delay of the Internet of Things communication framework is ≤20ms, and the error rate of robot cluster task allocation is ≤0.1%.

7. The cloud-based collaborative intelligent construction full-process digital management system according to claim 1 is characterized in that: In the Zhijun module, the cloud maps carbon emission data to the digital twin in real time, so that the components in the BIM model are associated with carbon emission attributes and support clicking on components to view carbon emission details.

8. The cloud-based collaborative intelligent construction full-process digital management system according to claim 7 is characterized in that: In step S40, after receiving the cloud report triggering the early warning, the digital twin automatically generates a low-carbon alternative plan, including adjusting the construction sequence or reallocating resources.

Images