Project progress and quality collaborative management method based on BIM visualization model

By adopting the collaborative management method of BIM visualization model in engineering projects, the problems of timeliness and poor results of construction progress and quality control are solved, and more efficient and reliable progress and quality management are achieved.

CN118536949BActive Publication Date: 2024-11-19NANTONG INST OF TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410969760.7
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-07-19
Publication Date
2024-11-19
Estimated Expiration
2044-07-19

AI Technical Summary

Technical Problem

In modern engineering projects, the timeliness of construction progress control and poor construction quality control results have led to major challenges in project management.

Method used

The project progress and quality collaborative management method based on the BIM visual model is adopted. By dismantling the construction plan, the construction BIM model is built, and the progress and quality monitoring data are combined to predict and detect, and the progress and quality reports are generated to achieve coordinated management of progress and quality.

Benefits of technology

It improves the timeliness and accuracy of construction progress control, enhances the comprehensiveness and reliability of construction quality inspection, ensures that the project is carried out as planned and improves the quality control effect.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118536949B_ABST
    Figure CN118536949B_ABST
Patent Text Reader

Abstract

The present invention discloses a project progress and quality collaborative management method based on a BIM visualization model, which relates to a field related to project management. The method includes: disassembling a project construction plan to obtain H node construction plans; extracting the h-th node construction plan corresponding to the h-th construction node; interacting with a construction monitoring system to obtain the h-th node construction monitoring data stream; constructing an h-th node construction BIM model; activating a project progress expected adaptation analytical function to predict the project progress expected adaptation, and generating an h-th node progress expected adaptation index; activating a project construction quality combing channel to detect the project construction quality, and generating an h-th node project construction quality inspection report; and performing project construction management according to the h-th node progress expected adaptation index and the h-th node project construction quality inspection report. The method solves the technical problems of low timeliness of project construction progress control and poor project construction quality control effect in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to fields related to project management, and in particular to a method for collaborative management of project progress and quality based on a BIM visualization model. Background Art

[0002] In modern engineering project management, construction progress control and construction quality control are two crucial links. With the continuous expansion of the scale of construction projects and the increase in the complexity of engineering projects, how to effectively control the construction progress and ensure the construction quality has become a major challenge in project management. At present, there are technical problems in the relevant technologies such as low timeliness of project construction progress control and poor effect of project construction quality control. Summary of the invention

[0003] This application solves the technical problems of low timeliness of project construction progress control and poor effect of project construction quality control in the prior art by providing a project progress and quality collaborative management method based on BIM visualization model. It achieves the technical effect of improving the timeliness and accuracy of project construction progress control, improving the effect of project construction quality control, and improving the comprehensiveness and reliability of project construction quality detection.

[0004] The present application provides a project progress and quality collaborative management method based on a BIM visualization model, the method comprising: disassembling a project construction plan to obtain H node construction plans corresponding to H construction nodes, wherein H is a positive integer greater than 1; extracting an h-th node construction plan corresponding to an h-th construction node according to the H node construction plans, wherein h is a positive integer and h belongs to H; interacting with a construction monitoring system to obtain an h-th node construction monitoring data stream corresponding to the h-th construction node; connecting a BIM system, and constructing an h-th node construction BIM model in combination with the h-th node construction monitoring data stream; activating a project progress expected adaptation analytical function, and performing a project progress expected adaptation prediction in combination with the h-th node construction plan and the h-th node construction BIM model to generate an h-th node progress expected adaptation index; activating a project construction quality combing channel, and performing a project construction quality inspection in combination with the h-th node construction plan and the h-th node construction BIM model to generate an h-th node project construction quality inspection report; and performing project construction management according to the h-th node progress expected adaptation index and the h-node project construction quality inspection report.

[0005] Preferably, the project schedule expected adaptation analytical function is activated, and the project schedule expected adaptation prediction is performed in combination with the h-th node construction plan and the h-th node construction BIM model to generate the h-th node schedule expected adaptation index, including: connecting the BIM system, building the h-th node benchmark BIM model in combination with the h-th node construction plan; comparing the h-th node benchmark BIM model and the h-th node construction BIM model to generate the h-th node construction auxiliary BIM model; predicting the construction time according to the h-th node construction auxiliary BIM model to obtain the h-th node construction auxiliary time zone; extracting the h-th node construction time limit according to the h-th node construction plan; evaluating the node construction time margin based on the h-th node construction time limit and the h-th node construction auxiliary time zone to generate the h-th node construction time margin coefficient; inputting the h-th node construction time margin coefficient into the project schedule expected adaptation analytical function, and outputting the h-th node schedule expected adaptation index.

[0006] Preferably, a node construction time margin evaluation is performed based on the h-th node construction time limit and the h-th node construction auxiliary time zone to generate an h-th node construction time margin coefficient, including: obtaining the h-th node construction monitoring time corresponding to the h-th node construction monitoring data stream; calculating the h-th node construction tolerance time zone according to the h-th node construction time limit and the h-th node construction monitoring time; building a node construction time margin evaluation model; inputting the h-th node construction auxiliary time zone and the h-th node construction tolerance time zone into the node construction time margin evaluation model, and outputting the h-th node construction time margin coefficient.

[0007] Preferably, the project progress expectation adaptation analytical function is:

[0008] ;

[0009] Among them, PSF represents the expected adaptation index of the node schedule, μ represents the expected adaptation analysis factor of the project schedule, μ is greater than 1, and ctm represents the node construction time margin coefficient.

[0010] Preferably, the project construction quality combing channel is activated, and the project construction quality inspection is performed in combination with the h-th node construction plan and the h-th node construction BIM model to generate the h-th node project construction quality inspection report, including: disassembling the h-th node construction BIM model to obtain multiple partition construction BIM sub-models; extracting the first partition construction BIM sub-model according to the multiple partition construction BIM sub-models; matching the first partition construction plan corresponding to the first partition construction BIM sub-model according to the h-th node construction plan; interacting with the BIM system, and building the first partition expected BIM sub-model in combination with the first partition construction plan; performing deviation identification on the first partition construction BIM sub-model based on the first partition expected BIM sub-model to generate a first partition construction deviation identification result; inputting the first partition construction deviation identification result into the project construction quality combing channel to obtain the first partition construction quality combing result, and adding the first partition construction quality combing result to the h-th node project construction quality inspection report; according to the project construction quality combing channel and the h-th node construction plan, continuing to perform project construction quality inspection on the multiple partition construction BIM sub-models to obtain the h-th node project construction quality inspection report.

[0011] Preferably, the first partition construction deviation identification result is input into the project construction quality combing channel to obtain the first partition construction quality combing result, including: the project construction quality combing channel includes a project construction deviation depth detection branch, a project construction deviation breadth detection branch and a project construction quality combing branch; based on the first partition construction deviation identification result, according to the project construction deviation depth detection branch, a first partition construction deviation depth coefficient is generated; based on the first partition construction deviation identification result, according to the project construction deviation breadth detection branch, a first partition construction deviation breadth coefficient is generated; the first partition construction deviation depth coefficient and the first partition construction deviation breadth coefficient are input into the project construction quality combing branch to generate a first partition construction quality index; the first partition construction deviation identification result, the first partition construction deviation depth coefficient, the first partition construction deviation breadth coefficient and the first partition construction quality index are added to the first partition construction quality combing result.

[0012] Preferably, the project construction quality combing branch includes a project construction quality combing function, and the project construction quality combing function is:

[0013] ;

[0014] Among them, CQI represents the partition construction quality index, α represents the first gain coefficient of construction quality combing, β represents the second gain coefficient of construction quality combing, α and β are both positive numbers, the sum of α and β is 1, r represents the construction quality combing factor, 0<r<1, ADX represents the partition construction deviation depth coefficient, and ABX represents the partition construction deviation breadth coefficient.

[0015] Preferably, the method includes: loading a construction deviation identification sample set, a construction deviation depth sample set and a construction deviation breadth sample set; training a construction deviation detection learning model according to the construction deviation identification sample set and the construction deviation depth sample set, and obtaining a construction deviation depth detection loss coefficient each time the training is performed for a preset number of times; if the construction deviation depth detection loss coefficient is less than a construction deviation depth detection loss threshold, generating the project construction deviation depth detection branch; training the construction deviation detection learning model according to the construction deviation identification sample set and the construction deviation breadth sample set, and obtaining a construction deviation breadth detection loss coefficient each time the training is performed for the preset number of times; if the construction deviation breadth detection loss coefficient is less than a construction deviation breadth detection loss threshold, generating the project construction deviation breadth detection branch.

[0016] This application proposes a project progress and quality collaborative management method based on a BIM visualization model. By disassembling the project construction plan, H node construction plans corresponding to H construction nodes are obtained. According to the H node construction plans, the h-th node construction plan corresponding to the h-th construction node is extracted. According to the construction monitoring system, the h-th node construction monitoring data stream corresponding to the h-th construction node is retrieved, and the h-th node construction BIM model is constructed in combination with the BIM system. The project progress expected adaptation analytical function and the project construction quality combing channel are activated, and the project progress expected adaptation prediction and project construction quality detection are performed in combination with the h-th node construction plan and the h-th node construction BIM model, and the h-th node progress expected adaptation index and the h-th node project construction quality detection report are generated, and the project construction management is performed according to the h-th node progress expected adaptation index and the h-th node project construction quality detection report. The technical problems of low timeliness of project construction progress control and poor effect of project construction quality control in the prior art are solved. The technical effects of improving the timeliness and accuracy of project construction progress control, improving the effect of project construction quality control, and improving the comprehensiveness and reliability of project construction quality detection are achieved. BRIEF DESCRIPTION OF THE DRAWINGS

[0017] In order to more clearly illustrate the technical solution of the embodiment of the present invention, the accompanying drawings of the embodiment of the present invention will be briefly introduced below. A flow chart is used in the present application to illustrate the operations performed by the system according to the embodiment of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps can be processed in reverse order or simultaneously as needed. At the same time, other operations can also be added to these processes, or one or more operations can be removed from these processes.

[0018] Figure 1 A flowchart of a method for collaborative management of project progress and quality based on a BIM visualization model is provided in an embodiment of the present application.

[0019] Figure 2 A structural schematic diagram of generating the h-th node construction time margin coefficient in the project progress and quality collaborative management method based on the BIM visualization model provided in an embodiment of the present application. DETAILED DESCRIPTION

[0020] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented in accordance with the contents of the specification. In order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are listed below.

[0021] In order to make the purpose, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in conjunction with the accompanying drawings. The described embodiments should not be regarded as limiting the present application. All other embodiments obtained by ordinary technicians in the field without making creative work are within the scope of protection of this application.

[0022] In the following description, reference is made to "some embodiments", which describe a subset of all possible embodiments, but it is understood that "some embodiments" may be the same subset or different subsets of all possible embodiments, and may be combined with each other without conflict, and the terms "first\second" involved are merely to distinguish similar objects and do not represent a specific ordering of objects. The terms "including" and "having" and any variations are intended to cover non-exclusive inclusions, for example, a process, method, system, product, or server that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or modules that are not clearly listed or inherent to these processes, methods, products, or devices. Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those generally understood by technicians in the technical field of this application. The terms used herein are for the purpose of describing the embodiments of the present application only.

[0023] The present application embodiment provides a project progress and quality collaborative management method based on BIM visualization model, such as Figure 1 As shown, the method includes:

[0024] First, execute step S100, disassemble the project construction plan, and obtain H node construction plans corresponding to H construction nodes, where H is a positive integer greater than 1. Specifically, the project construction plan is decomposed according to the construction process, and H node construction plans corresponding to H construction nodes are obtained, so as to improve the accuracy of project construction progress control and improve the refinement of project construction quality control. The project construction plan includes project location, project scale, construction conditions and other engineering overview data, as well as construction deployment data, construction plan data, construction schedule data, construction design data and other data information corresponding to the construction process. The construction process includes all construction nodes from the start of project construction to the end of project construction. Preferably, the construction process includes H construction nodes. For example, H construction nodes include foundation construction nodes, wall casting nodes, frame construction nodes (installation and connection of frame structures such as columns, beams, and floor slabs), pipeline construction nodes, indoor construction nodes, equipment installation nodes, etc. The construction plan for each node includes the construction location information, construction content information, construction time limit information, construction plan information (construction method information, construction technology information, construction resource allocation information), construction design drawings and other data information corresponding to each construction node.

[0025] Then, execute step S200, and extract the h-th node construction plan corresponding to the h-th construction node according to the H node construction plans, wherein h is a positive integer and h belongs to H. It should be noted that the h-th construction node is a real-time construction node. The h-th node construction plan is the node construction plan corresponding to the real-time construction node among the H node construction plans. Next, execute steps S300 and S400. Step S300, the interactive construction monitoring system obtains the h-th node construction monitoring data stream corresponding to the h-th construction node. The construction monitoring system monitors each construction node in real time through various monitoring sensors, thereby collecting, transmitting, processing and displaying the key data of each construction node, providing an accurate reference basis for project construction management. Communicate with the construction monitoring system through a specific interaction method (such as API interface, database connection, etc.), thereby loading the h-th node construction monitoring data stream corresponding to the h-th construction node. The h-th node construction monitoring data stream includes construction monitoring parameters such as real-time geometric monitoring data corresponding to the h-th construction node (such as the real-time size, real-time shape, real-time structure and other information of the building), real-time structural deformation data (such as settlement, displacement, deflection and other information of the building or foundation), and real-time stress and strain data.

[0026] Step S400, connect the BIM system, combine the h-th node construction monitoring data stream, and construct the h-th node construction BIM model. Specifically, the full name of the BIM system is the Building Information Model (Building Information Model) system, which is a method for creating and managing construction projects in a digital environment. The BIM system improves the visualization and intelligence of project construction management by integrating the building's geometric data, spatial relationships, materials and construction information into a unified model. The h-th node construction monitoring data stream is uploaded to the BIM system, and the BIM system is modeled according to the h-th node construction monitoring data stream to obtain the h-th node construction BIM model. The h-th node construction BIM model is the building information model corresponding to the h-th node construction monitoring data stream.

[0027] Further, execute step S500, activate the project schedule expected adaptation analytical function, combine the h-th node construction plan and the h-th node construction BIM model to predict the project schedule expected adaptation, and generate the h-th node schedule expected adaptation index. In a possible implementation, step S500 further includes steps S510 to S560. Step S510, connect the BIM system, and build the h-th node benchmark BIM model in combination with the h-th node construction plan. The construction design drawings in the h-th node construction plan are recorded as the h-th node construction design feature data. The BIM system is modeled according to the h-th node construction design feature data to obtain the h-th node benchmark BIM model. The h-th node benchmark BIM model includes the building information model corresponding to the h-th node construction design feature data.

[0028] On the basis of obtaining the h-th node benchmark BIM model, step S520 is executed to compare the h-th node benchmark BIM model and the h-th node construction BIM model to generate the h-th node construction auxiliary BIM model. Specifically, the h-th node benchmark BIM model is compared with the h-th node construction BIM model, the missing building information model between the two is identified, and the h-th node construction auxiliary BIM model is obtained. The h-th node construction auxiliary BIM model is the missing building information model between the h-th node benchmark BIM model and the h-th node construction BIM model. Next, steps S530 and S540 are executed. Step S530, the construction time is predicted according to the h-th node construction auxiliary BIM model, and the h-th node construction auxiliary time zone is obtained. Step S540, the h-th node construction time limit is extracted according to the h-th node construction plan. Specifically, the simulation function in the BIM system is used to simulate the construction time corresponding to the h-th node construction auxiliary BIM model, and the h-th node construction auxiliary time zone is determined. The h-th node construction auxiliary time zone is the simulated construction time corresponding to the h-th node construction auxiliary BIM model. The h-th node construction time limit includes the construction time limit information within the h-th node construction plan.

[0029] Then, step S550 is executed to evaluate the node construction time margin based on the h-th node construction time limit and the h-th node construction auxiliary time zone, and generate the h-th node construction time margin coefficient. Figure 2 As shown, step S550 further includes steps S551 to S554. Step S551, obtain the h-th node construction monitoring time corresponding to the h-th node construction monitoring data stream. Connect the construction monitoring system, query the monitoring time corresponding to the h-th node construction monitoring data stream, and obtain the h-th node construction monitoring time. The h-th node construction monitoring time includes the monitoring time corresponding to the h-th node construction monitoring data stream. Then, execute step S552, and calculate the h-th node construction tolerance time zone according to the h-th node construction time limit and the h-th node construction monitoring time. Specifically, the time difference is calculated according to the h-th node construction time limit and the h-th node construction monitoring time to obtain the h-th node construction tolerance time zone. The h-th node construction tolerance time zone is the time difference between the h-th node construction time limit and the h-th node construction monitoring time. For example, if the time difference between the h-th node construction time limit and the h-th node construction monitoring time is 5 days, then the h-th node construction tolerance time zone is 5 days.

[0030] Step S553, build a node construction time margin evaluation model. Specifically, use the existing data retrieval platform to load multiple node construction time margin evaluation record sets. Each node construction time margin evaluation record set includes a historical node construction auxiliary time zone, a historical node construction tolerance time zone, and a historical node construction time margin coefficient. According to the BP neural network, multiple node construction time margin evaluation record sets are continuously self-trained and learned until a convergence state, and a node construction time margin evaluation model is obtained. The BP neural network is a multi-layer feedforward neural network trained according to the error back propagation algorithm. The BP neural network has strong nonlinear mapping capabilities, robustness, fault tolerance and other characteristics. The node construction time margin evaluation model includes an input layer, a hidden layer, and an output layer. Then, execute step S554, input the h-th node construction auxiliary time zone and the h-th node construction tolerance time zone into the node construction time margin evaluation model, and output the h-th node construction time margin coefficient. It should be noted that the h-th node construction time margin coefficient is data information used to characterize the construction time margin corresponding to the h-th node construction auxiliary time zone and the h-th node construction tolerance time zone. The longer the time zone length of the h-th node construction tolerance time zone exceeds the h-th node construction auxiliary time zone, the higher the corresponding construction time margin, and the larger the corresponding h-th node construction time margin coefficient.

[0031] Further, based on the h-th node construction time margin coefficient, step S560 is executed to input the h-th node construction time margin coefficient into the project schedule expected adaptation analytical function, and output the h-th node schedule expected adaptation index. The project schedule expected adaptation analytical function is:

[0032] ;

[0033] Among them, PSF represents the expected adaptation index of the node schedule, μ represents the expected adaptation analysis factor of the project schedule, μ is greater than 1, and μ can be determined by custom settings. Preferably, μ is any one of 1.5, 2, 3.1..., and ctm represents the node construction time margin coefficient.

[0034] Step S600, activate the project construction quality combing channel, combine the h-th node construction plan and the h-th node construction BIM model to perform project construction quality inspection, and generate the h-th node project construction quality inspection report. In a possible implementation, step S600 further includes steps S610 to S670. Step S610, disassemble the h-th node construction BIM model to obtain multiple partition construction BIM sub-models. Split the h-th node construction BIM model according to the building components to obtain multiple partition construction BIM sub-models. Each partition construction BIM sub-model is a building information model corresponding to each building component in the h-th node construction BIM model. Then, execute step S620 to extract the first partition construction BIM sub-model according to the multiple partition construction BIM sub-models. Randomly extract multiple partition construction BIM sub-models to determine the first partition construction BIM sub-model. The first partition construction BIM sub-model is any one of the multiple partition construction BIM sub-models.

[0035] At the same time, execute step S630, and match the first partition construction plan corresponding to the first partition construction BIM sub-model according to the h-th node construction plan. It should be noted that the first partition construction plan includes the construction design drawing corresponding to the first partition construction BIM sub-model. After obtaining the first partition construction plan, execute step S640, interact with the BIM system, and build the first partition expected BIM sub-model in combination with the first partition construction plan. The BIM system performs modeling according to the first partition construction plan to obtain the first partition expected BIM sub-model. The first partition expected BIM sub-model is the building information model corresponding to the first partition construction plan.

[0036] After determining the first partition expected BIM sub-model and the first partition construction BIM sub-model, step S650 is executed to identify the deviation of the first partition construction BIM sub-model based on the first partition expected BIM sub-model, and generate the first partition construction deviation identification result. Specifically, the first partition expected BIM sub-model and the first partition construction BIM sub-model are geometrically compared to identify the differences between the two in terms of spatial position, size, etc., and determine the geometric shape deviation. At the same time, the attribute information of the first partition expected BIM sub-model and the first partition construction BIM sub-model, such as material, color, logo, etc., is compared to determine the attribute information deviation, and the first partition construction deviation identification result is generated in combination with the geometric shape deviation, so as to improve the comprehensiveness and accuracy of the project construction quality control. The first partition construction deviation identification result includes the geometric shape deviation (such as size difference information, position offset information, etc.) and attribute information deviation (material use error information, color mismatch information, etc.) between the first partition expected BIM sub-model and the first partition construction BIM sub-model.

[0037] Next, execute step S660, input the first partition construction deviation identification result into the project construction quality combing channel, obtain the first partition construction quality combing result, and add the first partition construction quality combing result to the h-th node project construction quality inspection report. In a possible implementation, step S660 further includes steps S661 to S665. Step S661, the project construction quality combing channel includes a project construction deviation depth detection branch, a project construction deviation breadth detection branch and a project construction quality combing branch. Step S662, based on the first partition construction deviation identification result, according to the project construction deviation depth detection branch, generate a first partition construction deviation depth coefficient. Input the first partition construction deviation identification result into the project construction deviation depth detection branch to obtain the first partition construction deviation depth coefficient. The first partition construction deviation depth coefficient is data information used to characterize the degree of construction deviation corresponding to the first partition construction deviation identification result. The greater the degree of construction deviation corresponding to the first partition construction deviation identification result, the higher the corresponding first partition construction deviation depth coefficient.

[0038] Step S663, based on the first partition construction deviation identification result and according to the project construction deviation breadth detection branch, generate the first partition construction deviation breadth coefficient. Input the first partition construction deviation identification result into the project construction deviation breadth detection branch to obtain the first partition construction deviation breadth coefficient. The first partition construction deviation breadth coefficient is data information used to characterize the construction deviation impact corresponding to the first partition construction deviation identification result. The higher the first partition construction deviation breadth coefficient, the greater the construction deviation impact corresponding to the first partition construction deviation identification result. Furthermore, after obtaining the first partition construction deviation depth coefficient and the first partition construction deviation breadth coefficient, execute step S664, input the first partition construction deviation depth coefficient and the first partition construction deviation breadth coefficient into the project construction quality combing branch to generate the first partition construction quality index. Among them, the project construction quality combing branch includes a project construction quality combing function. The project construction quality combing function is:

[0039] ;

[0040] Among them, CQI represents the partition construction quality index. α represents the first gain coefficient of construction quality combing. β represents the second gain coefficient of construction quality combing. α and β are both positive numbers, the sum of α and β is 1, and α and β can be customized. Preferably, α is 0.4 and β is 0.6. r represents the construction quality combing factor, 0<r<1, preferably, r is any one of 0.5, 0.3, 0.7... ADX represents the partition construction deviation depth coefficient. ABX represents the partition construction deviation breadth coefficient.

[0041] Step S665, adding the first partition construction deviation identification result, the first partition construction deviation depth coefficient, the first partition construction deviation breadth coefficient and the first partition construction quality index to the first partition construction quality combing result. Step S670, according to the project construction quality combing channel and the h-th node construction plan, continue to perform project construction quality inspection on the multiple partition construction BIM sub-models to obtain the h-th node project construction quality inspection report. Specifically, by analogy, according to the project construction quality combing channel and the h-th node construction plan, continue to perform project construction quality inspection on the multiple partition construction BIM sub-models to generate the h-th node project construction quality inspection report. The h-th node project construction quality inspection report includes multiple partition construction quality combing results corresponding to multiple partition construction BIM sub-models. The multiple partition construction quality combing results are generated in the same way as the first partition construction quality combing results. For the sake of brevity of the specification, they will not be repeated here. The first partition construction quality combing result includes the first partition construction deviation identification result, the first partition construction deviation depth coefficient, the first partition construction deviation breadth coefficient and the first partition construction quality index.

[0042] In a possible implementation, the construction process of the project construction deviation depth detection branch and the project construction deviation breadth detection branch in the project construction quality combing channel includes steps S661-1 to S661-5. Step S661-1, load the construction deviation identification sample set, the construction deviation depth sample set and the construction deviation breadth sample set. Using the existing data retrieval platform, retrieve the construction deviation identification sample set, the construction deviation depth sample set and the construction deviation breadth sample set. The construction deviation identification sample set includes multiple historical partition construction deviation identification results. The construction deviation depth sample set includes the historical partition construction deviation depth coefficient corresponding to each historical partition construction deviation identification result in the construction deviation identification sample set. The construction deviation breadth sample set includes the historical partition construction deviation breadth coefficient corresponding to each historical partition construction deviation identification result in the construction deviation identification sample set.

[0043] Step S661-2, according to the construction deviation identification sample set and the construction deviation depth sample set, the construction deviation detection learning model is trained, and the construction deviation depth detection loss coefficient is obtained every time the training is performed for a preset number of times. Step S661-3, if the construction deviation depth detection loss coefficient is less than the construction deviation depth detection loss threshold, the project construction deviation depth detection branch is generated. Specifically, the construction deviation identification sample set is set as input data, the construction deviation depth sample set is set as output data, and the construction deviation detection learning model is trained, and the construction deviation depth detection loss coefficient is obtained every time the training is performed for a preset number of times. Then, it is judged whether the construction deviation depth detection loss coefficient is less than the construction deviation depth detection loss threshold. When the construction deviation depth detection loss coefficient is less than the construction deviation depth detection loss threshold, a project construction deviation depth detection branch is generated. Among them, the construction deviation detection learning model can be any one of a plurality of machine learning models such as a neural network, a decision tree, and a support vector machine. The preset number of times includes a pre-set training number threshold. The construction deviation depth detection loss coefficient includes the mean of a plurality of construction deviation depth detection error rates when the training number reaches the preset number of times. The construction deviation depth detection loss threshold includes a preset expected construction deviation depth detection loss coefficient.

[0044] Exemplarily, when obtaining the construction deviation depth detection loss coefficient, a random historical partition construction deviation identification result in the construction deviation identification sample set is set as the first training input data. The historical partition construction deviation depth coefficient corresponding to the first training input data in the construction deviation depth sample set is set as the first expected output partition construction deviation depth coefficient. Then, the first training input data is input into the construction deviation detection learning model to obtain the first output partition construction deviation depth coefficient corresponding to the first training input data. The absolute value of the difference between the first expected output partition construction deviation depth coefficient and the first output partition construction deviation depth coefficient is recorded as the first training error coefficient. The ratio between the first training error coefficient and the first expected output partition construction deviation depth coefficient is set as the construction deviation depth detection error rate of this training. Similarly, when the number of trainings reaches a preset number of times, multiple construction deviation depth detection error rates corresponding to multiple trainings are obtained. The average value of multiple construction deviation depth detection error rates is set as the construction deviation depth detection loss coefficient.

[0045] Step S661-4, the construction deviation detection learning model is trained according to the construction deviation identification sample set and the construction deviation breadth sample set, and the construction deviation breadth detection loss coefficient is obtained each time the preset number of trainings is performed. Step S661-5, if the construction deviation breadth detection loss coefficient is less than the construction deviation breadth detection loss threshold, the project construction deviation breadth detection branch is generated. Similarly, the construction deviation identification sample set is set as input information, the construction deviation breadth sample set is set as output information, and the construction deviation detection learning model is trained, and the construction deviation breadth detection loss coefficient is obtained each time the preset number of trainings is performed. Then, it is determined whether the construction deviation breadth detection loss coefficient is less than the construction deviation breadth detection loss threshold. When the construction deviation breadth detection loss coefficient is less than the construction deviation breadth detection loss threshold, a project construction deviation breadth detection branch is generated. The construction deviation breadth detection loss coefficient is calculated in the same way as the construction deviation depth detection loss coefficient, and for the sake of brevity of the specification, it will not be repeated here. The construction deviation breadth detection loss threshold includes a pre-set and determined expected construction deviation breadth detection loss coefficient.

[0046] Further, step S700 is executed to perform project construction management according to the h-th node progress expected adaptation index and the h-th node project construction quality inspection report. On the one hand, it is determined whether the h-th node progress expected adaptation index is less than the node progress expected adaptation index threshold value determined in advance. If the h-th node progress expected adaptation index is less than the node progress expected adaptation index threshold value, an h-th node project progress warning signal is generated. Based on this, a reliable project progress warning is achieved, the timeliness and accuracy of the project construction progress control are improved, and the project is ensured to proceed according to the construction schedule. The h-th node project progress warning signal is a warning prompt information used to characterize that the h-th node progress expected adaptation index is less than the node progress expected adaptation index threshold value, and the h-th node construction plan needs to be adjusted. On the other hand, the h-th node project construction quality inspection report is sent to the project construction management personnel, and the project construction management personnel carry out construction rectification according to the construction quality combing results of each partition in the h-th node project construction quality inspection report to improve the project construction quality.

[0047] The above specific implementations do not constitute a limitation on the protection scope of this application. It should be understood by those skilled in the art that various modifications, combinations and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions and improvements made within the spirit and principles of this application should be included in the protection scope of this application.

Claims

1. A collaborative management method for project progress and quality based on BIM visualization model, characterized by: The method comprises: Disassemble the project construction plan and obtain H node construction plans corresponding to H construction nodes, where H is a positive integer greater than 1; According to the H node construction plans, extract the h-th node construction plan corresponding to the h-th construction node, where h is a positive integer and h belongs to H; The interactive construction monitoring system obtains the h-th node construction monitoring data stream corresponding to the h-th construction node; Connecting to the BIM system, combining the h-th node construction monitoring data stream, and constructing the h-th node construction BIM model; Activate the project schedule expected adaptation analytical function, combine the h-th node construction plan and the h-th node construction BIM model to predict the project schedule expected adaptation, and generate the h-th node schedule expected adaptation index; Activate the project construction quality sorting channel, perform project construction quality inspection in combination with the h-th node construction plan and the h-th node construction BIM model, and generate the h-th node project construction quality inspection report; Perform project construction management according to the h-th node progress expected adaptation index and the h-th node project construction quality inspection report; The project schedule expectation adaptation analytical function is: ; Among them, PSF represents the expected adaptation index of node progress, Characterize the expected adaptation factor of the project schedule, If it is greater than 1, ctm represents the node construction time margin coefficient; Activate the project construction quality sorting channel, combine the h-th node construction plan and the h-th node construction BIM model to perform project construction quality inspection, and generate the h-th node project construction quality inspection report, including: Disassembling the h-th node construction BIM model to obtain multiple partition construction BIM sub-models; Extracting a first partition construction BIM sub-model according to the multiple partition construction BIM sub-models; According to the h-th node construction plan, matching the first partition construction plan corresponding to the first partition construction BIM sub-model; Interacting with the BIM system, and building the expected BIM sub-model of the first partition in combination with the construction plan of the first partition; Based on the first partition expected BIM sub-model, the first partition construction BIM sub-model is subjected to deviation identification to generate a first partition construction deviation identification result; Input the first partition construction deviation identification result into the project construction quality combing channel to obtain the first partition construction quality combing result, and add the first partition construction quality combing result to the h-th node project construction quality inspection report; According to the project construction quality combing channel and the h-th node construction plan, continue to perform project construction quality inspection on the multiple partition construction BIM sub-models to obtain the h-th node project construction quality inspection report; Inputting the first partition construction deviation identification result into the project construction quality combing channel to obtain the first partition construction quality combing result, including: The project construction quality combing channel includes a project construction deviation depth detection branch, a project construction deviation breadth detection branch and a project construction quality combing branch; Based on the first partition construction deviation identification result, generating the first partition construction deviation depth coefficient according to the project construction deviation depth detection branch; Based on the first partition construction deviation identification result, generating the first partition construction deviation breadth coefficient according to the project construction deviation breadth detection branch; Inputting the first partition construction deviation depth coefficient and the first partition construction deviation breadth coefficient into the project construction quality combing branch to generate a first partition construction quality index; Adding the first partition construction deviation identification result, the first partition construction deviation depth coefficient, the first partition construction deviation breadth coefficient and the first partition construction quality index to the first partition construction quality combing result; The project construction quality combing branch includes a project construction quality combing function, and the project construction quality combing function is: ; Among them, CQI represents the construction quality index of the partition. Characterize the construction quality combing the first gain coefficient, Characterizing the construction quality combing the second gain coefficient, , are all positive numbers, , The sum of is 1, Characterize the construction quality combing factors, , ADX represents the depth coefficient of the partition construction deviation, and ABX represents the breadth coefficient of the partition construction deviation; The method further comprises: Load the construction deviation identification sample set, the construction deviation depth sample set and the construction deviation breadth sample set; Training the construction deviation detection learning model according to the construction deviation identification sample set and the construction deviation depth sample set, and obtaining the construction deviation depth detection loss coefficient after each preset number of trainings; If the construction deviation depth detection loss coefficient is less than the construction deviation depth detection loss threshold, generating the project construction deviation depth detection branch; The construction deviation detection learning model is trained according to the construction deviation identification sample set and the construction deviation breadth sample set, and a construction deviation breadth detection loss coefficient is obtained each time the preset number of trainings is performed; If the construction deviation breadth detection loss coefficient is less than the construction deviation breadth detection loss threshold, the project construction deviation breadth detection branch is generated.

2. The method according to claim 1, characterized in that Activate the project schedule expected adaptation analytical function, combine the h-th node construction plan and the h-th node construction BIM model to predict the project schedule expected adaptation, and generate the h-th node schedule expected adaptation index, including: Connecting the BIM system, combining the h-th node construction plan, and building the h-th node benchmark BIM model; Comparing the h-th node benchmark BIM model with the h-th node construction BIM model to generate the h-th node construction auxiliary BIM model; Predicting the construction time according to the h-th node construction auxiliary BIM model to obtain the h-th node construction auxiliary time zone; Extracting the h-th node construction time limit according to the h-th node construction plan; Performing node construction time margin evaluation based on the h-th node construction time limit and the h-th node construction auxiliary time zone, and generating an h-th node construction time margin coefficient; The h-th node construction time margin coefficient is input into the project schedule expected adaptation analytical function, and the h-th node schedule expected adaptation index is output.

3. The method according to claim 2, characterized in that Based on the h-th node construction time limit and the h-th node construction auxiliary time zone, a node construction time margin evaluation is performed to generate an h-th node construction time margin coefficient, including: Obtaining the h-th node construction monitoring time corresponding to the h-th node construction monitoring data stream; Calculate the h-th node construction tolerance time zone according to the h-th node construction time limit and the h-th node construction monitoring time; Build a node construction time margin evaluation model; The h-th node construction auxiliary time zone and the h-th node construction tolerance time zone are input into the node construction time margin evaluation model, and the h-th node construction time margin coefficient is output.