Large-scale AIOT node intelligent deployment method based on BIM model

Abstract

The present application provides a large-scale AIOT node intelligent deployment method based on the BIM model, which is as follows: the device management end searches the BIM database according to the deployment status of the AIOT node network, and distributes the device to the corresponding BIM model data; the AIOT node network obtains the sensor data of each key component; the AI ​​cloud server determines whether the AIOT node network has completed initialization; if the AIOT node network has completed initialization, the AIOT node network is dynamically incrementally deployed according to the sensor data and BIM model information to obtain a dynamically adjusted AIOT node network; if the AIOT node network has not completed initialization, the AIOT node network is re-initialized, and after completion, the AI ​​cloud server determines again whether the AIOT node network has completed initialization. This solution combines the advantages of the full life cycle of the BIM model, judges the current device weight coefficient according to the external and internal status of the facility, and dynamically adjusts whether the AIOT node needs to be adjusted. It has the advantages of low cost and no need for human maintenance.

Description

Technical Field

[0001] The present invention belongs to the technical field of AIOT node layout, and in particular relates to a large-scale AIOT node intelligent layout method based on a BIM model. Background Art

[0002] The Building Information Model (BIM), an important tool and product for promoting building informatization, is gradually being applied to smart buildings.

[0003] The rapid development and evolution of artificial intelligence (AI) theory and technology has led to significant changes in current information technology architectures. The Internet of Things (IoT) is one such area. As a source of real-world data, it presents both opportunities and challenges. The Artificial Intelligence of Things (AIoT) combines AI technology with IoT infrastructure to achieve more efficient IoT operations, improve human-computer interaction, and enhance data management and analysis capabilities. The AIOT module refers to the practical integration of AI technology and IoT in real-world applications and is a key direction for the future development of the IoT.

[0004] Existing AIOT node deployment technology uses facility locations for one-time deployment, and does not consider changes in the status of building facilities as construction continues. Summary of the Invention

[0005] The purpose of the embodiments of this specification is to provide a large-scale AIOT node intelligent deployment method based on the BIM model.

[0006] To solve the above technical problems, the embodiments of the present application are implemented in the following ways:

[0007] In a first aspect, the present application provides a method for intelligent deployment of large-scale AIOT nodes based on a BIM model, the method comprising:

[0008] The device management end searches the BIM database based on the layout of the AIOT node network and distributes the device data associated with the corresponding BIM model data;

[0009] The AIOT node network obtains sensor data from each key component;

[0010] The AI ​​cloud server determines whether the AIOT node network has completed initialization;

[0011] If the AIOT node network is initialized, the AIOT node network is dynamically and incrementally deployed based on sensor data and BIM model information to obtain a dynamically adjusted AIOT node network.

[0012] If the AIOT node network has not completed initialization, the AIOT node network is reinitialized, and after completion, the AI ​​cloud server determines again whether the AIOT node network has completed initialization.

[0013] In one embodiment, if the AIOT node network completes initialization, the AIOT node network is dynamically and incrementally deployed based on sensor data and BIM model information to obtain a dynamically adjusted AIOT node network, specifically: initial prediction of facility weight coefficients based on prior information of the initial BIM model; collection of sensor data of the AIOT node network; standardization of the sensor data; acquisition of BIM model inherent data from the BIM database and association of sensor data; the AI ​​cloud server predicts the status of the equipment based on the sensor data and BIM model information, and intelligently evaluates the current AIOT deployment situation; determines the degree of degradation of the equipment in the added AIOT nodes during their service life through a deep learning network, predicts the frequency of abnormal events and the usage pattern of components, and dynamically adjusts the AIOT node network in combination with the incremental plan.

[0014] In one embodiment, the AIOT node network is dynamically adjusted in combination with an incremental solution, specifically: based on the BIM model update, the facility weight coefficient is re-predicted, and if there are new facilities that meet the requirements, new AIOT nodes are deployed.

[0015] In one embodiment, if there is a new facility that meets the requirements, a new AIOT node is deployed. Specifically, if the weight coefficient of the new facility is greater than 0.7, a new AIOT node is deployed.

[0016] In one embodiment, if the AIOT node network has not completed initialization, the AIOT node network is reinitialized, specifically by constructing a BIM model data set, building a deep learning network based on the prior information of the BIM model, training the deep learning network through the BIM model data set, and the AI ​​cloud server predicting the status of the equipment based on the BIM model.

[0017] In one embodiment, the AI ​​cloud server predicts the status of the equipment based on the BIM model. Specifically, the weight coefficient is predicted using a deep neural network, the input of which is the model category, external state, and internal state, and the network output is the weight coefficient of the model.

[0018] In a second aspect, the present application provides a large-scale AIOT node intelligent deployment system based on a BIM model, which includes an AIOT node network, a BIM database, a device management system, a device management database, an AI cloud server, and a user interface;

[0019] The AI ​​cloud server and BIM database are used to obtain sensor data of key components through the user interface;

[0020] The construction of the BIM database is completed through the equipment management system and equipment management database;

[0021] The AI ​​cloud server is also used to determine whether the AIOT node network has completed initialization, dynamically and incrementally deploy the AIOT node network, and obtain a dynamically adjusted AIOT node network.

[0022] In one embodiment, the AIOT node network includes several AIOT nodes, which are used to complete the collection of external and internal states, upload them to the AI ​​cloud server, and perform data mining, refining, and modeling.

[0023] In one embodiment, each AIOT node includes at least an MCU, a storage unit, and a wireless transmission unit; the wireless transmission unit receives metadata of the current node distributed by the device management system and sends the external state and internal state of the current device.

[0024] It can be seen from the technical solution provided in the above embodiments of this specification that this solution combines the advantages of the BIM model throughout its entire life cycle, determines the current equipment weight coefficient based on the external and internal status of the facility, and dynamically adjusts whether the AIOT node needs to be adjusted. It has the advantages of low cost and no need for human maintenance. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] In order to more clearly illustrate the embodiments of this specification or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments recorded in this specification. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0026] Figure 1 A flowchart of a method for intelligent deployment of large-scale AIOT nodes based on a BIM model is provided for an embodiment of the present invention;

[0027] Figure 2 A schematic diagram of AIOT node deployment judgment conditions in a large-scale AIOT node intelligent deployment method based on a BIM model is provided for an embodiment of the present invention;

[0028] Figure 3 A connection block diagram of a large-scale AIOT node intelligent layout system based on a BIM model is provided for an embodiment of the present invention. DETAILED DESCRIPTION

[0029] To help those skilled in the art better understand the technical solutions in this specification, the following will provide a clear and complete description of the technical solutions in the embodiments of this specification, in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of this specification, not all of them. All other embodiments derived by those skilled in the art based on the embodiments in this specification without creative effort shall fall within the scope of protection of this specification.

[0030] In the following description, specific details such as specific system structures and techniques are provided for purposes of illustration rather than limitation to facilitate a thorough understanding of the embodiments of the present application. However, it will be apparent to those skilled in the art that the present application may be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to avoid obscuring the description of the present application with unnecessary detail.

[0031] It will be apparent to those skilled in the art that various modifications and variations may be made to the specific embodiments described herein without departing from the scope or spirit of the present application. Other embodiments will be apparent to those skilled in the art from the present description. The present description and examples are intended to be illustrative only.

[0032] The words “include,” “including,” “have,” “contain,” etc. used in this document are open-ended terms, meaning including but not limited to.

[0033] Unless otherwise specified, "parts" in this application are calculated by mass.

[0034] The present invention will be further described in detail below with reference to the accompanying drawings and embodiments.

[0035] The embodiment of the present invention provides a large-scale AIOT node intelligent deployment method based on the BIM model, such as Figure 1 、 2 As shown, the method is implemented by the following steps:

[0036] Step 1: The device management terminal searches the BIM database based on the layout of the AIOT node network and distributes the device data associated with the corresponding BIM model data;

[0037] Step 2: The AIOT node network obtains sensor data from each key component;

[0038] Step 3: The AI ​​cloud server determines whether the AIOT node network has completed initialization;

[0039] Specifically, if the AI ​​cloud server determines that the AIOT node network has completed initialization, go to step 4; if the AI ​​cloud server determines that the AIOT node network has not completed initialization, go to step 5.

[0040] Initial deployment includes the following steps:

[0041] Step S301: Constructing a BIM model dataset under the current construction progress;

[0042] Step S302: Building a deep learning network based on prior feature information of the BIM model;

[0043] Step S303: training a deep learning network;

[0044] Step S304: The AI ​​cloud server uses the BIM model information to predict the status of the equipment and generate an AIOT node initialization layout plan.

[0045] Step 4: If the AIOT node network is initialized, the AIOT node network is dynamically and incrementally deployed based on the sensor data and BIM model information to obtain a dynamically adjusted AIOT node network.

[0046] Specifically, the facility weight coefficient is initially predicted based on the prior information of the initial BIM model; sensor data of the AIOT node network is collected; the sensor data is standardized; BIM model inherent data is obtained from the BIM database and associated with the sensor data; the AI ​​cloud server predicts the status of the equipment based on the sensor data and BIM model information, and intelligently evaluates the current AIOT deployment situation; the degree of degradation of the equipment in the added AIOT node during its service life is determined through a deep learning network, the frequency of abnormal events and the usage pattern of components are predicted, and the AIOT node network is dynamically adjusted in combination with the incremental plan.

[0047] Based on the BIM model update, the facility weight coefficient is re-predicted. If there are new facilities that meet the requirements, new AIOT nodes are deployed.

[0048] If there is a new facility with a weight coefficient greater than 0.7, a new AIOT node will be deployed.

[0049] Dynamic incremental node deployment includes the following steps:

[0050] Step S401: Collecting AIOT node network sensor data;

[0051] Step S402: The digital control system performs standardization processing on the sensor data, including timing synchronization, filtering, amplification, and encoding;

[0052] Step S403: Acquire BIM model inherent data from the BIM database and associate it with sensor data;

[0053] Step S404: The AI ​​cloud server predicts the status of the equipment based on sensor data and BIM model information, and intelligently evaluates the current AIOT deployment status.

[0054] Step 5: If the AIOT node network has not completed initialization, the AIOT node network is reinitialized, and after completion, the AI ​​cloud server determines again whether the AIOT node network has completed initialization.

[0055] Specifically, a BIM model dataset is constructed, a deep learning network is built based on the prior information of the BIM model, the deep learning network is trained using the BIM model dataset, and the AI ​​cloud server predicts the status of the equipment based on the BIM model.

[0056] The weight coefficient is predicted using a deep neural network, the input of which is the model category, external state, and internal state, and the network output is the weight coefficient of the model.

[0057] The BIM model includes the geometric information and semantic information (non-graphic information) of building facilities, including CAD model, type, size, material, location, and layout time.

[0058] The BIM model covers the entire life cycle of the building and is continuously updated as the construction progresses. The initial layout of AIOT nodes is based on the weight coefficient of the current BIM model, which is the initialization process. As construction continues, if new facilities are laid out, the weight coefficient of the associated BIM model is recalculated, which is the incremental layout of AIOT nodes.

[0059] The BIM model provides the equipment management system with the location information of the facilities and the equipment associated with each device (such as the speed sensor, temperature sensor, working condition equipment, etc. of the workshop conveyor belt), and the AI ​​cloud server provides the equipment management system with the predicted weight coefficient.

[0060] This work is carried out during the initialization process. The equipment management system sends the metadata of each facility to each facility through the wireless transmission unit, providing initial values ​​for the subsequent calculation of the external and internal states of the facility.

[0061] The embodiment of the present invention also provides a large-scale AIOT node intelligent layout system based on the BIM model, such as Figure 3 As shown, the system includes an AIOT node network, a BIM database, an equipment management system, an equipment management database, an AI cloud server, and a user interface;

[0062] The AI ​​cloud server and BIM database are used to obtain sensor data of key components through the user interface;

[0063] The construction of the BIM database is completed through the equipment management system and equipment management database;

[0064] The AI ​​cloud server is also used to determine whether the AIOT node network has completed initialization, dynamically and incrementally deploy the AIOT node network, and obtain a dynamically adjusted AIOT node network.

[0065] The AIOT node network includes several AIOT nodes, which are used to complete the collection of external and internal states, upload them to the AI ​​cloud server, and perform data mining, refinement, and modeling.

[0066] Typical sensors in the AIOT sensor network include temperature sensors, humidity sensors, flow sensors, inertial sensors, and pressure sensors. The sensor (that is, each AIOT node) includes a sensor unit, a microcontroller unit (MCU), digital input and output, analog input and output, and a wireless communication module. The microcontroller unit monitors the operating status of key components, collects sensor unit measurement data, associates it with the inherent attribute information of the relevant BIM model, and sends the sensor data to the equipment management system through the wireless communication module.

[0067] The equipment management system collects maintenance-related data and documents, including inspection records and historical maintenance records. Maintenance-related documents provide detailed parameters of the equipment, including service life, number of inspections per year, number of abnormalities per year, number of minor maintenance per year, and number of major maintenance per year.

[0068] The AI ​​cloud server includes a status monitoring module, a fault alarm module, an intelligent assessment module, and a status prediction module. The AI ​​cloud server needs to complete deep learning network construction, deep learning network training, equipment status prediction, and AIOT node deployment plan generation.

[0069] The present invention is applied in scenarios such as large-scale construction sites (large-scale particle collision building facilities, large-scale hospital building facilities). The construction site needs to grasp the current construction progress and the working conditions of each facility. It is difficult to dynamically track and adjust the node layout position by relying on manual observation to adjust the AIOT node layout. Combined with the construction site BIM model, AIOT nodes can be dynamically and incrementally deployed throughout the construction life cycle.

[0070] It should be noted that the terms "comprises", "includes" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, product or apparatus that includes a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, product or apparatus.

[0071] In the absence of more constraints, an element defined by the phrase "comprises a . . . ..." does not preclude the existence of additional identical elements in the process, method, product, or apparatus that comprises the element.

[0072] The various embodiments in this specification are described in a progressive manner. Similar parts between the various embodiments can be referred to in conjunction with each other. Each embodiment focuses on the differences between the other embodiments. In particular, the system embodiments are generally similar to the method embodiments, so the description is relatively simple. For relevant parts, refer to the description of the method embodiments.

Claims

1. A large-scale AIOT node intelligent deployment method based on BIM model, characterized in that: The method comprises: The device management end searches the BIM database based on the layout of the AIOT node network and distributes the device data associated with the corresponding BIM model data; The AIOT node network acquires sensor data of each key component; The AI ​​cloud server determines whether the AIOT node network has completed initialization; If the AIOT node network is initialized, the AIOT node network is dynamically and incrementally deployed according to the sensor data and BIM model information to obtain a dynamically adjusted AIOT node network, specifically: Initially predict facility weight coefficients based on prior information from the initial BIM model; collect sensor data from the AIOT node network; standardize the sensor data; obtain BIM model-specific data from the BIM database and associate it with the sensor data; the AI ​​cloud server predicts the status of equipment based on sensor data and BIM model information, and intelligently evaluates the current AIOT deployment; determine the degree of degradation of equipment in the added AIOT nodes during their service life through a deep learning network, predict the frequency of abnormal events and component usage patterns, and dynamically adjust the AIOT node network based on incremental solutions; If the AIOT node network has not completed initialization, the AIOT node network is reinitialized, and after completion, the AI ​​cloud server determines again whether the AIOT node network has completed initialization.

2. The large-scale AIOT node intelligent layout method based on the BIM model according to claim 1 is characterized in that: The dynamic adjustment of the AIOT node network in combination with the incremental scheme is specifically as follows: based on the BIM model update, the facility weight coefficient is re-predicted, and if there are new facilities that meet the requirements, new AIOT nodes are deployed.

3. The large-scale AIOT node intelligent deployment method based on the BIM model according to claim 2 is characterized in that: If there is a new facility that meets the requirements, a new AIOT node is deployed. Specifically, if the weight coefficient of the new facility is greater than 0.7, a new AIOT node is deployed.

4. The large-scale AIOT node intelligent deployment method based on the BIM model according to claim 3 is characterized in that: If the AIOT node network has not completed initialization, the AIOT node network is reinitialized, specifically by: constructing a BIM model data set, building a deep learning network based on the prior information of the BIM model, training the deep learning network through the BIM model data set, and the AI ​​cloud server predicting the status of the equipment based on the BIM model.

5. The large-scale AIOT node intelligent deployment method based on the BIM model according to claim 4 is characterized in that: The AI ​​cloud server predicts the status of the equipment based on the BIM model. Specifically, the weight coefficient is predicted using a deep neural network, the input of which is the model category, external state, and internal state, and the network output is the weight coefficient of the model.

6. A large-scale AIOT node intelligent layout system based on BIM model, characterized by: The system includes an AIOT node network, a BIM database, an equipment management system, an equipment management database, an AI cloud server, and a user interface; The AI ​​cloud server and BIM database are both used to obtain sensor data of key components through a user interface; The construction of the BIM database is completed through the equipment management system and the equipment management database; The AI ​​cloud server is also used to determine whether the AIOT node network has completed initialization, dynamically and incrementally deploy the AIOT node network, and obtain a dynamically adjusted AIOT node network, specifically: Initial prediction of facility weight coefficients based on prior information of the initial BIM model; collection of sensor data from the AIOT node network; standardization of sensor data; acquisition of BIM model inherent data from the BIM database and association of sensor data; AI cloud server predicts the status of equipment based on sensor data and BIM model information, and intelligently evaluates the current AIOT deployment; determination of the degree of degradation of equipment in the added AIOT nodes during their service life through a deep learning network, prediction of the frequency of abnormal events and component usage patterns, and dynamic adjustment of the AIOT node network in combination with incremental solutions.

7. The large-scale AIOT node intelligent layout system based on the BIM model according to claim 6 is characterized in that: The AIOT node network includes several AIOT nodes, which are used to complete the collection of external and internal states, upload them to the AI ​​cloud server, and perform data mining, refining, and modeling.

8. The large-scale AIOT node intelligent layout system based on the BIM model according to claim 7 is characterized in that: Each AIOT node includes at least an MCU, a storage unit, and a wireless transmission unit; the wireless transmission unit receives the metadata of the current node distributed by the device management system and sends the external state and internal state of the current device.

Images