Prefabricated building prefabricated part early warning method and system based on Internet of Things

CN118917456AActive Publication Date: 2024-11-08GUANGDONG BAIYUN UNIV
View PDF 10 Cites 0 Cited by

Patent Information

Application Number
CN202410919326.8
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2024-07-10
Publication Date
2024-11-08
Estimated Expiration
2044-07-10

Smart Images

  • Figure CN118917456A_ABST
    Figure CN118917456A_ABST
Patent Text Reader

Abstract

The invention relates to a prefabricated building prefabricated part early warning method and system based on the Internet of Things, and the method comprises the steps: classifying the Internet of Things data obtained by monitoring a target prefabricated part based on preset Internet of Things data classification information, and inputting a corresponding combined learning model; based on the combined learning model, obtaining a corresponding model prediction relational expression and a correlation prediction relational expression; obtaining current prediction data of the target prefabricated part based on the model prediction relational expression and the association prediction relational expression; and triggering health state warning information of the target prefabricated part based on the current prediction data. The method has the effect of predicting the health condition of the component so as to find potential problems in advance.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of prefabricated component management, and in particular to an Internet of Things-based prefabricated component early warning method and system for assembled building buildings. Background Art

[0002] At present, with the development of prefabricated components for assembled buildings, the effective management methods for prefabricated components for assembled buildings have also developed rapidly. Among them, the comprehensive management method using Internet of Things technology combined with digital management platform is favored by most managers. The use of Internet of Things technology can realize the monitoring of the entire life cycle of prefabricated components, and combined with monitoring data and digital management platform, it can optimize the production of prefabricated components for assembled buildings and improve economic benefits.

[0003] In related technologies, the digital management platform for prefabricated components is usually connected to the Internet of Things data to monitor prefabricated components through digital means. However, this type of monitoring method can often only be discovered after the status of the prefabricated components has problems. There is a lack of prediction of the health status of prefabricated components, making it difficult to discover potential problems in advance. Summary of the invention

[0004] In order to predict the health status of components and discover potential problems in advance, the present application provides an early warning method and system for prefabricated components of assembled buildings based on the Internet of Things.

[0005] In the first aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: Based on the preset IoT data classification information, the IoT data obtained by monitoring the target prefabricated components is classified and input into the corresponding combined learning model; Based on the combined learning model, a corresponding model prediction relationship and an associated prediction relationship are obtained; Based on the model prediction relationship and the associated prediction relationship, respectively, obtaining current prediction data of the target prefabricated component; A health status warning message of the target prefabricated component is triggered based on the current prediction data.

[0006] By adopting the above technical solution, in the process of running the digital management platform, the data detected by the Internet of Things devices used to monitor the target prefabricated components are transmitted to the digital management platform by wireless or wired means. The Internet of Things devices can be positioning tags installed on the target prefabricated components, video monitoring equipment that monitors the production process of the target prefabricated components, and environmental sensors used to monitor the environmental parameters of the target prefabricated components. Different Internet of Things data formats and forms are different. Therefore, the data of the Internet of Things devices are input into the corresponding combined learning model to facilitate more accurate learning of the characteristics of the target prefabricated components at different stages, thereby achieving more accurate predictions; the model prediction relationship refers to a relationship for predicting the health status of the target prefabricated components using the Internet of Things data at the current stage, and the association prediction relationship refers to a relationship for predicting the health status of the target prefabricated components using the Internet of Things data at multiple stages. Therefore, through the model prediction relationship and the association prediction relationship, real-time monitoring and prediction of the target prefabricated components are achieved, and the accuracy of the prediction is improved to discover potential problems in advance.

[0007] In a preferred example, the present application can be further configured as follows: the IoT data classification information is obtained by: Based on a preset component full process cycle, the Internet of Things data is classified to obtain Internet of Things classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

[0008] By adopting the above technical solution, the preset component full process cycle refers to the full process cycle of prefabricated components from design to installation and use, wherein the component full process cycle includes the conceptual design stage, structural design stage, production preparation stage, production manufacturing stage, quality inspection stage, component packaging stage, component transportation stage, on-site installation stage, on-site inspection stage and operation and maintenance stage. Therefore, the IoT data of IoT devices are classified into different stages to avoid data confusion, and at the same time, the data of different stages divided by time are analyzed to facilitate prediction.

[0009] In a preferred example, the present application can be further configured as follows: the combined learning model is obtained by: Acquire historical IoT data obtained by monitoring prefabricated components, identify the historical IoT data, and distribute inputs to multiple independent learning models; Based on the historical IoT data, a temporal-spatial model is generated; The time-domain spatial model and the multi-path independent learning models are combined to obtain a combined learning model.

[0010] By adopting the above technical scheme, before the production of a new batch of target prefabricated components of new specifications begins each time, the IoT data monitored by the historical IoT devices are identified to determine whether a correct prediction can be made each time a problem occurs in the health status of the actual target prefabricated components, and whether the IoT data collected for prediction is associated with the problem in the health status of the target prefabricated components, that is, whether the correct data is input into the learning model. Thus, a learning model with a high prediction accuracy corresponding to different stages is selected, and IoT data collected when the prediction accuracy is high at different stages is set. Appropriate learning models are allocated to different stages, and a time-domain space model is generated based on different stages of the entire process cycle of the component. The time-domain space model is based on the time sequence and performs corresponding learning and analysis on the IoT data input at different stages, so as to realize the prediction of the health status of the component.

[0011] In a preferred example, the present application may be further configured as follows: based on the combined learning model, obtaining the corresponding model prediction relationship and the associated prediction relationship specifically includes: Based on the multiple independent learning models in the combined learning model, obtaining a multi-path learning result; Based on the time-domain spatial model and the multi-path learning results in the combined learning model, a model prediction relationship and an associated prediction relationship are obtained.

[0012] By adopting the above technical solution, the multi-path learning result refers to the result of multiple learning models learning the IoT data at different stages. For example, the multi-path learning result in the production preparation stage refers to the learning result of the multiple independent learning models corresponding to the production preparation stage. Therefore, in each stage, the corresponding multi-path learning results are used to generate a model prediction relationship for predicting the health status of the target prefabricated component based on the IoT data at the current stage, and an associated prediction relationship for predicting the health status of the target prefabricated component by combining the IoT data at the current stage and the subsequent stages. In this way, the accuracy of the prediction is improved through the double prediction of the model prediction relationship and the associated prediction relationship, so as to discover potential problems in advance.

[0013] In a preferred example, the present application can be further configured as follows: the model prediction relationship includes a current stage critical threshold, the associated prediction relationship includes an associated stage critical threshold, the current stage critical threshold is greater than the associated stage critical threshold, and the current prediction data of the target prefabricated component is obtained based on the model prediction relationship and the associated prediction relationship, respectively, specifically including: The Internet of Things data is compared with the current stage critical threshold of the model prediction relationship and the associated stage critical threshold of the associated prediction relationship to obtain the current prediction data of the target prefabricated component.

[0014] By adopting the above technical solution, the corresponding model prediction relationship and the associated prediction relationship include the current stage critical threshold and the associated stage critical threshold respectively. The current stage critical threshold is used to judge the health status of the target prefabricated component in the current stage, while the associated stage critical threshold is used to judge the health status of the target prefabricated component in the subsequent stage. The current stage critical threshold is not less than the associated stage critical threshold because the current stage critical threshold only relies on the IoT data of the current stage, while the associated stage critical threshold needs to combine the IoT data of the current stage and the subsequent stage. Therefore, the associated prediction relationship corresponding to the associated stage critical threshold requires a larger amount of data. Generally, the prediction result of the associated prediction relationship will be more accurate. However, in order to ensure the advance nature of the prediction and the accuracy of the prediction at the current stage, the current stage critical threshold with a smaller amount of data is not less than the associated stage critical threshold, so as to improve the accuracy of the prediction data at the current stage.

[0015] In the second aspect, the above invention objective of the present application is achieved through the following technical solutions: An Internet of Things-based prefabricated building component early warning system, the Internet of Things-based prefabricated building component early warning system comprising: A combined learning model updating module is used to classify the IoT data obtained by monitoring the target prefabricated component based on preset IoT data classification information, and input the data into the corresponding combined learning model; A relational expression acquisition module, used to obtain corresponding model prediction relational expressions and associated prediction relational expressions based on the combined learning model; A current prediction data acquisition module, used to acquire the current prediction data of the target prefabricated component based on the model prediction relationship and the associated prediction relationship respectively; A health status warning instruction module is used to trigger health status warning information of the target prefabricated component based on the current prediction data.

[0016] Optionally, the prefabricated component early warning system for assembled buildings based on the Internet of Things further includes: The IoT classification data acquisition module is used to classify IoT data based on a preset component full process cycle to obtain IoT classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

[0017] Optionally, the prefabricated component early warning system for assembled buildings based on the Internet of Things further includes: A multi-channel learning model distribution module is used to obtain historical IoT data obtained by monitoring prefabricated components, identify the historical IoT data, and distribute the input to multiple independent learning models; A time-domain spatial model generation module, used to generate a time-domain spatial model based on the historical IoT data; The combined learning model combination module is used to combine the time-domain spatial model and the multiple independent learning models to obtain a combined learning model.

[0018] In the third aspect, the above invention objective of the present application is achieved through the following technical solutions: A computer device comprises a memory, a processor and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the above-mentioned method for early warning of prefabricated components of assembled buildings based on the Internet of Things are implemented.

[0019] In a fourth aspect, the above-mentioned invention objective of the present application is achieved through the following technical solutions: A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for early warning of prefabricated components of assembled buildings based on the Internet of Things.

[0020] In summary, the present application includes at least one of the following beneficial technical effects: 1. In the process of running the digital management platform, the data detected by the IoT devices used to monitor the target prefabricated components are transmitted to the digital management platform by wireless or wired means. The IoT devices can be positioning tags installed on the target prefabricated components, video monitoring devices that monitor the production process of the target prefabricated components, and environmental sensors used to monitor the environmental parameters of the target prefabricated components. Different IoT data formats and forms are different. Therefore, the data of the IoT devices are input into the corresponding combined learning model to facilitate more accurate learning of the characteristics of the target prefabricated components at different stages, thereby achieving more accurate predictions; the model prediction relationship refers to a relationship that uses the IoT data of the current stage to predict the health status of the target prefabricated components, and the association prediction relationship refers to a relationship that uses the IoT data of multiple stages to predict the health status of the target prefabricated components. Therefore, through the model prediction relationship and the association prediction relationship, real-time monitoring and prediction of the target prefabricated components are achieved, and the accuracy of the prediction is improved to discover potential problems in advance; 2. The preset component full process cycle refers to the full process cycle of prefabricated components from design to installation and use, where the component full process cycle includes the conceptual design stage, structural design stage, production preparation stage, production manufacturing stage, quality inspection stage, component packaging stage, component transportation stage, on-site installation stage, on-site inspection stage and operation and maintenance stage. Therefore, the IoT data of IoT devices are classified into different stages to avoid data confusion, and the data of different stages divided by time are analyzed to facilitate prediction; 3. Before the production of a new batch of target prefabricated components of new specifications begins each time, the IoT data monitored by historical IoT devices is identified to determine whether it can be correctly predicted each time there is a problem with the health status of the actual target prefabricated components, and whether the IoT data collected for prediction is related to the problem with the health status of the target prefabricated components, that is, whether the correct data is input into the learning model. In this way, a learning model with a high prediction accuracy corresponding to different stages is selected, and IoT data collected when the prediction accuracy is high at different stages is set. Appropriate learning models are allocated to different stages, and a time-domain space model is generated based on the different stages of the entire process cycle of the component. The time-domain space model is based on the time sequence and performs corresponding learning and analysis on the IoT data input at different stages, so as to realize the prediction of the health status of the component. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] Figure 1 This is a flowchart of an implementation of an early warning method for prefabricated components of assembled buildings based on the Internet of Things in an embodiment of the present application; Figure 2 It is a flowchart of the implementation of the method for obtaining IoT data classification information in the embodiment of the present application; Figure 3 It is a flowchart of the method for obtaining the combined learning model in the embodiment of the present application; Figure 4 It is a flowchart for implementing S20 of the prefabricated component early warning method for assembled buildings based on the Internet of Things in an embodiment of the present application; Figure 5 It is a flowchart for realizing S30 of the prefabricated component early warning method for assembled buildings based on the Internet of Things in the embodiment of the present application; Figure 6 It is a principle block diagram of an early warning system for prefabricated components of assembled buildings based on the Internet of Things in an embodiment of the present application; Figure 7 It is an internal structure diagram of an Internet of Things-based prefabricated building component early warning computer device in an embodiment of the present application. DETAILED DESCRIPTION

[0022] The following is combined with Figure 1-7 This application is described in further detail.

[0023] In one embodiment, if Figure 1 As shown, the present application discloses an early warning method for prefabricated components of assembled buildings based on the Internet of Things, which specifically includes the following steps: S10: Based on the preset IoT data classification information, the IoT data obtained by monitoring the target prefabricated components is classified and input into the corresponding combined learning model.

[0024] In this embodiment, a digital management platform is used to collect data detected by an IoT device used to monitor a target prefabricated component. The target prefabricated component is a prefabricated concrete component. The IoT device includes a positioning tag installed on the target prefabricated component, a video surveillance device for monitoring the production process of the target prefabricated component, and an environmental sensor for monitoring the environmental parameters of the target prefabricated component. The IoT data refers to the data detected and acquired by the IoT device. The digital management platform is also used to obtain other data and information of the non-IoT device detection data of the target prefabricated component. The acquisition method can be associated with other systems, such as the target prefabricated component design system and the target prefabricated component three-dimensional building information model. IoT data classification information refers to IoT data acquired at different stages of the entire life cycle of the target prefabricated component. A combined learning model refers to a learning model used to predict the health status of a target prefabricated component.

[0025] Specifically, in the process of running the digital management platform, the data detected by the IoT devices used to monitor the target prefabricated components are transmitted to the digital management platform by wireless or wired means. For example, the IoT data of the video surveillance equipment in the production stage of the target prefabricated components can be transmitted to the digital management platform by wired means, and the IoT data of the positioning tags in the transportation stage can be transmitted to the digital management platform by wireless means. The preset IoT data classification information is the classification information of the data obtained by different IoT devices and different systems at different time points according to the different stages of the full life cycle of the target prefabricated components. Therefore, in the process of running the digital management platform, based on the IoT data classification information, the IoT data of the target prefabricated components monitored by different IoT devices at different time points and the data obtained by different systems are classified and input into the corresponding combined learning model. The combined learning model refers to a learning model used to predict the health status of the target prefabricated components. The combined learning model refers to a big data model that can perform autonomous learning to achieve prediction tasks. Therefore, continuously inputting IoT data to train the combined learning model can improve the prediction accuracy of the combined learning model.

[0026] S20: Based on the combined learning model, obtain the corresponding model prediction relationship and the associated prediction relationship.

[0027] In this embodiment, the model prediction relationship refers to a relationship used to predict the health status of the target prefabricated component based on the IoT data of the current stage. The association prediction relationship refers to a relationship used to predict the health status of the target prefabricated component by combining the IoT data of the current stage and the subsequent stage.

[0028] Specifically, the combined learning model refers to a big data model that can perform autonomous learning to achieve prediction tasks. Before the combined learning model is put into use, it has been trained and learned with a large amount of data and has the prediction ability. Therefore, when the Internet of Things data is input into the combined learning model, that is, when the Internet of Things data obtained in the corresponding stage is input into the combined learning model, according to the specific time point and data content in the Internet of Things data, the combined learning model is used to generate a relationship corresponding to the specific time point for predicting the health status of the target prefabricated component based on the data content, that is, the model prediction relationship. For example, in the production stage of the target prefabricated component, the Internet of Things data includes a specific time point, and the data content is the video data of the video surveillance device. Therefore, the generated model prediction relationship is a relationship for predicting the health status of the target prefabricated component by judging the state of the target prefabricated component in each frame of the video data. For example, based on the information in each frame of the video data such as the integrity of the surface coating of the target prefabricated component, whether there are cracks on the surface of the target prefabricated component, or whether the size of the target prefabricated component is normal, when the integrity of the surface coating of the target prefabricated component is less than the corresponding threshold, there are cracks on the surface of the target prefabricated component, or the size of the target prefabricated component is abnormal, the model is used to predict the health status of the target prefabricated component. The prediction relationship predicts that the health state of the target prefabricated component is poor; in addition, through the combined learning model, a relationship formula for predicting the health state of the target prefabricated component by combining the current Internet of Things data and the subsequent Internet of Things data, that is, the associated prediction relationship formula, is generated. For example, in the production stage of the target prefabricated component, the Internet of Things data includes a specific time point, and the data content is the video data of the video surveillance device. Therefore, the generated associated prediction relationship formula is a relationship formula for predicting the health state of the target prefabricated component through the state of the target prefabricated component in each frame of the current video data and the Internet of Things data in the subsequent stage. For example, based on the information in each frame of the video data such as the integrity of the surface coating of the target prefabricated component, whether there are cracks on the surface of the target prefabricated component, or whether the size of the target prefabricated component is normal, when the integrity of the surface coating of the target prefabricated component is less than the corresponding threshold, cracks exist on the surface of the target prefabricated component, or the size of the target prefabricated component is abnormal, and in the subsequent quality inspection stage, it is detected that the integrity of the surface coating of the target prefabricated component is further reduced, the surface of the target prefabricated component still has cracks or is further reduced, and the size of the target prefabricated component is still abnormal, the associated prediction relationship formula predicts that the health state of the target prefabricated component is poor. It should be noted that the prediction conditions of the model prediction relationship are generally greater than the prediction conditions of the association prediction relationship.

[0029] S30: Acquire current prediction data of the target prefabricated component based on the model prediction relationship and the associated prediction relationship.

[0030] In this embodiment, the current prediction data refers to the prediction results of the model prediction relationship and the associated prediction relationship.

[0031] Specifically, at different stages of the target prefabricated component, the IoT data at the corresponding time point is input into the corresponding model prediction relationship and the associated prediction relationship. The output results of the model prediction relationship and the associated prediction relationship are the current prediction data of the health status of the predicted target prefabricated component.

[0032] S40: triggering health status warning information of the target prefabricated component based on the current prediction data.

[0033] In this embodiment, the component health status warning information refers to information used to indicate that the health status of the target prefabricated component is poor.

[0034] Specifically, based on the current prediction data, if the current prediction data indicates that the corresponding Internet of Things data satisfies the conditions of the model prediction relationship and / or the associated prediction relationship, it is predicted that the health status of the target prefabricated component is poor. Therefore, information indicating that the health status of the target prefabricated component is poor is sent to the monitoring management end that monitors the status of the target prefabricated component, thereby triggering a component health status warning message.

[0035] In one embodiment, if Figure 2 As shown in the figure, IoT data classification information is obtained through the following methods: S01: Based on the preset component full process cycle, the IoT data is classified to obtain IoT classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

[0036] Specifically, the preset component full process cycle refers to the full process cycle of prefabricated components from design to installation and use. In the present embodiment, the component full process cycle includes the conceptual design stage, the structural design stage, the production preparation stage, the manufacturing stage, the quality inspection stage, the component packaging stage, the component transportation stage, the on-site installation stage, the on-site inspection stage and the operation and maintenance stage. Therefore, the IoT data is classified accordingly, and the obtained IoT classified data includes: conceptual design stage data, structural design stage data, production preparation stage IoT data, manufacturing stage IoT data, quality inspection stage IoT data, component packaging stage IoT data, component transportation stage IoT data, on-site installation stage IoT data, on-site inspection stage and operation and maintenance stage IoT data.

[0037] It should be noted that the conceptual design stage data and the structural design stage data are the data of the design stage of prefabricated components. Therefore, they are not obtained through IoT devices, but through the prefabricated component design system associated with the digital management platform. Since the conceptual design stage data and the structural design stage data are not obtained through IoT devices, the conceptual design stage data and the structural design stage data are mainly used to provide learning to the machine learning model, that is, the machine learning model learns the conceptual design stage data and the structural design stage data when predicting the health status of the prefabricated components. After the prefabricated component production stage begins, when the digital management platform is used, the conceptual design stage data and the structural design stage data are input into the digital management platform, so as to predict whether there is a problem with the health status of the current prefabricated components based on the conceptual design stage data and the structural design stage data.

[0038] In one embodiment, if Figure 3 As shown, the combined learning model is obtained in the following way: S02: Acquire historical IoT data obtained from monitoring prefabricated components, identify the historical IoT data, and distribute the input to multiple independent learning models.

[0039] In this embodiment, historical IoT data refers to IoT data acquired historically. Multiple independent learning models refer to several different independent machine learning models.

[0040] Specifically, a plurality of different independent machine learning models are built in the digital management platform. Before each production of a new batch of prefabricated components of new specifications begins, the IoT data obtained by monitoring the prefabricated components through historical IoT devices, i.e., historical IoT data, is obtained. The historical IoT data is identified and analyzed to determine the prediction accuracy of different machine learning models when problems with the health status of the actual historical prefabricated components occur. The prediction accuracy of the IoT data is also determined, and whether the IoT data collected is associated with the health status problems of the prefabricated components, i.e., whether the correct IoT data is input into the machine learning model. In this way, the machine learning models with prediction accuracy higher than the average at different stages are divided. Among the machine learning models with prediction accuracy higher than the average at different stages, the machine learning models with prediction accuracy higher than the average are further divided. The divided machine learning models are used as multi-path independent learning models. It should be noted that the purpose of continuing to divide the machine learning model that predicts and associates the collected IoT data with the problems in the health status of prefabricated components is that, in the actual operation of the digital management platform, there may be a situation where the IoT data collected by the machine learning model are not associated with the problems in the health status of prefabricated components, that is, the IoT data collected by the machine learning model and the data corresponding to the problems causing the health status of the prefabricated components are not the same data. Therefore, dividing the machine learning model that predicts and associates the collected IoT data with the problems in the health status of prefabricated components is conducive to improving the accuracy of the prediction and reducing the situation where the collected IoT data is not the required data.

[0041] S03: Generate a temporal-spatial model based on historical IoT data.

[0042] In this embodiment, the time-domain spatial model refers to a model formed by arranging multiple independent learning models in a time sequence of different stages.

[0043] Specifically, the route of movement of prefabricated components is determined based on historical IoT data, and the route is divided into multiple coordinate points (i.e., coordinate points in the same coordinate system as the data of the positioning tags installed on the prefabricated components). Based on the different stages of the entire life cycle of the prefabricated components and the coordinate points, a spatial model based on time and place is formed, thereby forming a time-domain spatial model.

[0044] S04: Combine the time-domain spatial model and the multi-path independent learning models to obtain a combined learning model.

[0045] Specifically, the data input and output ports of multiple independent learning models corresponding to different stages are associated with the corresponding positions of the time-domain space model to form a combined learning model. For example, the different stages of the entire life cycle of the prefabricated components are used as the vertical axis, and the coordinate points formed by the routes of movement of the prefabricated components are used as the horizontal axis to form a matrix of output results of multiple independent learning models. When the multiple independent learning models output results, the output results are displayed at the corresponding positions.

[0046] In one embodiment, if Figure 4 As shown, in step S20, based on the combined learning model, the corresponding model prediction relationship and the associated prediction relationship are obtained, which specifically include: S21: Based on the multiple independent learning models in the combined learning model, a multi-path learning result is obtained.

[0047] In this embodiment, the multi-path learning results refer to the learning results of multiple independent learning models.

[0048] Specifically, when IoT data is input into a multi-channel independent learning model, the IoT data is identified, the current time point is determined, and based on the current time point, the first IoT data factor that will cause problems with the health status of the target prefabricated component at the current time point is determined through the learning function of the multi-channel independent learning model, as well as the corresponding threshold for predicting problems with the health status of the target prefabricated component, and the content corresponding to the first IoT data factor in the data content of the IoT data is extracted. If the data content of the IoT data does not contain content corresponding to the first IoT data factor, the multi-channel learning result has no content. In addition, the second IoT data factor that will cause problems with the health status of the target prefabricated component in combination with the current time point and subsequent IoT data is determined, as well as the corresponding thresholds corresponding to the current IoT data and subsequent IoT data for predicting problems with the health status of the target prefabricated component, and the data content of the IoT data is extracted. In the data content of the Internet of Things data, the content corresponding to the second Internet of Things data factor is obtained. Similarly, if there is no content corresponding to the second Internet of Things data factor in the data content of the Internet of Things data, the multi-path learning result has no content. In this way, the first Internet of Things data factor that will cause problems in the health status of the target prefabricated component at the current time point, the threshold value corresponding to the first Internet of Things data factor for predicting problems in the health status of the target prefabricated component, the content corresponding to the first Internet of Things data factor in the data content of the Internet of Things data, the second Internet of Things data factor that will cause problems in the health status of the target prefabricated component combined with the current time point and subsequent Internet of Things data, the threshold value corresponding to the second Internet of Things data factor for predicting problems in the health status of the target prefabricated component, and the content corresponding to the second Internet of Things data factor in the data content of the Internet of Things data are associated to obtain the multi-path learning result corresponding to the current time point.

[0049] S22: Based on the time-domain spatial model and multi-path learning results in the combined learning model, a model prediction relationship and an associated prediction relationship are obtained.

[0050] Specifically, based on the multi-path learning results in the time-domain space model, that is, the learning results of multiple independent learning models, the learning results of each machine learning model are used to form a model prediction relationship, and the first Internet of Things data factor in the learning results of each machine learning model that will cause problems with the health status of the target prefabricated component at the current time point, the threshold value corresponding to the first Internet of Things data factor for predicting problems with the health status of the target prefabricated component, and the content corresponding to the first Internet of Things data factor in the data content of the Internet of Things data are extracted to form a model prediction relationship, and then the second Internet of Things data factor in the learning results of each machine learning model that will cause problems with the health status of the target prefabricated component at the current time point and subsequent Internet of Things data, the threshold value corresponding to the second Internet of Things data factor for predicting problems with the health status of the target prefabricated component, and the content corresponding to the second Internet of Things data factor in the data content of the Internet of Things data are extracted to form an associated prediction relationship.

[0051] Furthermore, since the conceptual design stage data and the structural design stage data are not obtained through IoT devices, the conceptual design stage data and the structural design stage data are mainly used to provide to the machine learning model for learning, that is, the conceptual design stage data and the structural design stage data when problems occur in predicting the health status of the target prefabricated components, as well as the IoT data of the subsequent stages, are learned through the machine learning model to generate the correlation prediction relationship between the conceptual design stage data and the structural design stage data and the IoT data of the subsequent stages.

[0052] In one embodiment, if Figure 5 As shown, in step S30, the model prediction relationship includes the current stage critical threshold, the associated prediction relationship includes the associated stage critical threshold, the current stage critical threshold is greater than the associated stage critical threshold, and the current prediction data of the target prefabricated component is obtained based on the model prediction relationship and the associated prediction relationship, specifically including: S31: Compare the IoT data with the current stage critical threshold of the model prediction relationship and the associated stage critical threshold of the associated prediction relationship to obtain the current prediction data of the target prefabricated component.

[0053] In this embodiment, the critical threshold value of the current stage refers to the threshold value in the model prediction relationship used to predict that the health state of the target prefabricated component has problems. The critical threshold value of the associated stage refers to the threshold value in the associated prediction relationship used to predict that the health state of the target prefabricated component has problems. The model prediction relationship includes a threshold value for predicting that the health state of the target prefabricated component has problems, that is, the critical threshold value of the current stage. Similarly, the associated prediction relationship also includes a threshold value for predicting that the health state of the target prefabricated component has problems, that is, the critical threshold value of the associated stage. Since the critical threshold value of the current stage only relies on the IoT data of the current stage, and the critical threshold value of the associated stage needs to be combined with the IoT data of the current stage and the subsequent stage, the associated prediction relationship corresponding to the critical threshold value of the associated stage requires a larger amount of data, so the prediction result of the general associated prediction relationship will be more accurate, but in order to ensure the advance of the prediction and the accuracy of the prediction at the current stage, the critical threshold value of the current stage with a smaller amount of data is not less than the critical threshold value of the associated stage.

[0054] Specifically, the data corresponding to the critical threshold of the current stage and the critical threshold of the associated stage in the IoT data are compared with the critical threshold of the current stage and the critical threshold of the associated stage, and the comparison result is used as the current prediction data. That is, when the data corresponding to the critical threshold of the current stage is greater than the critical threshold of the current stage, it is predicted that there is a problem with the health status of the target prefabricated component; when the data corresponding to the critical threshold of the associated stage is greater than the critical threshold of the associated stage, it is predicted that there is a problem with the health status of the target prefabricated component.

[0055] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present application.

[0056] In one embodiment, an early warning system for prefabricated components of assembled buildings based on the Internet of Things is provided, and the early warning system for prefabricated components of assembled buildings based on the Internet of Things corresponds one-to-one to the early warning method for prefabricated components of assembled buildings based on the Internet of Things in the above-mentioned embodiment. Figure 6 As shown, the prefabricated component early warning system for prefabricated buildings based on the Internet of Things includes a combined learning model update module, a relational acquisition module, a current prediction data acquisition module, and a health status warning instruction module. The detailed description of each functional module is as follows: A combined learning model updating module is used to classify the IoT data obtained by monitoring the target prefabricated component based on preset IoT data classification information, and input the data into the corresponding combined learning model; A relational expression acquisition module is used to obtain corresponding model prediction relational expressions and associated prediction relational expressions based on the combined learning model; A current prediction data acquisition module is used to acquire the current prediction data of the target prefabricated component based on the model prediction relationship and the associated prediction relationship; The health status warning instruction module is used to trigger the health status warning information of the target prefabricated component based on the current prediction data.

[0057] Optionally, the IoT-based prefabricated building component early warning system also includes: The IoT classification data acquisition module is used to classify IoT data based on a preset component full process cycle to obtain IoT classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

[0058] Optionally, the IoT-based prefabricated building component early warning system also includes: A multi-channel learning model distribution module is used to obtain historical IoT data obtained by monitoring prefabricated components, identify the historical IoT data, and distribute the input to multiple independent learning models; A time-domain spatial model generation module is used to generate a time-domain spatial model based on historical IoT data; The combined learning model combination module is used to combine the time-domain space model and multiple independent learning models to obtain the combined learning model.

[0059] Optionally, the relational acquisition module includes: A multi-path learning result acquisition submodule is used to obtain multi-path learning results based on the multi-path learning model in the combined learning model; The relational expression acquisition submodule is used to obtain the model prediction relational expression and the associated prediction relational expression based on the time-domain spatial model and the multi-path learning results in the combined learning model.

[0060] Optionally, the model prediction relationship includes a current stage critical threshold, the associated prediction relationship includes an associated stage critical threshold, the current stage critical threshold is greater than the associated stage critical threshold, and the current prediction data acquisition module includes: The current prediction data acquisition submodule is used to compare the IoT data with the current stage critical threshold of the model prediction relationship and the associated stage critical threshold of the associated prediction relationship to obtain the current prediction data of the target prefabricated component.

[0061] For the specific definition of the prefabricated building component early warning system based on the Internet of Things, please refer to the definition of the prefabricated building component early warning method based on the Internet of Things above, which will not be repeated here. Each module in the above-mentioned prefabricated building component early warning system based on the Internet of Things can be implemented in whole or in part through software, hardware and their combination. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0062] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 7 As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store Internet of Things data classification information, combined learning models, model prediction relationships, associated prediction relationships, current prediction data and health status warning instructions, etc. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, an early warning method for prefabricated components of assembled buildings based on the Internet of Things is implemented.

[0063] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: Based on the preset IoT data classification information, the IoT data obtained by monitoring the target prefabricated components is classified and input into the corresponding combined learning model; Based on the combined learning model, the corresponding model prediction relationship and the associated prediction relationship are obtained; Based on the model prediction relationship and the associated prediction relationship, current prediction data of the target prefabricated component is obtained; The health status warning information of the target precast component is triggered based on the current prediction data.

[0064] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented: Based on the preset IoT data classification information, the IoT data obtained by monitoring the target prefabricated components is classified and input into the corresponding combined learning model; Based on the combined learning model, the corresponding model prediction relationship and the associated prediction relationship are obtained; Based on the model prediction relationship and the associated prediction relationship, current prediction data of the target prefabricated component is obtained; The health status warning information of the target precast component is triggered based on the current prediction data.

[0065] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be implemented by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0066] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the system can be divided into different functional units or modules to complete all or part of the functions described above.

[0067] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. An early warning method for prefabricated components of assembled buildings based on the Internet of Things, characterized in that: The prefabricated component early warning method for assembled buildings based on the Internet of Things includes: Based on the preset IoT data classification information, the IoT data obtained by monitoring the target prefabricated components is classified and input into the corresponding combined learning model; Based on the combined learning model, a corresponding model prediction relationship and an associated prediction relationship are obtained; Based on the model prediction relationship and the associated prediction relationship, respectively, obtaining current prediction data of the target prefabricated component; A health status warning message of the target prefabricated component is triggered based on the current prediction data.

2. The prefabricated component early warning method for assembled buildings based on the Internet of Things according to claim 1 is characterized in that: The IoT data classification information is obtained in the following manner: Based on a preset component full process cycle, the Internet of Things data is classified to obtain Internet of Things classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

3. The prefabricated component early warning method for assembled buildings based on the Internet of Things according to claim 1 is characterized in that: The combined learning model is obtained in the following way: Acquire historical IoT data obtained by monitoring prefabricated components, identify the historical IoT data, and distribute inputs to multiple independent learning models; Based on the historical IoT data, a temporal-spatial model is generated; The time-domain spatial model and the multi-path independent learning models are combined to obtain a combined learning model.

4. The prefabricated component early warning method for assembled buildings based on the Internet of Things according to claim 3 is characterized in that: The obtaining of the corresponding model prediction relationship and the associated prediction relationship based on the combined learning model specifically includes: Based on the multiple independent learning models in the combined learning model, obtaining a multi-path learning result; Based on the time-domain spatial model and the multi-path learning results in the combined learning model, a model prediction relationship and an associated prediction relationship are obtained.

5. The prefabricated component early warning method for assembled buildings based on the Internet of Things according to claim 1 is characterized in that: The model prediction relationship includes a current stage critical threshold, the associated prediction relationship includes an associated stage critical threshold, the current stage critical threshold is greater than the associated stage critical threshold, and the current prediction data of the target prefabricated component is obtained based on the model prediction relationship and the associated prediction relationship, specifically including: The Internet of Things data is compared with the current stage critical threshold of the model prediction relationship and the associated stage critical threshold of the associated prediction relationship to obtain the current prediction data of the target prefabricated component.

6. An early warning system for prefabricated components of assembled buildings based on the Internet of Things, characterized in that: The prefabricated component early warning system for assembled buildings based on the Internet of Things includes: A combined learning model updating module is used to classify the IoT data obtained by monitoring the target prefabricated component based on preset IoT data classification information, and input the data into the corresponding combined learning model; A relational expression acquisition module, used to obtain corresponding model prediction relational expressions and associated prediction relational expressions based on the combined learning model; A current prediction data acquisition module, used to acquire the current prediction data of the target prefabricated component based on the model prediction relationship and the associated prediction relationship respectively; A health status warning instruction module is used to trigger health status warning information of the target prefabricated component based on the current prediction data.

7. The prefabricated component early warning system for assembled buildings based on the Internet of Things according to claim 6 is characterized in that: The prefabricated building component early warning system based on the Internet of Things also includes: The IoT classification data acquisition module is used to classify IoT data based on a preset component full process cycle to obtain IoT classification data. The component full process cycle refers to the full process cycle of prefabricated components from design to installation and use.

8. The prefabricated component early warning system for assembled buildings based on the Internet of Things according to claim 6 is characterized in that: The prefabricated building component early warning system based on the Internet of Things also includes: A multi-channel learning model distribution module is used to obtain historical IoT data obtained by monitoring prefabricated components, identify the historical IoT data, and distribute the input to multiple independent learning models; A time-domain spatial model generation module, used to generate a time-domain spatial model based on the historical IoT data; The combined learning model combination module is used to combine the time-domain spatial model and the multiple independent learning models to obtain a combined learning model.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the prefabricated building component early warning method based on the Internet of Things as described in any one of claims 1 to 5 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by the processor, the steps of the early warning method for prefabricated components of assembled buildings based on the Internet of Things as described in any one of claims 1 to 5 are implemented.

Citation Information

Patent Citations

  • System and method for fault prediction and on-line evaluation of health state of marine diesel generator

    CN108520080A

  • Fabricated building construction safety monitoring system, method and device and medium

    CN111210365A

  • Bridge health monitoring method and system based on wireless sensor network

    CN114894411A

  • Whole sewage treatment process supervision method and system based on Internet of Things, and storage medium

    CN115578015A

  • Tunnel equipment facility state monitoring and early warning system based on machine learning

    CN116090591A