Building intelligent management method and system based on BIM technology
By constructing equipment operation and maintenance information in the BIM model and analyzing the equipment operation status with sensors and deep learning algorithms, the problems of poor information circulation and inaccurate fault diagnosis in building operation and maintenance management in the existing technology are solved, and intelligent display of equipment health status and fault warning are realized.
Patent Information
- Application Number
- CN202510443977.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-04-10
- Publication Date
- 2025-07-25
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
The existing BIM model-based building operation and maintenance management lacks dynamic integration and intelligent analysis capabilities for equipment operation status data, and it is difficult to achieve early warning of complex failure modes, resulting in poor information circulation, difficulty in coordination, inefficient equipment operation and maintenance, and inaccurate fault diagnosis.
Build a BIM model and enter the equipment operation and maintenance information, use the sensor group to collect operation status data in real time, combine deep learning algorithms to perform feature extraction and interactive response analysis, explore potential failure modes, and display the equipment health status through color coding.
It improves the operation and maintenance efficiency of construction equipment and the accuracy of fault diagnosis, promptly detects and warns of potential fault risks, and enhances the intelligence level of building management.
Smart Images

Figure BDA0005351973890000121 
Figure BDA0005351973890000122 
Figure BDA0005351973890000123
Abstract
Description
Technical Field
[0001] This application relates to the field of intelligent management technologies, and more specifically, to a building intelligent management method and system based on BIM technology. Background Art
[0002] In today's construction industry, with the acceleration of urbanization and the continuous improvement of people's requirements for building functions and quality, building scales are increasingly large and structures are becoming more complex. When facing such complex building systems, the traditional building management mode gradually exposes many drawbacks, such as poor information circulation, difficult collaboration among various participants, low efficiency of equipment operation and maintenance, and difficulty in realizing real-time and effective fault diagnosis and early warning. These have seriously restricted the efficient development and sustainable operation of the construction industry.
[0003] Building Information Modeling (BIM) technology has emerged as the basis for the digital transformation of the architecture, engineering, and construction (AEC) industry, bringing new ideas and methods for the whole life cycle management of buildings. Based on an intelligent model supported by a remote platform, BIM technology can integrate structured, multi-domain data together to generate a digital representation of building assets throughout the whole life cycle from planning, design, construction to operation. Through the BIM model, various participants can achieve real-time information sharing and collaborative work, greatly improving the transparency and collaborative efficiency of building projects.
[0004] However, current research on building operation and maintenance management based on BIM models mainly focuses on three-dimensional visualization display and basic information management levels, lacking the ability of dynamic integration and intelligent analysis of equipment operation status data. Currently, for the fault diagnosis of building equipment, threshold alarms or simple statistical analysis are mostly used, which are difficult to effectively process multi-source heterogeneous real-time monitoring data and even more unable to realize early warning of complex fault modes.
[0005] Therefore, an optimized building intelligent management method and system based on BIM technology are expected. Summary of the Invention
[0006] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a method and system for intelligent building management based on BIM technology, which first constructs a BIM model of the building, and enters the equipment operation and maintenance information of the building equipment into the BIM model, and uses a sensor group to collect the operation status data of the building equipment in real time, and then introduces a deep learning algorithm, and performs feature extraction and deep interactive response analysis on the real-time operation status data and historical operation and maintenance information of the building equipment, so as to combine the historical operation and maintenance data and real-time status of the equipment to dig out the potential failure mode of the equipment, thereby realizing intelligent fault diagnosis of the building equipment, and intuitively displaying the health status of the equipment through color coding in the BIM model. In this way, the operation and maintenance efficiency and fault diagnosis accuracy of the building equipment can be improved, potential fault risks can be discovered and warned in a timely manner, and the intelligent level of building management can be enhanced.
[0007] According to one aspect of the present application, a building intelligent management method based on BIM technology is provided, which includes:
[0008] Construct a BIM model of the building and enter the equipment operation and maintenance information of the building equipment into the BIM model, wherein the equipment operation and maintenance information includes basic information, technical parameters, and historical maintenance records of the equipment;
[0009] Using a sensor group to collect a time series of operating status data of the building equipment in real time, the operating status data including temperature, current and power;
[0010] The time series of the operation status data and the equipment operation and maintenance information in the BIM model are transmitted to the remote monitoring center of building equipment for in-depth interactive analysis to determine the fault diagnosis result of the building equipment, wherein the in-depth interactive analysis of the time series of the operation status data and the equipment operation and maintenance information includes: performing operation status-historical operation and maintenance information interactive response reasoning based on local feature association on the time series of the operation status data and the equipment operation and maintenance information to obtain the fault diagnosis result;
[0011] Based on the fault diagnosis results, the health status of the building equipment is dynamically displayed in the BIM model with color coding.
[0012] According to another aspect of the present application, a building intelligent management system based on BIM technology is provided, which includes:
[0013] A BIM model building module, used to build a BIM model of a building and enter the equipment operation and maintenance information of the building equipment into the BIM model, wherein the equipment operation and maintenance information includes basic information, technical parameters, and historical maintenance records of the equipment;
[0014] The operating status data acquisition module is used to collect the time series of the operating status data of the building equipment in real time by using the sensor group. The operating status data includes temperature, current, and power.
[0015] The fault diagnosis and analysis module is used to transmit the time series of the operating status data and the equipment operation and maintenance information in the BIM model to the building equipment remote monitoring center for in-depth interaction analysis to determine the fault diagnosis result of the building equipment. Among them, the in-depth interaction analysis of the time series of the operating status data and the equipment operation and maintenance information includes: performing an operating status-historical operation and maintenance information interaction response inference based on local feature association on the time series of the operating status data and the equipment operation and maintenance information to obtain the fault diagnosis result.
[0016] The health status visualization module is used to dynamically display the health status of the building equipment in the BIM model with color coding based on the fault diagnosis result.
[0017] Compared with the prior art, the building intelligent management method and system based on the BIM technology provided by this application first constructs the BIM model of the building, enters the equipment operation and maintenance information of the building equipment into the BIM model, and at the same time uses the sensor group to collect the operating status data of the building equipment in real time. Furthermore, a deep learning algorithm is introduced, and through feature extraction and in-depth interaction response analysis of the real-time operating status data and historical operation and maintenance information of the building equipment, the potential fault modes of the equipment are mined by combining the historical operation and maintenance data and real-time status of the equipment, so as to realize the intelligent fault diagnosis of the building equipment, and the health status of the equipment is intuitively displayed in the BIM model with color coding. In this way, the operation and maintenance efficiency and fault diagnosis accuracy of the building equipment can be improved, potential fault risks can be discovered and warned in time, and the intelligent level of building management can be enhanced. Description of the Drawings
[0018] By describing the embodiments of the present application in more detail in conjunction with the drawings, the above and other objects, features, and advantages of the present application will become more obvious. The drawings are used to provide a further understanding of the embodiments of the present application, and constitute a part of the specification. Together with the embodiments of the present application, they are used to explain the present application and do not constitute a limitation to the present application. In the drawings, the same reference numerals generally represent the same components or steps.
[0019] Figure 1 It is a flowchart of the building intelligent management method based on the BIM technology according to the embodiment of the present application.
[0020] Figure 2 It is a flowchart of the sub-step S3 of the building intelligent management method based on the BIM technology according to the embodiment of the present application.
[0021] Figure 3 Schematic diagram of data flow for sub-step S3 of the building intelligent management method based on BIM technology according to an embodiment of the present application.
[0022] Figure 4 Flowchart of sub-step S33 of the building intelligent management method based on BIM technology according to an embodiment of the present application.
[0023] Figure 5 Flowchart of sub-step S332 of the building intelligent management method based on BIM technology according to an embodiment of the present application.
[0024] Figure 6 Block diagram of the building intelligent management system based on BIM technology according to an embodiment of the present application. Detailed implementation manners
[0025] As shown in the present application and the claims, unless the context clearly indicates otherwise, words such as "a", "an", "one" and / or "the" are not specifically singular and may also include plural. Generally speaking, the terms "comprising" and "including" only indicate the inclusion of the clearly identified steps and elements, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.
[0026] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, however, any number of different modules can be used and run on the user terminal and / or server. The modules are only illustrative, and different aspects of the system and method can use different modules.
[0027] In the present application, flowcharts are used to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the operations before or below do not necessarily need to be executed precisely in sequence. On the contrary, as needed, various steps can be executed in reverse order or simultaneously. At the same time, other operations can also be added to these processes, or one or several steps can be removed from these processes.
[0028] Next, exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments of the present application. It should be understood that the present application is not limited by the exemplary embodiments described here.
[0029] It should be noted that in the present application, all actions of obtaining data are carried out on the premise of complying with the corresponding data protection regulations and policies of the country where the location is located and obtaining the authorization given by the owner of the corresponding device.
[0030] In response to the technical problems described in the above background technology, this application proposes a method for intelligent building management based on BIM technology, which first constructs a BIM model of the building, and enters the equipment operation and maintenance information of the building equipment into the BIM model, and uses a sensor group to collect the operating status data of the building equipment in real time, and then introduces a deep learning algorithm, through the real-time operation status data and historical operation and maintenance information of the building equipment Feature extraction and deep interactive response analysis, in order to combine the historical operation and maintenance data and real-time status of the equipment, to dig out the potential failure mode of the equipment, thereby realizing intelligent fault diagnosis of the building equipment, and intuitively displaying the health status of the equipment through color coding in the BIM model. In this way, the operation and maintenance efficiency of the building equipment and the accuracy of fault diagnosis can be improved, potential fault risks can be discovered and warned in a timely manner, and the level of intelligent building management can be enhanced.
[0031] Figure 1 Flowchart of the intelligent building management method based on BIM technology according to an embodiment of the present application. Figure 1 As shown, the intelligent building management method based on BIM technology includes the following steps: S1, constructing a BIM model of a building, and entering the equipment operation and maintenance information of the building equipment into the BIM model, wherein the equipment operation and maintenance information includes basic information, technical parameters, and historical maintenance records of the equipment; S2, using a sensor group to collect the time series of the operating status data of the building equipment in real time, wherein the operating status data includes temperature, current, and power; S3, transmitting the time series of the operating status data and the equipment operation and maintenance information in the BIM model to a remote monitoring center for building equipment for deep interactive analysis to determine the fault diagnosis result of the building equipment, wherein the deep interactive analysis of the time series of the operating status data and the equipment operation and maintenance information includes: performing an interactive response reasoning of the operating status-historical operation and maintenance information based on local feature association on the time series of the operating status data and the equipment operation and maintenance information to obtain the fault diagnosis result; S4, based on the fault diagnosis result, dynamically displaying the health status of the building equipment in the BIM model with color coding.
[0032] In the above building intelligent management method based on BIM technology, in step S1, a BIM model of the building is constructed, and the equipment operation and maintenance information of the building equipment is input into the BIM model. The equipment operation and maintenance information includes the basic information, technical parameters, and historical maintenance records of the equipment. It should be understood that the current application of BIM models in the operation and maintenance stage is mostly limited to static information display. Equipment operation and maintenance data (such as historical maintenance records and technical parameters) are usually scattered in paper documents or independent systems, forming information silos. By structuring and inputting the equipment operation and maintenance information into the BIM model, this application can provide a unified data carrier for subsequent equipment operation and maintenance management, and realize the spatial association of equipment full-life cycle information. In specific implementation, tools such as Revit and Archicad can be used to create a three-dimensional model including the building's geometric structure, spatial relationship, and equipment location. Then, in the model, define an attribute set (such as equipment number, model, rated power, design life, installation date) for each equipment object (such as air conditioning unit, water pump), and connect to the operation and maintenance management system through the API to automatically synchronize the historical maintenance records of the equipment (such as failure type, maintenance time, replaced parts).
[0033] Specifically, to ensure that the equipment operation and maintenance information can be accurately input into the BIM model, during the process of using Revit or Archicad to create a three-dimensional model including the building's geometric structure, spatial relationship, and equipment location, it is necessary to detail and record the relevant attribute sets of each equipment object, such as basic information and technical parameters like equipment number, model, rated power, and design life. In addition, the input of historical maintenance records is also crucial, which includes information on failure type, maintenance time, and replaced parts, in order to form a complete equipment life cycle file. By connecting to the existing operation and maintenance management system through the API interface, these data can be automatically synchronized, thereby reducing manual input errors and ensuring the real-time update and accuracy of the information.
[0034] In the specific implementation process, creating the BIM model of the building is not just simply establishing a three-dimensional structure diagram, but more importantly, defining a unique attribute set for each piece of equipment. This requires detailed classification and coding of each piece of equipment to ensure that all relevant information can be correctly identified and associated. For example, for key equipment such as air conditioning units or water pumps, not only the basic technical specifications need to be clarified, but also the specific details of each maintenance activity should be recorded in detail, so that more accurate judgments can be made based on the complete historical data during subsequent analysis. At the same time, considering the possible differences between different projects, a certain degree of flexibility is also required when setting equipment attributes, allowing specific fields to be added or existing settings to be adjusted according to actual needs.
[0035] Furthermore, by using the BIM model as a unified data carrier, the equipment operation and maintenance data scattered in paper documents or independent systems can be centrally managed. This approach breaks the information silo phenomenon in the traditional sense and promotes the circulation and sharing of information. When all relevant data are integrated into the BIM model, managers can not only grasp the overall status of building equipment but also deeply explore the historical records of each equipment, which is of great significance for predicting potential future problems. For example, when analyzing the reasons for frequent failures of a certain equipment, potential design defects or improper operations can be identified by reviewing its previous maintenance records, and then targeted measures can be taken for improvement.
[0036] In addition, during the process of inputting equipment operation and maintenance information, attention should also be paid to the consistency and integrity of the data. This means that in addition to ensuring the authenticity and reliability of the input data, it is also necessary to ensure the coordination among various types of data to avoid contradictions or duplications. To this end, a set of strict standards and specifications can be formulated before data input to guide relevant personnel to operate in a unified format. At the same time, the input data should be regularly audited and verified to promptly detect and correct any possible problems. In this way, both the data quality can be improved and the subsequent intelligent analysis work can be smoothly carried out.
[0037] In the above-mentioned building intelligent management method based on BIM technology, in step S2, a sensor group is used to collect the time series of the operating state data of the building equipment in real time, and the operating state data includes temperature, current, and power. It should be understood that traditional threshold alarms can only detect the overlimit of a single parameter (such as too high temperature), but complex equipment failures (such as motor bearing wear) usually show abnormal multi-parameter coupling (such as temperature increase accompanied by current fluctuations). Therefore, in this application, a sensor group is deployed to collect time series data such as temperature, current, and power of building equipment to capture the multi-dimensional dynamic characteristics of equipment operation, which helps to realize the real-time perception of the operating state of building equipment and solve the lag problem of traditional manual inspections.
[0038] Specifically, by installing high-precision sensors at key parts of building equipment, various dynamic changes during equipment operation can be accurately captured. These sensors can not only measure basic parameters such as temperature, current, and power but also be extended to monitor other physical quantities according to specific needs, such as vibration and pressure, so as to realize multi-dimensional perception of the equipment operating state. The selection of sensors needs to be determined based on the specific parameters to be monitored and the working environment of the equipment to ensure that the selected sensors can work stably under specific conditions and provide accurate and reliable measurement results.
[0039] In the process of specific implementation, to ensure the effective deployment of the sensor group, it is necessary to carefully plan the location and quantity of each sensor. For large construction equipment, a reasonable layout of sensors is a crucial step. For example, in an air conditioning unit or a water pump system, in addition to installing sensors around the core components, additional monitoring points should also be added in areas where heat accumulation or current fluctuations may occur. The purpose of doing this is to more comprehensively capture the status information during equipment operation and avoid incomplete data or misjudgment caused by monitoring blind spots. In addition, the interaction between sensors and its impact on the overall system also need to be considered to ensure that the collected data has high representativeness and reliability.
[0040] The data collected by the sensor group will exist in the form of a time series, which means that the operating status of the equipment at each moment will be recorded, forming a continuous data stream. This data acquisition method based on time series helps to discover potential trends and patterns in equipment operation, especially those subtle changes that are not easily detectable. For example, by analyzing the change trends of temperature, current, and power over a period of time, it is possible to identify whether there are signs of gradual deterioration in the equipment, which is particularly important for early warning systems. At the same time, the long-term accumulation of time series data also provides rich materials for subsequent data mining and deep learning, making more accurate fault prediction possible.
[0041] It is worth noting that to ensure the data quality collected by the sensor group, the sensors must be calibrated and maintained regularly. Since construction equipment often operates in a complex environment, long-term operation may lead to a decline in sensor performance or drift, which will directly affect the accuracy of the data. Therefore, it is crucial to formulate a complete sensor maintenance plan. This plan should cover the whole process management from the initial installation and commissioning of the sensors to daily inspections, regular calibrations, and finally replacements, ensuring that the sensors are always in the best working condition. In addition, by using modern communication technologies such as wireless sensor networks or the Internet of Things (IoT), real-time data transmission can be achieved, enabling managers to access the latest equipment operating status information anytime and anywhere, greatly improving the response speed and decision-making efficiency.
[0042] In the above building intelligent management method based on BIM technology, in step S3, the time series of the operation state data and the equipment operation and maintenance information in the BIM model are transmitted to the building equipment remote monitoring center for in-depth interaction analysis to determine the fault diagnosis result of the building equipment. Among them, the in-depth interaction analysis of the time series of the operation state data and the equipment operation and maintenance information includes: performing operation state-historical operation and maintenance information interaction response reasoning based on local feature association on the time series of the operation state data and the equipment operation and maintenance information to obtain the fault diagnosis result. Specifically, in the traditional mode, the real-time sensor data of the equipment (such as temperature, current) and the historical operation and maintenance records (such as maintenance time, fault type) are usually stored separately in different systems (such as SCADA system, Excel spreadsheet), resulting in the fragmentation of data correlation. Usually, equipment failures do not occur suddenly, but there is a gradual development process. The operation state data of the equipment can reflect the current real-time situation of the equipment, while the historical operation and maintenance information contains various potential fault information and degradation laws accumulated during the long-term operation of the equipment. Therefore, through the joint analysis of the operation state data and operation and maintenance information of the equipment in this application, it is helpful to discover the subtle change trend of the equipment operation parameters and detect the potential fault risks of the equipment in advance. For example, in the UPS power supply system, when the real-time current harmonic distortion rate reaches a threshold (such as 5%), the traditional method will trigger an alarm; but through the joint analysis of its real-time operation data and historical operation and maintenance information, it is found that the harmonic value of this equipment has shown a slow upward trend in the past two years. Combining with the historical replacement records of the capacitors, it is possible to give an early warning of "filter capacitor aging" in advance to avoid sudden downtime, thus making up for the deficiencies of traditional diagnostic methods and improving the accuracy and reliability of fault diagnosis. Among them, Figure 2 It is a flowchart of sub-step S3 of the building intelligent management method based on BIM technology according to an embodiment of the present application.
[0043] Figure 3 It is a schematic diagram of data flow of sub-step S3 of the building intelligent management method based on BIM technology according to an embodiment of the present application. As Figure 2 and Figure 3As shown, step S3 includes steps: S31, extracting the time series characteristics of the operating state of the construction equipment from the time series of the operating state data to obtain the time series correlation implicit feature vector of the operating state of the construction equipment; S32, performing semantic encoding on the equipment operation and maintenance information to obtain the semantic feature encoding vector of the construction equipment operation and maintenance information; S33, performing an operation state-historical operation and maintenance information interaction response inference on the time series correlation implicit feature vector of the construction equipment operating state and the semantic feature encoding vector of the construction equipment operation and maintenance information to obtain an equipment real-time operating state-historical operation and maintenance feature interaction response inference encoding vector; S34, based on the equipment real-time operating state-historical operation and maintenance feature interaction response inference encoding vector, determining the fault diagnosis result, and the fault diagnosis result is used to indicate whether the equipment has a fault.
[0044] Specifically, in a specific example of the present application, step S31 includes: performing time series feature extraction based on the LSTM model on the time series of the operating state data to obtain the time series correlation implicit feature vector of the operating state of the construction equipment. That is, considering that the operating state data of construction equipment (such as temperature, current) has strong time series correlation, traditional threshold detection only focuses on instantaneous values and cannot capture the dynamic evolution law between parameters (such as the current waveform showing progressive distortion due to motor bearing wear). In response to this, the present application uses the LSTM (Long Short-Term Memory) model, which performs excellently in the field of time series analysis, to deeply mine the time series data such as temperature, current, and power of the equipment, so as to extract the implicit features of the equipment operating state evolving over time and establish a continuous representation of the equipment state evolution process. Specifically, the LSTM model receives the time series of the operating state data as input, and each time step input contains multiple parameters (temperature, current, power). The LSTM model captures the long-term dependence relationship between the operating state parameters of the equipment by performing cyclic processing on the input data step by step in time, thereby revealing the internal law of the equipment operating state changing over time, generating the time series correlation implicit feature vector of the equipment operating state, and further providing a key information basis for subsequent equipment fault diagnosis.
[0045] Specifically, in a specific example of the present application, the step S32 includes: extracting semantic features of the device operation and maintenance information based on the Bert model to obtain the semantic feature encoding vector of the building equipment operation and maintenance information. It should be understood that since the device operation and maintenance information (such as maintenance work order descriptions, spare part replacement records) contains unstructured text (such as "Replace the bearing of fan #3 on 2023 / 06 / 12 and find that the grease has dried up"), traditional text analysis methods are difficult to effectively understand the semantic associations therein (such as the causal relationship between "insufficient lubrication" and "increased vibration"). In response to this, the present application further uses the Bert (Bidirectional Encoder Representations from Transformers) model to perform semantic encoding on the device operation and maintenance information, aiming to convert discrete operation and maintenance events into computable semantic vectors and reveal the potential associations between historical events and real-time states. Specifically, as a pre-trained language representation model, the Bert model is based on a bidirectional Transformer architecture and can effectively capture the bidirectional semantic relationships between words in the text through large-scale unsupervised learning. In the present application, the Bert model receives the device operation and maintenance information (such as maintenance work order descriptions, spare part replacement records) as input, deeply understands its text content to extract the context semantics therein, generates the semantic feature encoding vector of the device operation and maintenance information, and is used to represent the core meaning of the operation and maintenance events, providing historical information support for subsequent device fault diagnosis.
[0046] Specifically, in step S33, the operation state-historical operation and maintenance information interactive response reasoning is performed on the implicit feature vector associated with the time series of the operation state of the building equipment and the semantic feature coding vector of the operation and maintenance information of the building equipment to obtain the equipment real-time operation state-historical operation and maintenance feature interactive response reasoning coding vector. It should be understood that the present application considers that the simple feature splicing of the implicit feature vector associated with the time series of the operation state of the building equipment and the semantic feature coding vector of the operation and maintenance information of the building equipment to fuse multi-source information will ignore the local correlation of cross-modal features (such as the causal relationship between a sudden increase in current and the replacement of a capacitor last week), thereby reducing the utilization efficiency of information. Based on this, the present application proposes a local interactive reasoning mechanism, which captures the local correlation between the equipment operation status and the historical operation and maintenance information by establishing a fine-grained feature interaction between the temporal association implicit feature vector of the building equipment operation status and the semantic feature encoding vector of the building equipment operation and maintenance information (such as the interaction between the equipment operation features of time window t and the semantic features of historical event k), and dynamically adjusts the importance of different feature interactions through adaptive attention mechanism and chain reasoning to enhance the expression of key information, and gradually transmits and integrates the results of each local feature interaction, excavates the dynamic correlation between the equipment state evolution and the operation and maintenance behavior, and finally generates the equipment real-time operation status-historical operation and maintenance feature interaction response reasoning encoding vector. Among them, Figure 4 FIG. 4 is a flowchart of sub-step S33 of the building intelligent management method based on BIM technology according to an embodiment of the present application. Figure 4 As shown, the step S33 includes the steps of: S331, performing feature interaction encoding based on local implicit association on the implicit feature vector of the temporal association of the building equipment operation status and the semantic feature coding vector of the building equipment operation and maintenance information to obtain a set of local implicit feature interaction response coding vectors of the equipment real-time operation status-historical operation and maintenance information; S332, performing weighted modulation based on feature distribution significance on the set of local implicit feature interaction response coding vectors of the equipment real-time operation status-historical operation and maintenance information to obtain a set of modulated local implicit feature interaction response coding vectors of the equipment real-time operation status-historical operation and maintenance information; S333, performing progressive reasoning based on the forward LSTM model on the set of local implicit feature interaction response coding vectors of the equipment real-time operation status-historical operation and maintenance information to obtain the equipment real-time operation status-historical operation and maintenance feature interaction response reasoning coding vector.
[0047] More specifically, the step S331 includes: first, performing local implicit feature extraction based on one-dimensional convolution coding on the temporal association implicit feature vector of the building equipment operation state and the semantic feature coding vector of the building equipment operation and maintenance information to obtain a set of local implicit feature coding vectors of the building equipment operation state and a set of local implicit feature coding vectors of the building equipment operation and maintenance information, which are expressed as follows:
[0048] Conv l×1 (X) = {x1, x2,..., x i ,..., x n}
[0049] Conv l×1 (Y) = {y1, y2,..., y i ,..., y n}
[0050] Among them, X represents the time - series - related implicit feature vector of the operating state of construction equipment, Conv l×1 (·) represents the one - dimensional convolutional encoding with a convolutional kernel scale of l, x1, x2, x i and x n respectively represent the 1st, 2nd, ith, and nth local implicit feature encoding vectors of the operating state of construction equipment in the set of local implicit feature encoding vectors of the operating state of construction equipment. n is the number of local implicit feature encoding vectors of the operating state of construction equipment. Y represents the semantic feature encoding vector of the operation and maintenance information of construction equipment, y1, y2, y i and y n respectively represent the 1st, 2nd, ith, and nth local implicit feature encoding vectors of the operation and maintenance information of construction equipment in the set of local implicit feature encoding vectors of the operation and maintenance information of construction equipment.
[0051] That is, by introducing one - dimensional convolutional technology, it helps to specifically analyze the local correlation between the time - series data of the equipment operating state and the operation and maintenance information. Specifically, one - dimensional convolution can automatically extract the implicit correlation patterns between adjacent time nodes in the time dimension through the sliding window mechanism. It can not only retain key time - series features to avoid dimensional explosion but also provide a finer - grained high - order feature representation basis for subsequent cross - domain feature interaction, generating the set of local implicit feature encoding vectors of the operating state of construction equipment and the set of local implicit feature encoding vectors of the operation and maintenance information of construction equipment, enabling the model to establish a local dynamic mapping relationship between the real - time operation parameters of the equipment and the historical operation and maintenance knowledge, and improving the recognition accuracy of composite fault modes.
[0052] Then, each group of corresponding local implicit feature encoding vectors of the operating state of construction equipment and local implicit feature encoding vectors of the operation and maintenance information of construction equipment in the set of local implicit feature encoding vectors of the operating state of construction equipment and the set of local implicit feature encoding vectors of the operation and maintenance information of construction equipment are respectively input into the single - entity feature interaction engine to obtain the set of local implicit feature interaction response encoding vectors of the real - time operation state - historical operation and maintenance information of the equipment, which is expressed by the formula:
[0053]
[0054] Among them, concat(·) represents the concatenation function, and ⊙ represents the dot product operation. represents the point addition operation. represents the point subtraction operation, b i represents the bias term, W i represents the weight matrix, v i represents the i-th device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vector in the set of device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vectors.
[0055] That is, by introducing a single feature interaction engine, multi-dimensional refined modeling is performed on the dimensional alignment relationship, time series synchronization, and semantic association between the local implicit feature coding vectors of the building equipment operation state and the local implicit feature coding vectors of the building equipment operation and maintenance information. Specifically, when the time series data of the operation state shows periodic fluctuations, it may form a phase-level association with the periodic maintenance records in the operation and maintenance information, and the single feature interaction engine can quantify this multiplicative interaction effect through the Hadamard product, thereby constructing a physically interpretable local interaction response coding. Furthermore, the powerful feature learning ability of the neural network is used to model the multi-dimensional interaction effect between the two, generating the device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vector.
[0056] Figure 5 It is a flowchart of sub-step S332 of the building intelligent management method based on BIM technology according to an embodiment of the present application. As Figure 5 shown, the step S332 includes steps: S3321, based on the feature distribution characteristics of each device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vector in the set of device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vectors, determining the chain inference attention weights of each device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vector to obtain a set of device real-time operation state - historical operation and maintenance information chain inference attention weights; S3322, based on the set of device real-time operation state - historical operation and maintenance information chain inference attention weights, performing feature modulation on the set of device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vectors to obtain the set of modulated device real-time operation state - historical operation and maintenance information local implicit feature interaction response coding vectors.
[0057] In a specific example of the present application, the step S3321 is expressed by the formula:
[0058]
[0059] Among them, softmax(·) represents the normalized exponential function, and L represents the characteristic scale value of v i,j ; ‖·‖ represents the calculation of the norm, and v i,j represents the eigenvalue at the j-th position of the local implicit feature interaction response coding vector of the device's real-time operation state - historical operation and maintenance information, and a i represents the chain inference attention weight of the device's real-time operation state - historical operation and maintenance information.
[0060] That is, by introducing a chain inference attention mechanism, the importance ranking of each interaction unit is dynamically evaluated based on the statistical characteristics of the local implicit feature interaction response coding vector of the device's real-time operation state - historical operation and maintenance information. In this way, by constructing a physically interpretable feature selection mechanism, the gradient backpropagation characteristic of the attention weight can be utilized to enable the model to automatically focus on the local interaction patterns with high contribution to compound fault diagnosis, while suppressing the interference of redundant feature noise on the inference chain. It can transform the set of discrete local implicit feature interaction response coding vectors of the device's real-time operation state - historical operation and maintenance information into a hierarchical feature importance map, so as to facilitate guiding the subsequent inference process to preferentially process high-significance feature combinations through the weight set, thereby enhancing the early capture ability of progressive faults and the positioning accuracy of sudden anomalies, and realizing the logical connection from local feature association to global state evolution.
[0061] In a preferred example of the present application, the step S3322 includes: First, based on the decomposition of the interaction space effect of each local implicit feature interaction response coding vector of the device's real-time operation state - historical operation and maintenance information in the set, the set of the chain inference attention weights of the device's real-time operation state - historical operation and maintenance information is compensated and corrected to obtain a set of corrected chain inference attention weights of the device's real-time operation state - historical operation and maintenance information, which is expressed by the formula:
[0062]
[0063] γ = ‖x i ⊙y i ‖ 2
[0064]
[0065] ζ = e γ ×(α + β)
[0066] a′ i = (ω1×ξ + ω2×ζ)a i
[0067] Among them, α and β respectively represent x i and yi The statistical quantity of the feature interaction translation effect vector between them, where γ represents x i and y i The statistical quantity of the feature interaction fluctuation effect vector between them, ln(·) represents the natural logarithm, ξ represents the periodic local rule compensation factor, e (·) represents the exponential function with the natural constant as the base, ζ represents the periodic local auxiliary phase transition factor, ω1 and ω2 respectively represent different weighting values, a′ i represents the corrected attention weight of the chain reasoning of the real-time operation state - historical operation and maintenance information of the device.
[0068] Here, when calculating the local implicit feature interaction response coding vectors of the real-time operation states - historical operation and maintenance information of each device, the interaction features between the corresponding first local implicit feature interaction response coding vector of the real-time operation state - historical operation and maintenance information of the device and the second local implicit feature interaction response coding vector of the real-time operation state - historical operation and maintenance information of the device will be introduced. That is, in essence, it corresponds to different interaction specifications, and thus has different spatial auxiliary constraint associations in the interaction space. Therefore, in order to enhance the auxiliary effect of the specification change when calculating the chain reasoning attention weight, the present application corrects the chain reasoning attention weight based on the spatial effect decomposition of the interaction specification. Specifically, can be regarded as the translation effect, that is, the gradient direction is consistent with the spatial interaction direction, while x i ⊙y i is regarded as the fluctuation effect, that is, the gradient direction is orthogonal to the spatial interaction direction. In this way, for the vector statistical quantities of different effects, such as γ = ‖x i ⊙y i ‖ 2 , it is considered that the fluctuation effect causes the localized periodic effect in the translation direction, and thus calculates its periodic local rule compensation factor. On the other hand, the fluctuation effect will also cause the phase transition of the translation locality, so the periodic local auxiliary phase transition factor is obtained. Therefore, by correcting the attention weight of the chain reasoning of the real-time operation state - historical operation and maintenance information of the device based on the weighted sum of the periodic local rule compensation factor and the periodic local auxiliary phase transition factor, it is possible to improve the correlation between different spatial auxiliary constraint specifications in the interaction space according to the difference in the normative effects of different interaction specifications corresponding to each local interaction response, thereby improving the calculation accuracy of the attention weight of the chain reasoning of the real-time operation state - historical operation and maintenance information of the device, and generating the corrected attention weight of the chain reasoning of the real-time operation state - historical operation and maintenance information of the device.
[0069] Then, based on the set of chain inference attention weights of the corrected real-time operating state - historical operation and maintenance information of the device, the set of encoded vectors of the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device is weighted and modulated to obtain the set of encoded vectors of the local implicit feature interaction response of the modulated real-time operating state - historical operation and maintenance information of the device, which is expressed by the formula:
[0070] I = {I1, I2,..., I i ,..., I n}
[0071] I i = a′ i ·v i
[0072] Among them, I1, I2, I i and I n respectively represent the 1st, 2nd, ith, and nth encoded vectors of the local implicit feature interaction response of the modulated real-time operating state - historical operation and maintenance information of the device in the set of encoded vectors of the local implicit feature interaction response of the modulated real-time operating state - historical operation and maintenance information of the device.
[0073] That is to say, by introducing a weighted modulation mechanism, the dynamic amplitude adjustment of the feature vectors can be implemented based on the corrected chain inference attention weights. The key features of the high-weight interaction response encoded vectors are amplified by gain, making them dominant in the subsequent inference chain, while the secondary features of the low-weight vectors are compressed and suppressed, thereby reducing the negative impact of sensor noise or accidental anomalies on global inference, and thus generating the encoded vectors of the local implicit feature interaction response of the modulated real-time operating state - historical operation and maintenance information of the device.
[0074] More specifically, the step S333 is expressed by the formula:
[0075] v f = LSTM(I)
[0076] Among them, LSTM(·) represents the forward LSTM model, and v f represents the encoded vector of the real-time operating state - historical operation and maintenance feature interaction response inference.
[0077] That is, through the hidden state iterative update feature of the forward LSTM model, the set of locally implicit feature interaction response encoding vectors of the modulated real-time operating state of the device - historical operation and maintenance information is transformed into a global feature representation containing temporal dependencies, enabling the model to capture the dynamic evolution trajectory of the device's health state from quantitative change to qualitative change. Specifically, the redundant noise across time steps is filtered through the LSTM gating mechanism, and the finally formed real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector can be used as a global representation of the device's health state, providing high-order feature inputs with physical interpretability for subsequent tasks such as fault classification and remaining life prediction.
[0078] Specifically, in step S34, based on the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector, the fault diagnosis result is determined, and the fault diagnosis result is used to indicate whether the device has a fault. It should be understood that the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector integrates the in-depth interaction results of the real-time operating state of the device and historical operation and maintenance information and can accurately represent the health status of the device. In a specific example of this application, step S34 includes: inputting the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector into a fault diagnosis module based on a classifier to obtain the fault diagnosis result. That is, in order to transform the abstract representation of the device's health state into an operable fault diagnosis result, this application uses a classification algorithm to process the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector. Specifically, the classifier learns the device state feature patterns of different categories (fault or normal) based on the existing training data and establishes a classification decision boundary. Then, after receiving the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector, based on the learned classification decision boundary, it calculates the probabilities of the real-time operating state of the device - historical operation and maintenance feature interaction response inference encoding vector belonging to different categories and outputs the category with the highest probability as the final fault diagnosis result, thus realizing the transformation from the device health state feature representation to the fault diagnosis result, so as to prompt the maintenance personnel to take measures for repair or prevention in a timely manner to ensure the stable operation of the device.
[0079] In the above building intelligent management method based on BIM technology, in step S4, based on the fault diagnosis result, the health status of the building equipment is dynamically displayed in the BIM model with color coding. It should be understood that displaying the equipment health status in the BIM model with color coding can present complex fault diagnosis results to the operation and maintenance personnel in an intuitive and easy-to-understand manner, greatly improving the efficiency of information transmission. Through this visualization method, the operation and maintenance personnel can quickly identify abnormal equipment, improving the efficiency and accuracy of operation and maintenance decision-making, and avoiding the expansion of faults caused by untimely information acquisition. In specific implementation, color coding rules are pre-established to match different fault diagnosis results with specific colors. For example, it is set that green indicates that the equipment is operating normally, all parameters of the equipment are within the normal range, and no abnormal situation occurs; red indicates that the equipment has a fault and maintenance personnel need to be arranged for inspection immediately. By using the secondary development interface provided by the BIM software, a program is written to realize the automatic matching of the fault diagnosis result and the color coding. When the fault diagnosis result of the equipment is obtained, it is automatically compared with the color coding rules, the health status of the equipment is converted into the corresponding color, and the equipment is visually marked in the BIM model, so as to realize the intuitive display of the equipment status.
[0080] In summary, the building intelligent management method based on BIM technology according to the embodiments of the present application is elucidated. First, a BIM model of the building is constructed, and the equipment operation and maintenance information of the building equipment is entered into the BIM model. At the same time, a sensor group is used to collect the operation status data of the building equipment in real time. Furthermore, a deep learning algorithm is introduced. By performing feature extraction and deep interaction response analysis on the real-time operation status data and historical operation and maintenance information of the building equipment, the potential fault modes of the equipment are mined by combining the historical operation and maintenance data and real-time status of the equipment, so as to realize the intelligent fault diagnosis of the building equipment, and the health status of the equipment is intuitively displayed in the BIM model by color coding. In this way, the operation and maintenance efficiency and fault diagnosis accuracy of the building equipment can be improved, potential fault risks can be discovered and warned in time, and at the same time, the intelligent level of building management can be enhanced.
[0081] Furthermore, a building intelligent management system based on BIM technology is also provided.
[0082] Figure 6 It is a block diagram of the building intelligent management system based on BIM technology according to the embodiments of the present application. As Figure 6As shown, the building intelligent management system 100 based on BIM technology according to an embodiment of the present application includes: a BIM model construction module 110 for constructing a BIM model of a building and inputting the equipment operation and maintenance information of building equipment into the BIM model, where the equipment operation and maintenance information includes the basic information, technical parameters, and historical maintenance records of the equipment; an operating state data acquisition module 120 for using a sensor group to collect in real time the time series of the operating state data of the building equipment, where the operating state data includes temperature, current, and power; a fault diagnosis and analysis module 130 for transmitting the time series of the operating state data and the equipment operation and maintenance information in the BIM model to a building equipment remote monitoring center for in-depth interaction analysis to determine the fault diagnosis result of the building equipment. Among them, the in-depth interaction analysis of the time series of the operating state data and the equipment operation and maintenance information includes: performing an operating state-historical operation and maintenance information interaction response inference based on local feature association on the time series of the operating state data and the equipment operation and maintenance information to obtain the fault diagnosis result; a health state visualization module 140 for dynamically displaying the health state of the building equipment in the BIM model in color coding based on the fault diagnosis result.
[0083] Here, those skilled in the art can understand that the specific operations of each module in the above building intelligent management system based on BIM technology have been introduced in detail in the description of the Figures 1 to 5 building intelligent management method based on BIM technology above, and therefore, the repeated description thereof will be omitted.
[0084] The basic principles of the present invention have been described above in conjunction with specific embodiments. However, it should be noted that the advantages, advantages, effects, etc. mentioned in the present invention are only examples and not limitations, and it cannot be considered that these advantages, advantages, effects, etc. are essential for each embodiment of the present invention. In addition, the specific details of the above embodiments are only for the purposes of illustration and easy understanding, rather than limitations, and the above details do not limit the present invention to necessarily adopt the above specific details to implement.
[0085] In the above embodiments, the descriptions of the various embodiments each have their own emphasis. For parts not detailed or recorded in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. In the several embodiments provided by the present invention, it should be understood that the disclosed system and method can be implemented in other ways. For example, the system embodiment described above is merely illustrative. For example, the unit division is only a logical function division, and there may be other division methods in actual implementation. The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0086] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and without departing from the spirit or basic characteristics of the present invention, the present invention can be implemented in other specific forms. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.
[0087] In addition, it is obvious that the term "including" does not exclude other units or steps, and the singular does not exclude the plural. The multiple units stated in the system claims can also be implemented by one unit through software or hardware.
[0088] Finally, it should be noted that the above description has been given for purposes of illustration and description. In addition, the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit them. Although the present invention has been described in detail with reference to the preferred embodiments, those of ordinary skill in the art should understand that the technical solutions of the present invention can be modified or equivalently replaced without departing from the spirit and scope of the technical solutions of the present invention.
Claims
1. A building intelligent management method based on BIM technology, characterized in that, Including: Construct a BIM model of a building and input the equipment operation and maintenance information of building equipment into the BIM model, where the equipment operation and maintenance information includes the basic information, technical parameters, and historical maintenance records of the equipment; Use a sensor group to collect in real time the time series of the operating state data of the building equipment, where the operating state data includes temperature, current, and power; Transmit the time series of the operating state data and the equipment operation and maintenance information in the BIM model to a building equipment remote monitoring center for in-depth interactive analysis to determine the fault diagnosis result of the building equipment. Among them, the in-depth interactive analysis of the time series of the operating state data and the equipment operation and maintenance information includes: performing an operating state-historical operation and maintenance information interactive response inference based on local feature association on the time series of the operating state data and the equipment operation and maintenance information to obtain the fault diagnosis result; Based on the fault diagnosis result, dynamically display the health state of the building equipment in the BIM model in color coding.
2. The building intelligent management method based on BIM technology according to claim 1, characterized in that, Performing an operating state-historical operation and maintenance information interactive response inference based on local feature association on the time series of the operating state data and the equipment operation and maintenance information to obtain the fault diagnosis result includes: Extract the time series features of the operating state of the building equipment from the time series of the operating state data to obtain the time series correlation implicit feature vector of the operating state of the building equipment; Perform semantic coding on the equipment operation and maintenance information to obtain the semantic feature coding vector of the equipment operation and maintenance information of the building; Perform an operating state-historical operation and maintenance information interactive response inference on the time series correlation implicit feature vector of the operating state of the building equipment and the semantic feature coding vector of the equipment operation and maintenance information of the building to obtain the equipment real-time operating state-historical operation and maintenance feature interactive response inference coding vector; Based on the equipment real-time operating state-historical operation and maintenance feature interactive response inference coding vector, determine the fault diagnosis result, where the fault diagnosis result is used to indicate whether the equipment has a fault.
3. The building intelligent management method based on BIM technology according to claim 2, characterized in that, Extracting the time series features of the operating state of the building equipment from the time series of the operating state data to obtain the time series correlation implicit feature vector of the operating state of the building equipment includes: Perform time series feature extraction on the time series of the operating state data based on the LSTM model to obtain the time series correlation implicit feature vector of the operating state of the building equipment.
4. The building intelligent management method based on BIM technology according to claim 3, characterized in that Performing semantic coding on the equipment operation and maintenance information to obtain the semantic feature coding vector of the equipment operation and maintenance information of the building includes: Perform semantic feature extraction on the equipment operation and maintenance information based on the Bert model to obtain the semantic feature coding vector of the equipment operation and maintenance information of the building.
5. The building intelligent management method based on BIM technology according to claim 4, characterized in that, Performing an operating state-historical operation and maintenance information interactive response inference on the time series correlation implicit feature vector of the operating state of the building equipment and the semantic feature coding vector of the equipment operation and maintenance information of the building to obtain the equipment real-time operating state-historical operation and maintenance feature interactive response inference coding vector includes: Perform feature interaction coding based on local implicit association on the time series correlation implicit feature vector of the operating state of the building equipment and the semantic feature coding vector of the equipment operation and maintenance information of the building to obtain a set of equipment real-time operating state-historical operation and maintenance information local implicit feature interactive response coding vectors; Perform weighted modulation based on the significance of feature distribution on the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the modulated device; Perform progressive inference based on the forward LSTM model on the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the modulated device to obtain the encoded vector for the feature interaction response of the real-time operating state - historical operation and maintenance feature of the device.
6. The building intelligent management method based on BIM technology according to claim 5, characterized in that, Perform feature interaction encoding based on local implicit association on the time-series associated implicit feature vector of the building device operating state and the semantic feature encoded vector of the building device operation and maintenance information to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device, including: Perform local implicit feature extraction based on one-dimensional convolutional encoding on the time-series associated implicit feature vector of the building device operating state and the semantic feature encoded vector of the building device operation and maintenance information respectively to obtain a set of encoded vectors for the local implicit features of the building device operating state and a set of encoded vectors for the local implicit features of the building device operation and maintenance information; Input each pair of corresponding encoded vectors for the local implicit features of the building device operating state and the encoded vectors for the local implicit features of the building device operation and maintenance information in the set of encoded vectors for the local implicit features of the building device operating state and the set of encoded vectors for the local implicit features of the building device operation and maintenance information into the single-feature interaction engine respectively to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device.
7. The building intelligent management method based on BIM technology according to claim 6, characterized in that, Perform weighted modulation based on the significance of feature distribution on the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the modulated device, including: Based on the feature distribution characteristics of each encoded vector for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device in the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device, determine the chain inference attention weights of each encoded vector for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device to obtain a set of chain inference attention weights for the real-time operating state - historical operation and maintenance information of the device; Based on the set of chain inference attention weights for the real-time operating state - historical operation and maintenance information of the device, perform feature modulation on the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the modulated device.
8. The building intelligent management method based on BIM technology according to claim 7, characterized in that, Based on the set of chain inference attention weights for the real-time operating state - historical operation and maintenance information of the device, perform feature modulation on the set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the device to obtain a set of encoded vectors for the local implicit feature interaction response of the real-time operating state - historical operation and maintenance information of the modulated device, including: Based on the interaction space decomposition of each device real-time operation status-historical operation and maintenance information local implicit feature interaction response coding vector in the set of device real-time operation status-historical operation and maintenance information local implicit feature interaction response coding vectors, compensate and correct the set of device real-time operation status-historical operation and maintenance information chain inference attention weights to obtain the corrected set of device real-time operation status-historical operation and maintenance information chain inference attention weights; Based on the corrected set of device real-time operation status-historical operation and maintenance information chain inference attention weights, perform weighted modulation on the set of device real-time operation status-historical operation and maintenance information local implicit feature interaction response coding vectors to obtain the modulated set of device real-time operation status-historical operation and maintenance information local implicit feature interaction response coding vectors.
9. The building intelligent management method based on BIM technology according to claim 8, characterized in that, Based on the device real-time operation status-historical operation and maintenance feature interaction response inference coding vector, determine the fault diagnosis result, where the fault diagnosis result is used to indicate whether the device has a fault, including: Input the device real-time operation status-historical operation and maintenance feature interaction response inference coding vector into the fault diagnosis module based on a classifier to obtain the fault diagnosis result.
10. A building intelligent management system based on BIM technology, characterized in that, Including: A BIM model construction module, configured to construct a BIM model of a building and input the device operation and maintenance information of building devices into the BIM model, where the device operation and maintenance information includes the basic information, technical parameters, and historical maintenance records of the devices; An operation status data acquisition module, configured to use a sensor group to collect the time series of the operation status data of the building devices in real time, where the operation status data includes temperature, current, and power; A fault diagnosis and analysis module, configured to transmit the time series of the operation status data and the device operation and maintenance information in the BIM model to a building device remote monitoring center for in-depth interaction analysis to determine the fault diagnosis result of the building devices. Among them, the in-depth interaction analysis of the time series of the operation status data and the device operation and maintenance information includes: performing operation status-historical operation and maintenance information interaction response inference based on local feature association on the time series of the operation status data and the device operation and maintenance information to obtain the fault diagnosis result; A health status visualization module, configured to dynamically display the health status of the building devices in color coding in the BIM model based on the fault diagnosis result.
Citation Information
Cited By
Environment-friendly resourceful treatment system and method for solid waste
CN120330269A
Building life cycle management system based on dynamic modeling
CN121329317A
