Construction equipment training data processing system and method based on digital twin

Abstract

The present application discloses a construction equipment training data processing system and method based on digital twins, which uses a data communication link to obtain the time queue of the state parameters (real-time current value and real-time voltage value) of the target construction equipment, and uses artificial intelligence data processing and encoding methods to perform data classification and time series implicit association encoding of the state parameters, so as to automatically judge whether the working state of the target construction equipment is abnormal based on the significant interaction characteristics between the current time series implicit association characteristics and the voltage time series implicit association characteristics. In this way, through the sensor network and data communication link, the operation data of the equipment can be collected in real time, and the real-time monitoring of the equipment status can be realized. At the same time, the time series interaction characteristics between current and voltage can be captured, so as to more comprehensively evaluate the working state of the equipment, thereby improving the accuracy and intelligence of fault detection.

Description

Technical Field

[0001] The present application relates to the field of data processing, and more specifically, to a construction equipment training data processing system and method based on digital twins. Background Art

[0002] With the rapid development of the construction industry, the types and complexity of construction equipment are increasing. Modern construction projects involve a large number of mechanical equipment, such as cranes, excavators, concrete pump trucks, air conditioning systems, elevators, etc. The efficient operation and maintenance of these equipment are crucial to the smooth progress of the project. Therefore, real-time monitoring and status analysis of construction equipment are becoming more and more important.

[0003] However, traditional methods rely on regular manual inspections, which not only consume a lot of manpower and time, but also have fixed inspection frequencies and schedules, and cannot flexibly respond to real-time status changes of equipment. For example, equipment may fail between two inspections, and regular inspections cannot detect it in time, causing the failure to expand and affect project progress and quality. In addition, traditional methods can usually only obtain limited data points, such as static parameters of equipment, and lack comprehensive monitoring of equipment operating status. This limited data coverage easily misses potential fault points, such as dynamic changes such as current fluctuations and voltage anomalies, making it impossible to warn and deal with potential problems in a timely manner. These defects seriously affect the reliability of equipment and the smooth progress of projects.

[0004] Therefore, an optimized construction equipment training data processing solution is desired. Summary of the invention

[0005] In order to solve the above technical problems, the present application is proposed. The embodiment of the present application provides a construction equipment training data processing system and method based on digital twins, which obtains the time queue of the state parameters (real-time current value and real-time voltage value) of the target construction equipment by utilizing a data communication link, and uses artificial intelligence data processing and encoding methods to perform data classification and timing implicit association encoding of the state parameters, thereby automatically judging whether there is an abnormality in the working state of the target construction equipment based on the significant interaction characteristics between the current timing implicit association characteristics and the voltage timing implicit association characteristics. In this way, through the sensor network and the data communication link, the operation data of the equipment can be collected in real time, and the real-time monitoring of the equipment status can be realized. At the same time, the timing interaction characteristics between current and voltage can be captured, so as to more comprehensively evaluate the working state of the equipment, thereby improving the accuracy and intelligence of fault detection.

[0006] According to one aspect of the present application, a digital twin-based construction equipment training data processing system is provided, which includes: a construction equipment simulation module, which is used to construct a three-dimensional model of the target construction equipment based on BIM technology to obtain a three-dimensional model simulation body of the construction equipment; a digital twin deployment module, which is used to construct a data communication link between a sensor network deployed on the target construction equipment and the three-dimensional model simulation body of the construction equipment to obtain a digital twin of the construction equipment; a digital twin display module, which is used to display the digital twin of the construction equipment on a display screen; a working status analysis module, which is used to analyze the working status of the target construction equipment to obtain an identification result; and an identification status display module, which is used to display the identification status on the display screen.

[0007] According to another aspect of the present application, a method for processing construction equipment training data based on digital twins is provided, which includes: constructing a three-dimensional model of the target construction equipment based on BIM technology to obtain a three-dimensional model simulation of the construction equipment; constructing a data communication link between a sensor network deployed on the target construction equipment and the three-dimensional model simulation of the construction equipment to obtain a digital twin of the construction equipment; displaying the digital twin of the construction equipment on a display screen; analyzing the working status of the target construction equipment to obtain an identification result; and displaying the identification status on the display screen.

[0008] Compared with the prior art, the present application provides a digital twin-based building equipment training data processing system and method, which uses a data communication link to obtain the time queue of the state parameters (real-time current value and real-time voltage value) of the target building equipment, and uses artificial intelligence data processing and encoding methods to perform data classification and time series implicit association encoding of the state parameters, so as to automatically judge whether the working state of the target building equipment is abnormal based on the significant interaction characteristics between the current time series implicit association characteristics and the voltage time series implicit association characteristics. In this way, through the sensor network and data communication link, the operation data of the equipment can be collected in real time, and the real-time monitoring of the equipment status can be realized. At the same time, the time series interaction characteristics between current and voltage can be captured, so as to more comprehensively evaluate the working state of the equipment, thereby improving the accuracy and intelligence of fault detection. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] By describing the embodiments of the present application in more detail in conjunction with the accompanying drawings, the above and other purposes, features and advantages of the present application will become more apparent. The accompanying 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 of the present application. In the accompanying drawings, the same reference numerals generally represent the same components or steps.

[0010] Figure 1It is a block diagram of a construction equipment training data processing system based on digital twin according to an embodiment of the present application.

[0011] Figure 2 This is a data flow diagram of a digital twin-based construction equipment training data processing system according to an embodiment of the present application.

[0012] Figure 3 It is a block diagram of the working status analysis module in the digital twin-based construction equipment training data processing system according to an embodiment of the present application.

[0013] Figure 4 It is a flowchart of a method for processing construction equipment training data based on digital twins according to an embodiment of the present application. DETAILED DESCRIPTION

[0014] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0015] As shown in this application and claims, unless the context clearly indicates an exception, the words "a", "an", "an" and / or "the" do not refer to the singular and may also include the plural. Generally speaking, the terms "include" and "comprise" only indicate the inclusion of the steps and elements that have been clearly identified, and these steps and elements do not constitute an exclusive list. The method or device may also include other steps or elements.

[0016] Although the present application makes various references to certain modules in the system according to the embodiments of the present application, 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.

[0017] Flowcharts are used in the present application to illustrate the operations performed by the system according to the embodiments of the present application. It should be understood that the preceding or following operations are not necessarily performed accurately in order. On the contrary, various steps may be processed in reverse order or simultaneously as required. Meanwhile, other operations may also be added to these processes, or a certain step or several steps of operations may be removed from these processes.

[0018] Below, the exemplary embodiments according to the present application will be described in detail with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments of the present application, and it should be understood that the present application is not limited to the exemplary embodiments described here.

[0019] Traditional methods rely on regular manual inspections, which not only consume a lot of manpower and time, but also have fixed inspection frequencies and schedules, and cannot flexibly respond to real-time status changes of equipment. For example, equipment may fail between two inspections, and regular inspections cannot detect it in time, causing the failure to expand and affect project progress and quality. In addition, traditional methods can usually only obtain limited data points, such as static parameters of equipment, and lack comprehensive monitoring of the equipment's operating status. This limited data coverage easily misses potential fault points, such as current fluctuations, voltage anomalies and other dynamic changes, making it impossible to warn and deal with potential problems in a timely manner. These defects seriously affect the reliability of the equipment and the smooth progress of the project. Therefore, an optimized construction equipment training data processing solution is desired.

[0020] It should be understood that digital twins are a simulation process that integrates multiple disciplines, multiple physical quantities, multiple scales, and multiple probabilities. It uses physical models, sensor updates, operation history and other data to complete mapping in virtual space, thereby reflecting the entire life cycle of the corresponding physical equipment.

[0021] In the technical solution of the present application, a construction equipment training data processing system based on digital twin is proposed. Figure 1 It is a block diagram of a construction equipment training data processing system based on digital twin according to an embodiment of the present application. Figure 2 Schematic diagram of data flow of a digital twin-based construction equipment training data processing system according to an embodiment of the present application. Figure 1 and Figure 2 As shown, according to the embodiment of the present application, the digital twin-based construction equipment training data processing system 300 includes: a construction equipment simulation module 310, which is used to construct a three-dimensional model of the target construction equipment based on BIM technology to obtain a three-dimensional model simulation body of the construction equipment; a digital twin deployment module 320, which is used to construct a data communication link between the sensor network deployed on the target construction equipment and the three-dimensional model simulation body of the construction equipment to obtain a digital twin of the construction equipment; a digital twin display module 330, which is used to display the digital twin of the construction equipment on a display screen; a working status analysis module 340, which is used to analyze the working status of the target construction equipment to obtain an identification result; and an identification status display module 350, which is used to display the identification status on the display screen.

[0022] In particular, the building equipment simulation module 310 is used to construct a three-dimensional model of the target building equipment based on BIM technology to obtain a three-dimensional model simulation of the building equipment. BIM technology is a method based on digital technology for creating and managing information of a building project throughout its life cycle. The BIM model contains not only geometric shapes, but also a large amount of non-geometric information, such as material properties, cost estimates, construction progress, etc. Through BIM technology, a building project can be comprehensively designed, constructed, and managed in a virtual environment.

[0023] The process of building a 3D model includes the following steps: First, it is necessary to collect relevant data of the target building equipment, including the physical size and geometry of the equipment, material properties, functional and performance parameters, manufacturer information and technical documents, installation location and environmental conditions, etc. This data can be obtained from a variety of sources such as the manufacturer's manual of the equipment, technical drawings, on-site measurements, etc. The collected data will be used for subsequent model design and construction.

[0024] Next, use professional BIM software (such as Revit, ArchiCAD, etc.) to design and build a 3D model based on the collected data. Specific steps include creating basic geometric shapes, such as cuboids, cylinders, etc., using precise dimensions and proportions to ensure the accuracy of the model. Then, add detailed information about the equipment (such as material, color, texture, etc.) to the model to ensure the integrity and realism of the model. In addition, it is necessary to add various attributes and parameters to the model, such as the model, manufacturer, production date, maintenance records, etc. of the equipment, which will play a role in subsequent data analysis and management.

[0025] After the initial design is completed, the model needs to be verified to ensure that it meets the specifications and standards of the actual equipment. If necessary, corrections are made to correct errors or inaccuracies in the model to ensure the accuracy and reliability of the model.

[0026] In order to improve the practicality and operability of the model, the model needs to be optimized. First, lightweight processing is performed to reduce the complexity of the model so that it can run more smoothly on the computer. This can be achieved by simplifying geometric shapes, reducing the number of polygons, etc. Secondly, interactive functions are added to the model, such as clicking on the device to display its detailed information, animating the working process of the device, etc., to improve the user's operating experience and the practicality of the model. Finally, the sensor data is associated with the model so that the model can display the operating status of the device in real time. For example, the current, voltage and other data collected by the sensor can be synchronized to the model in real time, and the status of the device can be intuitively displayed through color changes or other visualization means.

[0027] After the model is built and optimized, it can be published and shared. Export the model to common 3D formats (such as FBX, OBJ, IFC, etc.) for use in different software and platforms. Upload the model to the cloud for multi-user access and collaboration. Through the cloud platform, multiple team members can view and edit the model in real time, improving work efficiency. In addition, applications for mobile devices can be developed so that users can view and operate the model on their mobile phones or tablets, improving management flexibility and convenience.

[0028] In particular, the digital twin deployment module 320 is used to construct a data communication link between the sensor network deployed on the target building equipment and the three-dimensional model simulation body of the building equipment to obtain the digital twin of the building equipment. First, it is necessary to select suitable sensors to monitor various key parameters of the building equipment. Common sensor types include current sensors, voltage sensors, temperature sensors, vibration sensors, humidity sensors and pressure sensors. The current sensor is used to monitor the current value of the equipment and determine the load condition of the equipment; the voltage sensor is used to monitor the voltage value of the equipment and determine the stability of the power supply; the temperature sensor is used to monitor the temperature of the equipment to prevent failures caused by overheating; the vibration sensor is used to monitor the vibration of the equipment and determine the mechanical state of the equipment; the humidity sensor is used to monitor the humidity of the environment around the equipment to prevent electrical failures caused by excessive humidity; the pressure sensor is used to monitor the pressure of the equipment to ensure that the equipment operates within the normal pressure range.

[0029] After selecting the appropriate sensor, you need to determine the installation location of the sensor to ensure that the sensor can fully cover the key parts of the equipment. For example, the current sensor should be installed on the main power line of the equipment, the voltage sensor should be installed at the power interface of the equipment, the temperature sensor should be installed near the heating parts of the equipment, the vibration sensor should be installed on the moving parts of the equipment, the humidity sensor should be installed in the environment around the equipment, and the pressure sensor should be installed on the pressure pipe or container of the equipment.

[0030] When installing the sensor, make sure that the sensor is firmly and securely installed and will not become loose due to vibration or movement of the equipment. Also, make sure that the sensor wiring is correct to avoid problems such as short circuits or open circuits. After installation, it is necessary to select the appropriate communication protocol and technology to ensure that the sensor data can be transmitted to the central processing unit in real time. Common communication protocols and technologies include Wi-Fi, Bluetooth, LoRa, Zigbee, RS485, and Modbus.

[0031] Wi-Fi is suitable for short-distance, high-speed data transmission and is suitable for indoor environments; Bluetooth is suitable for short-distance, low-power data transmission and is suitable for portable devices; LoRa is suitable for long-distance, low-power data transmission and is suitable for outdoor environments; Zigbee is suitable for short-distance, low-power, multi-node wireless networks and is suitable for large-scale sensor networks; RS485 is suitable for wired communication and is suitable for long-distance, high-reliability scenarios; Modbus is suitable for wired or wireless communication of industrial equipment and supports a variety of transmission media.

[0032] Deploy the corresponding communication equipment according to the selected communication protocol and technology. For example, if you choose Wi-Fi, you need to install Wi-Fi routers and access points to ensure smooth wireless communication between sensors and the central processing unit; if you choose Bluetooth, you need to install a Bluetooth gateway to convert Bluetooth signals into wired or wireless signals and transmit them to the central processing unit; if you choose LoRa, you need to install a LoRa gateway to transmit LoRa signals to the central processing unit; if you choose RS485, you need to lay RS485 cables to connect sensors and the central processing unit; if you choose Modbus, you need to configure Modbus communication parameters to ensure normal communication between sensors and the central processing unit.

[0033] When configuring communication parameters, you need to set the corresponding parameters according to the selected communication protocol and technology. For example, if you choose Wi-Fi, you need to set the SSID and password of the Wi-Fi network to ensure that the sensor and the central processing unit are connected to the same network; if you choose Bluetooth, you need to set the MAC address and communication port of the Bluetooth device to ensure normal communication between the sensor and the Bluetooth gateway; if you choose LoRa, you need to set the channel and spreading factor of the LoRa device to ensure normal communication between the sensor and the LoRa gateway; if you choose RS485, you need to set the baud rate and data format of the RS485 device to ensure normal communication between the sensor and the central processing unit; if you choose Modbus, you need to set the device address and register address of the Modbus device to ensure normal communication between the sensor and the central processing unit.

[0034] After the sensor network starts working, various status parameters of the equipment are collected in real time. The collected data include current value, voltage value, temperature value, vibration value, humidity value and pressure value. Through the constructed data communication link, the collected data is transmitted to the central processing unit in real time. The central processing unit can be a server, computer or other data processing device. During data transmission, attention should be paid to data format, data integrity and data encryption. Ensure that the format of the data meets the requirements of the central processing unit, such as JSON, CSV, etc.; ensure that the data is not lost or damaged during transmission, and verify it through verification code and other methods; for sensitive data, encrypted transmission can be performed to ensure data security.

[0035] After receiving the data, the central processing unit performs preliminary processing, including data cleaning and format conversion. The processed data will be used for subsequent analysis and display. The specific steps include removing invalid or erroneous data to ensure the validity of the data; converting the data into a unified format for subsequent processing and analysis; and storing the processed data in a database for subsequent query and analysis.

[0036] The processed data is synchronized to the 3D model simulation of the building equipment in real time. The specific steps include mapping the data collected by the sensor to the corresponding position in the 3D model to ensure the accuracy of the data; updating the data in the 3D model in real time, and visually displaying the operating status of the equipment through color changes, icon flashing, etc.; providing a variety of data visualization methods, such as charts and graphs, to help users better understand and analyze data.

[0037] Before it is officially put into use, the data communication link needs to be tested to ensure its stability and reliability. The test content includes communication stability, communication speed, communication range and anti-interference ability. Test the stability of data transmission to ensure that data is not lost or damaged during transmission; test the speed of data transmission to ensure that data can be transmitted to the central processing unit in real time; test the range of data communication to ensure that the communication distance between the sensor and the central processing unit meets the requirements; test the anti-interference ability of data communication to ensure the stability of data transmission under electromagnetic interference and other environments.

[0038] According to the test results, the data communication link is optimized to improve its performance and reliability. The optimization measures include adding redundant equipment at key locations to improve the system's fault tolerance; optimizing communication parameters according to the test results to improve the efficiency and stability of data transmission; strengthening the physical protection of communication equipment to prevent equipment damage or theft; and strengthening the security of data transmission to prevent data from being stolen or tampered with.

[0039] In particular, the digital twin display module 330 is used to display the digital twin of the building equipment on the display screen. First of all, it is necessary to design a user-friendly interface so that users can easily view and operate the digital twin. The interface should be concise and easy to navigate. Specific design points include the reasonable layout of various functional modules, such as equipment list, real-time data display area, historical data query area, alarm information area, etc. Ensure that the position and size of each module are convenient for users to operate and view. Choose the right color combination to make the interface look comfortable and professional. For example, use cool colors to represent normal status and warm colors to represent abnormal status, so that users can identify the status of the equipment at a glance. Use intuitive icons and buttons so that users can quickly understand the role of each function. For example, use a magnifying glass icon to represent the search function and a gear icon to represent the setting function.

[0040] Next, a variety of view options are provided to meet the needs of different users. Common view options include overall view, partial zoom view, section view, and two-dimensional view. The overall view displays the 3D model of the entire building equipment, providing a global perspective so that users can quickly understand the overall layout and status of the equipment. The partial zoom view allows users to zoom in on a certain part of the equipment and view detailed information. For example, users can zoom in on the motor part of the equipment to view its temperature, current and other parameters. The section view provides a cross-sectional view of the equipment, showing the internal structure and components, which is very useful for understanding the internal working principle of the equipment. The two-dimensional view provides a two-dimensional plan view of the equipment, allowing users to quickly locate the equipment. The two-dimensional view can be used in conjunction with the three-dimensional model to provide more viewing options.

[0041] In terms of real-time data display, the data collected by the sensor is mapped to the corresponding position in the three-dimensional model in real time to ensure the accuracy of the data. The specific steps include receiving real-time data from the central processing unit. The central processing unit obtains data from the sensor network through a data communication link and transmits the data to the display system. Parse the received data and extract key parameters such as current value, voltage value, temperature value, etc. to ensure that the data format is correct for subsequent processing. Map the parsed data to the corresponding position in the three-dimensional model, for example, map the current value to the main power line of the device, and map the temperature value to the heating component of the device, to ensure that the data corresponds accurately to the position in the model, and the user can intuitively see the operating status of each part of the device.

[0042] In order to enable users to intuitively understand the working conditions of the equipment, the operating status of the equipment is displayed in a variety of visualization methods. Common visualization methods include color change, icon flashing, numerical display and charts. According to the change of data, the color of the corresponding part in the model is changed. For example, when the temperature exceeds the threshold, it is displayed in red; when the temperature is normal, it is displayed in green, so that users can identify the status of the equipment at a glance. When the equipment is abnormal, the corresponding icon or icon area flashes to remind the user to pay attention. For example, when the current exceeds the threshold, the corresponding icon flashes to remind the user to check the current. The numerical value of the data, such as current value, voltage value, etc., is directly displayed at the corresponding position of the model. Users can read the data directly without additional search. Provide charts and graphs of real-time data to show the trend of data changes. Users can view the operation of the equipment in different time periods and conduct data analysis and fault prediction.

[0043] In terms of interactive functions, users can click on a part of the device to view detailed information about that part. Specific functions include displaying basic information such as the model, manufacturer, and production date of the device, so that users can understand the basic properties of the device for easy management and maintenance. Displaying the real-time operating parameters of the device, such as current value, voltage value, temperature value, etc., allows users to monitor the operating status of the device in real time and detect abnormalities in a timely manner. Providing historical operating data of the device, users can view the operating status of the device in different time periods. Historical data helps users analyze the long-term performance of the device and formulate reasonable maintenance plans.

[0044] Provides animated demonstrations of the equipment's working process to help users better understand the working principle of the equipment. Specific functions include showing the entire work process of the equipment from start to stop, so that users can understand the equipment's operating steps and become familiar with the equipment's operating methods. Simulates the equipment's working status under different fault conditions to help users identify and troubleshoot faults. Users can understand possible problems with the equipment through fault simulation and prepare in advance.

[0045] In terms of alarm function, when the equipment is abnormal, the system automatically issues an alarm to remind the user to deal with it in time. Specific functions include sound alarms to remind users to pay attention. Sound alarms can quickly attract users' attention and avoid missing important fault information. Obvious alarm information is displayed on the screen, such as pop-up windows, flashing icons, etc. Visual alarms can continue to remind users until the user confirms and handles the fault. The time, location and cause of each alarm are recorded. Users can view historical alarm records for analysis and summary. Alarm records help users understand the fault history of the equipment and formulate improvement measures.

[0046] Different alarm levels are set according to the severity of the device abnormality. Specific levels include warnings indicating that the device has a minor abnormality that requires attention, for example, when the temperature is close to the threshold but does not exceed the threshold, the system issues a warning to prompt the user to pay attention. Alarms indicating that the device has a serious abnormality that requires immediate processing, for example, when the current exceeds the threshold, the system issues an alarm to prompt the user to check the current immediately. Urgent alarms indicating that the device has a major fault and needs to be shut down immediately for inspection, for example, when the temperature far exceeds the threshold, the system issues an emergency alarm to prompt the user to shut down immediately to prevent damage to the device.

[0047] In terms of operation guidance, maintenance suggestions are provided based on the operating status and historical data of the equipment to help users take timely measures. Specific functions include suggesting that users regularly perform equipment maintenance to prevent equipment aging and failure. Regular maintenance can extend the service life of the equipment and improve its reliability. Common troubleshooting guides are provided to help users quickly solve problems. The troubleshooting guides include fault phenomena, possible causes and solutions. Users can follow the guides to quickly restore the normal operation of the equipment.

[0048] Provides fault diagnosis function to help users quickly locate and solve equipment faults. Specific functions include providing fault diagnosis tools. Users can input abnormal symptoms of the equipment, and the system will give possible fault causes and solutions. Fault diagnosis tools can help users quickly locate faults and save time and energy. Provides online expert consulting services. Users can contact experts for consultation and help at any time. Experts can provide professional suggestions and solutions based on the user's description to help users solve complex fault problems.

[0049] In particular, the working state analysis module 340 is used to analyze the working state of the target building equipment to obtain an identification result. Figure 3 As shown, the working status analysis module 340 includes: a status parameter acquisition unit 341, which is used to use the data communication link to acquire the time queue of the status parameters of the target building equipment, wherein the status parameters include real-time current values ​​and real-time voltage values; a status parameter classification and encoding unit 342, which is used to perform data classification and sequence encoding on the time queue of the status parameters to obtain current timing implicit correlation features and voltage timing associated implicit features; a feature deviation correction significant interaction unit 343, which is used to perform feature deviation correction significant interaction on the current timing implicit correlation features and the voltage timing associated implicit features to obtain equipment current-voltage timing significant interaction features; an identification unit 344, which is used to obtain the identification result based on the equipment current-voltage timing significant interaction features, and the identification result is used to indicate whether the working status of the target building equipment is abnormal.

[0050] Specifically, the state parameter acquisition unit 341 is used to use the data communication link to acquire the time queue of the state parameters of the target building equipment, wherein the state parameters include real-time current value and real-time voltage value. It should be understood that the current value reflects the load condition of the equipment. By real-time monitoring of the current value, it can be determined whether the equipment is in normal working state and whether it is overloaded or lightly loaded. Overload may cause the equipment to overheat or even be damaged, while light load may indicate that the equipment is not fully utilized. Abnormal changes in current value may be early signs of equipment failure. For example, a sudden increase in current may indicate a short circuit or poor contact inside the equipment, and a sudden decrease in current may indicate a circuit disconnection or poor contact. The voltage value reflects the stability of the power supply. By real-time monitoring of the voltage value, it can be determined whether the power supply is stable and whether there is voltage fluctuation or abnormality. Voltage fluctuation may cause unstable operation of the equipment or even damage the equipment. Changes in voltage value can reflect the quality of power supply. For example, too high a voltage may cause the equipment to overheat, and too low a voltage may cause the equipment to fail to start or work normally.

[0051] Specifically, the state parameter classification encoding unit 342 is used to classify and sequence the time queue of the state parameter to obtain the current time series implicit correlation feature and the voltage time series implicit correlation feature. That is, first of all, considering that the voltage and current in the state parameter have their own patterns and time series change trends, for example, some specific current fluctuation patterns may indicate that there are potential problems with the equipment, while specific voltage change patterns may reflect the power supply situation, and there is a mutual correlation between the two parameters. Based on this, in the technical solution of the present application, the time queue of the state parameter is data classified to obtain the time queue of the real-time current value and the time queue of the real-time voltage value. Then, the time queue of the real-time current value and the time queue of the real-time voltage value are input into the sequence encoder based on the forward LSTM model to obtain the current time series implicit correlation feature vector as the current time series implicit correlation feature and the voltage time series implicit correlation feature vector as the voltage time series implicit correlation feature. Here, in order to further capture and mine the implicit timing associations in the time queue of the real-time current value and the time queue of the real-time voltage value, in the technical solution of the present application, the time queue of the real-time current value and the time queue of the real-time voltage value are input into a sequence encoder based on a forward LSTM model to utilize the forward LSTM model's expertise in processing long-term dependencies of long sequence data to effectively capture long-term associations and complex timing dynamic patterns in the time series, thereby obtaining the current timing association implicit feature vector and the voltage timing association implicit feature vector.

[0052] It is worth mentioning that LSTM is a special recurrent neural network (RNN) designed specifically for processing long sequence data, overcoming the gradient vanishing and gradient exploding problems of traditional RNN when processing long sequences. LSTM controls the flow and storage of information by introducing memory cells (cell state) and three gating mechanisms (input gate, forget gate, and output gate), enabling it to effectively capture and utilize long-term dependencies. For the time queue of real-time current values ​​and the time queue of real-time voltage values, the forward LSTM model can extract their time series implicit correlation features. These features contain not only information at the current moment, but also information at historical moments, which helps to fully understand the operating status of the equipment. In addition, the abnormal state of the equipment can be more accurately identified by extracting the time series implicit correlation features. The LSTM model can capture the complex interactive relationship between current and voltage, thereby improving the accuracy and robustness of fault detection.

[0053] Specifically, the feature deviation correction significant interaction unit 343 is used to perform feature deviation correction significant interaction on the current timing implicit correlation feature and the voltage timing associated implicit feature to obtain the device current-voltage timing significant interaction feature. Considering that there is a mutual correlation between the current timing implicit correlation feature and the voltage timing associated implicit feature in the time dimension. For example, a sudden change in current may cause voltage fluctuations. Therefore, although the individual current and voltage feature vectors already contain their respective time series information, they may not be able to fully reflect the overall state of the device. Based on this, in order to capture the significant interaction relationship between current and voltage, so as to more comprehensively and accurately evaluate the working state of the device, in the technical solution of the present application, the current timing implicit correlation feature vector and the voltage timing associated implicit feature vector are subjected to feature deviation correction significant interaction to obtain the device current-voltage timing significant interaction feature vector as the device current-voltage timing significant interaction feature.

[0054] Specifically, first, the current timing implicit correlation feature vector and the voltage timing implicit correlation feature vector are respectively subjected to feature modulation and interpolation processing to obtain the modulated current timing implicit correlation feature vector and the modulated voltage timing implicit correlation feature vector as well as the interpolated current timing implicit correlation feature vector and the interpolated voltage timing implicit correlation feature vector. That is, in an embodiment of the present application, first, the current time series implicit association feature vector and the voltage time series implicit association feature vector are input into a co-space mapper based on a fully connected layer to obtain the modulated current time series implicit association feature vector and the modulated voltage time series implicit association feature vector, wherein the modulated current time series implicit association feature vector and the modulated voltage time series implicit association feature vector have the same feature scale; here, considering that the features located in different feature spaces cannot directly interact across spaces, the co-space mapper constructed by the fully connected layer modulates the current time series implicit association feature vector and the voltage time series implicit association feature vector to capture the complex nonlinear relationship between the features, and ensure that the two features are consistent and stable, so as to obtain the modulated current time series implicit association feature vector and the modulated voltage time series implicit association feature vector. Then, the current time series implicit association feature vector and the voltage time series implicit association feature vector are interpolated to obtain the interpolated current time series implicit association feature vector and the interpolated voltage time series implicit association feature vector. Since some details of the original features may be lost during the spatial mapping of the current and voltage time series features, the omission of this information may weaken the effectiveness of feature interaction analysis, and if there is a certain correlation or covariation relationship between the features, independent spatial transformation may destroy these connections, making it more complicated to identify the mutual influence between them in subsequent analysis. Therefore, feature deviation compensation is performed on the original current and voltage time series features after mapping. Specifically, the current time series implicit association feature vector and the voltage time series implicit association feature vector are first interpolated to adjust the time resolution of the original features, improve the model's perception of small changes in a short period of time, and obtain the current time series implicit association feature vector after the interpolation processing and the voltage time series implicit association feature vector after the interpolation processing.

[0055] Among them, the specific steps of inputting the current timing implicit correlation feature vector and the voltage timing implicit correlation feature vector into a common space mapper based on a fully connected layer include: performing matrix-vector multiplication on the weight matrix and the current timing implicit correlation feature vector, and then adding them positionally with the bias vector to obtain the current timing implicit coding vector; performing matrix-vector multiplication on the weight matrix and the voltage timing implicit correlation feature vector, and then adding them positionally with the bias vector to obtain the voltage timing implicit coding vector; respectively inputting the current timing implicit coding vector and the voltage timing implicit coding vector into the Relu function for mapping processing to obtain the modulated current timing implicit correlation feature vector and the modulated voltage timing implicit correlation feature vector.

[0056] In summary, in the above embodiment, the current timing implicit association characteristic vector and the voltage timing implicit association characteristic vector are respectively subjected to characteristic modulation and interpolation processing to obtain the modulated current timing implicit association characteristic vector and the modulated voltage timing implicit association characteristic vector, as well as the interpolated current timing implicit association characteristic vector and the interpolated voltage timing implicit association characteristic vector, including: the current timing implicit association characteristic vector and the voltage timing implicit association characteristic vector are respectively subjected to characteristic modulation and interpolation processing to obtain the modulated current timing implicit association characteristic vector and the modulated voltage timing implicit association characteristic vector, as well as the interpolated current timing implicit association characteristic vector and the interpolated voltage timing implicit association characteristic vector according to the following characteristic modulation and interpolation formula; wherein the characteristic modulation and interpolation formula is: ;in, and are respectively the current time series implicit correlation feature vector and the voltage time series implicit correlation feature vector, and are the weight matrix and bias vector respectively, yes function, and They are the implicit correlation eigenvector of the modulated current sequence and the implicit correlation eigenvector of the modulated voltage sequence, To interpolate the eigenvectors, and They are respectively the implicit correlation feature vector of current time series after interpolation processing and the implicit correlation feature vector of voltage time series after interpolation processing.

[0057] Next, based on the interpolation-processed current timing implicit association feature vector and the interpolation-processed voltage timing implicit association feature vector, semantic compensation multi-dimensional significant interaction is performed on the modulated current timing implicit association feature vector and the modulated voltage timing implicit association feature vector respectively to obtain the device current-voltage timing significant interaction feature. That is, in an embodiment of the present application, first, the interpolation-processed current timing implicit association feature vector and the modulated current timing implicit association feature vector as well as the interpolation-processed voltage timing implicit association feature vector and the modulated voltage timing implicit association feature vector are input into a feature mapping deviation semantic measurement network to adjust the feature so that it is closer to the real state, so as to obtain the current timing mapping deviation semantic compensation factor and the voltage timing mapping deviation semantic compensation factor. Next, based on the current timing mapping deviation semantic compensation factor and the voltage timing mapping deviation semantic compensation factor, the modulated current timing implicit association feature vector and the modulated voltage timing associated implicit feature vector are compensated to obtain the compensated current timing implicit association feature modulation vector and the compensated voltage timing associated implicit feature modulation vector. That is, in this step, the previously detected deviation is actually compensated, and the modulated vector is adjusted or calibrated by applying the corresponding compensation factor to generate a more accurate and consistent compensated feature modulation vector, so as to enhance the model's ability to recognize detail changes. Finally, the compensated current timing implicit association feature modulation vector and the compensated voltage timing associated implicit feature modulation vector are input into the multi-dimensional significant interaction network between features to obtain significant patterns that are difficult to represent from a single current and voltage feature, and obtain the device current-voltage timing significant interaction feature vector.

[0058] Among them, the specific steps of inputting the compensated current timing implicit correlation feature modulation vector and the compensated voltage timing implicit correlation feature modulation vector into the multidimensional significant interaction network between features include: respectively calculating the position point subtraction, position point multiplication, position point addition and position point division between the compensated current timing implicit correlation feature modulation vector and the compensated voltage timing implicit correlation feature modulation vector to obtain the compensated current and voltage timing point subtraction vector, the compensated current and voltage timing point multiplication vector, the compensated current and voltage timing point addition vector and the compensated current and voltage timing point division vector; cascading the compensated current and voltage timing point subtraction vector, the compensated current and voltage timing point multiplication vector, the compensated current and voltage timing point addition vector and the compensated current and voltage timing point division vector and inputting them into a one-dimensional convolutional coding module to obtain a multidimensional collaborative interaction vector of current and voltage timing features; performing local window-based maximum value pooling processing on the multidimensional collaborative interaction vector of current and voltage timing features to obtain the device current-voltage timing significant interaction feature vector.

[0059] In summary, in the above embodiment, based on the interpolation processing of the current timing implicit association feature vector and the interpolation processing of the voltage timing implicit association feature vector, the semantic compensation multi-dimensional significant interaction is performed on the modulated current timing implicit association feature vector and the modulated voltage timing implicit association feature vector respectively to obtain the device current-voltage timing significant interaction feature, including: based on the interpolation processing of the current timing implicit association feature vector and the interpolation processing of the voltage timing implicit association feature vector, the following semantic compensation multi-dimensional significant interaction formula is used to perform semantic compensation multi-dimensional significant interaction on the modulated current timing implicit association feature vector and the modulated voltage timing implicit association implicit feature vector to obtain the device current-voltage timing significant interaction feature; wherein, the semantic compensation multi-dimensional significant interaction formula is: ;in, For the The eigenvalues ​​at each position in , For the The eigenvalues ​​at each position in , For the The eigenvalues ​​at each position in , For the The eigenvalues ​​at each position in , It means to calculate the logarithmic function value with base 2. is the and stated The number of eigenvalues ​​in , It means to calculate the exponential function value with the natural constant e as the base. is the semantic compensation factor for the current timing mapping deviation, is the voltage timing mapping deviation semantic compensation factor, is the implicit correlation characteristic modulation vector of the current timing after compensation, is the implicit characteristic modulation vector of the voltage timing correlation after compensation, and They are point-by-point subtraction, point-by-point multiplication, point-by-point addition, and point-by-point division. For cascade processing, is a one-dimensional convolutional coding operation, is the maximum pooling operation, is the significant interaction feature vector of the device current-voltage timing.

[0060] Specifically, the identification unit 344 is used to obtain the identification result based on the significant interaction feature of the device current-voltage time series, and the identification result is used to indicate whether the working state of the target building equipment is abnormal. In a specific example of the present application, the device current-voltage time series significant interaction feature vector is input into the device state identifier based on the SVM model to obtain the identification result, and the identification result is used to indicate whether the working state of the target building equipment is abnormal. That is, the device current-voltage time series significant interaction feature obtained by the significant interaction of the current time series implicit association feature vector and the voltage time series associated implicit feature vector is used for classification processing to automatically determine whether the working state of the target building equipment is abnormal. In this way, through the sensor network and the data communication link, the operation data of the equipment can be collected in real time, the real-time monitoring of the equipment state can be realized, and the time series interaction feature between the current and the voltage can be captured, so as to more comprehensively evaluate the working state of the equipment, thereby improving the accuracy and intelligence of fault detection.

[0061] Here, when the current timing implicit correlation feature vector and the voltage timing implicit correlation feature vector represent the short-range and long-range bidirectional timing correlation features of the current value and the voltage value respectively, when performing feature interaction optimization based on feature mapping deviation compensation, the device current-voltage timing significant interaction feature vector will also have multi-dimensional timing feature mapping deviation compensation diversity under the source data timing distribution difference, thereby having feature interaction distribution diversity based on feature mapping deviation compensation. Therefore, when the device current-voltage timing significant interaction feature vector is subjected to probabilistic regression through the device state identifier based on the SVM model, it will affect the accuracy of the regression result.

[0062] Therefore, the present application hopes to improve the overall interaction semantic consistency aggregation expression effect of the device current-voltage timing significant interaction feature vector when the device current-voltage timing significant interaction feature vector is input into the device state identifier based on the SVM model to obtain the identification result, thereby optimizing it.

[0063] That is, preferably, inputting the device current-voltage time series significant interaction feature vector into the device state identifier based on the SVM model to obtain the identification result includes: performing feature clustering on all feature values ​​of the device current-voltage time series significant interaction feature vector to obtain a device current-voltage time series significant interaction intra-class feature set The set of out-of-class features that significantly interact with the device current-voltage timing ,in, Represents the intra-class feature set of the significant interaction between the current and voltage time series of the device, The first feature set representing the significant interaction between the device current and voltage time series eigenvalues, The first one represents the set of out-of-class features of the device current-voltage time series significant interaction feature values.

[0064] Calculate the ratio of the number of eigenvalues ​​in the feature set within the device current-voltage time series significant interaction class to the number of eigenvalues ​​of all features of the device current-voltage time series significant interaction feature vector ,in, represents the number of eigenvalues ​​in the feature set within the class of significant interaction between current and voltage time series of the device, The number of eigenvalues ​​of all features representing the significant interaction eigenvectors of the device current-voltage timing series, Indicates a ratio.

[0065] Calculate the sum of the absolute values ​​of all feature values ​​in the feature set within the device current-voltage timing significant interaction class The sum of the absolute values ​​of all eigenvalues ​​in the eigenvector of the significant interaction between the current and voltage timing of the device The ratio of the powers is used to obtain the first device current-voltage timing significant interaction weight.

[0066] Calculate the sum of squares of all feature values ​​in the feature set of the device current-voltage timing significant interaction class The power of the sum of the squares of all eigenvalues ​​in the device current-voltage timing significant interaction eigenvector and the sum of the squares of all eigenvalues ​​in the device current-voltage timing significant interaction eigenvector The ratio of the powers is used to obtain the significant interaction weight of the current-voltage timing of the second device.

[0067] That is, the first device current-voltage timing significant interaction weight and the second device current-voltage timing significant interaction weights It is expressed as: ;in, Represents each eigenvalue of the significant interaction eigenvector of the current-voltage timing of the device, represents the significant interaction weight of the current-voltage timing of the first device, Represents the significant interaction weight of the current-voltage timing of the second device.

[0068] Then, for each feature value in the feature set within the device current-voltage timing significant interaction class, calculate the product of the feature value and the second device current-voltage timing significant interaction weight plus the first device current-voltage timing significant interaction weight to obtain the optimized feature value ;in, represents the first feature set of the device current-voltage time series significant interaction class Optimize the eigenvalues.

[0069] For each feature value in the device current-voltage timing significant interaction out-of-class feature set, calculate the product of the feature value and the first device current-voltage timing significant interaction weight to obtain an optimized feature value ;in, represents the first set of out-of-class features based on the significant interaction of the device current-voltage time series Optimize the eigenvalues.

[0070] Finally, an optimized device current-voltage timing significant interaction feature vector is formed based on the optimized feature values ​​of the feature set within the device current-voltage timing significant interaction class and the feature set outside the device current-voltage timing significant interaction class, and the optimized device current-voltage timing significant interaction feature vector is input into the device state identifier based on the SVM model to obtain the identification result.

[0071] That is, while the device current-voltage timing significant interaction feature vector is subjected to feature clustering, the interaction description of the key feature information of the device current-voltage timing significant interaction feature vector in the clustering process is carried out, and the geometric equivariant topology of the feature is constructed by low-rank harmonic modulation of the features on the equivariant basis of the clustering features of the device current-voltage timing significant interaction feature vector and the feature as a whole, so as to obtain the graphical distribution translation and rotation symmetry of the clustering features of the device current-voltage timing significant interaction feature vector relative to the feature as a whole, thereby introducing geometric message passing into the feature expression of the device current-voltage timing significant interaction feature vector and realizing the clustering mapping symmetry of the device current-voltage timing significant interaction feature vector through manipulation of irreducible low-rank order coefficients, thereby improving the consistency of the clustering-based feature representation of the device current-voltage timing significant interaction feature vector, thereby improving the accuracy of the recognition result obtained by inputting the device current-voltage timing significant interaction feature vector into the device state identifier based on the SVM model. In this way, through the sensor network and data communication link, the operating data of the equipment can be collected in real time, the real-time monitoring of the equipment status can be realized, and the timing interaction characteristics between current and voltage can be captured, so as to more comprehensively evaluate the working status of the equipment and thus improve the accuracy and intelligence of fault detection.

[0072] In particular, the identification status display module 350 is used to display the identification status on the display screen. First, design a user-friendly interface so that users can easily view and operate the digital twin. The interface should be concise and easy to navigate. Specific design points include the reasonable layout of various functional modules, such as device lists, real-time data display areas, historical data query areas, alarm information areas, etc. Ensure that the position and size of each module are convenient for users to operate and view. Choose the right color combination to make the interface look comfortable and professional. For example, use cool colors to represent normal states and warm colors to represent abnormal states, so that users can identify the status of the device at a glance. Use intuitive icons and buttons so that users can quickly understand the role of each function. For example, use a magnifying glass icon to represent the search function and a gear icon to represent the setting function.

[0073] Provides a variety of view options to meet the needs of different users. Common view options include overall view, partial magnification view, section view and two-dimensional view. The overall view displays the 3D model of the entire building equipment, providing a global perspective, so that users can quickly understand the overall layout and status of the equipment. The partial magnification view allows users to zoom in on a part of the equipment and view detailed information. For example, users can zoom in on the motor part of the equipment to view its temperature, current and other parameters. The section view provides a cross-sectional view of the equipment, showing the internal structure and components, which is very useful for understanding the internal working principle of the equipment. The two-dimensional view provides a two-dimensional plan view of the equipment, which allows users to quickly locate the equipment. The two-dimensional view can be used in conjunction with the three-dimensional model to provide more viewing options.

[0074] Next, the data collected by the sensor is mapped to the corresponding position in the three-dimensional model in real time to ensure the accuracy of the data. The specific steps include receiving real-time data from the central processing unit. The central processing unit obtains data from the sensor network through a data communication link and transmits the data to the display system. Parse the received data and extract key parameters such as current value, voltage value, temperature value, etc. to ensure that the data format is correct for subsequent processing. Map the parsed data to the corresponding position in the three-dimensional model, for example, map the current value to the main power line of the device, and map the temperature value to the heating component of the device, to ensure that the data corresponds accurately to the position in the model, and the user can intuitively see the operating status of each part of the device.

[0075] The operating status of the equipment is displayed in a variety of visual ways, so that users can intuitively understand the working status of the equipment. Common visualization methods include color change, icon flashing, numerical display and chart. According to the change of data, the color of the corresponding part in the model is changed. For example, when the temperature exceeds the threshold, it is displayed in red; when the temperature is normal, it is displayed in green, so that users can identify the status of the equipment at a glance. When the equipment is abnormal, the corresponding icon or icon area flashes to remind the user. For example, when the current exceeds the threshold, the corresponding icon flashes to remind the user to check the current. The numerical value of the data, such as current value, voltage value, etc., is directly displayed at the corresponding position of the model, and the user can directly read the data without additional search. Provide charts and graphs of real-time data to show the trend of data changes. Users can view the operation of the equipment in different time periods and conduct data analysis and fault prediction.

[0076] In terms of interactive functions, users can click on a part of the device to view detailed information about that part. Specific functions include displaying basic information such as the model, manufacturer, and production date of the device, so that users can understand the basic properties of the device for easy management and maintenance. Displaying the real-time operating parameters of the device, such as current value, voltage value, temperature value, etc., users can monitor the operating status of the device in real time and detect abnormalities in time. Providing historical operating data of the device, users can view the operating status of the device in different time periods. Historical data helps users analyze the long-term performance of the device and formulate reasonable maintenance plans. Provide animated demonstrations of the working process of the equipment to help users better understand the working principle of the equipment. Specific functions include showing the entire workflow of the equipment from startup to shutdown, so that users can understand the operating steps of the equipment and become familiar with the operation methods of the equipment. Simulating the working status of the equipment under different fault conditions helps users identify and troubleshoot faults. Users can understand possible problems with the equipment through fault simulation and prepare in advance.

[0077] In terms of alarm function, when the device is abnormal, the system automatically issues an alarm to remind the user to deal with it in time. Specific functions include sound alarms to remind users to pay attention. Sound alarms can quickly attract users' attention and avoid missing important fault information. Obvious alarm information is displayed on the screen, such as pop-up windows, flashing icons, etc. Visual alarms can continue to remind users until the user confirms and handles the fault. The time, location and cause of each alarm are recorded. Users can view historical alarm records for analysis and summary. Alarm records help users understand the fault history of the device and formulate improvement measures. Different alarm levels are set according to the severity of the device abnormality. Specific levels include warnings indicating that the device has a minor abnormality and needs to be paid attention to. For example, the temperature is close to the threshold but does not exceed the threshold. The system issues a warning to remind the user to pay attention. Alarms indicating that the device has a serious abnormality and needs to be handled immediately. For example, the current exceeds the threshold. The system issues an alarm to remind the user to check the current immediately. Indicates that the device has a major fault and needs to be stopped immediately for inspection. For example, the temperature far exceeds the threshold. The system issues an emergency alarm to remind the user to stop immediately to prevent damage to the device.

[0078] In terms of operation guidance, maintenance suggestions are provided based on the operating status and historical data of the equipment to help users take timely measures. Specific functions include suggesting that users regularly perform equipment maintenance to prevent equipment aging and failure. Regular maintenance can extend the service life of the equipment and improve the reliability of the equipment. Common troubleshooting guides are provided to help users quickly solve problems. The troubleshooting guides include fault phenomena, possible causes and solutions. Users can follow the guides to quickly restore the normal operation of the equipment. Fault diagnosis functions are provided to help users quickly locate and solve equipment failures. Specific functions include providing fault diagnosis tools. Users can enter abnormal symptoms of the equipment, and the system will give possible causes and solutions. Fault diagnosis tools can help users quickly locate faults and save time and energy. Online expert consulting services are provided. Users can contact experts for consultation and help at any time. Experts can provide professional advice and solutions based on the user's description to help users solve complex fault problems.

[0079] Through the above steps, the identification status of building equipment can be clearly and intuitively displayed on the display screen, allowing users to monitor the operating status of the equipment in real time, discover and handle faults in a timely manner, and improve the management efficiency and reliability of the equipment. This process not only improves the user experience, but also provides strong support for the management and maintenance of building equipment. The application of digital twins is not limited to equipment management, but can also be extended to training and education, design and planning, emergency response and other fields, providing strong technical support for the modernization and transformation of the construction industry.

[0080] As described above, the construction equipment training data processing system 300 based on digital twins according to the embodiment of the present application can be implemented in various wireless terminals, such as a server with a construction equipment training data processing algorithm based on digital twins. In one possible implementation, the construction equipment training data processing system 300 based on digital twins according to the embodiment of the present application can be integrated into the wireless terminal as a software module and / or hardware module. For example, the construction equipment training data processing system 300 based on digital twins can be a software module in the operating system of the wireless terminal, or it can be an application developed for the wireless terminal; of course, the construction equipment training data processing system 300 based on digital twins can also be one of the many hardware modules of the wireless terminal.

[0081] Alternatively, in another example, the digital twin-based construction equipment training data processing system 300 and the wireless terminal may also be separate devices, and the digital twin-based construction equipment training data processing system 300 may be connected to the wireless terminal via a wired and / or wireless network and transmit interactive information in accordance with an agreed data format.

[0082] Furthermore, a method for processing construction equipment training data based on digital twins is also provided.

[0083] Figure 4 Flowchart of a method for processing construction equipment training data based on digital twins according to an embodiment of the present application. Figure 4 As shown, according to the digital twin-based construction equipment training data processing method of the embodiment of the present application, the steps include: S1, constructing a three-dimensional model of the target construction equipment based on BIM technology to obtain a three-dimensional model simulation body of the construction equipment; S2, constructing a data communication link between the sensor network deployed on the target construction equipment and the three-dimensional model simulation body of the construction equipment to obtain a digital twin of the construction equipment; S3, displaying the digital twin of the construction equipment on a display screen; S4, analyzing the working status of the target construction equipment to obtain an identification result; S5, displaying the identification status on the display screen.

[0084] In summary, the method for processing building equipment training data based on digital twins according to the embodiment of the present application is explained, which uses a data communication link to obtain the time queue of the state parameters (real-time current value and real-time voltage value) of the target building equipment, and uses artificial intelligence data processing and encoding methods to perform data classification and time series implicit association encoding of the state parameters, so as to automatically judge whether there is an abnormality in the working state of the target building equipment based on the significant interaction characteristics between the current time series implicit association characteristics and the voltage time series implicit association characteristics. In this way, through the sensor network and data communication link, the operating data of the equipment can be collected in real time, and the real-time monitoring of the equipment status can be realized. At the same time, the time series interaction characteristics between current and voltage can be captured, so as to more comprehensively evaluate the working state of the equipment, thereby improving the accuracy and intelligence of fault detection.

[0085] The embodiments of the present disclosure have been described above, and the above description is exemplary, not exhaustive, and is not limited to the disclosed embodiments. Many modifications and changes will be apparent to those of ordinary skill in the art without departing from the scope and spirit of the described embodiments. The selection of terms used herein is intended to best explain the principles of the embodiments, practical applications, or improvements to the technology in the market, or to enable other persons of ordinary skill in the art to understand the embodiments disclosed herein.

Claims

1. A construction equipment training data processing system based on digital twins, characterized in that: include: A building equipment simulation module, which is used to construct a three-dimensional model of target building equipment based on BIM technology to obtain a three-dimensional model simulation body of the building equipment; A digital twin deployment module, used to construct a data communication link between a sensor network deployed on the target building equipment and the three-dimensional model simulation of the building equipment to obtain a digital twin of the building equipment; A digital twin display module, used for displaying the digital twin of the building equipment on a display screen; A working status analysis module, used for analyzing the working status of the target building equipment to obtain an identification result; An identification status display module is used to display the identification status on the display screen; wherein the working status analysis module includes: a status parameter acquisition unit, which is used to use the data communication link to acquire the time queue of the status parameters of the target building equipment, wherein the status parameters include real-time current value and real-time voltage value; a status parameter classification and coding unit, which is used to perform data classification and sequence coding on the time queue of the status parameters to obtain current timing implicit correlation features and voltage timing associated implicit features; a feature deviation correction significant interaction unit, which is used to perform feature deviation correction significant interaction on the current timing implicit correlation features and the voltage timing associated implicit features to obtain equipment current-voltage timing significant interaction features; an identification unit, which is used to obtain the identification result based on the equipment current-voltage timing significant interaction features, and the identification result is used to indicate whether the working status of the target building equipment is abnormal; Among them, the characteristic deviation correction significant interaction unit includes: a current and voltage characteristic modulation and interpolation processing subunit, which is used to perform characteristic modulation and interpolation processing on the current timing implicit association characteristic vector and the voltage timing associated implicit characteristic vector respectively to obtain the modulated current timing implicit association characteristic vector and the modulated voltage timing associated implicit characteristic vector and the interpolated current timing implicit association characteristic vector and the interpolated voltage timing associated implicit characteristic vector; a current and voltage timing significant interaction subunit, which is used to perform semantic compensation multi-dimensional significant interaction on the modulated current timing implicit association characteristic vector and the modulated voltage timing associated implicit characteristic vector based on the interpolated current timing implicit association characteristic vector and the interpolated voltage timing associated implicit characteristic vector respectively to obtain the device current-voltage timing significant interaction characteristics.

2. The construction equipment training data processing system based on digital twin according to claim 1 is characterized in that: The state parameter classification encoding unit includes: a data classification subunit, which is used to classify the time queue of the state parameter to obtain a time queue of real-time current values ​​and a time queue of real-time voltage values; a sequence encoding subunit, which is used to input the time queue of real-time current values ​​and the time queue of real-time voltage values ​​into a sequence encoder based on a forward LSTM model to obtain a current time series implicit association feature vector as the current time series implicit association feature and a voltage time series association implicit feature vector as the voltage time series association implicit feature.

3. The construction equipment training data processing system based on digital twin according to claim 2 is characterized in that: The current and voltage feature modulation interpolation processing subunit includes: a current and voltage timing modulation secondary subunit, which is used to input the current timing implicit association feature vector and the voltage timing associated implicit feature vector into a co-space mapper based on a fully connected layer to obtain the modulated current timing implicit association feature vector and the modulated voltage timing associated implicit feature vector, wherein the modulated current timing implicit association feature vector and the modulated voltage timing associated implicit feature vector have the same characteristic scale; an interpolation processing secondary subunit, which is used to perform interpolation processing on the current timing implicit association feature vector and the voltage timing associated implicit feature vector to obtain the interpolated current timing implicit association feature vector and the interpolated voltage timing associated implicit feature vector, wherein the interpolated current timing implicit association feature vector and the modulated current timing implicit association feature vector have the same characteristic scale, and the interpolated voltage timing associated implicit feature vector and the modulated voltage timing associated implicit feature vector have the same characteristic scale.

4. The construction equipment training data processing system based on digital twin according to claim 3 is characterized in that: The current and voltage timing modulation secondary subunit is used to: perform matrix-vector multiplication on the weight matrix and the current timing implicit association characteristic vector, and then add them to the bias vector in position to obtain the current timing implicit coding vector; perform matrix-vector multiplication on the weight matrix and the voltage timing implicit association characteristic vector, and then add them to the bias vector in position to obtain the voltage timing associated implicit coding vector; respectively input the current timing implicit coding vector and the voltage timing associated implicit coding vector into the Relu function for mapping processing to obtain the modulated current timing implicit association characteristic vector and the modulated voltage timing associated implicit characteristic vector.

5. The construction equipment training data processing system based on digital twin according to claim 4 is characterized in that: The current-voltage timing significant interaction subunit includes: a current-voltage timing deviation compensation secondary subunit, which is used to input the interpolation-processed current timing implicitly associated feature vector and the modulated current timing implicitly associated feature vector, as well as the interpolation-processed voltage timing associated implicit feature vector and the modulated voltage timing associated implicit feature vector into a feature mapping deviation semantic measurement network to obtain a current timing mapping deviation semantic compensation factor and a voltage timing mapping deviation semantic compensation factor; a current-voltage timing mapping deviation semantic compensation secondary subunit, which is used to obtain a current timing mapping deviation semantic compensation factor and a voltage timing mapping deviation semantic compensation factor based on the current timing mapping deviation semantic compensation factor and the modulated voltage timing associated implicit feature vector. The voltage timing mapping deviation semantic compensation factor compensates the modulated current timing implicit association feature vector and the modulated voltage timing implicit association feature vector to obtain the compensated current timing implicit association feature modulation vector and the compensated voltage timing implicit association feature modulation vector; the current-voltage timing feature interaction secondary subunit is used to input the compensated current timing implicit association feature modulation vector and the compensated voltage timing implicit association feature modulation vector into the multi-dimensional significant interaction network between features to obtain the device current-voltage timing significant interaction feature vector as the device current-voltage timing significant interaction feature.

6. The construction equipment training data processing system based on digital twin according to claim 5 is characterized in that: The current and voltage timing characteristic interaction secondary subunit is used to respectively calculate the position point subtraction, position point multiplication, position point addition and position point division between the compensated current timing implicitly associated characteristic modulation vector and the compensated voltage timing associated implicit characteristic modulation vector to obtain the compensated current and voltage timing point subtraction vector, the compensated current and voltage timing point multiplication vector, the compensated current and voltage timing point addition vector and the compensated current and voltage timing point division vector; The compensated current and voltage timing point subtraction vector, the compensated current and voltage timing point multiplication vector, the compensated current and voltage timing point addition vector and the compensated current and voltage timing point division vector are cascaded and input into a one-dimensional convolutional coding module to obtain a current and voltage timing feature multi-dimensional collaborative interaction vector; The multi-dimensional collaborative interaction vector of the current and voltage time series characteristics is subjected to a local window-based maximum pooling process to obtain a significant interaction feature vector of the device current-voltage time series.

7. The construction equipment training data processing system based on digital twin according to claim 6 is characterized in that: The identification unit is used to: input the equipment current-voltage time series significant interaction feature vector into the equipment state identifier based on the SVM model to obtain the identification result, and the identification result is used to indicate whether the working state of the target building equipment is abnormal.

8. A construction equipment training data processing method based on digital twins, used in the construction equipment training data processing system based on digital twins according to claim 1, characterized in that: include: Construct a three-dimensional model of target building equipment based on BIM technology to obtain a three-dimensional model simulation of the building equipment; Constructing a data communication link between a sensor network deployed on the target building equipment and the three-dimensional model simulation of the building equipment to obtain a digital twin of the building equipment; and displaying the digital twin of the building equipment on a display screen; Analyzing the working status of the target building equipment to obtain an identification result; The identification status is displayed on the display screen.

Images