Park operation abnormity alarm method and device based on digital twin system

Abstract

The embodiment of the invention provides a park operation abnormity alarm method and device based on a digital twin system, and belongs to the technical field of intelligent park operation and maintenance. The method comprises the following steps: acquiring a park digital twin model of a target park; a plurality of entity items are deployed in the target park, and the park digital twin model comprises a plurality of twin sub-models; acquiring real-time operation data of each entity item in the target park; performing fault analysis on the real-time operation data to obtain fault operation data including fault entity information, fault levels and item fault analysis parameters; generating fault processing suggestions based on the item fault analysis parameters; determining a fault sub-model based on the twinborn corresponding relation and the fault entity information; and determining an alarm rendering parameter based on the fault level, and performing alarm rendering on a fault sub-model in the park digital twin model based on the alarm rendering parameter, the item fault analysis parameter and the fault processing suggestion. According to the embodiment of the invention, the timeliness and intuition of abnormal operation alarm of the park can be improved.

Description

Technical Field

[0001] This application relates to the field of smart park operation and maintenance technology, and in particular to a method and device for alarming abnormal park operation based on a digital twin system. Background Technology

[0002] Currently, anomaly monitoring in park management scenarios primarily relies on IoT platforms. These platforms collect operational data from various devices within the park, analyze these data for anomalies, and notify park maintenance personnel via SMS or email when anomalies are detected. However, in practice, this IoT-based anomaly monitoring method suffers from issues such as delayed alarms and unintuitive alarm notifications.

[0003] Therefore, improving the timeliness and intuitiveness of alarms for abnormal park operations has become an urgent technical problem to be solved. Summary of the Invention

[0004] The main objective of this application is to propose a method and apparatus for alarming abnormal park operations based on a digital twin system, which aims to improve the timeliness and intuitiveness of alarming abnormal park operations.

[0005] To achieve the above objectives, a first aspect of this application proposes a method for alarming abnormal campus operations based on a digital twin system, the method comprising: Obtain a digital twin model of the target park; wherein the target park has multiple physical items deployed, the digital twin model of the park includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; Obtain real-time operational data for each of the physical items in the target park; Fault analysis is performed on the real-time operating data to obtain fault operating data; wherein, the fault operating data includes fault entity information, fault level, and item fault analysis parameters; Based on the fault analysis parameters of the item, generate fault handling suggestions; The fault sub-model is determined based on the twin correspondence and the fault entity information; Based on the fault level, alarm rendering parameters are determined, and based on the alarm rendering parameters, the item fault analysis parameters, and the fault handling suggestions, alarm rendering is performed on the fault sub-model in the digital twin model of the park.

[0006] In some embodiments, the step of performing fault analysis on the real-time operating data to obtain fault operating data includes: Obtain operational reference data for each of the physical items in the target park; wherein, the operational reference data includes historical operational data and park expert annotation data; For each physical item, the real-time operating data is subjected to status detection based on the historical operating data and the park expert annotation data to obtain the real-time operating status; wherein, the real-time operating status is used to characterize whether the physical item is in a stable operating state or a faulty operating state during operation. If the real-time operating status indicates that the physical item is in a faulty operating state during operation, fault analysis is performed based on the real-time operating data to obtain the faulty operating data.

[0007] In some embodiments, for each of the physical items, the step of performing status detection on the real-time operating data based on the historical operating data and the park expert annotation data to obtain the real-time operating status includes: Obtain information about the current operating environment; For each of the aforementioned entity items, the historical operating data and the park expert annotation data are matched based on the current operating environment information to obtain matched operating data; wherein, the historical operating environment information of the matched operating data is matched with the current operating environment information; Data analysis is performed on the matching operation data to obtain the steady-state operation data of each entity item; Based on the steady-state operating data, fault diagnosis is performed on the real-time operating data to obtain fault diagnosis results; The real-time operating status is generated based on the fault diagnosis results.

[0008] In some embodiments, the digital twin model of the park is constructed in the following manner: Receive a model drag command; wherein the model drag command includes a twin model and drag position information; Based on the drag position information, the twin model is placed on a preset park model sandbox to obtain the original park model; Receive a model connector drag command; wherein the model connector drag command includes connector type and connector position information; Based on the connector type and connector location information, the original park model is connected to obtain an initial park model; A relationship mapping is performed between the initial park model and the target park to obtain the digital twin model of the park.

[0009] In some embodiments, the step of connecting the original park model based on the connector type and the connector location information to obtain an initial park model includes: Based on the location information of the connectors, the original park model is filtered into sub-models to be connected. The target connector is determined based on the connector type; Determine the connection positioning point of the sub-model to be connected according to the type of connector; The sub-models to be connected are connected based on the connection positioning point and the target connector to obtain the initial park model.

[0010] In some embodiments, mapping the initial park model to the target park to obtain the park's digital twin model includes: Obtain the first location relationship information and IoT information interface for each of the physical items in the target park; Obtain the second positional relationship information of each twin model in the initial park model; The entity item is associated with the twin model based on the first positional relationship information and the second positional relationship information to obtain the twin correspondence relationship; Based on the twin correspondence, the twin sub-model is connected to the IoT information interface to obtain the digital twin model of the park.

[0011] In some embodiments, the method further includes: Receive device control instructions; wherein the device control instructions include target control device and target control parameters; Based on the target control parameters, the twin model is screened to obtain the sub-model to be controlled; The entity items are filtered based on the sub-model to be controlled to obtain the target entity; Based on the target control parameters, the operating parameters of the target entity are modified, and control feedback information is received; The control feedback information is used to render and update the sub-model to be controlled in the digital twin model of the park.

[0012] To achieve the above objectives, a second aspect of this application proposes a park operation anomaly alarm device based on a digital twin system, the device comprising: A digital twin model acquisition module is used to acquire a digital twin model of a target park; wherein, the target park has multiple physical items deployed, and the park digital twin model includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; The data acquisition module is used to acquire real-time operational data for each of the physical items in the target park. The fault analysis module is used to perform fault analysis on the real-time operating data to obtain fault operating data; wherein, the fault operating data includes fault entity information, fault level, and item fault analysis parameters; The suggestion generation module is used to generate fault handling suggestions based on the fault analysis parameters of the item; The fault model determination module is used to determine the fault sub-model based on the twin correspondence and the fault entity information; The alarm rendering module is used to determine alarm rendering parameters based on the fault level, and to perform alarm rendering on the fault sub-model in the digital twin model of the park based on the alarm rendering parameters, the item fault analysis parameters, and the fault handling suggestions.

[0013] To achieve the above objectives, a third aspect of this application provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the method described in the first aspect.

[0014] To achieve the above objectives, a fourth aspect of the present application provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the method described in the first aspect.

[0015] This application proposes a method and apparatus for alarming abnormal operation in a park based on a digital twin system. It acquires a digital twin model of the target park, where multiple physical objects are deployed. The digital twin model includes multiple twin sub-models, and there is a twin correspondence between the physical objects and their twin sub-models. Next, it acquires real-time operational data for each physical object in the target park and performs fault analysis on this data to obtain fault operation data. This fault operation data includes fault entity information, fault level, and object fault analysis parameters, accurately locating operational problems in the target park. Furthermore, it generates fault handling suggestions based on the object fault analysis parameters, providing direction for resolving the fault; it identifies fault sub-models based on the twin correspondence and fault entity information, pinpointing the faulty sub-models within the park's digital twin model; and it determines alarm rendering parameters based on the fault level to highlight the fault information. Finally, based on alarm rendering parameters, item fault analysis parameters, and fault handling suggestions, alarm rendering is performed on the fault sub-model in the digital twin model of the park. This not only intuitively presents the fault location and level in the digital twin model of the park, enabling park operation and maintenance personnel to quickly understand the fault situation and improve the timeliness and intuitiveness of abnormal alarms in park operation, but also provides handling suggestions so that park operation and maintenance personnel can take timely measures, effectively shorten the fault handling time, improve the park's operational efficiency and stability, and reduce losses caused by faults. Attached Figure Description

[0016] Figure 1 This is a flowchart of a park operation anomaly alarm method based on a digital twin system provided in an embodiment of this application; Figure 2 This is a flowchart illustrating the construction process of the digital twin model of the park provided in this application embodiment; Figure 3 yes Figure 2 The flowchart of step S204 in the process; Figure 4 yes Figure 2 The flowchart of step S205 in the document; Figure 5 yes Figure 1 The flowchart of step S103 in the process; Figure 6 yes Figure 5 The flowchart of step S502 in the document; Figure 7 This is a flowchart of a park operation anomaly alarm method based on a digital twin system provided in another embodiment of this application; Figure 8 This is a schematic diagram of the structure of the park operation anomaly alarm device based on a digital twin system provided in this application embodiment; Figure 9 This is a schematic diagram of the hardware structure of the electronic device provided in the embodiments of this application. Detailed Implementation

[0017] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application.

[0018] It should be noted that although functional modules are divided in the device schematic diagram and a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than the module division in the device or the order in the flowchart. The terms "first," "second," etc., in the specification, claims, and the aforementioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] First, let's analyze some of the terms used in this application: A smart park is a modern park management model that leverages next-generation information technologies such as the Internet of Things, big data, cloud computing, and artificial intelligence to comprehensively perceive, analyze, and integrate the people, events, and things within the park. It achieves intelligent linkage and collaborative operation of systems such as security monitoring, energy management, facility operation and maintenance, logistics and transportation, and enterprise services within the park by building a unified information management platform. The core of a smart park lies in improving park operational efficiency, reducing management costs, optimizing resource allocation, and providing a convenient, safe, and green working and living environment for resident enterprises and personnel. It promotes the transformation and upgrading of parks towards digitalization, networking, and intelligence, and is an important carrier for smart city construction.

[0021] Digital twins are a simulation technology that integrates multiple disciplines, physical quantities, scales, and probabilities. By constructing a digital model that is highly consistent with a real physical entity in terms of form, function, and behavior, and utilizing technologies such as sensors and the Internet of Things to collect data from the physical entity in real time, a two-way interaction and synchronous mapping between the virtual model and the real entity can be achieved. With the help of digital twins, physical entities can be simulated, analyzed, predicted, and optimized in virtual space, allowing for the early identification of potential problems and the development of solutions. Digital twins are widely used in manufacturing, urban management, healthcare, energy, and other fields, helping to improve efficiency, reduce costs, and enhance innovation capabilities.

[0022] Currently, anomaly monitoring in park management scenarios primarily relies on IoT platforms. These platforms collect operational data from various devices within the park, analyze these data for anomalies, and notify park maintenance personnel via SMS or email when anomalies are detected. However, in practice, this IoT-based anomaly monitoring method suffers from issues such as delayed alarms and unintuitive alarm notifications.

[0023] Based on this, this application provides a method and apparatus for alarming abnormal park operations based on a digital twin system, aiming to improve the timeliness and intuitiveness of alarming abnormal park operations.

[0024] The park operation anomaly alarm method and device based on digital twin system provided in this application are specifically described through the following embodiments. First, the XX method in the embodiments of this application is described.

[0025] The park operation anomaly alarm method based on a digital twin system provided in this application relates to the field of smart park operation and maintenance technology. This method can be applied to a terminal, a server, or software running on either a terminal or a server. In some embodiments, the terminal can be a smartphone, tablet, laptop, desktop computer, etc.; the server can be configured as an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms; the software can be an application implementing the park operation anomaly alarm method based on a digital twin system, but is not limited to the above forms.

[0026] This application can be used in a wide variety of general-purpose or special-purpose computer system environments or configurations. Examples include: personal computers, server computers, handheld or portable devices, tablet devices, multiprocessor systems, microprocessor-based systems, set-top boxes, programmable consumer electronics, network PCs, minicomputers, mainframe computers, and distributed computing environments including any of the above systems or devices. This application can be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc., that perform specific tasks or implement specific abstract data types. This application can also be practiced in distributed computing environments where tasks are performed by remote processing devices connected via a communication network. In distributed computing environments, program modules can reside in local and remote computer storage media, including storage devices.

[0027] It should be noted that in all specific embodiments of this application, when processing data related to user identity or characteristics, such as user information, user behavior data, user historical data, and user location information, user permission or consent is obtained first. Furthermore, the collection, use, and processing of this data comply with relevant laws, regulations, and standards. In addition, when embodiments of this application require access to sensitive personal information of users, separate permission or consent from the user is obtained through pop-ups or redirection to confirmation pages. Only after obtaining the user's separate permission or consent is the necessary user-related data required for the proper functioning of these embodiments acquired.

[0028] Figure 1 This is an optional flowchart of a park operation anomaly alarm method based on a digital twin system provided in this application embodiment. Figure 1The method may include, but is not limited to, steps S101 to S106.

[0029] Step S101: Obtain the digital twin model of the target park; wherein, the target park has multiple physical items deployed, and the digital twin model of the park includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; Step S102: Obtain real-time operational data for each physical item in the target park; Step S103: Perform fault analysis on the real-time operation data to obtain fault operation data; wherein, the fault operation data includes fault entity information, fault level and item fault analysis parameters; Step S104: Generate fault handling suggestions based on the fault analysis parameters of the item; Step S105: Determine the fault sub-model based on the twin correspondence and fault entity information; Step S106: Determine alarm rendering parameters based on fault level, and perform alarm rendering on fault sub-models in the digital twin model of the park based on alarm rendering parameters, item fault analysis parameters and fault handling suggestions.

[0030] Steps S101 to S106, as illustrated in this embodiment, involve acquiring a digital twin model of the target park. The target park contains multiple physical objects, and the digital twin model includes multiple twin sub-models, with a twin correspondence between the physical objects and their respective twin sub-models. Next, real-time operational data for each physical object in the target park is acquired, and fault analysis is performed on this data to obtain fault operational data. This fault operational data includes fault entity information, fault level, and object fault analysis parameters, accurately locating operational problems in the target park. Furthermore, fault handling suggestions are generated based on the object fault analysis parameters to provide direction for resolving the fault; fault sub-models are determined based on the twin correspondence and fault entity information to identify faulty sub-models within the park's digital twin model; and alarm rendering parameters are determined based on the fault level to highlight the fault information. Finally, based on alarm rendering parameters, item fault analysis parameters, and fault handling suggestions, alarm rendering is performed on the fault sub-model in the digital twin model of the park. This not only intuitively presents the fault location and level in the digital twin model of the park, enabling park operation and maintenance personnel to quickly understand the fault situation and improve the timeliness and intuitiveness of abnormal alarms in park operation, but also provides handling suggestions so that park operation and maintenance personnel can take timely measures, effectively shorten the fault handling time, improve the park's operational efficiency and stability, and reduce losses caused by faults.

[0031] It should be noted that the target park refers to a specific park area to be monitored, analyzed, and managed, including but not limited to: industrial parks (such as semiconductor industrial parks, hazardous chemical industrial parks, etc.), commercial parks (such as business districts, office buildings, etc.), logistics parks, research parks, educational parks, and other types. The target park contains multiple physical objects, which are various actual equipment, facilities, buildings, and other objects existing within the target park, such as production equipment, power supply facilities, water supply and drainage equipment, public facilities (such as streetlights, air conditioners), and buildings.

[0032] A digital twin model of a park is a digital virtual mapping of a target park. It is constructed by integrating various types of information within the park and can simulate the park's physical characteristics and operational status. The digital twin model includes multiple twin sub-models, which are digital sub-models that correspond one-to-one with physical items in the digital twin model, accurately reflecting the characteristics and behaviors of the corresponding physical items.

[0033] It is understandable that the digital twin model of the park is a digital virtual mapping of the target park. Therefore, each physical item has a corresponding twin sub-model, that is, there is a twin correspondence between the physical item and the twin sub-model.

[0034] In step S101 of some embodiments, by calling the digital twin model of the target park that has been pre-built for the target park, an accurate virtual foundation is provided for subsequent operation and maintenance matters such as park analysis, monitoring and anomaly detection, so that managers can have a comprehensive understanding of the park situation in the virtual environment and discover potential problems in advance.

[0035] Please see Figure 2 In some embodiments, the process of constructing a digital twin model of the park may include, but is not limited to, steps S201 to S205: Step S201: Receive model drag command; wherein, the model drag command includes twin model and drag position information; Step S202: Based on the drag-and-drop position information, place the twin model on the preset park model sandbox to obtain the original park model; Step S203: Receive model connector drag command; wherein, the model connector drag command includes connector type and connector position information; Step S204: Connect the original park model based on the connector type and connector location information to obtain the initial park model; Step S205: Map the relationship between the initial park model and the target park to obtain the park's digital twin model.

[0036] Steps S201 to S205, as illustrated in this embodiment, involve receiving a model drag-and-drop instruction to construct a park model. This instruction includes twin sub-models and drag-and-drop position information, accurately determining the placement of each sub-model. Based on the drag-and-drop position information, the twin sub-models are placed on a pre-set park model sandbox to obtain an original park model, visually presenting the general layout of the park. Next, a model connector drag-and-drop instruction is received. This instruction includes connector type and connector position information, and the original park model is connected based on these information to obtain an initial park model. This establishes a reasonable relationship between the sub-models, resulting in a more complete initial park model. Finally, a relationship mapping is performed between the initial park model and the target park, resulting in a digital twin model of the park that accurately reflects the target park's condition and can be used for simulation analysis, anomaly detection, etc., improving the timeliness and intuitiveness of park management and operational anomaly alarms.

[0037] In step S201 of some embodiments, the model drag command is an operation command issued by the park operation and maintenance personnel to instruct the model to move and place, which contains key information required to complete the model layout, including twin models and drag position information.

[0038] In some embodiments, the twin model can be pre-made to scale based on the actual shape and layout of the physical object. For example, if the twin model is a building, it needs to reflect the building's exterior shape, floor layout, window sill layout, and other information to achieve a proportional replication. Alternatively, the twin model can be simply created using shapes such as blocks or columns for illustrative purposes. The specific approach depends on the actual application scenario and is not limited to these methods.

[0039] In addition, the drag position information clarifies the specific placement coordinates or area of ​​the twin model in the preset park model sandbox. Specifically, if the park operation and maintenance personnel drag the twin model on the operation interface (which displays the park sandbox model) with their finger or mouse, the position is calculated based on the position of the finger or mouse on the operation interface and the display range of the park sandbox model to obtain the drag position information.

[0040] It should be noted that the preset park model sandbox is a pre-built virtual space framework used to carry and display the layout of various models within the park, simulating the geographical environment and spatial structure of the real park.

[0041] For example, in a digital twin modeling project for an industrial park, the park's operations and maintenance personnel want to place a twin sub-model representing a packaging workshop in a virtual sandbox. The personnel issue drag-and-drop commands through the interface, which include the data of the corresponding twin sub-model of the packaging workshop and its specific coordinates within the sandbox.

[0042] In step S202 of some embodiments, the twin model is placed into the park model sandbox based on the drag-and-drop location information, which can quickly build the original park model and intuitively show the spatial distribution of various elements in the park, helping park operation and maintenance personnel to grasp the overall layout of the park.

[0043] Specifically, the original park model is a virtual model of the park obtained after the initial arrangement of twin models. It presents the approximate positional relationship of the various components in the park, but does not yet consider the connection and interaction between the components.

[0044] In step S203 of some embodiments, the model connector drag command is an operation command issued by the park operation and maintenance personnel to instruct the addition of connectors to the original park model. It includes relevant information about the connectors, namely connector type and connector location information.

[0045] Specifically, connector type refers to the specific connection tool used to connect different twin models, such as road connection, pipeline connection (such as water supply pipe, drainage pipe, ventilation pipe, water pump, etc.), power connection (wire, cable), network connection (such as fiber optic, gateway, router, etc.). Different types of connectors reflect different interaction relationships between models.

[0046] The connector location information clarifies the specific placement of the connector in the original campus model, that is, which two / more twin models it connects to and the specific location of the connection.

[0047] Specifically, if park maintenance personnel connect components on the operation interface (which displays a park sand table model) using their fingers or mouse, the location information of the connectors can be obtained by calculating the position of the finger or mouse on the operation interface and the display range of the park sand table model.

[0048] Please see Figure 3 In some embodiments, step S204 may include, but is not limited to, steps S301 to S304: Step S301: Based on the connector location information, the original park model is filtered into sub-models to obtain the sub-models to be connected; Step S302: Determine the target connector based on the connector type; Step S303: Determine the connection positioning points of the sub-models to be connected according to the type of connector; Step S304: Connect the sub-models to be connected based on the connection positioning points and target connectors to obtain the initial park model.

[0049] Steps S301 to S304, as illustrated in this embodiment, involve filtering sub-models from the original park model based on connector location information to obtain sub-models to be connected; determining target connectors based on connector types; and determining connection positioning points for the sub-models to be connected according to connector types, providing coordinate basis for accurate connection. Connecting the sub-models to be connected based on the connection positioning points and target connectors yields the initial park model, improving the accuracy and efficiency of model construction.

[0050] In step S301 of some embodiments, corresponding sub-models are selected from the original park model based on the connector location information to obtain the sub-models to be connected. For example: if the connector location information is between sub-model A and sub-model B, then sub-model A and sub-model B are selected as the sub-models to be connected. If the connector location information is between sub-model A and sub-model D, then sub-model A and sub-model D are selected as the sub-models to be connected.

[0051] Understandably, by filtering based on the location information of the connectors, blind operation on the entire large original park model is avoided, and the sub-models that need to be connected are accurately located, which greatly reduces the amount of data processing and computational complexity, and improves the efficiency and accuracy of model processing.

[0052] In step S302 of some embodiments, a target connector for connecting the sub-model to be connected is determined based on the connector type, such as a road, water supply pipe, drainage pipe, water pump, wire, optical fiber, etc.

[0053] It should be noted that different connectors have different connection points. Therefore, it is necessary to determine the connection positioning point of the sub-model to be connected based on the connector type. This ensures precise alignment between the sub-model and the target connector, guaranteeing the accuracy and reliability of the connection. For example, the connection point of an electrical wire is at point A on the ground, while the connection point of a drainage pipe is at point B underground.

[0054] Finally, by connecting the connection points and target connectors, the sub-models to be connected are integrated into a preliminary overall park model, thus obtaining the initial park model.

[0055] For example, in a park model, park maintenance personnel drag a road (target connector) between the office building and the parking lot (two sub-models to be connected). Based on the determined connection location point (such as the channel interface location between the office building and the parking lot), the road connects the office building and the parking lot, thus obtaining an initial park model containing the office building and the parking lot.

[0056] When modeling another park, the park maintenance personnel drag a water pipe (target connector) between equipment A and equipment B (two sub-models to be connected). Based on the determined connection positioning points (such as the water inlet of equipment A and the water outlet of equipment B), the water pipe is used to connect equipment A and equipment B, thereby obtaining an initial park model containing equipment A and equipment B.

[0057] Understandably, park maintenance personnel can drag and drop target connectors between specific sub-models on the operation interface using their fingers or a mouse. The system will automatically select the sub-models as the ones to be connected and determine the connection positioning points based on the connector type of the target connector. Then, the target connectors will be connected between the sub-models to be connected based on the connection positioning points, forming an effect of "automatic snapping and connection establishment".

[0058] Please see Figure 4 In some embodiments, step S205 may include, but is not limited to, steps S401 to S404: Step S401: Obtain the first location relationship information and IoT information interface for each physical item in the target park; Step S402: Obtain the second positional relationship information of each twin model in the initial park model; Step S403: Based on the first positional relationship information and the second positional relationship information, the entity item is associated with the twin sub-model to obtain the twin correspondence relationship; Step S404: Based on the twin correspondence, the twin sub-model is connected to the Internet of Things information interface to obtain the digital twin model of the park.

[0059] Steps S401 to S404, as illustrated in this embodiment, involve acquiring the first location relationship information of each physical item in the target park and the IoT information interface to obtain the second location relationship information of each twin sub-model in the initial park model. Next, based on the first and second location relationship information, the physical items are associated with the twin sub-models to obtain a twin correspondence, ensuring accurate mapping between the virtual and real worlds. Finally, based on the twin correspondence, the twin sub-models are connected to the IoT information interface to obtain a digital twin model of the park, which can reflect the actual state of the park in real time and helps improve the level of intelligent park operation.

[0060] In step S401 of some embodiments, the first positional relationship information is used to describe data such as the spatial position and relative position of an entity within the target park, for example, the coordinate position of a building relative to the park gate and its distance from other buildings.

[0061] An IoT information interface is an interface used to connect IoT sensors or other data acquisition devices installed on physical objects to enable data transmission and interaction. Through the IoT information interface, data such as the operating status and environmental parameters of physical objects can be obtained.

[0062] It should be noted that the aforementioned first location relationship information was generated by the park's operation and maintenance personnel through manual measurement of the target park and is stored in the target park's equipment asset management database.

[0063] For example, in an industrial park, for a production workshop, a total station or other surveying equipment is used to determine its coordinates within the park, as well as its relative distances to surrounding roads and other workshops, thus obtaining initial location information. Simultaneously, the interfaces connected to IoT devices such as temperature sensors and pressure sensors installed within the workshop are located to subsequently acquire equipment operation data.

[0064] In step S402 of some embodiments, the second positional relationship information is used to describe the spatial position, relative position, and other relationships of the twin model within the initial park model. Specifically, the second positional relationship information includes three-dimensional coordinates, orientation angle, and positional relationships with other sub-models.

[0065] For example, after placing a building model A in the park, and then dragging in a road model B, the system automatically detects the boundary points of the road model B and calculates the nearest edge distance between it and the building model A, automatically generating the spatial relationship that "building model A is located to the west of road model B".

[0066] It should be noted that the aforementioned second positional relationship information is automatically generated during the process of building the park model and is automatically saved in the preset twin model database.

[0067] In step S403 of some embodiments, by comparing the first positional relationship information and the second positional relationship information, the physical items in the target park are matched and associated with the twin sub-models in the initial park model to form a twin correspondence relationship. Here, the twin correspondence relationship refers to the one-to-one correspondence established between the physical items in the target park and the twin sub-models in the initial park model, enabling the park model to be closely integrated with the target park. This provides an accurate basis for subsequent data transmission and model updates, ensuring that the digital twin model can realistically and accurately simulate the operation of the actual park.

[0068] Specifically, it can automatically compare the metadata of each twin sub-model in the "twin model database" with the fields such as "equipment number, geographical location, equipment type, ID" in the actual equipment asset management database of the target park to generate a mapping relationship.

[0069] Specifically, each twin sub-model in the "twin model database" is assigned a unique ID, which is mapped to the "ID" in the equipment asset management database, etc.

[0070] For example: There is a water pump device with the number "PUMP-101" in the target park. When it is detected that a water pump sub-model in the park model is also located at the same or similar coordinates, the mapping relationship of "PUMP-101-water pump sub-model" is automatically established.

[0071] Finally, based on the twin correspondence, the corresponding IoT information interface of the twin sub-model is determined, and the twin sub-model is connected to the corresponding IoT information interface to obtain the digital twin model of the park. This enables the twin sub-model to receive real-time operating data from physical objects, thereby realizing dynamic monitoring and simulation of the park's status.

[0072] The digital twin system has a pre-set IoT data interface module that supports mainstream protocols such as OPC UA, MQTT, and HTTP API. It establishes a connection with the IoT platform of the target park. When the IoT platform pushes device data (such as temperature, pressure, and operating status) of physical objects, the system automatically matches the corresponding twin sub-model based on the device ID and updates its attributes.

[0073] In step S102 of some embodiments, the real-time operating data refers to various data generated by the physical object at the current moment, such as the temperature, pressure, and rotational speed of the equipment, and the flow rate and energy consumption of the facility. By using IoT sensors or other data acquisition devices installed on the physical object, the operating data generated by the physical object can be collected in real time, enabling real-time monitoring of the physical object's operating status, timely detection of abnormal changes, and providing timely and accurate data support for fault warning and analysis.

[0074] After step S102 in some embodiments, real-time operating data of each physical item in the target park is obtained, and the real-time operating data is rendered in real-time in the digital twin model of the park.

[0075] For example, the actual equipment number of an air conditioning unit in a building is "AC-001", and its corresponding twin model is also bound to "AC-001". When the IoT platform uploads {Device ID: AC-001, Temperature: 26℃, Status: Running}, the system immediately updates the attributes of the twin model. In the digital twin model of the park, the surface color of the air conditioning unit is displayed as green, and the floating label of the temperature value is updated to "26℃".

[0076] Please see Figure 5 In some embodiments, step S103 may include, but is not limited to, steps S501 to S503: Step S501: Obtain operational reference data for each entity in the target park; wherein, the operational reference data includes historical operational data and park expert annotation data; Step S502: For each physical item, perform status detection on the real-time operation data based on historical operation data and park expert annotation data to obtain the real-time operation status; wherein, the real-time operation status is used to characterize whether the physical item is in a stable operation state or a fault operation state during operation. Step S503: If the real-time running status indicates that the entity is in a fault running state during operation, fault analysis is performed based on the real-time running data to obtain fault running data.

[0077] Steps S501 to S503, as illustrated in this embodiment, acquire operational reference data for each physical item in the target park, including historical operational data and park expert annotation data. This provides a comprehensive and professionally guiding foundation for subsequent analysis. Next, for each physical item, the real-time operational data is monitored based on the historical operational data and park expert annotation data to obtain the real-time operational status. The real-time operational status characterizes whether the physical item is in a stable or faulty operational state during operation, accurately determining whether it is stable or faulty, and promptly grasping the equipment's operational status. When a faulty operational state is determined, fault analysis is performed using the real-time operational data to obtain fault operational data. This helps to deeply analyze the causes and characteristics of the fault, achieving a complete and efficient fault monitoring and diagnosis mechanism. This allows for early detection of faults and clarification of fault conditions, providing strong support for subsequent maintenance and ensuring the stable operation of the park.

[0078] In step S501 of some embodiments, the operational reference data is reference information used to evaluate and monitor the operation of physical items, including historical operational data and expert-annotated data from the park. Historical operational data is a record of the physical item's operation over a past period, such as operating time, parameter changes, and fault records. Expert-annotated data from the park is annotation information on the physical item's operation based on the experience and expertise of professionals within the park, such as normal operating range and common fault characteristics.

[0079] For example, in an industrial park, sensors installed on production equipment collect historical operating parameters of the equipment over the past year, such as temperature, pressure, and speed. At the same time, senior engineers in the park are invited to annotate the normal operating range and common fault characteristics of the equipment, forming expert-annotated data for the park.

[0080] Please see Figure 6 In some embodiments, step S502 includes, but is not limited to, steps S601 to S605: Step S601: Obtain current operating environment information; Step S602: For each entity item, perform data matching between historical operating data and park expert annotation data based on the current operating environment information to obtain matched operating data; wherein, the historical operating environment information of the matched operating data is matched with the current operating environment information. Step S603: Perform data analysis on the matching operation data to obtain the steady-state operation data of each entity item; Step S604: Perform fault diagnosis on real-time operating data based on steady-state operating data to obtain fault diagnosis results; Step S605: Generate real-time operating status based on fault diagnosis results.

[0081] Steps S601 to S605, as illustrated in this embodiment, involve acquiring current operating environment information and, for each physical item, matching historical operating data and expert-annotated data based on the current operating environment information to obtain matched operating data. The matching operating data's historical operating environment information matches the current operating environment information, eliminating environmental differences and improving the accuracy of fault analysis. Next, data analysis is performed on the matched operating data to obtain steady-state operating data for each physical item, clarifying its normal state under similar environments. Fault diagnosis is then performed on the real-time operating data based on the steady-state operating data to obtain fault diagnosis results, enabling precise fault detection. Finally, a real-time operating status is generated based on the fault diagnosis results, reflecting the physical item's operating status promptly and accurately, facilitating early fault detection and ensuring stable park operation.

[0082] In step S601 of some embodiments, the current operating environment information refers to the environmental data of the physical objects within the target park at the current moment. This includes physical environmental parameters such as temperature, humidity, air pressure, light intensity, and air quality, as well as dynamic environmental factors such as production rhythm and personnel activity density within the park, and may also include seasonal factors. Accurately understanding the current operating environment information provides a basic environmental background for subsequent analysis of the operating status of the physical objects, as environmental factors significantly affect the operating performance and probability of equipment failure.

[0083] In step S602 of some embodiments, for each entity item, data matching is performed on historical operating data and park expert-annotated data based on the current operating environment information to obtain matched operating data; wherein, the historical operating environment information of the matched operating data is matched with the current operating environment information. Through data matching, the influence of different environments on equipment operation is eliminated, so that subsequent analysis is based on data under similar environments, thereby improving the accuracy and pertinence of the analysis.

[0084] Specifically, if the historical operating environment information of the historical operating data matches the current operating environment information, and the historical operating environment information of the data annotated by park experts matches the current operating environment information, the data annotated by park experts will be selected first, that is, the data annotated by park experts will be confirmed as the matching operating data.

[0085] If the historical operating environment information of the historical operating data matches the current operating environment information, but the historical operating environment information of the data annotated by park experts does not match the current operating environment information, the historical operating data is selected as the matched operating data.

[0086] If the historical operating environment information of the historical operating data does not match the current operating environment information, but the historical operating environment information of the data annotated by park experts matches the current operating environment information, the data annotated by park experts is selected as the matching operating data.

[0087] In step S603 of some embodiments, statistical analysis, machine learning and other data analysis methods are used to process the matching operation data, extract the key parameters and features of the equipment during stable operation, and obtain steady-state operation data. This provides a clear reference standard for judging whether the equipment is currently operating normally and helps to detect abnormal changes in the equipment in a timely manner.

[0088] Specifically, various statistical characteristics of the matching operational data can be calculated, such as mean, median, standard deviation, and range. Taking the temperature data of a physical object as an example, calculating its mean temperature over a period of time reflects the average temperature level of the object during that period; the standard deviation reflects the dispersion of the temperature data. The smaller the standard deviation, the smaller the temperature fluctuation, and the closer it is to steady-state operation. Then, based on the analysis results of the statistical characteristics, the steady-state operating range of the physical object is determined. For example, by setting reasonable ranges for the temperature mean and standard deviation, when the temperature mean and standard deviation of the real-time operational data both fall within this range, the object is considered to be in steady-state operation.

[0089] Alternatively, clustering models, such as K-means clustering, can be used to cluster the matching running data into different clusters. The running state corresponding to the cluster with the most concentrated data points and the smallest changes is the steady-state running state.

[0090] In step S604 of some embodiments, real-time operating data is compared and analyzed with steady-state operating data. Using a set fault diagnosis algorithm and rules, it is determined whether the equipment has malfunctioned, and a fault diagnosis result is obtained, enabling timely and accurate detection of equipment faults. The fault diagnosis result is used to characterize whether the real-time operating data is faulty or stable. Specifically, the differences between real-time operating data and steady-state operating data (such as differential values ​​or Mahalanobis distance) are calculated to obtain the difference data, and a fault diagnosis result is derived based on the difference data. If the difference data is greater than or equal to a preset threshold, the fault diagnosis result indicates that the real-time operating data is faulty; if the difference data is less than the preset threshold, the fault diagnosis result indicates that the real-time operating data is stable.

[0091] It should be noted that the preset threshold needs to be determined by the park's operation and maintenance personnel based on the actual application scenario, and it is set individually for each physical item.

[0092] For example: Suppose the fan speed of a ventilation duct is 1400 rpm, while the steady-state operating data is 1800 rpm. The difference between the two is 400 rpm, while the preset threshold is 300 rpm. Since the difference is greater than the preset threshold, the fault diagnosis result of the ventilation duct indicates that the real-time operating data is fault data.

[0093] Furthermore, a real-time operating status is generated based on the fault diagnosis results. If the fault diagnosis results indicate that the real-time operating data is faulty, then the real-time operating status indicates that the physical item is in a faulty operating state during operation; if the fault diagnosis results indicate that the real-time operating data is stable, then the real-time operating status indicates that the physical item is in a stable operating state during operation.

[0094] In step S503 of some embodiments, if the real-time running status indicates that the entity item is in a fault running state during operation, it is necessary to perform fault analysis on the real-time running data to obtain fault running data, wherein the fault running data includes fault entity information, fault level and item fault analysis parameters. Specifically, if the real-time operating status indicates that an entity is in a faulty operating state during operation, then the entity's information (such as its ID) is the faulty entity information.

[0095] Next, the real-time operating data corresponding to the physical items that malfunctioned is analyzed to determine the malfunction level, which can be divided into minor malfunction, general malfunction, and severe malfunction.

[0096] Specifically, the park expert-annotated data of the physical object can be selected and input into a machine learning algorithm (such as decision tree, support vector machine, neural network, etc.) to establish a fault level assessment model, which can accurately classify the fault level.

[0097] Furthermore, the real-time operating data and steady-state operating data corresponding to the faulty physical items are combined to obtain the item fault analysis parameters, which include: real-time operating data and steady-state operating data.

[0098] Understandably, fault analysis can accurately reveal the specifics of a fault, providing maintenance personnel with detailed fault information, which helps to quickly locate and resolve faults and improve maintenance efficiency.

[0099] In step S104 of some embodiments, a pre-trained large model can be used to analyze the fault analysis parameters of the object and generate fault handling suggestions. Alternatively, a deep learning model (such as a convolutional neural network, a recurrent neural network, etc.) can be trained using pre-collected expert experience knowledge to construct a fault suggestion generation model, which is used to analyze the fault analysis parameters of the object and derive fault handling suggestions.

[0100] For example: Suppose a ventilation duct is malfunctioning, and its real-time operating data (fan speed) is 1400 rpm, and its steady-state operating data is 1800 rpm. The generated handling suggestion could be: increase the fan's operating current to increase the fan speed to 1800 rpm.

[0101] In step S105 of some embodiments, based on the twin correspondence between the entity item and the twin sub-model and the fault entity information, the corresponding twin sub-model is found in the digital twin model of the park as the fault sub-model to accurately locate the fault location.

[0102] In step S106 of some embodiments, alarm rendering parameters are first determined based on the fault level. For example, minor faults are displayed in pink, general faults are displayed in red, and serious faults are displayed in flashing red.

[0103] Next, based on alarm rendering parameters, item fault analysis parameters, and fault handling suggestions, alarm rendering was performed on the fault sub-model in the digital twin model of the park. The alarm rendering has been visualized in the digital twin model of the park, enabling park operation and maintenance personnel to quickly understand the location, severity, and handling methods of the fault, thereby improving fault response speed and management efficiency.

[0104] Understandably, the digital twin model of the park will display the real-time operating status of each twin sub-model. If a twin sub-model is in a stable operating state, its rendering color will be green or blue. The color of its real-time operating data will be the same as the rendering color of the twin sub-model, but with higher saturation to highlight the real-time operating data. Alternatively, other colors (such as white, black, etc.) may be used to render the real-time operating data, and this is not a limitation.

[0105] If a twin sub-model malfunctions during operation and is in a faulty operating state (i.e., a faulty sub-model), alarm rendering is required. The alarm rendering parameters are determined based on the fault level, and alarm rendering is performed on the faulty sub-model in the digital twin model of the park based on the alarm rendering parameters, the item fault analysis parameters, and the fault handling suggestions.

[0106] For example, if a water pump in the park's digital twin model stops operating and is in a faulty state with a severe fault level, the corresponding alarm rendering parameter will be a fast-flashing red light. The digital twin model will then display the water pump in red and flash it at a preset frequency to provide park maintenance personnel with the most intuitive alarm information.

[0107] Please see Figure 7 In some embodiments, the method for handling abnormal campus operations based on a digital twin system may also include, but is not limited to, steps S701 to S705: Step S701: Receive device control instructions; wherein, the device control instructions include target control device and target control parameters; Step S702: Based on the target control parameters, the twin model is screened to obtain the sub-model to be controlled; Step S703: Filter the entity items based on the sub-model to be controlled to obtain the target entity; Step S704: Modify the operating parameters of the target entity based on the target control parameters, and receive control feedback information; Step S705: Render and update the sub-model to be controlled in the digital twin model of the park based on the control feedback information.

[0108] Steps S701 to S705, as illustrated in this embodiment, involve receiving equipment control commands, which include target control equipment and target control parameters. Based on the target control parameters, the twin sub-model is screened to obtain the sub-model to be controlled, enabling rapid location of the control-related twin sub-model portion and improving control accuracy. Next, based on the twin correspondence and the sub-model to be controlled, entity items are screened to obtain target entities. The operating parameters of the target entities are then modified according to the target control parameters, and control feedback information is received, allowing real-time monitoring of the control effect. Finally, based on the control feedback information, the sub-model to be controlled in the park's digital twin model is rendered and updated, synchronizing the park's digital twin model with the actual operating state of the target park, ensuring the accuracy of park equipment control and the effectiveness of the model.

[0109] In step S701 of some embodiments, park maintenance personnel issue equipment control commands through the operation interface. The target control equipment is a specified physical item that needs to be controlled, and the target control parameters are specific control values ​​or conditions set for the target control equipment, such as the set values ​​of parameters like temperature, speed, and pressure.

[0110] Specifically, park operations and maintenance personnel can click on a specific twin sub-model in the park's digital twin model through the operation interface to enter the parameter control window and adjust the operating parameters. The twin sub-model is the target control device, and the adjusted operating parameters are the target control parameters.

[0111] In step S702 of some embodiments, the click location information is obtained based on the location clicked by the park operation and maintenance personnel on the operation display interface, and then the display range of the park digital twin model in the operation interface is obtained. Then, the twin sub-model corresponding to the park digital twin model is determined based on the click location information and the display range to obtain the sub-model to be controlled.

[0112] In step S703 of some embodiments, entity items are filtered according to the sub-model to be controlled and the twin correspondence to obtain the target entity. Specifically, based on the ID of the sub-model to be controlled, the ID of the corresponding entity item is found from the twin correspondence, and the target entity is filtered from all entity items based on the ID of the entity item.

[0113] In step S704 of some embodiments, the target control parameters are sent to the target entity via the IoT platform to modify the target entity's operating parameters. After modification, control feedback information returned by the target entity is received in real time. This control feedback information is information returned by the target entity after receiving the modified operating parameters, including its actual operating status and whether the modification was successful.

[0114] For example, a parameter is sent to an air conditioner in the target park to set the temperature to 23 degrees Celsius. After receiving the parameter, the air conditioner adjusts itself and integrates information such as the actual temperature after adjustment and whether the set value has been reached to obtain control feedback information.

[0115] The parameters for turning off a specific light fixture in the target area are sent to that light fixture. After receiving the parameters, the light fixture makes adjustments and integrates the adjusted on / off status to obtain control feedback information.

[0116] In step S705 of some embodiments, the received control feedback information is applied to the sub-model to be controlled in the digital twin model of the park, and the display state of the sub-model is adjusted and updated by rendering technology so that the digital twin model can reflect the actual operating state of the physical equipment in real time, thereby improving the accuracy and real-time performance of the digital twin model.

[0117] The park operation anomaly alarm method based on a digital twin system provided in this application embodiment uses 3D modeling software such as 3DMAX, Blender, and Maya to pre-create relevant equipment models, forming common FBX and OBJ format files, which are then imported into a 3D engine. A drag-and-drop function is implemented using C# scripts to control the models. After dragging and dropping, the 3D coordinates and orientation information of the models are saved in real time. The models are numbered according to the actual equipment's location coding information, forming a one-to-one correspondence, thereby achieving a mapping relationship between sub-models and IoT physical devices. This restores the real layout of physical IoT devices in the real world and maps the twin sub-models to the physical IoT devices one-to-one, achieving the goal of digital twin models controlling real devices and truly realizing the effect of digital twins.

[0118] Furthermore, it allows for the manipulation of 3D models to control actual objects within the park, greatly enhancing the system's two-way interactivity. Park maintenance personnel can easily control equipment remotely, such as turning a device on or off or adjusting its operating parameters, achieving true two-way interaction between the virtual and real worlds. This brings unprecedented convenience and efficiency to park management, propelling it towards intelligent and digital transformation.

[0119] Please see Figure 8 This application also provides a park operation anomaly alarm device based on a digital twin system, which can realize the above-mentioned park operation anomaly alarm method based on a digital twin system. The device includes: The digital twin model acquisition module 801 is used to acquire the digital twin model of the target park; wherein, the target park has multiple physical items deployed, and the park digital twin model includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; The runtime data acquisition module 802 is used to acquire real-time runtime data for each physical item in the target park; The fault analysis module 803 is used to perform fault analysis on real-time operating data to obtain fault operating data; the fault operating data includes fault entity information, fault level and item fault analysis parameters; It is recommended that module 804 be used to generate fault handling suggestions based on the fault analysis parameters of the object; The fault model determination module 805 is used to determine the fault sub-model based on the twin correspondence and fault entity information. The alarm rendering module 806 is used to determine alarm rendering parameters based on the fault level, and to perform alarm rendering on the fault sub-model in the digital twin model of the park based on the alarm rendering parameters, the fault analysis parameters of the object, and the fault handling suggestions.

[0120] The specific implementation of the park operation anomaly alarm device based on the digital twin system is basically the same as the specific implementation of the park operation anomaly alarm method based on the digital twin system described above, and will not be repeated here.

[0121] This application also provides an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor executes the computer program to implement the above-described method for alarming abnormal campus operations based on a digital twin system. This electronic device can be any smart terminal, including tablet computers, in-vehicle computers, etc.

[0122] Please see Figure 9 , Figure 9 The hardware structure of an electronic device according to another embodiment is illustrated. The electronic device includes: The processor 901 can be implemented using a general-purpose CPU (Central Processing Unit), microprocessor, application-specific integrated circuit (ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this application. The memory 902 can be implemented as a read-only memory (ROM), static storage device, dynamic storage device, or random access memory (RAM). The memory 902 can store the operating system and other applications. When the technical solutions provided in the embodiments of this specification are implemented through software or firmware, the relevant program code is stored in the memory 902 and is called and executed by the processor 901 using the campus operation anomaly alarm method based on a digital twin system according to the embodiments of this application. The input / output interface 903 is used to implement information input and output; The communication interface 904 is used to enable communication and interaction between this device and other devices. Communication can be achieved through wired means (such as USB, Ethernet cable, etc.) or wireless means (such as mobile network, WIFI, Bluetooth, etc.). Bus 905 transmits information between various components of the device (e.g., processor 901, memory 902, input / output interface 903, and communication interface 904); The processor 901, memory 902, input / output interface 903, and communication interface 904 are connected to each other within the device via bus 905.

[0123] This application also provides a computer-readable storage medium storing a computer program that, when executed by a processor, implements the above-described method for alarming abnormal operation of a park based on a digital twin system.

[0124] Memory, as a non-transitory computer-readable storage medium, can be used to store non-transitory software programs and non-transitory computer-executable programs. Furthermore, memory may include high-speed random access memory, and may also include non-transitory memory, such as at least one disk storage device, flash memory device, or other non-transitory solid-state storage device. In some embodiments, memory may optionally include memory remotely located relative to the processor, and these remote memories can be connected to the processor via a network. Examples of such networks include, but are not limited to, the Internet, intranets, local area networks, mobile communication networks, and combinations thereof.

[0125] The park operation anomaly alarm method and apparatus based on a digital twin system provided in this application acquire a digital twin model of a target park. The target park has multiple physical items, and the park's digital twin model includes multiple twin sub-models, with a twin correspondence between the physical items and their twin sub-models. Next, real-time operational data for each physical item in the target park is acquired, and fault analysis is performed on the real-time operational data to obtain fault operation data. This fault operation data includes fault entity information, fault level, and item fault analysis parameters, accurately locating operational problems in the target park. Further, fault handling suggestions are generated based on the item fault analysis parameters to provide direction for resolving the fault; fault sub-models are determined based on the twin correspondence and fault entity information to identify the faulty sub-models in the park's digital twin model; and alarm rendering parameters are determined based on the fault level to highlight the fault information. Finally, based on alarm rendering parameters, item fault analysis parameters, and fault handling suggestions, alarm rendering is performed on the fault sub-model in the digital twin model of the park. This not only intuitively presents the fault location and level in the digital twin model of the park, enabling park operation and maintenance personnel to quickly understand the fault situation and improve the timeliness and intuitiveness of abnormal alarms in park operation, but also provides handling suggestions so that park operation and maintenance personnel can take timely measures, effectively shorten the fault handling time, improve the park's operational efficiency and stability, and reduce losses caused by faults.

[0126] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0127] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0128] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0129] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or appropriate combinations thereof.

[0130] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0131] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0132] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0133] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0134] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0135] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0136] The software tools or components not belonging to our company that appear in the embodiments of this application are for illustrative purposes only and do not represent actual use.

[0137] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A method for alarming abnormal operation of a park based on a digital twin system, characterized in that, The method includes: Obtain a digital twin model of the target park; wherein the target park has multiple physical items deployed, the digital twin model of the park includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; Obtain real-time operational data for each of the physical items in the target park; Fault analysis is performed on the real-time operating data to obtain fault operating data; wherein, the fault operating data includes fault entity information, fault level, and item fault analysis parameters; Based on the fault analysis parameters of the item, generate fault handling suggestions; The fault sub-model is determined based on the twin correspondence and the fault entity information; Based on the fault level, alarm rendering parameters are determined, and based on the alarm rendering parameters, the item fault analysis parameters, and the fault handling suggestions, alarm rendering is performed on the fault sub-model in the digital twin model of the park.

2. The method according to claim 1, characterized in that, The step of performing fault analysis on the real-time operating data to obtain fault operating data includes: Obtain operational reference data for each of the physical items in the target park; wherein, the operational reference data includes historical operational data and park expert annotation data; For each physical item, the real-time operating data is subjected to status detection based on the historical operating data and the park expert annotation data to obtain the real-time operating status; wherein, the real-time operating status is used to characterize whether the physical item is in a stable operating state or a faulty operating state during operation. If the real-time operating status indicates that the physical item is in a faulty operating state during operation, fault analysis is performed based on the real-time operating data to obtain the faulty operating data.

3. The method according to claim 2, characterized in that, For each of the aforementioned physical items, the real-time operating data is analyzed based on the historical operating data and the park expert annotation data to obtain the real-time operating status, including: Obtain information about the current operating environment; For each of the aforementioned entity items, the historical operating data and the park expert annotation data are matched based on the current operating environment information to obtain matched operating data; wherein, the historical operating environment information of the matched operating data is matched with the current operating environment information; Data analysis is performed on the matching operation data to obtain the steady-state operation data of each entity item; Based on the steady-state operating data, fault diagnosis is performed on the real-time operating data to obtain fault diagnosis results; The real-time operating status is generated based on the fault diagnosis results.

4. The method according to claim 1, characterized in that, The digital twin model of the park was constructed in the following way: Receive a model drag command; wherein the model drag command includes a twin model and drag position information; Based on the drag position information, the twin model is placed on a preset park model sandbox to obtain the original park model; Receive a model connector drag command; wherein the model connector drag command includes connector type and connector position information; Based on the connector type and connector location information, the original park model is connected to obtain an initial park model; A relationship mapping is performed between the initial park model and the target park to obtain the digital twin model of the park.

5. The method according to claim 4, characterized in that, The step of connecting the original park model based on the connector type and the connector location information to obtain the initial park model includes: Based on the location information of the connectors, the original park model is filtered into sub-models to be connected. The target connector is determined based on the connector type; Determine the connection positioning point of the sub-model to be connected according to the type of connector; The sub-models to be connected are connected based on the connection positioning point and the target connector to obtain the initial park model.

6. The method according to claim 4, characterized in that, The process of mapping the initial park model to the target park to obtain the park's digital twin model includes: Obtain the first location relationship information and IoT information interface for each of the physical items in the target park; Obtain the second positional relationship information of each twin model in the initial park model; The entity item is associated with the twin model based on the first positional relationship information and the second positional relationship information to obtain the twin correspondence relationship; Based on the twin correspondence, the twin sub-model is connected to the IoT information interface to obtain the digital twin model of the park.

7. The method according to claim 1, characterized in that, The method further includes: Receive device control instructions; wherein the device control instructions include target control device and target control parameters; Based on the target control parameters, the twin model is screened to obtain the sub-model to be controlled; The entity items are filtered based on the sub-model to be controlled to obtain the target entity; Based on the target control parameters, the operating parameters of the target entity are modified, and control feedback information is received; The control feedback information is used to render and update the sub-model to be controlled in the digital twin model of the park.

8. A park operation anomaly alarm device based on a digital twin system, characterized in that, The device includes: A digital twin model acquisition module is used to acquire a digital twin model of a target park; wherein, the target park has multiple physical items deployed, and the park digital twin model includes multiple twin sub-models, and there is a twin correspondence between the physical items and the twin sub-models; The data acquisition module is used to acquire real-time operational data for each of the physical items in the target park. The fault analysis module is used to perform fault analysis on the real-time operating data to obtain fault operating data; wherein, the fault operating data includes fault entity information, fault level, and item fault analysis parameters; The suggestion generation module is used to generate fault handling suggestions based on the fault analysis parameters of the item; The fault model determination module is used to determine the fault sub-model based on the twin correspondence and the fault entity information; The alarm rendering module is used to determine alarm rendering parameters based on the fault level, and to perform alarm rendering on the fault sub-model in the digital twin model of the park based on the alarm rendering parameters, the item fault analysis parameters, and the fault handling suggestions.

9. An electronic device, characterized in that, The electronic device includes a memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing a computer program, characterized in that, When the computer program is executed by a processor, it implements the method of any one of claims 1 to 7.

Images