Smart park operation and maintenance management method and system based on CIM and medium

Abstract

The invention provides a smart park operation and maintenance management method and system based on CIM and a medium, and belongs to the technical field of smart park management. The method comprises the following steps: constructing a CIM digital twinborn model based on a park building group, a geographic position, Internet of Things equipment and business data, and synchronously extracting equipment state and energy consumption information; analyzing the state data by using the equipment fault prediction model and generating a repair work order to realize predictive maintenance; performing gridding processing on the energy consumption data, generating a thermodynamic diagram and identifying an abnormal energy consumption area; and positioning a high-energy-consumption grid by combining an energy consumption analysis model, and generating a comprehensive operation and maintenance scheme of equipment regulation and control, energy scheduling and system optimization through matching of an energy management strategy library. According to the invention, the digital twinning technology and the CIM platform are fused, so that full-life-cycle management and dynamic energy consumption optimization of the equipment are realized, the operation and maintenance efficiency is remarkably improved, the failure rate and energy waste are reduced, and both economy and environmental protection are achieved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of smart park management, in particular to a smart park operation and maintenance management method, system and medium based on CIM. BACKGROUND

[0002] With the advancement of smart city construction, park management is gradually transforming towards digitization and intelligentization, but traditional operation and maintenance mode still faces many challenges. In the prior art, park equipment and facility management relies on manual inspection and post-maintenance, which has problems of response lag and insufficient fault prediction capability; energy consumption monitoring usually adopts decentralized metering and manual statistics, which is difficult to achieve fine analysis and dynamic regulation. At the same time, the multi-source data of park buildings, equipment and business systems lack unified integration, leading to prominent information island phenomenon, which restricts the scientificity of operation and maintenance decision. Although some technologies attempt to optimize through Internet of Things or big data, they have not effectively integrated city information model (CIM) and digital twin technology, and cannot realize deep collaboration between park physical space and virtual model, still having significant defects in equipment whole life cycle management, energy consumption anomaly positioning and strategy adaptive matching.

[0003] Therefore, an integrated operation and maintenance management method based on CIM is urgently needed to realize data-driven equipment predictive maintenance and energy dynamic optimization, and to improve park management efficiency and sustainability. SUMMARY

[0004] The purpose of the present application is to provide a smart park operation and maintenance management method, system and medium based on CIM, which is characterized by integrating building information, geographic information and Internet of Things data through a CIM platform, constructing a multi-dimensional digital twin model, and realizing real-time interaction between park physical space and virtual mapping. Based on CIM, multi-source heterogeneous data fusion integrates building structure, equipment operation, energy consumption and business system data, and establishes a dynamically updated twin model; a machine learning algorithm is used to train an equipment fault prediction model to predict potential equipment failures by analyzing real-time sensor data (such as vibration, temperature, current), and to automatically generate repair work orders and optimize maintenance paths; an energy consumption grid analysis method is innovated to divide the park into time and space related energy consumption units, and to identify abnormal high consumption areas by combining heat maps and clustering algorithms; an energy management strategy knowledge base is constructed, based on a rule engine and a dynamic weight matching algorithm, to generate comprehensive strategies for equipment operation parameter adjustment, energy distribution optimization and system collaborative control. The advantage of the present application lies in the deep integration of CIM and digital twin technology, which breaks down data barriers, realizes closed-loop management of equipment predictive maintenance, energy precise regulation and operation and maintenance strategy adaptation, significantly reduces operation and maintenance costs and improves energy utilization efficiency.

[0005] The present application provides a smart park operation and maintenance management method based on CIM, comprising the following steps: collect building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period and construct a park digital twin model, extract device facility state information and energy consumption information according to the park digital twin model; generate a repair work order according to the device facility state information through a preset device fault prediction model; perform grid processing according to the energy consumption information to obtain a park energy consumption heat map; extract energy consumption distribution data of a plurality of grids according to the park energy consumption heat map, process the energy consumption distribution data through a preset energy consumption analysis model, and obtain grid energy consumption overhigh information; generate an energy operation and maintenance adjustment scheme according to the grid energy consumption overhigh information through a preset energy management strategy library.

[0006] In the CIM-based smart park operation and maintenance management method described in the present application, the collection of building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period and the construction of a park digital twin model are specifically as follows: collect building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period; the building group information includes physical attributes, real scene point cloud data, energy consumption data and maintenance records; the geographic location information includes geographic coordinates, device relative position data and park topography and geomorphology; the Internet of Things device information includes device type information and running state information; the system service information includes business type information, business process information and business mapping relationship information; construct a park digital twin model according to the building group information, geographic location information, Internet of Things device information and system service information.

[0007] In the CIM-based smart park operation and maintenance management method described in the present application, the generation of a repair work order according to the device facility state information through a preset device fault prediction model is specifically as follows: extract real-time monitoring values, power curve fluctuation data, online state information and load data according to the device facility state information; generate a repair work order according to the real-time monitoring values, power curve fluctuation data, online state information and load data through a preset device fault prediction model; the repair work order includes fault device basic information, fault type and fault repair time length.

[0008] In the CIM-based smart park operation and maintenance method described in the present application, the grid processing according to the energy consumption information obtains a park energy consumption heat map, specifically: According to the energy consumption information, extract heterogeneous energy consumption type information, heterogeneous energy consumption data and energy consumption distribution space information, and through a preset energy consumption equivalent model, convert and fuse to obtain a three-dimensional energy consumption matrix; The three-dimensional energy consumption matrix is processed by a preset adaptive grid division engine to obtain an energy consumption grid structure diagram; According to the energy consumption grid structure diagram, process through a preset heat rendering model to obtain a park energy consumption heat map.

[0009] In the CIM-based smart park operation and maintenance method described in the present application, the grid energy consumption distribution data of the multiple grids is extracted from the park energy consumption heat map and processed by a preset energy consumption analysis model to obtain grid energy consumption over high information, specifically: According to the park energy consumption heat map, extract the color values of multiple grids; According to the color values of the multiple grids, query through a preset color energy consumption mapping table to obtain grid energy consumption distribution data of the multiple grids; According to the grid energy consumption distribution data of the multiple grids, process through a preset energy consumption analysis model to obtain grid energy consumption analysis data; According to the grid energy consumption analysis data and a preset energy consumption threshold value, compare; If the grid energy consumption analysis data is greater than or equal to the energy consumption threshold value, obtain grid energy consumption over high information.

[0010] In the CIM-based smart park operation and maintenance method described in the present application, the grid energy consumption over high information is processed through a preset energy management strategy library to generate an energy operation adjustment scheme, specifically: According to the grid energy consumption over high information, extract energy consumption location information, energy consumption over high value, energy consumption duration and energy consumption equipment type information; According to the energy consumption location information, energy consumption over high value, energy consumption duration and energy consumption equipment type information, query and process through a preset energy management strategy library to obtain multiple energy management strategies; According to the multiple energy management strategies, generate an energy operation adjustment scheme, including management strategy integration, scheme execution details and strategy priority sorting.

[0011] In a second aspect, the application provides a CIM-based smart park operation and maintenance management system, which comprises a memory and a processor, the memory comprising a CIM-based smart park operation and maintenance management method program, the CIM-based smart park operation and maintenance management method program being executed by the processor to implement the following steps: Collecting building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period and constructing a park digital twin model, extracting device facility state information and energy consumption information according to the park digital twin model; Processing according to the device facility state information through a preset device fault prediction model to generate a repair work order; According to the energy consumption information, grid processing is performed to obtain a park energy consumption heat map; According to the park energy consumption heat map, the energy consumption distribution data of a plurality of grids are extracted and processed through a preset energy consumption analysis model to obtain grid energy consumption overhigh information; According to the grid energy consumption overhigh information, processing is performed through a preset energy management strategy library to generate an energy operation and maintenance adjustment scheme.

[0012] In the CIM-based smart park operation and maintenance management system described in the application, the collection of building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period and the construction of a park digital twin model are specifically as follows: Collecting building group information, geographic location information, Internet of Things device information and system service information of the park in a preset time period; The building group information comprises physical attributes, real scene point cloud data, energy consumption data and maintenance records; The geographic location information comprises geographic coordinates, device relative position data and park topography and geomorphology; The Internet of Things device information comprises device type information and running state information; The system service information comprises business type information, business process information and business mapping relationship information; According to the building group information, geographic location information, Internet of Things device information and system service information, a park digital twin model is constructed.

[0013] In the CIM-based smart park operation and maintenance management system described in the application, the processing according to the device facility state information through a preset device fault prediction model to generate a repair work order is specifically as follows: According to the device facility state information, real-time monitoring values, power consumption curve fluctuation data, online state information and load data are extracted; According to the real-time monitoring value, power consumption curve fluctuation data, online state information and load data, a preset equipment fault prediction model is processed to generate a repair work order; The repair work order includes basic information of the faulty equipment, a fault type and a fault repair duration.

[0014] In a third aspect, the present application further provides a computer readable storage medium, wherein the computer readable storage medium comprises a CIM-based smart park operation and maintenance management method program, and the CIM-based smart park operation and maintenance management method program is executed by a processor to implement the steps of the CIM-based smart park operation and maintenance management method according to any one of the above.

[0015] As can be seen from the above, the CIM-based smart park operation and maintenance management method, system and medium provided by the embodiments of the present application first integrate building group information (including physical properties, real scene point cloud data and maintenance records), geographic location information (including geographic coordinates and terrain data), Internet of Things device information (including device types and operating states) and system business information (including business processes and mapping relationships), construct a multi-dimensional dynamic updated park digital twin model based on a CIM platform, and extract device facility real-time state information and energy consumption data therefrom. Secondly, a preset equipment fault prediction model is used to analyze device state data (such as power consumption curve fluctuation and load data), automatically generate a repair work order containing a fault type and device details, and realize predictive maintenance. Further, the energy consumption data is subjected to heterogeneous type fusion and three-dimensional matrix conversion, a space-time correlated energy consumption grid structure diagram is generated by a self-adaptive grid division engine, and a park energy consumption heat map is formed based on a heat rendering model. Based on the heat map, each grid energy consumption distribution data is analyzed by color value and a preset mapping table, and an abnormally high-consumption grid is identified by comparing a preset threshold value with an energy consumption analysis model. Finally, according to the energy consumption position, device type and duration of the high-consumption grid, a comprehensive operation and maintenance adjustment scheme containing device control parameter optimization, energy scheduling scheme and execution priority sorting is matched and generated from an energy management strategy library, and dynamic optimization and closed-loop management of park energy consumption and operation and maintenance decision are realized.

[0016] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art from the description, or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by particularly pointed out in the written description and the accompanying drawings. BRIEF DESCRIPTION OF DRAWINGS

[0017] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following will briefly introduce the drawings needed to be used in the embodiments of the present application. It should be understood that the following drawings only show some of the embodiments of the present application, and therefore should not be regarded as a limitation on the scope, and for those skilled in the art, other related drawings can also be obtained without creative labor on the basis of these drawings.

[0018] Figure 1 The flow chart of the CIM-based smart park operation and maintenance management method provided by the embodiments of the present application; Figure 2 The flow chart of the generation of repair work order of the CIM-based smart park operation and maintenance management method provided by the embodiments of the present application; Figure 3 The flow chart of the obtaining of park energy consumption heat map of the CIM-based smart park operation and maintenance management method provided by the embodiments of the present application; Figure 4 The flow chart of the obtaining of grid energy consumption too high information of the CIM-based smart park operation and maintenance management method provided by the embodiments of the present application; Figure 5 The flow chart of the generation of energy operation and maintenance adjustment scheme of the CIM-based smart park operation and maintenance management method provided by the embodiments of the present application. DETAILED DESCRIPTION

[0019] The technical solutions in the embodiments of the present application will be described clearly and completely in the following with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some of the embodiments of the present application, but not all the embodiments. The components of the embodiments of the present application described and shown in the drawings herein can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present application provided in the drawings is not intended to limit the scope of the claimed present application, but only represents selected embodiments of the present application. Based on the embodiments of the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of the present application.

[0020] It should be noted that similar reference numbers and letters represent similar items in the following drawings, and therefore, once an item is defined in one drawing, it does not need to be further defined and explained in subsequent drawings. Meanwhile, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description, and cannot be understood as indicating or implying relative importance. It should be noted that the user information (including but not limited to user equipment information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in the present application are all information and data authorized by the user or fully authorized by all parties, and the collection, use and processing of related data need to comply with relevant laws, regulations and standards of relevant countries and regions.

[0021] Please refer to Figure 1 , Figure 1 is a flowchart of a CIM-based smart park operation and maintenance method in some embodiments of the present application. The CIM-based smart park operation and maintenance method is used in a terminal device, such as a computer, a mobile phone terminal, etc. The CIM-based smart park operation and maintenance method includes the following steps: S101, collecting building group information, geographic location information, Internet of Things device information and system service information of a park in a preset time period and constructing a park digital twin model, extracting device facility state information and energy consumption information according to the park digital twin model; S102, processing according to the device facility state information through a preset device fault prediction model to generate a repair work order; S103, performing grid processing according to the energy consumption information to obtain a park energy consumption heat map; S104, extracting energy consumption distribution data of a plurality of grids according to the park energy consumption heat map, processing through a preset energy consumption analysis model to obtain grid energy consumption too high information; S105, processing according to the grid energy consumption too high information through a preset energy management strategy library to generate an energy operation and maintenance adjustment scheme.

[0022] Wherein, first, based on the CIM platform, the park building group information (including physical properties, real scene point cloud data, etc.), geographic location information (such as geographic coordinates, terrain data), Internet of Things device operation state and system business data are integrated, and a dynamically updated digital twin model is constructed, and the real-time state of the device (such as current, temperature, load) and multi-dimensional energy consumption data are extracted from it. Secondly, through the preset machine learning fault prediction model (such as LSTM or random forest algorithm), the device state is analyzed, the historical fault data and real-time monitoring values are combined to generate a repair work order containing the fault type and device details, and predictive maintenance is realized. At the same time, after the energy consumption data is fused by heterogeneous types (such as equivalent conversion of electricity, water and gas) and three-dimensional matrix conversion, the adaptive grid division algorithm is used to generate a spatio-temporal correlated energy consumption grid structure diagram, and a park energy consumption heat map is formed through a heat rendering model (such as color gradient mapping and three-dimensional visualization engine). Based on the comparison of the color value of the heat map with the preset threshold value, the abnormally high-consumption grid is located, and an optimization scheme is generated by combining the energy management strategy library (built-in device control rules, energy dispatching priority), such as adjusting the air conditioning operating parameters or turning off redundant lighting. The present application solves the problems of data island, response lag and extensive energy consumption management in traditional operation and maintenance through the fusion of CIM and digital twin technology, grid-based energy consumption analysis and closed-loop strategy matching.

[0023] Please refer to Figure 2 , Figure 2 is a flowchart of constructing a park digital twin model based on the CIM-based smart park operation and maintenance management method in some embodiments of the present application. According to the embodiment of the present application, the building group information, geographic location information, Internet of Things device information and system business information of the park in a preset time period are collected, and a park digital twin model is constructed, specifically: S201, collecting building group information, geographic location information, Internet of Things device information and system business information of the park in a preset time period; S202, the building group information includes physical properties, real scene point cloud data, energy consumption data and maintenance records; S203, the geographic location information includes geographic coordinates, device relative position data and park topography; S204, the Internet of Things device information includes device type information and operation state information; S205, the system business information includes business type information, business process information and business mapping relationship information; S206, constructing a park digital twin model according to the building group information, geographic location information, Internet of Things device information and system business information.

[0024] The technical core of the above-mentioned application is to collect building information (including building physical properties, high-precision real scene point cloud data, energy consumption records and maintenance history), geographic location information (geographic coordinates, device topology relationship and topographic data), Internet of Things device information (device type and real-time running state) and system business information (business type, process logic and system interaction mapping), and based on the CIM platform, the above-mentioned multi-source heterogeneous data is standardized, cleaned and associated. For example, by using the spatial coordinate alignment technology, the BIM model and the GIS topographic data are superimposed, and the Internet of Things sensor real-time data stream is bound by combining the device unique identifier, a time-space synchronous and business-coupled digital twin model is constructed. The model has a built-in dynamic update engine, which receives device state changes and business events in real time, and supports API extension of third-party data (such as weather, energy prices) to enhance scene adaptability. The innovation lies in: breaking the data island through the CIM platform, realizing the deep integration of building, geographic, device and business data; based on point cloud calibration and geographic coordinates to ensure three-dimensional spatial accuracy, and embedding business rules to realize operation and maintenance and business collaborative optimization.

[0025] Please refer to Figure 3 , Figure 3 is a flowchart of generating a repair work order based on the CIM-based smart park operation and maintenance management method in some embodiments of the application. According to the embodiment of the application, the device facility state information is processed by a preset device fault prediction model to generate a repair work order, specifically: S301, extracting real-time monitoring values, power curve fluctuation data, online state information and load data according to the device facility state information; S302, processing the real-time monitoring values, power curve fluctuation data, online state information and load data by a preset device fault prediction model to generate a repair work order; S303, the repair work order includes fault device basic information, fault type and fault repair time.

[0026] The technical core of the above-mentioned application is that first, the state information of the equipment and facility is extracted from the digital twin model, including real-time monitoring values (such as temperature, vibration frequency, current and voltage data), power consumption curve fluctuation data (abnormal peak value or periodic fluctuation is captured through time series analysis), online state information (device networking state, communication interruption record) and load data (running power, device load rate), and the above-mentioned information is normalized and feature extracted (for example, the current harmonic distortion rate is extracted as an electrical fault feature) through a data preprocessing module. Subsequently, the processed data is input into a preset device fault prediction model (such as a model constructed based on an LSTM neural network or a random forest algorithm, the training data of which covers historical fault records, device operation logs and sensor time series data), potential fault modes (such as motor overload, line short circuit, sensor failure) are identified and fault probabilities are calculated through model analysis. When the fault probability exceeds a preset threshold, a repair work order is automatically generated by the system, which includes basic information of the faulty device (device number, installation location, system to which it belongs), fault type (fault label output by the classification model, such as “bearing wear” and “insulation aging”) and fault repair time (estimated repair time based on the regression model). In addition, the work order generation module has built-in dynamic priority rules (such as combining device criticality level, fault impact range and maintenance resource status), which automatically assign work order processing priorities and push them to the operation and maintenance personnel terminal.

[0027] Please refer to Figure 4 , Figure 4 is a flowchart for obtaining a park energy consumption heat map in the CIM-based smart park operation and maintenance method in some embodiments of the application. According to the embodiment of the application, the grid processing is performed according to the energy consumption information to obtain a park energy consumption heat map, specifically: S401, extracting heterogeneous energy consumption type information, heterogeneous energy consumption data and energy consumption distribution space information from the energy consumption information, converting and fusing the information through a preset energy consumption equivalent model to obtain a three-dimensional energy consumption matrix; S402, performing grid processing on the three-dimensional energy consumption matrix through a preset adaptive grid division engine to obtain an energy consumption grid structure diagram; S403, processing the energy consumption grid structure diagram through a preset heat rendering model to obtain a park energy consumption heat map.

[0028] The energy consumption information is extracted from the digital twin model, including heterogeneous energy consumption types (such as consumption data of electricity, gas, and water resources), heterogeneous energy consumption quantities (such as kilowatt-hour, cubic meter, and other different unit data), and energy consumption distribution space information (spatial coordinates of equipment or regions and energy consumption associated data). Through a preset energy consumption equivalent model (for example, based on international standard unit conversion coefficients or industry energy efficiency ratio rules), the multi-source heterogeneous data is converted into a unified and comparable standard energy consumption equivalent value. For example, the gas consumption quantity is converted into equivalent electric energy according to the calorific value, and a three-dimensional energy consumption matrix (dimensions including time window, spatial coordinates, and energy consumption intensity) is constructed by fusing the time and space dimensions. Secondly, an adaptive grid division engine (based on a spatial clustering algorithm or a density distribution dynamic adjustment grid granularity) is used to divide the three-dimensional matrix into time and space associated energy consumption grid units according to the physical space topological structure of the park, for example, a fine-grained grid (such as 5m x 5m) is used in a high energy consumption density area, and a coarse-grained grid (such as 20m x 20m) is used in a low density area, to generate a grid structure diagram with energy consumption weight values. Finally, a thermal rendering model (based on a color gradient mapping rule, such as red representing high energy consumption and blue representing low energy consumption) is used to convert the energy consumption intensity data in the grid structure diagram into a visualized thermal map, and a three-dimensional rendering engine (such as WebGL or Unity3D) is used to realize dynamic interactive display (such as supporting time axis sliding to view historical energy consumption trends). The scheme solves the problems of scattered data and coarse spatial granularity in traditional energy consumption analysis, and realizes accurate positioning and multi-dimensional comparative analysis of energy consumption anomalies through standardized conversion and adaptive grid division.

[0029] Please refer to Figure 5 , Figure 5 is a flowchart for obtaining grid energy consumption overhigh information in the CIM-based smart park operation and maintenance method in some embodiments of the present application. According to the embodiment of the present application, the energy consumption distribution data of the plurality of grids is extracted from the park energy consumption thermal map, processed by a preset energy consumption analysis model, and grid energy consumption overhigh information is obtained, specifically as follows: S501, color values of a plurality of grids are extracted from the park energy consumption thermal map; S502, grid energy consumption distribution data of the plurality of grids is obtained by querying a preset color energy consumption mapping table according to the color values of the plurality of grids; S503, grid energy consumption analysis data is obtained by processing the grid energy consumption distribution data of the plurality of grids by a preset energy consumption analysis model; S504, the grid energy consumption analysis data is compared with a preset energy consumption threshold; S505, if the grid energy consumption analysis data is greater than or equal to the energy consumption threshold, grid energy consumption overhigh information is obtained.

[0030] Wherein, the color value (such as RGB or HSL value) of each grid unit is extracted from the park energy consumption heat map, and the energy consumption distribution data (including unit area energy consumption, time cumulative energy consumption and peak fluctuation value) of each grid is obtained by querying and converting through a preset color energy consumption mapping table (based on the linear or nonlinear correspondence between color gradient and energy consumption intensity, for example, deep red corresponds to energy consumption intensity ≥50kWh / m2·day). Subsequently, the grid energy consumption distribution data is input into a preset energy consumption analysis model (such as constructed based on clustering algorithm or time series regression model), and the energy consumption trend anomaly (such as sudden increase, continuous over-limit or periodic fluctuation) is identified through the analysis model and the grid energy consumption analysis data (including energy consumption mean, variance and deviation rate from historical benchmark) is generated. Further, the analysis data is compared with the preset energy consumption threshold (dynamically set according to the park type, seasonal factors or industry standards, such as 30kWh / m2·day for summer air conditioning area threshold), if the energy consumption analysis data of a certain grid exceeds or equals the threshold, it is marked as "high energy consumption" and high consumption information containing location coordinates, over-standard value and duration is generated. For example, the weekly energy consumption of a certain grid reaches 38kWh / m2·day and exceeds the threshold (30kWh / m2·day) for 3 days, the system will locate the corresponding area (such as A building 3rd floor east) and trigger the alarm. This method realizes the automatic identification and accurate positioning of energy consumption anomaly through the combination of color mapping and model analysis.

[0031] According to an embodiment of the present application, the grid energy consumption is processed according to the grid energy consumption high information through a preset energy management strategy library, and an energy operation adjustment scheme is generated, specifically: According to the grid energy consumption high information, energy consumption location information, energy consumption high value, energy consumption duration and energy consumption device type information are extracted; According to the energy consumption location information, energy consumption high value, energy consumption duration and energy consumption device type information, a plurality of energy management strategies are obtained by querying and processing through a preset energy management strategy library; According to the plurality of energy management strategies, an energy operation adjustment scheme is generated, including management strategy integration, scheme execution details and strategy priority sorting.

[0032] Wherein, based on the identified grid energy consumption is too high information, the energy consumption position (such as grid coordinates corresponding to the building floor and area number), energy consumption is too high value (such as unit area over standard energy consumption, peak power), energy consumption duration (such as continuous threshold number of days, time period distribution) and associated energy consumption equipment type (such as air conditioning system, lighting equipment, production machinery) are extracted, and the above data is input into the preset energy management strategy library for multi-dimensional matching query. The strategy library has built-in rule engine and dynamic weight algorithm, which integrates device control strategy (such as air conditioning temperature setting adjustment, lighting zoning and time closing), energy scheduling strategy (such as peak valley electricity price period load migration, renewable energy priority calling) and system coordination strategy (such as device linkage start-stop optimization, business scheduling and energy consumption matching), and through fuzzy logic matching or decision tree model, the applicable strategy is screened out (for example: for the continuously high-consumption air conditioning area, the strategy of "temperature up 2℃ + non-office hours closing" is matched; for the short-time peak of production machinery, the strategy of "load balancing + energy storage device intervention" is matched). Then, through the strategy integration module, multiple strategies are subjected to conflict detection and priority sorting (such as dynamic weighting according to energy saving potential, implementation cost, influence range), and a comprehensive operation and maintenance adjustment scheme containing execution details (such as control parameters, execution time window, responsible person) and priority labels (such as urgent, important, routine) is generated. For example, the air conditioning system in a certain area has been running continuously for 3 days above the threshold value, and the scheme will preferentially implement the "temperature setting optimization + night closing" strategy, and simultaneously push the operation and maintenance personnel mobile terminal for closed loop processing.

[0033] According to the embodiments of the present application, further comprising: The energy consumption information, device facility state information and energy operation and maintenance adjustment scheme are written into the blockchain node through the smart contract and the first data evidence that cannot be tampered with is generated based on the preset method; Cross-park data sharing is realized through the alliance chain architecture, and based on the permission control rules, the third party service provider is allowed to query the device historical state data and energy consumption record; A token incentive mechanism is designed, the smart contract automatically issues token rewards for energy saving behavior, and the on-chain voting mechanism is used to decide the global energy scheduling strategy.

[0034] Energy consumption information (such as itemized energy consumption records and grid analysis results), real-time status information of equipment and facilities (such as operating parameters and fault prediction data), and generated energy operation and maintenance adjustment plans (such as policy priorities and execution details) are encapsulated into structured data packets through smart contracts. A unique digital fingerprint is generated using a preset hash algorithm (such as SHA-256) and written into the blockchain node to form an unalterable first-level data certificate, ensuring data integrity and traceability. Secondly, a cross-park collaborative network is built based on the alliance chain architecture, and hierarchical data sharing is achieved through node permission control rules (such as role-based access control (RBAC)). For example, third-party energy service providers are allowed to query the maintenance history and energy consumption trends of specified equipment, but they must pass on-chain identity authentication and dynamic token authorization. A token incentive mechanism is also designed. When the system detects energy-saving behavior (e.g., energy consumption in a certain area remains below a threshold for five consecutive days), a smart contract is triggered to automatically issue token rewards (e.g., ERC-20 standard tokens) to the responsible party, which are then recorded in the blockchain ledger. For global energy scheduling strategies (e.g., peak-valley coordination across multiple campuses), an on-chain voting mechanism (e.g., a voting model based on token holding weight) is used for distributed decision-making, ensuring transparency and participation. For example, after a campus adopts a "photovoltaic energy storage priority" strategy through on-chain voting, the system automatically adjusts the equipment scheduling logic and synchronizes the update to all nodes. This solution leverages blockchain technology to achieve trusted data storage, secure cross-domain sharing, and a closed-loop incentive system for behavior.

[0035] The present invention also discloses a CIM-based smart park operation and maintenance management system, comprising a memory and a processor. The memory includes a CIM-based smart park operation and maintenance management method program. When the CIM-based smart park operation and maintenance management method program is executed by the processor, the following steps are implemented: Collect building complex information, geographic location information, IoT device information, and system business information for a preset time period in the park and build a digital twin model of the park. Extract equipment and facility status information and energy consumption information based on the digital twin model of the park. Processing the equipment and facility status information through a preset equipment failure prediction model to generate a repair work order; Performing grid processing based on the energy consumption information to obtain a park energy consumption heat map; Extracting energy consumption distribution data of multiple grids based on the energy consumption heat map of the park and processing the data through a preset energy consumption analysis model to obtain information about excessive grid energy consumption; The information on excessive grid energy consumption is processed through a preset energy management strategy library to generate an energy operation and maintenance adjustment plan.

[0036] Among them, first, based on the CIM platform, the park building group information (including physical properties, real scene point cloud data, etc.), geographic location information (such as geographic coordinates, terrain data), Internet of Things device running state and system business data are integrated, and a dynamically updated digital twin model is constructed, and the real-time state of the device (such as current, temperature, load) and multi-dimensional energy consumption data are extracted from it. Second, by presetting a machine learning fault prediction model (such as LSTM or random forest algorithm), the device state is analyzed, historical fault data and real-time monitoring values are combined to generate a repair work order containing fault type and device details, and predictive maintenance is realized. At the same time, after the energy consumption data is fused by heterogeneous types (such as equivalent conversion of electricity, water and gas) and three-dimensional matrix conversion, the adaptive grid division algorithm is used to generate a space-time related energy consumption grid structure diagram, and a thermal rendering model (such as color gradient mapping and three-dimensional visualization engine) is used to form a park energy consumption thermal map. Based on the comparison of the color value of the thermal map with the preset threshold value, the abnormally high-consumption grid is located, and the optimization scheme is generated by combining the energy management strategy library (built-in device control rules, energy dispatching priority), for example, adjusting the air conditioner operating parameters or closing redundant lighting. The present application solves the innovation of data island, response lag and extensive energy consumption management in traditional operation and maintenance through the fusion of CIM and digital twin technology, grid energy consumption analysis and closed-loop strategy matching.

[0037] According to the embodiment of the present application, the building group information, geographic location information, Internet of Things device information and system business information of the park in a preset time period are collected, and a digital twin model of the park is constructed, specifically: Collecting building group information, geographic location information, Internet of Things device information and system business information of the park in a preset time period; The building group information includes physical properties, real scene point cloud data, energy consumption data and maintenance records; The geographic location information includes geographic coordinates, device relative position data and park topography; The Internet of Things device information includes device type information and running state information; The system business information includes business type information, business process information and business mapping relationship information; According to the building group information, geographic location information, Internet of Things device information and system business information, a digital twin model of the park is constructed.

[0038] The technical core of the application is to collect building information (including building physical properties, high-precision real scene point cloud data, energy consumption records and maintenance history), geographic location information (geographic coordinates, device topology relationship and terrain data), Internet of Things device information (device type and real-time running state) and system business information (business type, process logic and system interaction mapping), and based on the CIM platform, the above multi-source heterogeneous data is standardized, cleaned and associated, for example, the BIM model and GIS terrain data are superimposed through spatial coordinate alignment technology, combined with the unique identifier of the device to bind the real-time data stream of the Internet of Things sensor, and a digital twin model with time and space synchronization and business coupling is constructed. The model has a built-in dynamic update engine that receives device state changes and business events in real time, and supports API extension of third-party data (such as weather, energy prices) to enhance scene adaptability. The innovation lies in: breaking the data island through the CIM platform to realize deep integration of building, geographic, device and business data; based on point cloud calibration and geographic coordinates to ensure three-dimensional spatial accuracy, and embedded business rules to realize operation and business collaborative optimization.

[0039] According to the embodiment of the application, the device facility state information is processed by a preset device fault prediction model to generate a repair work order, specifically: According to the device facility state information, real-time monitoring values, power curve fluctuation data, online state information and load data are extracted; According to the real-time monitoring values, power curve fluctuation data, online state information and load data, a preset device fault prediction model is used for processing to generate a repair work order; The repair work order includes fault device basic information, fault type and fault repair time length.

[0040] Among them, the technical core of the above-mentioned application is that first, the state information of the equipment facility is extracted from the digital twin model, including real-time monitoring values (such as temperature, vibration frequency, current and voltage data), power consumption curve fluctuation data (abnormal peak value or periodic fluctuation is captured through time series analysis), online state information (device networking state, communication interruption record) and load data (running power, device bearing rate), and the above-mentioned information is normalized and feature extracted (for example, the current harmonic distortion rate is extracted as an electrical fault feature) through a data preprocessing module. Subsequently, the processed data is input into a preset device fault prediction model (such as a model constructed based on an LSTM neural network or a random forest algorithm, which training data covers historical fault records, device operation logs and sensor time series data), potential fault modes (such as motor overload, line short circuit, sensor failure) are identified and fault probability is calculated through model analysis. When the fault probability exceeds the preset threshold, the system automatically generates a repair work order, which includes fault device basic information (device number, installation location, system to which it belongs), fault type (fault label output by the classification model, such as "bearing wear" and "insulation aging"), and fault repair time (maintenance time estimation based on the regression model prediction). In addition, the work order generation module has built-in dynamic priority rules (such as combining device criticality level, fault impact range and maintenance resource status), automatically assigning work order processing priority and pushing to the operation and maintenance personnel terminal.

[0041] According to the embodiment of the application, the energy consumption information is subjected to grid processing to obtain a park energy consumption heat map, specifically: The heterogeneous energy consumption type information, the heterogeneous energy consumption amount data and the energy consumption distribution space information are extracted from the energy consumption information, and are subjected to conversion and fusion processing through a preset energy consumption equivalent model to obtain a three-dimensional energy consumption matrix; The three-dimensional energy consumption matrix is subjected to grid processing through a preset adaptive grid division engine to obtain an energy consumption grid structure diagram; The energy consumption grid structure diagram is processed through a preset heat rendering model to obtain a park energy consumption heat map.

[0042] The energy consumption information is extracted from the digital twin model, including heterogeneous energy consumption types (such as consumption data of electricity, gas, and water resources), heterogeneous energy consumption amounts (such as kilowatt-hour, cubic meter, and other different unit data), and energy consumption distribution space information (spatial coordinates of equipment or regions and energy consumption associated data). Through a preset energy consumption equivalent model (for example, based on international standard unit conversion coefficients or industry energy efficiency ratio rules), the multi-source heterogeneous data is converted into a unified and comparable standard energy consumption equivalent value. For example, the gas consumption amount is converted into equivalent electric energy according to the calorific value, and a three-dimensional energy consumption matrix (dimensions including time window, spatial coordinates, and energy consumption intensity) is constructed by fusing the time and space dimensions. Secondly, an adaptive grid division engine (based on a spatial clustering algorithm or a density distribution dynamic adjustment grid granularity) is used to divide the three-dimensional matrix into time and space associated energy consumption grid units according to the physical space topological structure of the park, for example, fine-grained grids (such as 5m x 5m) are used in high energy consumption density areas, and coarse-grained grids (such as 20m x 20m) are used in low density areas, to generate a grid structure diagram with energy consumption weight values. Finally, the energy consumption intensity data in the grid structure diagram is converted into a visualized heat map through a heat rendering model (based on a color gradient mapping rule, such as red representing high energy consumption and blue representing low energy consumption), and a three-dimensional rendering engine (such as WebGL or Unity3D) is used to realize dynamic interactive display (such as supporting time axis sliding to view historical energy consumption trends). The scheme solves the problems of scattered data and coarse spatial granularity in traditional energy consumption analysis, and realizes accurate positioning and multi-dimensional comparative analysis of energy consumption anomalies through standardized conversion and adaptive grid division.

[0043] According to the embodiment of the application, the energy consumption distribution data of the plurality of grids extracted from the park energy consumption heat map is processed through a preset energy consumption analysis model to obtain grid energy consumption overhigh information, specifically: Color values of the plurality of grids are extracted from the park energy consumption heat map; The color values of the plurality of grids are queried through a preset color energy consumption mapping table to obtain grid energy consumption distribution data of the plurality of grids; The grid energy consumption distribution data of the plurality of grids is processed through a preset energy consumption analysis model to obtain grid energy consumption analysis data; The grid energy consumption analysis data is compared with a preset energy consumption threshold; If the grid energy consumption analysis data is greater than or equal to the energy consumption threshold, the grid energy consumption overhigh information is obtained.

[0044] Wherein, the color value (such as RGB or HSL value) of each grid unit is extracted from the park energy consumption heat map, and the energy consumption distribution data (including unit area energy consumption, time cumulative energy consumption and peak fluctuation value) of each grid is obtained by querying and converting through a preset color energy consumption mapping table (based on the linear or nonlinear correspondence between color gradient and energy consumption intensity, for example, deep red corresponds to energy consumption intensity ≥ 50 kWh / m2·day). Subsequently, the grid energy consumption distribution data is input into a preset energy consumption analysis model (such as constructed based on clustering algorithm or time series regression model), and the energy consumption trend anomaly (such as sudden increase, continuous over-limit or periodic fluctuation) is identified through the analysis model and the grid energy consumption analysis data (including energy consumption mean, variance and deviation rate from historical benchmark) is generated. Further, the analysis data is compared with the preset energy consumption threshold (dynamically set according to the park type, seasonal factors or industry standards, such as 30 kWh / m2·day for summer air conditioning area threshold), if the energy consumption analysis data of a certain grid exceeds or equals the threshold, it is marked as "high energy consumption" and high consumption information containing location coordinates, over-standard value and duration is generated. For example, the weekly energy consumption of a certain grid reaches 38 kWh / m2·day and exceeds the threshold (30 kWh / m2·day) for 3 days, the system will locate the corresponding area (such as A building 3rd floor east) and trigger the alarm. This method realizes the automatic identification and accurate positioning of energy consumption anomaly through the combination of color mapping and model analysis.

[0045] According to the embodiment of the present application, the grid energy consumption is processed according to the grid energy consumption high information through a preset energy management strategy library, and an energy operation adjustment scheme is generated, specifically: According to the grid energy consumption high information, energy consumption location information, energy consumption high value, energy consumption duration and energy consumption device type information are extracted; According to the energy consumption location information, energy consumption high value, energy consumption duration and energy consumption device type information, a plurality of energy management strategies are obtained by querying and processing through a preset energy management strategy library; According to the plurality of energy management strategies, an energy operation adjustment scheme is generated, including management strategy integration, scheme execution details and strategy priority sorting.

[0046] Wherein, based on the identified grid energy consumption is too high information, the energy consumption position (such as grid coordinates corresponding to the building floor and area number), energy consumption is too high value (such as unit area over standard energy consumption, peak power), energy consumption duration (such as continuous threshold number of days, time period distribution) and associated energy consumption equipment type (such as air conditioning system, lighting equipment, production machinery) are extracted, and the above data is input into the preset energy management strategy library for multi-dimensional matching query. The strategy library has built-in rule engine and dynamic weight algorithm, which integrates device control strategy (such as air conditioning temperature setting adjustment, lighting zoning and time closing), energy scheduling strategy (such as peak valley electricity price period load migration, renewable energy priority calling) and system coordination strategy (such as device linkage start-stop optimization, business scheduling and energy consumption matching), and through fuzzy logic matching or decision tree model, the applicable strategy is screened out (for example: for the continuously high-consumption air conditioning area, the strategy of "temperature up 2℃ + non-office hours closing" is matched; for the short-time peak of production machinery, the strategy of "load balancing + energy storage device intervention" is matched). Then, through the strategy integration module, multiple strategies are subjected to conflict detection and priority sorting (such as dynamic weighting according to energy saving potential, implementation cost, influence range), and a comprehensive operation and maintenance adjustment scheme containing execution details (such as control parameters, execution time window, responsible person) and priority labels (such as urgent, important, routine) is generated. For example, the air conditioning system in a certain area has been running continuously for 3 days above the threshold value, and the scheme will preferentially implement the "temperature setting optimization + night closing" strategy, and simultaneously push the operation and maintenance personnel mobile terminal to close the loop.

[0047] According to the embodiments of the present application, further comprising: The energy consumption information, device facility state information and energy operation and maintenance adjustment scheme are written into the blockchain node through the smart contract and the first data evidence that cannot be tampered with is generated based on the preset method; Cross-park data sharing is realized through the alliance chain architecture, and based on the permission control rules, the third party service provider is allowed to query the device historical state data and energy consumption record; A token incentive mechanism is designed, the smart contract automatically issues token rewards for energy saving behavior, and the on-chain voting mechanism is used to decide the global energy scheduling strategy.

[0048] Among them, the energy consumption information (such as sub-item energy consumption record, gridding analysis result), equipment and facility real-time state information (such as running parameter, fault prediction data) and generated energy operation adjustment scheme (such as strategy priority, execution details) are encapsulated as structured data package through intelligent contract, and unique digital fingerprint is generated by using preset hash algorithm (such as SHA-256), and is written into block chain node to form tamper-proof first data evidence, so that the data integrity and traceability are ensured. Secondly, based on the alliance chain architecture, the cross-park cooperation network is built, the data hierarchical sharing is realized through the node permission control rule (such as role-based access control RBAC), for example, the third-party energy service provider is allowed to query the maintenance history and energy consumption trend of the specified equipment, but needs to pass through on-chain identity authentication and dynamic token authorization. At the same time, the token incentive mechanism is designed, when the system detects the energy-saving behavior (such as the energy consumption of a certain area is lower than the threshold for 5 consecutive days), the smart contract is triggered to automatically issue token rewards (such as ERC-20 standard token) to the responsible subject, and is recorded to the block chain account book;For global energy dispatching strategy (such as multi-park peak-valley cooperation), the on-chain voting mechanism (such as the voting model based on token weight) is used for distributed decision-making, so that the strategy transparency and participation are ensured. For example, after a certain park decides to implement the "photovoltaic energy storage priority" strategy through on-chain voting, the system automatically adjusts the device scheduling logic and synchronously updates to all nodes. The scheme realizes data credible evidence, cross-domain safe sharing and behavior incentive closed loop through the block chain technology.

[0049] The third aspect of the application provides a computer readable storage medium, the computer readable storage medium comprises a CIM-based smart park operation and maintenance management method program, and the CIM-based smart park operation and maintenance management method program is executed by a processor to realize the steps of the CIM-based smart park operation and maintenance management method according to any one of the above.

[0050] The application discloses a CIM-based smart park operation and maintenance management method and system and a medium, and the core of the application is that building a dynamic digital twin model by integrating building group information (physical properties, point cloud data), geographic location information (geographic coordinates, topography), Internet of Things device operation state and system business data through a CIM platform, and extracting device state and energy consumption information based on the model to realize full life cycle management and energy optimization. Multi-source data fusion and digital twin modeling: through BIM, GIS and IoT data collaboration, accurate mapping of physical space and virtual model is realized, and real-time monitoring of device state (such as current, load) and multi-dimensional analysis of energy consumption are supported; Predictive maintenance: a device failure prediction model (such as LSTM) is constructed by using a machine learning algorithm, and a repair work order (including fault type and repair time) is generated based on power curve fluctuation, load anomaly and other data, which significantly shortens the fault response time; Grid energy consumption management: a three-dimensional matrix is generated through heterogeneous energy consumption equivalent conversion, combined with an adaptive grid division engine (dynamic adjustment granularity) and a heat rendering model, energy consumption heat map visualization is realized, and high-consumption areas are accurately located based on color mapping and threshold comparison; Strategy closed-loop optimization: from the energy management strategy library, device regulation, energy scheduling and system collaborative strategy are matched to generate priority-ordered operation and maintenance schemes; Blockchain trusted collaboration: through a smart contract, energy consumption data and operation and maintenance schemes are stored on a chain (such as SHA-256 hash), cross-park data security sharing is realized based on a consortium chain (RBAC permission control), and energy-saving behavior and global strategy collaboration are driven through a token incentive (ERC-20 standard) and an on-chain voting mechanism (token weight model). The application improves the accuracy of device failure prediction, the efficiency of energy consumption anomaly detection and the comprehensive energy saving rate; the introduction of blockchain technology reduces the risk of data tampering, improves cross-domain collaboration efficiency, and realizes the goals of reducing operation and maintenance costs and sustainable management through closed-loop optimization and incentive feedback mechanisms.

[0051] In several embodiments provided in the present application, it should be understood that the disclosed devices and methods can be implemented in other ways. The device embodiments described above are only illustrative, for example, the division of the units is only a logical function division, and actual implementation can have another division mode, for example, multiple units or components can be combined, or can be integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed components can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0052] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units; they can be located in one place or distributed on multiple network units; and part or all of the units can be selected according to actual needs to achieve the purposes of the embodiments.

[0053] In addition, each functional unit in each embodiment of the present application can be integrated into one processing unit, or each unit can be a separate unit, or two or more units can be integrated into one unit; the integrated unit can be implemented in the form of hardware or in the form of hardware plus software functional units.

[0054] Those of ordinary skill in the art can understand that all or part of the steps of the above method embodiments can be completed by relevant hardware instructed by programs, and the programs can be stored in readable storage media, and when the programs are executed, steps including the above method embodiments are executed; and the storage media includes mobile storage devices, read-only memories, random access memories, magnetic discs or optical discs, and various media that can store program codes.

[0055] Alternatively, the integrated units of the present application, if implemented in the form of software functional modules and sold or used as independent products, can also be stored in a readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present application can be embodied in the form of software products, which are stored in a storage medium and include several instructions for making a computer device (which can be a personal computer, a server, or a network device, etc.) execute all or part of the methods described in the embodiments of the present application. The storage medium includes mobile storage devices, ROM, RAM, magnetic discs or optical discs, and various media that can store program codes.

Claims

1. The CIM-based smart park operation and maintenance management method is characterized by: The following steps are involved: Collect building complex information, geographic location information, IoT device information, and system business information for a preset time period in the park and build a digital twin model of the park. Extract equipment and facility status information and energy consumption information based on the digital twin model of the park. Processing the equipment and facility status information through a preset equipment failure prediction model to generate a repair work order; Performing grid processing based on the energy consumption information to obtain a park energy consumption heat map; Extracting energy consumption distribution data of multiple grids based on the energy consumption heat map of the park and processing the data through a preset energy consumption analysis model to obtain information about excessive grid energy consumption; The information on excessive grid energy consumption is processed through a preset energy management strategy library to generate an energy operation and maintenance adjustment plan.

2. The CIM-based smart park operation and maintenance management method according to claim 1 is characterized in that: The collection of building complex information, geographic location information, IoT device information, and system service information within a preset time period of the park and the construction of a digital twin model of the park are specifically as follows: Collect building complex information, geographic location information, IoT device information, and system business information within a preset time period in the park; The building complex information includes physical attributes, real-time cloud data, energy consumption data and maintenance records; The geographic location information includes geographic coordinates, equipment relative location data and park topography; The IoT device information includes device type information and operating status information; The system business information includes business type information, business process information and business mapping relationship information; A digital twin model of the park is constructed based on the building complex information, geographic location information, IoT device information and system business information.

3. The CIM-based smart park operation and maintenance management method according to claim 1 is characterized in that: The equipment and facility status information is processed using a preset equipment failure prediction model to generate a repair work order, specifically: Extracting real-time monitoring values, power consumption curve fluctuation data, online status information and load data based on the equipment and facility status information; Generate a repair work order based on the real-time monitoring value, power consumption curve fluctuation data, online status information and load data through a preset equipment failure prediction model; The repair work order includes basic information of the faulty equipment, fault type and fault repair time.

4. The CIM-based smart park operation and maintenance management method according to claim 1, characterized in that: The energy consumption information is gridded to obtain a park energy consumption heat map, specifically: Heterogeneous energy consumption type information, heterogeneous energy consumption data and energy consumption distribution space information are extracted based on the energy consumption information, and converted and integrated through a preset energy consumption equivalent model to obtain a three-dimensional energy consumption matrix; The three-dimensional energy consumption matrix is ​​gridded by a preset adaptive grid division engine to obtain an energy consumption grid structure diagram; The energy consumption grid structure diagram is processed using a preset thermal rendering model to obtain a park energy consumption thermal map.

5. The CIM-based smart park operation and maintenance management method according to claim 4 is characterized in that: The energy consumption distribution data of multiple grids extracted from the park energy consumption heat map is processed through a preset energy consumption analysis model to obtain information on excessive grid energy consumption, specifically: Extracting color values ​​of multiple grids according to the park energy consumption heat map; Querying a preset color energy consumption mapping table according to the color values ​​of the plurality of grids to obtain grid energy consumption distribution data of the plurality of grids; Processing the grid energy consumption distribution data of the plurality of grids through a preset energy consumption analysis model to obtain grid energy consumption analysis data; Comparing the grid energy consumption analysis data with a preset energy consumption threshold; If the grid energy consumption analysis data is greater than or equal to the energy consumption threshold, the grid energy consumption is too high information is obtained.

6. The CIM-based smart park operation and maintenance management method according to claim 5 is characterized in that: The energy management strategy library is used to process the information about excessive grid energy consumption and generate an energy operation and maintenance adjustment plan, specifically: Extracting energy consumption location information, energy consumption value, energy consumption duration and energy consuming device type information based on the grid high energy consumption information; According to the energy consumption location information, the excessive energy consumption value, the energy consumption duration and the energy consuming device type information, a preset energy management strategy library is queried and processed to obtain multiple energy management strategies; An energy operation and maintenance adjustment plan is generated according to the multiple energy management strategies, including management strategy integration, plan execution details and strategy priority sorting.

7. The CIM-based smart park operation and maintenance management system is characterized by: The system includes a memory and a processor, wherein the memory includes a CIM-based smart park operation and maintenance management method program, and when the CIM-based smart park operation and maintenance management method program is executed by the processor, the following steps are implemented, specifically: Collect building complex information, geographic location information, IoT device information, and system business information for a preset time period in the park and build a digital twin model of the park. Extract equipment and facility status information and energy consumption information based on the digital twin model of the park. Processing the equipment and facility status information through a preset equipment failure prediction model to generate a repair work order; Performing grid processing based on the energy consumption information to obtain a park energy consumption heat map; Extracting energy consumption distribution data of multiple grids based on the energy consumption heat map of the park and processing the data through a preset energy consumption analysis model to obtain information about excessive grid energy consumption; The information on excessive grid energy consumption is processed through a preset energy management strategy library to generate an energy operation and maintenance adjustment plan.

8. The CIM-based smart park operation and maintenance management system according to claim 7 is characterized in that: The collection of building complex information, geographic location information, IoT device information, and system service information within a preset time period of the park and the construction of a digital twin model of the park are specifically as follows: Collect building complex information, geographic location information, IoT device information, and system business information within a preset time period in the park; The building complex information includes physical attributes, real-time cloud data, energy consumption data and maintenance records; The geographic location information includes geographic coordinates, equipment relative location data and park topography; The IoT device information includes device type information and operating status information; The system business information includes business type information, business process information and business mapping relationship information; A digital twin model of the park is constructed based on the building complex information, geographic location information, IoT device information and system business information.

9. The CIM-based smart park operation and maintenance management system according to claim 7, characterized in that: The equipment and facility status information is processed using a preset equipment failure prediction model to generate a repair work order, specifically: Extracting real-time monitoring values, power consumption curve fluctuation data, online status information and load data based on the equipment and facility status information; Generate a repair work order based on the real-time monitoring value, power consumption curve fluctuation data, online status information and load data through a preset equipment failure prediction model; The repair work order includes basic information of the faulty equipment, fault type and fault repair time.

10. A computer-readable storage medium, characterized in that The computer-readable storage medium includes a CIM-based smart park operation and maintenance management method, system and medium program. When the CIM-based smart park operation and maintenance management method, system and medium program are executed by a processor, the steps of the CIM-based smart park operation and maintenance management method as described in any one of claims 1 to 6 are implemented.

Images