City-level digital twin cloud management platform and method supporting multi-scene access

Abstract

The invention provides a city-level digital twinborn cloud management platform and method supporting multi-scene access, and relates to the technical field of digital twinborn, and the platform comprises a multi-dimensional modeling module which is used for constructing a city digital twinborn model; the risk analysis module is used for constructing a multi-scene risk map; the operation and maintenance decision module is used for obtaining a multi-scene operation and maintenance space; the evaluation optimization module is used for obtaining a multi-scene operation and maintenance population; the global optimization module is used for determining a multi-scene operation and maintenance optimization result; and the cloud management module is used for executing risk adaptive cloud management of the city according to the multi-scene operation and maintenance optimization result. The technical problems that in existing digital twin city management, multi-scene collaboration is difficult, risk analysis is one-sided and lagged, and management efficiency is low are solved, and the technical effects of improving city operation and maintenance efficiency and enhancing risk response capacity are achieved by constructing the multi-scene risk map and combining an evolutionary optimization algorithm.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of digital twinning, in particular to a city-level digital twinning cloud management platform and method supporting multi-scene access. BACKGROUND

[0002] With the accelerated advancement of global urbanization, the scale of cities is expanding and the complexity of functions is rising. Modern cities have gradually evolved into complex giant systems deeply intertwined by infrastructure, transportation networks, energy systems, public safety and other multi-scene scenarios. Under this background, city management is facing unprecedented challenges: on the one hand, data from different scenarios is scattered in different departments and systems, forming "data islands", making it difficult to achieve cross-scene information fusion and correlation analysis; on the other hand, traditional city management methods focus on single-scene risk warning and operation and maintenance decision-making, lacking the ability to analyze the dynamic coupling relationship of multi-scene risks, resulting in risk response often being limited to local optimization, making it difficult to develop scientific and coordinated operation and maintenance strategies from a global perspective. In addition, the real-time perception and dynamic simulation of city operation status are increasingly urgent, but existing digital twinning technologies focus on single-scene modeling, lacking the ability to support multi-scene data unified access, multi-source risk correlation deduction and global operation and maintenance decision optimization, making it difficult to meet the fine and intelligent management needs of city-level complex systems. SUMMARY

[0003] The present application provides a city-level digital twinning cloud management platform and method supporting multi-scene access, aiming to solve the technical problems of multi-scene coordination difficulty in existing digital twinning city management, leading to one-sided and lagging risk analysis, and low management efficiency.

[0004] The first aspect of the present application provides a city-level digital twinning cloud management platform supporting multi-scene access, which comprises: a multi-dimensional modeling module for multi-dimensional modeling according to multi-scene characteristic data of a city to construct a city digital twinning model; a risk analysis module for multi-scene risk analysis according to the city digital twinning model to construct a multi-scene risk map; an operation and maintenance decision module for operation and maintenance decision-making of the city according to the multi-scene risk map to obtain a multi-scene operation and maintenance space; an evaluation and optimization module for evaluation and optimization of the multi-scene operation and maintenance space through a multi-scene guarantee analysis model to obtain a multi-scene operation and maintenance population; a global optimization module for global evolutionary optimization of the multi-scene operation and maintenance population according to a predetermined evolution number to determine a multi-scene operation and maintenance optimization result; and a cloud management module for executing risk adaptive cloud management of the city according to the multi-scene operation and maintenance optimization result.

[0005] In a second aspect, the application discloses a city-level digital twin cloud management method supporting multi-scene access, which is implemented by the city-level digital twin cloud management platform supporting multi-scene access. The method comprises the following steps: performing multi-dimensional modeling according to multi-scene characteristic data of a city to construct a city digital twin model; performing multi-scene risk analysis according to the city digital twin model to construct a multi-scene risk atlas; performing operation and maintenance decision-making on the city according to the multi-scene risk atlas to obtain a multi-scene operation and maintenance space; evaluating and optimizing the multi-scene operation and maintenance space through a multi-scene guarantee analysis model to obtain a multi-scene operation and maintenance population; performing global evolution optimization on the multi-scene operation and maintenance population according to a predetermined evolution number to determine a multi-scene operation and maintenance optimization result; and performing risk adaptive cloud management on the city according to the multi-scene operation and maintenance optimization result.

[0006] The one or more technical solutions provided in the application have at least the following technical effects or advantages:

[0007] The method comprises the following steps: performing multi-dimensional modeling according to multi-scene characteristic data of a city to construct a city digital twin model; performing multi-scene risk analysis according to the city digital twin model to construct a multi-scene risk atlas; performing operation and maintenance decision-making on the city according to the multi-scene risk atlas to obtain a multi-scene operation and maintenance space; evaluating and optimizing the multi-scene operation and maintenance space through a multi-scene guarantee analysis model to obtain a multi-scene operation and maintenance population; performing global evolution optimization on the multi-scene operation and maintenance population according to a predetermined evolution number to determine a multi-scene operation and maintenance optimization result; and performing risk adaptive cloud management on the city according to the multi-scene operation and maintenance optimization result.

[0008] The above description is only a summary of the technical solutions of the application. In order to make the technical solutions of the application more clearly understood, the following detailed description is made in accordance with the content of the description, and in order to make the above and other purposes, characteristics and advantages of the application more obvious and easy to understand, the following detailed description is made. BRIEF DESCRIPTION OF DRAWINGS

[0009] Figure 1 A city-level digital twin cloud management platform structure diagram supporting multi-scene access is provided for the embodiments of the application.

[0010] Figure 2 A city-level digital twin cloud management method flow diagram supporting multi-scene access is provided for the embodiments of the application.

[0011] Figure labeling: Multidimensional modeling module 11, Risk analysis module 12, Operation and maintenance decision module 13, Evaluation and optimization module 14, Global optimization module 15, Cloud management module 16. Detailed Implementation

[0012] This application's embodiments address the technical problems in existing digital twin city management, such as difficulties in multi-scenario collaboration, leading to one-sided and delayed risk analysis and low management efficiency, by providing a city-level digital twin cloud management platform and method that supports multi-scenario access.

[0013] After introducing the basic principles of this application, various non-limiting embodiments of this application will be described in detail below with reference to the accompanying drawings. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit this application.

[0014] Example 1, as Figure 1 As shown in the embodiment of this application, a city-level digital twin cloud management platform supporting multi-scenario access is provided, the platform comprising:

[0015] Multidimensional modeling module 11 is used to perform multidimensional modeling based on multi-scene feature data of the city and build a digital twin model of the city.

[0016] Specifically, in the multi-dimensional modeling module 11, a multi-scenario monitoring dataset covering various key areas of urban operation is first obtained from data sources such as IoT sensing devices, traffic monitoring systems, energy management systems, and urban infrastructure operation and maintenance platforms. This dataset includes multi-dimensional information such as infrastructure monitoring data, traffic monitoring data, and energy monitoring data. Subsequently, the collected multi-scenario monitoring dataset undergoes data cleaning, including outlier removal, missing value completion, and duplicate value removal, to ensure the accuracy of the input data. Afterward, the cleaned multi-scenario feature data is input into the 3D simulation software and injected into a pre-set urban model framework using digital twin technology. This urban model framework typically employs a fusion design using Building Information Modeling (BIM), Geographic Information System (GIS), and real-time 3D engine technologies. The BIM model accurately depicts the internal structure and attributes of important individual facilities, GIS data provides macroscopic geospatial relationships and topography, and the 3D engine is responsible for integrating and rendering to form a visualized urban appearance. The resulting digital twin model of the city can not only intuitively reflect the physical structure of the city, but also dynamically simulate the operating status and evolution trend under different scenarios, thus providing a unified digital support environment for subsequent risk analysis, operation and maintenance decision-making and optimization analysis.

[0017] Furthermore, the multidimensional modeling module 11 includes:

[0018] A multi-scenario monitoring dataset for the city is obtained, which includes infrastructure monitoring data, traffic monitoring data, and energy monitoring data; the multi-scenario monitoring dataset is cleaned to generate multi-scenario feature data.

[0019] Preferably, in the multi-dimensional modeling module 11, the obtained multi-scenario monitoring dataset includes infrastructure monitoring data, traffic monitoring data, and energy monitoring data for the city. Infrastructure monitoring data includes building structure, water supply network pressure, drainage pipe flow, power line operation status, and communication facility operation status; traffic monitoring data includes road traffic flow, vehicle speed, road congestion, traffic signal status, and public transportation operation status; energy monitoring data includes electricity load, gas consumption, renewable energy supply, and energy supply-demand balance status. Subsequently, this data undergoes data cleaning. For potential outliers, threshold filtering and statistical models (such as Z-Score and IQR methods) are used to automatically identify and remove outliers that clearly exceed physical meaning. For potential missing values, linear interpolation is used to fill missing values ​​for continuous data (such as temperature and electricity consumption), and mode is used to fill missing values ​​for categorical data (such as equipment status). Data with a missing value rate exceeding 30% is directly removed. For potential duplicate values, deduplication is performed based on a composite primary key of timestamp and sensor ID. After cleaning the multi-scenario monitoring dataset, a set of high-quality, highly reliable multi-scenario feature data can be obtained, providing a reliable data foundation for subsequent multi-dimensional modeling.

[0020] The risk analysis module 12 is used to perform multi-scenario risk analysis based on the city digital twin model and construct a multi-scenario risk map.

[0021] Specifically, in the risk analysis module 12, after constructing the city's digital twin model, anomaly detection and simulation are performed for three different scenarios: infrastructure risk, transportation risk, and energy risk. The simulation results are then analyzed using the corresponding analysis network to construct a multi-scenario risk map. This multi-scenario risk map reflects the risk distribution and severity of each individual area, providing city managers with a complete and visualized panoramic risk map for subsequent operation and maintenance decisions and safeguard optimization.

[0022] Furthermore, the risk analysis module 12 includes:

[0023] Infrastructure risk analysis is performed based on the city's digital twin model to obtain an infrastructure risk map; traffic risk analysis is performed based on the city's digital twin model to obtain a traffic risk map; energy risk analysis is performed based on the city's digital twin model to obtain an energy risk map; the infrastructure risk map, the traffic risk map, and the energy risk map are integrated to obtain the multi-scenario risk map.

[0024] Preferably, in the risk analysis module 12, based on the city's digital twin model, infrastructure risk analysis, traffic risk analysis, and energy risk analysis are performed separately. Specifically, for infrastructure risk analysis, multi-point monitoring data from buildings, bridges, pipelines, power lines, and other locations accessed in the city's digital twin model are used for anomaly detection to identify potential structural damage, equipment failures, and other anomalies. Historical accident data is then combined to perform accident simulations, predicting the occurrence path and impact range of potential risk events. The simulation results are then input into a trained facility risk analysis network for infrastructure risk analysis, generating an infrastructure risk map reflecting the safety status of facilities. For traffic risk analysis, multi-point monitoring data from road traffic flow, vehicle speed, road congestion, traffic signal status, and public transportation operation accessed in the city's digital twin model are used for anomaly detection to identify potential traffic bottlenecks, potential congestion trends, and other anomalies. Historical accident data is then combined to perform accident simulations, predicting the occurrence path and impact range of potential risk events. The simulation results are then input into a trained traffic risk analysis network for traffic risk analysis, generating a traffic risk map reflecting the traffic safety status. In terms of energy risk analysis, multi-point monitoring data, including electricity load, gas consumption, and renewable energy supply, integrated into the city's digital twin model, are used for anomaly detection. This identifies potential energy supply-demand imbalances, equipment overloads, and energy supply interruptions. Historical accident data is then combined to perform accident simulations, predicting the occurrence paths and impact ranges of potential risk events. The simulation results are then input into a trained energy risk analysis network for further analysis, generating an energy risk map reflecting the energy security situation. Finally, the resulting infrastructure risk map, transportation risk map, and energy risk map are integrated. This maps the infrastructure risks, transportation risks, and energy risks of the same area, constructing a final multi-scenario risk map. This multi-scenario risk map not only displays the risk distribution characteristics of each area but also reveals the coupling effects and linkage mechanisms between infrastructure, transportation, and energy risks, providing a comprehensive, intuitive, and dynamic risk support environment for urban operation and maintenance decisions.

[0025] Furthermore, the risk analysis module 12 includes:

[0026] Anomaly detection of facilities at multiple locations is performed based on the city's digital twin model to obtain anomaly detection results for each facility; accident simulation is performed on the anomaly detection results of each facility using the city's digital twin model to obtain accident simulation paths for each facility; a facility risk analysis network is trained based on the city's facility accident risk record set; risk analysis is performed on the accident simulation paths of each facility using the facility risk analysis network to generate the infrastructure risk map.

[0027] Optionally, in the risk analysis module 12, based on historical monitoring data of multiple facilities, the mean and standard deviation of each parameter are calculated. Anomaly marking rules for each parameter are then constructed using the mean plus or minus multiple standard deviations (usually two, which can be set according to actual needs). For example, when calculating the mean and standard deviation of crack propagation rate, the constructed anomaly marking rule is that the value must not deviate from the mean crack propagation rate plus or minus two standard deviations of crack propagation rate. Subsequently, the real-time synchronized infrastructure monitoring data in the city's digital twin model is compared with the corresponding anomaly marking rules. If a monitoring value deviates from the anomaly marking rule for a duration exceeding multiple window periods (usually three), anomaly marking is triggered, and anomaly detection results for each facility are generated. Each facility anomaly detection result includes the facility ID, anomaly index, anomaly occurrence time, and the time period in which the anomaly occurred. Subsequently, for the detected anomalies, the accident simulation function of the city's digital twin model is invoked to simulate the expansion of facility anomalies in the time dimension and their impact in the spatial dimension. Specifically, representative historical cases (such as gas pipeline leaks and bridge structure collapses) are extracted from the facility accident risk record set. For each case, the triggering conditions of the accident (such as pipeline pressure sudden change exceeding 1.2 times the design value, bridge load exceeding the limit and causing resonance) and evolution path (such as gas diffusion path after leakage, failure sequence of key components during collapse) are marked to form a reusable case template. Then, a virtual accident simulation environment is constructed based on the city's digital twin model. The detection results of facility anomalies at multiple points are used as the initial disturbance input model. At the same time, an accident evolution rule base is defined to quantify the risk transmission logic. The rules in the accident evolution rule base can be such as "when pipeline pressure continuously exceeds 1.2 times the design value, the leakage probability increases exponentially with time" and "after the bridge vibration frequency enters the resonance zone, the structural damage rate increases to 3 times the normal state", thus providing rule support for the dynamic simulation of the virtual scene. Then, probability distribution modeling is performed for uncertain parameters in the accident evolution (such as rainfall, traffic load, and material fatigue coefficient) (e.g., rainfall follows a normal distribution, and traffic flow follows a Poisson distribution). The Latin hypercube sampling (LHS) method is used to generate 1000 sets of random scenarios, covering combinations of different environmental conditions and facility states. A parallel simulation engine is then built using a GPU cluster to perform accident evolution in each scenario, calculating accident consequence indicators (such as gas leakage, bridge collapse range, and secondary disaster impact area), and recording the complete accident simulation path, including key nodes (such as the initial leak point and the location of secondary damage) and time series (such as the evolution stages of "leakage occurrence → gas diffusion → triggering surrounding road collapse"). Finally, by integrating the simulation results of multiple scenarios, accident simulation paths for each facility can be generated, providing data support for risk analysis and emergency decision-making.Furthermore, historical accident projection paths, historical accident consequence indicators, and historical anomaly detection results (such as risk level, propagation probability, and main factors) are obtained from the city's facility accident risk record set to construct a facility accident risk record set. This set is then used as training samples to train the facility risk analysis network. This facility risk analysis network can adopt a deep learning structure, such as a graph neural network, a deep neural network, or a long short-term memory network. By inputting the training samples into this deep learning structure, iterative training is performed using steps such as forward propagation, loss calculation (such as the weighted sum of cross-entropy and mean squared error), backpropagation, and parameter optimization (such as the Adam optimizer, with the learning rate initialized to 1e-4 and decaying to 0.9 times the original value every 10 rounds) until the maximum number of iterations is reached or the loss function converges. After training, the network is validated using data not used for training. If the validation results show that the accuracy meets the preset accuracy, the current facility risk analysis network is output. Otherwise, the network structure parameters (such as the number of layers and neurons), activation function type, regularization coefficient, or optimizer hyperparameters (such as learning rate and weight decay) are adjusted, and iterative training is performed again until the validation accuracy meets the preset accuracy. This enables the facility risk analysis network to assess and analyze the risks of complex accident evolution paths. Finally, the accident simulation paths of each facility are input into the trained facility risk analysis network, and the anomaly detection results of each path at different evolution stages are output. The results are presented in a graphical format to generate an infrastructure risk map. This infrastructure risk map not only visually displays the risk distribution of urban infrastructure but also reveals the possible risk transmission relationships between different facilities, thus providing data support and decision-making basis for subsequent operation and maintenance decisions and emergency response.

[0028] The operation and maintenance decision module 13 is used to make operation and maintenance decisions for the city based on the multi-scenario risk map and obtain multi-scenario operation and maintenance space.

[0029] Specifically, in the operation and maintenance decision-making module 13, after constructing a multi-scenario risk map, a comprehensive analysis of the potential risks of urban infrastructure, transportation systems, and energy systems is conducted based on this map to determine the key operation and maintenance needs of various facilities and areas. Regarding infrastructure, by using data from the infrastructure risk portion of the multi-scenario risk map for infrastructure operation and maintenance decisions, multiple operation and maintenance strategies are generated for buildings, bridges, pipelines, etc., such as adjusting inspection frequency, deploying fault prevention measures, and formulating maintenance and reinforcement plans, thus forming an infrastructure operation and maintenance space. In the transportation sector, by using data from the transportation risk portion of the multi-scenario risk map for transportation operation and maintenance decisions, multiple operation and maintenance strategies are generated for congested road sections and accident-prone areas, such as traffic control schemes, signal optimization strategies, and emergency passage schemes, thus forming a transportation operation and maintenance space. In the energy sector, by using data from the energy risk portion of the multi-scenario risk map for energy operation and maintenance decisions, multiple operation and maintenance strategies are generated for abnormal loads and equipment overloads, such as dispatching schemes for electricity, gas, and renewable energy, thus forming an energy operation and maintenance space. Finally, the infrastructure operation and maintenance space, transportation operation and maintenance space, and energy operation and maintenance space are integrated to uniformly represent the city's operation and maintenance strategies, resource allocation, and emergency response plans in various scenarios. This provides a data foundation and decision support for subsequent operation and maintenance evaluation and optimization, enabling the scientific scheduling of urban resources and effective risk control.

[0030] Furthermore, the operation and maintenance decision module 13 includes:

[0031] Infrastructure operation and maintenance decisions are made for the city based on the infrastructure risk map to obtain infrastructure operation and maintenance space; traffic operation and maintenance decisions are made for the city based on the traffic risk map to obtain traffic operation and maintenance space; energy operation and maintenance decisions are made for the city based on the energy risk map to obtain energy operation and maintenance space; the infrastructure operation and maintenance space, the traffic operation and maintenance space, and the energy operation and maintenance space are integrated to generate the multi-scenario operation and maintenance space.

[0032] Preferably, in the operation and maintenance decision module 13, based on the infrastructure risk map in the multi-scenario risk map, the anomaly detection results of each region are obtained. For regions with anomalies, i.e., regions where the anomaly detection results are not empty, all infrastructure operation and maintenance solutions that meet the three requirements are extracted from the infrastructure operation and maintenance strategy rule base according to the risk level, propagation probability, and main factors in the anomaly detection results of that region. These solutions include possible inspection plans, preventive maintenance measures, fault repair strategies, emergency response plans, etc., and these infrastructure operation and maintenance solutions are summarized into an infrastructure operation and maintenance space. The infrastructure operation and maintenance solutions include the operation and maintenance solutions used in the past and the corresponding risk scenarios, as well as the operation and maintenance solutions and corresponding preset risk scenarios pre-set by experts. Similarly, based on the traffic risk map and energy risk map in the multi-scenario risk map, the traffic anomaly detection results and energy anomaly detection results for each region are obtained. Then, based on the traffic anomaly detection results and energy anomaly detection results, all traffic facility operation and maintenance schemes and energy operation and maintenance strategy rule bases that meet the three requirements are extracted from the traffic operation and maintenance strategy rule base and the energy operation and maintenance strategy rule base, respectively. These include possible signal optimization strategies, road control measures, dynamic scheduling schemes, emergency diversion schemes, energy scheduling optimization strategies, backup energy activation schemes, equipment maintenance plans, supply and demand balance adjustment schemes, etc., thereby constructing the traffic operation and maintenance space and the energy operation and maintenance space. Finally, the infrastructure operation and maintenance space, traffic operation and maintenance space, and energy operation and maintenance space are integrated according to their corresponding locations, thereby unifying and associating the operation and maintenance schemes of each scenario to form a complete multi-scenario operation and maintenance space. This multi-scenario operation and maintenance space not only includes the specific content and implementation path of various operation and maintenance schemes, but also reflects the resource coordination and strategy linkage between different scenarios, providing unified decision support and data foundation for subsequent operation and maintenance evaluation, optimization, and risk adaptive management.

[0033] The evaluation and optimization module 14 is used to evaluate and optimize the multi-scenario operation and maintenance space through the multi-scenario assurance analysis model to obtain the multi-scenario operation and maintenance population.

[0034] Specifically, in the evaluation and optimization module 14, after obtaining the multi-scenario operation and maintenance space, the multi-scenario assurance analysis model is activated. This multi-scenario assurance analysis model includes an infrastructure assurance evaluation model, a transportation assurance evaluation model, and an energy assurance evaluation model. Each sub-model corresponds to the operation and maintenance assurance requirements and evaluation indicators for different scenarios. For the infrastructure operation and maintenance space within the multi-scenario operation and maintenance space, simulated operation and maintenance is performed on each operation and maintenance scheme, and simulated data is collected. This simulated data is then input into the infrastructure assurance evaluation model within the multi-scenario assurance analysis model to obtain schemes that meet the infrastructure assurance thresholds and add them to the multi-scenario operation and maintenance population. Similarly, simulated operation and maintenance is performed on each operation and maintenance scheme in the transportation and energy operation and maintenance spaces, and simulated traffic and energy data are collected. The obtained simulated traffic and energy data are then input into the transportation assurance evaluation model and energy assurance evaluation model within the multi-scenario assurance analysis model, respectively, to obtain schemes that meet the transportation and energy assurance thresholds and add them to the multi-scenario operation and maintenance population. The resulting multi-scenario operation and maintenance population will include high-quality operation and maintenance solutions that have been evaluated, screened, and optimized in various scenarios, providing a foundation for subsequent global evolution and optimization to achieve efficient scheduling and risk control of urban resources.

[0035] Furthermore, the evaluation and optimization module 14 includes:

[0036] Activate the infrastructure assurance evaluation model embedded in the multi-scenario assurance analysis model; simulate the operation and maintenance of the city digital twin model according to each infrastructure operation and maintenance plan in the infrastructure operation and maintenance space to obtain multiple facility operation and maintenance simulation data; input the multiple facility operation and maintenance simulation data into the infrastructure assurance evaluation model to obtain an infrastructure assurance evaluation sequence; based on the infrastructure assurance evaluation sequence, optimize and screen the infrastructure operation and maintenance space according to the infrastructure assurance threshold to obtain an infrastructure operation and maintenance population, and add the infrastructure operation and maintenance population to the multi-scenario operation and maintenance population.

[0037] Preferably, in the evaluation and optimization module 14, when evaluating the infrastructure operation and maintenance space, the infrastructure security evaluation model embedded in the multi-scenario security analysis model is first activated. This infrastructure security evaluation model is a pre-trained machine learning model, typically built using a deep neural network. Subsequently, each infrastructure operation and maintenance plan in the infrastructure operation and maintenance space is sequentially input into the city digital twin model. The city digital twin model adjusts accordingly based on each plan and generates operation and maintenance simulation data corresponding to each plan through simulation operation. This simulation data covers dynamic information such as changes in infrastructure operating status, evolution trends of failure probability, maintenance period, and resource consumption. Then, multiple facility operation and maintenance simulation data are sequentially input into the infrastructure security evaluation model. This infrastructure security evaluation model analyzes the received simulation data based on the learned mapping relationship, calculates the infrastructure security evaluation coefficient for each infrastructure operation and maintenance plan, and sorts these infrastructure security evaluation coefficients according to the order of infrastructure operation and maintenance plan simulation to obtain an infrastructure security evaluation sequence. The larger the infrastructure security evaluation coefficient in this sequence, the better the overall performance of the corresponding plan in ensuring the safe operation of urban infrastructure. Then, based on preset infrastructure assurance thresholds, the infrastructure assurance evaluation sequence is optimized and screened. Infrastructure operation and maintenance (O&M) schemes with an evaluation coefficient greater than or equal to the threshold are identified, and schemes that do not meet the requirements are eliminated, ensuring that the screening results meet the minimum assurance needs of urban operation. Finally, all O&M schemes that pass the threshold screening constitute an infrastructure O&M population, which is then added to a multi-scenario O&M population, laying a reliable data and scheme foundation for subsequent global evolutionary optimization.

[0038] Furthermore, the evaluation and optimization module 14 includes:

[0039] The multi-scenario security analysis model includes an infrastructure security evaluation model, a transportation security evaluation model, and an energy security evaluation model.

[0040] Preferably, the multi-scenario assurance analysis model includes an infrastructure assurance evaluation model, a traffic assurance evaluation model, and an energy assurance evaluation model. The infrastructure assurance evaluation model uses infrastructure operation and maintenance simulation data as input, focusing on the operational safety and stability of key facilities such as buildings, bridges, pipelines, and power lines, and generates corresponding infrastructure assurance evaluation coefficients to measure the effectiveness of various infrastructure operation and maintenance schemes in risk control and operational assurance during actual implementation. The traffic assurance evaluation model uses traffic operation and maintenance simulation data as input to understand the impact of different control strategies on complex traffic flows and generates corresponding traffic assurance evaluation coefficients to reflect its comprehensive ability to improve road operation efficiency and reduce risks. The energy assurance evaluation model uses energy operation and maintenance simulation data as input to comprehensively evaluate the quality of energy status and generate corresponding energy assurance evaluation coefficients to measure the effectiveness of various energy operation and maintenance schemes in ensuring secure energy supply and optimizing resource utilization. These three sub-models are all constructed using deep neural networks or multilayer perceptrons, and they have all been trained iteratively using corresponding sample operation and maintenance data and sample guarantee evaluation coefficients through forward propagation, loss calculation (such as mean squared error), back propagation, parameter optimization (such as Adam optimizer), etc. They can comprehensively evaluate and screen different operation and maintenance solutions in multiple scenario operation and maintenance spaces, providing a basis and unified standard for subsequent multi-scenario operation and maintenance population construction and global optimization.

[0041] The global optimization module 15 is used to perform global evolution optimization on the multi-scenario operation and maintenance population according to a predetermined number of evolutions, and to determine the multi-scenario operation and maintenance optimization result.

[0042] Specifically, in the global optimization module 15, the multi-scenario operation and maintenance population undergoes iterative evolution according to a preset number of evolutions and evolution rules. In each round of evolution, the best-performing set of operation and maintenance solutions in the current population is identified through a guarantee evaluation, serving as a guiding factor. Subsequently, this guiding factor is used to optimize other solutions in the population, generating new candidate solutions. These newly generated candidate solutions are then evaluated again using the guarantee evaluation model for each sub-scenario, and the performance of the qualified operation and maintenance evolution group is selected through guarantee threshold screening and winner identification. This evolution and screening process is repeated until the predetermined number of evolutions is completed, yielding the multi-scenario operation and maintenance optimization result. This result serves as the decision-making basis for urban risk adaptive cloud management, thereby enabling the output of a globally optimal operation and maintenance strategy for the city in complex scenarios.

[0043] Furthermore, the global optimization module 15 includes:

[0044] Based on the infrastructure operation and maintenance (O&M) population, a first guiding factor for facility O&M is obtained through performance evaluation. Based on this first guiding factor, the infrastructure O&M population is further optimized using an infrastructure assurance evaluation model to obtain a first O&M evolutionary optimization group. Based on this first O&M evolutionary optimization group, a second guiding factor for facility O&M is obtained through performance evaluation. Based on this second guiding factor, the first O&M evolutionary optimization group is further optimized using the infrastructure assurance evaluation model until multiple O&M evolutionary optimization groups that meet the predetermined number of evolutions are obtained. Finally, a global assurance evaluation optimization is performed based on the infrastructure O&M population and the multiple O&M evolutionary optimization groups to obtain the infrastructure O&M optimization result, which is then added to the multi-scenario O&M optimization result.

[0045] Preferably, in the global optimization module 15, for the infrastructure operation and maintenance population in the multi-scenario operation and maintenance population, the guarantee evaluation superiority identification is performed based on the size of the infrastructure guarantee evaluation coefficient of each operation and maintenance scheme in the infrastructure operation and maintenance population. The operation and maintenance scheme with the largest guarantee evaluation coefficient is extracted as the first guiding factor for facility operation and maintenance. This first guiding factor for facility operation and maintenance represents the optimal facility operation and maintenance scheme at the current stage. Subsequently, based on this first guiding factor for facility operation and maintenance, the infrastructure operation and maintenance population is subjected to evolutionary optimization. In this process, difference comparisons are performed, multiple evolutionary adjustment vectors are generated, and other operation and maintenance schemes in the population are adjusted and mutated according to these evolutionary adjustment vectors, thereby generating new candidate schemes and forming the first operation and maintenance evolutionary optimization population. Then, the guarantee evaluation superiority identification is performed on this first operation and maintenance evolutionary optimization population, and the scheme with the largest guarantee evaluation coefficient is selected as the second guiding factor for facility operation and maintenance. Afterwards, based on the second guiding factor for facility operation and maintenance, the first operation and maintenance evolutionary optimization population continues to undergo differentiated evolution and screening, forming a new evolutionary population again, and repeating the above evolutionary optimization and superiority identification process. Through multiple rounds of iterative evolution until a preset number of evolutions is reached, multiple O&M evolution optimization groups are generated. Finally, the initial infrastructure O&M population is compared with the O&M evolution optimization groups generated in each round of evolution, and the solution with the highest guarantee evaluation coefficient is selected as the global optimal solution, thus determining the infrastructure O&M optimization result. Similar steps are performed for the transportation and energy O&M populations within the multi-scenario O&M population, yielding corresponding transportation and energy O&M optimization results. By adding the infrastructure, transportation, and energy O&M optimization results to the multi-scenario O&M optimization result, it can be ensured that the infrastructure O&M solution not only performs well in local evolution but also achieves global optimization, providing optimal infrastructure guarantee decisions for urban O&M.

[0046] Furthermore, the global optimization module 15 includes:

[0047] Based on the first guiding factor for facility operation and maintenance, the infrastructure operation and maintenance population is subjected to difference detection to obtain multiple operation and maintenance difference vectors; each operation and maintenance difference vector is randomly mutated to obtain multiple sets of evolutionary adjustment vectors; the infrastructure operation and maintenance population is adjusted according to the multiple sets of evolutionary adjustment vectors to obtain a first operation and maintenance evolutionary population; based on the infrastructure assurance threshold, the first operation and maintenance evolutionary population is optimized according to the infrastructure assurance evaluation model to obtain the first operation and maintenance evolution optimization population.

[0048] Optionally, in the global optimization module 15, during evolutionary optimization, the first guiding factor for facility operation and maintenance is used as the baseline scheme. Difference detection is then performed on all other operation and maintenance schemes within the infrastructure operation and maintenance population. By comparing the differences in key parameters such as construction period, material type, cost budget, and construction period among the schemes, multiple operation and maintenance difference vectors are generated. Each difference vector represents the performance difference characteristics between a candidate scheme and the guiding factor. Subsequently, a random mutation operation is performed on each operation and maintenance difference vector, randomly adjusting the magnitude or direction of some difference parameter values ​​to obtain multiple sets of evolutionary adjustment vectors. Based on this set of evolutionary adjustment vectors, the parameters of the original infrastructure operation and maintenance population are corrected and the schemes are adjusted to generate a new group of candidate schemes. This group of candidate schemes is then used as the first operation and maintenance evolutionary group. Subsequently, the city's digital twin model is invoked to model each candidate solution in the first operation and maintenance evolution group one by one, obtain simulation data for each candidate solution, and then activate the infrastructure security evaluation model embedded in the multi-scenario security analysis model. Based on these simulation data, the corresponding infrastructure security evaluation coefficient is calculated, and the solutions are filtered based on the preset infrastructure security threshold. All candidate solutions with security evaluation coefficients greater than or equal to the threshold are extracted to generate a first operation and maintenance evolution optimization group. This first operation and maintenance evolution optimization group consists of high-quality operation and maintenance solutions that have been evolved and verified by the security threshold, providing basic data support for subsequent iterative evolution and global optimization.

[0049] Cloud management module 16 is used to perform risk adaptive cloud management for the city based on the multi-scenario operation and maintenance optimization results.

[0050] Specifically, in cloud management module 16, after obtaining the multi-scenario operation and maintenance optimization results, these results are uploaded to the city-level cloud management platform. These results include the optimal operation and maintenance solutions selected and optimized for multiple scenarios such as infrastructure, transportation, and energy. The cloud management platform uniformly analyzes and distributes these results, mapping the optimal solutions for different scenarios to various functional modules of city operation management. For infrastructure, the cloud management platform issues inspection plans, repair and reinforcement instructions, and emergency response plans to the corresponding facility management subsystems based on the optimization results, achieving dynamic protection of buildings, pipelines, bridges, and other facilities. In the transportation sector, the cloud management platform adjusts traffic light control systems, road control systems, and public transportation dispatch systems in real time based on the traffic operation and maintenance optimization results to ensure smooth traffic flow and minimize accident risks. In the energy sector, the cloud management platform optimizes the allocation of electricity load, gas dispatch, and the utilization of renewable energy based on the energy operation and maintenance optimization results, ensuring energy supply and demand balance and supply security. Through the above process, the city has achieved adaptive risk management in a cloud environment, which not only ensures the optimality and real-time nature of operation and maintenance strategies, but also improves the overall security, resilience and resource utilization efficiency of the city.

[0051] In summary, the city-level digital twin cloud management platform supporting multi-scenario access provided in this application embodiment has the following technical effects:

[0052] The system comprises the following modules: a multi-dimensional modeling module 11, used to perform multi-dimensional modeling based on multi-scenario feature data of the city, and construct a digital twin model of the city; a risk analysis module 12, used to perform multi-scenario risk analysis based on the digital twin model of the city, and construct a multi-scenario risk map; an operation and maintenance decision module 13, used to make operation and maintenance decisions for the city based on the multi-scenario risk map, and obtain a multi-scenario operation and maintenance space; an evaluation and optimization module 14, used to evaluate and optimize the multi-scenario operation and maintenance space through a multi-scenario assurance analysis model, and obtain a multi-scenario operation and maintenance population; a global optimization module 15, used to perform global evolutionary optimization on the multi-scenario operation and maintenance population according to a predetermined number of evolutions, and determine the multi-scenario operation and maintenance optimization result; and a cloud management module 16, used to execute risk adaptive cloud management of the city based on the multi-scenario operation and maintenance optimization result. Through these steps, the system solves the technical problems of difficulty in multi-scenario collaboration in existing digital twin city management, which leads to one-sided and delayed risk analysis and low management efficiency. By constructing a multi-scenario risk map and combining it with an evolutionary optimization algorithm, the system achieves the technical effect of improving city operation and maintenance efficiency and enhancing risk response capabilities.

[0053] Example 2, based on the same inventive concept as the city-level digital twin cloud management platform supporting multi-scenario access in the aforementioned examples, such as... Figure 2As shown in the embodiments of this application, a city-level digital twin cloud management method supporting multi-scenario access is provided, the method comprising:

[0054] A multi-dimensional model is constructed based on multi-scenario characteristic data of the city to build a digital twin model of the city; multi-scenario risk analysis is performed based on the city digital twin model to construct a multi-scenario risk map; operation and maintenance decisions are made for the city based on the multi-scenario risk map to obtain a multi-scenario operation and maintenance space; the multi-scenario operation and maintenance space is evaluated and optimized through a multi-scenario assurance analysis model to obtain a multi-scenario operation and maintenance population; global evolution optimization is performed on the multi-scenario operation and maintenance population according to a predetermined number of evolutions to determine the multi-scenario operation and maintenance optimization result; and risk adaptive cloud management of the city is executed based on the multi-scenario operation and maintenance optimization result.

[0055] Furthermore, the method includes:

[0056] Infrastructure risk analysis is performed based on the city's digital twin model to obtain an infrastructure risk map; traffic risk analysis is performed based on the city's digital twin model to obtain a traffic risk map; energy risk analysis is performed based on the city's digital twin model to obtain an energy risk map; the infrastructure risk map, the traffic risk map, and the energy risk map are integrated to obtain the multi-scenario risk map.

[0057] Furthermore, the method includes:

[0058] Anomaly detection of facilities at multiple locations is performed based on the city's digital twin model to obtain anomaly detection results for each facility; accident simulation is performed on the anomaly detection results of each facility using the city's digital twin model to obtain accident simulation paths for each facility; a facility risk analysis network is trained based on the city's facility accident risk record set; risk analysis is performed on the accident simulation paths of each facility using the facility risk analysis network to generate the infrastructure risk map.

[0059] Furthermore, the method includes:

[0060] Infrastructure operation and maintenance decisions are made for the city based on the infrastructure risk map to obtain infrastructure operation and maintenance space; traffic operation and maintenance decisions are made for the city based on the traffic risk map to obtain traffic operation and maintenance space; energy operation and maintenance decisions are made for the city based on the energy risk map to obtain energy operation and maintenance space; the infrastructure operation and maintenance space, the traffic operation and maintenance space, and the energy operation and maintenance space are integrated to generate the multi-scenario operation and maintenance space.

[0061] Furthermore, the method includes:

[0062] Activate the infrastructure assurance evaluation model embedded in the multi-scenario assurance analysis model; simulate the operation and maintenance of the city digital twin model according to each infrastructure operation and maintenance plan in the infrastructure operation and maintenance space to obtain multiple facility operation and maintenance simulation data; input the multiple facility operation and maintenance simulation data into the infrastructure assurance evaluation model to obtain an infrastructure assurance evaluation sequence; based on the infrastructure assurance evaluation sequence, optimize and screen the infrastructure operation and maintenance space according to the infrastructure assurance threshold to obtain an infrastructure operation and maintenance population, and add the infrastructure operation and maintenance population to the multi-scenario operation and maintenance population.

[0063] Furthermore, the method includes:

[0064] Based on the infrastructure operation and maintenance (O&M) population, a first guiding factor for facility O&M is obtained through performance evaluation. Based on this first guiding factor, the infrastructure O&M population is further optimized using an infrastructure assurance evaluation model to obtain a first O&M evolutionary optimization group. Based on this first O&M evolutionary optimization group, a second guiding factor for facility O&M is obtained through performance evaluation. Based on this second guiding factor, the first O&M evolutionary optimization group is further optimized using the infrastructure assurance evaluation model until multiple O&M evolutionary optimization groups that meet the predetermined number of evolutions are obtained. Finally, a global assurance evaluation optimization is performed based on the infrastructure O&M population and the multiple O&M evolutionary optimization groups to obtain the infrastructure O&M optimization result, which is then added to the multi-scenario O&M optimization result.

[0065] Furthermore, the method includes:

[0066] Based on the first guiding factor for facility operation and maintenance, the infrastructure operation and maintenance population is subjected to difference detection to obtain multiple operation and maintenance difference vectors; each operation and maintenance difference vector is randomly mutated to obtain multiple sets of evolutionary adjustment vectors; the infrastructure operation and maintenance population is adjusted according to the multiple sets of evolutionary adjustment vectors to obtain a first operation and maintenance evolutionary population; based on the infrastructure assurance threshold, the first operation and maintenance evolutionary population is optimized according to the infrastructure assurance evaluation model to obtain the first operation and maintenance evolution optimization population.

[0067] Furthermore, the method includes:

[0068] A multi-scenario monitoring dataset for the city is obtained, which includes infrastructure monitoring data, traffic monitoring data, and energy monitoring data; the multi-scenario monitoring dataset is cleaned to generate multi-scenario feature data.

[0069] Furthermore, the method includes:

[0070] The multi-scenario security analysis model includes an infrastructure security evaluation model, a transportation security evaluation model, and an energy security evaluation model.

[0071] In summary, any step of the method described above can be stored as a computer instruction or program in an unrestricted computer memory, and can be called and identified by an unrestricted computer processor to implement any method in the embodiments of this application, without any additional restrictions.

[0072] Furthermore, the "first" or "second" mentioned above may not only represent a sequential relationship, but may also represent a specific concept, and / or refer to the individual or collective selection of multiple elements. Clearly, those skilled in the art can make various modifications and variations to this application without departing from its scope. Therefore, if such modifications and variations fall within the scope of this application and its equivalents, this application intends to include such modifications and variations.

Claims

1. A city-level digital twin cloud management platform supporting multi-scenario access, characterized in that: The platform includes: The multi-dimensional modeling module is used to perform multi-dimensional modeling based on multi-scene feature data of the city and build a digital twin model of the city. The risk analysis module is used to perform multi-scenario risk analysis based on the city's digital twin model and construct a multi-scenario risk map. The operation and maintenance decision module is used to make operation and maintenance decisions for the city based on the multi-scenario risk map and obtain multi-scenario operation and maintenance space; The evaluation and optimization module is used to evaluate and optimize the multi-scenario operation and maintenance space through the multi-scenario assurance analysis model to obtain the multi-scenario operation and maintenance population. The global optimization module is used to perform global evolutionary optimization on the multi-scenario operation and maintenance population according to a predetermined number of evolutions, and determine the multi-scenario operation and maintenance optimization result. The cloud management module is used to perform risk-adaptive cloud management for the city based on the multi-scenario operation and maintenance optimization results.

2. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The risk analysis module includes: Based on the aforementioned urban digital twin model, infrastructure risk analysis is performed to obtain an infrastructure risk map; Traffic risk analysis is performed based on the aforementioned urban digital twin model to obtain a traffic risk map; Energy risk analysis is performed based on the aforementioned city digital twin model to obtain an energy risk map; By integrating the infrastructure risk map, the transportation risk map, and the energy risk map, the multi-scenario risk map is obtained.

3. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 2, characterized in that, The risk analysis module includes: Based on the aforementioned urban digital twin model, multi-point facility anomaly detection is performed to obtain the anomaly detection results for each facility; The city's digital twin model is used to perform accident simulations based on the anomaly detection results of each facility, thereby obtaining the accident simulation path for each facility. Based on the facility accident risk record set of the city, a facility risk analysis network was trained. The facility risk analysis network is used to analyze the accident simulation paths of each facility and generate the infrastructure risk map.

4. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The operation and maintenance decision module includes: Based on the infrastructure risk map, infrastructure operation and maintenance decisions are made for the city to obtain infrastructure operation and maintenance space; Based on the traffic risk map, traffic operation and maintenance decisions are made for the city to obtain traffic operation and maintenance space; Based on the energy risk map, energy operation and maintenance decisions are made for the city to obtain energy operation and maintenance space; The infrastructure operation and maintenance space, the transportation operation and maintenance space, and the energy operation and maintenance space are integrated to generate the multi-scenario operation and maintenance space.

5. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The evaluation and optimization module includes: Activate the infrastructure assurance evaluation model embedded in the multi-scenario assurance analysis model; The city's digital twin model is simulated for operation and maintenance based on the operation and maintenance plan for each infrastructure within the infrastructure operation and maintenance space, thereby obtaining multiple facility operation and maintenance simulation data. Input the multiple facility operation and maintenance simulation data into the infrastructure assurance evaluation model to obtain the infrastructure assurance evaluation sequence; Based on the infrastructure assurance evaluation sequence, the infrastructure operation and maintenance space is optimized and screened according to the infrastructure assurance threshold to obtain the infrastructure operation and maintenance population, and the infrastructure operation and maintenance population is added to the multi-scenario operation and maintenance population.

6. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The global optimization module includes: Based on the infrastructure operation and maintenance population, the best performers are identified in the assurance evaluation to obtain the first guiding factor for infrastructure operation and maintenance; Based on the first guiding factor for facility operation and maintenance, the infrastructure operation and maintenance population is subjected to evolutionary optimization according to the infrastructure assurance evaluation model to obtain the first operation and maintenance evolutionary optimization population. Based on the first operation and maintenance evolution optimization group, the best performance of the guarantee evaluation is identified, and the second guiding factor for facility operation and maintenance is obtained. Based on the second guiding factor for facility operation and maintenance, the first operation and maintenance evolution optimization group continues to be evolved and optimized according to the infrastructure assurance evaluation model until multiple operation and maintenance evolution optimization groups that satisfy the predetermined number of evolutions are obtained. Based on the infrastructure operation and maintenance population and the multiple operation and maintenance evolution optimization groups, a global optimization of the assurance evaluation is performed to obtain the infrastructure operation and maintenance optimization results, and the infrastructure operation and maintenance optimization results are added to the multi-scenario operation and maintenance optimization results.

7. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 6, characterized in that, The global optimization module includes: Based on the first guiding factor for facility operation and maintenance, a difference detection is performed on the infrastructure operation and maintenance population to obtain multiple operation and maintenance difference vectors; Each operational difference vector is randomly mutated to obtain multiple sets of evolutionary adjustment vectors. The infrastructure operation and maintenance population is adjusted according to the multiple sets of evolutionary adjustment vectors to obtain the first operation and maintenance evolutionary population; Based on the infrastructure assurance threshold, the first operation and maintenance evolution group is optimized by performing assurance evaluation according to the infrastructure assurance evaluation model, thus obtaining the first operation and maintenance evolution optimization group.

8. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The multidimensional modeling module includes: Obtain a multi-scenario monitoring dataset for the city, which includes infrastructure monitoring data, traffic monitoring data, and energy monitoring data; The multi-scene monitoring dataset is cleaned to generate multi-scene feature data.

9. The city-level digital twin cloud management platform supporting multi-scenario access as described in claim 1, characterized in that, The multi-scenario security analysis model includes an infrastructure security evaluation model, a transportation security evaluation model, and an energy security evaluation model.

10. A city-level digital twin cloud management method supporting multi-scenario access, characterized in that: Based on the city-level digital twin cloud management platform supporting multi-scenario access as described in any one of claims 1-9, the method includes: Multi-dimensional modeling is performed based on multi-scenario characteristic data of the city to construct a digital twin model of the city; Based on the aforementioned city digital twin model, multi-scenario risk analysis is performed to construct a multi-scenario risk map; Based on the multi-scenario risk map, the city makes operation and maintenance decisions to obtain multi-scenario operation and maintenance space; The multi-scenario operation and maintenance space is evaluated and optimized through a multi-scenario assurance analysis model to obtain a multi-scenario operation and maintenance population. The multi-scenario operation and maintenance population is globally evolved and optimized according to a predetermined number of evolutions to determine the multi-scenario operation and maintenance optimization result. Based on the multi-scenario operation and maintenance optimization results, the city's risk adaptive cloud management is executed.

Images