Smart city monitoring system based on digital twinning

Abstract

The invention discloses a smart city monitoring system based on digital twinning. The smart city monitoring system comprises a sensing module, an edge gateway, an Internet of Things platform and a local large model. The sensing module comprises a sensor module, a data acquisition system and a peripheral thermal insulation material; the edge gateway comprises an industrial computer and a communication module; the microcomputer can communicate with the data acquisition box to obtain the environment temperature and the water temperature, and the ice layer thickness is obtained by establishing a mathematical model; the Internet of Things platform performs bidirectional interaction with the edge gateway through an MQTT protocol, is integrated with a data visualization module, can display the pipeline icing process in a three-dimensional manner, and dynamically displays the thickness of an ice layer; and the local large model can perform bidirectional data interaction with the Internet of Things platform to obtain pipeline physical parameters, environment temperature, ice layer thickness and pipeline pressure, so that prediction of the stress state of the pipeline is realized, and finally intelligent operation and maintenance of the urban pipe network are realized.

Description

Technical Field

[0001] The present invention relates to the field of edge computing, and in particular to a smart city monitoring system based on digital twins. Background Art

[0002] With the rapid development of smart cities, social operation efficiency has been greatly improved, but the problem of pipe network icing in winter is still an important challenge. Pipe network icing not only affects the normal operation of urban infrastructure, but also poses a serious threat to the quality of life of residents and the sustainable development of the city. At present, manual inspections are generally used to obtain pipeline icing data, which has the disadvantages of low accuracy and poor timeliness. With the advancement of technology, the field of pipeline network monitoring actively integrates modern technologies such as edge computing, the Internet of Things and artificial intelligence to ensure the normal operation of water supply and drainage systems in low temperature environments and reduce accidents and damage caused by pipe network icing.

[0003] In severe cold conditions, the water in the pipe network gradually freezes and expands in volume, causing the pressure in the pipe to increase rapidly, which may eventually cause the pipe to rupture. At the same time, the structural damage caused by ice will gradually accumulate, and the durability of the pipe will decrease after multiple freeze-thaw cycles, increasing the difficulty and cost of maintenance. Therefore, it is particularly important to monitor and evaluate the freezing status of the pipe in real time, detect hidden dangers early to prevent rupture accidents, and ensure the safety and stability of the winter water supply system.

[0004] At present, there are some technologies related to pipeline icing status monitoring on the market. For example, Chinese patent CN202410556234.8 discloses an intelligent processing system and method for monitoring icing of factory water intake pipelines in extremely cold winter, including an experimental monitoring mechanism and a water intake pipeline monitoring mechanism. The system obtains the icing status of the pipeline through a temperature sensor and a flow sensor. Specifically, after the pipeline is frozen, the inner diameter of the pipeline becomes smaller. When the water flow is reduced by half, a maintenance signal is sent to the pipeline network operation and maintenance personnel. This solution adopts the "after-the-fact maintenance" approach, that is, emergency repairs are carried out after the pipeline is blocked or damaged, which has obvious disadvantages, specifically: 1. Poor accuracy: The flow rate is related to factors such as the pipeline diameter, pipeline network layout and water pressure. It is difficult to predict information such as the thickness of the ice layer and the risk of pipeline rupture by the magnitude of the flow drop; 2. Poor timeliness: Pipeline freezing in low temperature environments is often difficult to be detected by the naked eye in the early stages, and potential hidden dangers may be ignored. By the time the pipeline ruptures or the pressure increases abnormally, repairs are usually carried out, which usually has caused certain losses; 3. Poor convenience: The repair process may cause water supply interruptions, causing inconvenience to residents' lives; 4. High cost: This solution cannot effectively obtain process data on pipeline freezing. When pipeline freezing causes flow changes, post-maintenance generally requires higher costs.

[0005] Therefore, in order to reduce the risk of urban pipeline freezing in winter, we have developed a smart city monitoring system based on digital twins. Combining advanced sensing technology and intelligent algorithms, we can obtain the evolution trends of ambient temperature, pipeline water temperature and water pressure in real time, and then build a mathematical model to predict the dynamic process of pipeline freezing. Finally, we use the Internet of Things technology to realize data collection, permanent storage and visualization. Summary of the invention

[0006] In view of the above problems, the present invention provides a smart city monitoring system based on digital twins, which combines sensor technology, edge computing and intelligent algorithms to obtain the dynamic process of pipeline icing in real time, and finally realizes data collection, permanent storage and visual display through Internet of Things technology. It is characterized by comprising: a perception module, an edge gateway, an Internet of Things platform and a local large model:

[0007] The perception module includes a sensor module, a data acquisition system and peripheral insulation materials; the sensor module includes an ambient temperature sensor, a water temperature sensor and a water pressure sensor; the data acquisition system includes a weak signal conditioning circuit, an acquisition circuit, a power module, a low-power main control and a communication module; the data acquisition module can obtain ambient temperature and water temperature data at regular intervals; the perception module can receive a read instruction sent by the edge gateway and obtain the real-time pressure of the pipeline through the water pressure sensor; the peripheral insulation material wraps the sensor module and the data acquisition module to reduce the rate of heat loss, delay the freezing process of the sensor, and improve the accuracy of water temperature and water pressure acquisition;

[0008] The edge gateway includes an industrial computer and a communication module; the industrial computer can communicate with the sensing module to obtain the ambient temperature and water temperature , a mathematical model is established to quantify the freezing process of the pipeline. The specific steps are:

[0009] S1: Heat exchange between pipeline and environment: When the ambient temperature is , water temperature is When the heat exchange rate between the pipeline and the environment is It is expressed as:

[0010]

[0011] in, is the convective heat transfer coefficient between the environment and the pipe; is the heat exchange area, is the ambient temperature, is the water temperature in the pipe;

[0012] S2: Water temperature acquisition: Before the water reaches the freezing point, the water temperature continues to decrease, and the energy of heat exchange With real-time water temperature The relationship between them is:

[0013]

[0014] in, is the density of water, is the specific heat of water, is the volume of water held by the pipe, is the initial water temperature;

[0015] S3: Ice thickness prediction: When the water temperature reaches the freezing point, the water begins to undergo phase change. According to the heat balance required for phase change, we know that:

[0016]

[0017] in, is the density of water, is the latent heat of solidification of water, is the duration of freezing. is the volume of the ice layer, specifically:

[0018]

[0019] in, is the inner diameter of the pipe, is the thickness of the ice layer. Due to the ice-water mixture state, is the length of the pipe; the above equation can be simplified to:

[0020]

[0021] The IoT platform interacts bidirectionally with the edge gateway through the MQTT protocol, and can not only issue instructions and read real-time data from the water pressure sensor, but also receive ice thickness uploaded by the edge gateway; the IoT platform is integrated with a data visualization module, and dynamically interacts with users through a large data screen; the large data screen can display the freezing process of the pipeline in a three-dimensional way;

[0022] The local large model can perform two-way data interaction with the Internet of Things platform, obtain the pipeline physical parameters, ambient temperature, ice thickness and pipeline pressure uploaded by the Internet of Things platform, judge the safety of the pipeline, and ultimately realize intelligent operation and maintenance of the pipeline.

[0023] The advantages of the present invention are:

[0024] 1. Intelligence: The present invention combines intelligent sensing, edge computing and intelligent algorithms to obtain the dynamic process of pipeline icing in real time, and finally realizes data collection, permanent storage and visual display through Internet of Things technology. The system can replace manual inspections by operation and maintenance masters in cold winter.

[0025] 2. Advance perception: Compared with post-maintenance technology, this solution adopts a pre-maintenance solution, which effectively avoids water supply interruptions caused by "problem maintenance" and improves the convenience of water use for residents.

[0026] 3. System integration: The IoT platform provides a data interface that can connect pipe network icing data with the cloud platform, providing a good foundation for smart cities. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] The drawings described herein are used to provide a further understanding of the embodiments of the present invention, constitute a part of the present invention, and do not constitute a limitation of the embodiments of the present invention.

[0028] Figure 1 : A framework for smart city monitoring system based on digital twin.

[0029] Figure 2 : Schematic diagram of pipe freezing.

[0030] Figure 3 :Functional module of Internet of Things platform.

[0031] Figure 4 : A deployment instance of a local large model.

[0032] Figure 5 :Evaluation results of pipeline network safety by large model. DETAILED DESCRIPTION

[0033] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with embodiments and drawings. The exemplary embodiments of the present invention and their description are only used to explain the present invention and are not intended to limit the present invention.

[0034] Implementation Example 1

[0035] Attached Figure 1 A smart city monitoring system based on digital twins is demonstrated. It combines sensor technology, edge computing and intelligent algorithms to obtain the dynamic process of pipeline icing in real time. Finally, the data is collected, permanently stored and visualized through the Internet of Things technology. It is characterized by: perception module, edge gateway, Internet of Things platform and local large model:

[0036] The perception module includes a sensor module, a data acquisition system and peripheral insulation materials; the sensor module includes an ambient temperature sensor, a water temperature sensor and a water pressure sensor; the data acquisition system includes a weak signal conditioning circuit, an acquisition circuit, a power module, a low-power main control and a communication module; the data acquisition module can obtain ambient temperature and water temperature data at regular intervals; the perception module can receive a read instruction sent by the edge gateway and obtain the real-time pressure of the pipeline through the water pressure sensor; the peripheral insulation material wraps the sensor module and the data acquisition module to reduce the rate of heat loss, delay the freezing process of the sensor, and improve the accuracy of water temperature and water pressure acquisition;

[0037] The edge gateway includes an industrial computer and a communication module; the industrial computer can communicate with the sensing module to obtain the ambient temperature and water temperature , a mathematical model is established to quantify the freezing process of the pipeline. The specific steps are:

[0038] S1: Heat exchange between pipeline and environment: When the ambient temperature is , water temperature is When the heat exchange rate between the pipeline and the environment is It is expressed as:

[0039]

[0040] in, is the convective heat transfer coefficient between the environment and the pipe; is the heat exchange area, is the ambient temperature, is the water temperature in the pipe;

[0041] S2: Water temperature acquisition: Before the water reaches the freezing point, the water temperature continues to decrease, and the energy of heat exchange With real-time water temperature The relationship between them is:

[0042]

[0043] in, is the density of water, is the specific heat of water, is the volume of water held by the pipe, is the initial water temperature;

[0044] S3: Ice thickness prediction: When the water temperature reaches the freezing point, the water begins to undergo phase change. According to the heat balance required for phase change, we know that:

[0045]

[0046] in, is the density of water, is the latent heat of solidification of water, is the duration of freezing. is the volume of the ice layer, specifically:

[0047]

[0048] in, is the inner diameter of the pipe, is the thickness of the ice layer. Due to the ice-water mixture state, is the length of the pipe; the above equation can be simplified to:

[0049]

[0050] The IoT platform interacts bidirectionally with the edge gateway through the MQTT protocol, and can not only issue instructions and read real-time data from the water pressure sensor, but also receive ice thickness uploaded by the edge gateway; the IoT platform is integrated with a data visualization module, and dynamically interacts with users through a large data screen; the large data screen can display the freezing process of the pipeline in a three-dimensional way;

[0051] The local large model can perform two-way data interaction with the Internet of Things platform, obtain the pipeline physical parameters, ambient temperature, ice thickness and pipeline pressure uploaded by the Internet of Things platform, judge the safety of the pipeline, and ultimately realize intelligent operation and maintenance of the pipeline.

[0052] Implementation Example 2

[0053] This example demonstrates the freezing process of pipelines through a specific implementation case, as shown below:

[0054] Attached Figure 2 Schematic diagram showing pipe icing, where the pipe diameter ;

[0055] Pipe length: ;

[0056] Initial water temperature: ℃;

[0057] Ambient temperature: ℃;

[0058] Convective heat transfer coefficient: Temperature: ;

[0059] Density of water: ;

[0060] Specific heat capacity of water: ;

[0061] Latent heat of solidification of water: ;

[0062] According to the algorithm provided in the first implementation example, the cooling and freezing process of the water in the pipeline is obtained, specifically:

[0063] S1: Calculate the time it takes for the water temperature to drop to freezing point : Since the energy of heat exchange between the pipeline and the environment is used to reduce the water temperature in the pipeline, its amplitude is equal, so for a short time:

[0064]

[0065] Integrating both sides, we know:

[0066]

[0067] Right now:

[0068]

[0069] S2: Calculate the thickness of the ice layer: Ice thickness for:

[0070]

[0071] When the ambient temperature remains stable, the thickness of the ice layer after 10 minutes is:

[0072]

[0073]

[0074] Implementation Example 3

[0075] Attached Figure 3 The functional modules of the IoT platform are demonstrated. The IoT platform is the foundation for building smart factories and deploying artificial intelligence algorithms. The project combines years of engineering implementation experience and can meet the needs of industrial robots, smart factories, aerospace, and electric energy. The IoT platform interacts with the edge gateway in a two-way manner through the MQTT protocol; it can not only issue instructions and read real-time data from the water pressure sensor, but also receive ice thickness uploaded by the edge gateway; the IoT platform is integrated with a data visualization module, and dynamically interacts with users through a large data screen; the large data screen can display the process of pipeline freezing in three dimensions.

[0076] The left side of the IoT platform is the navigation bar, which includes the following functional modules:

[0077] 1. Data screen: Dynamically present the official website icing data through three-dimensional visualization;

[0078] 2. Equipment management: products, equipment, and groups;

[0079] 3. Operation and maintenance monitoring: OTA upgrade, remote configuration, online debugging, and log service;

[0080] 4. System management: user management, role management, menu list, interface management, and log management.

[0081] The IoT platform in the smart city monitoring system uses efficient caching technology. By making rational use of memory and Redis, a hierarchical system of in-service cache and cross-service cache is constructed, which significantly reduces the frequency of database access and improves system performance. In this architecture, the in-service cache reads data from memory and Redis first, and only accesses the database when the cache misses; while the cross-service cache synchronizes data through RPC calls to ensure data consistency and fast access between multiple services. This solution effectively supports the real-time and high-efficiency requirements of smart city pipe network monitoring.

[0082] Cache loading adopts a lazy loading strategy, that is, when the cache data is updated, only the deletion operation is performed without updating the cache immediately, thereby reducing resource consumption. Since the memory cache is used, the update may cause the memory data of other services to be inconsistent with the actual data. Therefore, the system notifies each service through the message queue, and clears the memory cache after receiving the update notification to maintain consistency. In the case of short-term unavailability caused by network failure, some services may not receive the update notification, resulting in inconsistency between the cache and the actual data. At this time, you need to wait for the memory cache to expire automatically, and then obtain new data from the data source to achieve eventual consistency. Specifically:

[0083] func (c *Cache[dataT, keyType]) SetData(ctx context.Context, keykeyType, data *dataT) error {

[0084] cacheKey := c.genCacheKey(key)

[0085] if data != nil { / / If it is

[0086] dataStr, err := json.Marshal(data)

[0087] if err != nil {

[0088] logx.WithContext(ctx).Error(err)

[0089] return err

[0090] }

[0091] err = store.SetexCtx(ctx, cacheKey, string(dataStr), int(c.expireTime / time.Second))

[0092] if err != nil {

[0093] logx.WithContext(ctx).Error(err)

[0094] }

[0095] } else {

[0096] _, err := store.Del(cacheKey)

[0097] if err != nil {

[0098] logx.WithContext(ctx).Error(err)

[0099] }}

[0100] c.cache.Delete(cacheKey)

[0101] if c.fastEvent != nil { / / Publish cache update message

[0102] err := c.fastEvent.Publish(ctx, c.genTopic(), cacheKey)

[0103] if err != nil {

[0104] logx.WithContext(ctx).Error(err)

[0105] }}

[0106] return nil

[0107] }

[0108] Implementation Example 4

[0109] The local large model can perform two-way data interaction with the Internet of Things platform, obtain the pipeline physical parameters, ambient temperature, ice thickness and pipeline pressure uploaded by the Internet of Things platform, judge the safety of the pipeline, and ultimately realize intelligent operation and maintenance of the pipeline.

[0110] Figure 4 The deployment example of the local large model is shown. In recent years, artificial intelligence technology has achieved rapid development. AI large models have gradually become one of the core technologies in various industries, and have broad application potential in natural language processing, time series data processing, and medical fields. The deployment process of AI large models is as follows:

[0111] S1: Dataset construction: Establish a pipeline safety assessment dataset, including pipeline physical parameters, ambient temperature, ice thickness and pipeline pressure. Establish data labels through manual annotation, specifically: [

[0113] {"timestamp": 1694515200, "temperature": -5, "ice_thickness": 3, "water_temperature": 2, "internal_pressure": 1.2 , "material": "steel", "thickness": 5, "radius": 0.02, "safety_rating": "danger"},

[0114] {"timestamp": 1694518800, "temperature": -2, "ice_thickness": 1.5, "water_temperature": 3, "internal_pressure": 1.0, "material": "steel", "thickness": 5, "radius": 0.02, "safety_rating": "caution"}, ...... ]

[0117] S2: Model fine-tuning: fine-tune the AI ​​large model based on PEFT and perform quantitative operations;

[0118] S3: Local AI large model deployment: Install LM Studio software locally to load the model;

[0119] S4: Parameter adjustment and API service of AI big model: adjust the batch size, GPU load and Temperature parameters, and open the API to integrate the local AI big model and the IoT platform. The reference code for the IoT platform to call the AI ​​big model is:

[0120] S5: Safety assessment: Evaluate the pipeline network through a large model. The specific prompts used are:

[0121] Please analyze the pipeline safety status using the provided pressure and ice layer data. Apply the Kalman filter to smooth the pressure readingsand assess the risk of pipeline deformation or rupture. The analysis shouldinclude processed pressure values ​​and ice layer thickness trends over time,highlighting any significant increases that may compromise pipelineintegrity. actions, such as inspection, ice removal, or system shutdown, to address any detected risks.

[0122] S6: Result output: The output of the large model is passed to the IoT platform to realize intelligent operation and maintenance of the pipeline. The specific format is as follows Figure 5 shown.

[0123] The specific implementation method described above provides a detailed description of the objectives, technical solutions and beneficial effects of the present invention. It should be understood that the above is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A smart city monitoring system based on digital twins, combining sensor technology, edge computing and intelligent algorithms, obtains the dynamic process of pipeline icing in real time, and finally realizes data collection, permanent storage and visual display through Internet of Things technology, characterized by: Includes: perception module, edge gateway, IoT platform and local large model: The perception module includes a sensor module, a data acquisition system and peripheral insulation materials; the sensor module includes an ambient temperature sensor, a water temperature sensor and a water pressure sensor; the data acquisition system includes a weak signal conditioning circuit, an acquisition circuit, a power module, a low-power main control and a communication module; the data acquisition module can obtain ambient temperature and water temperature data at regular intervals; the perception module can receive a read instruction sent by the edge gateway and obtain the real-time pressure of the pipeline through the water pressure sensor; the peripheral insulation material wraps the sensor module and the data acquisition module to reduce the rate of heat loss, delay the freezing process of the sensor, and improve the accuracy of water temperature and water pressure acquisition; The edge gateway includes an industrial computer and a communication module; the industrial computer can communicate with the sensing module to obtain the ambient temperature and water temperature , a mathematical model is established to quantify the freezing process of the pipeline. The specific steps are: S1: Heat exchange between pipeline and environment: When the ambient temperature is , water temperature is When the heat exchange rate between the pipeline and the environment is It is expressed as: in, is the convective heat transfer coefficient between the environment and the pipe; is the heat exchange area, is the ambient temperature, is the water temperature in the pipe; S2: Water temperature acquisition: Before the water reaches the freezing point, the water temperature continues to decrease, and the energy of heat exchange With real-time water temperature The relationship between them is: in, is the density of water, is the specific heat of water, is the volume of water held by the pipe, is the initial water temperature; S3: Ice thickness prediction: When the water temperature reaches the freezing point, the water begins to undergo phase change. According to the heat balance required for phase change, we know that: in, is the density of water, is the latent heat of solidification of water, is the duration of freezing. is the volume of the ice layer, specifically: in, is the inner diameter of the pipe, is the thickness of the ice layer. Due to the ice-water mixture state, is the length of the pipe; the above equation can be simplified to: The IoT platform interacts bidirectionally with the edge gateway through the MQTT protocol, and can not only issue instructions and read real-time data from the water pressure sensor, but also receive ice thickness uploaded by the edge gateway; the IoT platform is integrated with a data visualization module, and dynamically interacts with users through a large data screen; the large data screen can display the freezing process of the pipeline in a three-dimensional way; The local large model can perform two-way data interaction with the Internet of Things platform, obtain the pipeline physical parameters, ambient temperature, ice thickness and pipeline pressure uploaded by the Internet of Things platform, judge the safety of the pipeline, and ultimately realize intelligent operation and maintenance of the pipeline.

Images