Urban mobile pump truck dispatching system research and development method based on digital twinborn technology

Abstract

The invention discloses an urban mobile pump truck dispatching system research and development method based on a digital twinborn technology. According to the method disclosed by the invention, by integrating a third-party navigation system, real-time data acquisition, a multi-target optimal scheduling algorithm and a perfect visual emergency response mechanism, efficient and intelligent scheduling, real-time monitoring and optimal management of the urban mobile pump truck are realized, and accurate scheduling and efficient rescue of the mobile pump truck are realized; dangerous cases such as road ponding and underpass ponding are handled, the efficiency and response speed of urban drainage flood prevention are improved, urban waterlogging disasters are effectively handled, and urban safety is guaranteed.

Description

Technical Field

[0001] The invention relates to an optimization method for an urban mobile pump truck dispatching system based on digital twin technology, and belongs to the technical field of urban drainage and flood control. Background Art

[0002] Urban drainage systems often face the problem of insufficient drainage capacity when facing extreme weather and sudden rainfall, leading to urban waterlogging. Traditional mobile pump truck scheduling methods rely on manual experience and limited information, making it difficult to achieve fast and accurate responses. Digital twin technology provides a virtual, real-time updated city model that can simulate and predict the actual operation of urban drainage systems, but existing technologies have not yet fully utilized digital twin technology for optimized scheduling of mobile pump trucks. Summary of the invention

[0003] The technical problem to be solved by the present invention is that the prior art has not fully utilized the digital twin technology to optimize the scheduling of mobile pump trucks.

[0004] In order to solve the above technical problems, the technical solution of the present invention is to disclose a method for developing a city mobile pump truck dispatching system based on digital twin technology, which is characterized by comprising the following steps:

[0005] Step 1: Sensor network deployment:

[0006] Install sensors and network equipment at key locations in the city to collect real-time information on rainfall, manhole water levels, road water depth, and underpass water depth;

[0007] Each mobile pump truck is equipped with a GPS positioning system and on-board sensors to monitor the location, speed, oil volume, and displacement of the pump truck in real time;

[0008] Step 2: Build a digital twin model:

[0009] Using urban GIS data, construct a three-dimensional model of the urban drainage system, including geographical elements and landscape elements, and create a pump truck model;

[0010] Step 3: Dynamic and static data integration and processing:

[0011] Clean, integrate and analyze the dynamic data collected by the sensor network. Through sensors deployed at key locations in the city, real-time data on rainfall, road waterlogging, and electronic water gauge data at underpasses are collected. The data from the sensor network is uploaded to the server, and the real-time data on the server is transmitted to the front end.

[0012] At the front end, the data in the model is updated in real time through the event monitoring mechanism of Three.js, and the real-time data is visualized. At the same time, the real-time traffic data of the third-party navigation system is obtained through the API interface, and the traffic data of the navigation system is integrated with the model of the urban drainage system established in step 2 to assist in scheduling decisions; the on-board sensor data of the pump truck is integrated to monitor the speed, oil volume, and displacement of the pump truck in real time, and the information is displayed on the model of the urban drainage system;

[0013] Step 4: Model optimization:

[0014] Use Level of Detail technology to dynamically adjust the model's detail level based on the user's viewing distance to improve rendering performance; use compressed textures for digital twin models with low relevance, including city street scenes, and merge multiple similar objects, such as urban building blocks, into one batch for rendering;

[0015] Step 5: Multi-objective optimization scheduling:

[0016] Based on the digital twin model and real-time data, a multi-objective optimization algorithm is developed to generate the optimal scheduling solution. The objective function of the multi-objective optimization problem is defined, which comprehensively considers the response time T, resource utilization U and scheduling cost C. The objective function is as follows:

[0017] Minimizef(T,U,C)=w1T+w2(1-U)+w3C

[0018] Among them, w1, w2, and w3 are weight coefficients, indicating the importance of each target;

[0019] And set the constraints as follows:

[0020] D i ≤D max

[0021] T i ≤T max

[0022] Among them, D i represents the travel distance of the i-th pump truck, D max Indicates the maximum allowable driving distance of the pump truck, T i represents the working time of the i-th pump truck, T max Indicates the maximum permissible working time of the pump truck;

[0023] The system monitors the flood risk of each digital twin area in the city in real time. When waterlogging is detected on roads or underpasses, the system automatically triggers the dispatching program, calculates the objective function based on the static and dynamic data connected to the system, uses non-dominated sorting to screen out a group of non-dominated solutions, performs local search on non-dominated solutions, further optimizes the quality of the solution, and generates specific dispatching instructions based on the multi-objective optimal dispatching solution;

[0024] Step 6: Schedule execution:

[0025] The dispatch instructions are sent to the mobile pump truck through the communication module, guiding the pump truck to go to the designated location to perform drainage operations; the system synchronously receives real-time feedback information from the mobile pump truck, including the current location, working status and operation progress, and dynamically adjusts the dispatch plan based on real-time monitoring data and dispatch execution to meet the real-time needs of urban drainage and flood control.

[0026] Preferably, in step 1, the data collected by the sensor network is transmitted to the server via the MQTT protocol.

[0027] Preferably, in step 2, the geographical elements and landscape elements include drainage networks, pumping stations, rivers, lakes, roads, buildings, and street scenes.

[0028] Preferably, in step 2, THREE.Geometry or THREE.BufferGeometry of Three.js is used to create the geometric shape of the geographic element; THREE.Object3D of Three.js is used to create the pump truck model, and its position is updated through the position attribute.

[0029] Preferably, in step 3, WebSocket or related real-time communication protocols are used to transmit real-time data on the server to the front end.

[0030] Preferably, in step 3, the front end uses materials and shaders of Three.js to visualize the real-time data.

[0031] Preferably, in step 3, THREE.TextGeometry or THREE.Sprite of Three.js is used to display the information of the pump truck on the model.

[0032] Preferably, in step 5, when setting the constraint conditions, it is considered that the pump truck must comply with local traffic regulations.

[0033] Preferably, in step 5, a genetic algorithm or a particle swarm optimization is used to perform local search.

[0034] The method disclosed in the present invention realizes efficient and intelligent scheduling, real-time monitoring and optimized management of urban mobile pump trucks by integrating a third-party navigation system, real-time data collection, a multi-objective optimal scheduling algorithm and a complete visual emergency response mechanism, thereby realizing accurate scheduling and efficient rescue of mobile pump trucks to cope with dangerous situations such as waterlogging on roads and underpasses, improving the efficiency and response speed of urban drainage and flood prevention, effectively coping with urban waterlogging disasters, and ensuring urban safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] Figure 1 It is a schematic diagram of the system workflow in the present invention;

[0036] Figure 2 Construct a flow chart for the digital twin model in the present invention;

[0037] Figure 3 Flowchart of the multi-objective optimization algorithm. DETAILED DESCRIPTION

[0038] The present invention will be further described below in conjunction with specific embodiments. It should be understood that these embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention. In addition, it should be understood that after reading the content taught by the present invention, those skilled in the art can make various changes or modifications to the present invention, and these equivalent forms fall within the scope limited by the appended claims of the application equally.

[0039] A method for developing a city mobile pump truck dispatching system based on digital twin technology disclosed in an embodiment of the present invention involves the following aspects:

[0040] 1. Construction of digital twin model: Based on the urban geographic information system (GIS) and Internet of Things (IoT) technology, a digital twin model of the urban drainage system is constructed. The model can reflect the status of the drainage network in each area of ​​the city, the operation of the pumping station, and environmental parameters such as rainfall in real time. Through real-time data collection and transmission, the data in the digital twin model is ensured to be consistent with the actual operation status of the urban drainage system.

[0041] 2. Data integration: Access to real-time traffic data from third-party navigation systems to provide accurate road traffic information and assist in scheduling decisions. Integrate dynamic monitoring information on road waterlogging, underpass waterlogging, and drainage pipe networks to update relevant data in the digital twin model in real time. Access to the GPS positioning system and on-board sensors of mobile pump trucks to monitor the location, speed, fuel volume, displacement, and other information of mobile pump trucks in real time.

[0042] 3. Multi-objective optimization algorithm: Based on the digital twin model and real-time data, a multi-objective optimization algorithm is developed. The algorithm can comprehensively consider factors such as response time, resource utilization and cost to generate the optimal mobile pump truck scheduling solution. Define the objective function of the multi-objective optimization problem, including minimizing response time, maximizing resource utilization and minimizing scheduling cost. Set reasonable constraints, such as the maximum driving distance, maximum working time and traffic rules of the pump truck.

[0043] 4. Real-time dispatch decision-making: The system monitors the flood risk in various areas of the city in real time. When dangerous situations such as waterlogging on roads and underpasses are detected, the dispatch program is automatically triggered. Based on the multi-objective optimal dispatch plan, specific dispatch instructions are generated, including the number of pump trucks to be dispatched, route planning, and arrival time. The dispatch instructions are sent to the mobile pump truck through the communication module to guide the pump truck to go to the designated location for drainage operations.

[0044] 5. Dynamic adjustment: The system receives feedback from the mobile pump truck in real time, including the current location, working status, and operation progress. Based on the real-time monitoring data and dispatch execution, the dispatch plan is dynamically adjusted to meet the real-time needs of urban drainage and flood control. The dispatch algorithm is continuously optimized to improve the accuracy and efficiency of the dispatch plan.

[0045] Based on the above technical means, the embodiment of the present invention specifically includes the following steps:

[0046] Step 1: Sensor network deployment: Install sensor networks at key locations in the city to collect real-time information such as rainfall, groundwater level, road water depth, and underpass water depth; equip each mobile pump truck with a GPS positioning system and on-board sensors to monitor the location, speed, fuel volume, displacement, and other information of the pump truck in real time. The data will be transmitted to the server via the MQTT protocol.

[0047] Step 2: Build a digital twin model: Use urban geographic information system (GIS) data to build a 3D model of the urban drainage system, including drainage pipe networks, pumping stations, rivers, lakes, roads, buildings, streetscapes and other geographical and landscape elements. Use Three.js's THREE.Geometry or THREE.BufferGeometry to create the geometric shapes of these geographical elements. Use Three.js's THREE.Object3D to create a pump truck model and update its position through the position property.

[0048] Step 3, integration and processing of dynamic and static data: Clean, integrate and analyze the collected dynamic data. Through sensors deployed at key locations in the city, real-time data such as rainfall, water level sensors, and electronic water gauges at underpasses are collected. The data is transmitted to the server using the MQTT protocol, and the real-time data on the server is transmitted to the front end using WebSocket or related real-time communication protocols. The data in the model is updated in real time through the event monitoring mechanism of Three.js on the front end. The real-time data is visualized using the materials and shaders of Three.js, such as changing the color of the drainage network and urban road sections to indicate the water accumulation in different areas. Real-time traffic data from a third-party navigation system is obtained through the API interface, and the traffic data of the navigation system is integrated with the model of the urban drainage system to assist in scheduling decisions. The on-board sensor data of the pump truck is integrated to monitor the speed, fuel volume, displacement and other information of the pump truck in real time, and the information is displayed on the model using THREE.TextGeometry or THREE.Sprite of Three.js.

[0049] Step 4, model optimization: Use Level of Detail (LOD) technology to dynamically adjust the model's detail level according to the user's viewing distance to improve rendering performance. For example, a lower-precision model can be used for a drainage network in the distance. Use compressed textures (DDS or ETC format textures) for digital twin models with low relevance, such as urban street scenes, to reduce memory usage and loading time, such as using DDS or ETC format textures. At the same time, merge multiple similar objects such as urban building blocks into a batch for rendering, reduce the number of draw calls, and improve rendering efficiency.

[0050] Step 5: Multi-objective optimization scheduling: Based on the digital twin model and real-time data, develop a multi-objective optimization algorithm to generate the optimal scheduling solution. Define the objective function of the multi-objective optimization problem, which comprehensively considers the response time (the time from the issuance of the scheduling command to the arrival of the pump truck at the destination) T, resource utilization (i.e. the efficiency of the pump truck) U and scheduling cost (including fuel costs, labor costs, etc.) C. The objective function is as follows:

[0051] Minimizef(T,U,C)=w1T+w2(1-U)+w3C

[0052] Among them, w1, w2, and w3 are weight coefficients, indicating the importance of each target.

[0053] In order to ensure that the generated scheduling plan is reasonable and feasible, the constraints are set as follows:

[0054] D i ≤D max

[0055] Ti ≤T max

[0056] Among them, D i represents the travel distance of the i-th pump truck, D max Indicates the maximum allowable driving distance of the pump truck, T i represents the working time of the i-th pump truck, T max Indicates the maximum allowable working time of the pump truck.

[0057] In addition, pump trucks must comply with local traffic regulations, including but not limited to speed limits, prohibited passage, etc.

[0058] When the system monitors the flood risk of each digital twin area in the city in real time, when dangerous situations such as waterlogging on roads and underpasses are detected, the dispatch program is automatically triggered, and the objective function is calculated based on the static and dynamic data connected to the system, and a group of non-dominated solutions (Pareto optimal solutions) are screened out using non-dominated sorting (such as NSGA-II algorithm), and non-dominated solutions are searched locally to further optimize the quality of the solution. Genetic algorithms, particle swarm optimization and other methods can be used for local search, and specific dispatch instructions are generated based on the multi-objective optimal dispatch plan, including the number of pump trucks to be dispatched, path planning and arrival time.

[0059] Step 6, Dispatch Execution: The dispatch instruction is sent to the mobile pump truck through the communication module to guide the pump truck to go to the designated location for drainage operations. The system synchronously receives feedback information from the mobile pump truck in real time, including the current location, working status and operation progress, etc. Based on the real-time monitoring data and dispatch execution, the dispatch plan is dynamically adjusted to meet the real-time needs of urban drainage and flood control.

Claims

1. A method for developing a city mobile pump truck dispatching system based on digital twin technology, characterized in that: The following steps are involved: Step 1: Sensor network deployment: Install sensors and network equipment at key locations in the city to collect real-time information on rainfall, manhole water levels, road water depth, and underpass water depth; Each mobile pump truck is equipped with a GPS positioning system and on-board sensors to monitor the location, speed, oil volume, and displacement of the pump truck in real time; Step 2: Build a digital twin model: Using urban GIS data, construct a three-dimensional model of the urban drainage system, including geographical elements and landscape elements, and create a pump truck model; Step 3: Dynamic and static data integration and processing: Clean, integrate and analyze the dynamic data collected by the sensor network. Through sensors deployed at key locations in the city, real-time data on rainfall, road waterlogging, and electronic water gauge data at underpasses are collected. The data from the sensor network is uploaded to the server, and the real-time data on the server is transmitted to the front end. At the front end, the data in the model is updated in real time through the event monitoring mechanism of Three.js, and the real-time data is visualized. At the same time, the real-time traffic data of the third-party navigation system is obtained through the API interface, and the traffic data of the navigation system is integrated with the model of the urban drainage system established in step 2 to assist in scheduling decisions; the on-board sensor data of the pump truck is integrated to monitor the speed, oil volume, and displacement of the pump truck in real time, and the information is displayed on the model of the urban drainage system; Step 4: Model optimization: Use Level of Detail technology to dynamically adjust the model's detail level based on the user's viewing distance to improve rendering performance; use compressed textures for digital twin models with low relevance, including city street scenes, and merge multiple similar objects, such as urban building blocks, into one batch for rendering; Step 5: Multi-objective optimization scheduling: Based on the digital twin model and real-time data, a multi-objective optimization algorithm is developed to generate the optimal scheduling solution. The objective function of the multi-objective optimization problem is defined, which comprehensively considers the response time T, resource utilization U and scheduling cost C. The objective function is as follows: Minimizef(T,U,C)=w1T+w2(1-U)+w3C Among them, w1, w2, and w3 are weight coefficients, indicating the importance of each target; And set the constraints as follows: D i ≤D max T i ≤T max Among them, D i represents the travel distance of the i-th pump truck, D max Indicates the maximum allowable driving distance of the pump truck, T i represents the working time of the i-th pump truck, T max Indicates the maximum permissible working time of the pump truck; The system monitors the flood risk of each digital twin area in the city in real time. When waterlogging is detected on roads or underpasses, the system automatically triggers the dispatching program, calculates the objective function based on the static and dynamic data connected to the system, uses non-dominated sorting to screen out a group of non-dominated solutions, performs local search on non-dominated solutions, further optimizes the quality of the solution, and generates specific dispatching instructions based on the multi-objective optimal dispatching solution; Step 6: Schedule execution: The dispatch instructions are sent to the mobile pump truck through the communication module, guiding the pump truck to go to the designated location to perform drainage operations; the system synchronously receives real-time feedback information from the mobile pump truck, including the current location, working status and operation progress, and dynamically adjusts the dispatch plan based on real-time monitoring data and dispatch execution to meet the real-time needs of urban drainage and flood control.

2. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 1, the data collected by the sensor network is transmitted to the server via the MQTT protocol.

3. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 2, the geographical elements and landscape elements include drainage networks, pumping stations, rivers, lakes, roads, buildings, and street scenes.

4. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 2, THREE.Geometry or THREE.BufferGeometry of Three.js is used to create the geometric shape of the geographic element; THREE.Object3D of Three.js is used to create the pump truck model, and its position is updated through the position attribute.

5. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 3, WebSocket or related real-time communication protocols are used to transmit real-time data on the server to the front end.

6. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 3, the front end uses Three.js materials and shaders to visualize the real-time data.

7. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 3, use THREE.TextGeometry or THREE.Sprite of Three.js to display the pump truck information on the model.

8. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 5, when setting constraints, consider that the pump truck must comply with local traffic regulations.

9. The method for developing a city mobile pump truck dispatching system based on digital twin technology according to claim 1, characterized in that: In step 5, a local search is performed using a genetic algorithm or a particle swarm optimization.

Images