CN-121998259-A - Intelligent city pipe network overflow emergency supervision Internet of things large model system and method

CN121998259ACN 121998259 ACN121998259 ACN 121998259ACN-121998259-A

Abstract

The invention provides a large model system and a method for intelligent city pipe network overflow emergency supervision Internet of things, which relate to the field of gas pipeline supervision, wherein the method comprises the steps of acquiring pipe network monitoring data based on a sensor deployed in a drainage pipe network through an emergency supervision object platform; the method comprises the steps of monitoring data of a pipe network and future weather data, generating overflow prediction data through a prediction model, responding to the overflow prediction data to meet overflow conditions, generating overflow control parameters based on the overflow prediction data, wherein the overflow control parameters comprise at least one of a intercepting well parameter, a pump station parameter and a regulation facility parameter, the pump station parameter comprises the running power and the extraction direction of a target water pump, and sending the overflow control parameters to an emergency supervision object platform and controlling the working parameters of overflow emergency equipment. The method realizes reasonable water quantity scheduling, reduces the frequency and influence of overflow occurrence, and improves the management level of the urban drainage pipe network.

Inventors

Shao Hanshu
Zhou Qiayan
Ru rui

Assignees

成都秦川物联网科技股份有限公司

Dates

Publication Date: 20260508
Application Date: 20260407

Claims (10)

1. A smart city pipe network overflow emergency supervision internet of things large model system, characterized in that the system comprises an emergency supervision management platform configured to: Acquiring pipe network monitoring data based on sensors deployed in a drainage pipe network through an emergency supervision object platform; generating overflow estimated data through a prediction model based on the pipe network monitoring data and future weather data; generating overflow control parameters based on the overflow prediction data in response to the overflow prediction data meeting overflow conditions, wherein the overflow control parameters include at least one of a vatch basin parameter, a pump station parameter, and a storage facility parameter, the pump station parameter including an operating power and a pumping direction of a target water pump, and Sending the overflow control parameters to the emergency supervision object platform and controlling working parameters of overflow emergency equipment, wherein the overflow control parameters comprise: Controlling the opening degree of a gate based on the parameter of the intercepting well, wherein the gate is deployed at an overflow port of the intercepting well; based on the pump station parameters, controlling the target water pump to operate in the corresponding extraction direction and the operation power; controlling to open a target pipeline valve to discharge the water pumped by the target water pump to a water discharge area, and And controlling the opening of a water inlet valve and the opening of a water outlet valve of the regulation facility based on the regulation facility parameters, wherein the regulation facility is connected with the water draining pipe network.
2. The system of claim 1, wherein the predictive model comprises a hydrologic simulation model and a hydrologic map model, the hydrologic simulation model being a physical model, the hydrologic map model being a neural network model; the emergency administration management platform is further configured to: Determining the duration to be predicted; Determining a prediction model type based on the duration to be predicted; constructing an urban pipe network map based on the structural data of the drainage pipe network, the pipe network monitoring data and the future weather data in response to the determined prediction model type being the hydrological map model, and And generating the overflow estimated data based on the urban pipe network map by using the hydrological map model.
3. The system of claim 2, wherein the emergency supervisory management platform is further configured to: acquiring future weather features based on the future weather data; Determining pipe network state characteristics based on the pipe network monitoring data and the structural data of the drainage pipe network; Determining model calling parameters based on the future weather characteristics, the pipe network state characteristics and the duration to be predicted, wherein the model calling parameters comprise calling time and the corresponding prediction model type, and And determining the type of the prediction model based on the model calling parameters.
4. The system of claim 1, wherein the emergency supervisory management platform is further configured to: determining candidate control parameters based on the overflow estimate data, and Performing an iterative process based on the candidate control parameters and the predictive model, the iterative process comprising: Inputting the candidate control parameters of the current round into the prediction model to generate comprehensive risk cost corresponding to the candidate control parameters of the current round, wherein the comprehensive risk cost is determined based on the predicted overflow quantity of the overflow port, the environmental risk weight and the equipment running cost output by the prediction model; Acquiring updated candidate control parameters as candidate control parameters for the next iteration based on the current round of candidate control parameters and the comprehensive risk cost in response to not meeting the stop condition, and In response to a stop condition being met, stopping iteration and determining the overflow control parameter based on the run candidate control parameter.
5. The system of claim 4, wherein the sensor further comprises a water quality sensor for acquiring water quality sensing data; the emergency administration management platform is further configured to: determining the pollutant concentration of the overflow port through a water quality prediction algorithm based on the water quality sensing data and the predicted overflow quantity, and The integrated risk cost is determined based on the contaminant concentration.
6. A smart city pipe network overflow emergency supervision method, wherein the method is performed by an emergency supervision management platform, the method comprising: Acquiring pipe network monitoring data based on sensors deployed in a drainage pipe network through an emergency supervision object platform; generating overflow estimated data through a prediction model based on the pipe network monitoring data and future weather data; generating overflow control parameters based on the overflow prediction data in response to the overflow prediction data meeting overflow conditions, wherein the overflow control parameters include at least one of a vatch basin parameter, a pump station parameter, and a storage facility parameter, the pump station parameter including an operating power and a pumping direction of a target water pump, and Sending the overflow control parameters to the emergency supervision object platform and controlling working parameters of overflow emergency equipment, wherein the overflow control parameters comprise: Controlling the opening degree of a gate based on the parameter of the intercepting well, wherein the gate is deployed at an overflow port of the intercepting well; based on the pump station parameters, controlling the target water pump to operate in the corresponding extraction direction and the operation power; controlling to open a target pipeline valve to discharge the water pumped by the target water pump to a water discharge area, and And controlling the opening of a water inlet valve and the opening of a water outlet valve of the regulation facility based on the regulation facility parameters, wherein the regulation facility is connected with the water draining pipe network.
7. The method of claim 6, wherein the predictive model comprises a hydrologic simulation model and a hydrologic map model, the hydrologic simulation model being a physical model, the hydrologic map model being a neural network model; Based on the pipe network monitoring data and future weather data, generating overflow estimated data through a prediction model comprises: Determining the duration to be predicted; Determining a prediction model type based on the duration to be predicted; constructing an urban pipe network map based on the structural data of the drainage pipe network, the pipe network monitoring data and the future weather data in response to the determined prediction model type being the hydrological map model, and And generating the overflow estimated data based on the urban pipe network map by using the hydrological map model.
8. The method of claim 7, wherein the determining a prediction model type based on the duration to be predicted comprises: acquiring future weather features based on the future weather data; Determining pipe network state characteristics based on the pipe network monitoring data and the structural data of the drainage pipe network; Determining model calling parameters based on the future weather characteristics, the pipe network state characteristics and the duration to be predicted, wherein the model calling parameters comprise calling time and the corresponding prediction model type, and And determining the type of the prediction model based on the model calling parameters.
9. The method of claim 6, wherein generating overflow control parameters based on the overflow prediction data comprises: determining candidate control parameters based on the overflow estimate data, and Performing an iterative process based on the candidate control parameters and the predictive model, the iterative process comprising: Inputting the candidate control parameters of the current round into the prediction model to generate comprehensive risk cost corresponding to the candidate control parameters of the current round, wherein the comprehensive risk cost is determined based on the predicted overflow quantity of the overflow port, the environmental risk weight and the equipment running cost output by the prediction model; Acquiring updated candidate control parameters as candidate control parameters for the next iteration based on the current round of candidate control parameters and the comprehensive risk cost in response to not meeting the stop condition, and In response to a stop condition being met, stopping iteration and determining the overflow control parameter based on the run candidate control parameter.
10. The method of claim 9, wherein the sensor further comprises a water quality sensor for acquiring water quality sensing data; The method further comprises the steps of: determining the pollutant concentration of the overflow port through a water quality prediction algorithm based on the water quality sensing data and the predicted overflow quantity, and The integrated risk cost is determined based on the contaminant concentration.

Description

Intelligent city pipe network overflow emergency supervision Internet of things large model system and method Technical Field The invention belongs to the field of gas pipeline supervision, and particularly relates to a large model system and method for intelligent city pipe network overflow emergency supervision Internet of things. Background In some urban areas, the drainage system adopts a confluence system, namely domestic sewage and rainwater are converged into the same pipeline. On sunny days, the system can normally convey sewage to a sewage treatment plant for treatment. However, during stormwater, a large amount of stormwater is gushed into the pipe network, resulting in a total water volume that far exceeds the design throughput of existing pipelines and sewage treatment plants. In order to prevent urban inland inundation and sewage backflow, a combined drainage system is generally provided with overflow ports at a intercepting well or the like, and rainwater and sewage mixed water exceeding the treatment capacity is allowed to be directly discharged into receiving water bodies such as nearby rivers, lakes and the like, and the phenomenon is called combined overflow (Combined Sewer Overflow, CSO). CSO events can present serious environmental problems. The overflowed rain and sewage mixed water is untreated and contains a large amount of suspended matters, organic pollutants, heavy metals and pathogenic microorganisms, and serious pollution and threat are caused to the quality of the receiving water body, the water ecological system and public health. How to accurately predict the occurrence time and the overflow total amount of CSO events and realize the fine and active control of overflow emergency equipment in a drainage pipe network so as to reduce the overflow amount and the environmental pollution risk is a key technical problem to be solved in the current smart city construction and water environment management field. Disclosure of Invention The intelligent city pipe network overflow emergency supervision Internet of things large model system comprises an emergency supervision object platform, wherein the emergency supervision object platform is used for acquiring pipe network monitoring data based on sensors deployed in a drainage pipe network, generating overflow estimated data based on the pipe network monitoring data and future weather data through a prediction model, responding to the overflow estimated data to meet overflow conditions, generating overflow control parameters based on the overflow estimated data, wherein the overflow control parameters comprise at least one of a intercepting well parameter, a pump station parameter and a regulating facility parameter, the pump station parameter comprises the operation power and the extraction direction of a target water pump, the overflow control parameters are sent to the emergency supervision object platform, and the working parameters of overflow emergency equipment are controlled, wherein the method comprises the steps of controlling the opening of a gate, the gate is deployed at an overflow port of a intercepting well based on the intercepting well parameter, controlling the target water pump to operate in the corresponding extraction direction and the operation power based on the pump station parameter, controlling to open a target pipeline valve, discharging the target water pump to a regulating facility area based on the pump opening of the intercepting well parameter, and the regulating facility controlling the opening of the water pump to be connected with the regulating facility. The intelligent city pipe network overflow emergency supervision method comprises the steps of obtaining pipe network monitoring data through an emergency supervision object platform based on sensors deployed in a drainage pipe network, generating overflow estimated data through a prediction model based on the pipe network monitoring data and future weather data, generating overflow control parameters based on the overflow estimated data in response to the overflow estimated data meeting overflow conditions, wherein the overflow control parameters comprise at least one of a intercepting well parameter, a pump station parameter and a regulation facility parameter, the pump station parameter comprises operation power and extraction direction of a target water pump, sending the overflow control parameters to the emergency supervision object platform and controlling working parameters of overflow emergency equipment, wherein the method comprises the steps of controlling opening of a gate, the gate is deployed at an overflow port of the intercepting well based on the intercepting well parameter, controlling the target water pump to operate with the corresponding extraction direction and the operation power based on the pump station parameter, controlling a target pipeline valve to be opened, discharging water extracted by the target water pump to a drainag