CN-121978910-A - Method and system for ventilating in tunnel by combining piston wind with renewable energy sources

CN121978910ACN 121978910 ACN121978910 ACN 121978910ACN-121978910-A

Abstract

The invention discloses a method and a system for collaborative energy supply and ventilation of piston wind and renewable energy sources in a tunnel, which comprise the following steps of S1, system initialization and multi-source data acquisition and fusion, S2, calculating tunnel ventilation requirements in a future time window through a prediction model based on acquired data, S3, dispatching energy sources according to a power distribution priority order with the aim of meeting the ventilation requirements, generating an initial control strategy comprising fan operation parameters and an electric energy dispatching scheme, S4, executing the initial control strategy and monitoring actual ventilation effects in the tunnel in real time, S5-S7, carrying out multistage evaluation and decision feedback, updating decisions until the actual ventilation effects reach standards, S8, data archiving and model updating, storing the final successful strategy and related data in a database in the control period, and updating and optimizing the prediction model. The intelligent energy allocation method for tunnel ventilation is used for realizing intelligent energy allocation for tunnel ventilation, improving the utilization rate of green energy, establishing a multi-stage decision feedback mechanism and improving control precision.

Inventors

YAO YI
XING HONGZHEN
ZHANG ZHIQIANG
LIU ZIMING
ZHANG KANGJIAN
GUO JIANBO
Shu Weiyu
GUO SHIRONG
YIN CHAO
LIU MIN

Assignees

中铁二十二局集团有限公司
西南交通大学

Dates

Publication Date: 20260505
Application Date: 20251226

Claims (10)

1. A method for cooperatively supplying energy and ventilating by piston wind and renewable energy sources in a tunnel is characterized by comprising the following steps: s1, system initialization and multi-source data acquisition and fusion, namely synchronously acquiring environment data, traffic flow data and energy state data in a tunnel; s2, ventilation demand prediction, namely calculating tunnel ventilation demand in a future time window through a prediction model based on the data acquired in the step S1; s3, generating a multi-target optimization control strategy, namely allocating energy according to the priority sequence of piston wind energy > hole solar energy and wind energy > energy storage > mains supply in a tunnel with the aim of meeting the ventilation requirement, and generating an initial control strategy comprising fan operation parameters and an electric energy allocation scheme; s4, strategy execution and real-time monitoring, wherein the initial control strategy is executed, and the actual ventilation effect in the tunnel is monitored in real time; S5, effect evaluation and decision are carried out, whether the actual ventilation effect reaches a preset standard is judged, if yes, step S8 is executed, and if not, step S6 is executed; s6, primary parameter adjustment, namely, carrying out primary optimization adjustment on key parameters in an initial control strategy within a preset adjustment range; S7, secondary evaluation and decision are carried out, whether the actual ventilation effect after primary parameter adjustment meets the standard is judged again, if the actual ventilation effect meets the standard, the step S8 is executed, and if the actual ventilation effect does not meet the standard, the step S7a is executed; s7a, strategy reconstruction, namely triggering data re-acquisition and demand re-prediction, regenerating a control strategy based on updated data and a prediction result, and then executing a step S7b; s7b, three-level evaluation and decision are carried out, whether the actual ventilation effect after strategy reconstruction meets the standard is judged, if the actual ventilation effect meets the standard, the step S8 is skipped, and if the actual ventilation effect does not meet the standard, the step S7c is carried out; S7c, three-level emergency adjustment, namely enabling an expert system based on a case library to make a decision, acquiring an emergency control strategy, and jumping to the step S8; and S8, data archiving and model updating, wherein the finally successful strategy and related data in the control period are stored in a database and are used for updating and optimizing the prediction model.
2. The method for ventilating in cooperation with piston wind and renewable energy sources in tunnels according to claim 1, wherein in step S1, the environmental data comprise CO concentration, NO x concentration and visibility, the traffic flow data comprise traffic flow and average speed, and the energy source state data comprise piston wind power generation, photovoltaic power generation and energy storage SOC values.
3. The method for ventilating by combining piston wind and renewable energy sources in a tunnel according to claim 1, wherein the predictive model is a double-layer LSTM predictive model trained based on historical environment data and traffic flow data.
4. The method for ventilating by combining piston wind and renewable energy sources in a tunnel according to claim 1, wherein in step S3, the fan operation parameters comprise fan rotation speed, start-stop states and operation numbers, and the electric energy allocation scheme is a power supply proportion of different energy sources.
5. The method for co-energizing ventilation of pistonic wind and renewable energy sources in tunnels according to claim 1, wherein said key parameters comprise core adjustment items in fan operating parameters and power distribution coefficients in power distribution schemes, and said preset adjustment ranges are determined based on tunnel ventilation design criteria and equipment operating limits.
6. The collaborative energy supply ventilation system for the piston wind and the renewable energy sources in the tunnel is characterized by comprising a distributed sensing module, an intelligent decision module, an executor module and a collaborative energy supply module, wherein the distributed sensing module is used for collecting tunnel environment parameters, traffic flow parameters, and power generation states and energy storage states of the renewable energy sources in real time, the intelligent decision module is used for executing a decision process, the executor module is used for executing ventilation control instructions sent by the intelligent decision module, and the collaborative energy supply module is used for supplying power to the executor module according to preset priorities.
7. The in-tunnel pistonic wind and renewable energy CO-powered ventilation system of claim 6, wherein the distributed sensing module comprises an environmental sensing unit comprising a CO concentration sensor, a NOx concentration sensor, a visibility meter, and an ultrasonic anemometer, a traffic sensing unit comprising a microwave car detector and video identification subunit, and an energy monitoring unit comprising a power sensor and a battery management subunit.
8. The in-tunnel pistonic wind and renewable energy co-powered ventilation system of claim 6, wherein the intelligent decision module comprises: The demand prediction unit is in communication connection with the distributed sensing module and is used for calculating tunnel ventilation demands in a future time window through a prediction model; The strategy generation unit is in communication connection with the demand prediction unit and is used for allocating energy according to the priority sequence of piston wind energy > hole solar energy and wind energy > energy storage > mains supply in the tunnel to generate an initial control strategy; The execution monitoring unit is in communication connection with the strategy generation unit and is used for executing an initial control strategy and monitoring the actual ventilation effect in the tunnel in real time; The evaluation and adjustment unit is in communication connection with the execution monitoring unit and is used for judging whether the actual ventilation effect reaches the standard or not, and primary parameter adjustment, strategy reconstruction or three-level emergency adjustment are sequentially executed; And the data archiving and model updating unit is in communication connection with the evaluation adjusting unit and is used for storing the final success strategy and related data and updating the optimized prediction model.
9. The in-tunnel pistonic wind and renewable energy co-powered ventilation system of claim 6, wherein the actuator module comprises a variable frequency speed fan cluster and an intelligent damper array.
10. The tunnel piston wind and renewable energy co-energy supply ventilation system according to claim 6, wherein the co-energy supply module comprises an in-tunnel piston wind power generation unit, a tunnel portal renewable energy unit, an energy storage system and a smart micro-grid manager, the in-tunnel piston wind power generation unit comprises a miniature vertical axis wind power generator set deployed in a tunnel, the tunnel portal renewable energy unit comprises a monocrystalline silicon solar photovoltaic panel arranged on a side slope of a tunnel portal and a horizontal axis wind power generator installed in an open area of the tunnel portal, and the in-tunnel piston wind power generation unit, the tunnel portal renewable energy unit and the energy storage system are electrically connected, and the smart micro-grid manager is used for executing an electric energy allocation scheme.

Description

Method and system for ventilating in tunnel by combining piston wind with renewable energy sources Technical Field The invention relates to the technical field of tunnel engineering, in particular to a method and a system for ventilating by cooperative energy supply of piston wind and renewable energy sources in a tunnel. Background The tunnel ventilation system is a key facility for guaranteeing the air quality in the tunnel and controlling smoke during fire. At present, tunnel operation ventilation mainly depends on a high-power fan powered by a municipal power grid, and the traditional mode has two outstanding disadvantages that firstly, the fan is a high-energy-consumption user, high electricity cost and a large amount of indirect carbon emission can be generated when the fan continuously operates and is not suitable for an environment-friendly strategy, and secondly, the traditional ventilation control strategy is based on a fixed time table or a simple concentration threshold value, lacks foresight, easily causes excessive ventilation or insufficient ventilation, wastes energy and possibly endangers driving safety. Notably, the piston effect is generated when trains or vehicles in the tunnel pass at high speed, and strong piston wind is formed. The part of wind energy is huge in reserves, but the kinetic energy is not effectively captured and utilized for a long time, and the kinetic energy is naturally discharged only through the wind tower, so that the energy is a huge energy waste. Therefore, an innovative technical scheme is urgently needed in the field, and the current passive energy-consuming ventilation system is converted into an energy-saving, low-carbon and intelligent integrated high-efficiency system which can actively capture and utilize renewable energy sources such as piston wind and realize fine operation through intelligent prediction. Disclosure of Invention The invention aims to solve the problems of huge energy consumption, single energy structure, extensive control strategy, lack of self-adaptive capacity and the like of a tunnel ventilation system, and provides a tunnel ventilation method and system by utilizing the cooperation of piston wind and renewable energy. In order to achieve the technical purpose, the invention adopts the following technical scheme: a method for ventilating a tunnel by cooperating energy supply of piston wind and renewable energy sources comprises the following steps: s1, system initialization and multi-source data acquisition and fusion, namely synchronously acquiring environment data, traffic flow data and energy state data in a tunnel; s2, ventilation demand prediction, namely calculating tunnel ventilation demand in a future time window through a prediction model based on the data acquired in the step S1; s3, generating a multi-target optimization control strategy, namely allocating energy according to the priority sequence of piston wind energy > hole solar energy and wind energy > energy storage > mains supply in a tunnel with the aim of meeting the ventilation requirement, and generating an initial control strategy comprising fan operation parameters and an electric energy allocation scheme; s4, strategy execution and real-time monitoring, wherein the initial control strategy is executed, and the actual ventilation effect in the tunnel is monitored in real time; S5, effect evaluation and decision are carried out, whether the actual ventilation effect reaches a preset standard is judged, if yes, step S8 is executed, and if not, step S6 is executed; s6, primary parameter adjustment, namely, carrying out primary optimization adjustment on key parameters in an initial control strategy within a preset adjustment range; S7, secondary evaluation and decision are carried out, whether the actual ventilation effect after primary parameter adjustment meets the standard is judged again, if the actual ventilation effect meets the standard, the step S8 is executed, and if the actual ventilation effect does not meet the standard, the step S7a is executed; s7a, strategy reconstruction, namely triggering data re-acquisition and demand re-prediction, regenerating a control strategy based on updated data and a prediction result, and then executing a step S7b; s7b, three-level evaluation and decision are carried out, whether the actual ventilation effect after strategy reconstruction meets the standard is judged, if the actual ventilation effect meets the standard, the step S8 is skipped, and if the actual ventilation effect does not meet the standard, the step S7c is carried out; S7c, three-level emergency adjustment, namely enabling an expert system based on a case library to make a decision, acquiring an emergency control strategy, and jumping to the step S8; and S8, data archiving and model updating, wherein the finally successful strategy and related data in the control period are stored in a database and are used for updating and optimizing the prediction model