Fan frequency conversion energy-saving regulation and control method and system facing tunnel environment

Abstract

The invention relates to the technical field of fan frequency conversion regulation and control, in particular to a fan frequency conversion energy-saving regulation and control method and system for a tunnel environment, and the method comprises a multi-parameter sensing module which is arranged in a tunnel, and the signal output end of the multi-parameter sensing module is connected to the input end of a data preprocessing and storage module. The system has the advantages that through the system consisting of the multi-parameter sensing module, the data preprocessing and storage module, the ventilation demand dynamic calculation module and the energy-saving optimization decision module, the current required air volume can be dynamically calculated based on traffic parameters and environmental parameters which change in real time in the tunnel; and the optimal energy consumption target operation frequency matched with the current required air volume is inquired according to the stored fan characteristic curve, and the rotating speed of the fan is continuously and accurately adjusted through the frequency conversion control module. According to the technical scheme, the situation that the draught fan still operates at high power in the low-demand time period is avoided, the cubic relation between the shaft power and the rotating speed of the draught fan is directly utilized, and energy consumption minimization on the premise that the ventilation demand is met is achieved.

Description

Technical Field

[0001] This invention relates to the field of variable frequency control technology for wind turbines, and in particular to a method and system for variable frequency energy-saving control of wind turbines for tunnel environments. Background Technology

[0002] Tunnel ventilation systems are critical facilities for ensuring safe tunnel operation. However, traditional systems are typically designed based on maximum ventilation demand and generally employ fixed-speed operation or simple gear adjustment modes. This results in high energy consumption, where the fans are underutilized in most actual operating conditions. Although variable frequency drive (VFD) technology has been introduced, which can adjust the fan speed by changing the motor power supply frequency, thereby achieving continuous airflow regulation and offering advantages such as soft start and reduced current surges, most existing control strategies still remain at the macroscopic system level or rely on limited sensor thresholds for passive responses. They lack core control algorithms capable of accurately matching the dynamic changes in tunnel requirements, thus failing to fully realize energy-saving potential.

[0003] Existing system designs, due to fan selection based on maximum ventilation demand and control strategies that are mostly static or semi-static, cannot dynamically and continuously optimize based on real-time changes in environmental parameters within the tunnel, such as CO concentration, dust content, and traffic conditions, such as vehicle flow and vehicle type ratio. Tunnel ventilation demand is a dynamic variable influenced by multiple factors, including traffic flow and weather conditions. Fixed speed or limited speed adjustments cannot respond precisely, resulting in fans operating at high power during periods of low demand, leading to significant energy waste. Furthermore, fan shaft power is proportional to the cube of the speed; even a slight reduction in speed can result in significant energy savings. Static control strategies cannot effectively utilize this principle to minimize energy consumption.

[0004] Secondly, current systems suffer from slow dynamic response and insufficient intelligent control capabilities. This is mainly manifested in the system's one-sided perception capabilities, typically relying only on limited sensors such as CO and VI; lagging control methods, often resorting to remedial measures after exceeding limits; and a lack of comprehensive monitoring and predictive control capabilities for multiple parameters, such as various harmful gases, temperature, humidity, and wind speed. An ideal intelligent control system should be able to predict short-term traffic flow and environmental change trends based on historical and real-time data, achieving proactive control. However, most existing technologies lack this capability. Parameter settings often rely on manual intervention, making it difficult to adapt to changes in different seasons, time periods, and weather conditions. The system lacks self-learning and self-optimization mechanisms, and in the event of equipment failure, it lacks effective fault diagnosis and fault-tolerant control capabilities, making it difficult to achieve a dynamic and precise balance between safety and energy conservation. Summary of the Invention

[0005] The purpose of this invention is to overcome the shortcomings of the prior art and provide a method and system for frequency conversion energy-saving control of fans in tunnel environments, which effectively solves the deficiencies of the prior art.

[0006] The objective of this invention is achieved through the following technical solution: a variable frequency energy-saving control system for fans in tunnel environments, comprising: A multi-parameter sensing module is installed inside the tunnel, and its signal output is connected to the input of the data preprocessing and storage module. The data preprocessing and storage module processes the received sensor data, and its output is connected to the input of the ventilation demand dynamic calculation module and the ventilation demand prediction module. The ventilation demand dynamic calculation module calculates the current air volume requirement based on real-time data, and its output is connected to the first input of the energy-saving optimization decision module. The ventilation demand forecasting module predicts future air volume based on historical data, and its output is connected to the second input of the energy-saving optimization decision module. An energy-saving optimization decision module, the output of which is connected to the input of a frequency converter control module, is equipped with a memory for storing fan characteristic curves and optimization algorithms. The variable frequency control module has its control signal output terminal connected to the frequency converter of the ventilation fan inside the tunnel; The wind turbine group coordinated control module has its signal input / output terminals connected to the frequency conversion control module and the controller of each wind turbine, respectively. The fault diagnosis and fault-tolerant control module has its signal acquisition terminal connected to the status monitoring points of each module in the system, and its control signal output terminal connected to the wind turbine group collaborative control module and the alarm emergency module. The human-computer interaction module has its data interface bidirectionally connected to the data preprocessing and storage module and the energy-saving optimization decision module; The alarm emergency module has its trigger signal input terminal connected to the alarm signal output terminal of the fault diagnosis and fault-tolerant control module and the multi-parameter sensing module.

[0007] Preferably, in any of the above schemes, the multi-parameter sensing module includes multiple sensor arrays distributed along the tunnel length direction, and the communication bus of each sensor array is connected to the centralized data interface of the data preprocessing and storage module.

[0008] Preferably, in any of the above schemes, the ventilation demand prediction module includes a processor and a memory storing a trained long short-term memory network model, wherein the data access port of the processor is connected to the time-series database of the data preprocessing and storage module.

[0009] Preferably, in any of the above schemes, the fan characteristic curve stored in the memory of the energy-saving optimization decision module includes a mapping table of fan speed, air volume and power consumption, and the processor of the energy-saving optimization decision module is configured to perform query and optimization calculations based on the mapping table and the input required air volume.

[0010] Preferably, in any of the above schemes, the wind turbine group collaborative control module is equipped with a logic control unit, which is programmed with collaborative control logic for controlling the sequential start-up and shutdown and speed ratio of multiple wind turbines.

[0011] Preferably, in any of the above schemes, the fault diagnosis and fault-tolerant control module includes a comparator circuit and a redundant control logic circuit. When the comparator circuit detects abnormal wind turbine operating parameters, it triggers the redundant control logic circuit to take over the control of the wind turbine.

[0012] Preferably, in any of the above schemes, the system further includes a remote monitoring platform, the communication unit of which establishes a bidirectional communication link with the data transmission interface of the data preprocessing and storage module through a data network.

[0013] The objective of this invention is also achieved through the following technical solution: a frequency conversion energy-saving control method for fans in tunnel environments, used in the above-mentioned system, comprising the following steps: S1: Collect environmental and traffic parameters through a sensor array deployed inside the tunnel; S2: Standardize the collected parameters and store them in the time series database; S3: Based on the parameters processed in real time, the current real-time ventilation volume required for the tunnel is calculated; S4: Based on historical time series data, the predicted ventilation volume for future periods is obtained through a prediction model; S5: Combine real-time ventilation volume and predicted ventilation volume, query fan characteristic curves, and calculate the target operating frequency of the fan or fan group; S6: Generates a variable frequency control signal based on the target operating frequency, adjusts the fan speed, and monitors changes in environmental parameters to form a closed-loop control.

[0014] Preferably, in step S5, the calculation of the target operating frequency specifically includes: taking the larger value between the real-time ventilation volume and the predicted ventilation volume as the decision air volume, and determining the target frequency point with the lowest energy consumption based on the correspondence between air volume and frequency in the fan characteristic curve.

[0015] Preferably, in step S6, the closed-loop control includes: comparing the actual values ​​of key environmental parameters monitored after adjusting the fan speed with preset safety thresholds, and dynamically adjusting the target operating frequency based on the comparison results.

[0016] The present invention has the following advantages: 1. This method and system for frequency conversion energy-saving control of ventilation fans in tunnel environments, comprised of a multi-parameter sensing module, a data preprocessing and storage module, a dynamic ventilation demand calculation module, and an energy-saving optimization decision-making module, dynamically calculates the current air volume requirement based on real-time changes in traffic and environmental parameters within the tunnel. It then queries the stored fan characteristic curves to find the optimal target operating frequency that matches the current air volume requirement, and continuously and precisely adjusts the fan speed via the frequency conversion control module. This technical solution avoids the fan operating at high power during periods of low demand, directly utilizing the cubic relationship between fan shaft power and speed, thus minimizing energy consumption while meeting ventilation requirements.

[0017] 2. This variable frequency energy-saving control method and system for ventilation fans in tunnel environments predicts future air volume demand based on historical time-series data through a ventilation demand prediction module. Combined with a fault diagnosis and fault-tolerant control module, the system monitors the system status in real time, enabling the system to adjust the fan operation status in advance based on the predicted air volume demand. When a single fan failure is detected, the ventilation task is automatically redistributed through redundant control logic. This technical solution transforms the control mode from passive remediation after exceeding the limit to proactive predictive control, and has fault-tolerant operation capability in case of failure, thereby maintaining the safety and stability of the ventilation system under changing tunnel conditions. Attached Figure Description

[0018] Figure 1 This is a schematic diagram of the system framework of the present invention; Figure 2 This is a schematic diagram of the method flow of the present invention. Detailed Implementation

[0019] The present invention will be further described below with reference to the accompanying drawings, but the scope of protection of the present invention is not limited to the following description.

[0020] like Figure 1 As shown, a variable frequency energy-saving control system for fans in tunnel environments includes: A multi-parameter sensing module is responsible for real-time acquisition of raw environmental and traffic data within the tunnel. In practice, sensor arrays are deployed at the tunnel entrance, middle, and exit. The following specific models are used for environmental data acquisition: an ES-DCO infrared CO sensor with a detection range of 0-300ppm; an HFX-100 visibility sensor for smoke concentration; and a PMS7003 laser dust sensor for dust concentration. Traffic data acquisition utilizes a DS-2CD6321FWD-V2 license plate recognition camera, in conjunction with an inductive loop detector, to count traffic flow and identify large vehicles, small vehicles, and new energy vehicles. All sensor signals are collected at the data acquisition station via an RS485 bus, using the Modbus RTU communication protocol. The sensors are powered by a 24V DC power supply and equipped with surge protectors.

[0021] The data preprocessing and storage module receives raw data from the sensor module and performs cleaning, fusion, and storage. Specifically, its hardware core uses an ARK-2121L industrial PC equipped with an Intel Core i5-10500H processor and 8GB DDR4 memory. The data preprocessing software runs on Ubuntu 20.04LTS, utilizing a data cleaning algorithm written in Python 3.9 to perform Kalman filtering on anomalous data and timestamp alignment and spatial registration on multi-source data. The processed data is categorized by data type: real-time data is stored in a high-speed cache composed of solid-state drives for fast access; historical time-series data is stored in a persistent storage array composed of multiple hard disk drives to ensure data security. The database management system uses MySQL 8.0, which writes cached data to persistent storage in batches every 5 minutes.

[0022] The ventilation demand dynamic calculation module calculates the current required ventilation volume based on real-time data. This module is deployed as software on the aforementioned Advantech industrial computer, and its air volume calculation model strictly adheres to the "Specifications for Ventilation Design of Highway Tunnels" (JTG / TD70 / 2-02-2014). During the calculation, fuel-powered vehicles and new energy vehicles are treated differently: the CO and smoke emission factors for fuel-powered vehicles are taken from Appendix B of the specifications; the CO and smoke emissions for new energy vehicles are counted as zero. This module performs the calculation every 30 seconds, outputting the total air volume currently required for the tunnel.

[0023] The ventilation demand prediction module forecasts future ventilation needs. Specifically, it uses a Long Short-Term Memory (LSTM) network prediction model built on Python's TensorFlow 2.9 framework. The model's input includes historical traffic flow, vehicle type ratios, CO concentration, and wind speed data from the past two hours, and its output is the predicted air volume required for the next 30 minutes. The model is trained using historical data from the existing tunnel over the past year, with 70% as the training set, 15% as the validation set, and 15% as the test set. After training, the model is integrated into the system, initiating a prediction every 5 minutes. The prediction results, along with real-time results from the dynamic calculation module, are then fed into the decision-making module.

[0024] The energy-saving optimization decision module is the core of the system, responsible for formulating the optimal energy-saving operation plan. Its hardware and data processing modules share the same industrial control computer. Internally, the module stores a complete characteristic curve dataset for each selected fan model, containing the mapping relationship between airflow, air pressure, and shaft power at different speeds. The optimization algorithm of this module executes once per minute, and its process is as follows: First, it compares the real-time airflow demand provided by the ventilation demand dynamic calculation module with the predicted airflow demand provided by the prediction module, taking the larger one as the decision airflow. Then, at this airflow, it queries the fan characteristic curves to find the highest operating frequency point for the fan's overall efficiency, including motor efficiency and fan aerodynamic efficiency. Finally, it outputs the optimal frequency command.

[0025] The variable frequency control module receives frequency commands from the decision module and drives the fan. In this implementation, the FR-F800 series fan and pump-specific variable frequency drive (VFD) is selected. The VFD connects to the industrial computer via its built-in RS485 interface. The VFD parameters are set as follows: acceleration time is set to 30 seconds, and deceleration time is set to 40 seconds to avoid overcurrent surges; the frequency command source is set to "network communication command". The VFD output is connected to the fan motor via a shielded cable.

[0026] The fan group collaborative control module is responsible for task allocation when multiple fans in a tunnel need to work collaboratively. In specific implementation, this module's functions are implemented using an S7-1200 series programmable logic controller (PLC), specifically model 6ES7212-1BE40-0XB0. The PLC communicates with each frequency converter and the central industrial control computer via a PROFIBUS-DP bus. Its internal programming includes collaborative control logic. When controlling three fans of the same power, the logic is set as follows: when the required airflow is less than 40% of the rated airflow of a single fan, only one fan is started and operated by frequency converter; when the required airflow is between 40% and 80%, one fan is started and another fan operates at low speed; when the required airflow exceeds 80%, two or three fans operate simultaneously. Furthermore, this module also manages the soft start and sequential start / stop of the fans to balance the cumulative operating time of each fan.

[0027] The fault diagnosis and fault-tolerant control module implements system safety monitoring. On the hardware side, it utilizes the PLC's DI / DO points and analog input module (6ES7231-5QD30-0XB0) to collect real-time status words and alarm codes from each inverter, such as overcurrent, overvoltage, and overheating. On the software side, diagnostic logic is written in the PLC to continuously monitor motor current. If the current continuously exceeds 110% of the rated value within one minute, it is determined to be an overload fault. Once a fan failure is detected, the module immediately executes a fault-tolerant control strategy: in a three-fan system, if fan number 1 fails, the PLC automatically calculates the required speed increase for the remaining two fans and sends new frequency commands to their inverters, taking over the ventilation task of the failed fan, while simultaneously triggering an alarm through the human-machine interface module.

[0028] The human-machine interface module provides the operator with a user interface. Specifically, it uses a TPC1570Gi 15-inch touchscreen, installed on the control panel in the tunnel management center. The touchscreen is connected to the industrial computer via Ethernet cable. The configuration software uses the MCGS embedded version, and the developed operating interface can display real-time data from various sensors within the tunnel, the operating status of the ventilation fans, and the system energy consumption curve. It also features "one-button start / stop," "manual / automatic" mode switching buttons, and a parameter setting window.

[0029] The alarm and emergency module is responsible for safety. Hardware-wise, an audible and visual alarm (Omron B3W-2L series, optional) and an emergency stop button are installed in the tunnel management room. The module's logic is implemented by a PLC. When the CO sensor reading exceeds a preset threshold or the frequency converter reports a serious fault, the PLC's DO point directly drives the alarm to sound and light, and forces the corresponding fan to switch to full-speed operation at the mains frequency. This is achieved by controlling a bypass contactor to ensure safe ventilation. The alarm event is simultaneously recorded and displayed on the touchscreen.

[0030] like Figure 2 As shown, the frequency conversion energy-saving control method for fans in tunnel environments includes the following steps: 1) Data acquisition: The multi-parameter sensing module deployed in the tunnel works continuously to collect data such as CO concentration, visibility, and traffic flow in real time.

[0031] 2) Data processing and storage: The data preprocessing module filters, denoises and formats the collected raw data, and classifies and stores the processed data in cache and persistent storage.

[0032] 3) Real-time air volume calculation: The ventilation demand dynamic calculation module calculates the minimum ventilation volume required by the tunnel at the current moment according to the standard formula based on real-time traffic flow and environmental data.

[0033] 4) Predicted air volume calculation: The ventilation demand prediction module uses an LSTM model to predict the ventilation demand trend for the next 40 minutes based on historical data.

[0034] 5) Optimization Decision: The energy-saving optimization decision module integrates real-time and predicted air demand, with the goal of minimizing the total energy consumption of the system, queries the fan characteristic curves, and calculates the optimal combination of operating frequencies for a single unit or a group of fans.

[0035] 6) Execution and Closed-Loop Control: The frequency converter control module and the fan group collaborative control module execute frequency commands to adjust the fan speed. Simultaneously, the system continuously monitors key environmental parameters and compares them with setpoints, dynamically adjusting frequency commands to form closed-loop control, ensuring energy saving while maintaining safety.

[0036] Example 1: Intelligent ventilation control in long-distance highway tunnels These tunnels are long, have complex ventilation systems, and energy consumption accounts for a high proportion of operating costs, so they have extremely high requirements for energy conservation and control precision.

[0037] System Configuration and Deployment Inside the tunnel, a multi-parameter sensing unit is deployed every 500 meters longitudinally. Each unit integrates an electrochemical CO sensor, an optical visibility (VI) sensor, a laser scattering PM2.5 / PM10 sensor, and a geomagnetic vehicle detector for comprehensive monitoring of environmental and traffic data. Tunnel ventilation employs a three-shaft segmented longitudinal ventilation scheme, with the system of this invention installed on the axial flow fan of each ventilation segment. The core energy-saving optimization decision module is hosted on the server in the tunnel management center. This module incorporates an LSTM-based prediction algorithm capable of learning the natural wind variation patterns and traffic flow patterns throughout the year under different weather conditions.

[0038] Control process and energy saving effect: 1. Data Acquisition and Prediction: Data collected in real time by the sensing unit is transmitted to the central server via industrial Ethernet. The ventilation demand prediction module predicts the air volume demand trend of each section of the tunnel within the next 30 minutes based on traffic flow and environmental data from the past 12 months and real-time data.

[0039] 2. Dynamic Optimization Decision-Making: The energy-saving optimization decision-making module compares the predicted air demand with the real-time calculated air demand and takes the larger value as the control target. Subsequently, the module queries the full characteristic curves of the fans stored in the database, using "lowest energy consumption per unit air volume" as the optimization objective, to calculate the optimal operating frequency combination for each axial fan. During off-peak traffic hours at night, if the prediction module determines that natural winds will be favorable in the near future, the decision-making module will instruct the fans to operate at a lower frequency to fully utilize natural wind compensation.

[0040] 3. Collaborative Execution and Fault Tolerance: The frequency converter control module sends frequency commands to the frequency converters of each fan. The fan group collaborative control module ensures that multiple fans start and stop smoothly in the order of commands, avoiding drastic fluctuations in wind pressure. Once the fault diagnosis module detects an anomaly in a fan, the fault-tolerant control module will immediately reallocate the load of the remaining fans to maintain ventilation safety.

[0041] Through the implementation of this embodiment, the system successfully transforms the operation of the ventilation system from a timed and scheduled, extensive mode to a demand-based, predictive, and refined mode. In practical applications, compared to traditional control methods, the overall energy saving rate of this system is expected to be improved by more than 20%, and it can effectively maintain the air quality in the tunnel consistently above safety standards.

[0042] Example 2: Collaborative Energy-Saving Operation of Urban Short Tunnel Groups Traffic flow in these tunnels fluctuates dramatically, and ventilation between adjacent tunnels may affect each other.

[0043] System configuration and deployment: In this tunnel complex, a complete system of this invention is deployed in each independent tunnel. The data preprocessing and storage modules of each tunnel system are interconnected via a fiber optic network to form a distributed control network. Wind speed and direction sensors are additionally installed in the connecting sections between adjacent tunnels to monitor the "crossflow" effect between the tunnels. The fans mainly use jet fans with a power of 30-55kW, all equipped with variable frequency drives.

[0044] 1. Control Process and Collaborative Optimization: Global Perception and Decision-Making: Sensor data from each tunnel is not only used for control within its own tunnel but is also uploaded to the regional collaborative server. Based on this, the energy-saving optimization decision-making module adds an overall energy consumption optimization algorithm for the tunnel group. This algorithm comprehensively considers the real-time traffic volume, pollutant concentration, and inter-tunnel interactions across all tunnels.

[0045] 2. Feedforward-Feedback Composite Control: The control strategy combines feedforward and feedback mechanisms. When the vehicle detector predicts a large flow of traffic about to move from tunnel A to tunnel B, the system will increase the fan speed in tunnel B in advance to prepare for ventilation, rather than waiting for the pollutant concentration to rise before taking action. At the same time, based on the wind speed sensor data between tunnels, the system dynamically adjusts the operating strategy of each fan to reduce fan energy consumption by utilizing favorable cross-ventilation.

[0046] 3. Peak and Off-Peak Strategies: During peak traffic hours, the system prioritizes ensuring ventilation, with the fans operating in a higher efficiency range; during off-peak hours, energy saving is the primary goal, with the fan speed reduced as much as possible and the fans allowed to operate intermittently at low speeds.

[0047] Through the implementation of this embodiment, the system achieves unified management of ventilation in tunnel groups, avoiding the problems of over-ventilation or under-ventilation in individual tunnels. In practical applications, this collaborative control method is particularly suitable for urban tunnel groups with significant traffic flow tidal phenomena. It can further improve energy-saving potential while ensuring environmental safety, and is expected to reduce the overall ventilation energy consumption of tunnel groups by 15%-30%, and significantly improve the system's response speed.

[0048] In summary, this invention, through a system composed of a multi-parameter sensing module, a data preprocessing and storage module, a ventilation demand dynamic calculation module, and an energy-saving optimization decision module, can dynamically calculate the current air volume demand based on real-time changes in traffic and environmental parameters within the tunnel, and query the optimal energy consumption target operating frequency that matches the current air volume demand based on the stored fan characteristic curves, and continuously and precisely adjust the fan speed via a frequency conversion control module. This technical solution avoids the fans operating at high power during periods of low demand. It directly utilizes the cubic relationship between fan shaft power and rotational speed, minimizing energy consumption while meeting ventilation requirements. The ventilation demand prediction module predicts future air volume requirements based on historical time-series data, and the fault diagnosis and fault-tolerant control module monitors the system status in real time. This allows the system to adjust the fan operating status in advance based on the predicted air volume requirements. When a single fan failure is detected, the ventilation task is automatically redistributed through redundant control logic. This technical solution transforms the control mode from passive remediation after exceeding the limit to proactive predictive regulation and has fault-tolerant operation capabilities under fault conditions, thus maintaining the safety and stability of the ventilation system under changing tunnel conditions.

[0049] Although embodiments of the invention have been shown and described, it will be understood by those skilled in the art that various changes, modifications, substitutions and alterations can be made to these embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the appended claims and their equivalents.

Claims

1. A variable frequency energy-saving control system for fans in tunnel environments, characterized in that: include: A multi-parameter sensing module is installed inside the tunnel, and its signal output is connected to the input of the data preprocessing and storage module. The data preprocessing and storage module processes the received sensor data, and its output is connected to the input of the ventilation demand dynamic calculation module and the ventilation demand prediction module. The ventilation demand dynamic calculation module calculates the current air volume requirement based on real-time data, and its output is connected to the first input of the energy-saving optimization decision module. The ventilation demand forecasting module predicts future air volume based on historical data, and its output is connected to the second input of the energy-saving optimization decision module. An energy-saving optimization decision module, the output of which is connected to the input of a frequency converter control module, is equipped with a memory for storing fan characteristic curves and optimization algorithms. The variable frequency control module has its control signal output terminal connected to the frequency converter of the ventilation fan inside the tunnel; The wind turbine group coordinated control module has its signal input / output terminals connected to the frequency conversion control module and the controller of each wind turbine, respectively. The fault diagnosis and fault-tolerant control module has its signal acquisition terminal connected to the status monitoring points of each module in the system, and its control signal output terminal connected to the wind turbine group collaborative control module and the alarm emergency module. The human-computer interaction module has its data interface bidirectionally connected to the data preprocessing and storage module and the energy-saving optimization decision module; The alarm emergency module has its trigger signal input terminal connected to the alarm signal output terminal of the fault diagnosis and fault-tolerant control module and the multi-parameter sensing module.

2. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The multi-parameter sensing module includes multiple sensor arrays distributed along the tunnel length direction, and the communication bus of each sensor array is connected to the centralized data interface of the data preprocessing and storage module.

3. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The ventilation demand prediction module includes a processor and a memory storing a trained long short-term memory network model. The processor's data access port is connected to the time-series database of the data preprocessing and storage module.

4. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The energy-saving optimization decision module's memory stores a fan characteristic curve containing a mapping table of fan speed, air volume, and power consumption. The processor of the energy-saving optimization decision module is configured to perform queries and optimization calculations based on the mapping table and the input required air volume.

5. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The wind turbine group collaborative control module is equipped with a logic control unit, which is programmed with collaborative control logic for controlling the sequential start-up and shutdown and speed ratio of multiple wind turbines.

6. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The fault diagnosis and fault-tolerant control module includes a comparator circuit and a redundant control logic circuit. When the comparator circuit detects abnormal wind turbine operating parameters, it triggers the redundant control logic circuit to take over the control of the wind turbine.

7. The frequency conversion energy-saving control method and system for fans in tunnel environments according to claim 1, characterized in that: The system also includes a remote monitoring platform, whose communication unit establishes a bidirectional communication link with the data transmission interface of the data preprocessing and storage module through a data network.

8. A frequency conversion energy-saving control method for fans in tunnel environments, as described in claims 1-5, characterized in that: Includes the following steps: S1: Collect environmental and traffic parameters through a sensor array deployed inside the tunnel; S2: Standardize the collected parameters and store them in the time series database; S3: Based on the parameters processed in real time, the current real-time ventilation volume required for the tunnel is calculated; S4: Based on historical time series data, the predicted ventilation volume for future periods is obtained through a prediction model; S5: Combine real-time ventilation volume and predicted ventilation volume, query fan characteristic curves, and calculate the target operating frequency of the fan or fan group; S6: Generates a variable frequency control signal based on the target operating frequency, adjusts the fan speed, and monitors changes in environmental parameters to form a closed-loop control.

9. The frequency conversion energy-saving control method for fans in tunnel environments according to claim 8, characterized in that: In step S5, the calculation of the target operating frequency specifically includes: taking the larger value between the real-time ventilation volume and the predicted ventilation volume as the decision air volume, and determining the target frequency point with the lowest energy consumption based on the correspondence between air volume and frequency in the fan characteristic curve.

10. The frequency conversion energy-saving control method for fans in tunnel environments according to claim 8, characterized in that: In step S6, the closed-loop control includes: comparing the actual values ​​of key environmental parameters monitored in the tunnel after adjusting the fan speed with preset safety thresholds, and dynamically adjusting the target operating frequency based on the comparison results.

Images