Tunnel fan energy-saving control system

Abstract

The invention relates to the technical field of tunnel ventilation control, in particular to a tunnel fan energy-saving control system which comprises a multi-parameter sensing module, an intelligent evaluation module, a dynamic prediction module, an energy-saving optimization module, a frequency conversion control module and an alarm emergency module. Wherein the multi-parameter sensing module is used for monitoring various environmental parameters in a tunnel in real time; the intelligent evaluation module is used for calculating the current ventilation demand; the dynamic prediction module is used for predicting the ventilation demand in a period of time in the future; the energy-saving optimization module is used for generating an optimal energy-saving control instruction; the frequency conversion control module is used for adjusting the operation frequency and speed of the fan according to the instruction; and the alarm emergency module is used for sending an alarm signal when an abnormal condition is detected. According to the invention, environmental parameters in the tunnel are monitored and intelligently managed in real time, a fan operation strategy is dynamically optimized, and the system has emergency response capability, so that the ventilation efficiency is remarkably improved, the energy consumption is reduced, and the construction safety is guaranteed.

Description

Technical Field

[0001] The invention relates to the technical field of tunnel ventilation control, and in particular to an energy-saving control system for a tunnel fan. Background Art

[0002] During tunnel construction, there are usually complex situations with multiple working faces and multiple processes working alternately. Since construction operations often involve processes such as blasting, drilling and shotcrete spraying, these operations will produce a large amount of harmful gases and dust, which seriously affect the air quality in the tunnel. In order to ensure the safety of the construction environment and the health of the workers, it is very important to establish an efficient ventilation system to provide sufficient fresh air circulation. However, most tunnel ventilation systems are currently designed for maximum ventilation volume. Even when the excavation working face is short or the ventilation demand is low, the system will run at maximum power, resulting in a huge waste of energy. In addition, most existing ventilation systems use fixed-speed axial flow fans, lack variable frequency control technology, and cannot dynamically adjust the operating status of the fan according to actual needs.

[0003] The main problem with existing technologies is the lack of intelligence and dynamic adjustment capabilities, which leads to energy waste and low operating efficiency. Specifically, the existing system is unable to monitor the environmental parameters in the tunnel in real time and optimize and adjust according to actual ventilation needs. In addition, when the concentration of harmful gases exceeds the standard, the existing system lacks rapid response and emergency handling capabilities, and is unable to discharge harmful gases in a timely and effective manner to ensure the safety of construction workers.

[0004] Therefore, there is an urgent need for a tunnel fan energy-saving control system that can monitor environmental parameters in real time, intelligently evaluate ventilation needs, dynamically optimize fan operation strategies and have emergency response capabilities to solve the above-mentioned problems in the existing technology and improve the safety and operation efficiency of tunnel construction. Summary of the invention

[0005] Based on the above purpose, the present invention provides a tunnel fan energy-saving control system.

[0006] A tunnel fan energy-saving control system includes a multi-parameter sensing module, an intelligent evaluation module, a dynamic prediction module, an energy-saving optimization module, a frequency conversion control module and an alarm emergency module; wherein:

[0007] Multi-parameter sensing module: used to monitor multiple environmental parameters in the tunnel in real time, including gas concentration, temperature, humidity, dust content and wind speed, and transmit the monitoring data to the intelligent evaluation module;

[0008] Intelligent evaluation module: connected to the multi-parameter sensing module, used to receive and analyze the monitoring data of the multi-parameter sensing module, calculate the current ventilation demand, and send the evaluation result to the dynamic prediction module;

[0009] Dynamic prediction module: connected with the intelligent evaluation module, used to conduct in-depth learning and analysis based on the evaluation results, historical data and real-time data, predict the ventilation demand in the future, and transmit the prediction results to the energy-saving optimization module;

[0010] Energy-saving optimization module: connected with the dynamic prediction module, used to optimize the operation strategy of the fan according to the prediction results and real-time requirements provided by the dynamic prediction module, generate the optimal energy-saving control instructions, and send the instructions to the frequency conversion control module;

[0011] Frequency conversion control module: connected to the energy-saving optimization module, used to receive energy-saving control instructions and adjust the operating frequency and speed of the fan according to the instructions;

[0012] Alarm emergency module: connected to the multi-parameter sensor module, it is used to send out an alarm signal when it detects that the concentration of harmful gases exceeds the standard or an abnormal situation occurs, and works with the energy-saving optimization module to automatically execute the emergency ventilation plan.

[0013] Optionally, the multi-parameter sensing module includes a gas concentration sensing unit, a temperature sensing unit, a humidity sensing unit, a dust sensing unit and a wind speed sensing unit; wherein:

[0014] Gas concentration sensing unit: including electrochemical sensors and infrared sensors, used to detect the concentration of harmful gases in the tunnel, including carbon monoxide, carbon dioxide and hydrogen sulfide. The electrochemical sensor generates current through the reaction of electrodes and electrolytes, and the infrared sensor determines the gas concentration by measuring the absorption intensity of different wavelengths.

[0015] Temperature sensing unit: including thermocouples and thermistors, used to measure the temperature in the tunnel. Thermocouples measure temperature by the change of temperature potential of different metal junctions, and thermistors measure temperature by the change of resistance value with temperature.

[0016] Humidity sensing unit: including capacitive humidity sensor and resistive humidity sensor, used to measure the humidity in the tunnel. Capacitive humidity sensor measures humidity by the change of capacitance due to the change of dielectric constant with humidity, and resistive humidity sensor measures humidity by the change of resistance of humidity-sensitive material.

[0017] Dust sensing unit: including optical particle sensor and laser scattering sensor, used to monitor the dust content in the tunnel. The optical particle sensor measures the particle concentration through the principle of light scattering, and the laser scattering sensor measures the dust concentration through the scattered light intensity of the laser beam and the particles.

[0018] Wind speed sensing unit: includes ultrasonic wind speed sensor and hot wire anemometer, which are used to measure the wind speed in the tunnel. The ultrasonic wind speed sensor determines the wind speed by measuring the change in the propagation speed of ultrasonic waves in the air, and the hot wire anemometer measures the wind speed by measuring the change in heat dissipation of the heated hot wire in the air flow.

[0019] Optionally, the intelligent assessment module includes a data acquisition unit, a data processing unit and a demand calculation unit; wherein:

[0020] Data acquisition unit: used to receive and store monitoring data from the gas concentration sensing unit, temperature sensing unit, humidity sensing unit, dust sensing unit and wind speed sensing unit;

[0021] Data processing unit: used to pre-process the received monitoring data, including data filtering, denoising and standardization, to ensure the accuracy and consistency of the data;

[0022] Demand calculation unit: Based on the pre-processed monitoring data, according to the preset calculation model, it comprehensively analyzes the gas concentration, temperature, humidity, dust content and wind speed, calculates the current ventilation demand, and transmits the calculation results to the dynamic prediction module.

[0023] Optionally, the demand calculation unit specifically includes:

[0024] Select calculation model: The preset calculation model specifically adopts a multi-factor weighted model, which is used to assign different weights to each monitoring parameter and comprehensively calculate the ventilation demand; the calculation formula is: Where V is the required ventilation volume, w i is the weight of the i-th parameter, P i is the measured value of the i-th parameter, and n is the total number of parameters;

[0025] Gas concentration calculation: Evaluate air quality based on the monitored harmful gas concentration, and perform weighted calculation based on the degree of harm of different gases; the formula is: Among them, C weighted is the weighted gas concentration, k j is the weight of the jth gas, C j is the measured concentration of the jth gas, and m is the total number of gas types;

[0026] Comprehensive analysis: Combining the parameters of gas concentration, temperature, humidity, dust content and wind speed, the overall ventilation demand is calculated through a multi-factor weighted model. The specific formula is:

[0027] V total =a×C weighted +b×T+c×H+d×D+e×W, where V total is the ventilation demand after comprehensive calculation, C weightedis the weighted gas concentration, T is the temperature, H is the humidity, D is the dust content, W is the wind speed, and a, b, c, d and e are the weight coefficients of each parameter.

[0028] Optionally, the dynamic prediction module includes a historical data storage unit, a real-time data acquisition unit, a deep learning unit and a prediction analysis unit; wherein:

[0029] Historical data storage unit: used to store historical monitoring data and evaluation results obtained from the multi-parameter sensing module and the intelligent evaluation module as training data for deep learning;

[0030] Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the current real-time monitoring data and evaluation results as input data for predictive analysis;

[0031] Deep learning unit: connected to the historical data storage unit and the real-time data acquisition unit, used to train the historical data, adopt a recursive neural network model, learn the time series pattern of the changes of various parameters in the tunnel, and generate a prediction model;

[0032] Predictive analysis unit: connected with the deep learning unit, it applies the prediction model generated after training and combines it with real-time data to predict ventilation demand in the future.

[0033] Optionally, the deep learning unit includes:

[0034] Data preprocessing: standardize the data in the historical data storage unit;

[0035] Construct a recursive neural network model: Construct a recursive neural network model including an input layer, several hidden layers and an output layer. The output of each hidden layer is transformed nonlinearly through an activation function. The activation function is a hyperbolic tangent function with the formula: h t =tanh(W h ·h t-1 +W x ·x t +b), where h t is the hidden state of the current time step, h t-1 is the hidden state of the previous time step, W h and W x are the weight matrices for hidden states and inputs, respectively, x t is the input of the current time step, and b is the bias term;

[0036] Model training: Use the training data to train the model through the back propagation algorithm and calculate the loss function. The formula is: Among them, L is the loss function, N is the number of samples, and y i is the true value, is the predicted value; the model parameters are updated by the gradient descent method, and the formula is: Among them, θ is the model parameter, η is the learning rate, is the gradient of the loss function with respect to the model parameters;

[0037] Model validation: Use the validation dataset to evaluate the performance of the trained model; the recurrent neural network prediction model after training is represented as: in, is the predicted value after k time steps in the future, f θ is the trained recurrent neural network model, x t is the input data of the current time step t, h t-1 is the hidden state of the previous time step, and θ is the model parameter.

[0038] Optionally, the energy-saving optimization module includes a prediction data receiving unit, a real-time data acquisition unit, an optimization algorithm unit and a control instruction generating unit; wherein:

[0039] Prediction data receiving unit: used to receive the ventilation demand prediction result within a period of time in the future provided by the dynamic prediction module;

[0040] Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the real-time environmental data and immediate ventilation needs in the current tunnel;

[0041] Optimization algorithm unit: connected to the prediction data receiving unit and the real-time data acquisition unit, used to comprehensively analyze the prediction results and real-time data, and calculate the optimal wind turbine operation strategy through the optimization algorithm;

[0042] Control instruction generation unit: used to generate control instructions according to the optimal fan operation strategy output by the optimization algorithm unit, and send it to the frequency conversion control module, specifically converting the fan operation parameters calculated by the optimization algorithm unit into control signals; the generated control instructions specifically include the start, stop, speed regulation and frequency regulation operations of the fan.

[0043] Optionally, the optimization algorithm unit specifically includes:

[0044] Step 1: Based on the current ventilation demand V calculated by the demand calculation unit total And the future ventilation demand V predicted by the dynamic prediction module predicted , construct optimization objectives and constraints;

[0045] Step 2: Use a linear programming algorithm with minimizing energy consumption as the objective function. The specific constraints include meeting current and predicted ventilation needs, the operating range of the fan, and the safety standards of the system. The mathematical expression of the optimization problem is: Among them, Pt is the fan power at time step t, Δt is the time step length, and the goal is to minimize the total energy consumption while meeting the ventilation requirements; the constraints include: V real-time ≤V total ≤V max , where V real-time For real-time needs, V total To optimize the calculated demand, V max is the maximum ventilation volume of the fan;

[0046] Step 3: Comprehensive forecast of future ventilation demand V predicted To optimize, the formula is:

[0047] V optimized =α×V total +β×V predicted , where V optimized is the optimized ventilation demand, α and β are weight coefficients used to balance the current demand and the future predicted demand;

[0048] Step 4: Based on the optimized ventilation requirement V optimized , calculate the optimal fan operating parameters, the specific formula is:

[0049]

[0050] Among them, f optimal is the optimized fan frequency, f max is the maximum frequency of the fan, V optimized For the optimized ventilation requirement, V max is the maximum ventilation volume of the fan, P optimal is the optimized fan power, P max is the maximum power of the fan.

[0051] Optionally, the frequency conversion control module includes a control signal receiving unit, a frequency conversion unit and a speed adjustment unit; wherein:

[0052] Control signal receiving unit: used to receive the generated control instructions, including the start, stop, speed regulation and frequency regulation operations of the fan;

[0053] Frequency conversion unit: connected to the control signal receiving unit, used to adjust the power supply frequency of the fan according to the received control command. The frequency conversion unit converts the frequency of the AC power supply into the predetermined frequency required by the fan through frequency conversion technology to control the speed of the fan;

[0054] Speed ​​regulating unit: used to adjust the speed of the fan according to the converted frequency signal. The speed regulating unit adjusts the input voltage and current of the fan motor through the frequency converter, thereby changing the speed of the fan.

[0055] Optionally, the alarm emergency module includes a gas monitoring unit, an alarm issuing unit and an emergency ventilation control unit; wherein:

[0056] Gas monitoring unit: connected to the multi-parameter sensor module, used to monitor the concentration of harmful gases in the tunnel in real time. The gas monitoring unit has a preset safety threshold. Once any harmful gas concentration exceeding the preset threshold is detected, it is judged as an abnormal situation;

[0057] Alarm issuing unit: connected to the gas monitoring unit, used to immediately activate the alarm device when the gas monitoring unit detects that the concentration of harmful gas exceeds the standard. The alarm device includes sound alarm and light signal alarm, which are used to issue warnings to tunnel operators and monitoring center;

[0058] Emergency ventilation control unit: used to automatically adjust the fan operation strategy after receiving an alarm that the concentration of harmful gases exceeds the standard. Specifically, according to the preset emergency response procedure, the ventilation volume is quickly increased to reduce the concentration of harmful gases in the tunnel to a safe level.

[0059] Beneficial effects of the present invention:

[0060] The present invention accurately calculates the current ventilation demand by comprehensively analyzing multiple parameters such as gas concentration, temperature, humidity, dust content and wind speed, and uses a deep learning model to predict future ventilation demand. Based on these data, the system dynamically adjusts the fan operation strategy through an optimization algorithm to ensure that the fan operates in the most energy-efficient manner while meeting the ventilation demand. Compared with traditional fixed-speed fan systems, it can significantly reduce energy consumption, improve ventilation efficiency, extend equipment service life, and reduce maintenance costs.

[0061] The present invention uses an alarm emergency module. When it detects that the concentration of harmful gases exceeds the standard or other abnormal conditions occur, the system can quickly send out an alarm signal and automatically execute an emergency ventilation plan. By increasing the operating frequency and speed of the fan, the concentration of harmful gases can be quickly reduced to ensure the safety of the environment in the tunnel. The system not only improves the safety management level of tunnel construction, but also enhances the emergency response capability to ensure the health and safety of construction personnel. This intelligent and dynamic ventilation control system provides comprehensive environmental protection for tunnel construction and greatly improves construction efficiency and safety. BRIEF DESCRIPTION OF THE DRAWINGS

[0062] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only for the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0063] Figure 1 A schematic diagram of a tunnel fan energy-saving control system according to an embodiment of the present invention;

[0064] Figure 2 Schematic diagram of an energy-saving optimization module according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] The present invention is described in detail below in conjunction with the accompanying drawings and specific embodiments. At the same time, it is explained here that in order to make the embodiments more detailed, the following embodiments are the best and preferred embodiments, and those skilled in the art may also adopt other alternatives to implement some known technologies; and the accompanying drawings are only for more specific description of the embodiments, and are not intended to specifically limit the present invention.

[0066] It should be noted that the references to "one embodiment", "an embodiment", "an exemplary embodiment", "some embodiments" and the like in the specification indicate that the embodiments described may include specific features, structures or characteristics, but not every embodiment may include the specific features, structures or characteristics. In addition, when a specific feature, structure or characteristic is described in conjunction with an embodiment, it should be within the knowledge of a person skilled in the art to implement such feature, structure or characteristic in conjunction with other embodiments (whether or not explicitly described).

[0067] In general, a term can be understood, at least in part, from its use in context. For example, depending, at least in part, on the context, the term "one or more" as used herein can be used to describe any feature, structure, or characteristic in the singular sense, or can be used to describe a combination of features, structures, or characteristics in the plural sense. Additionally, the term "based on" can be understood as not necessarily intended to convey an exclusive set of factors, but can instead, depending, at least in part, on the context, allow for the presence of other factors that are not necessarily explicitly described.

[0068] like Figure 1-Figure 2 As shown, a tunnel fan energy-saving control system includes a multi-parameter sensing module, an intelligent evaluation module, a dynamic prediction module, an energy-saving optimization module, a frequency conversion control module and an alarm emergency module; wherein:

[0069] Multi-parameter sensing module: used to monitor multiple environmental parameters in the tunnel in real time, including gas concentration, temperature, humidity, dust content and wind speed, and transmit the monitoring data to the intelligent evaluation module;

[0070] Intelligent evaluation module: connected to the multi-parameter sensor module, used to receive and analyze the monitoring data of the multi-parameter sensor module, calculate the current ventilation demand, and send the evaluation results to the dynamic prediction module;

[0071] Dynamic prediction module: connected with the intelligent evaluation module, used to conduct in-depth learning and analysis based on the evaluation results, historical data and real-time data, predict the ventilation demand in the future, and transmit the prediction results to the energy-saving optimization module;

[0072] Energy-saving optimization module: connected with the dynamic prediction module, used to optimize the operation strategy of the fan according to the prediction results and real-time requirements provided by the dynamic prediction module, generate the optimal energy-saving control instructions, and send the instructions to the frequency conversion control module;

[0073] Frequency conversion control module: connected to the energy-saving optimization module, used to receive energy-saving control instructions and adjust the operating frequency and speed of the fan according to the instructions;

[0074] Alarm emergency module: connected with the multi-parameter sensor module, it is used to send out alarm signals when the concentration of harmful gases exceeds the standard or abnormal conditions are detected, and work with the energy-saving optimization module to automatically execute the emergency ventilation plan to quickly respond to and handle emergencies.

[0075] The multi-parameter sensing module includes a gas concentration sensing unit, a temperature sensing unit, a humidity sensing unit, a dust sensing unit and a wind speed sensing unit; wherein:

[0076] Gas concentration sensing unit: including electrochemical sensors and infrared sensors, used to detect the concentration of harmful gases in the tunnel, including carbon monoxide, carbon dioxide and hydrogen sulfide. The electrochemical sensor generates current through the reaction of electrodes and electrolytes, and the infrared sensor determines the gas concentration by measuring the absorption intensity of different wavelengths.

[0077] Temperature sensing unit: including thermocouples and thermistors, used to measure the temperature in the tunnel. Thermocouples measure temperature by the change of temperature potential of different metal junctions, and thermistors measure temperature by the change of resistance value with temperature.

[0078] Humidity sensing unit: including capacitive humidity sensor and resistive humidity sensor, used to measure the humidity in the tunnel. Capacitive humidity sensor measures humidity by the change of capacitance due to the change of dielectric constant with humidity, and resistive humidity sensor measures humidity by the change of resistance of humidity-sensitive material.

[0079] Dust sensing unit: including optical particle sensor and laser scattering sensor, used to monitor the dust content in the tunnel. The optical particle sensor measures the particle concentration through the principle of light scattering, and the laser scattering sensor measures the dust concentration through the scattered light intensity of the laser beam and the particles.

[0080] Wind speed sensing unit: including ultrasonic wind speed sensor and hot wire anemometer, used to measure wind speed in tunnel. Ultrasonic wind speed sensor determines wind speed by measuring the change of ultrasonic wave propagation speed in air, and hot wire anemometer measures wind speed by measuring the change of heat dissipation of heated hot wire in air flow. By integrating electrochemical sensor, infrared sensor, thermocouple, thermistor, capacitive humidity sensor, resistive humidity sensor, optical particle sensor, laser scattering sensor, ultrasonic wind speed sensor and hot wire anemometer in multi-parameter sensing module, real-time monitoring of multiple environmental parameters in tunnel is realized. Each sensor uses its unique measurement principle to ensure the accuracy and reliability of data, and provides detailed and accurate basic data support for intelligent evaluation module.

[0081] The intelligent evaluation module includes a data acquisition unit, a data processing unit and a demand calculation unit; wherein:

[0082] Data acquisition unit: used to receive and store monitoring data from the gas concentration sensing unit, temperature sensing unit, humidity sensing unit, dust sensing unit and wind speed sensing unit;

[0083] Data processing unit: used to pre-process the received monitoring data, including data filtering, denoising and standardization, to ensure the accuracy and consistency of the data;

[0084] Demand calculation unit: Based on the pre-processed monitoring data, according to the preset calculation model, it comprehensively analyzes the gas concentration, temperature, humidity, dust content and wind speed, calculates the current ventilation demand, and transmits the calculation results to the dynamic prediction module.

[0085] The calculation models preset in the demand calculation unit specifically include:

[0086] Select calculation model: The preset calculation model specifically adopts a multi-factor weighted model, which is used to assign different weights to each monitoring parameter and comprehensively calculate the ventilation demand; the calculation formula is: Where V is the required ventilation volume, w i is the weight of the i-th parameter, P i is the measured value of the i-th parameter, and n is the total number of parameters;

[0087] Gas concentration calculation: Evaluate air quality based on the monitored harmful gas concentration, and perform weighted calculation based on the degree of harm of different gases; the formula is: Among them, C weighted is the weighted gas concentration, k j is the weight of the jth gas, C j is the measured concentration of the jth gas, and m is the total number of gas types;

[0088] Comprehensive analysis: Combining the parameters of gas concentration, temperature, humidity, dust content and wind speed, the overall ventilation demand is calculated through a multi-factor weighted model. The specific formula is:

[0089] V total =a×C weighted +b×T+c×H+d×D+e×W, where V total is the ventilation demand after comprehensive calculation, C weighted is the weighted gas concentration, T is temperature, H is humidity, D is dust content, W is wind speed, a, b, c, d and e are weight coefficients of each parameter;

[0090] By integrating the data acquisition unit, data processing unit and demand calculation unit in the intelligent evaluation module, and using the multi-factor weighted model and weighted gas concentration calculation model, efficient processing and accurate evaluation of the monitoring data of the multi-parameter sensing module are achieved. Each unit uses its unique functions to ensure the integrity and reliability of the data, providing a solid foundation for the calculation of ventilation demand. The module can quickly and accurately calculate the current ventilation demand through preset calculation models and algorithms, and provide necessary data support for the dynamic prediction module. This design improves the system's response speed and accuracy to environmental changes, and helps to optimize the operating efficiency of the tunnel ventilation system.

[0091] The dynamic prediction module includes a historical data storage unit, a real-time data acquisition unit, a deep learning unit and a prediction analysis unit; wherein:

[0092] Historical data storage unit: used to store historical monitoring data and evaluation results obtained from the multi-parameter sensing module and the intelligent evaluation module as training data for deep learning;

[0093] Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the current real-time monitoring data and evaluation results as input data for predictive analysis;

[0094] Deep learning unit: connected to the historical data storage unit and the real-time data acquisition unit, used to train the historical data, adopt the recursive neural network (RNN) model, learn the time series pattern of the changes of various parameters in the tunnel, and generate a prediction model;

[0095] Prediction analysis unit: connected with the deep learning unit, it applies the prediction model generated after training and combines it with real-time data to predict ventilation demand in the future;

[0096] The specific steps for predicting ventilation demand in the future are as follows:

[0097] According to the trained recursive neural network model, real-time monitoring data is input and the predicted values ​​of various environmental parameters in the future period are output;

[0098] Based on the forecast value, the ventilation demand in the future period is calculated using the same calculation model as the demand calculation unit;

[0099] The prediction results are transmitted to the energy-saving optimization module: used to optimize the operation strategy of the fan;

[0100] By integrating the historical data storage unit, real-time data acquisition unit, deep learning unit and predictive analysis unit in the dynamic prediction module, deep learning and predictive analysis based on historical data and real-time data are realized. The deep learning unit accurately captures the time series pattern of changes in various parameters in the tunnel through the recursive neural network (RNN), thereby improving the accuracy of the prediction. The predictive analysis unit uses the trained RNN model combined with real-time data to accurately predict the ventilation demand in the future. This design improves the system's response speed and accuracy to environmental changes and helps optimize the operating efficiency of the tunnel ventilation system.

[0101] The Deep Learning module includes:

[0102] Data preprocessing: standardize the data in the historical data storage unit;

[0103] Construct a recursive neural network model: Construct a recursive neural network model including an input layer, several hidden layers and an output layer. The output of each hidden layer is transformed nonlinearly through an activation function. The activation function is the hyperbolic tangent function (tanh), and the formula is: h t =tanh(W h ·h t-1 +W x ·x t +b), where h t is the hidden state of the current time step, h t-1 is the hidden state of the previous time step, W h and W x are the weight matrices for hidden states and inputs, respectively, x t is the input of the current time step, and b is the bias term;

[0104] Model training: Use the training data to train the model through the back propagation algorithm and calculate the loss function (such as mean square error). The formula is: Among them, L is the loss function, N is the number of samples, and y i is the true value, is the predicted value; the model parameters are updated by the gradient descent method, and the formula is: Among them, θ is the model parameter, η is the learning rate, is the gradient of the loss function with respect to the model parameters;

[0105] Model validation: Use the validation data set to evaluate the performance of the trained model to ensure that the model has good generalization ability; the recursive neural network prediction model after training is expressed as: in, is the predicted value after k time steps in the future, f θ is the trained recurrent neural network model, x t is the input data of the current time step t, h t-1 is the hidden state of the previous time step, and θ is the model parameter. By integrating the recurrent neural network (RNN) model in the deep learning unit and conducting a detailed training process on historical data, including data preprocessing, model construction, model training, and model verification, accurate learning and prediction of the time series pattern of changes in various parameters in the tunnel are achieved.

[0106] The energy-saving optimization module includes a prediction data receiving unit, a real-time data acquisition unit, an optimization algorithm unit and a control instruction generation unit; wherein:

[0107] Prediction data receiving unit: used to receive the ventilation demand prediction result within a period of time in the future provided by the dynamic prediction module;

[0108] Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the real-time environmental data and immediate ventilation needs in the current tunnel;

[0109] Optimization algorithm unit: connected to the prediction data receiving unit and the real-time data acquisition unit, used to comprehensively analyze the prediction results and real-time data, and calculate the optimal wind turbine operation strategy through the optimization algorithm;

[0110] Control instruction generation unit: used to generate control instructions according to the optimal fan operation strategy output by the optimization algorithm unit, and send it to the frequency conversion control module, specifically converting the fan operation parameters calculated by the optimization algorithm unit into control signals; the generated control instructions specifically include the start, stop, speed and frequency regulation operations of the fan to achieve the best energy-saving effect; by integrating the prediction data receiving unit, real-time data acquisition unit, optimization algorithm unit and control instruction generation unit in the energy-saving optimization module, and using linear programming algorithm and mathematical expressions of optimization problems, the fan operation strategy optimization based on comprehensive current and future ventilation needs is realized, the current ventilation demand calculated by the demand calculation unit and the future ventilation demand provided by the dynamic prediction module are comprehensively analyzed through the optimization algorithm to ensure that the fan can operate in the optimal state in each time period, and the control instruction generation unit converts the optimization results into specific control instructions to ensure that the system operates efficiently and energy-saving.

[0111] The optimization algorithm unit specifically includes:

[0112] Step 1: Based on the current ventilation demand V calculated by the demand calculation unit total And the future ventilation demand V predicted by the dynamic prediction module predicted , construct optimization objectives and constraints;

[0113] Step 2: Use a linear programming algorithm with minimizing energy consumption as the objective function. The specific constraints include meeting current and predicted ventilation needs, the operating range of the fan, and the safety standards of the system. The mathematical expression of the optimization problem is: Among them, P t is the fan power at time step t, Δt is the time step length, and the goal is to minimize the total energy consumption while meeting the ventilation requirements; the constraints include: V real-time ≤V total ≤V max , where V real-time For real-time needs, V toal To optimize the calculated demand, V max is the maximum ventilation volume of the fan;

[0114] Step 3: Comprehensive forecast of future ventilation demand V predicted To optimize, the formula is:

[0115] V optimized =α×V total +β×V predicted , where V optimized is the optimized ventilation demand, α and β are weight coefficients used to balance the current demand and the future predicted demand;

[0116] Step 4: Based on the optimized ventilation requirement V optimized , calculate the optimal fan operating parameters (such as speed and frequency), the specific formula is:

[0117]

[0118] Among them, f optimal is the optimized fan frequency, f max is the maximum frequency of the fan, V optimized For the optimized ventilation requirement, V max is the maximum ventilation volume of the fan, P optimal is the optimized fan power, P max is the maximum power of the fan.

[0119] The frequency conversion control module includes a control signal receiving unit, a frequency conversion unit and a speed adjustment unit; wherein:

[0120] Control signal receiving unit: used to receive the generated control instructions, including the start, stop, speed regulation and frequency regulation operations of the fan;

[0121] Frequency conversion unit: connected to the control signal receiving unit, used to adjust the power supply frequency of the fan according to the received control command. The frequency conversion unit converts the frequency of the AC power supply into the predetermined frequency required by the fan through frequency conversion technology to control the speed of the fan;

[0122] Speed ​​regulation unit: used to adjust the speed of the fan according to the converted frequency signal. The speed regulation unit adjusts the input voltage and current of the fan motor through the frequency converter, thereby changing the speed of the fan to achieve the required ventilation volume; by integrating the control signal receiving unit, the frequency conversion unit and the speed regulation unit in the frequency conversion control module, the precise adjustment of the fan operating frequency and speed is achieved. The control signal receiving unit receives control instructions from the energy-saving optimization module, the frequency conversion unit adjusts the power supply frequency according to these instructions, and the speed regulation unit adjusts the speed of the fan through the frequency converter to ensure that the fan can operate in the optimal state in each time period.

[0123] The alarm emergency module includes a gas monitoring unit, an alarm issuing unit and an emergency ventilation control unit; wherein:

[0124] Gas monitoring unit: connected to the multi-parameter sensor module, used to monitor the concentration of harmful gases in the tunnel in real time. The gas monitoring unit has a preset safety threshold. Once any harmful gas concentration exceeding the preset threshold is detected, it is judged as an abnormal situation;

[0125] Alarm issuing unit: connected to the gas monitoring unit, used to immediately activate the alarm device when the gas monitoring unit detects that the concentration of harmful gas exceeds the standard. The alarm device includes sound alarm and light signal alarm, which is used to warn the tunnel operator and the monitoring center;

[0126] Emergency ventilation control unit: It is used to automatically adjust the operation strategy of the fan after receiving an alarm of excessive concentration of harmful gases. Specifically, according to the preset emergency response procedure, the ventilation volume is quickly increased to reduce the concentration of harmful gases in the tunnel to a safe level. This adjustment is achieved by sending an emergency adjustment command to the frequency conversion control module, instructing the fan to run at a higher frequency and speed to accelerate air circulation and the discharge of harmful gases. By integrating the gas monitoring unit, the alarm issuing unit and the emergency ventilation control unit in the alarm and emergency module, real-time monitoring and rapid response to the concentration of harmful gases in the tunnel are achieved. Once the concentration of harmful gases is detected to be excessive, the alarm issuing unit can quickly activate the alarm system. At the same time, the emergency ventilation control unit automatically adjusts the fan operation strategy, quickly increases the ventilation volume, effectively reduces the concentration of harmful gases, and ensures the safety of tunnel construction personnel and the safety and stability of the environment in the tunnel.

[0127] The present invention covers any substitution, modification, equivalent method and scheme made on the essence and scope of the present invention. In order to make the public have a thorough understanding of the present invention, specific details are described in detail in the following preferred embodiments of the present invention, but those skilled in the art can fully understand the present invention without the description of these details. In addition, in order to avoid unnecessary confusion about the essence of the present invention, well-known methods, processes, procedures, components and circuits are not described in detail.

[0128] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principle of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. A tunnel fan energy-saving control system, characterized in that: It includes multi-parameter sensing module, intelligent evaluation module, dynamic prediction module, energy-saving optimization module, frequency conversion control module and alarm emergency module; among which: Multi-parameter sensing module: used to monitor multiple environmental parameters in the tunnel in real time, including gas concentration, temperature, humidity, dust content and wind speed, and transmit the monitoring data to the intelligent evaluation module; Intelligent evaluation module: connected to the multi-parameter sensing module, used to receive and analyze the monitoring data of the multi-parameter sensing module, calculate the current ventilation demand, and send the evaluation result to the dynamic prediction module; Dynamic prediction module: connected with the intelligent evaluation module, used to conduct in-depth learning and analysis based on the evaluation results, historical data and real-time data, predict the ventilation demand in the future, and transmit the prediction results to the energy-saving optimization module; Energy-saving optimization module: connected with the dynamic prediction module, used to optimize the operation strategy of the fan according to the prediction results and real-time requirements provided by the dynamic prediction module, generate the optimal energy-saving control instructions, and send the instructions to the frequency conversion control module; Frequency conversion control module: connected to the energy-saving optimization module, used to receive energy-saving control instructions and adjust the operating frequency and speed of the fan according to the instructions; Alarm emergency module: connected to the multi-parameter sensor module, it is used to send out an alarm signal when it detects that the concentration of harmful gases exceeds the standard or an abnormal situation occurs, and works with the energy-saving optimization module to automatically execute the emergency ventilation plan.

2. A tunnel fan energy-saving control system according to claim 1, characterized in that: The multi-parameter sensing module includes a gas concentration sensing unit, a temperature sensing unit, a humidity sensing unit, a dust sensing unit and a wind speed sensing unit; wherein: Gas concentration sensing unit: including electrochemical sensors and infrared sensors, used to detect the concentration of harmful gases in the tunnel, including carbon monoxide, carbon dioxide and hydrogen sulfide. The electrochemical sensor generates current through the reaction of electrodes and electrolytes, and the infrared sensor determines the gas concentration by measuring the absorption intensity of different wavelengths. Temperature sensing unit: including thermocouples and thermistors, used to measure the temperature in the tunnel. Thermocouples measure temperature by the change of temperature potential of different metal junctions, and thermistors measure temperature by the change of resistance value with temperature. Humidity sensing unit: including capacitive humidity sensor and resistive humidity sensor, used to measure the humidity in the tunnel. Capacitive humidity sensor measures humidity by the change of capacitance due to the change of dielectric constant with humidity, and resistive humidity sensor measures humidity by the change of resistance of humidity-sensitive material. Dust sensing unit: including optical particle sensor and laser scattering sensor, used to monitor the dust content in the tunnel. The optical particle sensor measures the particle concentration through the principle of light scattering, and the laser scattering sensor measures the dust concentration through the scattered light intensity of the laser beam and the particles. Wind speed sensing unit: includes ultrasonic wind speed sensor and hot wire anemometer, which are used to measure the wind speed in the tunnel. The ultrasonic wind speed sensor determines the wind speed by measuring the change in the propagation speed of ultrasonic waves in the air, and the hot wire anemometer measures the wind speed by measuring the change in heat dissipation of the heated hot wire in the air flow.

3. A tunnel fan energy-saving control system according to claim 2, characterized in that: The intelligent evaluation module includes a data acquisition unit, a data processing unit and a demand calculation unit; wherein: Data acquisition unit: used to receive and store monitoring data from the gas concentration sensing unit, temperature sensing unit, humidity sensing unit, dust sensing unit and wind speed sensing unit; Data processing unit: used to pre-process the received monitoring data, including data filtering, denoising and standardization, to ensure the accuracy and consistency of the data; Demand calculation unit: Based on the pre-processed monitoring data, according to the preset calculation model, it comprehensively analyzes the gas concentration, temperature, humidity, dust content and wind speed, calculates the current ventilation demand, and transmits the calculation results to the dynamic prediction module.

4. A tunnel fan energy-saving control system according to claim 3, characterized in that: The demand calculation unit specifically includes: Select calculation model: The preset calculation model specifically adopts a multi-factor weighted model, which is used to assign different weights to each monitoring parameter and comprehensively calculate the ventilation demand; the calculation formula is: Where V is the required ventilation volume, w i is the weight of the i-th parameter, P i is the measured value of the i-th parameter, and n is the total number of parameters; Gas concentration calculation: Evaluate air quality based on the monitored harmful gas concentration, and perform weighted calculation based on the degree of harm of different gases; the formula is: Among them, C wighted is the weighted gas concentration, k j is the weight of the jth gas, C j is the measured concentration of the jth gas, and m is the total number of gas types; Comprehensive analysis: Combining the parameters of gas concentration, temperature, humidity, dust content and wind speed, the overall ventilation demand is calculated through a multi-factor weighted model. The specific formula is: V total =a×C weighted +b×T+c×H+d×D+e×W, where V total is the ventilation demand after comprehensive calculation, C weighted is the weighted gas concentration, T is the temperature, H is the humidity, D is the dust content, W is the wind speed, and a, b, c, d and e are the weight coefficients of each parameter.

5. The tunnel fan energy-saving control system according to claim 1, characterized in that: The dynamic prediction module includes a historical data storage unit, a real-time data acquisition unit, a deep learning unit and a prediction analysis unit; wherein: Historical data storage unit: used to store historical monitoring data and evaluation results obtained from the multi-parameter sensing module and the intelligent evaluation module as training data for deep learning; Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the current real-time monitoring data and evaluation results as input data for predictive analysis; Deep learning unit: connected to the historical data storage unit and the real-time data acquisition unit, used to train the historical data, adopt a recursive neural network model, learn the time series pattern of the changes of various parameters in the tunnel, and generate a prediction model; Predictive analysis unit: connected with the deep learning unit, it applies the prediction model generated after training and combines it with real-time data to predict ventilation demand in the future.

6. A tunnel fan energy-saving control system according to claim 5, characterized in that: The deep learning unit comprises: Data preprocessing: standardize the data in the historical data storage unit; Construct a recursive neural network model: Construct a recursive neural network model including an input layer, several hidden layers and an output layer. The output of each hidden layer is transformed nonlinearly through an activation function. The activation function is a hyperbolic tangent function with the formula: h t =tanh(W h ·h t-1 +W x ·x t +b), where h t is the hidden state of the current time step, h t-1 is the hidden state of the previous time step, W h and W x are the weight matrices for hidden states and inputs, respectively, x t is the input of the current time step, and b is the bias term; Model training: Use the training data to train the model through the back propagation algorithm and calculate the loss function. The formula is: Among them, L is the loss function, N is the number of samples, and y i is the true value, is the predicted value; the model parameters are updated by the gradient descent method, and the formula is: Among them, θ is the model parameter, η is the learning rate, is the gradient of the loss function with respect to the model parameters; Model validation: Use the validation dataset to evaluate the performance of the trained model; the recurrent neural network prediction model after training is represented as: in, is the predicted value after k time steps in the future, f θ is the trained recurrent neural network model, x t is the input data of the current time step t, h t-1 is the hidden state of the previous time step, and θ is the model parameter.

7. The tunnel fan energy-saving control system according to claim 1, characterized in that: The energy-saving optimization module includes a prediction data receiving unit, a real-time data acquisition unit, an optimization algorithm unit and a control instruction generation unit; wherein: Prediction data receiving unit: used to receive the ventilation demand prediction result within a period of time in the future provided by the dynamic prediction module; Real-time data acquisition unit: connected with the multi-parameter sensing module and the intelligent evaluation module to obtain the real-time environmental data and immediate ventilation needs in the current tunnel; Optimization algorithm unit: connected to the prediction data receiving unit and the real-time data acquisition unit, used to comprehensively analyze the prediction results and real-time data, and calculate the optimal wind turbine operation strategy through the optimization algorithm; Control instruction generation unit: used to generate control instructions according to the optimal fan operation strategy output by the optimization algorithm unit, and send it to the frequency conversion control module, specifically converting the fan operation parameters calculated by the optimization algorithm unit into control signals; the generated control instructions specifically include the start, stop, speed regulation and frequency regulation operations of the fan.

8. A tunnel fan energy-saving control system according to claim 7, characterized in that: The optimization algorithm unit specifically includes: Step 1: Based on the current ventilation demand V calculated by the demand calculation unit total And the future ventilation demand V predicted by the dynamic prediction module predicted , construct optimization objectives and constraints; Step 2: Use a linear programming algorithm with minimizing energy consumption as the objective function. The specific constraints include meeting current and predicted ventilation needs, the operating range of the fan, and the safety standards of the system. The mathematical expression of the optimization problem is: Among them, P t is the fan power at time step t, Δt is the time step length, and the goal is to minimize the total energy consumption while meeting the ventilation requirements; the constraints include: V real-time ≤V total ≤V max , where V real-time For real-time needs, V total To optimize the calculated demand, V max is the maximum ventilation volume of the fan; Step 3: Comprehensive forecast of future ventilation demand V predicted To optimize, the formula is: V optimized =α×V total +β×V predicted , where V optimized is the optimized ventilation demand, α and β are weight coefficients used to balance the current demand and the future predicted demand; Step 4: Based on the optimized ventilation requirement V optimized , calculate the optimal fan operating parameters, the specific formula is: Among them, f optimal is the optimized fan frequency, f max is the maximum frequency of the fan, V optimized For the optimized ventilation requirement, V max is the maximum ventilation volume of the fan, P optimal is the optimized fan power, P max is the maximum power of the fan.

9. The tunnel fan energy-saving control system according to claim 1, characterized in that: The frequency conversion control module includes a control signal receiving unit, a frequency conversion unit and a speed adjustment unit; wherein: Control signal receiving unit: used to receive the generated control instructions, including the start, stop, speed regulation and frequency regulation operations of the fan; Frequency conversion unit: connected to the control signal receiving unit, used to adjust the power supply frequency of the fan according to the received control command. The frequency conversion unit converts the frequency of the AC power supply into the predetermined frequency required by the fan through frequency conversion technology to control the speed of the fan; Speed ​​regulating unit: used to adjust the speed of the fan according to the converted frequency signal. The speed regulating unit adjusts the input voltage and current of the fan motor through the frequency converter, thereby changing the speed of the fan.

10. The tunnel fan energy-saving control system according to claim 1, characterized in that: The alarm emergency module includes a gas monitoring unit, an alarm issuing unit and an emergency ventilation control unit; wherein: Gas monitoring unit: connected to the multi-parameter sensor module, used to monitor the concentration of harmful gases in the tunnel in real time. The gas monitoring unit has a preset safety threshold. Once any harmful gas concentration exceeding the preset threshold is detected, it is judged as an abnormal situation; Alarm issuing unit: connected to the gas monitoring unit, used to immediately activate the alarm device when the gas monitoring unit detects that the concentration of harmful gas exceeds the standard. The alarm device includes sound alarm and light signal alarm, which are used to issue warnings to tunnel operators and monitoring center; Emergency ventilation control unit: used to automatically adjust the fan operation strategy after receiving an alarm that the concentration of harmful gases exceeds the standard. Specifically, according to the preset emergency response procedure, the ventilation volume is quickly increased to reduce the concentration of harmful gases in the tunnel to a safe level.

Images