Tunnel ventilation and illumination intelligent control method based on wireless transmission technology

Abstract

The invention discloses a tunnel ventilation and illumination intelligent control method based on a wireless transmission technology, and belongs to the field of intelligent environment control. The system collects tunnel environment data in real time through uniformly deploying wireless sensors, acoustic sensor arrays and industrial cameras, and uploads the tunnel environment data to a cloud end through a LoRaWAN protocol for Kalman filtering noise reduction and anomaly detection. A fuzzy PID algorithm is adopted for ventilation control, the fan rotating speed is dynamically adjusted according to the gas concentration error, and the response time is shortened; according to the illumination control, the personnel position, the illumination deviation and the area priority are fused through an adaptive weighting algorithm, and a pulse width modulation signal is generated to drive illumination equipment. The acoustic data is used for equipment fault pre-diagnosis and rockburst risk early warning based on spectral analysis. The system integrates an edge calculation model to predict the gas diffusion trend, and supports a three-dimensional visual human-computer interaction interface. Actual measurement shows that the method still keeps high robustness in a complex noise environment, and is suitable for intelligent management of tunnel construction and operation scenes.

Description

Technical Field

[0001] This invention relates to the field of automatic control, and more specifically to an intelligent control method for tunnel ventilation and lighting based on wireless transmission technology. Background Technology

[0002] Construction ventilation is a crucial step in tunnel construction and a key factor in ensuring safe tunnel operation. To address ventilation control during the construction phase, a variable frequency ventilation system based on a fuzzy controller has been designed. This system uses a fuzzy controller to calculate the control voltage based on the pollution level at the tunnel construction face, thereby controlling the ventilation volume and achieving energy savings and efficiency improvements.

[0003] As can be seen from the above technologies, current tunnel ventilation systems typically rely on fieldbus communication for sensor data acquisition and transmission. In such network communication, data packet transmission delays, instantaneous errors and data packet loss in the communication system, and inconsistencies in the order of sending and receiving data all undermine the determinism inherent in traditional control systems, making the analysis and synthesis of control systems more complex and negatively impacting the performance of the control systems. Summary of the Invention

[0004] To address the aforementioned shortcomings in the existing technology, this invention provides a method for intelligent control of tunnel ventilation and lighting based on wireless transmission technology.

[0005] To achieve the above-mentioned objectives, the technical solution adopted by this invention is as follows:

[0006] A method for intelligent control of tunnel ventilation and lighting based on wireless transmission technology includes the following steps:

[0007] S1. Construct a tunnel environment data acquisition system, including gas sensors, oxygen sensors, carbon monoxide sensors, methane sensors, light intensity sensors, acoustic sensor arrays and industrial cameras evenly distributed in various areas of the tunnel. Collect gas concentration data, light intensity data, acoustic data and personnel location information in real time through wireless transmission via an Internet of Things module.

[0008] S2. Upload the data collected in S1 to the cloud server for storage and preprocessing via IoT transmission device, and receive the data sent from the cloud via PLC logic controller;

[0009] S3. In the ventilation control subsystem, based on the preset gas concentration threshold and the real-time collected gas concentration data, the fan speed adjustment is dynamically calculated through the fuzzy PID control algorithm, and the control command is sent to the fan controller wirelessly.

[0010] S4. In the lighting control subsystem, based on the personnel location information and light intensity data obtained by the industrial camera, the target value of lighting brightness for each area is calculated by an adaptive weighting algorithm, and the control command is sent to the lighting controller wirelessly.

[0011] S5. The tunnel environment parameters, acoustic warning information and equipment operating status are displayed in real time through the human-machine interface, and remote parameter configuration and intervention are performed.

[0012] Furthermore, the data preprocessing in S2 includes:

[0013] S21. Perform Kalman filtering noise reduction on the sensor data. The filtering equation is:

[0014] ;

[0015] In the formula, for State estimate at time 10:00 for External control input signal at any time, for The observed value at time, for Moment-time Kalman gain, For the system matrix;

[0016] S22. Time series analysis is used to detect data anomalies. If data from N consecutive periods exceeds the standard deviation... If the range is reached, an alarm will be triggered and redundant sensor data will be enabled;

[0017] S23. Preprocess and extract features from the audio data collected by the acoustic sensor array.

[0018] Furthermore, step S23 specifically includes the following steps:

[0019] S231. Perform frame segmentation and windowing on the audio signal, and calculate the Fast Fourier Transform of each frame to obtain the spectrum:

[0020] ;

[0021] In the formula, It is a discrete audio signal. For window functions, For frame length, For frequency spectral components at the location;

[0022] S232, Calculate a specific frequency band The ratio of energy stations within the area is used as a characteristic value, and the specific calculation method is as follows:

[0023] ;

[0024] In the formula, For the sampling frequency, when An abnormal sound event warning is triggered when the dynamic threshold is exceeded continuously.

[0025] Furthermore, the cloud server adopts an edge computing architecture and deploys a lightweight machine learning model to predict gas concentration diffusion trends. The prediction model is as follows:

[0026] ;

[0027] In the formula, for The gas concentration at time , For gas concentration at The Laplace operator at time t is used to calculate the tendency of gas to diffuse from a region of high concentration to a region of low concentration. To predict the step size, Where is the diffusion coefficient. For real-time wind speed, Airflow velocity influencing factors;

[0028] The edge computing architecture also deploys a voiceprint recognition model for identifying sound events in S232. This model is a convolutional neural network, and its convolutional layer operations are as follows:

[0029] ;

[0030] In the formula, This is the index of the current convolutional layer, representing the level in the neural network. For the first Layer output feature map at position The value, It is a non-linear activation function. This is the index of the input channel. These are the row and column offset indices of the convolution kernel in the spatial dimension, respectively. The order is number 1 The height and width of the convolution kernel. For the first The voiceprint image input by the layer. For the first Layer convolution kernel at position and channels The weight value, For the first Layer bias terms.

[0031] Furthermore, the fuzzy PID control algorithm in S3 specifically includes:

[0032] S31. Define gas concentration error and error change rate ,in, For the preset threshold, for Real-time concentration at any given moment;

[0033] S32. Design a fuzzy rule base, and adjust the PID parameters according to the membership function of the gas concentration error and its error transformation rate. The output is:

[0034] ;

[0035] In the formula, For controller output, For proportional gain, For integral gain, For time integrals, This is the differential gain;

[0036] S33, based on controller output Generate fan speed adjustment command ,in, As the reference speed, This is the adjustment coefficient.

[0037] Furthermore, the adaptive weighting algorithm in S4 is specifically as follows:

[0038] S41. Define personnel position weights Light intensity weight and regional priority weights And satisfy ;

[0039] S42. Calculate the target brightness. The specific calculation method is as follows:

[0040] ;

[0041] in, For the light of the goal, This is the brightness compensation value for densely populated areas. This is the compensation value for light intensity deviation. Preset priority brightness;

[0042] S43. Generate a pulse width modulation signal based on the target brightness to control the output power of the lighting equipment. The pulse width modulation signal is represented as follows:

[0043] ;

[0044] In the formula, It is a pulse width modulation signal. For the maximum brightness of the lighting equipment, For nonlinear compensation coefficients, As a dynamic response factor, This refers to dynamic brightness deviation.

[0045] Furthermore, the personnel location weights Light intensity weight and regional priority weights For dynamic adjustment, the specific rules are as follows:

[0046] When the personnel density exceeds a set threshold, the weight of personnel location is increased. Reduce the weight of light intensity ;

[0047] When the light intensity deviation exceeds the set threshold, the light intensity weight is increased. Reduce regional priority weight ;

[0048] When the tunnel area is the core construction zone, the priority weight of the fixed area is determined. .

[0049] Furthermore, the IoT module uses the LoRaWAN protocol for data transmission, and its dynamic transmission power meets the following requirements:

[0050] ;

[0051] In the formula, For dynamic output power, As the reference power, This is the path loss index. For transmission distance, This is an environmental noise correction item.

[0052] Furthermore, the human-computer interaction interface in S5 supports multi-dimensional data visualization, including:

[0053] S51. Display a real-time 3D map of the tunnel and mark sensor locations, environmental parameters, and equipment status;

[0054] S52. Generate historical data trend curves and alarm logs, supporting filtering by time, region, and parameter type;

[0055] S53. Receive remote control commands through an encrypted communication protocol and execute them after verifying operation permissions.

[0056] The present invention has the following beneficial effects:

[0057] The IoT-based wireless transmission intelligent control system for tunnel ventilation and lighting combines industrial vision, voiceprint, IoT and PLC logic control, which eliminates the limitations of traditional wired data acquisition in terms of acquisition distance, greatly reduces the number of CPUs used in the control, and saves labor and material costs for laying communication cables during sensor installation. Attached Figure Description

[0058] Figure 1 This is a schematic diagram of the intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to the present invention. Detailed Implementation

[0059] The specific embodiments of the present invention are described below to enable those skilled in the art to understand the present invention. However, it should be understood that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, various changes are obvious as long as they are within the spirit and scope of the present invention as defined and determined by the appended claims. All inventions utilizing the concept of the present invention are protected.

[0060] A method for intelligent control of tunnel ventilation and lighting based on wireless transmission technology, such as Figure 1 As shown, it includes the following steps:

[0061] S1. Construct a tunnel environment data acquisition system, including gas sensors, oxygen sensors, carbon monoxide sensors, methane sensors, light intensity sensors and industrial cameras evenly distributed in various areas of the tunnel. Collect gas concentration data, light intensity data and personnel location information in real time through wireless transmission via an Internet of Things module.

[0062] In this embodiment, sensors are deployed evenly within the tunnel, including gas, oxygen, carbon monoxide, and methane sensors (range 0-5% vol, accuracy ±0.1%), a light intensity sensor (range 0-65535 lux), and an acoustic sensor array (microphone frequency response range 20Hz-12kHz, sensitivity -36±3dB). A group of nodes is set every 50 meters. An infrared camera (1080P resolution) is used to detect personnel location and density. Wireless transmission is achieved by uploading data to the cloud in real time via a LoRaWAN module (868MHz band, transmission distance ≥2km).

[0063] S2. The data collected in S1 is uploaded to the cloud server for storage and preprocessing via IoT transmission equipment, and the data sent from the cloud is received by the PLC logic controller.

[0064] In this embodiment, the preprocessing includes the following steps:

[0065] S21. Perform Kalman filtering noise reduction on the sensor data. The filtering equation is:

[0066] ;

[0067] In the formula, for State estimate at time 10:00 for External control input signals at any given time, such as fan speed regulation. for The observed value at time, for Moment-time Kalman gain, This is the system matrix. In this embodiment, the matrix... It can be a control input matrix, which converts control signals... The physical effects are mapped to the system state. In the middle. For example, if Indicates the oxygen concentration inside the tunnel For the fan speed increment, then This item describes the dilution effect of the fan on the oxygen concentration. In ventilation control, It can be a fan speed adjustment command output by a fuzzy PID controller; in lighting control, This can represent the PWM duty cycle adjustment signal. If This represents a gas concentration vector (e.g., [O2, CH4)). T (unit: % vol), then the matrix The dimensions need to be consistent with Dimensional matching. For example, If the fan speed is a scalar value (rpm), then It is a 2×1 matrix, representing the combined effect coefficient of rotational speed on oxygen and methane concentration.

[0068] S22. Use time series analysis to detect data anomalies. If the data exceeds the standard deviation σ range for N consecutive periods, trigger an alarm and enable redundant sensor data.

[0069] In this embodiment, the cloud server adopts an edge computing architecture and deploys a lightweight machine learning model to predict the gas concentration diffusion trend. The prediction model is as follows:

[0070] ;

[0071] In the formula, for The gas concentration at time , For gas concentration at The Laplace operator at time t is used to calculate the tendency of gas to diffuse from a region of high concentration to a region of low concentration. For real-time wind speed, This is an influencing factor on airflow velocity.

[0072] S23. Acoustic Preprocessing: Edge computing nodes segment the acoustic data into frames with a frame length N=1024 and a frame shift of 512. Hamming windowing is applied, and the FFT spectrum is calculated using the formula. The 3kHz-8kHz high-frequency band is the key monitoring area, as it represents a common frequency band for equipment faults. The 50Hz-200Hz low-frequency band is the characteristic frequency band for rock mass fracture. Energy percentage Set an adaptive threshold. Its initial value is set as the 95th quantile of the historical energy distribution of this frequency band, when If the sound continues for more than 5 seconds, it is marked as an abnormal sound event, and the audio data segment is compressed and uploaded to the cloud voiceprint model for accurate classification.

[0073] The voiceprint recognition model employs a lightweight convolutional neural network (CNN) architecture. Its input is a 256th-order log-Melogram spectrogram, and the convolutional layer operations are as follows:

[0074] ;

[0075] In the formula, This is the index of the current convolutional layer, representing the level in the neural network. For the first Layer output feature map at position The value, It is a non-linear activation function. This is the index of the input channel. These are the row and column offset indices of the convolution kernel in the spatial dimension, respectively. The order is number 1 The height and width of the convolution kernel. For the first The voiceprint image input by the layer. For the first Layer convolution kernel at position and channels The weight value, For the first Layer bias terms.

[0076] The first convolutional layer uses the following dimensions. convolution kernel Feature extraction and activation function ReLU is employed. Training is performed using historical equipment failure audio samples in the cloud, enabling the system to distinguish between common mechanical failure sounds such as wind turbine imbalance, misalignment, and bearing damage, as well as the low-frequency rumbling sound of rock fracturing, achieving an accuracy rate of over 85%. The classification results will be displayed in a three-level alarm system on the human-machine interface: red (high risk - rockburst), orange (medium risk - equipment failure), and yellow (low risk - requires attention), along with suggested maintenance measures.

[0077] S3. In the ventilation control subsystem, based on the preset gas concentration threshold and the real-time collected gas concentration data, the fan speed adjustment is dynamically calculated through the fuzzy PID control algorithm, and the control command is sent to the fan controller wirelessly.

[0078] This embodiment specifically includes the following steps:

[0079] The fuzzy PID control algorithm specifically includes:

[0080] S31. Define gas concentration error and error change rate ,in, For the preset threshold, for Real-time concentration at any given moment.

[0081] S32. Design a fuzzy rule base and adjust the PID parameters based on the membership function of the gas concentration error and its error transformation rate.

[0082] In this embodiment, the fuzzy rule base is based on error. and error change rate Fuzzy set partitioning, dynamically adjusting PID parameters through If-Then logic. and For example, the fuzzy set of numerical variables is defined as:

[0083] error : Negative Big (NB), Negative Small (NS), Zero (ZO), Positive Small (PS), and Positive Big (PB);

[0084] Error rate of change: negative fast (NF), negative slow (NS), zero (ZO), positive slow (PS), positive fast (PF).

[0085] Output variables and The adjustment strategy is as follows:

[0086] The proportional effect is enhanced based on the magnitude of the error;

[0087] Adjust the integral action according to the rate of error accumulation;

[0088] Adjust the differential action according to the rate of change of error.

[0089] The specific rule base design is shown in Table 1 below:

[0090] Table 1 Fuzzy Rule Base

[0091]

[0092] Its output is:

[0093] ;

[0094] In the formula, For controller output, For proportional gain, For integral gain, For time integrals, This is the differential gain.

[0095] S33, based on controller output Generate fan speed adjustment command ,in, As the reference speed, This is the adjustment coefficient.

[0096] The reference speed is the basic speed of the fan when there is no control signal, set according to the tunnel ventilation requirements or equipment specifications. For example, it is the safe speed to maintain the minimum ventilation volume. The adjustment coefficient is a proportional factor that converts the controller output u(t) into the actual speed adjustment, used to adapt to the dynamic characteristics or operating conditions of different fans. If u(t) is a voltage signal, α represents the speed increment per volt. The final calculated fan speed command is generated by superimposing the reference speed and the control signal, and must be limited within the maximum / minimum allowable speed range of the fan.

[0097] S4. In the lighting control subsystem, based on the personnel location information and light intensity data obtained by the industrial camera, the target value of lighting brightness for each area is calculated through an adaptive weighting algorithm, and the control command is sent to the lighting controller wirelessly.

[0098] In this embodiment, the adaptive weighting algorithm is specifically as follows:

[0099] S41. Define personnel position weights Light intensity weight and regional priority weights And satisfy ;

[0100] S42. Calculate the target brightness. The specific calculation method is as follows:

[0101] ;

[0102] in, For the light of the goal, This is the brightness compensation value for densely populated areas. This is the compensation value for light intensity deviation. Preset priority brightness.

[0103] Personnel position weight Light intensity weight and regional priority weights For dynamic adjustment, the specific rules are as follows:

[0104] When the personnel density exceeds a set threshold, the weight of personnel location is increased. Reduce the weight of light intensity ;

[0105] When the light intensity deviation exceeds the set threshold, the light intensity weight is increased. Reduce regional priority weight ;

[0106] When the tunnel area is the core construction zone, the priority weight of the fixed area is determined. .

[0107] S43. Generate a pulse width modulation signal based on the target brightness to control the output power of the lighting equipment. The pulse width modulation signal is represented as follows:

[0108] ;

[0109] In the formula, It is a pulse width modulation signal. For the maximum brightness of the lighting equipment, For nonlinear compensation coefficients, As a dynamic response factor, This refers to dynamic brightness deviation.

[0110] In this embodiment, the core item The target brightness is linearly mapped to the duty cycle range (0%~100%) to ensure that the brightness requirement directly drives the PWM signal. For example, if , Then the basic duty cycle is 60%.

[0111] The brightness of actual lighting fixtures, such as LEDs, may have an exponential or logarithmic relationship with the duty cycle. It is necessary to calibrate the linear model through η. If the measured duty cycle is 60%, the actual brightness is 280 lux (lower than the theoretical value of 300 lux), then η=1.07 is set to compensate for nonlinear losses.

[0112] When people suddenly enter the area ( Or a sudden drop in light ( ),pass Increase the duty cycle adjustment range to improve response speed. For example, if κ=0.1, Then the dynamic correction term is 0.1⋅0.2=0.02, and the duty cycle increases by an additional 2%.

[0113] The PWM signal expression, by combining target brightness calculation, nonlinear compensation, and dynamic response correction, achieves precise control of the lighting system. The parameter design considers both theoretical models and actual operating conditions, ensuring efficient and stable operation of the system in both static and dynamic scenarios.

[0114] S5. The tunnel environment parameters and equipment operating status are displayed in real time through the human-machine interface, and remote parameter configuration and intervention are performed.

[0115] In this embodiment, a 3D map of the tunnel is constructed based on WebGL technology, sensor data is labeled in real time, and historical curves can be viewed by clicking. At the same time, the AES-256 encryption protocol is used, and remote commands need to pass two-factor authentication. In the test, the illegal intrusion attempt interception rate was 100%.

[0116] Specific embodiments have been used to illustrate the principles and implementation methods of this invention. The descriptions of the embodiments above are only for the purpose of helping to understand the method and core ideas of this invention. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this invention. Therefore, the content of this specification should not be construed as a limitation of this invention.

[0117] Those skilled in the art will recognize that the embodiments described herein are intended to help the reader understand the principles of the invention, and should be understood that the scope of protection of the invention is not limited to such specific statements and embodiments. Those skilled in the art can make various other specific modifications and combinations based on the technical teachings disclosed in this invention without departing from the spirit of the invention, and these modifications and combinations are still within the scope of protection of this invention.

Claims

1. A method for intelligent control of tunnel ventilation and lighting based on wireless transmission technology, characterized in that, Includes the following steps: S1. Construct a tunnel environment data acquisition system, including gas sensors, oxygen sensors, carbon monoxide sensors, methane sensors, light intensity sensors, acoustic sensor arrays and industrial cameras evenly distributed in various areas of the tunnel. Collect gas concentration data, light intensity data, acoustic data and personnel location information in real time through wireless transmission via an Internet of Things module. S2. Upload the data collected in S1 to the cloud server for storage and preprocessing via IoT transmission device, and receive the data sent from the cloud via PLC logic controller; S3. In the ventilation control subsystem, based on the preset gas concentration threshold and the real-time collected gas concentration data, the fan speed adjustment is dynamically calculated through the fuzzy PID control algorithm, and the control command is sent to the fan controller wirelessly. S4. In the lighting control subsystem, based on the personnel location information and light intensity data obtained by the industrial camera, the target value of lighting brightness for each area is calculated by an adaptive weighting algorithm, and the control command is sent to the lighting controller wirelessly. S5. The tunnel environment parameters, acoustic warning information and equipment operating status are displayed in real time through the human-machine interface, and remote parameter configuration and intervention are performed.

2. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, The data preprocessing in S2 includes: S21. Perform Kalman filtering noise reduction on the sensor data. The filtering equation is: ； In the formula, for State estimate at time 10:00 for External control input signal at any time, for The observed value at time, for Moment Kalman gain, For the system matrix; S22. Time series analysis is used to detect data anomalies. If data from N consecutive periods exceeds the standard deviation... If the range is reached, an alarm will be triggered and redundant sensor data will be enabled; S23. Preprocess and extract features from the audio data collected by the acoustic sensor array.

3. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, S23 specifically includes the following steps: S231. Perform frame segmentation and windowing on the audio signal, and calculate the Fast Fourier Transform of each frame to obtain the spectrum: ； In the formula, It is a discrete audio signal. For window functions, For frame length, For frequency spectral components at the location; S232, Calculate a specific frequency band The ratio of energy stations within the area is used as a characteristic value, and the specific calculation method is as follows: ； In the formula, For the sampling frequency, when An abnormal sound event warning is triggered when the dynamic threshold is exceeded continuously.

4. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 3, characterized in that, The cloud server employs an edge computing architecture and deploys a lightweight machine learning model to predict gas concentration diffusion trends. The prediction model is as follows: ； In the formula, for The gas concentration at time , For gas concentration at The Laplace operator at time t is used to calculate the tendency of gas to diffuse from a region of high concentration to a region of low concentration. To predict the step size, Where is the diffusion coefficient. For real-time wind speed, Factors affecting airflow velocity; The edge computing architecture also deploys a voiceprint recognition model for identifying sound events in S232. This model is a convolutional neural network, and its convolutional layer operations are as follows: ； In the formula, This is the index of the current convolutional layer, representing the level in the neural network. For the first Layer output feature map at position The value, It is a non-linear activation function. This is the index of the input channel. These are the row and column offset indices of the convolution kernel in the spatial dimension, respectively. The order is number 1 The height and width of the convolution kernel. For the first The voiceprint image input by the layer. For the first Layer convolution kernel at position and channels The weight value, For the first Layer bias terms.

5. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, The fuzzy PID control algorithm in S3 specifically includes: S31. Define gas concentration error and error change rate ,in, For the preset threshold, for Real-time concentration at any given moment; S32. Design a fuzzy rule base, and adjust the PID parameters according to the membership function of the gas concentration error and its error transformation rate. The output is: ； In the formula, For controller output, For proportional gain, For integral gain, For time integral, This is the differential gain; S33, based on controller output Generate fan speed adjustment command ,in, As the reference speed, This is the adjustment coefficient.

6. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, The adaptive weighting algorithm in S4 is specifically as follows: S41. Define personnel position weights Light intensity weight and regional priority weights And satisfy ; S42. Calculate the target brightness. The specific calculation method is as follows: ； in, For the light of the goal, This is the brightness compensation value for densely populated areas. This is the compensation value for light intensity deviation. Preset priority brightness; S43. Generate a pulse width modulation signal based on the target brightness to control the output power of the lighting equipment. The pulse width modulation signal is represented as follows: ； In the formula, It is a pulse width modulation signal. For the maximum brightness of the lighting equipment, For nonlinear compensation coefficients, As a dynamic response factor, This refers to dynamic brightness deviation.

7. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 6, characterized in that, Personnel location weight Light intensity weight and regional priority weights For dynamic adjustment, the specific rules are as follows: When the personnel density exceeds a set threshold, the weight of personnel location is increased. Reduce the weight of light intensity ; When the light intensity deviation exceeds the set threshold, the light intensity weight is increased. Reduce regional priority weight ; When the tunnel area is the core construction zone, the priority weight of the fixed area is determined. .

8. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, The IoT module uses the LoRaWAN protocol for data transmission, and its dynamic transmission power meets the following requirements: ； In the formula, For dynamic output power, As the reference power, This is the path loss index. For transmission distance, This is an environmental noise correction item.

9. The intelligent control method for tunnel ventilation and lighting based on wireless transmission technology according to claim 1, characterized in that, The human-computer interaction interface in S5 supports multi-dimensional data visualization, including: S51. Display a real-time 3D map of the tunnel and mark sensor locations, environmental parameters, and equipment status; S52. Generate historical data trend curves and alarm logs, supporting filtering by time, region, and parameter type; S53. Receive remote control commands through an encrypted communication protocol and execute them after verifying operation permissions.

Images