Polluted site high-precision in-situ monitoring method and system driven by optical fiber sensing technology

Abstract

The invention relates to the technical field of optical fiber sensing, in particular to a polluted site high-precision in-situ monitoring method and system driven by the optical fiber sensing technology, and the method comprises the following steps: 1, outputting optical signals by adopting an argon ion laser or a semiconductor laser, the output optical signals comprise two monochromatic lights with different wavelengths, namely lambda1 and lambda2, one part of the light enters the optical fiber transmission system through the coupler, the other part of the light enters the calibration box to serve as reference light intensity to calibrate the input light intensity, and the reference light intensity is I lambda 1, 0 and I lambda 2, 0; according to the invention, the optical fiber sensing technology is combined with the differential absorption spectrometry, online continuous monitoring is realized, the real-time performance and accuracy of data are improved, and meanwhile, environmental parameters are acquired in real time by arranging the optical fiber Bragg grating temperature and humidity sensor and the particulate matter and wind speed sensor; and the AI error correction module and the pollution compensation factor are utilized to dynamically compensate the data, so that errors caused by environmental interference are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of optical fiber sensing, and specifically to a high-precision in-situ monitoring method and system for contaminated sites driven by optical fiber sensing technology. Background Art

[0002] High-precision in-situ monitoring of contaminated sites driven by optical fiber sensing technology is a real-time detection method for environmental pollutants based on optical principles, which realizes in-situ, dynamic, and multi-dimensional monitoring of pollutants through an optical fiber sensor network;

[0003] Its core is to use a laser to emit an optical signal with a specific wavelength, which is transmitted through an optical fiber to the sensing probe at the contaminated site. Based on the differential absorption spectrum characteristics of gas molecules, the concentration of pollutants is retrieved by measuring the attenuation degree of the optical intensity.

[0004] Existing methods usually adopt off-line sampling or laboratory analysis, which are difficult to achieve real-time and in-situ monitoring of industrial emission areas and traffic pollution areas. Moreover, environmental parameters such as temperature, humidity, particulate matter concentration, and air flow velocity have a great influence on the optical signal and the absorption characteristics of pollutants, resulting in large measurement errors of traditional monitoring methods under complex working conditions. Therefore, in view of the above problems, a high-precision in-situ monitoring method and system for contaminated sites driven by optical fiber sensing technology are proposed. Summary of the Invention

[0005] The purpose of the present invention is to provide a high-precision in-situ monitoring method and system for contaminated sites driven by optical fiber sensing technology, so as to solve the problems that existing methods usually adopt off-line sampling or laboratory analysis, which are difficult to achieve real-time and in-situ monitoring of industrial emission areas and traffic pollution areas, and environmental parameters such as temperature, humidity, particulate matter concentration, and air flow velocity have a great influence on the optical signal and the absorption characteristics of pollutants, resulting in large measurement errors of traditional monitoring methods under complex working conditions.

[0006] To achieve the above purpose, the present invention provides the following technical solutions:

[0007] A high-precision in-situ monitoring method and system for contaminated sites driven by optical fiber sensing technology, comprising the following steps:

[0008] Step 1: Use an argon ion laser or a semiconductor laser to output an optical signal, the output optical signal includes two monochromatic lights with different wavelengths, namely λ1 and λ2. Part of the light enters the optical fiber transmission system through a coupler, and the other part of the light enters a calibration box as a reference optical intensity for calibrating the input optical intensity. The reference optical intensity is I λ1,0 and I λ2,0 ;

[0009] Step 2: The optical fiber transmission system transmits the optical signal to the sensor head of the contaminated site to be measured. Inside the sensor head, the light of two wavelengths interacts with the contaminated gas. Based on the differential absorption characteristics of the gas, the light of different wavelengths is selectively absorbed by the contaminated gas;

[0010] Step 3: The light after being absorbed by the contaminated gas is transmitted to the signal processing unit through the output optical fiber, and the output light intensity is I λ1 and I λ2 , and then calculate the gas concentration, and then output the concentration data of the pollutant in real time;

[0011] Step 4: Calculate the concentration of the pollutant by using the differential absorption spectroscopy method, and optimize the data accuracy through AI error correction. The calculation formula of the pollutant concentration C is:

[0012]

[0013] In the formula, ln is the natural logarithm, I λ1,0 and I λ2,0 are the reference light intensities of wavelengths λ1 and λ2 respectively, I λ1 and I λ2 are the output light intensities of wavelengths λ1 and λ2 respectively, α λ1 and α λ2 are the gas absorption coefficients of the pollutant at λ1 and λ2 respectively, L is the optical path length, and K corr is the pollutant compensation factor calculated by AI.

[0014] As a further optimized content of the present invention, wherein: the calculation process of the pollutant compensation factor K corr is as follows:

[0015] S1: Environmental data acquisition: The fiber Bragg grating sensor, particulate matter sensor, and wind speed sensor devices collect environmental parameters, and the collected environmental parameters include temperature, humidity, PM2.5 and PM10 concentrations, and air flow velocity;

[0016] S2: Error modeling training: Use big data to train the AI model and calculate the optimal value of the regression coefficient based on historical error data;

[0017] S3: Real-time compensation: During the actual measurement process, substitute the collected environmental parameters into the formula to calculate the pollutant compensation factor K corr and correct the calculated value of the pollutant concentration.

[0018] As a further optimized content of the present invention, wherein: the calculation formula of the pollutant compensation factor K corr is:

[0019] K corr = 1 + β1T + β2H + β3PM 2.5+β4PM 10 +β5V

[0020] Wherein, T is the ambient temperature, H is the ambient humidity, PM 2.5 and PM 10 are the concentrations of PM2.5 and PM10 particles in the air, V is the air flow velocity, and β1, β2, β3, β4, β5 are the regression coefficients obtained from AI training and are fitted according to historical measurement data.

[0021] As a further optimization content of the present invention, wherein: the steps of the error modeling training are as follows:

[0022] A1: Data collection: Measure the true pollutant concentration C meas and the reference measurement value C true under different temperature, humidity, air flow velocity and particulate matter concentration conditions;

[0023] A2: Calculate the error according to the measured true pollutant concentration C true and the reference measurement value C meas . The error function is:

[0024] ΔC = C meas - C true

[0025] A3: Model training: According to the calculated error value ΔC, when the error reaches the minimum value, a pollutant compensation factor is obtained accordingly. Then, use the AI model to train to obtain β1, β2, β3, β4, β5, and the specific expression is:

[0026]

[0027] Use the least squares method, support vector regression, neural network or random forest regression for fitting.

[0028] As a further optimization content of the present invention, wherein: the fiber optic sensing head adopts an anti-pollution coating, the fiber optic sensing head is equipped with a fiber optic self-cleaning system, and the self-cleaning system uses ultrasonic oscillation or air flow purging for cleaning.

[0029] As a further optimization content of the present invention, wherein: the method includes using a fiber Bragg grating temperature and humidity sensor for temperature and humidity drift compensation to correct the error caused by environmental factor changes in the optical signal.

[0030] As a further optimization content of the present invention, wherein: the fiber optic sensing system adopts a multi-point distributed sensing structure to improve the spatial resolution of the polluted site and perform three-dimensional pollution concentration monitoring.

[0031] As a further optimized content of the present invention, wherein: the method combines an AI algorithm to perform real-time correction on measurement errors, and the input variables include monitoring time, humidity, PM2.5 and PM10 concentrations, and air flow velocity environmental parameters.

[0032] As a further optimized content of the present invention, wherein: it includes a laser emission module, which includes an argon ion laser or a semiconductor laser, and is used to output two monochromatic lights with different wavelengths, namely λ1 and λ2;

[0033] An optical path coupling module, which includes a coupler and a calibration box. The coupler inputs part of the light into the optical fiber transmission system, and the other part of the light into the calibration box as the reference light intensity I λ1,0 and I λ2,0 ;

[0034] An optical fiber transmission system, which is used to transmit the optical signal to the sensor head arranged in the pollution site to be measured. In the sensor head, the two-wavelength light has a selective absorption effect based on the differential absorption characteristics with the polluting gas;

[0035] A signal processing module, which receives the light intensity signals I λ1 and I λ2 after absorption by the polluting gas through the output optical fiber, and calculates the pollutant concentration;

[0036] An environmental parameter acquisition module, which includes a fiber Bragg grating sensor, a particulate matter sensor and an anemometer, and is used to collect the temperature T, humidity H, PM2.5 concentration P1, PM10 concentration P2 and air flow velocity V in real time;

[0037] An AI error correction module, which calculates the pollutant compensation factor by training the regression coefficient, and optimizes the model based on the historical error data by using the least squares method, support vector regression or neural network;

[0038] An anti-pollution sensing component, the surface of the sensor head is coated with an anti-pollution coating, and an ultrasonic oscillation or air flow purging self-cleaning system is integrated;

[0039] A distributed monitoring structure, which uses fiber optic sensor heads arranged in multiple points to form a three-dimensional sensing network, and combines with the signal processing module to realize spatial resolution monitoring of the pollution concentration.

[0040] Compared with the prior art, the beneficial effects of the present invention are:

[0041] 1. In the present invention, through the combination of fiber optic sensing technology and differential absorption spectroscopy, online continuous monitoring is realized, which improves the real-time performance and accuracy of data. At the same time, by arranging fiber Bragg grating temperature and humidity sensors, particulate matter and anemometers, environmental parameters are collected in real time, and the AI error correction module and pollution compensation factor are used to dynamically compensate the data, thereby reducing the errors caused by environmental interference;

[0042] 2. In the present invention, an anti-pollution coating and an optical fiber self-cleaning system are adopted to keep the surface of the sensing head clean, ensuring the long-term stable operation of the sensor. At the same time, by introducing Raman amplification technology and erbium-doped fiber amplifiers, the quality of long-distance signal transmission is improved, ensuring that the signal is strong enough and the noise is low during remote monitoring;

[0043] 3. In the present invention, a multi-point distributed sensing structure is adopted, and a data fusion algorithm is combined to achieve three-dimensional pollution concentration monitoring, greatly improving the spatial resolution and monitoring coverage;

[0044] 4. In the present invention, an error model based on big data and AI training is introduced to calculate the pollution compensation factor in real time, enabling the system to dynamically and adaptively correct measurement errors and improve the overall data accuracy. BRIEF DESCRIPTION OF THE DRAWINGS

[0045] Figure 1 is a system block diagram of the high-precision in-situ monitoring system for polluted sites driven by the optical fiber sensing technology of the present invention;

[0046] Figure 2 is a flowchart of the high-precision in-situ monitoring method for polluted sites driven by the optical fiber sensing technology of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0047] Please refer to Figure 1-2 , the present invention provides a technical solution:

[0048] A high-precision in-situ monitoring method and system for polluted sites driven by optical fiber sensing technology, comprising the following steps:

[0049] Step 1: An argon ion laser or a semiconductor laser is used to output an optical signal, and the output optical signal includes two monochromatic lights with different wavelengths, namely λ1 and λ2. A part of the light enters the optical fiber transmission system through a coupler, and the other part of the light enters a calibration box as a reference light intensity for calibrating the input light intensity. The reference light intensity is I λ1,0 and I λ2,0 ;

[0050] Step 2: The optical fiber transmission system transmits the optical signal to the sensing head of the polluted site to be measured. Inside the sensing head, the two-wavelength light interacts with the polluted gas. Based on the differential absorption characteristics of the gas, the light of different wavelengths is selectively absorbed by the polluted gas;

[0051] Step 3: The light after being absorbed by the polluted gas is transmitted to the signal processing unit through the output optical fiber, and the output light intensity is I λ1 and I λ2 , and then the gas concentration is calculated, and the concentration data of the pollutant is output in real time;

[0052] Step 4: Calculate the pollutant concentration using the differential absorption spectroscopy method and optimize the data accuracy through AI error correction. The calculation formula for the pollutant concentration C is as follows:

[0053]

[0054] In the formula, ln is the natural logarithm, I λ1,0 and I λ2,0 are the reference light intensities at wavelengths λ1 and λ2 respectively, I λ1 and I λ2 are the output light intensities at wavelengths λ1 and λ2 respectively, α λ1 and α λ2 are the gas absorption coefficients of the pollutant at λ1 and λ2 respectively, L is the optical path length, K corr is the pollutant compensation factor calculated by AI, realizing real-time on-line monitoring of pollutants. The background interference is effectively eliminated through the dual-wavelength differential absorption spectroscopy technology, and the signal is ensured to be stably transmitted over a long distance by combining optical fiber transmission.

[0055] As a further technical solution for the implementation of this scheme, the calculation process of the pollutant compensation factor K corr is as follows:

[0056] S1: Environmental data acquisition: The fiber Bragg grating sensor, particulate matter sensor, and wind speed sensor devices collect environmental parameters, including temperature, humidity, PM2.5 and PM10 concentrations, and air flow velocity.

[0057] S2: Error modeling training: Use big data to train the AI model and calculate the optimal value of the regression coefficient based on historical error data.

[0058] S3: Real-time compensation: During the actual measurement process, substitute the collected environmental parameters into the formula to calculate the pollutant compensation factor K corr and correct the calculated value of the pollutant concentration. Dynamically compensate for the measurement error through environmental parameters, significantly improving the concentration detection accuracy in complex environments and enabling the system to have the ability to adapt to environmental changes.

[0059] As a further technical solution for the implementation of this scheme, the calculation formula for the pollutant compensation factor K corr is as follows:

[0060] K corr = 1 + β11T + β2H + β3PM 2.5 + β4PM 10 + β5V

[0061] In the formula, T is the environmental temperature, H is the environmental humidity, PM 2.5 and PM 10Let \(C_{PM2.5}\) and \(C_{PM10}\) be the concentrations of PM2.5 and PM10 particles in the air, \(V\) be the air flow velocity, and \(\beta_1\), \(\beta_2\), \(\beta_3\), \(\beta_4\), \(\beta_5\) be the regression coefficients obtained from AI training. Based on historical measurement data for fitting, a quantitative relationship model between multi-dimensional environmental parameters and compensation factors is established. The compensation coefficients are optimized through AI fitting to make the error correction physically interpretable and mathematically rigorous;

[0062] As a further implementation technical solution of this scheme, the steps of error modeling training are as follows:

[0063] A1: Data collection: Measure the true pollutant concentration \(C\) under different temperature, humidity, air flow velocity, and particulate matter concentration conditions true and the reference measurement value \(C_{ref}\) meas ;

[0064] A2: Calculate the error based on the measured true pollutant concentration \(C\) true and the reference measurement value \(C_{ref}\). The error function is: meas \(\Delta C = C - C_{ref}\)

[0065] \(\Delta C = C\) meas - \(C_{ref}\) true

[0066] A3: Model training: According to the calculated error value \(\Delta C\), when the error reaches the minimum value, a pollutant compensation factor is obtained accordingly. Then, use the AI model to train to obtain \(\beta_1\), \(\beta_2\), \(\beta_3\), \(\beta_4\), \(\beta_5\). The specific expression is:

[0067]

[0068] Use the least squares method, support vector regression, neural network, or random forest regression for fitting. Adopt an AI training framework with multi-algorithm fusion, which can handle both linear relationships and capture non-linear error characteristics, ensuring that the error model has strong generalization ability and high prediction accuracy;

[0069] As a further implementation technical solution of this scheme, the fiber optic sensing head adopts an anti-pollution coating, and the fiber optic sensing head is equipped with a fiber optic self-cleaning system. The self-cleaning system uses ultrasonic oscillation or air flow purging for cleaning. Through the combination of surface modification and self-cleaning technology, it can effectively prevent the measurement baseline drift caused by pollutant attachment and reduce the system maintenance frequency by more than 50%;

[0070] As a further implementation technical solution of this scheme, the method includes using a fiber Bragg grating temperature and humidity sensor for temperature and humidity drift compensation, which is used to correct the error caused by the change of the optical signal due to environmental factors, realize the synchronous compensation of temperature / humidity cross-sensitivity, and reduce the measurement error caused by environmental factors to within ±0.5%;

[0071] As a further implementation technical solution of this scheme, the fiber optic sensing system adopts a multi-point distributed sensing structure, which is used to improve the spatial resolution of the polluted site, conduct three-dimensional pollution concentration monitoring, construct a three-dimensional pollution diffusion model, with a spatial resolution reaching the centimeter level, and support pollution source positioning and migration path analysis;

[0072] As a further implementation technical solution of this scheme, the method combines an AI algorithm to correct measurement errors in real time. The input variables include monitoring time, humidity, PM2.5 and PM10 concentrations, air flow velocity and other environmental parameters, and a dynamic correlation model between time-varying environmental parameters and system errors is established to achieve minute-level iterative optimization of measurement results;

[0073] As a further implementation technical solution of this scheme, it includes a laser emission module, which contains an argon ion laser or a semiconductor laser, and is used to output two monochromatic lights with different wavelengths, namely λ1 and λ2;

[0074] An optical path coupling module, including a coupler and a calibration box. The coupler inputs part of the light into the optical fiber transmission system, and the other part of the light is input into the calibration box as the reference light intensity I λ1,0 and I λ2,0 ;

[0075] An optical fiber transmission system, which is used to transmit the optical signal to the sensor head set in the polluted site to be measured. The two wavelengths of light in the sensor head have a selective absorption effect based on the differential absorption characteristics with the polluted gas;

[0076] A signal processing module, which receives the light intensity signals I λ1 and I λ2 after absorption by the polluted gas through the output optical fiber, and calculates the pollutant concentration;

[0077] An environmental parameter acquisition module, including a fiber Bragg grating sensor, a particulate matter sensor and an anemometer, which is used to collect the temperature T, humidity H, PM2.5 concentration P1, PM10 concentration P2 and air flow velocity V in real time;

[0078] An AI error correction module, which calculates the pollutant compensation factor by training the regression coefficient, and optimizes the model based on historical error data using the least squares method, support vector regression or neural network;

[0079] An anti-pollution sensing component, the surface of the sensor head is coated with an anti-pollution coating, and an ultrasonic oscillation or air flow purge self-cleaning system is integrated;

[0080] A distributed monitoring structure, which adopts a three-dimensional sensing network composed of multi-point arranged fiber optic sensor heads, and combines with the signal processing module to achieve spatial resolution monitoring of pollution concentration. The modular design makes the system highly scalable, supports multi-parameter fusion monitoring, shortens the on-site deployment time by 60%, and reduces the maintenance cost by 40%.

[0081] In this article, specific examples are used to elaborate on the principles and implementation manners of the present invention. The description of the above examples is only for helping to understand the method and its core idea of the present invention. The above is only the preferred implementation manner of the present invention. It should be noted that due to the limitation of literal expression and objectively there are infinite specific structures. For those of ordinary skill in the art in this technical field, without departing from the principle of the present invention, several improvements, refinements or changes can also be made, or the above technical features can be combined in an appropriate manner; these improvements, refinements, changes or combinations, or directly applying the concept and technical solution of the invention to other occasions without improvement, shall all be regarded as the protection scope of the present invention.

Claims

1. A high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology, characterized in that: It includes the following steps: Step 1: Use an argon ion laser or a semiconductor laser to output an optical signal. The output optical signal contains two monochromatic lights with different wavelengths, namely λ1 and λ2. A part of the light enters the optical fiber transmission system through a coupler, and the other part of the light enters the calibration box as the reference light intensity for calibrating the input light intensity. The reference light intensity is I λ1,0 and I λ2,0 ; Step 2: The optical fiber transmission system transmits the optical signal to the sensing head at the contaminated site to be measured. Inside the sensing head, the light of two wavelengths interacts with the contaminated gas. Based on the differential absorption characteristics of the gas, the light of different wavelengths is selectively absorbed by the contaminated gas; Step 3: The light after being absorbed by the polluted gas is transmitted to the signal processing unit through the output optical fiber, and the output light intensity is I λ1 and I λ2 , then calculate the gas concentration, and further output the concentration data of pollutants in real time; Step 4: The differential absorption spectroscopy method is used to calculate the pollutant concentration, and the data accuracy is optimized by AI error correction. The calculation formula for the pollutant concentration C is: Wherein, ln is the natural logarithm, I λ1,0 and I λ2,0 are the reference light intensities at wavelengths λ1 and λ2 respectively, I λ1 and I λ2 are the output light intensities at wavelengths λ1 and λ2 respectively, α λ1 and α λ2 are the gas absorption coefficients of the pollutant at λ1 and λ2 respectively, L is the optical path length, K corr is the pollutant compensation factor calculated by AI.

2. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 1, wherein: The pollutant compensation factor K corr has the following calculation process: S1: Environmental data collection: The fiber Bragg grating sensor, particulate matter sensor, and wind speed sensor devices collect environmental parameters. The collected environmental parameters include temperature, humidity, PM2.5 and PM10 concentrations, and air flow velocity; S2: Error modeling training: Use big data to train the AI model and calculate the optimal value of the regression coefficient based on historical error data; S3: Real-time compensation: During the actual measurement process, substitute the collected environmental parameters into the formula to calculate the pollutant compensation factor K corr and correct the calculated value of the pollutant concentration.

3. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 2, wherein: The pollutant compensation factor K corr has the following calculation formula: K corr = 1 + β1T + β2H + β3PM 2.5 + β4PM 10 + β5V where T is the ambient temperature, H is the ambient humidity, PM 2.5 and PM 10 are the concentrations of PM2.5 and PM10 particles in the air, V is the air flow velocity, and β1, β2, β3, β4, β5 are regression coefficients obtained from AI training and are fitted based on historical measurement data.

4. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 2, characterized in that: The steps of the error modeling training are: A1: Data collection: Measure the true pollutant concentration C under different conditions of temperature, humidity, air flow velocity, and particulate matter concentration true and the reference measurement value C meas ; A2: Calculate the error based on the measured true pollutant concentration C true and the reference measurement value C meas using the following formula: ΔC = C meas -C true A3: Model training: According to the calculated error value ΔC, when the error reaches the minimum value, a pollutant compensation factor is obtained correspondingly. Then, use the AI model to train to obtain β1, β2, β3, β4, β5, and the specific expression is: Use the least squares method, support vector regression, neural network or random forest regression for fitting.

5. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 1, characterized in that: The optical fiber sensing head uses an anti-pollution coating, and the optical fiber sensing head is equipped with an optical fiber self-cleaning system, and the self-cleaning system uses ultrasonic oscillation or air flow purging for cleaning.

6. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 1, characterized in that: The method includes using a fiber Bragg grating temperature and humidity sensor for temperature and humidity drift compensation to correct the error caused by environmental factor changes in the optical signal.

7. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 1, characterized in that: The optical fiber sensing system adopts a multi-point distributed sensing structure to improve the spatial resolution of the contaminated site and perform three-dimensional pollution concentration monitoring.

8. The high-precision in-situ monitoring method for contaminated sites driven by fiber optic sensing technology according to claim 1, characterized in that: The method combines the AI algorithm to perform real-time correction on the measurement error, and the input variables include monitoring time, humidity, PM2.5 and PM10 concentrations, and air flow velocity environmental parameters.

9. The high-precision in-situ monitoring system for contaminated sites driven by fiber optic sensing technology according to claim 1, characterized in that: It includes a laser emission module, which contains an argon ion laser or a semiconductor laser, and is used to output two different wavelengths of monochromatic light, namely λ1 and λ2; An optical path coupling module, comprising a coupler and a calibration box, wherein the coupler inputs part of the light into an optical fiber transmission system, and inputs the other part of the light into the calibration box as a reference light intensity I λ1,0 and I λ2,0 ; The optical fiber transmission system is used to transmit the optical signal to the sensing head arranged at the contaminated site to be measured. Inside the sensing head, the light of two wavelengths has a selective absorption effect based on the differential absorption characteristics with the contaminated gas; A signal processing module receives the light intensity signals I λ1 and I λ2 absorbed by the polluted gas through an output optical fiber, and calculates the pollutant concentration; The environmental parameter collection module includes a fiber Bragg grating sensor, a particulate matter sensor and a wind speed sensor, and is used to collect the temperature T, humidity H, PM2.5 concentration P1, PM10 concentration P2 and air flow velocity V in real time; The AI error correction module calculates the pollutant compensation factor by training the regression coefficient, and optimizes the model based on historical error data using the least squares method, support vector regression or neural network; The anti-pollution sensing component, the surface of the sensing head is coated with an anti-pollution coating, and an ultrasonic oscillation or air flow purging self-cleaning system is integrated; The distributed monitoring structure uses fiber optic sensing heads arranged in multiple points to form a three-dimensional sensing network, and combines with the signal processing module to achieve spatial resolution monitoring of the pollution concentration.

Images