Tunnel monitoring and evaluation method based on multi-dimensional internet-of-things perception data

Abstract

The invention discloses a tunnel monitoring and evaluating method based on multi-dimensional internet-of-things sensing data. The invention relates to the technical field of tunnel safety. The method comprises the following steps: S1, establishing a tunnel monitoring evaluation database; s2, acquiring an acquisition signal of the Internet of Things sensing equipment; s3, obtaining a numerical value of the tunnel monitoring object; s4, setting an initial threshold value of each monitored object; s5, carrying out dangerous vehicle identification algorithm analysis, waterlogging early warning algorithm analysis, structure safety early warning algorithm analysis and air quality early warning algorithm analysis according to the monitoring values of the various monitoring objects; s6, determining a comprehensive early warning level; and S7, determining a tunnel safety condition grade according to the comprehensive early warning grade and the attribute data of the tunnel structure. According to the monitoring data of various internet-of-things sensing devices, in combination with the attribute data of the tunnel structure, correct early warning of the tunnel safety state is achieved, and technical support can be provided for improving the intelligent degree of the tunnel in the operation period.

Description

Technical Field

[0001] This invention relates to the field of engineering technology, and in particular to a tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data. Background Technology

[0002] Many urban tunnels and rail transit infrastructures under construction or in operation in my country are prone to structural deformation due to prolonged periods of traffic or gravity loads. Furthermore, with the development of new technologies and the need to address the safety of urban lifeline infrastructure, many tunnel structures have already been equipped with or are planned to be equipped with corresponding automated monitoring IoT sensing devices. Currently, the utilization of data from tunnel IoT sensing devices is relatively limited, often analyzing single-dimensional data such as settlement and stress, and it is difficult to directly assess the safety status of the tunnel structure based on sensing data. Judging the tunnel structure condition solely based on single monitoring data and set thresholds is biased, easily leading to false alarms or delayed alarms, which will significantly impact the operational safety management of tunnels. Summary of the Invention

[0003] To address the shortcomings of the above technologies, this invention provides a tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data. By combining monitoring data from various IoT sensing devices with the tunnel's own structural attribute data, accurate early warnings of tunnel safety status can be achieved, providing technical support for improving the intelligence level of tunnels during operation.

[0004] To achieve the above technical objectives, the technical solution adopted by this invention is as follows:

[0005] A tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data includes the following steps:

[0006] S1. Establish a tunnel monitoring and evaluation database to store data collected by IoT sensing devices and tunnel structure attribute data.

[0007] S2. Acquire the collection signal from the IoT sensing device;

[0008] S3. Demodulate the acquisition signal obtained by the IoT sensing device to obtain the following values ​​of the tunnel monitoring objects: arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, crack width, expansion joint width, as well as temperature, humidity, water level and concentration of harmful gases in the tunnel.

[0009] S4. Set the initial threshold for each monitoring object based on the tunnel structure's own attribute data;

[0010] S5. Based on the monitoring values ​​of various monitoring objects, conduct analysis of algorithms for dangerous vehicle identification, urban flooding early warning, structural safety early warning, and air quality early warning.

[0011] The hazardous vehicle identification algorithm analysis includes sensing the time of vehicle entry and exit from the tunnel using video camera equipment, analyzing the changes in monitored tunnel objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, tunnel temperature, and tunnel humidity} during vehicle entry and exit, comparing the changes in each monitored object with its corresponding initial threshold, and classifying them into four levels of hazardous vehicle warning: Level I, Level II, Level III, and Level IV.

[0012] Dangerous Vehicle Level I Warning: The change in value of any monitored object is greater than or equal to the corresponding initial threshold.

[0013] Level II Dangerous Vehicle Warning: For a Level I Non-Dangerous Vehicle Warning, if the change value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold...

[0014] Dangerous vehicle Level III warning: When both the non-dangerous vehicle Level I and non-dangerous vehicle Level II warnings are in effect, if the change value of any monitored object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold,

[0015] Dangerous vehicle level IV warning: Other situations where non-dangerous vehicle level I warning, non-dangerous vehicle level II warning, and non-dangerous vehicle level III warning are issued;

[0016] The waterlogging early warning algorithm analysis includes comparing the real-time monitored values ​​of tunnel monitoring objects {tunnel water level, tunnel humidity} with the initial thresholds corresponding to each monitoring object, and classifying them into four levels of waterlogging warning: Level I, Level II, Level III, and Level IV.

[0017] Level I flood warning: Water level inside the tunnel is greater than or equal to the corresponding initial threshold.

[0018] Level II flood warning: The water level inside the tunnel is below the corresponding initial threshold but greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 2 of the corresponding initial threshold.

[0019] Level III Flooding Warning:

[0020] ① The water level inside the tunnel is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold, or...

[0021] ② The water level inside the tunnel is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 4 of the corresponding initial threshold.

[0022] Level IV flood warning: All other situations that are not under Level I, Level II, or Level III flood warnings.

[0023] Monitoring humidity inside tunnels can help predict the trend of tunnel flooding and improve the accuracy of flood warnings.

[0024] The structural safety early warning algorithm analysis includes comparing the values ​​of real-time monitored tunnel monitoring objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, crack width, and expansion joint width} with the initial thresholds of each monitoring object, and classifying them into structural safety level I, II, III, and IV early warnings.

[0025] Structural safety level I warning: The monitored value of any monitored object is greater than or equal to the corresponding initial threshold.

[0026] Structural safety level II warning: When a non-structural safety level I warning occurs, the monitored value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the change in the value of the monitored object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold.

[0027] Structural safety level III warning: When there is a non-structural safety level I warning and a non-structural safety level II warning, if the monitored value of any monitored object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the change value of the monitored object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold,

[0028] Structural safety level IV warning: All other situations where there are no structural safety level I warnings, no structural safety level II warnings, and no structural safety level III warnings;

[0029] The air quality early warning algorithm analysis includes comparing the monitored concentration of harmful gases in the tunnel with the corresponding initial threshold, and classifying them into four levels: Air Quality Level I, Air Quality Level II, Air Quality Level III, and Air Quality Level IV.

[0030] Air quality level I alert: The monitored value of the concentration of harmful gases is greater than or equal to the corresponding initial threshold.

[0031] Air quality level II warning:

[0032] ① The monitored value of the harmful gas concentration is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, or

[0033] ② The change in the concentration of harmful gases over a set time interval Δt' is greater than or equal to half of the corresponding initial threshold.

[0034] Air quality level III warning:

[0035] ① The monitored value of the harmful gas concentration is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, or

[0036] ② The change in the concentration of harmful gas over a set time interval Δt' is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold.

[0037] Air quality level IV warning: All other situations that are not air quality level I warning, air quality level II warning, or air quality level III warning;

[0038] S6. Determine the comprehensive early warning level based on the analysis results of the dangerous vehicle identification algorithm, the urban flooding early warning algorithm, the structural safety early warning algorithm, and the air quality early warning algorithm.

[0039] Comprehensive Warning Level I: The analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show at least one Level I warning or at least three Level II warnings.

[0040] Comprehensive Warning Level II: In cases other than Comprehensive Warning Level I, the analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show two Level II warnings or at least three Level III warnings.

[0041] Comprehensive Warning Level III: When neither Comprehensive Warning Level I nor Comprehensive Warning Level II is met, the analysis results of the hazardous vehicle identification algorithm, the urban flooding warning algorithm, the structural safety warning algorithm, and the air quality warning algorithm show one Level II warning or two Level III warnings.

[0042] Comprehensive Warning Level IV: All other situations that are neither Comprehensive Warning Level I, nor Comprehensive Warning Level II, nor Comprehensive Warning Level III;

[0043] S7. Determine the tunnel safety status classification based on the comprehensive early warning level and the tunnel structure's own attribute data. Divide the tunnels into four importance levels based on the tunnel structure's own attribute data: long tunnels, extra-long tunnels, or important traffic tunnels in urban areas are of level one importance; highway or urban arterial road tunnels are of level two importance; tunnels located in strata with poor geological conditions are of level three importance; and other tunnels are of level four importance.

[0044] The safety status classification of tunnels is shown in the table below:

[0045]

[0046] When the tunnel safety status is classified as Level A, the tunnel must be closed immediately, and experts must be organized to conduct on-site investigations and take appropriate measures. When the tunnel safety status is classified as Level B, the tunnel condition must be closely monitored, and reports must be made to management personnel, along with proposed solutions. When the tunnel safety status is classified as Level C, the tunnel condition must be monitored periodically, and corresponding prediction methods must be used to forecast future trends. When the tunnel safety status is classified as Level D, no special attention is required, and normal maintenance is sufficient.

[0047] This invention monitors multi-dimensional IoT sensing data of tunnels using IoT sensing devices, then fuses the data to form four specialized early warning levels: dangerous vehicle identification, flood warning, structural safety warning, and air quality warning. A comprehensive early warning level is then established, and finally, the tunnel's safety status is determined by combining the tunnel's structural attribute data. Suggestions for handling measures are provided, offering a basis for tunnel management, maintenance, and accident tracing. This improves the accuracy of tunnel safety status early warnings and provides technical support for enhancing the intelligence level of tunnels during operation.

[0048] The present invention also has the following preferred designs:

[0049] The air quality early warning algorithm of the present invention analyzes the monitoring object values ​​including: oxygen concentration, carbon monoxide concentration, hydrogen sulfide concentration, nitric oxide concentration, and nitrogen dioxide concentration.

[0050] The IoT sensing devices of the present invention include video camera equipment, hydrostatic level, visual displacement meter, laser rangefinder, inclinometer, strain gauge, accelerometer, thermo-hygrometer, water level gauge, crack gauge, wire displacement meter, oxygen concentration monitoring equipment, carbon monoxide concentration monitoring equipment, hydrogen sulfide concentration monitoring equipment, nitric oxide concentration monitoring equipment, and nitrogen dioxide concentration monitoring equipment.

[0051] The IoT sensing device of the present invention further includes an edge computing module, which is used to convert the wavelength, frequency, polarization state, and current intensity data collected by the IoT sensing device into displacement, strain, acceleration, and gas concentration through calculation and processing to obtain the values ​​of each monitoring object in the tunnel.

[0052] Preferably, when the hazardous vehicle identification algorithm analyzes the data, the initial thresholds for each monitored object in the tunnel are as follows:

[0053] The initial threshold for arch settlement is 5 mm;

[0054] The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel.

[0055] The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure.

[0056] The initial threshold for sidewall tilt is 1°;

[0057] The initial threshold for structural strain is 50με, where με is micro-strain.

[0058] The initial threshold for structural acceleration is 0.5g, where g is the acceleration due to gravity.

[0059] The initial threshold for temperature inside the tunnel is 5℃~40℃;

[0060] The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

[0061] Preferably, when the waterlogging early warning algorithm is analyzed, the initial thresholds for various monitoring objects in the tunnel are as follows:

[0062] The initial threshold for the water level inside the tunnel is 0.5m;

[0063] The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

[0064] Preferably, when the structural safety early warning algorithm analyzes the data, the initial thresholds for various monitoring objects in the tunnel are as follows:

[0065] The initial threshold for arch settlement is 5 mm;

[0066] The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel.

[0067] The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure.

[0068] The initial threshold for sidewall tilt is 1°;

[0069] The initial threshold for the crack width is 2 mm;

[0070] The initial threshold corresponding to the expansion joint width is ±10%d, where d is the design width of the expansion joint.

[0071] Preferably, when the air quality early warning algorithm analyzes the data, the initial thresholds for various monitoring objects in the tunnel are as follows:

[0072] The initial threshold for oxygen concentration is 18% to 40%.

[0073] The initial threshold for carbon monoxide concentration is 30 ppm;

[0074] The initial threshold for hydrogen sulfide concentration is 15 ppm;

[0075] The initial threshold for nitric oxide concentration is 5 ppm;

[0076] The initial threshold for nitrogen dioxide concentration is 5 ppm.

[0077] Preferably, the set time Δt = 1h.

[0078] Preferably, the time Δt' is set to 1h.

[0079] The beneficial effects of this invention patent are: by collecting multi-dimensional IoT sensing data of tunnels, it is possible to realize special early warning classifications in four aspects: dangerous vehicles, waterlogging, structural safety and air quality. Furthermore, by combining the comprehensive early warning classification with the tunnel's own structural attribute data, it is possible to determine the safety status classification of the tunnel, realize the comprehensive and automatic judgment of the tunnel safety status from multiple dimensions, and provide suggestions for handling measures, thus providing a basis for tunnel management, maintenance and accident tracing. Attached Figure Description

[0080] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0081] Figure 1 This is a schematic diagram of a tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data. Detailed Implementation

[0082] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, the technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0083] A tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data, such as Figure 1 As shown, it includes the following steps:

[0084] S1. Establish a tunnel monitoring and evaluation database to store data collected by IoT sensing devices and tunnel structure attribute data.

[0085] S2. Acquire the collection signal from the IoT sensing device;

[0086] S3. Demodulate the acquisition signal obtained by the IoT sensing device to obtain the following values ​​of the tunnel monitoring objects: arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, crack width, expansion joint width, as well as temperature, humidity, water level and concentration of harmful gases in the tunnel.

[0087] S4. Set the initial threshold for each monitoring object based on the tunnel structure's own attribute data. The tunnel's own attribute data includes tunnel cross-sectional dimensions, tunnel structure type, tunnel material type, tunnel technical condition, and tunnel importance classification. The initial threshold for each monitoring object is mainly determined by the tunnel's technical condition, which is determined by the civil engineering structure technical condition level assessment in the "Highway Tunnel Maintenance Technical Specifications," and is divided into Class 1, Class 2, Class 3, Class 4, and Class 5.

[0088] S5. Based on the monitoring values ​​of various monitoring objects, conduct analysis of algorithms for dangerous vehicle identification, urban flooding early warning, structural safety early warning, and air quality early warning.

[0089] The hazardous vehicle identification algorithm analysis includes sensing the time of vehicle entry and exit from the tunnel using video camera equipment, analyzing the changes in monitored tunnel objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, tunnel temperature, and tunnel humidity} during vehicle entry and exit, comparing the changes in each monitored object with its corresponding initial threshold, and classifying them into four levels of hazardous vehicle warning: Level I, Level II, Level III, and Level IV.

[0090] Dangerous Vehicle Level I Warning: The change in value of any monitored object is greater than or equal to the corresponding initial threshold.

[0091] Level II Dangerous Vehicle Warning: For a Level I Non-Dangerous Vehicle Warning, if the change value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold...

[0092] Dangerous vehicle Level III warning: When both the non-dangerous vehicle Level I and non-dangerous vehicle Level II warnings are in effect, if the change value of any monitored object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold,

[0093] Dangerous vehicle level IV warning: Other situations where non-dangerous vehicle level I warning, non-dangerous vehicle level II warning, and non-dangerous vehicle level III warning are issued;

[0094] The waterlogging early warning algorithm analysis includes comparing the real-time monitored values ​​of tunnel monitoring objects {tunnel water level, tunnel humidity} with the initial thresholds corresponding to each monitoring object, and classifying them into four levels of waterlogging warning: Level I, Level II, Level III, and Level IV.

[0095] Level I flood warning: Water level inside the tunnel is greater than or equal to the corresponding initial threshold.

[0096] Level II flood warning: The water level inside the tunnel is below the corresponding initial threshold but greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 2 of the corresponding initial threshold.

[0097] Level III Flooding Warning:

[0098] ① The water level inside the tunnel is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold, or...

[0099] ② The water level inside the tunnel is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 4 of the corresponding initial threshold.

[0100] Level IV flood warning: All other situations that are not under Level I, Level II, or Level III flood warnings;

[0101] The structural safety early warning algorithm analysis includes comparing the values ​​of real-time monitored tunnel monitoring objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, crack width, and expansion joint width} with the initial thresholds of each monitoring object, and classifying them into structural safety level I, II, III, and IV early warnings.

[0102] Structural safety level I warning: The monitored value of any monitored object is greater than or equal to the corresponding initial threshold.

[0103] Structural safety level II warning: When a non-structural safety level I warning occurs, the monitored value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the change in the value of the monitored object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold.

[0104] Structural safety level III warning: When there is a non-structural safety level I warning and a non-structural safety level II warning, the monitoring value of any monitoring object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the change value of the monitoring object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold. In this embodiment, the set time Δt = 1h.

[0105] Structural safety level IV warning: All other situations where there are no structural safety level I warnings, no structural safety level II warnings, and no structural safety level III warnings;

[0106] The air quality early warning algorithm analysis includes comparing the monitored concentration of harmful gases in the tunnel with the corresponding initial threshold, and classifying them into four levels: Air Quality Level I, Air Quality Level II, Air Quality Level III, and Air Quality Level IV.

[0107] Air quality level I alert: The monitored value of the concentration of harmful gases is greater than or equal to the corresponding initial threshold.

[0108] Air quality level II warning:

[0109] ① The monitored value of the harmful gas concentration is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, or

[0110] ② The change in the concentration of harmful gases over a set time interval Δt' is greater than or equal to half of the corresponding initial threshold.

[0111] Air quality level III warning:

[0112] ① The monitored value of the harmful gas concentration is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, or

[0113] ② The change in the concentration of harmful gas over a set time interval Δt' is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold.

[0114] In this embodiment, the time Δt' is set to 1 hour.

[0115] Air quality level IV warning: All other situations that are not air quality level I warning, air quality level II warning, or air quality level III warning;

[0116] S6. Determine the comprehensive early warning level based on the analysis results of the dangerous vehicle identification algorithm, the urban flooding early warning algorithm, the structural safety early warning algorithm, and the air quality early warning algorithm.

[0117] Comprehensive Warning Level I: The analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show at least one Level I warning or at least three Level II warnings.

[0118] Comprehensive Warning Level II: In cases other than Comprehensive Warning Level I, the analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show two Level II warnings or at least three Level III warnings.

[0119] Comprehensive Warning Level III: When neither Comprehensive Warning Level I nor Comprehensive Warning Level II is met, the analysis results of the hazardous vehicle identification algorithm, the urban flooding warning algorithm, the structural safety warning algorithm, and the air quality warning algorithm show one Level II warning or two Level III warnings.

[0120] Comprehensive Warning Level IV: All other situations that are neither Comprehensive Warning Level I, nor Comprehensive Warning Level II, nor Comprehensive Warning Level III;

[0121] S7. Determine the tunnel safety status classification based on the comprehensive early warning level and the tunnel structure's own attribute data. Using the tunnel structure's own attribute data, divide the tunnels into four importance levels: Level 1: Long tunnels, extra-long tunnels, or important traffic tunnels within urban areas; where long tunnels refer to tunnels longer than 1000 meters, and extra-long tunnels refer to tunnels longer than 3000 meters; Level 2: Expressway or urban arterial road tunnels; Level 3: Tunnels located in geologically poor strata; and Level 4: Other tunnels.

[0122] The safety status classification of tunnels is shown in the table below:

[0123]

[0124] When the tunnel safety status is classified as Level A, the tunnel must be closed immediately, and experts must be organized to conduct on-site investigations and take appropriate measures. When the tunnel safety status is classified as Level B, the tunnel condition must be closely monitored, and reports must be made to management personnel, along with proposed solutions. When the tunnel safety status is classified as Level C, the tunnel condition must be monitored periodically, and corresponding prediction methods must be used to forecast future trends. When the tunnel safety status is classified as Level D, no special attention is required, and normal maintenance is sufficient.

[0125] In this embodiment, the monitored values ​​analyzed by the air quality early warning algorithm include: oxygen concentration, carbon monoxide concentration, hydrogen sulfide concentration, nitric oxide concentration, and nitrogen dioxide concentration.

[0126] The IoT sensing devices of this invention include video cameras, hydrostatic levels, visual displacement gauges, laser rangefinders, inclinometers, strain gauges, accelerometers, thermometers, hygrometers, water level gauges, crack gauges, wire displacement gauges, oxygen concentration monitoring devices, carbon monoxide concentration monitoring devices, hydrogen sulfide concentration monitoring devices, nitric oxide concentration monitoring devices, and nitrogen dioxide concentration monitoring devices. These IoT sensing devices can all utilize existing technologies. The tunnel monitoring objects collected by various IoT sensing devices and their corresponding initial thresholds are shown in the table below:

[0127]

[0128] The IoT sensing device of the present invention also includes an edge computing module, which is used to convert the wavelength, frequency, polarization state, and current intensity data collected by the IoT sensing device into displacement, strain, acceleration, and gas concentration through calculation and processing to obtain the values ​​of each monitored object in the tunnel. The edge computing module is determined by the IoT sensing device used and belongs to the prior art.

[0129] In this embodiment, the initial thresholds for each monitored object in the tunnel during the analysis by the dangerous vehicle identification algorithm are as follows:

[0130] The initial threshold for arch settlement is 5 mm;

[0131] The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel.

[0132] The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure.

[0133] The initial threshold for sidewall tilt is 1°;

[0134] The initial threshold for structural strain is 50με, where με is micro-strain.

[0135] The initial threshold for structural acceleration is 0.5g, where g is the acceleration due to gravity.

[0136] The initial threshold for temperature inside the tunnel is 5℃~40℃;

[0137] The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

[0138] In this embodiment, the initial thresholds for various monitoring objects in the tunnel are as follows when the waterlogging early warning algorithm is analyzed:

[0139] The initial threshold for the water level inside the tunnel is 0.5m;

[0140] The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

[0141] In this embodiment, the initial thresholds for various monitoring objects in the tunnel are as follows when the structural safety early warning algorithm performs its analysis:

[0142] The initial threshold for arch settlement is 5 mm;

[0143] The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel.

[0144] The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure.

[0145] The initial threshold for sidewall tilt is 1°;

[0146] The initial threshold for the crack width is 2 mm;

[0147] The initial threshold corresponding to the expansion joint width is ±10%d, where d is the design width of the expansion joint.

[0148] In this embodiment, the initial thresholds for various monitoring objects in the tunnel are as follows when the air quality early warning algorithm analyzes the data:

[0149] The initial threshold for oxygen concentration is 18% to 40%.

[0150] The initial threshold for carbon monoxide concentration is 30 ppm;

[0151] The initial threshold for hydrogen sulfide concentration is 15 ppm;

[0152] The initial threshold for nitric oxide concentration is 5 ppm;

[0153] The initial threshold for nitrogen dioxide concentration is 5 ppm.

[0154] Of course, the present invention may have other various embodiments. Without departing from the spirit and essence of the present invention, those skilled in the art can make various corresponding changes and modifications according to the present invention, but these corresponding changes and modifications should all fall within the protection scope of the appended claims.

Claims

1. A tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data, characterized in that, Includes the following steps: S1. Establish a tunnel monitoring and evaluation database to store data collected by IoT sensing devices and tunnel structure attribute data. S2. Acquire the collection signal from the IoT sensing device; S3. Demodulate the acquisition signal obtained by the IoT sensing device to obtain the following values ​​of the tunnel monitoring objects: arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, crack width, expansion joint width, as well as temperature, humidity, water level and concentration of harmful gases in the tunnel. S4. Set the initial threshold for each monitoring object based on the tunnel structure's own attribute data; S5. Based on the monitoring values ​​of various monitoring objects, conduct analysis of algorithms for dangerous vehicle identification, urban flooding early warning, structural safety early warning, and air quality early warning. The hazardous vehicle identification algorithm analysis includes sensing the time of vehicle entry and exit from the tunnel using video camera equipment, analyzing the changes in monitored tunnel objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, structural strain, structural acceleration, tunnel temperature, and tunnel humidity} during vehicle entry and exit, comparing the changes in each monitored object with its corresponding initial threshold, and classifying them into four levels of hazardous vehicle warning: Level I, Level II, Level III, and Level IV. Dangerous Vehicle Level I Warning: The change in value of any monitored object is greater than or equal to the corresponding initial threshold. Level II Dangerous Vehicle Warning: For a Level I Non-Dangerous Vehicle Warning, if the change value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold... Dangerous vehicle Level III warning: When both the non-dangerous vehicle Level I and non-dangerous vehicle Level II warnings are in effect, if the change value of any monitored object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, Dangerous vehicle level IV warning: Other situations where non-dangerous vehicle level I warning, non-dangerous vehicle level II warning, and non-dangerous vehicle level III warning are issued; The waterlogging early warning algorithm analysis includes comparing the real-time monitored values ​​of tunnel monitoring objects {tunnel water level, tunnel humidity} with the initial thresholds corresponding to each monitoring object, and classifying them into four levels of waterlogging warning: Level I, Level II, Level III, and Level IV. Level I flood warning: Water level inside the tunnel is greater than or equal to the corresponding initial threshold. Level II flood warning: The water level inside the tunnel is below the corresponding initial threshold but greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 2 of the corresponding initial threshold. Level III Flooding Warning: ① The water level inside the tunnel is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the humidity inside the tunnel is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold, or... ② The water level inside the tunnel is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the humidity inside the tunnel is greater than or equal to 1 / 4 of the corresponding initial threshold. Level IV flood warning: All other situations that are not under Level I, Level II, or Level III flood warnings; The structural safety early warning algorithm analysis includes comparing the values ​​of real-time monitored tunnel monitoring objects {arch settlement, uneven settlement, cross-sectional convergence, sidewall tilt, crack width, and expansion joint width} with the initial thresholds of each monitoring object, and classifying them into structural safety level I, II, III, and IV early warnings. Structural safety level I warning: The monitored value of any monitored object is greater than or equal to the corresponding initial threshold. Structural safety level II warning: When a non-structural safety level I warning occurs, the monitored value of any monitored object is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, and the change in the value of the monitored object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold. Structural safety level III warning: When there is a non-structural safety level I warning and a non-structural safety level II warning, if the monitored value of any monitored object is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, and the change value of the monitored object within a set time Δt is greater than or equal to 1 / 2 of the corresponding initial threshold, Structural safety level IV warning: All other situations where there are no structural safety level I warnings, no structural safety level II warnings, and no structural safety level III warnings; The air quality early warning algorithm analysis includes comparing the monitored concentration of harmful gases in the tunnel with the corresponding initial threshold, and classifying them into four levels: Air Quality Level I, Air Quality Level II, Air Quality Level III, and Air Quality Level IV. Air quality level I alert: The monitored value of the concentration of harmful gases is greater than or equal to the corresponding initial threshold. Air quality level II warning: ① The monitored value of the harmful gas concentration is less than the corresponding initial threshold and greater than or equal to 3 / 4 of the corresponding initial threshold, or ② The change in the concentration of harmful gases over a set time interval Δt' is greater than or equal to half of the corresponding initial threshold. Air quality level III warning: ① The monitored value of the harmful gas concentration is less than 3 / 4 of the corresponding initial threshold and greater than or equal to 1 / 2 of the corresponding initial threshold, or ② The change in the concentration of harmful gas over a set time interval Δt' is less than 1 / 2 of the corresponding initial threshold and greater than or equal to 1 / 4 of the corresponding initial threshold. Air quality level IV warning: All other situations that are not air quality level I warning, air quality level II warning, or air quality level III warning; S6. Determine the comprehensive early warning level based on the analysis results of the dangerous vehicle identification algorithm, the urban flooding early warning algorithm, the structural safety early warning algorithm, and the air quality early warning algorithm. Comprehensive Warning Level I: The analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show at least one Level I warning or at least three Level II warnings. Comprehensive Warning Level II: In cases other than Comprehensive Warning Level I, the analysis results of the hazardous vehicle identification algorithm, urban flooding warning algorithm, structural safety warning algorithm, and air quality warning algorithm show two Level II warnings or at least three Level III warnings. Comprehensive Warning Level III: When neither Comprehensive Warning Level I nor Comprehensive Warning Level II is met, the analysis results of the hazardous vehicle identification algorithm, the urban flooding warning algorithm, the structural safety warning algorithm, and the air quality warning algorithm show one Level II warning or two Level III warnings. Comprehensive Warning Level IV: All other situations that are neither Comprehensive Warning Level I, nor Comprehensive Warning Level II, nor Comprehensive Warning Level III; S7. Determine the tunnel safety status classification based on the comprehensive early warning level and the tunnel structure's own attribute data. Divide the tunnels into four importance levels based on the tunnel structure's own attribute data: long tunnels, extra-long tunnels, or important traffic tunnels in urban areas are of level one importance; highway or urban arterial road tunnels are of level two importance; tunnels located in strata with poor geological conditions are of level three importance; and other tunnels are of level four importance. The safety status classification of tunnels is shown in the table below: Specifically, when the tunnel safety status is classified as Level A, the tunnel must be closed immediately; when the tunnel safety status is classified as Level B, the tunnel condition needs to be closely monitored; when the tunnel safety status is classified as Level C, the tunnel condition needs to be monitored periodically; and when the tunnel safety status is classified as Level D, no special attention is required, and normal maintenance is sufficient.

2. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 1, characterized in that, The air quality early warning algorithm analyzes the monitoring data including: oxygen concentration, carbon monoxide concentration, hydrogen sulfide concentration, nitric oxide concentration, and nitrogen dioxide concentration.

3. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 2, characterized in that, The IoT sensing devices include video cameras, hydrostatic levels, visual displacement gauges, laser rangefinders, inclinometers, strain gauges, accelerometers, thermometers, hygrometers, water level gauges, crack gauges, wire displacement gauges, oxygen concentration monitoring devices, carbon monoxide concentration monitoring devices, hydrogen sulfide concentration monitoring devices, nitric oxide concentration monitoring devices, and nitrogen dioxide concentration monitoring devices.

4. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 3, characterized in that, The IoT sensing device also includes an edge computing module, which is used to convert the wavelength, frequency, polarization state, and current intensity data collected by the IoT sensing device into displacement, strain, acceleration, and gas concentration through calculation and processing.

5. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 1, characterized in that, When the dangerous vehicle identification algorithm analyzes the data, the initial thresholds for each monitored object in the tunnel are as follows: The initial threshold for arch settlement is 5mm; The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel. The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure. The initial threshold for sidewall tilt is 1°; The initial threshold for structural strain is 50με, where με is micro-strain. The initial threshold for structural acceleration is 0.5g, where g is the acceleration due to gravity. The initial threshold for temperature inside the tunnel is 5℃~40℃; The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

6. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 1, characterized in that, When the waterlogging early warning algorithm is analyzed, the initial thresholds for various monitoring objects in the tunnel are as follows: The initial threshold for the water level inside the tunnel is 0.5m; The initial threshold for humidity inside the tunnel is 30%rh~60%rh, where rh is relative humidity.

7. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 1, characterized in that, When the structural safety early warning algorithm is analyzed, the initial thresholds for various monitoring objects in the tunnel are as follows: The initial threshold for arch settlement is 5mm; The initial threshold for uneven settlement is 3mm / 10m, which means that the settlement is 3mm every 10m along the longitudinal direction of the tunnel. The initial threshold for cross-sectional convergence is ±6‰D, where D is the designed outer diameter of the tunnel structure. The initial threshold for sidewall tilt is 1°; The initial threshold for the crack width is 2 mm; The initial threshold corresponding to the expansion joint width is ±10%d, where d is the design width of the expansion joint.

8. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 2, characterized in that, When the air quality early warning algorithm is analyzed, the initial thresholds for various monitoring objects in the tunnel are as follows: The initial threshold for oxygen concentration is 18% to 40%. The initial threshold for carbon monoxide concentration is 30 ppm; The initial threshold for hydrogen sulfide concentration is 15 ppm; The initial threshold for nitric oxide concentration is 5 ppm; The initial threshold for nitrogen dioxide concentration is 5 ppm.

9. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 1, characterized in that, Set the time Δt = 1h.

10. The tunnel monitoring and evaluation method based on multi-dimensional IoT sensing data according to claim 8, characterized in that, Set the time Δt' = 1h.

Images