Bridge health state intelligent monitoring method and system based on cloud computing

Abstract

The invention provides a bridge health state intelligent monitoring method and system based on cloud computing, and the method mainly comprises the steps: 1, determining a key stress part according to a bridge design drawing and finite element analysis; 2, applying a fluorescent coating to the selected area in the step 1 by using a spraying process, wherein the coating coverage area per square meter is not less than 80%; the fluorescence monitoring module monitors the change of a fluorescent particle coating through an optical sensor (a CCD camera or a spectrograph) and a data collector and carries out calculation, according to the system and the method, the sensitivity of fluorescent particles to mechanical stress is utilized, calculation is combined with wavelength and position offset, tiny anomalies can be detected, and early warning is achieved; fluorescent signals are used in sunny weather and sound waves are used in rainy and foggy weather, so that all-weather stable monitoring is ensured; the fluorescent coating covers key parts, and the sound wave device performs multi-point monitoring, so that the traditional blind area problem is solved; large-scale data are processed in real time through cloud computing, and evaluation precision is improved through machine learning; the coating and the sound wave device are simple and convenient to install without transforming a bridge structure, and the maintenance cost is low.

Description

Technical Field

[0001] The present invention relates to the technical field of bridge monitoring, and in particular to a cloud computing-based intelligent bridge health status monitoring method and system. Background Art

[0002] Current bridge health monitoring relies primarily on traditional technologies, such as strain gauges, accelerometers, and ultrasonic testing. While these methods can reflect the structural status of bridges, they have the following shortcomings:

[0003] 1. Limited monitoring range: Traditional sensors are mostly concentrated in local areas, making it difficult to cover all key parts of the bridge and resulting in blind spots.

[0004] 2. Poor environmental adaptability: In bad weather such as rain, fog, and strong wind, optical or electromagnetic detection is easily interfered with and the accuracy is reduced.

[0005] 3. Low data processing efficiency: Existing systems rely heavily on local computing and are unable to process large amounts of data in real time, limiting their intelligence and response speed.

[0006] 4. Insufficient damage location accuracy: Traditional methods are insensitive to small stress changes, making it difficult to achieve early warning.

[0007] In recent years, fluorescent particles have garnered attention due to their optical properties' sensitivity to mechanical stress. Cloud computing has also demonstrated significant advantages in data processing and storage. However, there is currently no solution for embedding fluorescent particles into bridge coatings, combining them with acoustic positioning technology, and enabling intelligent monitoring of bridge health through cloud computing. This patent aims to fill this gap and improve monitoring accuracy and reliability. Summary of the Invention

[0008] To this end, the present invention provides a cloud computing-based intelligent monitoring method and system for bridge health status, which improves the accuracy and reliability of bridge monitoring by combining fluorescent particles with acoustic wave positioning technology.

[0009] To achieve the above objectives, the present invention provides a cloud computing-based intelligent bridge health status monitoring method, comprising the following steps:

[0010] Step 1: Determine the selected areas to be monitored based on the bridge design drawings and finite element analysis;

[0011] Step 2: Apply the fluorescent coating to the selected area in step 1 by spraying or brushing, with the coating covering no less than 80% of the area per square meter; after the coating is cured, test its stability in a temperature range of -20°C to 60°C and a humidity of 0-100%.

[0012] Step 3: Install ultrasonic transmitters (frequency 20-100kHz, power 5-10W) and receivers in the selected areas selected in step 1, with a spacing of 5-10 meters, and at least one set of ultrasonic devices for every 50 meters of bridge length;

[0013] Step 4: Install a high-resolution optical sensor (such as a CCD camera with a resolution of ≥2000×2000 pixels, or a spectrometer with a wavelength resolution of 0.1 nm) above the coating, 0.5-1 meter away from the coating, covering the coating area; at least one sensor is arranged for every 10 square meters of coating area;

[0014] Step 5: When the bridge is unloaded, record the initial emission wavelength λ0 (unit: nm) and the emission position coordinates of the fluorescent particles.

[0015] (x0, y0, z0) (unit: mm); the acquisition frequency is 1 time / second, lasting for 10 minutes, and the average value is taken as the calibration reference.

[0016] Step 6: Construct an experimental material of the same material in the laboratory; apply a known stress σ (unit: MPa) to the material and measure the wavelength shift Δλ. Establish a linear relationship:

[0017] Δλ=k·σ

[0018] Where k is the stress sensitivity coefficient (typical value 0.05-0.2nm / MPa, determined by experiments). After calibration, k is entered into the system database.

[0019] Step 7: During the operation of the bridge, the optical sensor collects the fluorescence wavelength λ at a frequency of 1 Hz. t and the luminous position (x t ,y t , z t ); the data is converted into a digital signal by the analog-to-digital converter (ADC) and stored in the local cache.

[0020] Step 8: Calculate the real-time wavelength offset:

[0021] Δλ t =λ t ―λ0

[0022] If Δλ t >0.5nm, marked as potential stress abnormal point.

[0023] Step 9: Position offset calculation

[0024] Calculate the three-dimensional offset distance of the light emitting position:

[0025]

[0026] If d t>1mm, recorded as abnormal deformation point.

[0027] Step 9: Abnormal comparison and preliminary judgment

[0028] Define the health status index H t :

[0029]

[0030] Among them, w1=0.6, w2=0.4 are weight coefficients, λ th =1nm,d th =2mm is the threshold value. t , proceed to the next step of analysis.

[0031] Step 10: In clear weather, emit a fixed frequency sound wave (such as 40kHz) and record the initial sound source position (x s0 ,y s0 , z s0 ) and propagation time t0.

[0032] Calculating the speed of sound waves

[0033]

[0034] L is the distance between the transmitter and the receiver (unit: m).

[0035] Step 11, Sound wave monitoring in rainy and foggy weather: When humidity > 80% or visibility < 100 meters, start the sound wave device and record the sound source location (x s ,y s , z s ) and propagation time t s .

[0036] Calculate the sound source position offset:

[0037]

[0038] Calculate the change in sound wave velocity:

[0039]

[0040] like

[0041] Step 12: Data upload and cloud computing processing

[0042] Upload fluorescence signal data and acoustic wave data to the cloud platform via 5G network or LoRa module at a frequency of 1 time per minute;

[0043] Data is stored in a distributed database (such as Hadoop); a convolutional neural network (CNN) is used to extract time series features and train a model to identify abnormal patterns; and a comprehensive health index is calculated:

[0044]

[0045] Where, α = 0.7, β = 0.3, dsth = 3 mm

[0046] H c <0.5: healthy;

[0047] 0.5≤H c <1: mild abnormality;

[0048] H c ≥1: Severe abnormality.

[0049] Step 13: Health status assessment and early warning

[0050] The cloud platform generates a health status heat map, marking abnormal areas and H c The value is displayed through the web interface.

[0051] If H c ≥1, the system automatically sends a text message or email alert, including the abnormal location and recommended measures.

[0052] A cloud computing-based intelligent bridge health monitoring system includes: a fluorescence monitoring module, an acoustic wave monitoring module, an environmental monitoring module, a data collector, a data transmission device, and a cloud server. The fluorescence monitoring module is composed of an optical sensor that detects fluorescence wavelengths and transmits data to the data collector. The acoustic wave monitoring module is composed of an ultrasonic transmitter, a receiver, and a signal processor, and transmits data to the data collector. The environmental monitoring module includes a temperature and humidity sensor and an anemometer to assist in determining weather conditions.

[0053] Data collector: The data collector is used to collect and process data transmitted by the fluorescence monitoring module, acoustic wave monitoring module and environmental monitoring module, and then transmit it to the cloud server through the data transmission device;

[0054] The data transmission protocol uses MQTT or HTTP to ensure data security and efficient transmission;

[0055] The acoustic wave monitoring module monitors the signal of the ultrasonic transmitter through the signal processor and receiver;

[0056] Furthermore, the data calculated by the aforementioned fluorescence monitoring module, acoustic wave monitoring module, environmental monitoring module, and data collector are stored using the Hadoop distributed file system; the system is also provided with a computing unit: deployed on a cloud server, running a machine learning model (such as CNN) for data analysis; the system is provided with a model training unit: regularly using historical data to train and optimize the monitoring model to improve prediction accuracy; providing a web interface and mobile application to display the health status of the bridge, historical data and early warning information; and setting up an early warning module with integrated SMS and email push functions to notify managers in a timely manner.

[0057] Compared with the existing technology, the beneficial effects of the present invention are: the fluorescent particles are sensitive to mechanical stress, and combined with wavelength and position offset calculation, they can detect tiny anomalies and achieve early warning; fluorescent signals are used in clear weather, and acoustic positioning is used in rainy and foggy weather to ensure stable monitoring around the clock; the fluorescent coating covers key parts, and the acoustic device monitors at multiple points, overcoming the traditional blind spot problem; cloud computing processes large-scale data in real time, and machine learning improves assessment accuracy; the coating and acoustic device are easy to install, without the need to modify the bridge structure, and the maintenance cost is low. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 It is the system workflow diagram; DETAILED DESCRIPTION

[0059] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are merely used to explain the present invention and are not intended to limit the present invention.

[0060] The present invention provides a method for intelligently monitoring bridge health status based on cloud computing, comprising the following steps:

[0061] Step 1: Determine the selected areas to be monitored based on the bridge design drawings and finite element analysis;

[0062] Step 2: Apply the fluorescent coating to the selected area in step 1 by spraying or brushing, with the coating covering no less than 80% of the area per square meter; after the coating is cured, test its stability in a temperature range of -20°C to 60°C and a humidity of 0-100%.

[0063] Step 3: Install ultrasonic transmitters (frequency 20-100kHz, power 5-10W) and receivers in the selected areas selected in step 1, with a spacing of 5-10 meters, and at least one set of ultrasonic devices for every 50 meters of bridge length;

[0064] Step 4: Install a high-resolution optical sensor (such as a CCD camera with a resolution of ≥2000×2000 pixels, or a spectrometer with a wavelength resolution of 0.1 nm) above the coating, 0.5-1 meter away from the coating, covering the coating area; at least one sensor is arranged for every 10 square meters of coating area;

[0065] Step 5: When the bridge is unloaded, record the initial emission wavelength λ0 (unit: nm) and the emission position coordinates of the fluorescent particles.

[0066] (x0, y0, z0) (unit: mm); the acquisition frequency is 1 time / second, lasting for 10 minutes, and the average value is taken as the calibration reference.

[0067] Step 6: Construct an experimental material of the same material in the laboratory; apply a known stress σ (unit: MPa) to the material and measure the wavelength shift Δλ. Establish a linear relationship:

[0068] Δλ=k·σ

[0069] Where k is the stress sensitivity coefficient (typical value 0.05-0.2nm / MPa, determined by experiments). After calibration, k is entered into the system database.

[0070] Step 7: During the operation of the bridge, the optical sensor collects the fluorescence wavelength λ at a frequency of 1 Hz. t and the luminous position (x t ,y t , z t ); the data is converted into a digital signal by the analog-to-digital converter (ADC) and stored in the local cache.

[0071] Step 8: Calculate the real-time wavelength offset:

[0072] Δλ t =λ t ―λ0

[0073] If Δλ t >0.5nm, marked as potential stress abnormal point.

[0074] Step 9: Position offset calculation

[0075] Calculate the three-dimensional offset distance of the light emitting position:

[0076]

[0077] If d t >1mm, recorded as abnormal deformation point.

[0078] Step 9: Abnormal comparison and preliminary judgment

[0079] Define the health status index H t :

[0080]

[0081] Among them, w1=0.6, w2=0.4 are weight coefficients, λ th =1nm,d th =2mm is the threshold value. t , proceed to the next step of analysis.

[0082] Step 10: In clear weather, emit a fixed frequency sound wave (such as 40kHz) and record the initial sound source position (x s0 ,y s0 , z s0 ) and propagation time t0.

[0083] Calculating the speed of sound waves

[0084]

[0085] L is the distance between the transmitter and the receiver (unit: m).

[0086] Step 11, Sound wave monitoring in rainy and foggy weather: When humidity > 80% or visibility < 100 meters, start the sound wave device and record the sound source location (x s ,y s , z s ) and propagation time t s .

[0087] Calculate the sound source position offset:

[0088]

[0089] Calculate the change in sound wave velocity:

[0090]

[0091] like

[0092] Step 12: Data upload and cloud computing processing

[0093] Upload fluorescence signal data and acoustic wave data to the cloud platform via 5G network or LoRa module at a frequency of 1 time per minute;

[0094] Data is stored in a distributed database (such as Hadoop); a convolutional neural network (CNN) is used to extract time series features and train a model to identify abnormal patterns; and a comprehensive health index is calculated:

[0095]

[0096] Where, α=0.7, β=0.3, d sth =3mm

[0097] H c <0.5: healthy;

[0098] 0.5≤H c <1: mild abnormality;

[0099] H c ≥1: Severe abnormality.

[0100] Step 13: Health status assessment and early warning

[0101] The cloud platform generates a health status heat map, marking abnormal areas and H c The value is displayed through the web interface.

[0102] If H c ≥1, the system automatically sends a text message or email alert, including the abnormal location and recommended measures.

[0103] A cloud computing-based intelligent bridge health monitoring system includes: a fluorescence monitoring module, an acoustic wave monitoring module, an environmental monitoring module, a data collector, a data transmission device, and a cloud server. The fluorescence monitoring module is composed of an optical sensor that detects fluorescence wavelengths and transmits data to the data collector. The acoustic wave monitoring module is composed of an ultrasonic transmitter, a receiver, and a signal processor, and transmits data to the data collector. The environmental monitoring module includes a temperature and humidity sensor and an anemometer to assist in determining weather conditions.

[0104] Data collector: The data collector is used to collect and process data transmitted by the fluorescence monitoring module, acoustic wave monitoring module and environmental monitoring module, and then transmit it to the cloud server through the data transmission device;

[0105] The data transmission protocol uses MQTT or HTTP to ensure data security and efficient transmission;

[0106] The acoustic wave monitoring module monitors the signal of the ultrasonic transmitter through the signal processor and receiver;

[0107] Furthermore, the data calculated by the aforementioned fluorescence monitoring module, acoustic wave monitoring module, environmental monitoring module, and data collector are stored using the Hadoop distributed file system; the system is also provided with a computing unit: deployed on a cloud server, running a machine learning model (such as CNN) for data analysis; the system is provided with a model training unit: regularly using historical data to train and optimize the monitoring model to improve prediction accuracy; providing a web interface and mobile application to display the health status of the bridge, historical data and early warning information; and setting up an early warning module with integrated SMS and email push functions to notify managers in a timely manner.

Claims

1. A cloud computing-based intelligent monitoring method for bridge health status, characterized by Use the following steps: Step 1: Determine the selected areas to be monitored based on the bridge design drawings and finite element analysis; Step 2: Apply the fluorescent coating to the selected area in step 1 by spraying, with the coating covering no less than 80% per square meter; Step 3: Install ultrasonic transmitters in the selected area selected in step 1: frequency 20-100kHz, power 5-10W, and corresponding receivers at the same time. The distance between the ultrasonic transmitter and the receiver is 5-10 meters, and at least one set of ultrasonic wave devices is arranged for every 50 meters of bridge length; Step 4: Install an optical sensor above the fluorescent coating installed in step 2, 0.5-1 meter away from the coating, covering the coating area; at least one sensor is arranged for every 10 square meters of coating area; Step 5: When the bridge is unloaded, use the optical sensor installed in step 4 to record the initial emission wavelength λ0 and emission position coordinates of the fluorescent particles. (x0, y0, z0); the acquisition frequency is 1 time / second, lasting for 10 minutes, and the average value is taken as the calibration reference; Step 6: Construct an experimental material of the same material in the laboratory; apply a known stress σ to the material and measure the wavelength shift Δλ; and establish a linear relationship: Δλ=k·σ Among them, k is the stress sensitivity coefficient, which is input into the system database after calibration; Step 7: During the operation of the bridge, the optical sensor installed in step 4 collects the fluorescence wavelength λ at a frequency of 1 Hz. t And the emission position (xt, yt, zt): The data is converted into digital signals by the analog-to-digital converter (ADC) and stored in the local cache; Step 8: Calculate the real-time wavelength offset based on the data collected in step 7: Dl t =λ t ―λ0 If Δλ t >0.5nm, marked as potential stress abnormal point; Step nine, calculate the position offset based on the data collected in step seven. Calculate the three-dimensional offset distance of the light emitting position: If d t >1mm, recorded as abnormal deformation point; Step 9: Abnormal comparison and preliminary judgment Define the health status index H t : Among them, w1=0.6, w2=0.4 are weight coefficients, λ th =1nm,d th =2mm is the threshold value, if H t >1, proceed to the next step of analysis; Step 10: In clear weather, emit a fixed frequency sound wave (such as 40kHz) and record the initial sound source position (x s0 ,y s0 , z s0 ) and propagation time t0, Calculate the speed of sound waves: L is the distance between the transmitter and the receiver; Step 11, Sound wave monitoring in rainy and foggy weather: When humidity > 80% or visibility < 100 meters, start the sound wave device and record the sound source location (x s ,y s , z s ) and propagation time t s , Calculate the sound source position offset: Calculate the change in sound wave velocity: like Mark as abnormal; Step 12: Data upload and cloud computing processing Upload fluorescence signal data and acoustic wave data to the cloud platform via 5G network or LoRa module at a frequency of 1 time per minute; Data is stored in a distributed database; a convolutional neural network (CNN) is used to extract time series features and train a model to identify abnormal patterns; and a comprehensive health index is calculated: Where, α = 0.7, β = 0.3, dsth = 3 mm; H c <0.5: healthy; 0.5≤H c <1: mild abnormality; H c ≥1: severe abnormality; Step 13: Health status assessment and early warning: The cloud platform generates a health status heat map, marking abnormal areas and H c Value, displayed through the web interface; If H c ≥1, the system automatically sends a notification including the abnormal location and recommended measures.

2. A cloud computing-based intelligent bridge health status monitoring system, characterized by include: Fluorescence monitoring module, acoustic wave monitoring module, environmental monitoring module, data collector, data transmission device, cloud server; the fluorescence monitoring module is composed of an optical sensor for detecting fluorescence wavelength data and transmitting it to the data collector; The acoustic wave monitoring module is composed of an ultrasonic transmitter, a receiver, and a signal processor, and the data is transmitted to the data collector; The environmental monitoring module includes temperature and humidity sensors and anemometer to assist in judging weather conditions; Data collector: The data collector is used to collect and process the data transmitted by the fluorescence monitoring module, the acoustic wave monitoring module and the environmental monitoring module, and then transmit it to the cloud server through the data transmission device.

Images