The invention discloses an intelligent detection method for multiple types of faults for near-water bridges and an unmanned surface vehicle. The method includes an infrastructure fault target detection network CenWholeNet and a bionics-based parallel attention module PAM. CenWholeNet is a deep learning-based Anchor-free target detection network, which mainly comprises a primary network and a detector, used to automatically detect faults in acquired images with high precision. Wherein, the PAM introduces an attention mechanism into the neural network, including spatial attention and channel attention, which is used to enhance the expressive power of the neural network. The unmanned surface vehicle includes hull module, video acquisition module, lidar navigation module and ground station module, which supports lidar navigation without GPS information, long-range real-time video transmission and highly robust real-time control, used for automated acquisition of information from bridge underside.

The present disclosure provides an automatic test system for actual stress of a bridge based on DIC technology, where the system includes a camera, a phosphor spraying device, a computer, and a sliding rail; the sliding rail is arranged on both sides of an upper wing of a box-shaped concrete beam; the phosphor spraying device is used to spray phosphor on a web of the box-shaped concrete beam to form speckles of varying light and shade; the camera is slidably connected to the sliding rail through a bracket, and is used to photograph the speckles and transmit a speckle image to the computer; and the computer is used to analyze and process the speckle image taken by the camera and generate a time history diagram of stress.

A cable tension calculation method simultaneously considering the sag, inclination angle and bending stiffness includes: querying basic parameters of a stay cable according to design data and construction data; considering influences of the sag, the inclination angle θ and the bending stiffness EI, to calculate dimensionless parameters γ, ε and λ.sup.2; testing an acceleration response of the stay cable by an acceleration sensor, to identify a frequency ω of the acceleration response of the stay cable, further calculating a dimensionless frequency {circumflex over (ω)} of the stay cable and the dimensionless parameters γ, ε and λ.sup.2, and substituting the dimensionless frequency {circumflex over (ω)} of the stay cable into a vibration characteristic equation, to establish a function relation between the dimensionless frequency {circumflex over (ω)} and a cable tension H* of the stay cable; and solving a root of the vibration characteristic equation, and identifying the cable tension H* of the stay cable according to the root.

A measurement method includes generating first displacement data based on data of observation points of a structural object, generating observation information, calculating a time interval in which each of vehicles of a moving object moves alone on the structural object, calculating a first deflection amount of the structural object, calculating a displacement response when each of the vehicles moves alone on the structural object based on the first displacement data and the time interval, calculating a deflection response when each of the vehicles moves alone on the structural object based on the first deflection amount and the time interval, calculating weighting coefficients to the respective vehicles based on the displacement response and the deflection response, and calculating a second deflection amount obtained by correcting the first deflection amount based on the weighting coefficients.

A measurement method includes generating first displacement data based on data of observation points of a structural object, generating observation information, calculating deflection amounts of the structural object by vehicles of a moving object, calculating approach times and exit times of the vehicles with respect to the structural object, calculating time intervals divided by a plurality of times obtained by sorting the approach times and the exit times by time, calculating an amplitude amount of the first displacement data in each of the time intervals, calculating an amplitude amount of the deflection amount in each of the time intervals, and calculating weighting coefficients assuming that a sum of products of the amplitude amounts of the deflection amounts in the time intervals and the weighting coefficients to the vehicles is equal to the amplitude amount of the first displacement data in the time intervals.

An apparatus includes an acquisition means for acquiring displacement quantity in a time-series manner, the displacement quantity being generated at a measurement part of a structure by the weight of a vehicle that travels on the structure, a detection means for detecting the size of the vehicle that passes through the structure and detecting the type of the vehicle from the size, and a control means for controlling the acquisition means on the basis of the detected type of the vehicle.

A computer-vision-based fatigue crack detection approach using a short video is described. Feature tracking is applied to the video for tracking the surface motion of the monitored structure under repetitive load. Then, a crack detection and localization algorithm is established to search for differential features at different frames in the video. The effectiveness of the proposed approach is validated through testing two experimental specimens with in-plane and out-of-plane fatigue cracks. Results indicate that the proposed approach can robustly identify fatigue cracks, even when the cracks are under ambient lighting conditions, surrounded by other crack-like edges, covered by complex surface textures, or invisible to human eyes due to crack closure. The approach enables accurate quantification of crack openings under fatigue loading with good accuracy.

A measurement method include a step to obtain observation point information, including physical quantities in association of a plurality of times, via observation devices at observation points of a structure on which a moving object moves, a step to calculate a correction coefficient that corrects the physical quantities based on a plurality of time periods and a reference time periods, a step to calculate a plurality of deflection waveforms of the structure generated by a plurality of parts of the moving object, a step to calculate a second deflection waveform of the structure generated by the moving object by adding the plurality of deflection waveforms, and a step to calculate a displacement of the structure based on the second deflection waveform. The structure is a superstructure of a road bridge or a railway bridge.

A measurement method includes: a step of acquiring first observation point information including a time point when each part of an m-th moving object passes a first observation point and a physical quantity which is a response to an action; a step of acquiring second observation point information including a time point when the each part passes a second observation point and a physical quantity which is a response to an action; a step of calculating a deflection waveform of a structure generated by the each part; a step of adding the deflection waveforms to calculate an m-th moving object deflection waveform; a step of calculating a displacement waveform at the third observation point; and a step of calculating first to M-th amplitude coefficients by assuming that a waveform obtained by multiplying an m-th amplitude coefficient by the m-th moving object deflection waveform is an m-th amplitude adjusted deflection waveform, and that a sum of first to M-th amplitude adjusted deflection waveforms is approximated to the displacement waveform.

A method for monitoring the structural health of a structure that supports guided propagation modes of elastic waves, includes the following steps: a) acquiring an ambient noise propagating through the structure by means of at least one pair of non-collocated elastic-wave sensors; b) estimating a function representative of an impulse response of the structure for elastic propagation between the constituent sensors of said pair; c) extracting at least one dispersion curve of the elastic propagation through the structure by time-frequency analysis of this function representative of an impulse response; and d) estimating at least one parameter indicative of a mechanical property of a constituent material of the structure from the dispersion curve obtained in step c). A system for implementing such a method is also provided.