The fastener plays a critical role in ensuring the stability and safety of modern engineering structures. However, factors such as vibration, shock, temperature changes, and others can cause fasteners to become loose, thereby compromising the stability and safety of the overall structure. Currently, fastener inspection is primarily done manually, and there is no widely adopted automatic method for real-time detection of fastener looseness. We proposed a fastener looseness inspection method based on digital shearing speckle pattern interferometry (DSSPI) and convolutional neural network (CNN). The key distinction between our proposed method and traditional vision-based methods is that our approach can identify loose fasteners without relying on direct visual observation of the fasteners themselves. Our approach involved setting up a DSSPI system to capture shearing speckle patterns, and the CNN model automatically extracted features from these images and classified them to detect loose fasteners. Principle-validation experiments were conducted to verify the feasibility of the methodology. The trained model achieved a classification accuracy of 92.57%, with a resolution of 0.04 mm and a completion time of only 2.03 ms for a single judgment. That is quite accurate, more sensitive, and much faster than the three-dimensional vision-based method. Furthermore, our proposed method has strong robustness to ambient light, while the incorporation of Random Erasing technology enhances robustness to part occlusion or damage of the measured surface. Most notably, our method can detect loose fasteners before deformation, a capability that conventional vision-based methods lack. These findings demonstrate the tremendous potential of our method for real-time inspection of fastener looseness.
Nowadays, the application of MEMS is more and more important. With the development of microstructure technology, higher requirements are also placed on measurement methods. However, the current measurement methods cannot meet these requirements due to their own limitations. We developed a method based on the temporal microscopic speckle interferometry, which has advantages of real-time, full field, high-precision, and nondestructive. The interferometer based on Linnik microscopic structure is built up. The corresponding displacement measuring experiments have been performed, and the measurement errors are <0.05 μm. The experimental results demonstrate the validity of our homemade device.
A subpixel displacement measurement method based on the combination of particle swarm optimization (PSO) and gradient algorithm (GA) was proposed for accuracy and speed optimization in GA, which is a subpixel displacement measurement method better applied in engineering practice. An initial integer-pixel value was obtained according to the global searching ability of PSO, and then gradient operators were adopted for a subpixel displacement search. A comparison was made between this method and GA by simulated speckle images and rigid-body displacement in metal specimens. The results showed that the computational accuracy of the combination of PSO and GA method reached 0.1 pixel in the simulated speckle images, or even 0.01 pixels in the metal specimen. Also, computational efficiency and the antinoise performance of the improved method were markedly enhanced.
Interferometry is an optical measuring method with the character of non-destructive, high sensitivity and high accuracy. However, its measurement range is limited by the phase ambiguity. Hence the method with two separate different wavelengths light source is introduced to enlarge the measurement range.
As for the two-wavelength interferometry case, phase shifting is the traditional way to acquire the phase map, it needs to repeat the measurement twice, which means the measurement cannot be accomplished in real time. Hence to solve the problem, a temporal sequence interferometry has been used. This method can obtain the desired phase information in real time by using the Fourier transform methods of the interferogram recorded in a sequence while the object is being deformed. But, it is difficult to retrieve the phase information directly due to the multi extreme points in one period of the cosine function.
In this paper, an algorithm based on the wavelet ridge analysis is adopted to retrieve the two wavelength phase fluctuation caused by the displacement simultaneously.
The preliminary experiment is conducted and the results are compared with theoretical simulations to validate the proposed approach. The laser emits light with two wavelengths 532 nm and 473 nm, two separated interference patterns in time sequence are detected by the CCD camera in the same time. The overlapped interferograms of two colors are analyzed by this algorithm and the corresponding phase information are obtained. The maximum error value between the simulation and theory is 0.03 um and the relative error is 0.33%.
Digital shearing speckle pattern interferometry (DSSPI) is a powerful tool in the measurement of strain, residual stress and the non-destructive testing (NDT). It is widely used in the fields of wood testing, tire inspection and aerospace, etc. The DSSPI system based on the Wollaston prism is attractive because of its compact arrangement, high immunity to disturbance, and, most of all, the ability to measure strain directly. It could show the strain distribution of the measured object by producing fringe patterns. In conventional DSSPI systems, phase-shifting devices are commonly adopted to extract phase information from the fringe patterns, which means dynamical measurement cannot be realized. In this paper, the principle of a novel DSSPI system based on the temporal analysis is presented. Phase information is extracted with the Fourier Transform method instead of the phase-shifting devices in this system. In this way, dynamical measurement is realized. The measuring accuracy is mostly determined by the quality of the fringe patterns (the fringe width and the contrast ratio). There are several factors that influence the quality of the fringe patterns. Here we mainly discuss the influence of the shearing distance and the polarization state. The preliminary experiments with different shearing distances and polarization states are conducted. The ideal shearing distance and polarization state are suggested.
In this paper, a ridge algorithm which is based on wavelet analysis is adopted in the measurement of in-plane displacement. To measure in-plane displacement by electronic speckle pattern interferometry (ESPI), a series of speckle patterns are captured with the help of a CCD camera which is known as temporal speckle pattern interferometry (TSPI) technique and TSPI technique has better correlation and a larger measuring range compared with ESPI technique. To retrieve the phase fluctuation caused by the displacement of specimen, three types of complex wavelets are selected in the wavelet analysis to compare with the traditional Fourier analysis.
As a measuring technique, owing to its high throughput and multichannel advantages, interference imaging spectroscopy is widely used in many fields. This technique can be classified as temporally modulated Fourier transform spectrometer (TMFTS) and spatially modulated Fourier transform spectrometer (SMFTS). In contrast to TMFTS-based instruments, instruments using SMFTS are more stable, simple, and compact. In spectrometry, improvements of the spectral resolution and the optical throughput are always the focus points. A new static Fourier-transform imaging spectrometer based on the use of Wollaston prisms is presented. The novelty of this work comes from the use of a longer optical path difference, which provides higher spectral resolution. The principle and the system configuration are described. An experimental system based on the Wollaston prisms has been built and preliminary imaging spectroscopy experiments have been performed with it.
KEYWORDS: Inspection, Image processing, Video processing, Field programmable gate arrays, Safety, Laser systems engineering, CCD cameras, Laser processing, Signal processing, Video
Rail track geometric parameters, such as gage, level, twist, longitudinal irregularity, and alignment irregularity, etc., have
much influence on the operation safety of train vehicles. GJ-4 track inspection car is a large scale dynamic measurement
equipment for measuring track geometric parameters precisely and efficiently. It is useful to find track defects, guide
track maintenance, and eliminate potential safety problems of track. However the device of measuring gage and
alignment irregularity of this track inspection car is installed on a hanging beam, which is not suitable for rapid
inspection and has higher failure rate. Hence this sub-system is replaced by the laser-camera method. The rebuild car is
named GJ-4G. It greatly eliminates the measurement errors caused by the existing subsystem and increases the measuring
stability. The feasibility of this track inspection car has been proven by the practical experiments carried out by Beijing
Railway Administration.
The geometric parameters of wheelsets, such as flange thickness, and rim width, and rim inside distance, are key
parameters that influence the wheel-rail contact. The online measurement techniques of these parameters are important to
ensure the safety of train vehicle and increase the reliability and efficiency of maintaining. The paper purposed the
measurement system based on the optoelectronic techniques. The measuring system is composed of the trigger sensor
and the laser displacement sensors fixed on the rails and the system can measure the wheelset's parameters when trains
pass through. The measuring results are improved by the wavelet analysis denoised. The average value difference is
between 0-0.3mm comparing the system and the manual that shows two methods are coincided. When trains pass
through the measuring system under the speed of 10km/h, measuring results shows that the system can meet with the
measuring requirement on line.
Rail track geometric parameters, such as gage, level, twist, longitudinal irregularity, alignment irregularity, etc., have much influence on the operation safety of train vehicles. With the development of railway, the demand for measuring track geometric parameters precisely and efficiently has become a common concern, and to date this problem has not been properly solved. In this work, a new measurement method and a system for track geometric parameters are presented. Through analyzing advantages and disadvantages of existing measurement methods of track geometric parameters, a fiber-optic gyro is adopted for the straightness measurement. It greatly eliminates the measurement errors caused by existing methods. The feasibility of this track parameter measurement trolley is proven by practical experiments.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.