Non-contact Vibration Sensor Research Articles

Proactive Fault Detection in Rotating Machinery using Machine Learning- A Survey

This study presents a survey of approaches for proactive fault detection in rotating machinery, with a focus on the early identification of bearing faults to enhance equipment reliability and operational efficiency. Traditional methods, relying on physical sensors and manual inspections, often lack the ability to provide timely insights into emerging faults. In contrast, the surveyed approaches integrate non-contact vibration sensors with advanced machine learning techniques, revolutionizing fault detection capabilities. The study presents a brief overview of the methods used in classification of the rotating machinery defects using the machine learning and recommends a combination of machine learning methods at different stages to overcome the challenges of the traditional methods. The collected vibration signals undergo noise reduction via the Hilbert transform, followed by dimensionality reduction and feature selection using Independent Component Analysis (ICA) and Genetic Algorithms (GA), respectively. The selected features are then employed for fault detection and categorization using Random Forest (RF) and Deep Belief Networks (DBN). The Future work will involve the implementation and evaluation of these approaches in real-world industrial settings to validate their effectiveness and reliability.

Signal processing and acoustic calibration method of millimeter-wave vibration sensor

Millimeter-wave sensors can be utilized as non-contact vibration sensors. Applications of millimeter-wave vibration sensors are the vital sensing of humans (heartbeat, respiration, body motion), factory machines, and vibration sensing of social infrastructures, such as buildings and bridges. Millimeter-wave vibration sensors can simultaneously detect the position and the waveforms of the vibration displacements of vibration objects. The primary signal processing of millimeter-wave sensors is two-dimensional fast Fourier transform (2D-FFT), detecting the arrival direction (DOA) and processing the micro-Doppler signals. The detectable areas of the millimeter-wave vibration sensors are defined using the parameters related to these three signal-processing blocks. Measured vibration waveforms by millimeter-wave vibration sensors include all components of the vibration displacements in the defined detectable area. Therefore, the waveform of the vibration displacement is influenced by the definition of the detectable area and the vibration form of the vibrating object. The measured values of millimeter-wave vibration sensors must be calibrated with attention to these influences. The vibration waveforms of vibrating objects are estimated by acoustic measuring methods, such as the laser Doppler vibrometer and the parallel-phase shifting interferometry. This paper describes calibration methods of millimeter-wave vibration sensors employing these two measuring methods.

Transformer vibration fault detection based on spectrum analysis

Measuring the vibration signal of transformer is one of the ways to verify whether the transformer is faulty. In this paper, taking the vibration detection of transformer as the technical starting point, the signals before and after the vibration fault of transformer are compared by frequency spectrum analysis, and the vibration fault detection of transformer is realized. The vibration test system is constructed and tested in the field. The results show that the non-contact vibration sensor can be used to detect the uninterruptible power failure of the transformer through spectrum analysis and processing, which is simple, safe and reliable, and has good application value.

Non-contact vibration sensor using deep learning and image processing

This paper proposes a non-contact vibration measurement method based on deep learning and image processing. The deep learning method is used to realize the automatic and efficient selection of effective pixels and the optical flow method is used to extract vibration signals to realize non-contact and targetless visual vibration measurement. In this study, a carbon plate board and aluminum C-beam structure were measured and verified under artificial and non-human excitation in a laboratory environment. Additionally, bridge and cable structures in an outdoor environment were selected as measurement targets to verify the reliability of the proposed method. This paper compares the experimental results of Canny and Sobel edge detection algorithms and deep learning methods to verify the efficiency of deep learning. The results demonstrate that our method is robust, even under real-world unfavorable conditions, meaning it can serve as a novel measurement method in the field of vibration measurement.

Support vector machines based non-contact fault diagnosis system for bearings

Bearing defects have been accepted as one of the major causes of failure in rotating machinery. It is important to identify and diagnose the failure behavior of bearings for the reliable operation of equipment. In this paper, a low-cost non-contact vibration sensor has been developed for detecting the faults in bearings. The supervised learning method, support vector machine (SVM), has been employed as a tool to validate the effectiveness of the developed sensor. Experimental vibration data collected for different bearing defects under various loading and running conditions have been analyzed to develop a system for diagnosing the faults for machine health monitoring. Fault diagnosis has been accomplished using discrete wavelet transform for denoising the signal. Mahalanobis distance criteria has been employed for selecting the strongest feature on the extracted relevant features. Finally, these selected features have been passed to the SVM classifier for identifying and classifying the various bearing defects. The results reveal that the vibration signatures obtained from developed non-contact sensor compare well with the accelerometer data obtained under the same conditions. A developed sensor is a promising tool for detecting the bearing damage and identifying its class. SVM results have established the effectiveness of the developed non-contact sensor as a vibration measuring instrument which makes the developed sensor a cost-effective tool for the condition monitoring of rotating machines.

Study on the non-contact FBG vibration sensor and its application

A non-contact vibration sensor based on the fiber Bragg grating (FBG) sensor has been presented, and it is used to monitor the vibration of rotating shaft. In the paper, we describe the principle of the sensor and make some experimental analyses. The analysis results show that the sensitivity and linearity of the sensor are −1.5 pm/μm and 4.11% within a measuring range of 2 mm–2.6 mm, respectively. When it is used to monitor the vibration of the rotating shaft, the analysis signals of vibration of the rotating shaft and the critical speed of rotation obtained are the same as that obtained from the eddy current sensor. It verifies that the sensor can be used for the non-contact measurement of vibration of the rotating shaft system and for fault monitoring and diagnosis of rotating machinery.

A non-contact fiber Bragg grating vibration sensor

A non-contact vibration sensor based on fiber Bragg grating (FBG) sensing has been proposed and studied in this paper. The principle of the sensor as well as simulation and experimental analyses are introduced. When the distance between the movable head and the measured shaft changed, the diaphragm deformed under magnetic coupling of the permanent magnet on the measured magnetic shaft. As a result, the center wavelength of the FBG connected to the diaphragm changed, based on which the vibration displacement of the rotating shaft could be obtained. Experimental results show that the resonant frequency of the sensor is about 1500 Hz and the working band ranges within 0-1300 Hz, which is consistent with the simulation analysis result; the sensitivity is -1.694 pm/μm and the linearity is 2.92% within a range of 2-2.4 mm. It can be used to conduct non-contact measurement on the vibration of the rotating shaft system.

Non-Contact Vibration Sensor Using Bifurcated Bundle Fiber for Real Time Monitoring of Diesel Engine

A non-contact vibration sensor is demonstrated using bifurcated bundle fiber based on the principle of extrinsic reflective intensity modulation for monitoring the health condition of the diesel engine. An IR-source is used along with glass fibers to avoid the effect of stray light in sensing. The encapsulation of the sensor enables easy alignment, flexible handling and usage in harsh environments. The sensor is capable of measuring the frequencies up to 650Hz with vibration amplitude resolution of 10µm, enough to monitor the vibrations generated in heavy machines like diesel engine.

Vibration Characteristics of Various Surfaces Using an LDV for Long-Range Voice Acquisition

Laser Doppler vibrometers (LDVs) as non-contact vibration sensors have an ability of remote voice acquisition. With the assistance of a visual sensor (camera), various targets in the environment, where an audio event takes place, can be selected as reflecting surfaces for collecting acoustic signals by an LDV. The performance of the LDV greatly depends on the vibration characteristics of the selected targets (surfaces) in the scene, on which a laser beam strikes and from which it returns. In this paper, the relations of a target's material and structural properties with its vibration characteristics are studied, and a vibration amplitude model is established. Then the vibration characteristics of several typical surfaces with different materials and structures are explored through both simulations and real-sensor experiments. Based on their responses to the frequencies in the range of human voice, the targets are classified into three categories by the number of fluctuations (zero, one, or two) in their vibration returns in the range of speech. Some short- and long-range experimental results are presented for the speech acquisition from surfaces of these three categories, and their feasibilities in speech acquisition are also evaluated.

Wavelet analysis of optical signal extracted from a non-contact fibre-optic vibration sensor using an extrinsic Fabry–Perot interferometer

Interferometric optical fibre sensors have proved to be many orders of magnitude more sensitive than their electrical counterparts, but they suffer from limitations in signal demodulation caused by phase ambiguity and complex fringe counting when the output phase difference exceeds one fringe period and for multiple fringes. This paper presents a novel signal decoding technique based on the wavelet transform of optical data extracted from a non-contact vibration sensor using an extrinsic Fabry–Perot interferometer (EFPI) implemented using single-mode fibre. The EFPI cavity has been used to generate an optical interference signal between two parallel, highly reflective surfaces separated by a variable distance. Firstly, a few recorded experimental results of the interference fringe formation due to vibration are presented in this paper. Then the wavelet transform is used for decoding the vibration signature for three major purposes of the data analyses, namely elimination of noise from the optical signals collected in real time, identification of the frequency breakdown points of the signal efficiently and automatic counting of the interference fringes. In turn, the wavelet transform is successfully employed to decode the vibration signature from the non-stationary output signal of an EFPI sensor.

Noncontact vibration sensors based on current modulated external cavity semiconductor lasers

An improvement in performance and design of noncontact vibration sensors based on external cavity semiconductor lasers is demonstrated. A technique for narrowing RF spectral peaks in external cavity lasers with moderate optical feedback by direct current modulation is explained. Current modulation frequencies suitable for use with developed position and vibration sensors are identified. Improvements in accuracy and resolution for the sensors are recorded and illustrated.

MICROWAVE INTERFEROMETERS FOR NON-CONTACT VIBRATION MEASUREMENTS ON LARGE STRUCTURES

This paper describes a non-contact vibration measuring system that is based on a microwave interferometer similar to those used to detect the presence of people in monitored areas. Displacement response of a target surface on the structure relative to the interferometer is measured by analysing the interference in microwaves reflected off the vibrating target surface. The system was built from commercially available off-the-shelf electronic components and, unlike most commercially available far-field non-contact vibration sensors, it does not require a mounted target when used to measure the response of metallic and concrete structures. In this study, the interferometers are coupled with homodyne detection hardware and software to make low-noise measurements during swept-sine tests. These interferometers can also be used to detect static displacements and the transient response of the structure. In addition to its non-contact feature, this system offers other advantages including low cost, quick set-up time, a wide frequency range of response and portability. An application of these sensors to the measurement of vibration response on a bridge structure in a non-contact manner is summarised. Resonant frequencies of the bridge that were identified with the microwave interferometers are compared to similar quantities measured with conventional accelerometers. In all cases, resonant frequencies identified from data obtained with the microwave interferometers were within 2.2% of the resonant frequencies determined from data obtained with the conventional accelerometers.