At present, machine vision roughness detection mostly needs to design roughness related indexes based on images, and the index design has human intervention and is heavily dependent on the light source environment. To solve this problem, the paper classifies the surface roughness based on the deep convolutional neural network method, which can realize the roughness detection without index design. The

3D surface topography provides critical information about surface textures and has begun to be used in additive manufacturing applications such as in-situ 3D monitoring and sample porosity comparisons, etc. In this research, we establish a thorough framework to quantify the similarity of 3D surface topography measurements and determine whether they are from the same surface or not based on the frequency

Positioning errors are a primary performance indicator of precision stages. Calibration of stage positioning errors usually requires expensive, specialised instruments or artefacts. In this paper, we introduce a simple and cost-effective, machine vision-based method for stage error calibration. The novelty is that we used an arbitrarily textured plane, for example an array of coins, as the imaging

To achieve an accurate structural health assessment, data collected by multiple sensors needs to be fused effectively. When the number of sensors is limited, it is necessary to determine the reasonable position of sensors and adopt the adequate fusion method. Therefore, a structural health assessment method based on evidential reasoning (ER) rule considering the optimal sensor placement (OSP) is proposed

This paper is dedicated to dealing with the recursive filtering problem for a class of microseismic signal arrival time picking with dynamic transmission mechanism (DTM) and sensor saturation (SS). Firstly, the microseismic wave and its environmental noise are established as an exponentially decaying cyclic wave and a Markov process, respectively, and then the state space expression of the microseismic

Transfer learning has good ability to transfer knowledge for fault diagnosis under working condition, while domain mismatches or domain shift can still occur during single-source domain transfer fault diagnosis. To alleviate the problem, a multi-source ensemble domain adaptation method is proposed for rotary machinery fault diagnosis. Firstly, multi-source and target domain anchor adapters are constructed

Ultrasonic measurement is an effective technical method for the bolt stress detection of the precise structural connection. This paper proposed an acoustic time difference algorithm based on adaptive hybrid extended Kalman filter to reduce the calculation error of acoustic time difference in bolt stress ultrasonic measurement. The initial value is firstly selected by particle filter algorithm, and

For the high-demand operating safety and flight safety, the hysteresis dead-zone as a health indicator (HI) related to backlash abrasion is proposed for health monitoring and prediction of aircraft mechanical control systems (MCSs). First, a multi-backlash mass-damper-spring (MDS) model is built for MCSs degradation simulation to demonstrate the HI’s validity. Then, by comparing with Prandtl-Ishlinskii

Particle image velocimetry (PIV) is an experimental approach widely used to investigate the flow inside stirred tanks. PIV noise sources deteriorate the velocity fields and compromise the measurements, mainly in the estimation of the turbulent parameters. PIV correction approaches based on the primary peak ratio (PPR), namely the ratio between the primary correlation peak to the second highest peak

To increase the test sensitivity, the resonance theory was introduced to the magnetoelastic method. After analyzing the correlation between the stress and the induced voltage, the resonance enhanced magnetoelastic (REME) method was proposed. A REME sensor with a low resonant frequency was made to carry out the experiment. The results showed that the resonant frequency, the resonant voltage, and the

Advanced developments of Industrial Cyber-Physical Systems (CPSs), comprising Internet of Things (IoT) finds useful in several application areas such as transportation, smart cities, healthcare, energy distribution, agriculture, etc. At the same time, the increased utilization of industrial CPS offers many threats which could have major significances for users. Recently, cognitive computing and artificial

The aim of this paper was to describe the interdependencies between the surface areas of characteristic FTIR spectral bands, reflecting the amounts of chemical substances generated during oil deterioration in engine, and the mileage of the cars depending on the oil used. The tested engine oils were used in 12 similar vehicles operated in similar conditions and an attempt was made to describe the differences

Aiming at the problem of low measurement efficiency of conventional single-point chromatic confocal technology, a one-shot chromatic confocal measurement system based on DMD (Digital Micromirror Device) is presented in this paper. This system was set up by applying a polychromatic light source, a color camera, a dispersive lens, and DMD. Firstly, the DMD was used to modulate the polychromatic light

Aiming at the problem that the systematic errors affect the coaxiality measurement accuracy of turbine shaft, this paper proposes a seven systematic errors measurement model which considers eccentricity, workpiece tilt, probe offset, probe radius, probe strut tilt, horizontal and vertical guide rail tilt. Considering the unequal interval distribution of sample angle, this paper designed an unequal

Water pipeline leakage is a common and significant global problem. In-pipe inspection based on hydrophone is one of the most direct, accurate, and reliable solutions for leak detection and recognition. In this study, a scheme of in-pipe detector was designed to pick up and identify acoustic signal due to leak. To investigate the characteristic of acoustic signal, an experimental platform was built

We present an approach based on computer vision and machine learning methods to identify two-phase flow with complex flow patterns in oscillatory conditions. A visualization experiment bench was designed, constructed, and used to simulate the actual reciprocating motion of the cooling gallery inside the piston of low-speed diesel engines. The results of our proposed approach show that the feature vectors

Order tracking (OT) of vibration envelope signal based on instantaneous frequency (IF) estimated from a time-frequency representation (TFR) is generally applied to detect bearing defects under time-varying speed conditions. However, these TFR based OT approaches require a high resolution for accurate estimation of the IF. To overcome these issues, a tacholess OT technique based on the fast dynamic

As solar power becomes more important, sunshine duration has become a critical variate for meteorological observations and research. In this review, the evolution of the operation principle and construction of sunshine recorders was summarized. Sunshine recorders were classified according to their measurement methods, and their historical and technological development were reviewed. Characters, such

For clayey soil, an effective solution to accelerate pore water pressure dissipation after pile installation is using permeable piles. But the differences in bearing capacity efficiency between permeable and normal piles are still unclear. In this paper, a series of load tests were conducted on permeable and normal piles. The bare fiber Bragg grating (FBG) sensors were used to explore the pile-soil

To eliminate the electromagnetic deceleration force, remove the limitations of striker bar’s length and improve the efficiency for the miniature split Hopkinson pressure bar (mini-SHPB) device, the electromagnetic launch system and energy supply system are improved. The series-parallel coil array launch structure is proposed. The multi-winding parallel coils discharge rapidly to eliminate electromagnetic

Continuously distributed sensors (CDS) disclose a principally new way to provide space distribution measurements for different physical fields, such as temperature, velocity and light intensity fields. The design of one-dimensional CDS and corresponding pulse measurement method are proposed. The numerical algorithm implementing the pulse measurement method are obtained based on inverse operator problem

This paper presents a study to improve the calibration process of a calorimetric sensor for medical application. The sensor has been designed for determination of the heat loss, heat capacity and equivalent thermal resistance of the skin region on which the sensor is applied. Localized constants models have been found to be effective. For a good calibration of the sensor, suitable experiments have

A sensitive frequency f margin SFM has been determined for quantification of aggregated interstitial protein concentrations Фprot by frequency difference electrical impedance tomography fd-EIT. Impedances of increasing Фprot of albumin-globulin mixtures in phantoms were measured and changes in protein’s adjacent f point conductivity Δσadj and loss factor Δε''adj plotted against f to determine a Фprot

The earth is constantly being changed by natural events and human activities that constantly threaten our environment. Therefore, accurate and timely monitoring of changes at the surface of the earth is of great importance for properly facing their consequences. This research presents a new hyperspectral change detection (HCD) framework based on a robust binary mask and convolutional neural network

The unstable movement of the cage directly affects the performance of the high-precision ball bearing. Because the cage is located inside the bearing, and affected by the working conditions and lubrication states, its dynamic characteristics are extremely complicated, the existing theory and experimental methods are difficult to evaluate the stability of the cage effectively. This paper presents an

Nondestructive testing and evaluation (NDT&E) are commonly used in the industry for their ability to identify damage and assess material conditions. Ultrasonic testing (UT) is one of the most popular NDT&E techniques. A variant of ultrasonic testing known as nonlinear ultrasonic testing (NUT) has some advantages over conventional (linear) UT as it is more sensitive to damages in their early stages;

Internet of Things (IoT) provides more and more adequate infrastructures for many applications and advanced services. This context promotes the ability to satisfy the growing demand for innovative measuring systems, increasingly popular with intelligent nodes, totally wireless, easy to install that require the least possible maintenance. This paper aims to contribute to the state-of-the-art with an

In order to solve the problem of measuring the spatial position of each projectile that are fired using multi-barrel weapons in high-frequency continuous firing modes, this paper proposes a new method to measure the spatial position of multiple projectiles with dual light field intersection imaging mechanism. According to the four-dimensional light field imaging information of light field camera and

Acoustic-based diagnosis (ABD) is a promising method for machinery fault detection due to its ability of non-contact measurement by air-couple. However, most of the ABD methods are constrained by strong and highly non-stationary background noise interference in practical industrial application. To address the shortcoming, a novel anti-noise ABD method based on recursive attention mechanism (RAM) is

Unsteady aerodynamic loads have a significant influence on the running safety of a train in crosswinds. Full-scale tests were carried out to measure the pressure on a fast streamlined train in crosswinds, and the unsteady aerodynamic loads were obtained by the discrete integration of the pressure to assess the influence of different crosswinds on the loads. The maximum wind speed was 34.0 m/s in the

The regulation existing on NORM activities requires the accurate and quick measurement of natural radionuclides in a wide range of matrices by gamma spectrometry. The aim of this work has been to develop a comprehensive and accurate methodology to determine natural long-lived radionuclides (210Pb, 228,226Ra, 234,228Th and 40K) by gamma spectrometry with Ge detectors in NORM samples. An exhaustive calibration

Towed transient electromagnetic method (TEM) is an efficient geophysical method for urban underground space measurement. However, compared with the field environment, the power harmonic noise as urban electromagnetic noise is the key reason for the low signal-to-noise ratio (SNR) of the towed TEM data. We propose an efficient preprocessing method based on a multi-step processing strategy, which can

Electric rudder system exerts an immense influence on the movement of aircraft, missiles and ships. To solve the problem of low automation in traditional rudder system, we developed a novel intelligent electric rudder system test equipment, and proposed a new machine learning algorithm for fault diagnosis. This study mainly focuses on the multidimensional data set test and fault diagnosis of the rudder

In the paper an attempt was made to evaluate influence of type (maltodextrin, gum Arabic and inulin) and content (50, 60, 70% solids) of carrier on quality of raspberry powders. The different types of powders were compared taking into account the structure of microparticles, water activity and their humidity. The use of modern methods such as: low temperature spray drying, artificial intelligence together

The large number, scattered distribution, and complex working environment of idlers makes their faults challenging to detect. In this paper, a fault analysis method of belt conveyor idlers based on sound and thermal infrared image (TII) features is proposed. According to 18 classes of idler sound and TII data, the time-domain (TD) features of sound signals are analysed using statistical methods, the

Undesired dynamic characteristics constitute a major source of dynamic measurement errors for contact probes and seriously restrict the improvement of measurement velocity and accuracy. However, the dynamic characteristics of probes are difficult to improve through structural enhancement. A novel dynamic compensation method based on Bayesian inversion was proposed to improve the dynamic performance

The sensor-based structural health monitoring (SHM) systems are widely embedded in the new-constructed and rehabilitated dam. Due to the harsh working environment, poor installation, and sampling error, sensor fault often inevitably occurs. In this paper, rather than using conventional Gaussian process regression(GPR) to reconstruct missing data from multiple sensors independently, we propose a multi-task

The standard deviation of the nonlinear functional value can be obtained by the law of covariance propagation. Existing covariance propagation methods of the nonlinear model contain the following problems: the approximate function method requires complicated derivative operation; the Monte Carlo method has a high simulated burden and low convergence effectiveness. To overcome these disadvantages, we

Landslide displacement monitoring is an efficient method to mitigate casualties and economic losses caused by landslide disasters. In recent years, distributed fiber-optic sensing technology, due to distributed and long-distance advantages, was widely used in subsurface displacement monitoring of landslides. However, existing fiber-optic displacement sensors has a large monitoring error when the landslide

Detection of micro-cracks before assembling has always been a challenge in gear defect detection. A mature detection method of micro-cracks is not available. Due to the complex detection environment and large production of gears, it’s urgent to develop a rapid and accurate detection method of gear micro-cracks. It’s the key to separate and extract weak vibration signals accurately under complex disturbances

Four-mirror-assisted single-camera stereo-digital image correlation (stereo-DIC) system overperforms conventional two-camera stereo-DIC system in terms of system compactness, cost investment and easy implementation. However, how to design a suitable four-mirror adaptor orienting a specific demand has not been clearly described in previous researches. To address this issue and satisfy practical requirements

Elaboration of the technology of the multicomponent Quantum Wells (QWs) based devices requires repeated time consuming diffraction curves analysis proceeded for each of the grown structures to determine their basis structural parameters. Optimization of the diagnostic procedures and making them more efficient is the key point from the manufacturer point of view. In this paper we present the use of

Regression modeling is one of the most widely used statistical processes to estimate the relationships between dependent and independent variables, which have been frequently applied in a wide range of applications successfully. This method includes many techniques for modeling and analyzing several variables to cover real-world problems. The performance basis in conventional regression modeling is

Accurate traffic conditions and their development regularity can help in the management of future traffic demand and bridge design. This study proposes a bridge weigh-in-motion method for identifying the vehicle parameters of motorway bridges considering random traffic flow and capitalizes on the advantages of long-gauge fibre Bragg grating sensors. A bridge-vehicle coupling system is numerically simulated

As the temperature has a great effect on the cycle life and capacity of power battery on electric vehicles (EVs), a practical battery thermal management (BTM) strategy is required to adjust the battery temperature within an appropriate range and reduce the temperature inconsistency in the battery module. To achieve the multiple objectives, a nonlinear model predictive control (NMPC) method is proposed

Brakes in mechanical equipment are crucial for operational safety, and their effects are directly affected by friction performance. The fault signal induced by friction interface presents the phenomenon of multi-source, and the fault samples are difficult to obtain in practical engineering. Both aspects yield unsatisfactory recognition performance of diagnosis models. To address the issues, in this

Sparse representation is one of the effective approaches for bearing fault diagnosis. Conventional sparse representation only focuses on fault feature extraction from bearing vibration signals while requiring experts to empirically make a diagnosis. This paper investigates bearing intelligent fault classification based on sparse representation based classification (SRC) method. A novel SRC algorithm

Fault diagnosis methods based on signal analysis techniques are widely used to diagnose faults in gear and bearing. This paper introduces a fault diagnosis model that includes a multi-scale deep residual learning with a stacked long short-term memory (MDRL-SLSTM) to address sequence data in a gearbox health prediction task in an internal combustion (IC) engine. In the MDRL-SLSTM network, CNN and residual

Accurate judgment of gear working state is essential to the normal operation of mechanical equipment. To effectively extract the dynamic features representing the gear state from the vibration signals, this paper proposes refined composite hierarchical fluctuation dispersion entropy (RCHFDE), where the composite hierarchical decomposition is employed to replace the traditional hierarchical decomposition

This study proposes a measurement system to detect spalling phenomena of ball-type constant velocity joints (CVJ). The spalling phenomena that usually occur in the inner race of a CVJ are a significant factor to the CVJ’s life, but it is very difficult to measure the spalling because the inner race is mechanically enclosed by an outer race and a cage. The developed system can not only detect the spalling

The refraction phenomenon of light at the interface of different media causes the epipolar to bend (the traditional camera model is invalid), and the stereo matching can’t be performed under the row matching. Therefore, we proposed a new model based on light field, in which an underwater image is expressed with the direction-information image and position image. The underwater stereo matching is conducted

A method is proposed in this paper to automatically estimate the workability of six different strength grades concrete by recording the mixing process based on deep learning. The concrete mixing videos were collected in a specially designed set up fixed on a mixer located in the mixing station. These videos were transformed into a series of image sequences to fit the deep learning model to predict

Flowrate being one of the most measured process parameters, thus it is essential to produce higher accuracy. The objective of the paper is to design an estimator using the Linear Parameter Varying (LPV) model which would estimate the flow rate using the data from the orifice meter for varying parameters like, the beta ratio of an orifice, and liquid density. For the development of an estimator, a process