This research proposes a novel predictive model to improve the gas prediction accuracy in transformer oil and provide guarantees for accident prevention. First, this study constructs a cross-entropy loss function with variable thresholds and dynamic weights to reduce error transmission in the deep residual shrinkage network, enhancing the sensitivity of the normal and abnormal transformer states by

Inspection of defects in weld has both safety and economic significance in industries. However, it is still a challenging problem to be studied due to the interference of the uneven surface of the weld and nonuniformity of the material. This article proposes a new flexible eddy current testing (ECT) probe with differential multimodes for weld inspection. The probe is constructed based on a flexible

An image reconstruction algorithm, which is developed for a 12-electrode capacitively coupled electrical resistance tomography (CCERT) system under 2-electrode excitation strategy, is proposed. Based on L-curve and Reginska’s method, truncated singular value decomposition (TSVD) is used to reconstruct the initial image. The algebraic reconstruction technique (ART) algorithm is used to obtain the final

Light field image (LFI) records the radiation intensity and direction information of light in scene, offering powerful capabilities for computer vision. It is found that the distortion caused by LFI processing is obviously reflected in the two representations of LFI, that is, subaperture images (SAIs) and microlens images (MLI). Specifically, on the one hand, pseudoreference SAI (PSAI) of a distorted

This study is concerned with the analysis of the displacement measurements simultaneously retrieved from multiple Doppler radars placed at different positions of a traffic light’s mast. Currently, the structural health monitoring (SHM) works based on portable Doppler radars consider primarily methods for the extraction of displacement measurements. However, other measurements in the form of instantaneous

The measurement of ac/dc hybrid electric fields in converter transformers is important for the verification of electric field calculation model and the insulation optimization. Electro-optical (EO) sensors have obvious advantages for measuring strong electric fields, but their response characteristics and mechanisms under the action of ac/dc hybrid electric fields are not fully understood by researchers

An algorithmic instrumentation amplifier (INA) with dynamic analog signal processing (DASP) is presented in this article. The proposed approach is based on any basic INA (BINA) subjected to a simple algorithmic operation performed by DASP. The resulting common-mode rejection ratio (CMRR) equals double squared CMRR value of the BINA, with no need for any additional matching. The prototype has been made

This article presents an offline deep learning approach focused to model and identify a 270- to 28-V dc–dc step-down converter used in on-board distribution systems of more electric aircrafts (MEAs). Manufacturers usually do not provide enough information of the converters. Thus, it is difficult to perform design and planning tasks and to check the behavior of the power distribution system without

To reduce the ranging error, a field programmable gate array (FPGA) pulse laser ranging method based on deep learning is proposed. By simulating the echo waveforms, the deep learning sample data are constructed to train the ranging convolutional neural networks (CNNs), and the influences of different convolution kernels numbers and noise levels on the performance of the ranging neural network are analyzed

The tactile sensor design and data measurements have been playing an important role in surface material recognition. In inevitable unstructured environments, the performance of the material classification is bottlenecked by multimodal deficiency or data collection intermittency. This article investigates the influence of surface tactile data quantity on material classification in unstructured environments

Multisource information perception is the basic means for humans to explore the universe, and information decision fusion has become a crucial technique in some fields. Limited by the unknown distribution of multisource information, this article proposes a decision fusion method based on the distributed wavelet neural network (DWNN) and the Bayesian inference. The proposed fusion decision framework

Due to the strong dynamic and time-varying characteristics of the surface electromyography (sEMG) signal and the coupling between lower limb muscles, it is challenging to accurately estimate the joint angle of complex lower limb motion. Firstly, we proposed a wavelet packet decomposition correlation dimension (WPD_CD) analysis method. A three-level wavelet packet decomposes the sEMG signal, and the

Our society exhibits a worldwide trait of a quickly growing cohort of patients with neurodegenerative diseases, such as Parkinson’s disease (PD). According to the analysts, there is a plausible “PD pandemic” to occur within the next two decades. Nowadays, the research in the area focuses on how to detect, predict, or classify PD and similar diseases without addressing the point of what activities or

As a typical safety-critical system, satellite has extremely stringent requirements for reliability. However, some satellite components, especially attitude sensors, are prone to suffer from performance degradation or even drastic failure in space environment, which leads to serious threats to satellite. A series of fault diagnosis methods have been investigated to diagnose these failures. However

In recent years, more and more researchers are using deep learning to monitor and diagnose mechanical equipment faults. When new task data not considered in the training stage are generated during the operation of the equipment, it is difficult for the model to recognize this type of data. If only new task data are used in training, it will lead to poor performance in the old task. When using all the

In modern industrial systems, the processes often operate under different modes. Potential fault diagnosis and mode identification are extremely vital to maintain the system safe and reliable. Recently, many methods have been proposed to address these problems separately. Moreover, many of them make an assumption that the data from industrial site only contain the Gaussian noise. However, this assumption

Partial discharge (PD) detection and localization is one of the most effective methods in gas-insulated transmission lines (GIL) insulation fault diagnosis, which is important to the early troubleshooting and safe operation. Compared with the widely used ultrahigh frequency (UHF) and acoustic PD localization methods, the PD localization method based on optical signals has good resistance to electromagnetic

Polymerase chain reaction (PCR) is the gold standard method to amplify deoxyribonucleic acid (DNA) fragments. Several methods have been used to miniaturize and integrate PCR to execute in a microfluidic platform. A continuous-flow-based microfluidic PCR device permits the required rapid thermal cycling and multiplexing, which are hard to realize in a benchtop PCR or microchamber PCR. This work aims

In this study, transverse heat flow suppression (THFS) technique was proposed to enhance the ability of thermal-wave radar thermography (TWRT) to resist lateral thermal diffusion and uneven heating. The enhanced TWRT was used to detect subsurface defects of carbon fiber reinforced plastic (CFRP) laminates. The principle of THFS was described in detail by the optical flow analogy. The three-dimension

The article presents the findings of main recent research and development works conducted for gas leak detection and measurement. Higher emphasis are considered for 2-D arrays sensors because of the wider coverage area they can handle in real-time, especially if they are carried within moving vehicles such as drones, helicopters, and satellites. This includes long-wave infrared (LWIR)- and medium-wave

The calibration of camera systems employing zoom lenses raises several challenges, as changes in lens control settings introduce various imaging conditions, especially different degrees of defocus. This article presents a Fourier-based defocus calibration method to calibrate a camera attached with an electronically focus-tunable lens (ETL). Different from the traditional method which requires changing

Aiming at the problems of complex background, tiny-size objects, long-tailed distribution, and so on, a hybrid knowledge region-based convolutional neural network (HK R-CNN) is proposed to detect multiple fittings in aerial images of transmission lines. First, the structure combination rules of transmission line fittings are studied, and the relationships of co-occurrence connection and spatial location

In the process of product assembly, parts need to be assembled in a given assembly sequence. Failure to detect the correctness of the newly assembled parts in time can affect the quality and assembly efficiency of products. For effective detection of newly assembled parts in the assembly process from different viewing angles, this study applies scene change detection to mechanical assembly monitoring

Brass (e.g., H80 brass) is widely used in different industrial sectors. To ensure its quality and reliability, the stress damage state of brass has to be monitored and analyzed in practice. This article introduces a new micro-magnetic method for monitoring and analyzing the tensile stress damage state of brass. Specifically, the stress-magnetic flux density model of H80 brass in the micro-magnetic

Brittle fracture of the composite insulator is a malignant accident. There is a lack of means to monitor the formation and expansion of stress corrosion cracking in rods, resulting in little understanding of the process of brittle fracture development. First, this article proposes a mechanical model for identifying cracks in rods by the wavelength shift trends of fiber Bragg gratings (FBGs). Second

Eddy current pulsed thermography (ECPT) is widely used in the nondestructive testing (NDT) of metal surface defects. Because defect information is sometimes affected by the edge effect, it is necessary to segment the ECPT image sequence, that is, separate the defected part from the background, to improve the detection effect. Tensor robust principal component analysis has been widely used in many image

Ultraviolet light-emitting diodes (UV LEDs) have been widely applied in various fields, such as sewage treatment, sterilization, and disinfection medical treatment. However, the remained problems of UV LEDs mainly concern poor photoelectric stability, low efficiency, safety protection, and among others. In order to evaluate and predict the stability and lifetime of UV LEDs safely and efficiently, a

Most of the existing robot calibration methods have high technical requirements for the installation of end tools and detection sensors as well as other calibration equipments involved, which makes the calibration cumbersome and expensive. This article proposes a novel and easy pose-error calibration method for articulated serial robots based on three-closed-loop transformations. First, the principle

In this article, we present a novel flowrate measurement method for horizontal gas–water slug flow from the differential pressure of a Venturi tube and the average liquid film thickness from a conductance sensor, which can be developed into a promising cost-effective flowrate measurement solution. First, a Venturi differential pressure model for slug flow is proposed based on de Leeuw’s overreading

Time delay is a novel celestial navigation measurement that can provide the distance information of the spacecraft relative to the nearby celestial body. Combining time delay measurement with traditional star angle measurement can greatly improve navigation performance. However, the navigation accuracy will be affected by the ephemeris error of the nearby celestial body. To solve this problem, this

In this article, a new method is proposed to identify the health condition of composite insulators through investigating the leakage current (LC) along with the electric potential (EP) and electric field stress (EFS) profiles. In this regard, variations of the LC harmonics and the distribution profiles of the EP and EFS are investigated through a series of experimental and simulation analyses conducted

This article proposes an auxiliary framework to address the challenges of transformer differential protection for single-phase transformers or three-phase transformer banks. This framework enables the differential scheme to: 1) work properly if transformers or current transformers (CTs) saturate; 2) detect internal and cross-country faults; 3) detect internal faults while energizing transformers; and

The target motion analysis (TMA) based on multiple hybrid sensors is currently performed with a batch algorithm, which is generally memory-demanding for online applications. This article proposes a recursive estimator for the batch counterpart with sequential calculation for multistatic TMA using hybrid measurements of the angle of arrival, time difference of arrival, and frequency difference of arrival

Xylene is a toxic carcinogen, which may irritate eyes and respiratory tract, or damage the central nervous system. However, the traditional semiconductor gas sensor can only detect the ppm level of xylene gas, which cannot meet the building air quality monitoring requirements. Therefore, the development of low concentration gas detection of xylene gas sensor is necessary. In this article, a one-step

The printed circuit board Rogowski coil (PCB RC) has been widely applied in the complex electromagnetic environment, such as power electronic devices, where it is placed outside but very close to current-carrying conductors; thus, this brings great challenges to the anti-interference ability of it. Generally, the anti-interference ability of PCB RC is greater with more turns; however, the number of

Point clouds from 3-D light detection and ranging (LiDAR) are useful for roadside units (RSU) applications in intelligent transportation system (ITS). High-density LiDAR products are restricted by high cost while the low-density and cheap ones are usually insufficient to perceive. Event-based cameras react to the changes in light intensity and output dense event streams consisting of triggered pixels

During the last years, different methods for identifying permanent magnet synchronous motor (PMSM) parameters have been developed. Such methods allow a better characterization of PMSMs, thus enabling a better control. This article presents a novel PMSM parameter estimation method based on the differential power factor due to the harmonic distortion, which allows the identification of the motor parameters

Intelligent tool wear recognition techniques have great significances to guide the cutting process in automated manufacturing systems. Traditional methods heavily rely on human experience and fail to consider the impact on processing. In this article, a novel deep kernel autoencoder (DKAE) feature learning method optimized by the gray wolf optimizer (GWO) is proposed for tool wear state intelligent

For pneumatically operated train doors, continuous monitoring and earlier detection of air leakages would greatly reduce train downtime and ensure both safety and high availability of the rail system. Deep learning, a powerful tool to extract useful information from a large amount of sensor data is widely used in fault detection. A large collection of known fault samples is necessary to generate reliable

The 3-D measurement methods based on fringe projection intensity adjustment (FPIA) have been widely adopted to measure the multireflectivity scenes. However, the signal-to-noise ratios (SNRs) of the captured fringe patterns in the FPIA-based methods are reduced because of a large range of reflectivity variations (LRRVs). In our research, a reflection model and a crosstalk model are built to analyze

In this article, a novel low-light image enhancement (LIME) using reflection model and principal component analysis (PCA) has been proposed. The proposed algorithm works adaptively for dark images based on reflection model and multiscale principle. An input RGB color image is first stretched to correct any type of color distortion and then converted to HSV color space. By using the concept of multiscale

Surface defect detection is a challenging task in industrial manufacture. Recent methods using supervised learning need a large-scale dataset to achieve precise detection. However, the time-consuming and the difficulty of data acquisition make it difficult to build a large-scale dataset. This article proposes a domain adaptive network, called multiscale adversarial and weighted gradient domain adaptive

The goal of photometric stereo is to measure the precise surface normal of a 3-D object from observations with various shading cues. However, non-Lambertian surfaces influence the measurement accuracy due to irregular shading cues. Despite deep neural networks being used to simulate the performance of non-Lambertian surfaces, the error in specularities, shadows, and crinkle regions is hard to be reduced

Accurately measuring the mass flow of molten iron at the bottom of a blast furnace is of great significance for energy savings and efficient operation in the iron making process. However, the lack of texture information on the surface of molten iron will severely limit the accuracy of conventional displacement reconstruction algorithms. To this end, this article presents a methodology based on trusted

Assembling crankshaft bearing caps (CBCs) on automobile engine is a vital and complicated task that manual work is usually inefficient and become more prone to error. In this article, an autofeeding system with vision and line laser combined with an industrial object location and classification method is proposed for assembling the CBCs. First, an improved fully convolution one-stage network is used

An underwater caterpillar vehicle has been designed and developed to profile along the beach and shoreface. This prototype is employed for zones that are unsuitable to study through bathymetry or manual measurements. The system consists of a metallic structure propelled by two caterpillar tracks. An electronic accelerometer and a GPS receiver measure the profile data. These components provide the seabed

Integration of microelectromechanical system-based inertial navigation system (MEMS-INS) and global positioning system (GPS) is a promising approach to vehicle localization. However, such a scheme may have poor performance during GPS outages and is less robust to measurement noises in changeable urban environments. In this article, we give an improved extended Kalman filter (IEKF) using an adaptation

Water holdup measurement in multiphase flow with varying water salinity is a significant and challenging research topic. In this study, a new microstrip-antenna-based microwave transmission sensor (MAMTS) and a new decoupling method are proposed to achieve salinity independent measurement of water holdup in oil–gas–water slug flows. The MAMTS is formed by two identical microstrip antennas whose configurations

The accuracy of gravity disturbance horizontal components is an obstacle in strapdown airborne vector gravimetry at present. In the strapdown inertial navigation system (SINS) field, the rotation modulation technique has been put into practice to improve the accuracy of navigation for decades, which could suppress the divergence of SINS errors. Since there is a close connection between SINS and strapdown

This article presents a two-step stochastic hybrid estimation (TS-SHE) algorithm for robust and accurate carrier phase tracking of global navigation satellite system (GNSS) signals in urban environments with significant power degradation and fluctuation. The proposed algorithm adaptively combines a bank of parallel Kalman filters (KFs) with different dynamic state models to cope with the nonstationarity

This article presents a newly invented emergency positioning system deployed on a satellite communication on-the-move (SOTM) platform, which can extend the SOTM communication function to the positioning function. Inherent to the SOTM system’s high reliability, this emergency positioning system can effectively estimate the vehicle’s position by fusing a geosynchronous orbit (GEO) satellite Doppler frequency

Resolver is an electromagnetic position sensor typically used in the closed-loop control of permanent magnet synchronous motors (PMSMs). In terms of structure and principle of operation, resolvers are very similar to electrical machines. In this regard, different numerical and analytical models have been developed for the performance prediction of a resolver, with a compromise between computational

The electrically sensing characteristics of a liquid-crystal (LC)-infiltrated polarization-maintaining photonic crystal fiber (PCF) have been studied. The small holes on the end face of the fiber collapse and two large holes remain open by controlling discharging-time, -current, and -position of a fiber splicer, then LC is selectively infiltrated into the two large holes, which can not only save LC

A high-performance fiber optic interferometric hydrophone based on a push–pull mandrel structure, with high sensitivity and wide-frequency response, is designed and developed. Each arm of the Michelson interferometer is a fiber coil wrapped onto a separate but concentric thin elastic tube as the sensing arm to detect acoustic pressure wave. The fiber optic hydrophone is fabricated and examined experimentally

In this article we enunciate and rigorously demonstrate a new lemma which, based on a previously proposed theorem, proves the identifiability of leverage points in state estimation with specific reference to the least absolute value (LAV) estimator. In this context, we also propose an algorithm for the leverage point identification in LAV estimators whose performance is validated by means of extensive

In view of the large thermal drift of microelectromechanical system (MEMS) triaxial accelerometer and the high cost of traditional calibration schemes, this article proposes a low-cost and efficient thermal drift calibration scheme combining the parameter-correction method and the proposed least squares method based on the nine-parameter model. In this scheme, first, the parameter-correction method

Electroencephalogram (EEG) is an essential tool used to analyze the activities effectively and different states of the brain. Drowsiness is a short period state of the brain that is also called an inattentiveness state. Drowsiness can be observed during the transition from being awake state to a sleepy state. Drowsiness can reduce a person’s alertness that increases accidental risks when involved in

Due to the heavy background noise and strong interference, a blurry or even false time-frequency (TF) representation (TFR) by synchrosqueezing wavelet transform (SST) always results in inaccurate or meaningless gear fault extractions. To solve this problem, a novel TF analysis (TFA) method termed dual-core denoised SST is proposed in this article. The concepts critical to the proposed method are: 1)

Although the autonomous detection of network status and localization of network faults can be a valuable tool for network and service operators, very few works have investigated this subject. As a result in today’s networks, fault detection and localization remains a mostly manual process. In this article, we propose a machine learning (ML) method that can automatically detect the status of a network

Wire rope is a widely used load-bearing component, and the detection of the degree of damage of the wire rope directly determines its usability. The signal obtained by the existing detection methods is weak, which hampers the quantitative detection task. Considering the original method of wire rope axial detection, this study proposes a method of radial magnetic vector used for flexible printed circuit