Search

Fault diagnosis techniques of electrical motors can prevent unplanned downtime and loss of money, production, and health. Various parts of the induction motor can be diagnosed: rotor, stator, rolling bearings, fan, insulation damage, and shaft. Acoustic analysis is non-invasive. Acoustic sensors are low-cost. Changes in the acoustic signal are often observed for faults in induction motors. In this paper, the authors present a fault diagnosis technique for three-phase induction motors (TPIM) using acoustic analysis. The authors analyzed acoustic signals for three conditions of the TPIM: healthy TPIM, TPIM with two broken bars, and TPIM with a faulty ring of the squirrel cage. Acoustic analysis was performed using fast Fourier transform (FFT), a new feature extraction method called MoD-7 (maxima of differences between the conditions), and deep neural networks: GoogLeNet, and ResNet-50. The results of the analysis of acoustic signals were equal to 100% for the three analyzed conditions. The proposed technique is excellent for acoustic signals. The described technique can be used for electric motor fault diagnosis applications. [ABSTRACT FROM AUTHOR]

This paper presents the project proposal of a low-cost transducer with a Hall-effect sensor placed in a ferromagnetic core's air gap, which enables the measurement of the distorted voltage instantaneous values without the feedback loop used for measurements in electrical machines. The presented transducer allows for electrical separation between the measured voltage and the voltage at the output. Moreover, the influences of frequency, additional resistance, and the reactance of the winding circuit on the voltage phase shift caused by winding inductance with ferrite core and amplitude are discussed. The result of simulating leakage inductance of measuring winding with ferrite core with an air gap is calculated using finite element analysis. Experimental investigations of the voltage phase shift angle and output voltage amplitude drop for the voltage transducers with an open feedback loop are carried out, taking into account the linear core magnetization characteristic. [ABSTRACT FROM AUTHOR]

The article describes the non-contact and contact analysis of 1-MVA dry power transformers with epoxy-resin insulation using an acoustic camera and frequency analyzer with automatic sweeping for low-middle frequency areas. Power transformers are most commonly used for construction component (core, windings, taps) analysis. The electrical, non-rotating machine generates electromagnetic and acoustic emissions that can be used to analyze dry transformers during their operation. Non-contact online diagnostic methods have many advantages over offline methods because it is not necessary to shut down the transformer, and also, the condition and behaviour of the machine are analyzed during its normal operation. The article presents the analysis and comparison of structural parts of the distribution dry transformers of the same type and power. The problem of insufficient or incorrect clamp-screw connection was identified using the SFRA (Sweep Frequency Response Analysis) method. [ABSTRACT FROM AUTHOR]

Early detection and diagnosis of faults in synchronous machine (SM) are crucial since they drive critical applications. In this paper, the authors exploited the combined information from numerical simulation and experimental validation to evaluate the merits of certain fault indicators, for detecting machine faults. A specially designed SM was chosen for both simulation and measurement with the ability to physically introduce electro-mechanical failures. Shorted turn fault was made through accessible intermediate terminals of respective stator and rotor windings. Eccentricity faults of different intensity were created by suitable changeover of customized end-shield. Finite element method was used to develop healthy and faulty simulation models. The experimental setup facilitated measurement and subsequent calculation of key parameters such as stator branch currents, phase current, circulating current, rotor field current and shaft voltage. From the investigation of both simulation and experimental data, field current and shaft voltage were found to be two effective fault indicators from safety and reliability prospects. Both indicators have the ability to identify and discriminate between electro-mechanical and electrical faults. Further, it is demonstrated that with availability of physical dimensions and measured rotor parameters, a know-how can be created to detect failures, well before a catastrophic event occurs. [ABSTRACT FROM AUTHOR]

Unsupervised domain adaptation, which aims to alleviate the domain shift between source domain and target domain, has attracted extensive research interest; however, this is unlikely in practical application scenarios, which may be due to privacy issues and intellectual rights. In this paper, we discuss a more challenging and practical source-free unsupervised domain adaptation, which needs to adapt the source domain model to the target domain without the aid of source domain data. We propose label consistent contrastive learning (LCCL), an adaptive contrastive learning framework for source-free unsupervised domain adaptation, which encourages target domain samples to learn class-level discriminative features. Considering that the data in the source domain are unavailable, we introduce the memory bank to store the samples with the same pseudo label output and the samples obtained by clustering, and the trusted historical samples are involved in contrastive learning. In addition, we demonstrate that LCCL is a general framework that can be applied to unsupervised domain adaptation. Extensive experiments on digit recognition and image classification benchmark datasets demonstrate the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The belt conveyor is an essential piece of equipment in coal mining for coal transportation, and its stable operation is key to efficient production. Belt surface of the conveyor is vulnerable to foreign bodies which can be extremely destructive. In the past decades, much research and numerous approaches to inspect belt status have been proposed, and machine learning-based non-destructive testing (NDT) methods are becoming more and more popular. Deep learning (DL), as a branch of machine learning (ML), has been widely applied in data mining, natural language processing, pattern recognition, image processing, etc. Generative adversarial networks (GAN) are one of the deep learning methods based on generative models and have been proved to be of great potential. In this paper, a novel multi-classification conditional CycleGAN (MCC-CycleGAN) method is proposed to generate and discriminate surface images of damages of conveyor belt. A novel architecture of improved CycleGAN is designed to enhance the classification performance using a limited capacity images dataset. Experimental results show that the proposed deep learning network can generate realistic belt surface images with defects and efficiently classify different damaged images of the conveyor belt surface. [ABSTRACT FROM AUTHOR]

• A new tube with V-cut twisted tape turbulator is developed. • Magnetic field effect and nano ferrofluid flow are considered in the turbulator. • The present new turbulator enables to provide high-quality thermodynamics. The magnetic field (MF) effect on the heat transfer of Fe 3 O 4 ferrofluid swirl flow inside a tube with turbulator was investigated under three Re numbers (200, 400, and 600), turbulator pitches (H = 50 mm, 100 mm, and 150 mm), and three scenarios of MF location. The outputs demonstrated that by applying the MF on zone#1 (near the entrance), zone#2 (middle of tube), and zone#3 (near the outlet) improves convective heat transfer coefficient (h) over the tube without MF by 1.1% (or 2.49%), 11.13% (or 14.94%), and 39.42% (or 10.91%), respectively, at Re of 200 (or 600). In consequence, the absorber tube temperature reduces by 0.207% (or 2.23%), 0.058% (or 0.498%), and 0.068% (or 0.293%), respectively, for zones 1, 2, and 3 and at Re = 200 (or 600). In addition, the MF increases the pressure drop over the tube without MF by nearly 16%, 9%, and 4%, for zones 1, 2, and 3, respectively. Furthermore, the intensification of H from 50 mm to 150 mm at Re s of 200–600 decreased h by 30.21–19.32% and 28.51–26.91% under zone#1 and zone#2 scenarios, respectively, while enhanced that by 5.52–0.26% for MF applied on zone#3. Furthermore, the highest PEC was obtained as 1.55–2.36 for H values of 50 mm-150 mm when MF is applied on zone#3 and at Re = 200. [ABSTRACT FROM AUTHOR]

• The acoustic based fault diagnosis technique is proposed for detection of bearings and ventilation faults of power tools. • Six acoustic signals of motors were measured and analyzed. • Feature extraction methods SMOFS-NFC is presented. • Results of the analysis were shown. • The acoustic based analysis is useful for analysis of electrical and other mechanical faults of machines. Electric motors use about 68% of total generated electricity. Fault diagnosis of electrical motors is an important task, because it allows saving a large amount of money and time. An analysis of acoustic signals is a promising tool to improve the accuracy of fault diagnosis. It is essential to analyze acoustic signals to assess the state of the motor. In this paper, three electric impact drills (EID) were analyzed using acoustic signals: healthy EID, EID with damaged rear bearing, EID with damaged front bearing. Three angle grinders (AG) were analyzed: healthy AG, AG with 1 blocked air inlet, AG with 2 blocked air inlets. The authors proposed a method for feature extraction: SMOFS-NFC (Shortened Method of Frequencies Selection Nearest Frequency Components). Acoustic features vectors were classified by the nearest neighbor classifier and Naive Bayes classifier. The classification accuracy were in the range of 89.33–97.33% for three electric impact drills. The classification accuracy were in the range of 90.66–100% for three angle grinders. The presented method is very useful for diagnosis of bearings, ventilation faults and other mechanical faults of power tools. It can be also useful for diagnosis of similar power tools. [ABSTRACT FROM AUTHOR]