Rolling element bearing is a critical component in rotating machinery that reduces the friction between moving pairs. Bearing fault diagnosis always considered as research hotspot field of prognostics and health management, especially with application deep learning. Deep learning, such convolutional neural network (CNN), can extract features automatically compared traditional methods. However, construction CNN model training process still need lot prior knowledge, it takes time to build an...

A novel index termed weighted cyclic harmonic-to-noise ratio (WCHNR) is proposed to directly evaluate the quality and quantity of harmonics bearing characteristic frequency (BCF) in squared envelope spectrum (SES). There are four steps construct index. First, (CHNR) defined prominence harmonic, which inspired by (HNR) content (RCC). Interestingly, it showed this paper that a special case CHNR local L∞/L1 norm, bridges with other indexes such as spectral Gini kurtosis. Second, 0-dB threshold...

Lithium-ion rechargeable batteries are widely used in various electronic products and equipment due to their immense benefits power supplying. The exact remaining useful life (RUL) prediction of lithium-ion has shown excellent achievements preventing severe economic security consequences incurred failing provide necessary levels. Recently, the nonlinear-drifted fractional Brownian motion made quite a splash RUL prediction, since its first hitting time distribution can be approximated by weak...

With the development of unmanned aerial vehicle (UAV) technology, a UAV is gradually applied to variety civil fields, such as photography, power line inspection, and environmental monitoring. At same time, safety reliability also attract wide attention. Anomaly detection one key technologies improve an UAV. The structure system complex, there are complex spatio-temporal correlations among high-dimensional flight data with many parameters. However, existing methods often ignore correlation...

Traditional data-driven intelligent fault diagnosis methods for rotating component commonly assume that sufficient labeled data is available. However, the rotary machine works in a normal state most of time practical engineering, resulting scenarios with extremely limited and imbalanced data. This phenomenon deteriorates performance methods. In this article, augmentation method based on an improved variational autoencoding generative adversarial network proposed to address problem. First,...

Benefited from the sampling signal monitoring sensors installed in electro-mechanical actuator (EMA), data-driven methods, such as deep learning models that can mine adaptive features signal, have received wide attention EMA fault diagnosis. A generalized hypothesis accepted by previous efforts on diagnosis, is target domain datasets (i.e., testing signal) are drawn same distribution with source training signal). However, except for different working loads and velocities, various driving...

Objective: To design and implement a specialized nurse decision support system in the Department of Neurology explore its effectiveness preventing stroke-associated pneumonia (SAP). Methods: A module for nurses was developed based on SAP-graded prevention strategies. total 664 neurology inpatients admitted to The First People’s Hospital Xuzhou between July 2023 September were selected as conventional group, receiving standard nursing care. Another 704 October December experimental strategies...

Mechanical rotating components such as bearing and gear are widely used in various industrial occasions. Fault diagnosis of component can guarantee operational reliability reduce maintenance cost system. Although many fault methods have been developed based on artificial intelligence methods, most them ignore the existing signal processing knowledge element domain. Meanwhile, these just assume that working conditions load or speed keep constant, which may cause low accuracy once operating...

Brushless DC motors (BLDCMs) are widely used in the industrial field, and it is important to diagnose their faults for improving operational reliability. However, existing methods fault diagnosis of BLDCM face challenges terms multiple faults, motor types, cross-operating conditions. Hence, we propose a subdomain adaptation order network (SAON) address these challenges. Firstly, tacholess tracking method proposed transform phase current from time domain angular eliminate interference speed...

A common necessity for prior unsupervised domain adaptation methods that can improve the in unlabeled target dataset is access to source and simultaneously. However, data privacy makes it not always possible actual industrial equipment simultaneously, especially aviation component like Electro-Mechanical Actuator (EMA) whose are often shareable due copyright confidentiality. To address this problem, paper proposes a free framework EMA fault diagnosis. The proposed combination of feature...

Health monitoring of electro-mechanical actuator (EMA) is critical to ensure the security airplanes. It difficult or even impossible collect enough labeled failure degradation data from actual EMA. The autoencoder based on reconstruction loss a popular model that can carry out anomaly detection with only consideration normal training data, while it fails capture spatio-temporal information multivariate time series signals multiple sensors. To mine signals, this paper proposes an attention...

Rotating machines are widely used in industry, and occurrence of failures may cause severe economic losses social impacts. Hence, this paper conducts an investigation on rotating machine fault diagnosis, a novel method based the structure fast kurtogram is proposed. On one hand, index constructed that makes use both second order cyclostationary theory threshold statistical test hypothesis coloured noise. In to reduce impact outliers proposed method, information characteristic frequency be...

High resistance connection (HRC) in brushless dc motors (BLDCMs) would cause motor performance reduction, equipment breakdown, and even fires. Therefore, it is important to diagnose HRC. Until now, there are few studies focusing on HRC diagnosis, most of them cannot adapt well various application scenarios. To address this problem, transient current ratio dendrite net (TCR-DD) proposed for diagnosis. TCR-DD consists two parts: (TCR) (DD). TCR a novel index that constructed with the currents...

Abstract The control system of unmanned vehicles must demonstrate strong capability to promptly diagnose and address faults. Such a can improve transportation efficiency, ensure the smooth execution production tasks, certain extent, mitigate risk human casualties. To upkeep diagnostic requirements systems, this study integrates traditional wheeled vehicle systems with digital twin (DT) technology establish framework for fault diagnosis maintenance, primary objective fulfilling task. By...

Meyer wavelet filters are the key building blocks of empirical transform. In mechanical fault diagnosis, however, boundaries usually defined empirically. order to solve problems, this paper proposes a new index called harmonic infinite-taxicab norm guide grasshopper optimization algorithm primarily optimize band-pass filter and thus, concurrently secondarily low-pass high-pass wavelet. The proposed is inspired by spectral Lp/Lq it closely related characteristic frequency rotating machinery....

This paper presents a procedure for the lubrication state analysis in double-row angular contact ball bearing. During this procedure, Elastic theory, Stribeck's model, and Sjovall's model are applied. Besides, detailed calculation of oil film thickness elasto-hydrodynamic (EHL) elliptical zone is given. With ratio relationship between minimum roughness surface, (lambda ratio) can be calculated evaluated.

Vibration and acoustics emission based methods are commonly used in condition monitoring fault diagnosis of rotating machinery. However, low-speed bearings may be more difficult than that high-speed due to its low signal-to-noise ratio. A detailed discussion on vibration acoustic implemented recent years for detection health is presented this paper. The comparison these two given, some suggestions considerations included as well.