A5100343439- Fault Detection and Control Systems
- Industrial Vision Systems and Defect Detection
- Machine Fault Diagnosis Techniques
- Integrated Circuits and Semiconductor Failure Analysis
- Target Tracking and Data Fusion in Sensor Networks
- Ultrasonics and Acoustic Wave Propagation
- Industrial Technology and Control Systems
- Control Systems and Identification
- Non-Destructive Testing Techniques
- Anomaly Detection Techniques and Applications
- Advanced Sensor and Control Systems
- Advanced Algorithms and Applications
- Dynamics and Control of Mechanical Systems
- Oil and Gas Production Techniques
- Mechanical Behavior of Composites
- Advanced Data Processing Techniques
- Advanced Computational Techniques and Applications
- Neural Networks and Applications
- Photoacoustic and Ultrasonic Imaging
- Engineering Diagnostics and Reliability
- Robotic Mechanisms and Dynamics
- Fluid Dynamics and Vibration Analysis
- Distributed Sensor Networks and Detection Algorithms
- Thermography and Photoacoustic Techniques
- Advanced Battery Technologies Research
Jiangnan University
2013-2024
National Institute of Metrology
2024
Chongqing University
2024
Institute of Automation
2024
Beihang University
2014-2023
University of Lethbridge
2023
Meta (Israel)
2022
Merchants Chongqing Communications Research and Design Institute
2020
Mie University
2010-2016
Shanghai University
2015
Sensors provide insights into the industrial processes, while misleading sensor outputs may result in inappropriate decisions or even catastrophic accidents. In this article, Bayesian estimation algorithms are developed to estimate unforeseen signals without tuning. The optimal method is first derived by incorporating a Gaussian distribution specifying potential unmodeled dynamics measurement equation. Since its performance depends on tuning parameters, an iterative algorithm using...
Zearalenone (ZEN) and ochratoxin A (OTA) are key concerns of the food industry because their toxicity pollution scope. This study investigated effects ozone electron beam irradiation (EBI) on degradation ZEN OTA. Results demonstrated that 2 mL 50 μg/mL was completely degraded after 10 s treatment by 2.0 mg/L ozone. The rate 1 16 kGy EBI 92.76%. Methanol superior to acetonitrile in terms degrading when dose higher than 6 kGy. 5 OTA at 180 34%, exceeded 90%. Moreover, more rapidly...
Abstract AES has been used in many applications to provide the data confidentiality. A new 32-bit reconfigurable and compact architecture for encryption decryption is presented implemented non-BRAM FPG this paper. It can be reconfigured options of different key sizes which very flexible users apply various application environments. The proposed design employs a single-round subpipeling minimize hardware cost. fully composite field GF((2 4 ) 2 )-based encryption/decryption keyschedule lead...
In spacecraft electrical signal characteristic data, there exists a large amount of data with high-dimensional features, high computational complexity degree, and low rate identification problems, which causes great difficulty in fault diagnosis electronic load systems. This paper proposes feature extraction method that is based on deep belief networks (DBN) classification the random forest (RF) algorithm; The proposed algorithm mainly employs multi-layer neural network to reduce dimension...
According to the large variety of data generated during spacecraft test and fault diagnosis, this paper designs a multi class classification algorithm based on deep learning method. The uses stack auto-Encoder initialize initial weights offsets multi-layer neural network, then monitor parameters after initialization with gradient descent can overcome many weaknesses SVM, for example, it is too complex occupied more space when or categories are huge. By studying measured data, expert...
Acoustic micro-imaging based on high-frequency ultrasound has been widely and effectively used for microdefect detection in microelectronic packages. With the miniaturization of devices reduction defects, edge blurring occurs ultrasonic scanning directly affects accuracy signal-to-noise ratio, especially spherical structures, such as ball grid arrays, wafer-level chip-scale packaging, flip-chip solder bumps. This paper depicts interaction behaviors effects during imaging, which provide a...
This paper improves the streaming transformer transducer for speech recognition using non-causal convolution. Many works apply causal convolution to improve ignoring lookahead context. We propose use process center block and context separately. method leverages in maintains similar training decoding efficiency. Given latency, with gives better accuracy than convolution, especially open-domain dictation. Besides, this applies talking-head attention a novel history compression scheme further...
Abstract Polyoxymethylene (POM) composites filled with low‐density polyethylene (LDPE) and rice husk flour (RHF) were prepared by injection molding. The POM/5 wt % LDPE/7.5 RHF composite exhibited the lowest wear rate, whereas coefficient of friction remained low, LDPE/5 had best mechanical properties. X‐ray diffraction analysis was carried out, worn surfaces examined scanning electron microscopy. results showed that addition filler reduced crystallinity degree POM composites. main mechanism...
In the condition monitoring and fault diagnosis, useful information about incipient features in measured signal is always corrupted by noise. Fortunately, Kalman filtering technique can filter noise effectively, impending system be revealed to prevent from malfunction. This paper has discussed recent progress of filters for diagnosis. A case study on rolling bearing diagnosis using support vector machine (SVM) been presented. The analysis result showed that integration SVM was feasible...
This paper proposes a novel multi-label classification method for resolving the spacecraft electrical characteristics problems which involve many unlabeled test data processing, high-dimensional features, long computing time and identification of slow rate. Firstly, both fuzzy c-means (FCM) offline clustering principal component feature extraction algorithms are applied selection process. Secondly, approximate weighted proximal support vector machine (WPSVM) online is used to reduce...