A5002923257- Gas Sensing Nanomaterials and Sensors
- Advanced Chemical Sensor Technologies
- Analytical Chemistry and Sensors
- Machine Fault Diagnosis Techniques
- Plasmonic and Surface Plasmon Research
- Advanced Fiber Optic Sensors
- Fault Detection and Control Systems
- Non-Destructive Testing Techniques
- Mass Spectrometry Techniques and Applications
- Mercury impact and mitigation studies
- Photonic and Optical Devices
- Industrial Vision Systems and Defect Detection
- Electrohydrodynamics and Fluid Dynamics
- Inorganic Fluorides and Related Compounds
- Photonic Crystal and Fiber Optics
- Inorganic Chemistry and Materials
- Gear and Bearing Dynamics Analysis
- Advanced Sensor and Energy Harvesting Materials
- Speech and Audio Processing
- Spectroscopy and Laser Applications
- Hand Gesture Recognition Systems
- Transition Metal Oxide Nanomaterials
- Luminescence Properties of Advanced Materials
- Engineering Diagnostics and Reliability
- Emotion and Mood Recognition
Northeast Electric Power University
2018-2025
Electric Power University
2022-2025
Jilin University
2015-2017
State Key Laboratory of Inorganic Synthesis and Preparative Chemistry
2015-2017
Jilin Medical University
2015-2017
As a rising star in the field of deep learning, Transformers have achieved remarkable achievements numerous tasks. Nonetheless, due to safety considerations, complex environment, and limitation deployment cost actual industrial production, algorithms used for fault diagnosis often face three challenges limited samples, noise interference, lightweight, which is an impediment practice transformer with high requirements number samples parameters. For this reason, article proposes lightweight...
High precision and fast fault diagnosis is an important guarantee for the safe reliable operation of machinery. In recent years, due to strong recognition ability, data-driven technology based on deep learning has attracted enormous attention. The module proposed by many scholars achieved excellent results, but some them are too complex deploy in practice, high costs. this article, efficient feature extraction method convolutional neural networks (CNN) was proposed, high-precision task...
Although Transformer has achieved excellent results in various tasks industrial scenes, owing to the environmental noise and cost limitation, fault diagnosis approaches based on are facing two serious challenges, that is, robustness lightweight. With original intention of promoting transformation from theoretical design practical engineering application, we designed a lightweight framework with strong robustness, named X-self-attention convolution neural network (XACNN), meet these...
Because of the cost, it is unrealistic to sample failure state for a long time, which makes data collected from scenario engineering usually extremely imbalanced. However, imbalanced training pose negative effect on fault diagnosis algorithms based driven. When are imbalanced, this problem becomes more challenging. Furthermore, reduce deployment in industrial practice, often required that parameters and computation deployed model should be within certain range, puts forward requirement...
A photonic crystal fiber based on a surface plasmon resonance sensor coated with segmented silver-titanium dioxide ( <mml:math xmlns:mml="http://www.w3.org/1998/Math/MathML" display="inline"> <mml:mrow class="MJX-TeXAtom-ORD"> <mml:mi mathvariant="normal">A</mml:mi> mathvariant="normal">g</mml:mi> </mml:mrow> <mml:mtext>-</mml:mtext> <mml:msub> mathvariant="normal">T</mml:mi> mathvariant="normal">i</mml:mi> mathvariant="normal">O</mml:mi> <mml:mn>2</mml:mn> </mml:msub> </mml:math> ) film is...
Effective fault diagnosis is an important guarantee for the safe and stable operation of mechanical systems. Nowadays, most methods are known classes. However, unknown usually occurs in process may be wrongly divided into defined classes, which increases risk shutdown difficulty maintenance. Therefore, to achieve high-accuracy with fault, a method based on transfer learning deep clustering (DTC) proposed, named calculation center points (TCCP). TCCP completes task class by calculating...
Nitrogen dioxide (NO2), the main component of pollutants in atmospheric environments, causes and exacerbates respiratory diseases, especially during outdoor sports even at 100 ppb level. Currently, environmental gas detection still faces challenges such as high limits, low SNR, sensitivity. A NO2 sensor based on In(OH)3-α-Fe2O3-ZnO was prepared using a hydrothermal method, featuring an ultralow limit 82 ppt, exceptionally SNR 574,000, ultrahigh sensitivity 252.25 mV/ppm (100 to 1 ppm). And...
Two kinds of photonic crystal fiber (PCF) sensors based on surface plasmon resonance (SPR) with silver nano-continuous gratings (i) and (ii) are designed. The coupling characteristics sensing properties analyzed numerically by the finite element method (FEM). results show that proposed sensor grating can achieve better performance than plane film structures. When segmented number is 50 angle 0.5°, a wavelength sensitivity obtained as high 13,600 nm/RIU in refractive index (RI) range from...
Due to its promising potential applications in seawater desalination and purification, solar steam conversion has attracted tremendous attention recently. The light‐to‐heat capacity of absorbers directly affects the rate at which freshwater is produced by evaporation system. Herein, an efficient double‐layer evaporator developed using MoS 2 /LaF 3 /PDMS ink as absorber that printed onto a commercial PTFE membrane controlled ink‐spray method. LaF nanoparticles‐decorated nanoflowers...
Inorganic compounds of Sm<sub>3−x</sub>Ca<sub>x</sub>Fe<sub>5</sub>O<sub>12</sub> (<italic>x</italic> = 0, 0.1, 0.3, 0.5) samples can be used as a new family thermochromic materials with the colour change from green (20 °C) to brown (240 and introduction Ca<sup>2+</sup> ions shows gradual changes in colour.