Wyniki wyszukiwania - BazTech

1

Markov transition fields and auto-encoder-based preprocessing for event recognition of Φ-OTDR

Hu Xin, Dai Jingyi Dai, Wei Ziyi, Shen Wei, Yu Hao, Wu Haiyang, Xu Yingwen, Hu Chengyong, Deng Chuanlu, Huang Yi

Optica Applicata

|

2024

|

Vol. 54, nr 2

217--229

EN

To improve the model training efficiency and the classification performance of the phase-sensitive optical time-domain reflectometer (Φ-OTDR) in disturbance events recognition, a preprocessing method based on Markov transition fields (MTF) and auto-encoder (AE) is proposed. The phase time series, derived from demodulation of the original scattering signals, are converted into images by using the MTF method. Subsequently, an auto-encoder is introduced to perform a dimensionality reduction characterization of the MTF images, and the outputs of the encoder will be used as features for classification. The experimental results demonstrate that, compared with directly processing time series using 1-D CNN and classifying MTF images using CNN, the features obtained by the proposed method can accelerate the training process and improve the recognition performance of the classification model. The recognition accuracy for the four classes of events on the fence reaches 95.6%, representing a 12% increase.

2

An extrinsic Fabry–Pérot interference fiber sensor for ultrasonic detection of partial discharge

Zhang Ximin, Qian Sen, Liu Huixin, Chen Chuan, Deng Chuanlu, Hu Chengyong, Huang Yi

Optica Applicata

|

2023

|

Vol. 53, nr 2

199--211

EN

An ultrasonic sensor based on extrinsic Fabry–Pérot interference (EFPI) has been designed and demonstrated to detect the ultrasonic wave signal. The sensitivity and natural frequency of fiber Fabry–Pérot (F-P) sensor with different structure parameter have been simulated by COMSOL. The simulation results illustrate that the sensitivity is up to 1.737 nm/kPa and the natural frequency is 2.1 MHz, when the silica diaphragm thickness is 2 μm, the radius is 90 μm, and the cavity length is 18 μm. The most suitable parameters have been selected and the F-P sensor has been fabricated. When the ultrasonic signals with the frequencies of 40 kHz and 1.2 MHz are respectively applied to the sensor, the frequencies detected by the EFPI ultrasonic sensor are 39 kHz and 1.21 MHz based on a partial discharge detection experiment for the designed demodulation system. The experimental results show that the sensor can accurately detect ultrasonic signals. As an excellent platform for ultrasonic signal sensing, this EFPI ultrasonic sensing system has great potential applications in partial discharge detection field.

3

Stator-rotor fault diagnosis of induction motor based on time-frequency domain feature extraction

Yi Lingzhi, Long Jiao, Wang Yahui, Sun Tao, Huang Jianxiong, Huang Yi

Metrology and Measurement Systems

|

2023

|

Vol. 30, nr 4

773--790

EN

Since the induction motor operates in a complex environment, making the stator and rotor of the motor susceptible to damage, which would have significant impact on the whole system, efficient diagnostic methods are necessary to minimize the risk of failure. However, traditional fault diagnosis methods have limited applicability and accuracy in diagnosing various types of stator and rotor faults. To address this issue, this paper proposes a stator-rotor fault diagnosis model based on time-frequency domain feature extraction and Extreme Learning Machine (ELM) optimized with Golden Jackal Optimization (GJO) to achieve high-precision diagnosis of motor faults. The proposed method first establishes a platform for acquiring induction motor stator-rotor fault data. Next, wavelet threshold denoising is used to pre-process the fault current signal data, followed by feature extraction to perform time-frequency domain eigenvalue analysis. By comparison, the impulse factor is finally adopted as the feature vector of the diagnostic model. Finally, an induction motor fault diagnosis model is constructed by using the GJO to optimize the ELM. The resulting simulations are carried out by comparing with neural networks, and the results show that the proposed GJO-ELM model has the highest diagnostic accuracy of 94.5%. This finding indicates that the proposed method outperforms traditional methods in feature learning and classification of induction motor fault diagnosis, and has certain engineering application value.

4

A multiscale experimental analysis of mechanical properties and deformation behavior of sintered copper-silicon carbide composites enhanced by high-pressure torsion

Nosewicz Szymon, Bazarnik Piotr, Clozel Melanie, Kurpaska Łukasz, Jenczyk Piotr, Jarząbek Dariusz, Chmielewski Marcin, Romelczyk-Baishya Barbara, Lewandowska Malgorzata, Pakieła Zbigniew, Huang Yi, Langdon Terence G.

Archives of Civil and Mechanical Engineering

|

2021

|

Vol. 21, no. 3

776--794

EN

Experiments were conducted to investigate, within the framework of a multiscale approach, the mechanical enhancement, deformation and damage behavior of copper–silicon carbide composites (Cu–SiC) fabricated by spark plasma sintering (SPS) and the combination of SPS with high-pressure torsion (HPT). The mechanical properties of the metal–matrix composites were determined at three different length scales corresponding to the macroscopic, micro- and nanoscale. Small punch testing was employed to evaluate the strength of composites at the macroscopic scale. Detailed analysis of microstructure evolution related to SPS and HPT, sample deformation and failure of fractured specimens was conducted using scanning and transmission electron microscopy. A microstructural study revealed changes in the damage behavior for samples processed by HPT and an explanation for this behavior was provided by mechanical testing performed at the micro- and nanoscale. The strength of copper samples and the metal–ceramic interface was determined by microtensile testing and the hardness of each composite component, corresponding to the metal matrix, metal–ceramic interface, and ceramic reinforcement, was measured using nano-indentation. The results confirm the advantageous effect of large plastic deformation on the mechanical properties of Cu–SiC composites and demonstrate the impact on these separate components on the deformation and damage type.