Article
Chemistry, Analytical
Zengyuan Liu, Xiujuan Feng, Chengliang Dong, Mingzhi Jiao
Summary: This paper proposes an analytical method of PID signal with the adaptive weight of small wave packet decomposition node to suppress noise caused by the photoionization detector monitoring signal of VOCs. The PID signal is transmitted to the upper machine software through a single-chip microcontroller. By comparing with traditional wavelet packet denoising method, the superiority of the proposed method in denoising signals of PID is verified. This method lays a foundation for accurate VOCs monitoring in a high humidity environment by eliminating noise generated by local non-uniformity on the photocathode surface of PID ionization chamber.
Article
Optics
Deyang Duan, Rong Zhu, Yunjie Xia
Summary: This study introduces a novel color night vision imaging method based on a ghost imaging framework and optimized coincidence measurement using wavelet transformation, which can directly produce color night vision images with high reconstruction ability.
Article
Chemistry, Analytical
Feng He, Qing Ye
Summary: A new method for bearing fault diagnosis based on wavelet packet transform and convolutional neural network optimized by a simulated annealing algorithm is proposed, showing better and more reliable diagnosis effect compared to existing machine learning and deep learning methods.
Article
Materials Science, Multidisciplinary
Jingzong Yang, Chengjiang Zhou
Summary: A fault feature extraction method for a diaphragm pump check valve based on LMD and wavelet packet transform is proposed in this study. By decomposing, reconstructing, denoising, and extracting features from the signal, the proposed method can effectively extract the fault characteristics of a check valve.
Article
Engineering, Multidisciplinary
Zhiwei Qiu, Rui Min, Daozhi Wang, Siwen Fan
Summary: This study proposes an intelligent fault diagnosis method based on energy features fusion to detect seal wear and internal leakage in hydraulic cylinders. By analyzing the flow field using computational fluid dynamics (CFD) technology, the energy features of the pressure signal are found to be related to internal leakage. Wavelet packet transform is applied to extract the energy features, which are then decomposed into statistics using multivariate statistics theory. Experimental investigations confirm the method's robustness and accuracy, outperforming several classical fault diagnosis methods.
Article
Engineering, Mechanical
Maohua Xiao, Wei Zhang, Kai Wen, Yue Zhu, Yilidaer Yiliyasi
Summary: In this study, Wavelet Packet Decomposition is used for feature extraction of vibration signals, which accurately distinguishes different states of the bearing through visualization of energy features using K-Means clustering. A fault diagnosis model based on BP Neural Network optimized by Beetle Algorithm is proposed to identify bearing faults with an accuracy exceeding 95% and certain anti-interference capability. Two experiments demonstrate the effectiveness of the model in fault diagnosis.
CHINESE JOURNAL OF MECHANICAL ENGINEERING
(2021)
Article
Acoustics
Souhir Bousselmi, Kais Ouni
Summary: This paper proposes a new time-frequency representation based on a tight framelet packet transform to improve the quality and intelligibility of telephone-band speech coding. It is effective in reducing quantization noise and ensuring reconstruction stability, while also providing sub-band decomposition and good time-frequency localization based on critical bands of the human ear.
SPEECH COMMUNICATION
(2023)
Article
Computer Science, Artificial Intelligence
Jun Shao, Tien D. Bui
Summary: In this work, a cycle-consistent loss based method for face aging with wavelet-based multi-level facial attributes extraction is proposed. The application of multi-level generator improves identity preserving effects and reduces training time significantly.
COMPUTER VISION AND IMAGE UNDERSTANDING
(2022)
Article
Computer Science, Information Systems
Caixia Liu, Li Zhang
Summary: Denoising is essential in image processing and plays a crucial role in image preprocessing. It helps to enhance image quality, which contributes to subsequent image processing tasks such as image segmentation and feature extraction. In this paper, a novel denoising method based on wavelet transform and nonlocal moment mean filtering approach (NMM) is proposed.
Article
Computer Science, Artificial Intelligence
Minghang Zhao, Xuyun Fu, Yongjian Zhang, Linghui Meng, Baoping Tang
Summary: This paper proposes a new fault diagnosis method based on wavelet packet distortion and convolutional neural networks, which improves the accuracy of fault diagnosis in mechanical systems by increasing faulty samples and using balanced training datasets.
ADVANCED ENGINEERING INFORMATICS
(2022)
Article
Mechanics
Jie Wang, Wei Zhou, Xia-ying Ren, Ming-ming Su, Jia Liu
Summary: A real-time analytical approach for damage mode identification of carbon fiber reinforced polymer using machine learning and acoustic emission is proposed. Waveform features are extracted from acoustic emission signals using wavelet packet transform, and a waveform-based clustering model is constructed to reveal the relevance between acoustic emission signals and damage modes. Different types of composite laminates can be recognized by the developed softmax layer classifier.
COMPOSITE STRUCTURES
(2023)
Article
Materials Science, Multidisciplinary
Peilu Li, Chunguang Xu, Qinxue Pan, Yuren Lu, Shuangyi Li
Summary: This paper introduces the application of the lifting scheme wavelet packet transform (LSWPT) denoising method to suppress noise in LCR wave signals, showing that it has fast calculation speed and good denoising effect for online ultrasonic measurement of residual stress on rail surfaces.
Article
Computer Science, Information Systems
Maohua Xiao, Wei Zhang, Yuanfang Zhao, Xiaomei Xu, Shufang Zhou
Summary: A fault diagnosis method of gearbox based on WPT-CLSPSO-BP is proposed in this study, which decomposes and reconstructs the signal using wavelet packet transform and optimizes the weights and thresholds of the network using chaotic particle swarm algorithm. Experimental results show that the optimized network has a higher fault recognition rate.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Chemistry, Multidisciplinary
Qingyun Zhang, Jin Tao, Qinglin Sun, Xianyi Zeng, Matthias Dehmer, Quan Zhou
Summary: Accidental falls pose serious threats to the health and safety of the elderly, and the injuries caused are closely related to the postures during falls. A novel method using wavelet packet transform, random forest, and support vector machine was proposed for recognizing fall postures, achieving a classification accuracy of 99% in experiments on simulated falls and daily living activities dataset.
APPLIED SCIENCES-BASEL
(2021)
Article
Optics
Randa Atta, Mohammad Ghanbari
Summary: This paper proposes an image steganography method based on dual tree complex wavelet transform (DT-CWT) to increase capacity and maintain image quality. By utilizing the human visual system's insensitivity to edges, more secret bits can be hidden, making the method superior in terms of capacity and image fidelity compared to existing methods.