Homepage
BIOGRAPHY
Wei-Tao Zhang was born in Xi'an, Shaanxi Province in 1983. He received the B.S. degree (with distinction) in Electronic and Information Engineering from Xidian University, Xi'an 710071, China, in 2006. He received his M.S. and Ph.D. degrees both in Control Science and Engineering, from Xidian University, Xi'an, China, in 2009 and 2011, respectively. Since 2011, he has joined the School of Electronic Engineering of Xidian University, where he is Lecturer from 2011 to 2015. Since August 2015, he was promoted as an Associate Professor. He received the M.S. student supervisor qualification in August, 2016. He is now a Professor at the School of Electronic Engineering of Xidian University.
His research interests include blind signal processing, machine learning, wireless communication, and hardware implementations of digital signal processing systems. In recent years, he also extended his research interests to the applications of blind processing technique to target detection, fault diagnosis and medical signal analysis. His recent research activities can be categorized into two broad topics: I) weak signal analysis and fault detection based on blind signal processing technique and deep learning; II) tensor factorization and its applications to blind deconvolution with considerable reverberation, machine learning, and MIMO-OFDM communications. He is the author or co-author of one textbook and more than 40 articles in journals and conference proceedings. As principal investigator, he hosts and/or participates in some projects including NSFC project, fundamental research program of Shaanxi Province, and joint projects with companies. Dr. Zhang was elected as Young Science and Technology Star of Shaanxi Province in 2017.
RESEARCH
RESEARCH INTERESTS
Dr. Zhang focuses on both theoretical research and system development of signal processing machine learning and wireless communications. The detailed research topics include blind source separation, blind deconvolution, blind channel identification and equalization, deep neural network and its applications, fault detection and diagnosis. Some topics are shown as follows.
| Signal Processing |
● Blind source separation/extraction for instantaneous or convolved mixtures ● Target tracking in MIMO radar scenar ● Blind channel identification and equalization in MIMO communications ● Medical signal analysis based on BSS or BSE ● Matrix/Tensor factorization and their applications in signal processing. |
| Machine Learning |
● Feature extraction and classifier design: HOG, SIFT, SVM, etc. ● Models: Hidden Markov Model, Gaussian Mixture Model ● New Methods: Deep Learning, Transfer Learning, Reinforcement Learning; ● New Tool: Non-negative Matrix Factorization (NMF), PARAFAC Analysis, etc. |
| Implementation |
● Speech enhancement based on BSS: FPGA implementations of classical or proposed BSS algorithms ● Fault detection and recognition based on BSS and DL: embedded system design for implementation of various algorithms. |
PROJECTS
Our work was supported in part by the National Natural Science Foundation of China (NSFC), and in part by the innovative talents cultivate Program of Shaanxi Province.
RECRUIT
I am looking for self-motivated, self-controlled, and independent Ph.D. and M.S. students to work on signal processing, machine learning and wireless communications. If you are interested, please do not hesitate to contact me.
PUBLICATIONS
BOOKS
S.-T. Lou, J.-S. Zhou, and W.-T. Zhang, Microcomputer Principle and System Design, Second Edition, Science Press, 2015.
S.-T. Lou, J.-S. Zhou, and W.-T. Zhang, Microcomputer Principle and System Design, Third Edition, Science Press, 2020.
JOURNAL PAPERS
W.-T. Zhang, S.-T. Lou ,X.-J. Li , J. Guo, “Tracking multiple targets in MIMO radar via adaptive asymmetric joint diagonalization,” IEEE Transactions on Signal Processing, vol. 64, no. 11, pp. 2880–2893, 2016. Code PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, D.-Z. Feng. “Adaptive quasi-Newton algorithm for source extraction via CCA approach,” IEEE Transactions on Neural Networks and Learning Systems, vol. 25, no. 4, pp. 677–689, 2014. Code PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou. “Iterative algorithm for joint zero diagonalization with application in blind source separation,” IEEE Transactions on Neural Networks, vol. 22, no. 7, pp. 1107-1118, 2011. PDF (Extraction Code: 8216)
X.-G. Yuan, W.-T. Zhang, J. Guo. “Robust non-unitary joint block diagonalization for non-square mixture,” IET Electronics Letters, vol. 51 no. 24, pp. 2005–2007, 2015. PDF (Extraction Code: 8216)
J. Guo, W.-T. Zhang, Y. Liu , L. Fu, “Improving the accuracy of local frequency estimation for interferometric synthetic aperture radar interferogram noise filtering considering large coregistration errors,” IET Radar Sonar and Navigation, vol. 8, no. 6, pp. 676–684, 2014. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, “A recursive solution to nonunitary joint diagonalization,” Signal Processing, vol. 93, no. 1, pp. 313–320, 2013. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou. “A low complexity iterative algorithm for joint zero diagonalization,” IEEE Signal Processing Letters. vol. 19, no. 2, pp. 115-118, 2012. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, H.-M. Lu . “Fast nonunitary joint block diagonalization with degenerate solution elimination for convolutive blind source separation,” Digital Signal Processing, vol. 22, no. 5, pp. 808–819, 2012. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, Y.-L. Zhang , “Robust nonlinear power iteration algorithm for adaptive blind separation of independent signals,” Digital Signal Processing, vol. 20, no. 2, pp. 541-551. 2010. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, “Householder transform based joint diagonal zero diagonalization for source separation using time-frequency distributions,” Multidimensional Systems and Signal Processing, vol. 21, no. 2, pp.161-177, 2010. PDF (Extraction Code: 8216)
W.-T. Zhang, N. Liu , S.-T. Lou, “Joint approximate diagonalization using bilateral rank-reducing Householder transform with application in blind source separation,” Chinese Journal of Electronics, vol. 18, no. 3, pp. 471 – 476, 2009. PDF (Extraction Code: 8216)
J. Guo, H. Li, J. Ning, W. Han, W.-T. Zhang, Z.-S. Zhou, “Feature dimension reduction using stacked sparse auto-encoders for crop classification with multi-temporal, quad-pol SAR data,” Remote Sensing, vol. 12, pp. 321, 2020. PDF (Extraction Code: 8216)
W.-T. Zhang, M. Wang, J. Guo, S.-T. Lou. “Crop Classification Using MSCDN Classifier and Sparse Auto-Encoders with Non-Negativity Constraints for Multi-Temporal, Quad-Pol SAR Data,” Remote Sensing, vol. 13, no. 14, 2749, 2021. PDF (Extraction Code: 8216)
W.-T. Zhang, X.-F. Ji, J. Huang, S.-T. Lou, “Compound fault diagnosis of aero-engine rolling element bearing based on CCA blind extraction,” IEEE Access, vol. 9, pp. 159873-159881, 2021. PDF (Extraction Code: 8216)
W.-T. Zhang, D. Cui, S.-T. Lou, “Training Images Generation for CNN Based Automatic Modulation Classification,” IEEE Access, vol. 9, pp. 62916-62925, 2021. PDF (Extraction Code: 8216)
R.-N. Yang, W.-T. Zhang, S.-T. Lou, “Joint Adaptive Blind Channel Estimation and Data Detection for MIMO-OFDM Systems,” Wireless Communications and Mobile Computing, 2508130, July 2020. PDF (Extraction Code: 8216)
Y. Li, W.-T. Zhang, S.-T. Lou, “Generative adversarial networks for single channel separation of convolutive mixed speech signals,” Neurocomputing, vol. 438, pp. 63-71, May 2021. PDF (Extraction Code: 8216)
J. Guo, Q. Bai, W. Guo, Z. Bu, W.-T. Zhang, “Soil moisture content estimation in winter wheat planting area for multi-source sensing data using CNNR,” Computers and Electronics in Agriculture, vol. 193, pp. 106670, Feb. 2022. PDF (Extraction Code: 8216)
W.-T. Zhang, Y.-B. Li, S.-D. Zheng, L. Liu, “A full tensor network for hyperspectral image classification,” IEEE Geoscience and Remote Sensing Letters, vol. 19: 6013905, 2022. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-D. Zheng, Y.-B. Li, J. Guo, H. Wang, “A full tensor decomposition network for crop classification with polarization extension,” Remote Sensing, vol. 15, no. 1, 56, 2023. PDF (Extraction Code: 8216)
W.-T. Zhang, L. Liu, Y. Bai, Y.-B. Li, J. Guo, “Crop classification based on multi-temporal PolSAR images with a single tensor network,” Pattern Recognition, vol. 143, 2023. 109773 PDF (Extraction Code: 8216)
W.-T. Zhang, L. Liu, D. Cui, Y.-Y. Ma, J. Huang, “An anti-noise convolutional neural network for bearing fault diagnosis based on multi-channel data,” Sensors, 2023, 23(15), 6654. PDF(Extraction Code: 8216)
J. Guo, Q.-Y. Bai, W.-C. Guo, Z.-D. Bu, W.-T. Zhang, “Soil moisture content estimation in winter wheat planting area for multi-source sensing data using CNNR,” Computers and Electronics in Agriculture, Feb. 2022, 193, 106670. PDF(Extraction Code: 8216)
W.-T. Zhang, Y.-B. Li, L. Liu, Y. Bai, J. Cui, “Hyperspectral Image Classification Based on Spectral–Spatial Attention Tensor Network,” IEEE Geoscience and Remote Sensing Letters, vol. 21, pp. 1-5, 2024. PDF(Extraction Code: 8216)
W.-T. Zhang, Z.-Z. Huang, Y.-Y. Ma, D.-J. Zhang, “A Fast Adaptive LPCA Method for Fetal ECG Extraction Based on Multichannel Signals,” IEEE Transactions on Instrumentation and Measurement, Jan. 2024, 73(1): 1-11. Code PDF(Extraction Code: 8216)
Y. Li, W.-T. Zhang, S.-T. Lou, “A Dual-Region Speech Enhancement Method Based on Voiceprint Segmentation,” Neural Networks, 180 (2024) 106683. Code PDF(Extraction Code: 8216)
D.-J. Zhang, W.-T. Zhang, Y.-Y. Ma, Z.-Z. Huang, “Anti-Aliasing Speech DOA Estimation Under Spatial Aliasing Conditions,” IEEE/ACM Transactions on Audio, Speech and Language Processing, June 2024, 32: 3324-3338. PDF(Extraction Code: 8216)
CONFERENCE PAPERS
W.-T. Zhang, Y.-B. Li, L. Liu, J. Guo, “A Full 4-way tensor network for crop classification with time-series fully polarization SAR image,” in proc. 4th China International SAR Symposium (CISS 2023), Xi’an, China, Dec. 4-6, 2023. PDF (Extraction Code: 8216)
W.-T. Zhang, M. Wang, J. Guo, “A Novel Multi-Scale CNN Model for Crop Classifiction with Time-Series Fully Ploarization SAR Images,” China International SAR Symposium 2021 (CISS 2021), Shanghai, China, Nov. 3-5, 2021. PDF (Extraction Code: 8216)
W.-T. Zhang, J.-L. Sun, “Nonunitary joint diagonalization for overdetermined convolutive blind signal separation,” in Proc. 26th European Signal Processing Conference (EUSIPCO2018), Sept. 3–7, Rome, Italy, pp.1242-1246, 2018. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou, “Multicriteria optimization for nonunitary joint block diagonalization,” in Proc. IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP2016), Mar. 20–25, Shanghai, China, pp. 2509–2513, 2016. PDF (Extraction Code: 8216)
W.-T. Zhang, S.-T. Lou. “Search free algorithms for DOA estimation of quasi-stationary signals,” in Proc. IEEE International Workshop on Machine Learning for Signal Processing (MLSP), Sept. 18–21, Beijing, China, 2011. PDF (Extraction Code: 8216)
OPEN RESOURCES
Dataset
Wide Speed Range Aero Engine Rolling Vibration Dataset (Download)
-
Abstract: Bearing fault diagnosis is an important research topic in aviation engine prediction and health management. Signal processing algorithms and deep learning models in this field rely on datasets. However, publicly available datasets generally cover narrow speed ranges, large speed intervals, single loads, and a lack of composite fault data, making it difficult to support the practical development of fault diagnosis methods. This article discloses a vibration dataset of aircraft main shaft bearings with a wide speed range. In addition to providing single fault data, this dataset also provides multiple composite bearing fault data, covering multi-channel bearing vibration signals with a wide speed range under different loads. The dataset well supports the research of classic fault diagnosis algorithms, and due to the large speed range covered by the data and high speed sampling rate, it is more conducive to training deep learning fault diagnosis models.
-
Introudction: The wide speed range aero engine rolling vibration dataset was acquired on SB25 aeroengine bearing testbed through eight vibration sensors, whose numbers were AC0 to AC7 in turn, as shown in Fig. 1. Data was collected from the machine under six different loads (4, 5, 6, 7, 8, and 9kN), the speed range of the bearing was 1000rpm to 10000rpm, the sampling frequency was 20kHz, the data duration was 10s. The bearing dataset consisted of the following five conditions: (1) normal condition (NC), (2) with inner race fault (IF), (3) with outer race fault (OF), (4) with ball fault (BF), and with cage fault (CF). The type of fault is presented in Fig. 2. Model D276126NQ1U was used for the test bearing, which is the front fulcrum thrust bearing supporting the high-pressure compressor in the aeroengine, and its size parameters are shown in Tab. 1.
Tab. 1. The size parameters of test bearing
Internal diameter(mm) External diameter(mm) Width(mm) Number of balls Ball diameter(mm) Pitch diameter(mm) Preset contact angle(°) Actual contact angle(°) 142.9 190.0 33 17 24.6 166.45 28 25.45-31.50 Note: the actual contact angle is related to the load and speed of the bearing, and the actual contact angle will increase when the load or speed increases.
-
Data set Format: The data are stored in the form of mat files, which can be loaded directly through matlab. The storage structure uses the struct structure, which contains five domains: Num of sample points, Channel, Load, Rotate speed, and Data. Table 2 shows the corresponding meanings.
Tab. 2. Fault data storage structure and meaning
Field Meaning Num_of_sample_points Number of sample points Channel The index of channel, from channel1 to channel 8 Load Load, including "Low" and "High" two elements, representing low load and high load respectively Rotate_speed The rotate speed, from 1000rpm to 10000rpm, increases by 200rpm Data 4-way tensor, to obtain the vibration signal sampling value The data files are in mat file format. The file name of each data file consists of parts such as signal type, speed, load, defect type, and interference type. For example, the file name AC_1000_00_12 indicates that the acceleration signal of the compound failure of the inner and outer rings (12) is collected at a speed of 1000 RPM and an axial load of 4kN (00) under the condition of no interference. AC 1000 02 123 interfer0 indicates that under the interference of DC vibration motor, the speed is 1000rpm, the load is 6kN (02), and the acceleration signal of the inner ring, the outer ring and the roller compound fault (123) is collected.
-
Copyright: The wide speed range aero engine rolling vibration dataset can be used for academic purposes only and need to cite the following paper, but anny commercial use id prohibited.
References: [1] W.-T. Zhang, Y.-R. Zhang, N. Xu, J. Huang, "Aero Engine Rolling Bearing vibration data set with wide speed range," Journal of Vibration Engineering.
NOTICE: This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.
TEACHING
COURSES
M. S. Course
Intelligent Control Theory and Applications
Undergraduate Courses
Microcomputer Principles and System Design
MATLAB Language
Computer Control Systems
Digital Logic and Microprocessor
STUDENTS
Stduent at School
- Ph.D. Candidates
- M.S. Students
Students Graduated
Ph.D. students
M.S. Students
Undergraduate. Students
| name | Enrollment Date | Subject |
| Dong-Jiang Zhang（张东江） | Spet. 2022- | Microphone array signal processing and radar anti-jamming |
| Name | Enrollment Date | Subject | Lu Liu（刘璐） | Sept. 2021- | Tensor machine learning and remote sensing image process |
| Yi-Bang Li（李仪邦） | Sept. 2021 - | Tensor computation and software development |
| Yv-Ying Ma（马钰莹） | Sept. 2021 - | Direction Of Arrival estimation |
| Zhen-Zhen Huang（黄珍珍） | Sept. 2022 - | Machine learning and blind source separation |
| Yv Bai（白宇） | Sept. 2022 - | Remote sensing image process and attention mechanism |
| Jian Cui（崔坚） | Sept. 2022 - | Change detecation and remote sensing image process |
| Ya-Ru Zhang（张亚茹） | Sept. 2023 - | Fetal Electrocardio-signals extraction |
| Nuo Xu（许诺） | Sept. 2023 - | Remote sensing image process |
| Hai-Bin Hu（胡海斌） | Sept. 2023 - | Remote sensing image classification |
 |
 |
| Ruo-Nan Yang（杨若男） Huawei 华为 |
Yang Li（李扬） Xi’an International Studies University 西安外国语大学 |
 |
 |
 |
 |
| Jin-Ling Sun（孙瑾铃） Huawei 华为 |
Jing-Chao Wang（汪靖超） AGRICULTURAL BANK OF CHINA 中国农业银行 |
Jing Ning（宁婧）(co-supervised) China Academy of Space Technology 中国空间技术研究院 |
Kang Yin（殷康） Meituan 美团 |
 |
 |
 |
 |
| Ya-Qi Liang（梁雅琪） POSTAL SAVINGS BANK OF CHINA 中国邮政储蓄银行 |
Meng-Di Pei（裴梦迪） Inspur 浪潮 |
Xiao-Fan Ji（纪晓凡） ByteDance 字节跳动 |
Dan Cui（崔丹） BANK OF CHINA 中国银行 |
 |
 |
 |
 |
| Min Wang（王敏） HIKVISION 海康威视 |
Xiu-Bin Shi（史秀斌） DIDI 滴滴 |
Sheng-Di Zheng（郑胜迪） POSTAL SAVINGS BANK OF CHINA 中国邮政储蓄银行 |
Li Huang（黄力） CHANGAN AUTOMOBILE 长安汽车 |
 |
 |
 |
 |
| Hu-Ning Yang（杨虎宁） BYD 比亚迪汽车 |
Yi-Bang Li（李仪邦） INDUSTRIAL AND COMMERCIAL BANK OF CHINA 中国工商银行 |
Lu Liu（刘璐） HIKVISION 海康威视 |
Yv-Ying Ma（马钰莹） Inspur 浪潮 |
| Name | Enrollment Date | Dong Pan（潘东） | Dec. 2011-July 2012 |
| Hai-Tang Lin（凌海堂） | Dec. 2011-July 2012 |
| Bo-Jun Jing（井博军） | Dec. 2011-July 2012 |
| Hai-Jun Zhang（张海军） | Dec. 2012-July 2013 |
| Cui-Lan Huang（黄翠兰） | Dec. 2012-July 2013 |
| Jian-Kai Fang（方建凯） | Dec. 2012-July 2013 |
| Qiang Fu（付蔷） | Dec. 2013-July 2014 |
| Zi-Hao Zhang（张子豪） | Dec. 2013-July 2014 |
| Tian-Jiao Mao（毛天骄） | Dec. 2014-July 2015 |
| Ya-Xin Shen（申亚鑫） | Dec. 2014-July 2015 |
| Wei Dai（戴威） | Dec. 2015-July 2016 |
| Ze-Qing Xu（徐泽清） | Dec. 2015-July 2016 |
| Zhong-Yu Li（李钟毓） | Dec. 2017-July 2018 |
| Yun-Zhao Liu（刘云昭） | Dec. 2017-July 2018 |
| Chuan-Chuan Chen（陈串串） | Dec. 2017-July 2018 |
| Peng-Hui Han（韩鹏辉） | Dec. 2018-July 2019 |
| Ming-Chao Li（李鸣超） | Dec. 2018-July 2019 |
| Ai-Haun Yao（姚爱欢） | Dec. 2018-July 2019 |
| Bo Yang（杨波） | Dec. 2018-July 2019 |
| Zi-Yang Wan（万梓洋） | Dec. 2018-July 2019 |
| Peng-Fei Wang（王鹏飞） | Dec. 2019-July 2020 |
| Ming-Qi Li（李明祺） | Dec. 2019-July 2020 |
| Lin Tang（唐林） | Dec. 2019-July 2020 |
| Dai-Yi Zhu（朱戴义） | Dec. 2020-July 2021 |
| Xin Lei（雷鑫） | Dec. 2020-July 2021 |
| Xiao-Wu Zhang（张潇午） | Dec. 2020-July 2021 |
| Chen-Xv Niu（牛晨煦） | Dec. 2021-July 2022 |
| Qing Xve（薛晴） | Dec. 2021-July 2022 |
| Jia-He Bi（毕家赫） | Dec. 2021-July 2022 |
| Wen-Xiang Li（李文翔） | Dec. 2022-July 2023 |
| Bu-Xiao Li（李步霄） | Dec. 2022-July 2023 |
| Fan Bu（步凡） | Dec. 2022-July 2023 |
| Yang-Hui Yuan（袁仰辉） | Dec. 2023-July 2024 |
| Qiang Li（李强） | Dec. 2023-July 2024 |