{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:42:46Z","timestamp":1763620966067,"version":"build-2065373602"},"reference-count":35,"publisher":"MDPI AG","issue":"11","license":[{"start":{"date-parts":[[2021,5,25]],"date-time":"2021-05-25T00:00:00Z","timestamp":1621900800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>For early fault detection of a bearing, the localized defect generally brings a complex vibration signal, so it is difficult to detect the periodic transient characteristics from the signal spectrum using conventional bearing fault diagnosis methods. Therefore, many matrix analysis technologies, such as singular value decomposition (SVD) and reweighted SVD (RSVD), were proposed recently to solve this problem. However, such technologies also face failure in bearing fault detection due to the poor interpretability of the obtained eigenvector. Non-negative Matrix Factorization (NMF), as a part-based representation algorithm, can extract low-rank basis spaces with natural sparsity from the time\u2013frequency representation. It performs excellent interpretability of the factor matrices due to its non-negative constraints. By this virtue, NMF can extract the fault feature by separating the frequency bands of resonance regions from the amplitude spectrogram automatically. In this paper, a new feature extraction method based on sparse kernel NMF (KNMF) was proposed to extract the fault features from the amplitude spectrogram in greater depth. By decomposing the amplitude spectrogram using the kernel-based NMF model with L1 regularization, sparser spectral bases can be obtained. Using KNMF with the linear kernel function, the time\u2013frequency distribution of the vibration signal can be decomposed into a subspace with different frequency bands. Thus, we can extract the fault features, a series of periodic impulses, from the decomposed subspace according to the sparse frequency bands in the spectral bases. As a result, the proposed method shows a very high performance in extracting fault features, which is verified by experimental investigations and benchmarked by the Fast Kurtogram, SVD and NMF-based methods.<\/jats:p>","DOI":"10.3390\/s21113680","type":"journal-article","created":{"date-parts":[[2021,5,25]],"date-time":"2021-05-25T22:02:23Z","timestamp":1621980143000},"page":"3680","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Feature Extraction Using Sparse Kernel Non-Negative Matrix Factorization for Rolling Element Bearing Diagnosis"],"prefix":"10.3390","volume":"21","author":[{"given":"Lin","family":"Liang","sequence":"first","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"},{"name":"Key Laboratory of Education Ministry for Modern Design and Rotor-Bearing System, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"given":"Xingyun","family":"Ding","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"given":"Fei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"given":"Yuanming","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4500-6169","authenticated-orcid":false,"given":"Haobin","family":"Wen","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, Xi\u2019an Jiaotong University, Xi\u2019an 710049, China"}]}],"member":"1968","published-online":{"date-parts":[[2021,5,25]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"295","DOI":"10.1016\/j.measurement.2016.08.003","article-title":"Feature selection for machine fault diagnosis using clustering of non-negation matrix factorization","volume":"94","author":"Liang","year":"2016","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"1350","DOI":"10.1109\/TIA.2010.2049623","article-title":"Diagnosis of bearing faults in induction machines by vibration or current signals: A critical comparison","volume":"46","author":"Immovilli","year":"2010","journal-title":"IEEE Trans. Ind. Appl."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"17","DOI":"10.1109\/MIAS.2017.2740463","article-title":"Bearing Health Diagnosed with a Mobile Phone: Acoustic Signal Measurements Can be Used to Test for Structural Faults in Motors","volume":"24","author":"Rzeszucinski","year":"2018","journal-title":"IEEE Ind. Appl. Mag."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Orman, M., Rzeszucinski, P., Tkaczyk, A., Krishnamoorthi, K., Pinto, C.T., and Sulowicz, M. (2015, January 10\u201312). Bearing fault detection with the use of acoustic signals recorded by a hand-held mobile phone. Proceedings of the 2015 International Conference on Condition Assessment Techniques Electrical Systems (CATCON), Bangalore, India.","DOI":"10.1109\/CATCON.2015.7449545"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"1846","DOI":"10.1109\/TIE.2014.2361115","article-title":"Induction machine bearing fault detection by means of statistical processing of the stray flux measurement","volume":"62","author":"Frosini","year":"2014","journal-title":"IEEE Trans. Ind. Electron."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"349","DOI":"10.1016\/j.ymssp.2016.04.033","article-title":"Kurtosis based weighted sparse model with convex optimization technique for bearing fault diagnosis","volume":"80","author":"Zhang","year":"2016","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"912","DOI":"10.1016\/j.measurement.2010.03.011","article-title":"An envelope analysis based on the resonance modes of the mechanical system for the bearing defect diagnosis","volume":"43","author":"Sheen","year":"2010","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_8","first-page":"250","article-title":"Application of adaptive filtering for weak impulsive signal recovery for bearings local damage detection in complex mining mechanical systems working under condition of varying load","volume":"180","author":"Zimroz","year":"2012","journal-title":"Trans Tech Publ."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1352","DOI":"10.1016\/j.ymssp.2008.07.019","article-title":"Application of spectral kurtosis for detection of a tooth crack in the planetary gear of a wind turbine","volume":"23","author":"Barszcz","year":"2009","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"108","DOI":"10.1016\/j.ymssp.2005.12.002","article-title":"Fast computation of the kurtogram for the detection of transient faults","volume":"21","author":"Antoni","year":"2007","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.ymssp.2004.09.001","article-title":"The spectral kurtosis: A useful tool for characterising non-stationary signals","volume":"20","author":"Antoni","year":"2006","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"431","DOI":"10.1016\/j.ymssp.2010.05.018","article-title":"A novel method for the optimal band selection for vibration signal demodulation and comparison with the Kurtogram","volume":"25","author":"Barszcz","year":"2011","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"294","DOI":"10.1016\/j.ymssp.2017.12.009","article-title":"The Autogram: An effective approach for selecting the optimal demodulation band in rolling element bearings diagnosis","volume":"105","author":"Moshrefzadeh","year":"2018","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Tse, P.W., and Wang, D. (2011, January 24\u201325). The sparsogram: A new and effective method for extracting bearing fault features. Proceedings of the 2011 Prognostics and System Health Managment Conference, Shenzhen, China.","DOI":"10.1109\/PHM.2011.5939587"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.ymssp.2015.04.034","article-title":"The infogram: Entropic evidence of the signature of repetitive transients","volume":"74","author":"Antoni","year":"2016","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"218","DOI":"10.1016\/j.ymssp.2012.06.005","article-title":"Short-time matrix series based singular value decomposition for rolling bearing fault diagnosis","volume":"34","author":"Cong","year":"2013","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1016\/j.ymssp.2018.08.056","article-title":"Research on bearing fault feature extraction based on singular value decomposition and optimized frequency band entropy","volume":"118","author":"Li","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/j.ymssp.2014.07.019","article-title":"Study on Hankel matrix-based SVD and its application in rolling element bearing fault diagnosis","volume":"52\u201353","author":"Jiang","year":"2015","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_19","first-page":"10","article-title":"Machine fault diagnosis based on reassigned wavelet scalogram and SVD","volume":"4","author":"Jiang","year":"2012","journal-title":"Int. J. Adv. Comput. Technol."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1016\/j.ymssp.2017.02.036","article-title":"A novel strategy for signal denoising using reweighted SVD and its applications to weak fault feature enhancement of rotating machinery","volume":"94","author":"Zhao","year":"2017","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Wen, H., Liang, L., and Liu, F. (2020). Speech enhancement using nonnegative matrix factorization with overlapping group sparsity constraint. ACM Int. Conf. Proceeding Ser., 87\u201391.","DOI":"10.1145\/3406971.3406975"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Zhou, Q., Feng, Z., and Benetos, E. (2019). Adaptive noise reduction for sound event detection using subband-weighted NMF. Sensors, 19.","DOI":"10.3390\/s19143206"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"88617","DOI":"10.1109\/ACCESS.2020.2993226","article-title":"Impulse Feature Extraction of Bearing Faults Based on Convolutive Nonnegative Matrix Factorization","volume":"8","author":"Liang","year":"2020","journal-title":"IEEE Access"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Liu, H., Wen, H., Liang, L., Wang, J., Fan, Z., and Hu, J. (2019, January 20\u201322). Impulse Response Extraction for Rolling Bearing Faults Based on Semi-NMF. Proceedings of the 2019 IEEE 4th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC), Chengdu, China.","DOI":"10.1109\/IAEAC47372.2019.8997968"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"585","DOI":"10.1016\/j.ymssp.2019.05.020","article-title":"Novel method of informative frequency band selection for vibration signal using Nonnegative Matrix Factorization of spectrogram matrix","volume":"130","author":"Wodecki","year":"2019","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"2800","DOI":"10.1016\/j.patcog.2011.03.023","article-title":"Nonlinear nonnegative matrix factorization based on Mercer kernel construction","volume":"44","author":"Pan","year":"2011","journal-title":"Pattern Recognit."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"3066","DOI":"10.1016\/j.patcog.2013.03.021","article-title":"Non-negativity constraints on the pre-image for pattern recognition with kernel machines","volume":"46","author":"Kallas","year":"2013","journal-title":"Pattern Recognit."},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Li, Y., and Ngom, A. (2012, January 9\u201312). A new Kernel non-negative matrix factorization and its application in microarray data analysis. Proceedings of the 2012 IEEE Symposium on Computational Intelligence in Bioinformatics and Computational Biology (CIBCB), San Diego, CA, USA.","DOI":"10.1109\/CIBCB.2012.6217254"},{"key":"ref_29","first-page":"1457","article-title":"Non-negative matrix factorization with sparseness constraints","volume":"5","author":"Hoyer","year":"2004","journal-title":"J. Mach. Learn. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1109\/TPAMI.2006.60","article-title":"Nonsmooth nonnegative matrix factorization (nsNMF)","volume":"28","author":"Carazo","year":"2006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"29","DOI":"10.1016\/j.laa.2005.06.025","article-title":"Nonnegative matrix factorization for spectral data analysis","volume":"416","author":"Pauca","year":"2006","journal-title":"Linear Algebra Its Appl."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"1495","DOI":"10.1093\/bioinformatics\/btm134","article-title":"Sparse non-negative matrix factorizations via alternating non-negativity-constrained least squares for microarray data analysis","volume":"23","author":"Kim","year":"2007","journal-title":"Bioinformatics"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1107","DOI":"10.1137\/070698920","article-title":"Fixed-point continuation for 11-minimization: Methodology and convergence","volume":"19","author":"Hale","year":"2008","journal-title":"SIAM J. Optim."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"155","DOI":"10.1016\/j.csda.2006.11.006","article-title":"Algorithms and applications for approximate nonnegative matrix factorization","volume":"52","author":"Berry","year":"2007","journal-title":"Comput. Stat. Data Anal."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1066","DOI":"10.1016\/j.jsv.2005.03.007","article-title":"Wavelet filter-based weak signature detection method and its application on rolling element bearing prognostics","volume":"289","author":"Qiu","year":"2006","journal-title":"J. Sound Vib."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/11\/3680\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:07:41Z","timestamp":1760162861000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/11\/3680"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,25]]},"references-count":35,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2021,6]]}},"alternative-id":["s21113680"],"URL":"https:\/\/doi.org\/10.3390\/s21113680","relation":{},"ISSN":["1424-8220"],"issn-type":[{"type":"electronic","value":"1424-8220"}],"subject":[],"published":{"date-parts":[[2021,5,25]]}}}