{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T17:05:50Z","timestamp":1780506350705,"version":"3.54.1"},"reference-count":35,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2019,4,30]],"date-time":"2019-04-30T00:00:00Z","timestamp":1556582400000},"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>Rolling bearings are the core components of rotating machinery. Their health directly affects the performance, stability and life of rotating machinery. To prevent possible damage, it is necessary to detect the condition of rolling bearings for fault diagnosis. With the rapid development of intelligent fault diagnosis technology, various deep learning methods have been applied in fault diagnosis in recent years. Convolution neural networks (CNN) have shown high performance in feature extraction. However, the pooling operation of CNN can lead to the loss of much valuable information and the relationship between the whole and the part may be ignored. In this study, we proposed CNNEPDNN, a novel bearing fault diagnosis model based on ensemble deep neural network (DNN) and CNN. We firstly trained CNNEPDNN model. Each of its local networks was trained with different training datasets. The CNN used vibration sensor signals as the input, whereas the DNN used nine time-domain statistical features from bearing vibration sensor signals as the input. Each local network of CNNEPDNN extracted different features from its own trained dataset, thus we fused features with different discrimination for fault recognition. CNNEPDNN was tested under 10 fault conditions based on the bearing data from Bearing Data Center of Case Western Reserve University (CWRU). To evaluate the proposed model, four aspects were analyzed: convergence speed of training loss function, test accuracy, F-Score and the feature clustering result by t-distributed stochastic neighbor embedding (t-SNE) visualization. The training loss function of the proposed model converged more quickly than the local models under different loads. The test accuracy of the proposed model is better than that of CNN, DNN and BPNN. The F-Score value of the model is higher than that of CNN model, and the feature clustering effect of the proposed model was better than that of CNN.<\/jats:p>","DOI":"10.3390\/s19092034","type":"journal-article","created":{"date-parts":[[2019,5,2]],"date-time":"2019-05-02T03:15:22Z","timestamp":1556766922000},"page":"2034","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":101,"title":["Bearing Fault Diagnosis with a Feature Fusion Method Based on an Ensemble Convolutional Neural Network and Deep Neural Network"],"prefix":"10.3390","volume":"19","author":[{"given":"Hongmei","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer and Engineering Control, North University of China, Taiyuan 030051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinying","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Mechanical Engineering, North University of China, Taiyuan 030051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuwei","family":"Ji","sequence":"additional","affiliation":[{"name":"School of Computer and Engineering Control, North University of China, Taiyuan 030051, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2019,4,30]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"29520","DOI":"10.1109\/ACCESS.2019.2900503","article-title":"A novel fault diagnosis method of gearbox based on maximum kurtosis spectral entropy deconvolution","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE ACCESS."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.measurement.2019.03.033","article-title":"Research and application of improved adaptive momeda fault diagnosis method","volume":"140","author":"Wang","year":"2019","journal-title":"Meas."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, J., and Du, W. (2018). Research on fault diagnosis of gearbox with improved variational mode decomposition. Sensors, 10.","DOI":"10.3390\/s18103510"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Gao, J., He, X., Yih, W., and Deng, L. (2014, January 22\u201327). Learning continuous phrase representations for translation modeling. Proceedings of the 52nd Annual Meeting of the Association for Computational, Baltimore, MD, USA.","DOI":"10.3115\/v1\/P14-1066"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Le, D., and Provost, E.M. (2013, January 8\u201312). Emotion recognition from spontaneous speech using hidden markov models with deep belief networks. Proceedings of the 2013 IEEE Workshop on Automatic Speech Recognition and Understanding, Olomouc, Czech Republic.","DOI":"10.1109\/ASRU.2013.6707732"},{"key":"ref_6","first-page":"303","article-title":"Deep neural networks: A promising tool for fault characteristic mining and intelligent diagnosis of rotating machinery with massive data","volume":"72","author":"Feng","year":"2016","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"Lecun","year":"2015","journal-title":"Nature"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"455","DOI":"10.1016\/0031-3203(82)90024-3","article-title":"Neocognitron: A new algorithm for patternrecognition tolerant of deformations and shifts in position","volume":"15","author":"Fukushima","year":"1982","journal-title":"Pattern Recognit."},{"key":"ref_9","first-page":"1","article-title":"Gearbox fault identication and classica-tion with convolutional neural networks","volume":"2","author":"Chen","year":"2015","journal-title":"Shock Vib."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"331","DOI":"10.1016\/j.jsv.2016.05.027","article-title":"Convolutional neural network based fault detection for rotating machinery","volume":"377","author":"Janssens","year":"2016","journal-title":"J. Sound Vib."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Wei, Z., Peng, G., and Li, C. (2019, April 29). Bearings fault diagnosis based on convolutional neural networks with 2-d representation of vibration signals as input. Available online: https:\/\/www.matec-conferences.org\/articles\/matecconf\/pdf\/2017\/09\/matecconf_icmme2017_13001.pdf.","DOI":"10.1051\/matecconf\/20179513001"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"246","DOI":"10.1016\/j.measurement.2018.05.098","article-title":"Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis","volume":"127","author":"Yan","year":"2018","journal-title":"Measurement"},{"key":"ref_13","first-page":"1","article-title":"Fault diagnosis for rotating machinery based on con-volutional neural network and empirical mode decomposition","volume":"19","author":"Yuan","year":"2017","journal-title":"Shock Vib."},{"key":"ref_14","first-page":"1","article-title":"Fault diagnosis for rotat-ing machinery using multiple sensors and convolutional neural networks","volume":"99","author":"Min","year":"2017","journal-title":"IEEE\/ASME Transact. Mechatron."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"490","DOI":"10.1016\/j.measurement.2016.07.054","article-title":"Hierarchical adaptive deep convolution neural network and its application to bearing fault diagnosis","volume":"93","author":"Guo","year":"2016","journal-title":"Measurement"},{"key":"ref_16","first-page":"223","article-title":"An adaptive deep convo-lutional neural network for rolling bearing fault diagnosis","volume":"28","author":"Wang","year":"2017","journal-title":"Meas. Sci. Techn."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"7067","DOI":"10.1109\/TIE.2016.2582729","article-title":"Real-time motorfault detection by 1d convolutional neural networks","volume":"63","author":"Ince","year":"2016","journal-title":"IEEE Transact. Industr. Electron."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2017\/8617315","article-title":"Bearing fault detection by one dimensional convolutional neural networks, Mathematical Problems in Engineering","volume":"2017","author":"Eren","year":"2017","journal-title":"Math. Probl. Eng."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Jing, L., Wang, T., Zhao, M., and Wang, P. (2017). An adaptive multi-sensor data fusion method based on deep convolutional neural networks for fault diagnosis of planetary gearbox. Sensors, 17.","DOI":"10.3390\/s17020414"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1551","DOI":"10.1016\/j.measurement.2012.12.011","article-title":"Fault diagnosis of rotating machinery based on the statistical parameters of wavelet packet paving and a generic support vector regressive classier","volume":"46","author":"Shen","year":"2013","journal-title":"Meas. J. Int. Meas. Confed."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Mach. Learn."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"208","DOI":"10.1016\/j.isatra.2014.09.006","article-title":"A novel procedure for diagnosing multiple faults in rotating machinery","volume":"55","author":"Wang","year":"2015","journal-title":"ISA trans."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"44871","DOI":"10.1109\/ACCESS.2019.2909300","article-title":"Application of parameter optimized variational mode decomposition method in fault diagnosis of gearbox","volume":"7","author":"Wang","year":"2019","journal-title":"IEEE Access."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"2800","DOI":"10.1080\/02664763.2018.1441383","article-title":"The relative performance of ensemble methods with deep convolutional neural networks for image classication","volume":"25","author":"Ju","year":"2018","journal-title":"J. Appl. Statist."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.dsp.2018.11.005","article-title":"Ensemble of jointly trained deep neural network-based acoustic models for reverberant speech recognition","volume":"85","author":"Lee","year":"2019","journal-title":"Digit. Signal Process."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"93","DOI":"10.1016\/j.cmpb.2016.12.005","article-title":"Recognition of emotions using multimodal physiological signals and an ensemble deep learning model","volume":"140","author":"Yin","year":"2017","journal-title":"Comput. Meth. Progr. Biomed."},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Li, S., Liu, G., Tang, X., Lu, J., and Hu, J. (2017). An ensemble deep convolutional neural network model with improved d-s evidence fusion for bearing fault diagnosis. Sensors, 17.","DOI":"10.3390\/s17081729"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1016\/j.media.2017.01.008","article-title":"Deep ensemble learning of sparse regression models for brain disease diagnosis","volume":"37","author":"Suk","year":"2017","journal-title":"Med. Image Anal."},{"key":"ref_29","first-page":"325","article-title":"Adaptive control for uncertain nonlinear systems based on multiple neural networks","volume":"34","year":"2004","journal-title":"IEEE Trans. Syst."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"85","DOI":"10.1016\/j.neunet.2014.09.003","article-title":"Deep learning in neural networks: An overview","volume":"61","author":"Schmidhuber","year":"2015","journal-title":"Neural Netw."},{"key":"ref_31","first-page":"1","article-title":"Ian goodfellow, yoshua bengio, and aaron courville: Deep learning","volume":"19","author":"Heaton","year":"2017","journal-title":"Genet. Program. Evol. Mac."},{"key":"ref_32","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overtting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1016\/S0888-3270(03)00077-3","article-title":"Bearing fault diagnosis based on wavelet transform and fuzzy inference","volume":"18","author":"Lou","year":"2004","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_34","unstructured":"Sun, S. (2016, January 19\u201323). Ensemble-compression: A new method for parallel training of deep neural networks. Proceedings of the Joint European Conference on Machine Learning and Knowledge Discovery in Databases, Riva del Garda, Italy."},{"key":"ref_35","first-page":"2579","article-title":"Visualizing data using t-sne","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/9\/2034\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T12:48:20Z","timestamp":1760186900000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/19\/9\/2034"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,4,30]]},"references-count":35,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2019,5]]}},"alternative-id":["s19092034"],"URL":"https:\/\/doi.org\/10.3390\/s19092034","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,4,30]]}}}