End-To-End Convolutional Neural Network Model for Gear Fault Diagnosis Based on Sound Signals
Open accessThe DOI matches its Crossref record; 31 of the 31 references it cites were found in a registry or an index.
Abstract
Currently gear fault diagnosis is mainly based on vibration signals with a few studies on acoustic signal analysis. However, vibration signal acquisition is limited by its contact measuring while traditional acoustic-based gear fault diagnosis relies heavily on prior knowledge of signal processing techniques and diagnostic expertise. In this paper, a novel deep learning-based gear fault diagnosis method is proposed based on sound signal analysis. By establishing an end-to-end convolutional neural network (CNN), the time and frequency domain signals can be fed into the model as raw signals without feature engineering. Moreover, multi-channel information from different microphones can also be fused by CNN channels without using an extra fusion algorithm. Our experiment results show that our method achieved much better performance on gear fault diagnosis compared with other traditional gear fault diagnosis methods involving feature engineering. A publicly available sound signal dataset for gear fault diagnosis is also released and can be downloaded as instructed in the conclusion section.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Reducing the dimensionality of data with neural networks
Hinton, G. E., & Salakhutdinov, R. R. (2006) · Science · doi:10.1126/science.1127647 · Cited by 20,928
Environmental sound classification with convolutional neural networks
Piczak, K. J. (2015) · 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP) · doi:10.1109/mlsp.2015.7324337 · Cited by 931 · cited 1×
“At present, deep learning models have been widely applied in speech recognition [25,26], acoustic scene classification [27,28], and environmental sound classification [29,30].”
MethodVery deep convolutional neural networks for raw waveforms
Dai, W., Dai, C., Qu, S., Li, J., & Das, S. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952190 · Cited by 357 · cited 1×
“At present, deep learning models have been widely applied in speech recognition [25,26], acoustic scene classification [27,28], and environmental sound classification [29,30].”
Sawalhi, N., & Randall, R. B. (2011) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2010.09.009 · Cited by 283
Speech acoustic modeling from raw multichannel waveforms
Hoshen, Y., Weiss, R. J., & Wilson, K. W. (2015) · 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2015.7178847 · Cited by 226 · cited 3×
“At present, deep learning models have been widely applied in speech recognition [25,26], acoustic scene classification [27,28], and environmental sound classification [29,30].”
Borghesani, P., Pennacchi, P., Randall, R. B., Sawalhi, N., & Ricci, R. (2013) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2012.11.001 · Cited by 221
Li, S., Liu, G., Tang, X., Lu, J., & Hu, J. (2017) · Sensors · doi:10.3390/s17081729 · Cited by 211 · cited 1×
“Many researchers also applied deep learning models in vibration signal analysis to detect fault modes [1,2,4,31].”
BackgroundSelf-citationLearning environmental sounds with end-to-end convolutional neural network
Tokozume, Y., & Harada, T. (2017) · 2017 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · doi:10.1109/icassp.2017.7952651 · Cited by 207 · cited 1×
“At present, deep learning models have been widely applied in speech recognition [25,26], acoustic scene classification [27,28], and environmental sound classification [29,30].”
Acoustic based fault diagnosis of three-phase induction motor
Glowacz, A. (2018) · Applied Acoustics · doi:10.1016/j.apacoust.2018.03.010 · Cited by 189
Planetary Gears Feature Extraction and Fault Diagnosis Method Based on VMD and CNN
Liu, C., Cheng, G., Chen, X., & Pang, Y. (2018) · Sensors · doi:10.3390/s18051523 · Cited by 109
Research works printed but not linked: 1
- Hou, 2011, The application of NAH-based fault diagnosis method based on blocking feature extraction in coherent fault conditions, J. Vib. Eng., 24, 555
Cited by
Applications of machine learning to machine fault diagnosis: A review and roadmap
Lei, Y., Yang, B., Jiang, X., Jia, F., Li, N., & Nandi, A. K. (2020) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.106587 · Cited by 2,997
A comprehensive review on convolutional neural network in machine fault diagnosis
Jiao, J., Zhao, M., Lin, J., & Liang, K. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.07.088 · Cited by 575
Limited Data Rolling Bearing Fault Diagnosis With Few-Shot Learning
Zhang, A., Li, S., Cui, Y., Yang, W., Dong, R., & Hu, J. (2019) · IEEE Access · doi:10.1109/access.2019.2934233 · Cited by 419
“Deep learning methods have also been applied to fault diagnosis and obtained state-of-the-art results [6] using techniques such as auto-encoders (AE) [12]–[15], restricted boltzmann machine (RBM) [16]–[19], convolutional neural networks (CNNs) [20]–[24], recurrent neural”
MethodSelf-citationDeep learning for prognostics and health management: State of the art, challenges, and opportunities
Rezaeianjouybari, B., & Shang, Y. (2020) · Measurement · doi:10.1016/j.measurement.2020.107929 · Cited by 310
Data-driven machinery fault diagnosis: A comprehensive review
Neupane, D., Bouadjenek, M. R., Dazeley, R., & Aryal, S. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129588 · Cited by 178
Latest developments in gear defect diagnosis and prognosis: A review
Kumar, A., Gandhi, C. P., Zhou, Y., Kumar, R., & Xiang, J. (2020) · Measurement · doi:10.1016/j.measurement.2020.107735 · Cited by 246
Transfer Learning with Deep Recurrent Neural Networks for Remaining Useful Life Estimation
Zhang, A., Wang, H., Li, S., Cui, Y., Liu, Z., Yang, G., & Hu, J. (2018) · Applied Sciences · doi:10.3390/app8122416 · Cited by 181
Self-citationAn End-to-End Deep Neural Network for Autonomous Driving Designed for Embedded Automotive Platforms
Kocić, J., Jovičić, N., & Drndarević, V. (2019) · Sensors · doi:10.3390/s19092064 · Cited by 161
“This recommends the J-Net model for deployment on low-performing embedded automotive platforms.”
MethodAI-enabled Enterprise Information Systems for Manufacturing
Zdravković, M. M., Panetto, H., & Weichhart, G. (2021) · Enterprise Information Systems · doi:10.1080/17517575.2021.1941275 · Cited by 196
“For example, the ML algorithm can be trained to distinguish between normal and faulty behaviour by learning from the large set of recorded sounds, each of which was associated with one of the labels – nominal output features (normal, fault), where those associations were made by the expert (Yao et al. 2018).”
BackgroundData-Driven Fault Diagnosis for Electric Drives: A Review
Gonzalez-Jimenez, D., del Olmo, J., Poza, J., Garramiola, F., & Madina, P. (2021) · Sensors · doi:10.3390/s21124024 · Cited by 174
“[184] Bias and ramp i abc PCA and KLD ANN Test-bench [193] Ramp, stuck and offset i abc , ω and v dc - DeepPCA Test-bench [187] Generic faults i abc an ω PCA ANN and k NN Simu.”
MethodA survey of mechanical fault diagnosis based on audio signal analysis
Tang, L., Tian, H., Huang, H. P., Shi, S., & Ji, Q. (2023) · Measurement · doi:10.1016/j.measurement.2023.113294 · Cited by 135
Prognostics and Health Management of Industrial Assets: Current Progress and Road Ahead
Biggio, L., & Kastanis, I. (2020) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2020.578613 · Cited by 126
“, 2019) and gears (Jing et al., 2017; Yao et al., 2018; Han et al., 2019b) fault diagnosis.”
Yao, Y. F., Zhang, S., Yang, S., & Gui, G. (2020) · Sensors · doi:10.3390/s20041233 · Cited by 111
“The experiment table, as shown in the top-left corner of Figure 5 [34], consisted of the following equipment: a variable frequency motor, a two-stage gearbox, a tension controller, a frequency converter, and a magnetic brake.”
BackgroundMethodSelf-citationChen, H., Wei, J., Huang, H., Wen, L., Yuan, Y., & Wu, J. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125171 · Cited by 111
An Expert System for Rotating Machine Fault Detection Using Vibration Signal Analysis
Kafeel, A., Aziz, S., Awais, M., Khan, M. A., Afaq, K. S., Idris, S. A., Alshazly, H. A., & Mostafa, S. M. (2021) · Sensors · doi:10.3390/s21227587 · Cited by 95
“In another study [19], a multidimensional signal acquired from several microphones is used for the detection of gear faults.”
BackgroundAcoustic fault analysis of three commutator motors
Głowacz, A. (2019) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2019.07.007 · Cited by 94
Fault Detection of Electric Impact Drills and Coffee Grinders Using Acoustic Signals
Głowacz, A. (2019) · Sensors · doi:10.3390/s19020269 · Cited by 88
Xiao, D., Qin, C., Yu, H., Huang, Y., Liu, C., & Zhang, J. (2021) · Measurement · doi:10.1016/j.measurement.2021.109186 · Cited by 79
Łuczak, D. (2024) · Electronics · doi:10.3390/electronics13020452 · Cited by 74
“Possibilities include displacement [30], vibrations [3,4,7,31,32], sound [33–35], sound recorded with multiple microphones [36], or ultrasound [37,38].”
BackgroundEnhancing image processing architecture using deep learning for embedded vision systems
Udendhran, R., -, M. B., Suresh, A., & Varatharajan, R. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103094 · Cited by 69
Gültekın, Ö., Çinar, E. M., Özkan, K., & Yazıcı, A. T. (2022) · Sensors · doi:10.3390/s22093208 · Cited by 83
A Systematic Review of Multisensor Information Fusion for Equipment Fault Diagnosis
Lin, T., Ren, Z., Zhu, L., Zhu, Y., Feng, K., Ding, W., Yan, K. L., & Beer, M. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3529577 · Cited by 119
Wang, R., Liu, F., Hou, F., Jiang, W., Hou, Q., & Yu, L. (2020) · IEEE Access · doi:10.1109/access.2020.3010272 · Cited by 64
“According to the end-to-end ABD method [30], in this experiment, acoustic signals of the three reference microphones are respectively fed into a 1-D CNN model for bearing fault diagnosis.”
BackgroundMethodResultInfluentialMamun, A. A., Bappy, M. M., Senanayaka, A., Li, J., Jiang, Z., Tian, Z., Fuller, S., Falls, T. C., Bian, L., & Tian, W. (2022) · The International Journal of Advanced Manufacturing Technology · doi:10.1007/s00170-022-10525-4 · Cited by 61
“Acoustics signal-based multi-channel sensor has also been used for machinery fault diagnosis [33, 34].”
MethodA data-driven adaptive fault diagnosis methodology for nuclear power systems based on NSGAII-CNN
He, C., Ge, D., Yang, M., Yong, N., Wang, J., & Yu, J. (2021) · Annals of Nuclear Energy · doi:10.1016/j.anucene.2021.108326 · Cited by 62
Sun, Y., Cao, Y., & Li, P. (2021) · Accident Analysis & Prevention · doi:10.1016/j.aap.2021.106549 · Cited by 59
Yao, Y. F., Gui, G., Yang, S., & Zhang, S. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3108216 · Cited by 48
Self-citationKumar, P., Raouf, I., & Kim, H. S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107126 · Cited by 50
Planetary-Gearbox Fault Classification by Convolutional Neural Network and Recurrence Plot
Wang, D.-F., Guo, Y., Wu, X., Na, J., & Litak, G. (2020) · Applied Sciences · doi:10.3390/app10030932 · Cited by 45
“The time- and frequency-domain indicators were combined with the CNN for fault classification of a fixed shaft gearbox in [5,6].”
MethodA Survey on Artificial Intelligence-Based Acoustic Source Identification
Zaheer, R., Ahmad, I., Habibi, D., Islam, K. Y., & Phung, Q. V. (2023) · IEEE Access · doi:10.1109/access.2023.3283982 · Cited by 49
The Variational Kernel-Based 1-D Convolutional Neural Network for Machinery Fault Diagnosis
Mo, Z., Zhang, Z., & Tsui, K. (2021) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2021.3105252 · Cited by 43
Multisensor Fusion Time–Frequency Analysis of Thruster Blade Fault Diagnosis Based on Deep Learning
Tsai, C.-M., Wang, C.-S., Chung, Y.-J., Sun, Y.-D., & Perng, J. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3204709 · Cited by 41
“In [19], an end-to-end convolutional NN (CNN) model was proposed to realize gear fault diagnosis using sound signals.”
MethodHa, J. M., & Fink, O. (2023) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2023.110680 · Cited by 38
Matania, O., Bachar, L., Khemani, V., Das, D. B., Azarian, M. H., & Bortman, J. (2023) · Advanced Engineering Informatics · doi:10.1016/j.aei.2023.101945 · Cited by 36
Yao, Y. F., Chen, Q., Gui, G., Yang, S., & Zhang, S. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.106449 · Cited by 36
Self-citationDan, Y., Dong, R., Cao, Z., Li, X., Niu, C., Li, S., & Hu, J. (2020) · IEEE Access · doi:10.1109/access.2020.2981874 · Cited by 38
“It was first successfully applied in computer vision and since then has achieved remarkable success in many other areas such as gear fault diagnosis [40], [41], in which vibration and sound signals are converted into matrix/image format to exploit CNN’s feature learning capabilities.”
MethodSelf-citationYao, Y. F., Gui, G., Yang, S., & Zhang, S. (2021) · Measurement · doi:10.1016/j.measurement.2021.110169 · Cited by 36
Self-citationPrognosis of Bearing and Gear Wears Using Convolutional Neural Network with Hybrid Loss Function
Lo, C.-C., Lee, C., & Huang, W.-C. (2020) · Sensors · doi:10.3390/s20123539 · Cited by 31
“The classifier part was designed as a fully connected simple neural network structure of [8,16,2] (one hidden layer).”
BackgroundMethodInfluentialHe, C., Han, P., Lu, J., Wang, X., Song, J., Li, Z., & Lu, S. (2023) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2023.3295476 · Cited by 31
“Related experiment data analysis result demonstrates the superiority of the improved non-contact diagnosis method [16].”
MethodYu, L., Yao, X., Yang, J., & Li, C. (2020) · Information · doi:10.3390/info11050266 · Cited by 31
“The platform is composed of a two-stage ge rbox, a variable frequency motor, a frequency conv rter, a magnetic brak component, a tension controller, sensor, acquisition card and system [21].”
BackgroundMethodApplication of Rotating Machinery Fault Diagnosis Based on Deep Learning
Cui, W., Meng, G., Wang, A., Zhang, X., & Ding, J. (2021) · Shock and Vibration · doi:10.1155/2021/3083190 · Cited by 35
“…vibration signal is a 1D signal, researchers often use 1D CNN to extract features from vibration signals, and they conducted health detection and fault diagnosis classification for a variety of equipment, such as rolling bearings [85], motors [86], planetary gearboxes [87], and fixed gearboxes [88].”
Yousaf, M. Z., Guerrero, J. M., & Sadiq, M. T. (2025) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2025.110597 · Cited by 29
A Weight Multinet Architecture for Bearing Fault Classification Under Complex Speed Conditions
Ding, X., Lin, L., He, D. K., Wang, L., Huang, W., & Shao, Y. (2020) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2020.3026461 · Cited by 26
“These new network models with special architectures have shown their strong potential in complex health detection and fault recognition [23]–[25].”
BackgroundFault Diagnosis of Gear Based on Multichannel Feature Fusion and DropKey-Vision Transformer
Yang, N., Liu, J., Zhao, W., & Tan, Y. (2023) · IEEE Sensors Journal · doi:10.1109/jsen.2023.3344999 · Cited by 26
“Compared with the traditional machine learning methods, feature extraction and fault recognition are integrated to realize fault diagnosis in an end-to-end way, for example, convolutional neural network (CNN) [19], deep belief network (DNN) [20], and their variants [21], [22], [23], [24].”
MethodJarwar, M. A., Khowaja, S. A., Dev, K., Adhikari, M., & Hakak, S. (2021) · IEEE Internet of Things Journal · doi:10.1109/jiot.2021.3109668 · Cited by 26
“It should be noted that the results from [19] and [23] are reproduced based on our understanding of their implementation.”
BackgroundMethodŁuczak, D., Brock, S., & Siembab, K. (2023) · Sensors · doi:10.3390/s23073755 · Cited by 22
“The problem of spectrum update at each new sample was solved using the SDFT method (sliding discrete Fourier transform).”
MethodŁuczak, D., Brock, S., & Siembab, K. (2023) · Actuators · doi:10.3390/act12030125 · Cited by 21
“…camera [55,56]; furthermore, depending on the frequency range, displacement [57], vibrations [58–61], sound [62–64], sound from several microphones [65] or ultrasound [66,67], vibro-acoustic [7], chemical analyses of lubrication [68,69], chemical analyses using spectral imaging [70–73], camera…”
In-Situ Analysis of Vibration and Acoustic Data in Additive Manufacturing
Waheed, M. F., & Bernadin, S. (2024) · IEEE SoutheastCon · doi:10.1109/southeastcon52093.2024.10500055 · Cited by 21
“Accelerometers have been utilized to analyze and control the vibration of 3D printers, with the extracted acceleration data being used to identify various states of the FFF machine and predict product quality[14][15].”
BackgroundMethodGear Fault Diagnosis Under Variable Load Conditions Based on Acoustic Signals
Chen, Q., Yao, Y. F., Gui, G., & Yang, S. (2022) · IEEE Sensors Journal · doi:10.1109/jsen.2022.3214286 · Cited by 20
Self-citationPlanetary gear train microcrack detection using vibration data and convolutional neural networks
Emmanuel, S., Yihun, Y., Ahmadabadi, Z. N., & Boldsaikhan, E. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-06314-x · Cited by 20
Wu, F., Xiang, Z., Xiao, D., Hao, Y., Qin, Y., Pu, H., & Luo, J. T. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109550 · Cited by 19
Acoustic signal analysis for gear fault diagnosis using a uniform circular microphone array
Li, C., Chen, C., & Gu, X. (2023) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-023-1002-8 · Cited by 17
“With the development of deep learning in recent years, researchers have extensively introduced related algorithms including convolutional neural network (CNN), backpropagation (BP), support vector machine (SVM), etc. [24-27].”
BackgroundTu, F., Zhang, T. Y., Liu, T., Zhang, D., & Yang, S. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551919 · Cited by 16
“For instance, Yao et al. [12] developed an end-to-end convolutional neural network (CNN) for gear fault diagnosis.”
Electrical Motor Fault Detection System using AI's Random Forest Classifier Technique
Yaqub, R., Ali, H., & Wahab, M. H. B. A. (2023) · IEEE International Conference on Advanced Systems and Emergent Technologies (IC_ASET) · doi:10.1109/ic_aset58101.2023.10150924 · Cited by 13
“End-to-end convolutional neural network model for gear fault diagnosis based on sound signals also uses sound dataset [6].”
Parking Guidance System Using Wireless Sensor Networks
Rasheed, K., Shahzad, L., Saad, S., Khan, H. A., Ahmed, W., & Sadiq, T. (2021) · International Conference on Decision Aid Sciences and Applications (DASA) · doi:10.1109/dasa53625.2021.9682213 · Cited by 13
Research on Fault Diagnosis Method Based on Improved CNN
Hao, H., Feng, F., Zhu, J., Xun, Z., Jiang, P., Feng, J., Jun, X., Yazhi, L., & Guanghui, S. (2022) · Shock and Vibration · doi:10.1155/2022/9312905 · Cited by 13
“[22] proposed a novel deep learning-based gear fault diagnosis method based on sound signal analysis.”
BackgroundDecai, Z., Ren, X., & Zuo, H. (2021) · Shock and Vibration · doi:10.1155/2021/6669006 · Cited by 13
“[23] input the time-domain and frequency-domain signals as the original signals to the end-toend convolutional neural network (CNN) for gear fault diagnosis.”
BackgroundFault Diagnosis of Wind Turbine Gearboxes Based on Multisource Signal Fusion
Zhong, Q., Liu, S., Liu, C., Liu, W., Liu, S., Zhao, Y., & Wu, Y. (2025) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2025.3551792 · Cited by 15
Fault Diagnosis to Nuclear Power Plant System Based on Time‐Series Convolution Neural Network
Li, X., Han, D., Dai, X., Lv, S., Tao, M., Zheng, W., & Tang, Y. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/3323239 · Cited by 15
“[16] integrated the time-domain and frequency-domain characteristics of multichannel acoustic signals through CNN and realized the diagnosis of gear fault.”
BackgroundHa, J. M., & Youn, B. D. (2021) · IEEE Access · doi:10.1109/access.2021.3083804 · Cited by 12
“The difference signal is obtained from the TSA signal by eliminating the regular components of the planetary gearbox, including GMF and their sidebands along with the harmonics that are not significantly related to the fault of the gearbox [4], [38].”
BackgroundHerzog, C., Wolf, M., Schubert, D., & Drummer, D. (2022) · Forschung im Ingenieurwesen · doi:10.1007/s10010-022-00591-1 · Cited by 12
Lee, S., & Lee, S. (2020) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-020-1009-3 · Cited by 11
Fault detection in water pumps based on sound analysis using a deep learning technique
Nguyen, M.-T., & Huang, J. H. (2021) · Proceedings of the Institution of Mechanical Engineers Part E Journal of Process Mechanical Engineering · doi:10.1177/09544089211039304 · Cited by 14
“Yao et al. 4 proposed a fault diagnosis method that involved the frequency domain analysis of a sound signal emitted from a gearbox placed in a semi-anechoic room; the spectrogram images were classi fi ed by a convolution neural network (CNN) model and the classi fi cation accuracy was over 96%.”
BackgroundMethodJo, H.-K., Kim, S.-H., & Kim, C.-L. (2022) · Nuclear Engineering and Technology · doi:10.1016/j.net.2022.10.019 · Cited by 11
“Finally, there is also a way to use the CNN algorithm by receiving sound from several microphones and composing the input with multiple channels [14].”
Fault Diagnosis of Electric Impact Drills Based on Time‐Varying Loudness and Logistic Regression
Ya-peng, J., Su, H., Wang, S., Gui, W., & Qing, G. (2021) · Shock and Vibration · doi:10.1155/2021/6655090 · Cited by 11
A confidence-guided DS fault diagnosis method for tidal stream turbines blade
Xu, Y., Wang, T., Diallo, D., & Amirat, Y. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2024.118807 · Cited by 10
Xu, J., Wang, Z., Tan, C., Lu, D., Wu, B., Su, Z. C., & Tang, Y. (2018) · Symmetry · doi:10.3390/sym10120736 · Cited by 10
“The acoustic-based system has obvious advantages due to its compact structure, non-touching measurement style, and convenient maintenance [6].”
BackgroundA Dynamic Spatial–Temporal Subgraph Convolutional Network for Noncontact Fault Diagnosis
Cao, Y., Chen, Y., Zhang, D., & Guo, F. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3522422 · Cited by 9
“The acquisition process is highly affected by the surface of mechanical equipment, such as oil, slippery, and geometric irregularities, which makes it difficult to collect vibration signals [18].”
Gear fault diagnosis based on SGMD noise reduction and CNN
Chen, W., Hao, W. A. N. G., Zhuoxian, L. I., & Zhou, Z. (2022) · Journal of Advanced Mechanical Design Systems and Manufacturing · doi:10.1299/jamdsm.2022jamdsm0031 · Cited by 9
Self-citationGear Reducer Fault Diagnosis Using Learning Model for Spectral Density of Acoustic Signal
Oh, S. W., Lee, C., & You, W. (2019) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc46691.2019.8939913 · Cited by 9
“Lots of studies have been done on how to analyze vibration [1-4], temperature [5, 6], electric current [7, 8], or acoustic signals [9-11] to diagnose failures of various machines such as pumps, turbines, and generators.”
BackgroundBiswas, S., Mamun, A. A., Islam, M. S., & Bappy, M. M. (2025) · Manufacturing Letters · doi:10.1016/j.mfglet.2025.06.015 · Cited by 9
Asalapuram, V., Khan, I., & Rao, K. P. (2019) · International Symposium on Measurement and Control in Robotics (ISMCR) · doi:10.1109/ismcr47492.2019.8955729 · Cited by 8
“In [11], CNN based deep learning scheme is proposed by Yong Yao et.”
MethodHerzog, C., & Drummer, D. (2023) · Polymers · doi:10.3390/polym15183809 · Cited by 7
“Numerous studies focus on the detection of acoustic and vibrational signals as an expression of typical types of gear failure, such as cracks [13,14], tooth flank wear [13,15] and pitting [13,16].”
BackgroundYang, N., Liu, J., Ma, H., Zhao, W., & Gao, Y. (2025) · Journal of Mechanical Science and Technology · doi:10.1007/s12206-025-0406-z · Cited by 6
“Many current models, such as CNN [25], AlexNet [26], GoogLeNet [27], deep belief network [28], and their variants [29-31], excel at local feature modeling using convolutional-pooling-fully connected layers.”
Test Rig for the In Situ Measurement of the Elastic Tooth Deflection of Plastic Gears
Herzog, C., & Drummer, D. (2023) · Polymers · doi:10.3390/polym15071732 · Cited by 6
“Numerous studies focus on the detection of acoustic and vibrational signals as an expression of typical types of gear failure such as cracks [12,13], tooth flank wear [12,14] and pitting [12,15].”
BackgroundA Novel Air-Door Opening and Closing Identification Algorithm Using a Single Wind-Velocity Sensor
Shang, W., Deng, L., & Liu, J. (2022) · Sensors · doi:10.3390/s22186837 · Cited by 6
“proposed a gear fault diagnosis method based on the time and frequency‐domain signals and a convolutional neural network (CNN) model [10].”
BackgroundMethodA novel dust collection system fault diagnosis based on the noise emission of solenoid pulse valve
Guan, D., Wang, R., Li, J., & Hou, J. (2024) · Measurement · doi:10.1016/j.measurement.2024.114676 · Cited by 5
Han, S., Li, J., Pang, K., Zhen, D., Feng, G., Tian, F., & Niu, P. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adc761 · Cited by 7
“Yao et al [13] developed an end-to-end CNN is capable of processing time and frequency domain signals as raw inputs for the model and fusing multi-channel information from different sound signals through its channels without an extra fusion algorithm.”
Fault diagnosis of gear based on URP-CVAE-MGAN under imbalanced and small sample conditions
Yang, N., Liu, J., Ma, H., Zhao, W., & Gao, Y. (2024) · Eksploatacja i Niezawodnosc - Maintenance and Reliability · doi:10.17531/ein/199417 · Cited by 5
“Convolutional Neural Networks (CNN) [25], AlexNet [26], GoogLeNet [27], Deep Belief Network [28] and their variants [29-31] The paper is organized as follows: Section 2 presents the theoretical backdrop, Section 3 elaborates on the proposed method, Section 4 compares the method’s performance to…”
FPGA-based intelligent bearing fault diagnosis under varying-speed conditions
Li, J., Cheng, M., Wei, Y.-B., & Dai, Z. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/add288 · Cited by 5
“Neural networks can directly extract features from raw time-domain vibration signals and classify fault types with high accuracy [16–18], significantly improving diagnostic efficiency and reliability.”
Mechanical Fault Diagnosis Using Audio Signal Feature Fusion and Fuzzy Inference
Tang, L., Tian, H., Huang, H. F., & Xie, J. (2023) · China Automation Congress (CAC) · doi:10.1109/cac59555.2023.10451234 · Cited by 4
Acoustic Monitoring in Industrial Plants with Autoencoders and a Mobile Robot
Fujita, H., Kasahara, J. Y. L., Kanda, S., Nagatani, K., Kasahara, S., Fukumoto, S., Tamura, S., Kato, T., Korenaga, M., Sasamura, A., et al. (2023) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur57808.2023.10202270 · Cited by 3
Artificial Neural Networks for Induction Motor Fault Classification
Mujaahid, F., Huda, T., Hsieh, M., & Mustar, M. Y. (2024) · International Conference on Electronic and Electrical Engineering and Intelligent System (ICE3IS) · doi:10.1109/ice3is62977.2024.10775319 · Cited by 3
“The findings indicate that this approach is effective in classifying motor faults [6][7].”
Optimized LSTM-BiTCN parallel network model for anomalous sound detection in rotating machinery
Luo, Y., Wang, M., Luo, L., Liu, Z., & Zhao, J. (2025) · Measurement Science and Technology · doi:10.1088/1361-6501/adc1f7 · Cited by 3
“Yao et al [7] proposed a stacked convolutional neural network (CNN) model for gear fault diagnosis, leveraging the network’s ability to automatically extract features.”
Self-citationDevelopment of Fast Refinement Detectors on AI Edge Platforms
Choi, M.-K., & Jung, H. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-68799-1_43 · Cited by 4
Wang, Z., Liang, B., Si, L., Tong, K., & Tan, C. (2020) · Shock and Vibration · doi:10.1155/2020/8835462 · Cited by 3
“Yao et al. [6] established a convolutional neural network for gear fault diagnosis by using the time and frequency domain sound signals.”
BackgroundGuo, R., Zhang, J., Chen, D., Zhang, H., Wei, C., Wang, J., & Xiong, C. (2025) · Nondestructive Testing And Evaluation · doi:10.1080/10589759.2025.2588693 · Cited by 2
Acoustic-Based Fault Detection for Robotic Arms
Gong, C. A., Su, C.-H. S., Chao, K.-W., Lin, C.-Y., & Chen, Y.-H. (2025) · IEEE Journal of Selected Areas in Sensors · doi:10.1109/jsas.2025.3638975 · Cited by 2
“By capturing intricate temporal and spectral patterns, these representations are quite effective in detecting mechanical faults in rotating machinery [93].”
Liu, Y., Kang, J., Guo, C., Bai, Y., & Meng, S. (2022) · Wireless Communications and Mobile Computing · doi:10.1155/2022/7674421 · Cited by 2
“Further in terms of feature extraction, the time-frequency domain signal analysis method can accurately describe and cover the fault information of the signal from the perspective of the fault mechanism [22, 23]; therefore, this paper extracts the MCKD value, 14 common time-domain features, and wavelet packet decompos…”
MethodResearch on fault type identification method for electrical equipment based on MFCC-CNN
Wang, C., Zheng, H., Yin, Q., & Yi, X. (2024) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2770/1/012028 · Cited by 2
“Yao et al. fused multi-channel acoustic signals by establishing an end-to-end stacked CNN model [8] .”
BackgroundFang, X., Fang, H., Feng, Z. Z., Wang, J., & Zhou, L. (2019) · Applied Sciences · doi:10.3390/app10010139 · Cited by 2
“With the development of neural networks, more deep learning models have become outstanding in the field of detection, including machine vision non-standard workpiece detection [3–6], motor fault current signal detection [7], bearing vibration signal detection [8], and gear fault diagnosis based on sound signals [9].”
Background(2019) · International Journal of Innovative Technology and Exploring Engineering · doi:10.35940/ijitee.a9165.119119 · Cited by 2
Detection method for electric impact drill parts defect based on auditory peripheral model
Su, H., Gu, J., Li, J., Hu, H., & Xu, C. (2023) · Applied Acoustics · doi:10.1016/j.apacoust.2023.109599 · Cited by 2
Han, D., Dai, X., & Lyu, S. (2023) · International Conference on Computer Science and Network Technology (ICCSNT) · doi:10.1109/iccsnt58790.2023.10334584 · Cited by 2
“The study of time-varying characteristics has a more mature paradigm in mechanical failure analysis [17] [18] [19] [20], which is usually studied using a time-series method.”
BackgroundReview on Intelligent Fault Diagnosis of Wind Tunnel Test System
Yan, G. (2024) · Mechanisms and machine science · doi:10.1007/978-981-97-0922-9_94 · Cited by 2
Deep Autoencoder Model for Hypoid Gear Fault Diagnosis With Dynamic Torque and Rotation Speed
Žvirblis, T., Skrickij, V., & Kilikevičius, A. (2024) · IEEE Workshop on Advances in Information, Electronic and Electrical Engineering (AIEEE) · doi:10.1109/aieee62837.2024.10586692 · Cited by 1
“Yao et al. [9] proposed a method of integrated CNN valve recurrent unit models to solve the problem of gear pit fault diagnosis.”
MethodAbnormal sound detection for gearboxes based on multiscale spectrum and temporal fusion network
Wang, K., Zhu, W., Qu, W., Mao, L., Yang, L., Yang, G. J., Gu, X., & Guo, L. (2025) · Industrial Lubrication and Tribology · doi:10.1108/ilt-11-2024-0431 · Cited by 1
Non-contact Sensor-Based Gear Fault Diagnosis with Bark Domain Feature Analysis
Su, H., Huang, J., Gu, J., Xu, C., Xu, J. Q., & Hu, H. (2025) · Journal of Failure Analysis and Prevention · doi:10.1007/s11668-025-02322-4 · Cited by 1
“The dataset from an article by Yao et al. is used in this study [13, 14].”
InfluentialKuendee, P. (2019) · International Conference on Big Data and Internet of Things (BDIOT) · doi:10.1145/3361758.3361772 · Cited by 1
“Hence, a sound signal is used as an input for these reasons[11-12].”
BackgroundUnknown Abnormal Sound Recognition of Aircraft Cabin Noise Based on Autoencoder
Zhao, C., Chen, J., & Song, C. (2024) · International Conference on Cloud Computing, Big Data Application and Software Engineering (CBASE) · doi:10.1109/cbase64041.2024.10824484 · Cited by 1
Metadata
- Authors
- Yao, Y., Wang, H., Li, S., Liu, Z., Gui, G., Dan, Y., & Hu, J.
- Affiliations
- Guizhou University (CN)
- University of South Carolina (US)
- National Institute of Measurement and Testing Technology (CN)
- Corresponding author
- Li, Shaobo
- Hu, Jianjun
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2018-09-07
- Volume
- 8
- Issue
- 9
- Pages
- 1584
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W2891044424
- Cited by
- 120
- References
- 30
- Citations by year
- 2026: 4 · 2025: 21 · 2024: 14 · 2023: 19 · 2022: 13 · 2021: 20 · 2020: 16 · 2019: 11 · 2018: 2
- FWCI
- 7.58
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- Scholar Commons (University of South Carolina) (submittedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Natural Science Foundation of China (91746116 and 51741101)
- Science and Technology Project of Guizhou Province (. [2017]2308, Talents [2015]4011 and [2016]5013, Collaborative Innovation [2015]02)
- Topics
- Physical Sciences › Engineering › Control and Systems Engineering › Machine Fault Diagnosis Techniques
- Physical Sciences › Engineering › Mechanical Engineering › Gear and Bearing Dynamics Analysis
- Physical Sciences › Computer Science › Signal Processing › Music and Audio Processing
- Keywords
- gear fault diagnosis, acoustic signal analysis, acoustic signals, end-to-end convolutional neural network, channel fusion, vibration signal acquisition
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.