Estimation of Rotational Speeds Based on Gearbox Vibrations via Artificial Neural Networks

This work investigates the estimation of rotational speeds based on neural networks and high sampled gearbox vibration data. A total of 18 different network architectures consisting of fully connected network layers, long short-term memory cells, and different activation functions are compared. In addition, the impact of the sampling rate of the vibration data, the signal length, and the input data type is investigated. Vibration data in the time domain, frequency domain, and a combination of both are examined as input data. Finally, the number of neurons is varied to obtain the best possible rotational speed estimation. In order to generate an appropriate dataset for the training of the neural networks, an experimental setup is presented, which is used to record the vibration data of the gearboxes. It becomes apparent that especially vibration data in the frequency domain are suitable for the estimation of the rotational speed. Furthermore, it could be shown that the low sampling rates result in an inaccurate speed estimation. Likewise, signal lengths that are too short result in inaccurate estimates. Overall, the speed can be estimated with an accuracy of 7.88 rpm at an average speed of the test dataset of 202 rpm.

[1]  R. Karlsson,et al.  Speed Estimation From Vibrations Using a Deep Learning CNN Approach , 2021, IEEE Sensors Letters.

[2]  Kishor Kumar Sadasivuni,et al.  Comparison of BPN, RBFN and wavelet neural network in induction motor modelling for speed estimation , 2020 .

[3]  Yu Yang,et al.  Enhanced deep gated recurrent unit and complex wavelet packet energy moment entropy for early fault prognosis of bearing , 2020, Knowl. Based Syst..

[4]  Myoungho Sunwoo,et al.  Ego-Vehicle Speed Prediction Using a Long Short-Term Memory Based Recurrent Neural Network , 2019, International Journal of Automotive Technology.

[5]  Steven B. Leeb,et al.  Review and comparison of tacholess instantaneous speed estimation methods on experimental vibration data , 2019, Mechanical Systems and Signal Processing.

[6]  Siliang Lu,et al.  Tacholess Speed Estimation in Order Tracking: A Review With Application to Rotating Machine Fault Diagnosis , 2019, IEEE Transactions on Instrumentation and Measurement.

[7]  Yi Qin,et al.  Adaptively Estimating Rotation Speed From DC Motor Current Ripple for Order Tracking and Fault Diagnosis , 2019, IEEE Transactions on Instrumentation and Measurement.

[8]  Kesheng Wang,et al.  An Order Analysis Based Second-Order Cyclic Function Technique for Planetary Gear Fault Detection , 2017, 2017 International Conference on Sensing, Diagnostics, Prognostics, and Control (SDPC).

[9]  Robert Jenssen,et al.  Recurrent Neural Networks for Short-Term Load Forecasting , 2017, SpringerBriefs in Computer Science.

[10]  Abdelkader Chaari,et al.  Spur gearbox mixed fault detection using vibration envelope and motor stator current signatures analysis , 2016, 2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering (STA).

[11]  Fang Liu,et al.  A Novel Contactless Angular Resampling Method for Motor Bearing Fault Diagnosis Under Variable Speed , 2016, IEEE Transactions on Instrumentation and Measurement.

[12]  Robert B. Randall,et al.  Rolling element bearing diagnostics using the Case Western Reserve University data: A benchmark study , 2015 .

[13]  Jimmy Ba,et al.  Adam: A Method for Stochastic Optimization , 2014, ICLR.

[14]  Hayri Arabaci,et al.  An artificial neural network approach for sensorless speed estimation via rotor slot harmonics , 2014 .

[15]  Yaguo Lei,et al.  A tacho-less order tracking technique for large speed variations , 2013 .

[16]  Konstantinos Gryllias,et al.  Estimation of the instantaneous rotation speed using complex shifted Morlet wavelets , 2013 .

[17]  José R. Perán,et al.  Angular resampling for vibration analysis in wind turbines under non-linear speed fluctuation , 2011 .

[18]  Geoffrey E. Hinton,et al.  Rectified Linear Units Improve Restricted Boltzmann Machines , 2010, ICML.

[19]  Radford M. Neal.  Pattern Recognition and Machine Learning , 2007, Technometrics.

[20]  Robert B. Randall,et al.  Use of the acceleration signal of a gearbox in order to perform angular resampling (with limited speed fluctuation) , 2005 .

[21]  S. Hochreiter,et al.  Long Short-Term Memory , 1997, Neural Computation.

[22]  Timothy Masters,et al.  Practical neural network recipes in C , 1993 .

[23]  J. W. Tukey,et al.  The Measurement of Power Spectra from the Point of View of Communications Engineering , 1958 .

[24]  Abhishek Chatterjee,et al.  Speed Estimation of Three Phase Induction Motor Using Artificial Neural Network , 2014 .

[25]  Andrew L. Maas.  Rectifier Nonlinearities Improve Neural Network Acoustic Models , 2013 .

[26]  Brian P. Graney,et al.  Rolling Element Bearing Analysis , 2012 .

[27]  Robert B. Randall,et al.  Comparison of Amplitude-Based and Phase-Based Methods for Speed Tracking in Application to Wind Turbines , 2011 .

[28]  Uwe Kiencke,et al.  Signalverarbeitung: Zeit-Frequenz-Analyse und Schätzverfahren , 2008 .

[29]  Michael Negnevitsky,et al.  Artificial Intelligence: A Guide to Intelligent Systems , 2001 .

[30]  J. Hoffmann.  Messen nichtelektrischer Größen , 1996 .

[31]  F. Kohlrausch.  Praktische Physik: Zum Gebrauch fur Unterricht, Forschung und Technik , 1960 .