Rotary Machines Diagnosis Systems Based on Feed Forward Neural Networks

Kazakov, Yu. N.; Kornaev, Alexey; Polyakov, Roman

doi:10.1109/rusautocon49822.2020.9208118

Cited by 4 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The data received from the Analog input module NI 9205 is used to collect the dataset. The data received from the contact resistance sensor, 28 the pressure sensor KPT5-3, the proximity probes AE051.00.07 and the electromotor frequency converter ALTIVAR 312 is the half part of the dataset for machine learning. The other part of the data received from the microphone 4192-L-001 and the vibroaccelerometers 4507-001 of the Bruel&Kjaer portable data acquisition unit PULSE Type 356° C (see Figure 2 and Table 1).…”

Section: The Test Rig and The Test Resultsmentioning

confidence: 99%

Fault diagnosis systems for rotating machines operating with fluid-film bearings

Stebakov

Kornaev

Popov

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part J:

Self Cite

View full text Add to dashboard Cite

The paper deals with the application of deep learning methods to rotating machines fault diagnosis. The main challenge is to design a fault diagnosis system connected with multisensory measurement system that will be sensitive and accurate enough in detecting weak changes in rotating machines. The experimental part of the research presents the test rig and results of high-speed multisensory measurements. Six states of a rotating machine, including a normal one and five states with loosened mounting bolts and small unbalancing of the shaft, are under study. The application of deep network architectures including multilayer perceptron, convolutional neural networks, residual networks, autoencoders and their combination was estimated. The deep learning methods allowed to identify the most informative sensors, then solve the anomaly detection and the multiclass classification problems. An autoencoder based on ResNet architecture demonstrated the best result in anomaly detection. The accuracy of the proposed network is up to 100% while the accuracy of an expert is up to 65%. A one-dimensional convolutional neural network combined with a multilayer perceptron that contains a pretrained encoder demonstrated the best result in multiclass classification. The detailed fault detection accuracy with the determination of the specific fault is 83.3%. The combinations of known deep network architectures and application of the proposed approach of pretraining of the encoders together with using a block of inputs for one prediction demonstrated high efficiency.

show abstract

Section: The Test Rig and The Test Resultsmentioning

confidence: 99%

Fault diagnosis systems for rotating machines operating with fluid-film bearings

Stebakov

Kornaev

Popov

et al. 2022

Proceedings of the Institution of Mechanical Engineers, Part J:

Self Cite

View full text Add to dashboard Cite

show abstract

“…A large number of research works focus on the development of a calculation model for radial sliding bearings with metal coating [1][2][3][4][5][6][7][8][9][10][11][12]. However, lubrication on fused coatings is not a self-sustaining process.…”

Section: Introductionmentioning

confidence: 99%

Calculation model for lubrication of bearings with unconventional support surface profile and fusible shaft surface coating

Badakhov

Zinoviev²,

Мукутадзе³

et al. 2023

E3S Web of Conf.

View full text Add to dashboard Cite

This research work uses the true viscous fluid flow equation for the thin layer, the continuity equation, and the equation describing the radius of the fused shaft coated with a metal alloy taking into account the mechanical energy dissipation rate formula to find the asymptotic and the exact self-similar solution for the zero and first-order approximation for the radial sliding bearing with the support profile adapted to friction and lightalloy coating for incomplete filling of the working gap. We obtained the analytical dependencies for the fused surface radius of metal coating and the speed and pressure field. Besides, we determined the key operating parameters of the reviewed friction couple, the carrying capacity, and the friction force. The authors assess the impact of the parameters associated with the fusing of the coating of the friction-adapted support profile and the length of the loaded area on the carrying capacity and the friction force.

show abstract

Mathematical Model of Flow of Lubricant and Molten Coating with Micropolar Rheological Properties in Running Clearance of Journal Bearing with Non-circular Bearing Surface Profile, Considering Pressure Dependence of Viscosity

Мукутадзе

Lagunova

2022

Proceedings of the 8th International Conference on Industrial Engineering

View full text Add to dashboard Cite

Rotary Machines Diagnosis Systems Based on Feed Forward Neural Networks

Cited by 4 publications

References 12 publications

Fault diagnosis systems for rotating machines operating with fluid-film bearings

Fault diagnosis systems for rotating machines operating with fluid-film bearings

Calculation model for lubrication of bearings with unconventional support surface profile and fusible shaft surface coating

Mathematical Model of Flow of Lubricant and Molten Coating with Micropolar Rheological Properties in Running Clearance of Journal Bearing with Non-circular Bearing Surface Profile, Considering Pressure Dependence of Viscosity

Contact Info

Product

Resources

About