A Convolutional Neural Network Aided Physical Model Improvement for AC Solenoid Valves Diagnosis

@article{Tod2019ACN,
  title={A Convolutional Neural Network Aided Physical Model Improvement for AC Solenoid Valves Diagnosis},
  author={Georges Tod and Tamir Mazaev and Kerem Eryilmaz and Agusmian Partogi Ompusunggu and Erik Hostens and Sofie van Hoecke},
  journal={2019 Prognostics and System Health Management Conference (PHM-Paris)},
  year={2019},
  pages={223-227}
}
This paper focuses on the development of a physics-based diagnostic tool for alternating current (AC) solenoid valves which are categorized as critical components of many machines used in the process industry. Signal processing and machine learning based approaches have been proposed in the literature to diagnose the health state of solenoid valves. However, the approaches do not give a physical explanation of the failure modes. In this work, being capable of diagnosing failure modes while… 

Figures and Tables from this paper

Monitoring of solenoid parameters based on neural networks and optical fiber squeezer for solenoid valves diagnosis
TLDR
A new methodology for the functional diagnosis of electromagnetic solenoids used in hydraulic systems is proposed, which monitors online the electrical and mechanical parameters varying over time by using artificial neural networks algorithm coupled with an optical fiber polarization squeezer based on EMS for polarization scrambling.
Machine Learning for Monitoring of the Solenoid Valves Coil Resistance Based on Optical Fiber Squeezer
Solenoid valves represent indispensable elements in various engineering systems. Their failure can lead to unexpected problems. This failure may be caused by fluctuations in the coil resistance of
A Multi-Domain Diagnostics Approach for Solenoid Pumps Based on Discriminative Features
TLDR
This study presents a robust approach for vibration-based failure diagnostics of electromagnetic/solenoid pumps which employ a multi-domain feature extraction procedure (statistical time-domain and frequency-domain features, Mel frequency cepstral coefficients, and continuous wavelet coefficients) for capturing linear and nonlinear properties from the signals.

References

SHOWING 1-10 OF 10 REFERENCES
Real-Time Motor Fault Detection by 1-D Convolutional Neural Networks
TLDR
A fast and accurate motor condition monitoring and early fault-detection system using 1-D convolutional neural networks that has an inherent adaptive design to fuse the feature extraction and classification phases of the motor fault detection into a single learning body is proposed.
Deep learning and its applications to machine health monitoring
Detecting Solenoid Valve Deterioration in In-Use Electronic Diesel Fuel Injection Control Systems
TLDR
A diagnostic algorithm is proposed, including a feedback controller, a parameter identifier, a linear variable differential transformer (LVDT) sensor, and a neural network classifier that can accurately identify the usability of solenoid valves.
Computational and experimental investigation on solenoid valve dynamics
  • V. Szente, J. Vad
  • Engineering
    2001 IEEE/ASME International Conference on Advanced Intelligent Mechatronics. Proceedings (Cat. No.01TH8556)
  • 2001
A generally applicable, synthetic simulation model and computational tool has been elaborated for dynamic simulation of solenoid valves (SV) applied as control elements in fast-response pneumatic
KEA-71 Smart Current Signature Sensor (SCSS)
This slide presentation reviews the development and uses of the Smart Current Signature Sensor (SCSS), also known as the Valve Health Monitor (VHM) system. SCSS provides a way to not only monitor
Towards better understanding of gradient-based attribution methods for Deep Neural Networks
TLDR
This work analyzes four gradient-based attribution methods and formally prove conditions of equivalence and approximation between them, and constructs a unified framework which enables a direct comparison, as well as an easier implementation.
Learning representations by back-propagating errors
TLDR
Back-propagation repeatedly adjusts the weights of the connections in the network so as to minimize a measure of the difference between the actual output vector of the net and the desired output vector, which helps to represent important features of the task domain.
Model Selection for Support Vector Machines
New functionals for parameter (model) selection of Support Vector Machines are introduced based on the concepts of the span of support vectors and rescaling of the feature space. It is shown that
Detecting solenoid valve deterioration in inuse electronic diesel fuel injection control
  • 2010