Abstract
Toward the prognostic and health management of mechanical systems, we propose and validate a novel effective, data-driven fault diagnosis method. In this method, we develop a trained subtracted spectrogram, the so called critical information map (CIM), identifying the difference between the signal spectrograms of normal and abnormal status. We believe this diagnosis process may be implemented in an autonomous manner so that an engineer employs it without expert knowledge in signal processing or mechanical analyses. Firstly, the CIM method applies sequential and autonomous procedures of time-synchronization, time frequency conversion, and spectral subtraction on raw signal. Secondly, the subtracted spectrogram is then trained to be a CIM for a specific mechanical system failure by finding out the optimal parameters and abstracted information of the spectrogram. Finally, the status of a system health can be monitored accurately by comparing the CIM with an acquired signal map in an automated and timely manner. The effectiveness of the proposed method is successfully validated by employing a diagnosis problem of six-degree-of-freedom industrial robot, which is the diagnosis of a non-stationary system with a small amount of training datasets.
Highlights
Uncertainty in engineering has been considered as a critical problem as it could result in serious financial losses or catastrophic accidents
In order to overcome the limitations of the three different methods, we propose a new fault diagnosis method called a critical information map (CIM), that works with (1) relatively small amounts of data, (2) non-stationary signals, and (3) unknown system structures and dynamics as discussed in this study
We propose a Time Frequency Representation (TFR)-based CIM that includes the information of the locations within the TFR spectrograms that shows clear difference between normal and fault conditions
Summary
Uncertainty in engineering has been considered as a critical problem as it could result in serious financial losses or catastrophic accidents. It is critical to predict malfunctions or the life of manufacturing machines This requirement has resulted in active research regarding the prognostics and health management of machinery with the benefit of the fourth industrial revolution from the significant progress in data science, computer performance, and communication. For the health monitoring or diagnosis of a machine, we need sensors to measure the status of the machine, including sensors to measure temperature [1], pressure [2], volume pressure [3,4], and acceleration [5,6,7] Among these sensors, acoustic emission sensors and accelerometers are the most commonly used for monitoring machines as they can provide instantaneously the status of a machine with high data sampling frequencies, which is not possible with temperature or pressure sensors
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
