|
Fault Diagnosis using Kernel Linear Independence Test in Reproducing Kernel Hilbert Space |
|
Lamsu Kim(KAIST, Korea), Jayden Dongwoo Lee, Hyochoong Bang(Korea Advanced Institute of Science and Technology, Korea) |
| Fault detection and identification (FDI) is essential for ensuring the safety of mechanical systems. Typically, FDI algorithms begin by establishing fault detection methods and subsequently identifying the faults. The fault detection
process aims to detect abnormalities within the system. To initiate the fault detection process, a mathematical model is required for comparison. However, this mathematical model may not be fully known in advance. In this study, we propose
the implementation of Gaussian process regression (GPR) to learn the current nominal model using sensor datasets. The
learned model is then compared with newly acquired data to detect any occurrence of faults. |
|
|
Design and Implementation of a Fault Inspection System for the Festo Modular Production System (MPS) |
|
Alisultan Sagynbay, Azat Balapan, Tohid Alizadeh(Nazarbayev University, Kazakhstan) |
| The rapid development of automation systems and the increased demand for efficient fault detection in manufacturing processes have led to the need for advanced fault detection systems. In this study, we present a novel fault detection system for the Festo MPS 500 system that provides an easier approach of communication.
The system implements a camera and Python algorithms for accurate and reliable detection of misaligned parts. An image processing pipeline is developed that includes ROI selection, rectangle detection, fixed point selection, distance calculation, and digital signal communication with PLCs. The proposed system achieved a high level of accuracy in detecting misaligned parts. |
|
|
A Fault Diagnosis Method Based on Optimized SVDD And Multi-Symplectic Geometry Mode Decomposition for Rolling Bearings |
|
Jianqun Zhang, Qing Zhang, Wenzong Feng, Yuantao Sun(Tongji University, China) |
| The machine learning-based intelligent fault diagnosis method has the merits of fast response speed and automation, but requires many fault samples which are difficult to obtain. For rolling bearings in engineering, the normal samples collected are sufficient, while the fault samples are scarce. Because the operating time of the equipment in a normal state is much longer than the fault time. This paper proposes a two-stage rolling bearing fault diagnosis method that combines the advantages of machine learning and signal processing. In the first stage, the support vector data description optimized by a multi-objective grasshopper optimization algorithm is used to construct a fault detection m |
|
|
Application of a Statistical-based Feature Extraction Method for Harbor Crane Bearings in Fault Diagnosis |
|
Wenzong Feng, Qing Zhang, Jianqun Zhang, Yuantao Sun(Tongji University, China) |
| In response to the weak early fault features of harbor crane bearings that are difficult to extract and monitor online, this article proposes a signal feature extraction method based on maximum likelihood estimation and a generalized likelihood ratio index based on frequency domain statistical features, used for the identification of early bearing faults. The normalized envelope spectrum and sample labels of the signal are taken as inputs data, with several similar statistical models designed under this hypothesis. Key parameters are obtained for each statistical model via the maximum likelihood ratio method, and from this, a fault diagnosis index based on the log-likelihood ratio is design |
|
|
Transformer-based Network for Remaining Useful Life Estimation of Filter |
|
Keon hee Lee(Pusan National University, Korea), Dong-Joong Kang(Pusan National Univ, Korea) |
| Filters have played an important role in mechanical devices, and the proper use of filters has been able to extend the life of the mechanical device further. As a result, predicting the remaining life of the filter has been of great help in maintaining machine repair. In this study, we apply a method to predict the remaining life of the filter using the Transformer network. Using differential pressure data from filters and Gas turbine duct pressure data, we train Transformer networks and perform filter life prediction. This study demonstrates the potential of Transformer networks as an important tool for optimizing filter replacement planning and improving machine reliability. |
|
|
Sliding Mode Observer-Based Position-sensorless Control for Switched Reluctance Motors with Actuator Faults |
|
DongYoon Han, Seungju Moon, Gyu won Kim, Huibeom Youn(Kumoh National Institute of Technology, Korea), Bo-goon Kim(NUC Electronics, Korea), Jaepil Ban(Kumoh National Institute of Technology, Korea) |
| This paper proposes an actuator fault detection sliding mode observer (AFDSMO) for position-sensorless control of switched reluctance motors (SRMs) afflicted with failures in a motor drive. Specifically, we address the scenarios where a fault arise within the semiconductor switching devices of SRM drive, and we develop a dynamic model that describes an SRM control system with the fault. Then, we propose the AFDSMO that utilizes only phase current measurements to simultaneously estimate both the rotor position and faults. As a result, the proposed AFDSMO facilitates achieving position-sensorless control for SRMs in the presence of the actuator faults. |
|