Abstract
Finding reliable condition monitoring solutions for large-scale complex systems is currently a major challenge in industrial research. Since fault diagnosis is directly related to the features of a system, there have been many research studies aimed to develop methods for the selection of the relevant features. Moreover, there are no universal features for a particular application domain such as machine diagnosis. For example, in machine bearing fault diagnosis, these features are often selected by an expert or based on previous experience. Thus, for each bearing machine type, the relevant features must be selected. This paper attempts to solve the problem of relevant features identification by building an automatic fault diagnosis process based on relevant feature selection using a data-driven approach. The proposed approach starts with the extraction of the time-domain features from the input signals. Then, a feature reduction algorithm based on cross-correlation filter is applied to reduce the time and cost of the processing. Unsupervised learning mechanism using K-means++ selects the relevant fault features based on the squared Euclidian distance between different health states. Finally, the selected features are used as inputs to a self-organizing map producing our health indicator. The proposed method is tested on roller bearing benchmark datasets.
Highlights
Bearing fault are one of the foremost causes of breakdown in rotating machines
The most important layer is the diagnostics layer or the health assessment because the successor layers such as presentation and decision supports rely strongly and directly on the diagnostics outputs, there will be no decision to make or data to present if the health sate of the machine in unknown. This is why we focused on the diagnostics, noting that the prognostic which is a main layer in condition-based maintenance (CBM) can be deducted from diagnostics result
The simulation was started with 12 features, and 7 were eliminated at isolation of redundant features process while the remaining were normalized for the relevant features selection task where the distance of K probability from equation (7) is measured and the two features with the best representation and the highest distance are considered as the relevant fault features
Summary
Bearing fault are one of the foremost causes of breakdown in rotating machines. It represents over 40% of the motor faults according to the research conducted by Electric Power Research Institute (EPRI) [1], [2]. Data-driven methods aim at transforming the raw monitoring data into relevant information of the system including the degradation which offers a good diagnostics accuracy; especially when the operating context is variable or in the case of new systems because of a lack of experts The results they offer are less precise than those provided by model-based methods [8]. The proposed method is an automatic fault diagnosis based on the extraction of time domain descriptors from the raw vibration signal. Health indicator is built for monitoring the health state of the bearing using self-organizing map as dimension reduction approach This method has the advantage of being simple because it is based on time domain descriptors calculated from vibration signals directly without any frequency response calculation which reduces computation time and costs.
Sign-in/Register to view highlights & summary 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.
