FMECA and MFCC-Based Early Wear Detection in Gear Pumps in Cost-Aware Monitoring Systems

Abstract

Gear pump failures in industrial settings are common due to their exposure to uneven high-pressure outputs within short time periods of machine operation and uncertainty. Improving the field and line clam are considered as the solutions for these failures, yet they are quite insufficient for optimal reliability. This research, therefore, suggests a method for early wear detection in gear pumps following an extensive failure modes, effects, and criticality analysis (FMECA) of an AP3.5/100 external gear pump manufactured by BESCO. To replicate this condition, fine particles of iron oxide (Fe2O3) were mixed with the experimental fluid, and the resulting vibration data were collected, processed, and exploited for wear detection. The intelligent wear detection process was explored using various machine learning algorithms following a mel-frequency cepstral coefficient (MFCC)-based discriminative feature extraction process. Among these algorithms, extensive performance evaluation reveals that the random forest classifier returned the highest test accuracy of 95.17%, while the k-nearest neighbour was the most cost efficient following cross validations. This study is expected to contribute to improved evaluations of gear pump failure diagnosis and prognostics.

Fault analysis and reliability evaluation for motorized spindle of cycloidal gear grinding machine based on multi-source bayes

“…Therefore, it is important to determine the problem of motorized spindle failure promptly and select an appropriate maintenance method [31] to reduce the impact of motorized spindle failure on normal production. Figure 10 shows that the signal energy corresponding to the node [3,6] accounts for 84.07%, and the remaining signal energy accounts for less than 10%. It can be observed that the frequency of the original signal is distributed in this node, and the other nodes are the frequency distribution of the noise signal.…”

“…Gajanand [2] considered the fuzzy Failure Mode, Effects and Criticality Analysis (FMECA) method to be more suitable for the system criticality problem by comparing traditional and fuzzy FMECA analysis methods. Lee [3] analyzed the fault in a gear pump and explored an intelligent wear detection process based on the Mel-Frequency Cepstrum coefficient. Joanna [4] proposed and discussed a matrix FMEA analysis method and applied it to select hydraulic components.…”

Current Status and Applications for Hydraulic Pump Fault Diagnosis: A Review

“…Ma et al [33] established a simulation model of the hydraulic system by using AMESim software and analyzed the failure modes and mechanisms of key components in the system and their failure effects. Lee et al [34] proposed to use FMECA to carry out extensive fault analysis of hydraulic gear pumps and proposed to use MFCC combined with a random forest classifier (RFC) to extract features and identify faults of vibration signals.…”

Towards Trustworthy Safety Assessment by Providing Expert and Tool-Based XMECA Techniques

“…In Ref. [25], it is stated that assessing the likelihood of failure, severity level, and detection rate provides a more reliable perspective for prioritizing failure modes as an adjunct to the "classic" addressing the severity of failure modes approach. The methodology proposed in Ref.…”