2022/05/10 by Israel Zamudio-Ramirez, Israel Zamudio-Ramírez, Juan José Saucedo-Dorantes +6
Engineering · #Advanced machining processes and optimization #Gear and Bearing Dynamics Analysis #Machine Fault Diagnosis Techniques
paper · doi:10.1109/tia.2022.3174049
openalex publication_date 2022/05/10 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Gearboxes are core elements in power transmission systems. Although gearboxes are reliable and high-efficiency components, the occurrence of different faults is frequent since they are often subjected to adverse operating conditions. Classical gearbox condition monitoring approaches are based on the analysis of vibration and current motor signals and rely on the identification of specific fault-related frequency patterns. In this regard, this article proposes a novel diagnosis methodology based on the analysis of stray flux signals for detecting uniform wear in the gear teeth. The proposed methodology is based on the processing of the stray flux signals through feature calculation and extraction stages that lead to a high-performance signal characterization by estimating a set of statistical time domain-based features and then reducing the dimensionally by means of the principal component analysis and linear discriminant analysis techniques. Additionally, an automatic fault diagnosis is achieved through a neural network-based classifier for the detection and identification of uniform wear in a gearbox. The obtained results prove the potential of the proposal for its incorporation in condition maintenance programs in the industry, becoming an excellent alternative to classical approaches.