Showing papers by "Stephen Ekwaro-Osire published in 2018"

Machine Learning in Crack Size Estimation of a Spur Gear Pair Using Simulated Vibration Data

Abstract: Gears are the main components of power transmissions and are subjected to high cyclic load regime which can lead to premature fracture of the gear teeth. In order to prevent such events, research on gear condition monitoring and fault diagnostics techniques have received considerable attention. Machine learning (ML) applications have been widely combined with vibration measurement and analysis techniques for fault diagnostics in gearboxes and the majority of current techniques rely on experiments to generate training data. Despite the recognized advantages of using simulated data to train ML classifiers, this approach is still not a widespread practice. This paper proposes a simulation-driven ML framework to estimate the crack size in a gear tooth using simulated vibrations signals. Firstly, a 6-degrees-of-freedom model of a one-stage gearbox was developed to simulate the dynamic behavior of a cracked pinion. Secondly, a sample with 900 simulated vibration signals was generated considering 4 different crack sizes in the pinion tooth. Thirdly, the features of the vibration signals were extracted using 20 statistical indicators and, then, the extracted features were used to train and test 4 machine learning classifiers. Several performance evaluation metrics were computed, and the performance of the ML classifiers was compared and discussed. It was shown that the Decision Tree Classifier (DTC) performed best in the identification of small crack sizes regardless of the random selection of the training subsample.

Factors affecting innovation in engineering design teams: An empirical investigation of student team perceptions

Abstract: Innovation is a catalyst for economic growth, competitiveness, and sustainability worldwide. Knowledge has beenidentified as a key drivingforce for innovation usually resulting in intellectual property as a reward for creativity. Engineersof today are expected to possess abilities for teamwork, creativity, and innovation in order to meet the challenges andcomplexities of the 21st century. However, there is insufficient empirical evidence explaining the organizational, social andcognitive processes affecting innovation among engineering student design teams—the engineers of tomorrow. Theresearch addresses the question: What are the factors affecting Innovation in engineering student design teams? The studyadvances a framework for engineering student team innovation and uses survey data from a representative ABETaccredited four-year institution of higher learning involving 709 participants constituting 210 design teams from 40 designsections across nine academic departments at a college of engineering during an academic year. Validity and reliability ofthe survey instrument were obtained by using pre-existing scales, a pilot test, factor analyses, and scale reliability analysis.Other analyses involved aggregation analysis, ANOVA, correlation, and hierarchical linear modeling. A validated 59-itemsurvey scale was realized. Perceived engineering student team innovation is found to be significantly related to leadership,support for innovation, rewards, team size, communication, task orientation, effort, learning, cohesion, conflict andparticipative safety at the team level. Most study findings agree with general organization team innovation literature withexceptions of participative safety and support for innovation. Findings from the study have implications for theimprovement of engineering design curriculum and provide a framework for endeavors to harness skills for teamworkand innovation among engineering graduates through enhancing or regulating the determinants of innovation. A linearmodel for assessing team innovation among engineering students is elaborated in the study.