This paper uses the combination between support vector machine and multi-scale principal component analysis. For motor fault detection, the principal component model can be established in various scales. Through T2 and Q statistic judgment whether motor can run normally. The experimental results show that the method of combination vector machine and multi-scale principal component analysis is supported to diagnose motor fault. This offers a new method and idea to diagnose motor. This method improves the accuracy of motor fault detection and practical significance.

In today’s competitive educational environment, the quality of physical education is ever more recognized as a fundamental factor in gaining competitive advantage. The evaluation and improvement of the quality of physical education in higher education is an important issue of on-going concern. The aim of this article is to focus on an automated management and evaluation system to efficiently control the administration of physical education. Reported in this article is an evaluation index of the quality of undergraduate education, and an analytic hierarchy process (AHP) model that is both practical and has proven to be successful. The results of the presented case study demonstrate the practicability and effectiveness of this model in physical education quality evaluation.

Basic principle and inference algorithm of Bayesian network (BN) were emphasized. As to the Fault Tree with basic events of common cause failure, accident probability cannot be computed correctly. An open press blunt hand accident risk assessment BN model was set up, in addition, the BN nodes of common cause failure were illustrated and the accident probability of occurrence was obtained. The discussions about computed results indicate that regarding to system with unit events of common cause failure or interdependent events, result of accident probability computed from a BN model is higher than that computed from the Fault Tree/Event Tree model.