As the core of transmission system, gear fault could be the cause of a huge train accident. In this paper, a novel diagnosis strategy of gear fault based on the artificial intelligence deep learning method and the rig...
详细信息
ISBN:
(纸本)9781665453318
As the core of transmission system, gear fault could be the cause of a huge train accident. In this paper, a novel diagnosis strategy of gear fault based on the artificial intelligence deep learning method and the rigid-flexible coupling dynamic analysis technology is proposed. Firstly, the train-rail dynamics model is created in SIMPACK and ANSYS. The finite element analysis is carried out to make the rail flexible. The rigid-flexible coupling model is obtained by introducing the flexible rail into the rigid SIMPACK model. Then, parametrically model the healthy and the fault gears in MATLAB and SOLIDWORKS. The gear pair is loaded into SIMULINK to sample vibration signals, which are then imported into SIMPACK as vibration exciter to stimulate the dynamic response vibration signal of the train-rail system. Finally, considering that image is the ideal medium for complex information representation, the vibration signal is converted into the image to generate the training dataset of the deep learning network. The improved Efficient Net with the Coordinate Attention Module is proposed and trained to recognize gear faults. The test experiment verifies the effectiveness and reliability of the proposed method.
The recent availability of quantum annealers as cloud-based services has enabled new ways to handle machine learning problems, and several relevant algorithms have been adapted to run on these devices. In a recent wor...
详细信息
ISBN:
(纸本)9798331541378
The recent availability of quantum annealers as cloud-based services has enabled new ways to handle machine learning problems, and several relevant algorithms have been adapted to run on these devices. In a recent work, linear regression was formulated as a quadratic binary optimization problem that can be solved via quantum annealing. Although this approach promises a computational time advantage for large datasets, the quality of the solution is limited by the necessary use of a precision vector, used to approximate the real-numbered regression coefficients in the quantum formulation. In this work, we focus on the practical challenge of improving the precision vector encoding: instead of setting an array of generic values equal for all coefficients, we allow each one to be expressed by its specific precision, which is tuned with a simple adaptive algorithm. This approach is evaluated on synthetic datasets of increasing size, and linear regression is solved using the D-Wave Advantage quantum annealer, as well as classical solvers. To the best of our knowledge, this is the largest dataset ever evaluated for linear regression on a quantum annealer. The results show that our formulation is able to deliver improved solution quality in all instances, and could better exploit the potential of current quantum devices.
With the rapid development of emerging engineering education, virtual simulation has become a major direction in experimental teaching. However, virtual simulation experiment teaching is clearly different from traditi...
详细信息
Generated Adversarial Network has been widely used in the field of image style transfer. Among them, ChipGAN is specifically aimed at the study of Chinese ink painting style transfer. In previous studies, it has demon...
详细信息
Recently we have been hearing a lot about artificial intelligence and how it can influence the ways we are doing things, for the better or the worse. In particular, the effects it has on education and learning has rec...
详细信息
In essence, doctoral students who opt for an academic career path will have to become instructors. Nonetheless, research indicates that most PhD students have greater research experience than teaching experience. Furt...
详细信息
ISBN:
(纸本)9798350376234
In essence, doctoral students who opt for an academic career path will have to become instructors. Nonetheless, research indicates that most PhD students have greater research experience than teaching experience. Furthermore, they may have taught through graduate teaching assistantships, which may or may not have included teaching-related training. If the doctoral students are not completely aware of all the different aspects that come with teaching, it can be challenging if they decide to become faculty members. The purpose of this study is to examine the factors influencing engineering doctoral students' perceptions on their preparedness to teaching courses when they start their academic careers.A survey instrument was distributed digitally to students across 16 R1 universities across the United States (resulting n = 285). Three sections comprised the survey instrument: demographic data, free response questions, and Likert scale questions. The Likert scale questions evaluate the participants' confidence or preparedness in areas of teaching such as the teaching and learning process (9 items);course design and delivery (8 items);creating a dynamic classroom (9 items);harnessing the power of technology (6 items);collaborative learning (6 items);and effective assessment (8 items). The data was collected in fall 2023. Exploratory factor analysis (EFA) was conducted to validate the factor structure. EFA revealed six factors, five factors were same as hypothesized (the teaching and learning process, course design and delivery, creating a dynamic classroom, collaborative learning, and effective assessment) and one new factor (ethical practices). The factor loadings for the final factors ranged from 0.42 to 0.99, and the internal consistency reliability (Cronbach's α) for the six factors ranged from 0.77 to 0.86, indicating high *** this study, the t-test, one-way ANOVA, and multiple regression analyses were conducted. Gender identity of engineering doctoral stu
Despite their considerable dissemination, existing UML modeling tools suffer from significant limitations that stand in the way of their profitable use in practice as well as in teaching. This paper presents a new UML...
详细信息
ISBN:
(纸本)9783031790584;9783031790591
Despite their considerable dissemination, existing UML modeling tools suffer from significant limitations that stand in the way of their profitable use in practice as well as in teaching. This paper presents a new UML modeling tool, called UML-MX (c), that overcomes these limitations. It is based on a language architecture that not only enables the integration of class and object diagrams, but also the execution of objects in the diagram editor. Thus, it promotes a more inspiring learning experience. At the same time, it goes beyond the limitations of traditional approaches to model-driven software development by enabling a common representation of models and programs.
In this research, we focus on the on-demand learning environment where learners study alone and examine the possibility of facial expression measurement as a method to grasp the state of learners. In the on-demand lea...
详细信息
ISBN:
(纸本)9781665453318
In this research, we focus on the on-demand learning environment where learners study alone and examine the possibility of facial expression measurement as a method to grasp the state of learners. In the on-demand learning environment, it is considered that the learner's emotions are less likely to be expressed in facial expressions than in general face-to-face learning or communication with others. Also, we don't have sufficient information about what kind of emotions will represent. Therefore, in this paper, we construct a general facial expressions measurement system for measuring basic emotions, which appear commonly in all people, by image analysis and examine the possibility of grasping learners' states from the facial expression analysis results. We extracted scenes in which the emotional states of the participants were assumed to be different and compared the results of emotional output in each scene. We adopted correct and wrong answers to the quiz task as a criterion for the differences in participants' emotional states. The analysis results showed that the types of emotional output in scenes with different participants' emotional states were similar. Still, there were differences in the output patterns of emotions. Based on these results, it is expected that a facial expression measurement system specialized for on-demand learning environments can be constructed by adjusting the facial expressions and emotions that appear in learning situations.
Deep learning, a cutting-edge approach of machine learning, surpasses classical machine learning when it comes to detecting particular structures in complicated, high-dimensional data in the area of computer vision. T...
详细信息
teaching management of laboratory engineering courses is very important in higher education. Hands-on learning in a remote, proactive learning environment, encourages students to have expected competencies and working...
详细信息
ISBN:
(纸本)9783031268755;9783031268762
teaching management of laboratory engineering courses is very important in higher education. Hands-on learning in a remote, proactive learning environment, encourages students to have expected competencies and working experience. In particular, the innovative remote MIAP teaching model using a virtual laboratory can provide real-time online interactions for electrical engineering education in 21(st) century. The findings of this research show that the quality of the research tools and the effectiveness of the remote-based MIAP teaching model are agreeing to research hypothesis. In addition, it can be seen that teaching in the laboratory using an online laboratory package can enhance engineering students' ability to create themselves experiences and expected skills. Moreover, results could be helping to solve problems in online, on-hands or onsite learning that fails to provide learners with real practical skills.
暂无评论