Artificial intelligent fault diagnosis system of complex electronic equipment

Research on Deep Learning Method and Optimization of Vibration Characteristics of Rotating Equipment

CNN extracts the signal characteristics layer by layer through the local perception of convolution kernel, but the rotation speed and sampling frequency of the vibration signal of rotating equipment are not the same. Extracting different signal features with a fixed convolution kernel will affect the local feature perception and ultimately affect the learning effect and recognition accuracy. In order to solve this problem, the matching between the size of convolution kernel and the signal (rotation speed, sampling frequency) was optimized with the matching relation obtained. Through the study of this paper, the ability of extracting vibration features of CNN was improved, and the accuracy of vibration state recognition was finally improved to 98%.

Characterization of top 100 researches on e-waste based on bibliometric analysis

With rapid development of energy, information, and communication technology, e-waste problem has become one of the global issues to be settled urgently. The main features on publication years, journals, countries and institutions, authors, keywords, and content types of the 100 most-cited articles on e-waste had been unfolded in this research. The direction and way forward were illustrated, the trends to date were demonstrated, and the terrain and pathways were evaluated on the research of e-waste. Bibliometric analysis method was applied to analyze various attributes on the 100 most-cited articles which were retrieved from WoSCC on May 25, 2021, by utilizing the software tools Microsoft Excel 2016 and VOS viewer 1.6.9. The publication year and citation number of the 100 articles ranged between 2003 and 2017 and from 83 to 925, respectively. Environmental Science & Technology (n=17) published the maximum articles. Waste Management, Journal of Hazardous Materials, and Environmental Science & Technology were the core journals on e-waste. One hundred twenty-three institutions and 25 countries were involved in publishing the 100 articles. Three hundred seventy authors contributed to the 100 articles in total. A total of 267 keywords occurred in the 100 articles. The keywords "e-waste" and "recycling" held the highest occurrences. The study content of the 100 articles could be classified into four types including the characteristic-and-property type, the environment-and-health type, the management-and-economic type, and the technique-and-processing type. Overall completeness and applicability of the evidence found in this study were verified sufficiently; the potential biases in the review process were also considered. The innovations of the research from the past bibliometric analysis work on e-waste were stated, and the implication for practice and research of this study were explained as well. 2007, 2008, and 2009 were a peak of the researches on e-waste, while the recent years were experiencing a valley. China and its institutions were most influential in this field on e-waste. India was becoming more and more influential on e-waste research in the world. Nigeria was the research center in Africa, and Brazil was the research center in Latin America. Wong Minghung was the most important expert on e-waste. The impact on environment and human being's health was the hot topic of researches on e-waste; the characteristic and property of e-waste were studied not enough. The researches of technique and processing would be the direction and way forward in the study field on e-waste. The characteristic and property on e-waste would need more attention to be researched. The researchers could develop new pathways based on and beyond the four types of content evaluated in this research.