Year: 2025
Type: conference-paper
Abstract: Using a tobacco factory as an example, this paper creates an intelligent fault diagnosis model based on artificial intelligence to improve the reliability of the work and the accuracy of fault diagnosis. By combining data collection, feature extraction and various algorithms, a false positive rate of 95.6% and 92.8% of fault diagnosis is achieved. At the same time, the average system response time was reduced to 1.25 s and the false alarm rate to 3.2%. The results show that the system has strong self-adaptive ability and can achieve 97.0% diagnosis accuracy under high temperature and voltage anomaly conditions, and the research results have significant theoretical significance and application value for improving the management level of industrial equipment.
Authors: Zhenzhen Yan, Wencheng Wang, Yu Zhang, Hong Wang
Institution: China Tobacco
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4410776709