Call for Paper: Special Issue on Machinery Diagnostics and Prognostics Using Artificial Intelligent Techniques
摘要截稿:
全文截稿: 2019-05-31
影响因子: 6.471
期刊难度:
CCF分类: 无
中科院JCR分区:
• 大类 : 工程技术 - 1区
• 小类 : 工程:机械 - 1区
Overview
Diagnostics and prognostics are two important aspects in enhancing the availability and reliability of machineries. The past decades have witnessed an increasingly growing research interest in machinery diagnostics and prognostics due to significant advances in sensing techniques, and real interest in safe and reliable control of the machinery operations. The success of machinery diagnostics and prognostics relies on the timely acquisition, intelligent processing and shrewd utilization of various types of condition monitoring data from machineries. Huge amounts of data that are gathered to form the big data required for the delivery of machinery diagnostics and prognostics introduce significant challenges in applying traditional diagnostic and prognostic methods. Advanced artificial intelligence techniques, such as statistical learning, deep learning, transfer learning and adversarial learning, appear to offer potential tools to tackle these challenges. These techniques help to mine automatically valuable information from the big data and accurately identify/predict the state-of-health of machinery. It would make machinery diagnostics and prognostics less dependent on human labour and provide comprehensive information for predictive maintenance of machineries, to ensure their safe, reliable, and effective operations.
This special issue aims to provide a platform to present very high quality and promising original research as well as review articles on the latest developments of artificial intelligence techniques for machinery diagnostics and prognostics, including new theories, technical methodologies, and industrial applications. The research is expected to use real data collected from mechanical systems instead of generated data from hypothetical systems. In addition, any research inventing a simple model and then applying sophisticated techniques should be avoided. Potential topics include, but are not limited to:
Data cleaning using artificial intelligent techniques
Health indicator construction using artificial intelligent techniques
Transfer learning/adversarial learning for machinery diagnostics
Statistical learning/deep learning based diagnostics and prognostics
Condition-based maintenance and remaining useful life prediction