Data Analytics and Artificial Intelligence for Prognostics and Health Management (PHM) Using Disparate Data Streams

Submission Deadline: 30 November 2019

IEEE Access invites manuscript submissions in the area of Data Analytics and Artificial Intelligence for Prognostics and Health Management (PHM) Using Disparate Data Streams.

As the key technology of condition-based maintenance and autonomous protection for engineering systems and critical components, prognostics and health management (PHM) is of increasing interest to industry, government, and academia. Due to the complexity, integration and intelligence of engineered systems and critical components, there are two significant challenges in implementing fault prediction and health management of complex modern engineered systems. First, health monitoring data obtained by sensing systems have characteristics such as large volume, high velocity, and inhomogeneity. In engineering practice, in most cases, indirect health monitoring data streams are obtained rather than direct health monitoring data. Therefore, it is necessary to extract and derive valuable and meaningful system health indices from a large amount of disorganized/unstructured and difficult to understand raw data through data analytics. Second, the health degradation process of engineered systems and critical components exhibits a high degree of nonlinearity due to significant influencing factors, such as complex structure and varying environments, and uncertain tasks. These nonlinearities are difficult to be analytically derived. By simulating and extending human intelligence, artificial intelligence (AI) can help solve such highly nonlinear problems and achieve more accurate health prediction. Therefore, the application of data analytics and artificial intelligence possesses great potential to advance the innovations and implementation of prognostics and health management using large quantities of disparate data streams.

The topics of interest include, but are not limited to:

  • Advanced information sensing technologies for emitting excitations and receiving degradation data
  • Advanced Big Data Analytics for degradation data
  • Signal processing algorithms for reprocessing degradation data
  • Data fusion for degradation data
  • Extraction of health indicators from engineered systems and critical components
  • Abnormal health detection algorithms
  • Advanced modeling of complex engineered systems with nonlinearity and uncertainty
  • Advanced learning technologies for diagnostics and prognostics
  • Deep learning based diagnostic and prognostic algorithms
  • Uncertainty interpretation, uncertainty quantification, uncertainty propagation and uncertainty management
  • Intelligent performance evaluation
  • Decision Making for maintenance
  • Industrial applications and their success in prognostics and health management


We also highly recommend the submission of multimedia with each article as it significantly increases the visibility, downloads, and citations of articles.


Associate Editor:  Zhaojun (Steven) Li, Western New England University, USA

Guest Editors:

    1. Qiang Miao, Sichuan University, China
    2. Faisal Khan, Memorial University of Newfoundland, Canada
    3. Lance Fiondella, University of Massachusetts Dartmouth, USA
    4. Janet Lin, Lulea University of Technology, Sweden
    5. Jeff Voas, National Institute of Standard and Technology, USA


Relevant IEEE Access Special Sections:

  1. AI-Driven Big Data Processing: Theory, Methodology, and Applications
  2. Advances in Prognostics and System Health Management
  3. Data Mining for Internet of Things

IEEE Access Editor-in-Chief:
  Prof. Derek Abbott, University of Adelaide

Article submission: Contact Associate Editor and submit manuscript to:

For inquiries regarding this Special Section, please contact: