Big Data Predictive Maintenance

Scheduled maintenance plays a significant role in any product-based industry. As a result, the losses due to unscheduled maintenance are required to be minimized. The losses add immense financial burden to the manufacturers. The losses can occur due to loss of cycle time, cost of lost throughput, yield loss, rework, repair, and maintenance cost. Researchers and practitioners have developed a plethora of preventive maintenance techniques to determine the condition of in-service equipment in order to predict the schedule of maintenance. The predictive maintenance helps in downsizing unplanned shutdowns, thereby increasing equipment availability. Some other potential advantages include increased equipment life time, planned safety, optimal spare part handling, and few accidents with negative impact on environment, thus increasing total profit of the manufacturer.

The motivation of organizing this workshop at the 2020 IEEE International Conference on Big Data is to integrate the ideas of predictive maintenance using machine learning methods and data-driven optimization. Every industry has to work on predictive maintenance to rectify failure before it occurs. In this regard, the main topics of interest of this session are the developments and challenges in bringing the concepts of computer-integrated manufacturing and maintenance strategies. Big data analytics techniques are being applied in every sector including predictive maintenance. Big data is becoming popular due to the continuous developments of high-speed computer. The data is increasing rapidly everyday so handling this much data becomes more and more difficult.

Topics of interest to this workshop include (but are not limited to):

• Predictive maintenance using Artificial Intelligence techniques, Machine Learning and Deep Learning algorithms
• Identification of fault diagnosis
• Structural health monitoring, condition monitoring and decision support systems
• Modelling and optimization of processes
• Pre-processing and data analysis
• Characteristic fault features
• Critical manufacturing and industrial system for predictive maintenance
• Uncertainty based predictive maintenance
• Fault classification and feature selection for system diagnosis
• Time series based predictive maintenance
• Soft computing for predictive maintenance
• Predictive maintenance with live streaming data
• Internet of things (IoT) in big data and predictive maintenance
• Data Security and Privacy for predictive maintenance
• Distributed computing of sub-system maintenance data and aggregating the results on the system level

Paper Format and Submission

• Please submit a full-length paper (up to 10 page IEEE 2-column format) through the online submission system.
  
• Papers should be formatted to IEEE Computer Society Proceedings Manuscript Formatting Guidelines (see Formatting Instructions below).
  

Formatting Instructions

• 8.5" x 11" (DOC, PDF)
• LaTex Formatting Macros

Important Dates

Workshop Chairs

• Rituparna Datta, School of Computing, University of South Alabama
• Ryan Benton, School of Computing, University of South Alabama
• Aviv Segev, School of Computing, University of South Alabama

Presented Papers

• Ivan Melendez-Vazquez, Rolando Doelling, and Oliver Bringmann, "Multipath Temporal Convolutional Network for Remaining Useful Life Estimation"
• Sabtain Ahmad, Kevin Styp-Rekowski, Sasho Nedelkoski, and Odej Kao, "Autoencoder-based Condition Monitoring and Anomaly Detection Method for Rotating Machines"
• Sam Heim, Jason Clemens, James Steck, Christopher Basic, David Timmons, and Kourtney Zwiener, "Predictive Maintenance on Aircraft and Applications with Digital Twin"
• Henry Roberts and Aviv Segev, "Animal Behavior Prediction with Long Short-Term Memory"
• Bruno Paes Leao, Dmitriy Fradkin, Yubo Wang, and Sindhu Suresh, "Big Data Processing for Power Grid Event Detection"
• Suresh Choubey, Ryan Benton, and Tom Johnsten, "Dynamic Thresholding Leading to Optimal Inventory Maintenance"
• Hiroko Nagashima and Yuka Kato, "Method for Selecting a Data Imputation Model Based on Programming by Example for Data Analysts"
• Jarrod Carson, Kane Hollingsworth, Rituparna Datta, George Clark, and Aviv Segev, "A Hybrid Decision Tree-Neural Network (DT-NN) Model for Large-Scale Classification Problems"

Program Committee

• Subhash C. Bagui, University of West Florida
• Jian Chen, University of North Alabama
• Djellel Difallah, Wikimedia Foundation
• Jennifer Lavergne, McNeese State University
• Satya Katragadda, University of Louisiana at Lafayette
• Kaustubh Kaluskar, Shell
• Murali Pusala, AT&T