Manuscript Topics

The advancements of Industry 4.0 and autonomous systems in recent years have led to an increase of research interest in the field of fault diagnosis. Using advanced theories and algorithms, researchers seek to detect, isolate, and reconstruct faults in various industries involving automation to enhance overall performance, improve production yield, better predictive maintenance planning, improve safety and reliability, as well as to save cost.

While most established fault diagnosis schemes and algorithms are fundamentally model-based techniques developed using mathematical models of the systems, data-driven techniques using artificial intelligence and machine learning methods have also gained much popularity lately. No matter the method used, mathematics, including statistics and probability theories play critical roles in the design and development of the fault diagnosis schemes.

This Special Issue aims to bring together novel research methodologies using model-based techniques, data-driven methods, or a hybrid of both for fault diagnosis. Contributions of research topics including, but not limited to the following are welcome:
 • Fault detection
• Fault isolation
• Fault reconstruction
• Fault diagnosis
• Fault tolerant control
• Predictive maintenance
• Sliding mode
• Model-based design
• Data-driven methods
• Hybrid of model-based and data-driven techniques

Instruction for Authors
http://www.aimspress.com/math/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/