Watchdog Agent - an infotronics-based prognostics approach for product performance degradation assessment and prediction

By Dragan Djurdjanovic, Jay H. Lee, Jun Ni. Advanced Engineering Informatics, 2003

302 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, Control and Systems Engineering, Industrial and Manufacturing Engineering

View Paper: https://www.semanticscholar.org/paper/8cbeb9c38fb492c72b76b0067939929d0b6b43ef

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Networks and Communications

In Control and Systems Engineering

In Industrial and Manufacturing Engineering

Citations in the corpus

A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data (2018, background): “An accurate detection is crucial to avoid serious ﬁnancial and business losses as it has been reported that 1 minute downtime of an automotive manufacturing plant may cost up to 20 , 000 US dollars (Djurdjanovic, Lee, and Ni 2003).”
Smart Agents in Industrial Cyber–Physical Systems (2016, methodology): “These analytical agents have been successfully implemented in several applications, such as monitoring and diagnosing air compressor equipment and machine tools components [27].”
Intelligent prognostics tools and e-maintenance (2006, background): “In addition, a model of the process or piece of equipment that is being considered, or specific knowledge available for the application can be used to aid the degradation process description, provided that such a model and/or such knowledge exists.”
A novel method for machine performance degradation assessment based on fixed cycle features test (2009, methodology): “Mixtures of Gaussians can be utilized to approximate an arbitrary distribution within an arbitrary accuracy [24].”
On condition based maintenance policy (2015, background): “[9] proposed the framework of watchdog agent for predictive condition-based maintenance by realizing multi-sensor assessment and prediction of machine or process performance.”
On the concept of e-maintenance: Review and current research (2008, methodology): “The algorithms include neural network-based, time-seriesbased, wavelet-based and hybrid joint time–frequency methods [49].”
A review of diagnostic and prognostic capabilities and best practices for manufacturing (2016, background): “Most product maintenance is either completely reactive or blindly preventative (Djurdjanovic et al. 2003).”