DiagFit
Published by
Amiral Technologies
Overview
A unique innovation in automatic feature generation for time series
DiagFit is a failure prediction software for IIoT-enabled equipment. Our technology was born in the labs of the French National Research Centre (CNRS).
It combines Artificial Intelligence with principles of automation and control theory to bring unique solutions for processing of Industrial Time Series.
How does it work?
Step1 : Transform IIoT data generated by the industrial equipment (time series) into discrete features.
Step2 : Inject these features into the Machine Learning algorithm to perform the learning and evaluate model performance before putting it into production.
A unique innovation in automatic feature generation for time series
DiagFit is a failure prediction software for IIoT-enabled equipment. Our technology was born in the labs of the French National Research Centre (CNRS). It combines Artificial Intelligence with principles of automation and control theory to bring unique solutions for processing of Industrial Time Series.
How does it work?Step1 : Transform IIoT data generated by the industrial equipment (time series) into discrete features.
Step2 : Inject these features into the Machine Learning algorithm to perform the learning and evaluate model performance before putting it into production.
Benefits
Address the lack of historical dataIndustry suffers from lack of historical data of defects. DiagFit addresses this issue/shortcoming with the accuracy of DiagFit’s health indicators. Unsupervised learning allows training the algorithm during normal operations to build the “good behaviour space” and detect deviation with unprecedented precision levels.
Maximize prediction performanceWhether it is the defects detection rate or the false alerts rate, DiagFit allows reaching unprecedented precision levels. False alerts rate is minimized thanks to the accuracy of DiagFit’s health indicators that allow to build voting mechanisms reducing the false alerts rate.
Reduce time to build predictive modelsThis criteria is of particular importance in multiple domains, for example in Aeronautics, when a very large number of models needs to be designed to cover numerous equipments, systems and subsystems on different aircrafts (potentially hundreds of models per aircraft version).
Address complex problems for critical equipmentThanks to the extraction of state of health indicators, DiagFit allows detecting weak and transitory signals and address finer correlation challenges between variables.
Address the lack of historical dataIndustry suffers from lack of historical data of defects. DiagFit addresses this issue/shortcoming with the accuracy of DiagFit’s health indicators. Unsupervised learning allows training the algorithm during normal operations to build the “good behaviour space” and detect deviation with unprecedented precision levels.
Maximize prediction performanceWhether it is the defects detection rate or the false alerts rate, DiagFit allows reaching unprecedented precision levels. False alerts rate is minimized thanks to the accuracy of DiagFit’s health indicators that allow to build voting mechanisms reducing the false alerts rate.
Reduce time to build predictive modelsThis criteria is of particular importance in multiple domains, for example in Aeronautics, when a very large number of models needs to be designed to cover numerous equipments, systems and subsystems on different aircrafts (potentially hundreds of models per aircraft version).
Address complex problems for critical equipmentThanks to the extraction of state of health indicators, DiagFit allows detecting weak and transitory signals and address finer correlation challenges between variables.
Product Attributes
Solutions for
Segment
Schneider Electric Certification
Domain
Solutions for
Segment
Schneider Electric Certification
Domain
Get Resources and Start FREE Trials
Easy Product Activation with Your Account
Products Saved to Personal Digital Library
Register Now
Already have an account?
Log In