DiagFit value proposition is based on the four key competitive elements:

 1. Address the lack of historical failure data 

Industry suffers from lack of historical failure data. 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.

 2. Maximize prediction performance 

Whether 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.

 3. Address complex problems for critical equipment

Thanks to the extraction of State of Health indicators, DiagFit allows detecting weak and transitory signals and to address fine correlation issues between variables. 

 4. Shorten time to build predictive models

This criterion is particularly of importance in aeronautics for example where 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). 

Predictive Maintenance Model Process

Automatic Features Generation


DiagFit : A Unique Innovation in Automatic Feature Generation for Time Series

DiagFit automatically generates discriminant features out of time series
  • Whatever the nature of the time signal input (electric signal, temperature, humidity, vibration, pressure, …or a combination of these signals)
  • Without the need for a subject matter expert at this stage
  • DiagFit features:
    • Are infinitely rich and discriminant
    • Lead to more performant predictive models with Machine Learning algorithms


Without DiagFit:

discriminant features

With DiagFit:

discriminant features

Use cases

Remaining Useful Life Prediction 

Generic Model and its application for Turbofans

Defects and Aging Prediction 

Generic Model and its application for Railway Point Systems and Industrial Printers 

Defects and Aging Prediction

Generic Model and its application for  Wind Turbines and Induction Motors

Our Integration Options

  • In your IoT (standard or proprietary) platform
  • Hosted on Amiral Technologies' cloud
  • Embedded in the equipment
Close Menu