Amiral Technologies is proud to be one of the winners of the competition: https://cache.media.enseignementsup-recherche.gouv.fr/file/Innovation/41/5/palmares_concours_i-nov-v6_1415415.pdf Waves 5 and 6 of the i-Nov Competition: 131 winners Co-piloted
DiagFit fills the gap of the predictive maintenance workflow: the processing of IIoT data to provide actionable predictions.
It contains algorithms consisting in an automatic feature generation for time series, these are mathematical properties that describe time-dependent data series originating from an equipment which behavior is governed by laws, and that are captured by physical sensors.
These properties are extremely rich to the point that they significantly increase the odds of finding solutions to problems such as the detection of signs of failure, ageing or nearing end-of-life for an equipment.
The automatic feature generation for time series (or properties/indicators) is similar to having a large number of photographs of the time series. These photographs, if obtained on a sufficiently representative number of healthy equipment data, allow to shape a robust and rich view of what normality looks like. This allows detection of anomalies with quite a high precision and a low rate of false alarms. These photographs represent the fingerprints of normality. It is the abundance of discriminant properties that makes the identification so reliable.
This is what allows Amiral Technologies to develop a failure detection solution without needing historical failure data. The industry (luckily) does not have so many occurrences of failures to learn from.
DiagFit is powered by scientific inventions
- Blind: operates without historical failure data
- Fully automated: no data science skills required
- Sensor-agnostic and equipment-agnostic
- Accurate: reduced false alerts rate
- Quick: models built in hours/days versus weeks/months