Blind failure prediction for the most complex equipment

Maximizing profitability, improving performance, and differentiating themselves from the competition are today’s priorities for manufacturers. Amiral Technologies, a pioneer and expert in blind failure prediction, helps manufacturers get the most out of their critical assets by promoting the implementation of a strategy ranging from preventive to predictive and prescriptive maintenance.

DiagFit

Our failure prediction software monitors the health of equipment throughout its life

Combining a technological core based on incremental Machine Learning and an intelligent automated interface for business experts, DiagFit is a failure prediction software featuring numerous scientific inventions. This “no code” configurable software is used to monitor the health status of all types of instrumented equipment, whether they are concentrated in one point, geographically distributed or in motion. With DiagFit, deploying a predictive maintenance approach finally becomes possible and quick to implement.

Usability

Interpretable detections
By displaying health indicators for each sensor, in addition to the overall health indicator, decision making becomes more rational.
Designed for domain experts
An iterative approach to managing decisions in the field.
Incremental learning
Models can adapt to the evolving contexts encountered by the equipment, making them robust to operational changes.
No-Code
An interface designed entirely in no code to be used without development or data science skills.

Performance

High accuracy
DiagFit has a unique technological core, developed in conjunction with academic research, and produces accurate models (low FP and FN).
Frugal AI
DiagFit is very frugal in terms of processor power and data volume, which allows it to operate in embedded mode in particular.
Agnostic
DiagFit works with all types of equipment as long as they are equipped with sensors producing data in the form of industrial time series.
Fast model production
DiagFit is fast, thanks to the small amount of historical data required, the automated approach and the accuracy of the algorithmic core.

Customers

Use cases

Failure prediction on an anonymized ship's system

Using anonymized healthy data acquired over a year on the ship, DiagFit was used to create a unique model in hours that captures correlations between sensor data and produces a health status per sensor.

Partners

News & Events

Awardees from

FAQ

Frequently Asked Questions

The prediction of industrial equipment failures in blind mode is a term invented by Amiral Technologies to illustrate its inventions contained in its DiagFit software. “Blind mode” means that Amiral Technologies’ DiagFit software does not need to know the type of equipment it is monitoring, and does not need historical failure data to produce predictive models. This operation allows extremely fast implementation of the software.

More about blind mode

No, we are publishers of the DiagFit software. We do not provide sensors and we do not connect to sensors. Our software is fed with data from sensors already installed by the customer.

We act in three sectors: energy (renewables, electricity, nuclear, gas), transport (aerospace, automotive, rail, naval) and manufacturing (test benches, robotics, microelectronics).

See all use cases