Auto-Tuning [Cognitive]

Auto-tuning releases the full capacity of machine learning systems, enabling smart self-configuration systems, increasing equipment utilization, improving energy efficiency and lowering environmental footprint.

Edge Opportunities
Ekkono’s SDK enables autonomous performance optimization, on the edge in real-time. Use a machine learning model to explain complex behavior of a machinery and add an optimizer to find parameters for best possible performance. Apply parameters to the machinery and let the tuning start all over to continuously run the machinery at optimal performance. When letting the embedded system auto-tune itself the operational safety is of greatest importance. To guarantee a safe operation the auto-tuning result is constantly evaluated to ensure that parameter values are within safety margins.

Predictive models can be trained with batch or incremental learning. Batch learning is carried out offline on already collected data. Data that needs to be collected in a lab or in live operation, and needs to include a variety of operating conditions for the device. In many cases, the data requirements for batch learning are prohibitive, which is why our focus lies on incremental learning technologies that eliminate the need for historical data. Instead of collecting data up-front, actual learning is performed on data collected in real-time on the device. Training on the device makes it possible for the model to learn the unique conditions for each device, making the model specifically tailored to the device on which it resides.

Problem
Proper tuning of a machine with complex dependencies requires a complex model. It may be unfeasible to test all possible settings and conditions before deployment and dependencies may change over time.

Solution
Continuously train an ML model to predict target values based on operational parameters and ambient factors. Search for the best setting using the model to evaluate scenarios and tune the machine accordingly.

Application
Let the ML based tuner operate the machinery within current safety systems to optimize performance.

Related content

More Use Cases

Virtual Sensor [Current State]

Virtual Sensor [Current State]

Physical sensors could be expensive, prone to fail or to drift. With the Ekkono SDK, you can create a virtual sensor based on related physical sensors. The virtual sensor can then replace a physical sensor, provide support on sensor failure or act as a reference when...

Health Monitoring [Current State]

Health Monitoring [Current State]

Health monitoring provides insights about system health beyond raw sensor values, and helps you prevent severe failures and unplanned production stops by exposing the true health of your machine. When using incremental learning, the need of historic data is replaced...

Predictive Alarming [Predictive]

Predictive Alarming [Predictive]

Predictive alarming lets you apply alarm levels on future sensor values, enabling the possibility to act in advance. Alarms on predicted values gives valuable input to operation teams, preventing potential problems from happening, thereby increasing uptime and...