Energy and logistics optimization

context

Our client offers a range of digital tools, for agricultural cooperatives, to facilitate and optimize the production, storage and sale of cereals.

In order to expand its offer, in a tense energy context, our client wishes to propose a tool for optimizing the electrical consumption of grain storage sites.

More specifically, grain storage silos are equipped with fans, which allow them to maintain the quality of the cereals by maintaining an adequate temperature inside the silos. These fans are particularly energy-intensive and can be completely ineffective if they are not used properly (for example if it is too hot outside). It therefore seems very important to be able to control and optimize the operating periods of the fans.

The objective of this project is to develop a tool to automatically detect when the fans are on at a grain storage site, based on a simple survey of the total consumption of the site.

A vast field of green cereals undulating under a clear sky with a small pile of hay in the distance.

mission

As part of this energy optimization project, OSE Engineering has developed a web service capable of automatically detecting the operating hours of fans at grain storage sites.

This service is integrated directly into the customer's application, making it possible to analyze electricity consumption in real time and to extract the relevant periods of activity for more precise and economical management.

Data collection

The algorithm is based solely on two types of data: the electrical power of the fans installed on the site, and the total consumption of the site (including fans and other equipment). This information is sufficient to identify global energy behavior without additional instrumentation.

Automatic detection

Thanks to advanced algorithmic processing, the service automatically — and instantly — identifies fan on and off ranges.
It isolates these signals from the consumption curve and returns the results in the form of precise schedules that can be used by the client application.

Web service integration

The algorithm is encapsulated in a web service that can be interfaced with the client's application.
The calculation requests are sent automatically, and the results (ignition times, operating times) are returned directly to the user in his dashboard.

Production of results

Deployed on more than a hundred storage sites, the service is now fully operational.
It allows cooperatives to reduce their electricity consumption, improve the energy management of silos and measure the gains obtained in a sustainable efficiency approach.

benefits

The energy optimization of storage sites is based on a detailed analysis of electrical consumption, where the proportion of fans is often difficult to isolate.

OSE met this challenge by developing an algorithm capable of automatically detecting their ignition periods based on the site's overall consumption records — a robust scientific approach that makes it possible to precisely identify energy-saving levers. This solution is based on four complementary axes:

Signal analysis and processing

Application of advanced techniques for processing the temporal power consumption signal (sampled every 10 minutes) in order to extract and recognize characteristic patterns.

Business expert rules

Integration of expert rules resulting from exchanges with business engineers, in order to refine the interpretation of data and improve the accuracy of the model.

Robustness and reliability of the results

The combination of signal processing and expert rules made it possible to obtain a high level of robustness, explainability and accuracy of the results, on a wide variety of sites and equipment configurations.

Assessment and validation

The performance of the model was evaluated by comparison with manual timestamp readings from the ventilation controllers, confirming the reliability of detection on several storage sites.

Energy and logistics optimization

In a context of energy tension, the project aims to optimize the electrical consumption of cereal storage sites, based on the modeling and analysis of real data to improve the performance and sustainability of the installations.

Data collection

Automatic detection

Web service integration

Production of results

ADVANCED ALGORITHMS FOR AUTOMATIC DETECTION RELIABLE AND EXPLAINABLE.

The integration of signal processing methods and expert rules ensures accurate and interpretable detection of ignition times. Do you have an energy optimization project?

Signal analysis and processing

Business expert rules

Robustness and reliability of the results

Assessment and validation

a single conversation can spark Innovation