CLH: how to predict demand, maintenance and leak detection with AI

CLH, a leader in fuel transportation and with more than 53 storage facilities worldwide, trusted Plain Concepts to develop three innovation projects in the field of Industry 4.0using Artificial Intelligence and the Internet of Things (IoT), high-value technological services and great potential for cost savings.

Artificial Intelligence
Machine Learning, Databricks, Vision Computer, IoT Edge
The proofs of concept developed to show that thanks to the use of Artificial Intelligence we can predict the monthly and daily demand for fuel achieving more accurate forecasts, thus improving efficiency and timing in supply logistics.
By applying predictive maintenance techniques, we are able to forecast anomalies more effectively and thus anticipate possible failures in transmission pumps. And finally, computer vision with continuous real-time checking, allows us to automatically detect leaks reliably and avoid false alarms.


Improving existing fuel demand forecasts using techniques such as data analysis and engineering and Deep Learning, and integrate them with the company's current tools. Planning a fully automated data flow and tasks, in which predictions of possible failures are updated every day. And developing a Deep Learning model capable of recognizing facility leaks and adapting to changing environmental conditions.
planta de manufacturing


Specific models were obtained for each station on a daily and monthly basis with very precise estimates, which will be scalable and adaptable in the future, to facilitate decision-making in logistics and personnel.
Thanks to this predictive maintenance we can save time and costs and avoid the negative impact of potential unplanned downtimes. In addition, real-time leak detection and alarm will enable security personnel to react quickly and manage potential incidents in the most appropriate way.


By developing and using reliable and affordable solutions and infrastructures such as video surveillance or Azure IoT services, we can generate alerts more efficiently and avoid potential failures.
Choosing a Cloud ecosystem like Azure, also helped us both to integrate Artificial Intelligence functionalities and to create fully scalable and automated workflows.