Termosun, Pervasive and Imae join forces in an R&D project for biomass

Termosun , Pervasive and Imae, in collaboration with Schneider, are joining their resources and knowledge in a new R&D project for the optimization of the combustion of biomass and related by-products in industrial boilers through the methodology of Machine Learning and Big Data.

The significant increase in fossil gas prices, as well as the rise in the price of carbon credits, are pushing a large number of industries in Spain towards the conversion of their thermal plants, replacing traditional and obsolete gas boilers with boilers that use renewable biofuels, such as forest biomass and agro-industrial by-products.

Therefore, there is a growing demand for biomass boilers in the food, automotive, chemical, and other industries . However, at Termosun we observe that industrial operators and maintenance personnel lack sufficient skills for boiler management, ensuring maximum energy efficiency and minimal pollutant emissions.

The operation and maintenance of biomass boilers is more complex than the simple operation of gas boilers , and this technological leap must be supported by advanced control technologies, avoiding leaving the boiler's efficiency to the operator's discretion in many cases.

On the other hand, they ensure that the useful life of the boilers is not reduced or even suffer defects that cause emissions into the atmosphere or overconsumption of biomass, making it necessary to work with advanced technologies for data acquisition and control of this equipment to guarantee energy conservation and environmental protection.

The solution under study being developed by Termosun in collaboration with Pervasive and Imae, called “3BD – Biomass Boiler Big Data”, aims to offer the biomass boiler market a solution to guarantee functional performance in terms of energy efficiency, impact reduction and reduction of operating and maintenance costs.

Under the concept of a toolbox, this project is conceived as a combination of tools that integrate into the system at different layers of scalability and licensing, the basic tools being:

• Continuous measurement of the parameters that occur in the different physical-chemical states during the combustion process,
• Image capture of combustion grill inside oven
• Set of oxygen and temperature probes in exhaust gas line
• Massive data acquisition and interpretation platform
• Digital training model and data affinity and self-learning
• Operating parameter correction interface

As shown in the following image, these tools are arranged in different layers, starting with layer 0, also known as the field hardware layer, and progressively scaling the information to higher layers of acquisition, interpretation, iteration and alteration of operating parameters to finally culminate with the report to the technical support service.

The 3BD (Biomass Boiler Big Data) project was created to improve current algorithm models through Machine Learning treatments, a discipline within the field of Artificial Intelligence that, through the creation of twins and algorithms, allows the identification of patterns in massive Big Data data to develop predictions that allow the digitization of boiler operation for optimal combustion, performance, and minimal emissions.