Energy disaggregation, essential for both industrial and residential energy management, offers detailed insights into energy usage patterns. In industrial settings, it helps identify inefficiencies and optimize energy usage, crucial for cost reduction. Similarly, in residential buildings, disaggregating energy consumption empowers consumers to conserve energy, optimize appliance usage, and reduce bills. It facilitates the integration of renewable energy sources, maximizing self-consumption and reducing reliance on the grid. The increasing demand for accurate energy disaggregation methods is driven by sustainability goals and regulatory requirements to reduce carbon emissions. Accurate disaggregation enables targeted interventions to minimize energy waste and greenhouse gas emissions, contributing to a more sustainable and efficient energy ecosystem. This work presents the results of an industrial forecasting algorithm to predict the disaggregated electricity and gas consumption of an oven in the food manufacturing industry located in Spain. Artificial intelligence techniques have been applied, in particular, neural networks. Promising results are achieved thanks to the metrics obtained. The coefficient of determination R2 shows values higher than 0.75, which, statistically speaking, specifies a good fitting.