Non-intrusive monitoring methods of energy consumption through machine learning techniques

IFP Energies nouvelles (IFPEN) offers a PhD opportunity in the field of Non-Intrusive Load Monitoring (NILM) applied to industrial environments. The project aims to develop an innovative method using Convolutional Neural Networks (CNN) to enhance the accuracy of device energy signature detection. NILM analyzes the overall energy consumption of a building and breaks it down into appliance-specific consumption without individual sensors. While current methods like combinatorial optimization and pattern recognition have proven effective in residential contexts, their application to industrial settings remains underexplored. This thesis seeks to fill this gap by applying CNNs to real industrial data provided by an industry partner and using public databases for comparative evaluation. 
The PhD candidate will join a multidisciplinary team (process and data scientist) and inter-laboratories IFPEN (Dr. Julien Gornay, Dr. Denis Guillaume, Eric Volland, Dr. Aurélie Chataignon and Julien Peyrelon) and G-SCOP (thesis director Dr. Eric Gascard and Zineb Simeu-Abazi Prof. Emeritus). IFPEN also offers a competitive salary policy and encourages participation in seminars and training dedicated to PhD students. 
We are looking for a candidate with a degree in mathematics, computer science, or chemical engineering, with skills in deep learning and signal processing. An interest in energy optimization is a plus. To apply, please submit your CV and a cover letter via our online portal. Join us to contribute to innovation in industrial energy management!

Keywords: NILM, decarbonization of the industry, energy efficiency, CNN, Machine Learning

• Academic supervisor    Dr Eric GASCARD, Laboratoire G-SCOP, ORCID : 0000-0003-4332-0752
• Doctoral School    Ecole Doctorale Electronique, Electrotechnique, Automatique, Traitement du Signal (ED EEATS), Université Grenoble Alpes
• IFPEN supervisor    Dr Julien GORNAY, ORCID : 0009-0000-7772-5446
• PhD location    IFPEN, Lyon, France  
• Duration and start date    3 years, starting in the fourth quarter 2025 (Novembre 3)
• Employer    IFPEN
• Funding    ANR (PEPR SPLEEN)
• Academic requirements    University master’s degree in Chemical engineering or Process engineering    
• Language requirements    French level C1 and English level B2 (CEFR)    
• Other requirements    Interested in computer science and machine learning

To apply, please send your cover letter and CV to the IFPEN supervisor indicated here below.