Ing. /MSc. Internship Proposal in Computer Science à Pau : Data-Driven Anomaly Prediction for Reducing Energy Consumption in the Low-Carbon Aircraft Production Chain
CESIJoining LINEACT at CESI for a research internship would be a fantastic opportunity to contribute to innovative projects while deepening my skills in a cutting-edge environment focused in Computer Science
Abstract
The production chain of low-carbon aircraft relies on high-precision industrial equipment to manufacture and assemble the various aircraft components. The proper functioning of these production machines is essential to ensure efficient manufacturing, minimize downtime, and optimize energy consumption. However, unexpected anomalies and failures can lead to costly disruptions and excessive energy use. This internship focuses on developing an anomaly prediction system for aircraft parts production machines, leveraging big data and artificial intelligence (AI). The goal is to analyze data from industrial sensors to detect weak signals indicating potential malfunctions, predict failures, and optimize maintenance strategies.
Keywords: Failure prediction, Predictive maintenance, Machine learning, Optimization
Research Work
Scientific Fields:
Machine Learning / Deep Learning, Big Data analysis and anomaly detection, predictive maintenance.
Work Program/Objectives:
1. Development of a data collection and integration platform to aggregate real-time sensor data from production machines, ensuring a comprehensive view of operational parameters.
2. Design of machine learning-based predictive maintenance models to anticipate failures, optimize maintenance schedules, and assess their impact on production efficiency and energy consumption.
3. Development of reliability and accuracy metrics to evaluate the effectiveness of predictive models in minimizing downtime and improving operational performance.
4. Deployment and validation of predictive strategies in real-world manufacturing conditions to test model robustness, and enhance energy efficiency.
Prior works in the laboratory
As part of the LINEACT laboratory, several research initiatives have been conducted in the field of predictive maintenance with a particular focus on applying artificial intelligence and metaheuristics to optimize the management of complex systems. Marwa DAAJI proposed an innovative approach to failure prediction in cyber-physical systems, notably for wind turbines, by framing the problem as a multi-objective optimization task and applying evolutionary algorithms (Daaji et al., 2023). Her research demonstrated the effectiveness of her methods, validated with real-world data, to anticipate defects and improve system reliability. On the other hand, Ghita BENCHEIKH developed a multi-agent system for the joint scheduling of production tasks and predictive maintenance, optimizing resource usage while considering the health status of machines (Bencheikh, 2022; Bencheikh & Bettayeb, 2024). She also designed failure prediction models for industrial machines using machine learning techniques, enabling proactive maintenance and reducing unexpected breakdowns (Maataoui et al., 2023).
Expected scientific/technical production
- A comprehensive review of existing predictive maintenance methods, specifically applied to manufacturing machines used in aircraft parts production.
- A cleaned and well-organized dataset of sensor data from production machines, ready for machine learning modeling to predict failures and optimize maintenance.
- A machine learning model to predict potential failures, with a detailed explanation of the methodology and techniques used.
- An evaluation of the predictive model’s performance, including key metrics and analysis of its ability to reduce downtime and improve energy efficiency in production.
- A user-friendly dashboard to visualize machine performance, real-time anomalies, and predictive maintenance insights for better decision-making in the production environment.
Context
Lab presentation
CESI LINEACT (UR 7527), Laboratory for Digital Innovation for Businesses and Learning to Support the Competitiveness of Territories, anticipates and accompanies the technological mutations of sectors and services related to industry and construction. The historical proximity of CESI with companies is a determining element for our research activities. It has led us to focus our efforts on applied research close to companies and in partnership with them. A human-centered approach coupled with the use of technologies, as well as territorial networking and links with training, have enabled the construction of cross-cutting research; it puts humans, their needs and their uses, at the center of its issues and addresses the technological angle through these contributions.
Its research is organized according to two interdisciplinary scientific teams and several application areas.
- Team 1 "Learning and Innovating" mainly concerns Cognitive Sciences, Social Sciences and Management Sciences, Training Techniques and those of Innovation. The main scientific objectives are the understanding of the effects of the environment, and more particularly of situations instrumented by technical objects (platforms, prototyping workshops, immersive systems...) on learning, creativity and innovation processes.
- Team 2 "Engineering and Digital Tools" mainly concerns Digital Sciences and Engineering. The main scientific objectives focus on modeling, simulation, optimization and data analysis of cyber physical systems. Research work also focuses on decision support tools and on the study of human-system interactions in particular through digital twins coupled with virtual or augmented environments.
These two teams develop and cross their research in application areas such as
- Industry 5.0,
- Construction 4.0 and Sustainable City,
- Digital Services.
Areas supported by research platforms, mainly that in Rouen dedicated to Factory 5.0 and those in Nanterre dedicated to Factory 5.0 and Construction 4.0.
Links to the research axes of the research team involved
This internship topic falls within the ‘Management and Decision’ and ‘Predictive Maintenance’ focus areas of Team 2, ‘Engineering and Digital Tools’.
Presentation of C2A project
Supported by state investment as part of the France 2030 Plan, Campus Aero Adour (C2A) is a project to support the digital and environmental transition of the aeronautics industry in the Adour territory. As a laureate of the "AMI Compétences et Métiers d’Avenir" call for projects under the ’Producing Low-Carbon Aircraft’ strand, C2A will benefit from State support through the France 2030 initiative over five years.
Skills
The candidate should be a Master's student or hold an equivalent degree in Computer Science or Applied Mathematics. They should have knowledge and experience in several of the following areas:
1. Data Science & AI Skills
- Machine Learning / Deep Learning : Classification models, anomaly detection (SVM, Random Forest, LSTM, Autoencoders, etc.).
- Big Data Processing: Handling and analyzing large datasets from sensors.
- Programming : Python (NumPy, Pandas, Scikit-learn, TensorFlow, PyTorch), SQL for data analysis.
2. Tools & Environments
- Data Visualization: Power BI, Tableau, Matplotlib, Seaborn.
3. Soft Skills
- Strong analytical and problem-solving abilities.
- Capacity to interpret data and effectively communicate results.
Modalities
File review and interview.
A cover letter, a resume, transcripts of M1 and the current year of M2 (or equivalent level), BSc/MSc/Ing. certificates and at least two recommendation letters. Applications will be processed as they arrive, early application is highly encouraged.
Application should include:
- Detailed Curriculum Vitae of the candidate. In case of a break in academic studies, please provide an explanation;
- A motivation letter;
- Transcripts of MASTER I and/or II and/or corresponding grade reports;
- BSc/MSc/Ing. certificates;
- Two recommendation letters.
Please submit all documents in a PDF FIRSTNAME_LASTNAME.
Internship Organization
• Funding: France 2030.
• Workplace: CESI LINEACT, Campus PAU, 8 rue des Frères d’Orbigny 64000 Pau, France.
• Start Date: 01/04/2025.
• Duration: 5/6 months.
Supervisor(s):
- BENCHEIKH Ghita, Associate Professor.
- DAAJI Marwa, Associate Professor.
Acknowledgements:
This work is conducted as part of Campus Aero Adour (C2A) project funded by the government under the France 2030 Plan.
References:
- Daaji, M., Ouni, A., Gammoudi, M. M., Bouktif, S., & Mkaouer, M. W. (2023). BPEL process defects prediction using multi-objective evolutionary search. Journal of Systems and Software, 204, 111767. https://www.sciencedirect.com/science/article/pii/S0164121223001620
- Bencheikh, G. (2022). An approach for joint scheduling of production and predictive maintenance activities. Journal of Manufacturing Systems, 15.
- Bencheikh, G., & Bettayeb, B. (2024). Simultaneous Scheduling of Production and Maintenance in a Flexible Job-Shop Workshop. In Y. Benadada, F.-Z. Mhada, J. Boukachour, F. Ouzayd, & A. El Hilali Alaoui (Eds.), Proceeding of the 7th International Conference on Logistics Operations Management, GOL’24 (Vol. 1105, pp. 283–292). Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-68634-4_26
- Maataoui, S., Bencheikh, G., & Bencheikh, G. (2023). Predictive maintenance in the industrial sector: A CRISP-DM approach for developing accurate machine failure prediction models. 2023 Fifth International Conference on Advances in Computational Tools for Engineering Applications (ACTEA), 223–227. https://ieeexplore.ieee.org/abstract/document/10193983/