Nexans Autoelectric Tunisia
Tunisie

Subject 08: Prediction of Scrap Rate Using AI PFE

Quality EngineeringData Science / AIManufacturing Engineering

Publié il y a 14 jours

Stage
⏱️4-6 mois
💼Hybride
📅Expire dans environ 3 heures
Cohérence LinkedIn / CV vérifiée.

Description du poste

Overview

  • Department: Quality - Production - Engineering. Profile sought: Industrial/Manufacturing/Data student with focus on AI & process optimization.
  • Objective: identify and predict scrap rate variations across workstations/teams and propose operational settings to reduce scrap.

Tasks & Deliverables

  • Create a consolidated database including production data, operators, machine parameters, timestamps, and defect records; ensure data cleaning, labeling and time alignment.
  • Develop AI/ML models (classification/regression/time-series) to predict scrap risk based on production conditions and operator/machine contexts; produce model evaluation and validation reports.
  • Propose optimal machine settings or operating conditions derived from model insights; deliver concrete recommendations and implementation guidelines.

Required Skills & Tools

  • Manufacturing and quality control knowledge to interpret process parameters and defect modes.
  • Data analysis and AI/ML experience (Python or R), including preprocessing, feature engineering, model training and evaluation.
  • Familiarity with databases (SQL), data visualization/dashboard tools and basic experimental design for validating recommended settings.

Expected Outcomes & Impact

  • Quantifiable reduction in scrap rate through targeted adjustments and data-driven operating recommendations.
  • Improved understanding of hidden root causes of defects and operator/machine interactions contributing to scrap.
  • Deliverables: cleaned database, trained models, evaluation results, recommended parameter ranges, and a short implementation plan for the production team.

How to apply

  • Send your application to G-TN-StagePFE@autoelectric.com with the subject line specified below.
  • Include CV, a short motivation letter highlighting relevant projects (data/ML and/or manufacturing) and any sample code or reports if available.