How better control the quality of your products?

Analyze your mass of data to improve product quality control

Whether you are an actor in the industry, a research laboratory, or even a technical center, you certainly have data from different sources (physicochemical measurements, agronomic parameters, sensory profiles, process parameters, spectroscopic measurements, etc. ..).

You wish to

Develop

accurate and robust models for predicting quality

model update and mainteannce

Update

existing models using new samples

data fusion

Merge

information from various sources and select the most relevant

methodes d'analyses de données pour la prédiction de critères qualité

You want to correlate them with quality criteria to build prediction models, in order to quickly characterize your products or optimize your processes.

But you don’t know how to combine all this information…

There are very powerful data fusion methods to integrate all the information acquired on your products and even if this information comes from different sources (blocks). Chemometrics and Machine Learning, calibration or multi-block fusion algorithms allow you to define which parameters are the most relevant in order to best predict your quality criteria.

Thanks to our knowledge in Chemometrics and Machine Learning, we help you in the development and implementation of prediction tools that respond to your quality issues.

Predition de critères qualité
  • Data normalization
  • Multivariate calibration (PLS, SVMR, ANN, regression trees (RF),…)
  • Classification (PLS-DA, SIMCA, SVM, ANN, decision trees (RF, XGBoost),…)
  • Validation and model robustness
  • Selection of the most discriminating or informative sensors or parameters
  • Multi-sensor fusion using multi-block methods
  • Multi-way methods for 3D data
  • Model update

Software implementation

We develop your calibrations with all the Chemometrics and Machine Learning software on the market: Unscrambler®, SOLO® or PLS_Toolbox® in the MATLAB® environment, SIMCA®, etc… , but also free software (R, Python…).

Our expertise for the analysis of your data

With more than 15 years of experience in data analysis (Chemometrics and Machine Learning), the experts of our teams support you at every stage of your projects.

They talk about us


« With Ondalys, we work in confidence. ! »

Pierre COSTET, Sensory Expertise Manager, Valrhona

  • Thomas Giordanengo

    Ondalys supported us during our innovative project for the development of an optical sensor for wood material qualification during its transformation in Radoux factory. Methodology, technical skills, creativity - all of which have enabled us to progress efficiently, and to develop robust tools for our applications: the OakScan®.

    Thomas Giordanengo
    R&D Engineer - Tonnellerie Radoux

Examples of concrete applications


Scientific publications
Valrhona 2019
User case
Pharmaceutical industry
Scientific publicatoin
Tonnellerie Radoux 2008

Register to
receive Ondalys newsletter