Understanding the measurement principle helps users select a suitable method and interpret its results. This section explains the physical and computational approaches behind our technologies.

Droplets and particles generate light-scattering signals as they pass through an optical measurement region. Classical TSTOF evaluation uses timing information and the measurement geometry to determine properties such as size and velocity.

Machine-learning models establish relationships between measured signals and reference information. Their performance depends on the measurement configuration, training data, and conditions under which they are applied.

ParticleTensorAI investigates how retaining complex light-scattering data can support further analysis of particles, materials, and dynamic processes.

SprayConeAI uses images to evaluate spray geometry and spray patterns. Image quality, camera position, and calibration influence how the results should be interpreted.

Learn more about our measurement technologies.