FIELD: measuring equipment.
SUBSTANCE: system for granulometric analysis of liquid dispersion media contains a light source, a camera and a neural network block. The test material is transferred from the process tank 1 to the flow measuring chamber 3, where a probe collimated light beam is introduced. The pattern of the radiation scattered by the medium is photographed by a digital camera 10. In the feature sampling module 11, the necessary data for neural network data conversion is selected in the neural network block 12. The training vector is fed to the block 12 from the objective analysis unit 14 based on the sedimentometric or microscopic method of granulometric analysis. The neural network block is trained at the initial graduation, and also in cases when the light scattering pattern differs greatly from the already known ones. The described system is able to perform express analysis in flowing conditions and has increased metrological reliability due to periodic calibration and additional training of the system during operation.
EFFECT: increased accuracy and metrological reliability of the system for the express determination of grain-size composition due to periodic automatic calibration and additional training of the system during operation.
1 dwg
Title | Year | Author | Number |
---|---|---|---|
METHOD FOR DETERMINING THE DROP SIZE OF AN EMULSION | 2021 |
|
RU2783468C1 |
SYSTEM FOR ADAPTIVE NEURON NETWORK DETECTION OF GRANULE-METRIC COMPOSITION OF PARTICLES OF PELLET OR GRANULATED MATERIAL | 2004 |
|
RU2300753C2 |
SYSTEM FOR ANALYZING DATA READ BY CAMERA TRAPS FOR OPERATIONAL REMOTE MONITORING OF NATURAL AREAS | 2022 |
|
RU2799114C1 |
HARDWARE-SOFTWARE COMPLEX DESIGNED FOR TRAINING AND (OR) RE-TRAINING OF PROCESSING ALGORITHMS FOR AERIAL PHOTOGRAPHS IN VISIBLE AND FAR INFRARED BAND FOR DETECTION, LOCALIZATION AND CLASSIFICATION OF BUILDINGS OUTSIDE OF LOCALITIES | 2020 |
|
RU2747214C1 |
HARDWARE-SOFTWARE COMPLEX DESIGNED FOR TRAINING AND (OR) RE-TRAINING OF PROCESSING ALGORITHMS FOR AERIAL PHOTOGRAPHS OF THE TERRITORY FOR DETECTION, LOCALIZATION AND CLASSIFICATION UP TO TYPE OF AVIATION AND GROUND EQUIPMENT | 2020 |
|
RU2747044C1 |
METHOD FOR DETECTING AND CLASSIFYING NAVAL TARGETS BASED ON NEURAL NETWORK TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE ELEMENTS | 2021 |
|
RU2780606C1 |
METHOD FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763125C1 |
METHOD AND DEVICE FOR MEASURING SPECTRAL AND INTEGRAL DENSITY OF NEUTRON STREAM | 2008 |
|
RU2390800C2 |
SYSTEM FOR OPERATIONAL IDENTIFICATION OF MARINE TARGETS BY THEIR INFORMATION FIELDS BASED ON NEURO-FUZZY MODELS | 2021 |
|
RU2763384C1 |
SYSTEM FOR DETECTING AND CLASSIFYING NAVAL TARGETS BASED ON NEURAL NETWORK TECHNOLOGIES AND ARTIFICIAL INTELLIGENCE ELEMENTS | 2021 |
|
RU2780607C1 |
Authors
Dates
2017-07-26—Published
2016-09-26—Filed