Machine learning-based particle-laden flow field characterization

1. A method, carried out using an optical data acquisition arrangement, for rendering a characteristic for a set of particles measured while passing through a measurement volume of a particle measurement system including a machine learning stage, the method comprising:

acquiring a raw particle data for the set particles passing through the measurement volume of the particle measurement system, where the raw particle data comprises a set of raw particle records and each of one of the raw particle records includes a particle data content;

preconditioning the particle data content of the set of raw particle records to render a conditioned input data; and

processing, by the machine learning stage, the conditioned input data to render an output characteristic parameter value for the set of particles,

wherein, during the acquiring, the raw particle data is acquired using the optical data acquisition arrangement comprising:

an optical source comprising a light scattered off particles;

a sensor; and

a set of optical components that relay the light from the optical source to the sensor such that there is a functional relationship between a position on the sensor and a scattering angle of light from the optical source,

wherein the set of optical components comprise at least one component taken from the group consisting of:

an aperture whose geometric relationship with the rest of the optical components and the sensor sets the functional relationship; and

a series of channels that only allow light of a specific angle to reach any part of the sensor.

2. The method of claim 1 , wherein the machine learning stage comprises an artificial neural network comprising a topology and a set of weights.

3. The method of claim 2 , further comprising setting values for ones of the set of weights.

4. The method of claim 3 , further comprising changing the topology.

5. The method of claim 1 , wherein the processing, by the machine learning stage, further comprises rendering a confidence factor for the output characteristic parameter.

6. The method of claim 1 , wherein the processing, by the machine learning stage, further comprises rendering a numeric physical description.

7. The method of claim 1 , wherein the particle measurement is an optical measurement.

8. A particle measurement system that renders a characteristic for a set of particles measured while passing through a measurement volume, the system comprising:

a source that generates a particle-laden field containing the set of particles;

a sensor that generates a raw particle data corresponding to the set particles passing through the measurement volume of the particle measurement system, where the raw particle data comprises a set of raw particle records and each of one of the raw particle records includes a particle data content;

a preconditioning stage configured to carry out a preconditioning operation on the particle data content of the set of raw particle records to render a conditioned input data; and

a machine learning stage configured to process the conditioned input data to render an output characteristic parameter value for the set of particles,

wherein the raw particle data is generated by using an optical data acquisition arrangement comprising:

an optical source comprising a light scattered off particles;

the sensor; and

a set of optical components that relay the light from the optical source to the sensor such that there is a functional relationship between a position on the sensor and a scattering angle of light from the optical source,

wherein the set of optical components comprise at least one component taken from the group consisting of:

an aperture whose geometric relationship with the rest of the optical components and the sensor sets the functional relationship; and

a series of channels that only allow light of a specific angle to reach any part of the sensor.

9. The system of claim 8 wherein the machine learning stage comprises an artificial neural network comprising a topology and a set of weights.

10. The system of claim 9 , wherein the machine learning stage supports setting values for ones of the set of weights.

11. The system of claim 10 , wherein the machine learning stage supports changing the topology.

12. The system of claim 8 , wherein the machine learning stage is configured to render a confidence factor for the output characteristic parameter.

13. The system of claim 8 , wherein the processing, by the machine learning stage, further comprises rendering a numeric physical description.

14. The system of claim 8 , wherein the particle measurement is an optical measurement.

15. An optical data acquisition arrangement comprising:

an optical source comprising a light scattered off particles;

a sensor; and

a set of optical components that relay the light from the optical source to the sensor such that there is a functional relationship between a position on the sensor and a scattering angle of light from the optical source,

wherein the first optical component is an aperture whose geometric relationship with the rest of the optical components and the sensor sets the functional relationship.

16. An optical data acquisition arrangement comprising:

an optical source comprising a light scattered off particles;

a sensor; and

a set of optical components that relay the light from the optical source to the sensor such that there is a functional relationship between a position on the sensor and a scattering angle of light from the optical source,

wherein the optical components are a series of channels that only allow light of a specific angle to reach any part of the detector.