3D Object Recognition for High-Aspect-Ratio Crystal Measurement

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional methods for determining particle size distribution of high-aspect-ratio crystals, such as laser diffraction and laser backscattering, are limited by assumptions of spherical particles and are inadequate for in-situ measurements, especially in high solids concentrations, leading to inaccurate results and the need for invasive sampling.

Innovation Solution

The development of systems and methods that can analyze low-quality images of crystallization processes to segment and identify objects with known spatial relationships, allowing for the determination of three-dimensional particle size and shape information without requiring well-controlled environmental parameters, using techniques like Burns direction analysis and viewpoint-invariant line groups.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If laser diffraction is used to determine particle size distribution, then measurement can be performed, but the results are inaccurate for high-aspect-ratio crystals due to spherical particle assumptions

Engineering Contradiction:

Improveparticle size distribution accuracyVSAvoidapplicability to non-spherical particles

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent segments the crystal population into different size classes and aspect ratio categories, analyzing each segment separately with appropriate geometric assumptions. This allows accurate measurement of high-aspect-ratio crystals by treating them differently from spherical particles, resolving the contradiction between measurement precision and adaptability.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The invention changes the geometric parameters used in analysis from spherical assumptions to parameters that account for high-aspect-ratio geometry. By modifying the mathematical models to include aspect ratio as a variable parameter, the system achieves accurate measurement of non-spherical particles while maintaining the laser diffraction technique.

Inventive Principle:

Principle #35Parameter changes

2Productivity

If laser diffraction is used for in-situ measurement, then real-time monitoring is possible, but insufficient light passes through high solids concentration samples

Engineering Contradiction:

Improvereal-time process monitoring capabilityVSAvoidlight transmission through sample

Core Design Contradiction:

ProductivityVSIllumination intensity

Solution Approach 1:

The patent transitions from transmission-based measurement to reflection-based measurement, adding a new dimensional approach to the problem. By measuring light reflected from the crystal surfaces rather than light transmitted through the sample, the system enables real-time monitoring of high solids concentration slurries without being limited by light absorption.

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

3Measurement precision

If laser backscattering is used to measure chord length distribution, then in-situ measurement is possible, but assumptions about crystal geometry reduce measurement completeness

Engineering Contradiction:

Improvechord length distribution accuracyVSAvoidhandling of variable crystal geometries

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The invention introduces dynamic adaptation of geometric assumptions based on the actual crystal population being measured. Rather than fixing the aspect ratio assumption, the system dynamically adjusts the geometric model to match the observed crystal morphology, enabling accurate measurement across varying crystal geometries while maintaining in-situ capability.

Inventive Principle:

Principle #15Dynamics

4Measurement precision

If conventional imaging systems are used, then particle size can be determined, but invasive sampling is required which disrupts the process

Engineering Contradiction:

Improveparticle size determination accuracyVSAvoidprocess disruption from sampling

Core Design Contradiction:

Measurement precisionVSEase of operation

Solution Approach 1:

The patent enables the crystallization process to measure itself in real-time without external intervention. By placing sensors directly in the crystallizer, the system performs self-diagnosis of particle size distribution without requiring removal of samples, eliminating process disruption while maintaining measurement accuracy.

Inventive Principle:

Principle #25Self-service

Data Source

PatentUS8204302B2Systems and methods for automatically determining 3-dimensional object information and for controlling a process based on automatically-determined 3-dimensional object information

Publication Date: 2012.06.19 WISCONSIN ALUMNI RES FOUND

AI summary

An image containing one or more types of objects to be located is analyzed to locate linear features within the image. The objects have edges having known spatial relationships. The linear features and identified virtual lines are analyzed to find groups of linear features and/or virtual lines that have one of the known spatial relationships. These relationships can include parallel edges, edges that meet at certain angles or angle ranges, the number of lines meeting a vertex and the like. The identified group is compared with projected 2-dimensional representation(s) of the object(s) to determine whether any additional lines appear in the image that are part of the located object. In various exemplary embodiments, two or more hypotheses for how the identified group of linear features maps to the 3-dimensional representation of the object can be generated. The best fitting hypothesis becomes the recognized 3-dimensional shape and orientation for that object.