Machine Learning Particle Measurement for Spray Flow Characterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current systems for characterizing spray flow fields are complex and expensive, making them impractical for many spraying applications that require field configuration, such as in farm fields or shops, as they involve lengthy testing procedures and high costs.
Innovation Solution
A particle measurement system that uses a machine learning stage to process data from a particle-laden flow field, incorporating a preconditioning stage to generate conditioned input data, which then renders accurate characterizations of spray flow fields by predicting droplet size distribution using off-axis light scattering and supervised machine learning techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If high precision measuring devices are used to characterize spray flow fields, then measurement precision is improved, but device complexity and cost increase significantly
Solution Approach 1:
The patent replaces complex mechanical measurement systems with a machine learning-based computational system. Instead of using high-precision mechanical sensors and lengthy physical testing procedures, the system uses a trained neural network that processes images from a standard camera to predict spray flow field characteristics instantly, eliminating the need for complex mechanical measurement apparatus.
Solution Approach 2:
The patent creates a virtual model (neural network) that copies the behavior and characteristics of complex spray flow fields. By training the neural network on data from high-precision measurements, the system creates a digital twin that can predict flow field characteristics without requiring the physical measurement devices during operation.
2Measurement precision
If high precision measuring devices and complex testing procedures are used, then measurement precision is improved, but loss of time increases due to lengthy testing procedures
Solution Approach 1:
The patent performs preliminary action by training the neural network model in advance using data from high-precision measurements and complex testing procedures. Once trained, the model can instantly predict spray flow field characteristics without requiring the time-consuming physical testing procedures, as the learning has already been completed during the training phase.
Solution Approach 2:
The patent substitutes time-consuming mechanical measurement procedures with instant computational predictions. The machine learning model processes images and predicts flow field characteristics in real-time, eliminating the need for lengthy physical testing while maintaining measurement precision.
3Measurement precision
If high precision measuring devices are used, then measurement precision is improved, but ease of operation deteriorates due to complex testing procedures
Solution Approach 1:
The patent replaces complex mechanical measurement systems with a simple computational system. Instead of requiring operators to set up and conduct complex physical tests, the system simply captures images with a camera and uses the trained neural network to predict flow field characteristics, dramatically simplifying operation while maintaining precision.
Solution Approach 2:
The patent enables the system to perform measurements automatically without requiring expert operators. The neural network autonomously processes images and predicts flow field characteristics, eliminating the need for skilled personnel to conduct complex testing procedures and interpret results.
4Measurement precision
If complex testing procedures are used to characterize spray flow fields, then measurement precision is improved, but productivity decreases due to lengthy testing procedures
Solution Approach 1:
The patent performs the complex learning work in advance during the training phase. Once the neural network is trained on comprehensive data, it can instantly predict spray flow field characteristics during operation, transforming a previously time-consuming process into an immediate one and dramatically improving productivity.
Solution Approach 2:
The patent substitutes slow mechanical measurement and testing procedures with fast computational predictions. The machine learning model processes images and outputs flow field characteristics instantly, eliminating the time delays inherent in physical measurement systems and significantly increasing productivity.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables robust and dynamic characterization of spray flows for various applications, reducing the need for expensive and complex systems by providing real-time data processing and configuration, thus improving operational efficiency and cost-effectiveness.
Implementation Method 1
A particle measurement system uses a machine learning stage to process data from a particle-laden flow field... predicting droplet size distribution using off-axis light scattering
Data Source
AI summary
A particle measurement system and method of operation thereof are described. The system and method render a characteristic for a set of particles measured while passing through a measurement volume. The system includes a source that generates a particle-laden field containing the set of particles. The system further includes 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 carries out a preconditioning operation on the particle data content of the set of raw particle records to render a conditioned input data. A machine learning stage processes the conditioned input data to render an output characteristic parameter value for the set of particles.