Changing contours
Droplet boundaries varied across experimental images and needed reliable measurement.
Anonymous fluid-mechanics AI case study
Analyzing droplet contours and surface energy with physics-informed AI
A physics-informed analysis workflow connected experimental imagery, droplet-contour detection, surface-tension and free-energy calculations, equation solving, and repeatable reporting.
The situation
Experimental droplet imagery and fluid equations required specialist interpretation across several disconnected steps.
Researchers needed to detect changing liquid-surface contours accurately and relate those measurements to surface tension and free energy.
Complex partial differential equations also had to be solved consistently as part of the same analytical process.
The challenge
Connect visual measurement and physics-informed computation without hiding the experimental evidence.
Contour detection, physical calculation, equation solving, and repeatability all had to remain reviewable.
Complex equations
Partial differential equations required efficient numerical treatment grounded in the physical problem.
Repeatable analysis
Capture, calculation, and reporting needed a consistent workflow across experiments.
The solution
AI vision and physics-informed neural networks combined visual detection with fluid-mechanics analysis.
The application joined image-based measurement and physics-informed modelling rather than treating them as separate research tools.
- 01
Detect the contour
Use computer vision to identify and measure the liquid-surface boundary in experimental imagery.
- 02
Apply physical models
Calculate surface tension and free energy from the captured measurements.
- 03
Solve and report
Use physics-informed neural networks for equation solving and organize the results for review.
How the work was structured
The workflow preserved a traceable path from source imagery to interpreted physical results.
Source images and detected contours stayed visible together for review.
Equation-solving steps remained connected to the measurements and physical quantities they represented.
Reusable capture and reporting stages made repeated experiments easier to compare.
01Capture
Receive experimental imagery.
02Detect
Measure the droplet contour.
03Model
Calculate physical behavior.
04Report
Review and record the result.
The result
Researchers gained one repeatable path from droplet imagery to physics-informed interpretation.
The documented application connected visual detection, physical calculation, equation solving, and reporting in one experimental workflow.
Contour detectionfrom experimental imagery
Physics-informed analysisfor surface behavior
Repeatable reportingacross experiments
Evidence stayed visible
Detected boundaries remained connected to the source imagery.
Calculations became coordinated
Surface tension, free energy, and equation solving operated in one workflow.
Experiments became easier to repeat
Capture, analysis, and reporting followed the same sequence.
Case taxonomy
Searchable by industry, technology, product, and business need.
Industry and product
- Manufacturing
- Materials Science
- Fluid Mechanics
- Research Software
Technology and delivery
- Computer Vision
- Neural Networks
- Physics-informed Neural Networks
- Numerical Analysis
Business need
- Droplet Detection
- Contour Measurement
- Surface Tension
- Free Energy
- PDE Solving
- Experimental Reporting
Connect experimental evidence to applied AI
Need intelligent software for a complex scientific analysis workflow?
Get in touch
Ready to build software that fits your business?
Tell us what you need to build, modernize, automate, or augment with AI. We can start with a focused discussion or a no-risk 1-week trial.
“A fantastic company to work with.” After the initial rapid development project, American Shipping Co. kept two Shinetech developers embedded for nearly four years, supporting internal and external tools and new AI initiatives.
CEO, American Shipping Co. - 5-star Google Review