Overview
Analysis
Solutions
Complete
·Feb 17, 2026
The Core Insight

Monitoring is a state estimation problem, not an imaging problem

  • The L-PBF monitoring field framed defect detection as 'capture pictures of defects forming.' This locked the field into optical sensing, which has fundamental observability limitations for subsurface keyhole dynamics.
  • Reframing to 'estimate per-voxel defect probability from all available physical observables' — the approach used in robotics SLAM, volcanology, and neuroscience BCI — opens acoustic, electromagnetic, and interferometric channels that are individually stronger than optical imaging for this specific problem.
Viability
Solvable with Effort
  • No single modality achieves 90% PoD for 50 μm pores, but multi-modal Bayesian fusion of 3 independent modalities at 70% each yields >92% — and the individual modalities are all proven in adjacent domains.
Key Decision

If you prioritize speed-to-deployment and lowest risk, start with the photodiode array alone and add modalities incrementally. If you prioritize the fastest path to 90% PoD, install photodiodes AND acoustic sensors in parallel — the combined investment is under $25K in hardware and the two modalities have anti-correlated failure modes that make Bayesian fusion particularly powerful.

Solution Paths
01NEEDS VALIDATION

Multi-Spectral Photodiode Array (Automotive Welding Transfer)

Commodity photodiodes at 1 MHz replace the camera, proven at higher speeds in welding, but alone tops out at ~65-75% PoD for individual 50 μm pores — a foundation layer, not a complete solution.

02NEEDS VALIDATION

Acoustic Emission with Matched-Filter Processing for Keyhole Collapse Detection

Treats keyhole collapse as cavitation and applies naval acoustics signal processing through the build plate — 28-40 dB SNR advantage over thermal imaging, but background noise spectrum is unknown.

Recommendation
  1. If this were my project, I would do three things in parallel starting Monday morning.
  2. First, I'd order the photodiode hardware from Thorlabs and the piezoelectric sensors from PCB Piezotronics — total cost under $10K, delivery in 2-3 weeks.
  3. While waiting, I'd characterize the scan head optical path at 1060 and 1310 nm to determine whether OCT is viable on this specific system.
  4. The photodiodes and acoustic sensors install simultaneously in the co-axial path and on the build plate underside respectively, sharing a single integration effort.
  5. Second, and this is the part most people would skip: I'd run the $500 diffraction experiment on an existing L-PBF sample.
  6. Collimated laser, camera, grazing incidence, 2 hours of work.
  7. It will almost certainly fail — the surface roughness is too high — but if it works, it's a game-changer for inter-layer inspection.
  8. The cost of learning is negligible.
  9. Similarly, I'd run the thermal wave analysis on archived thermal camera data from previous builds that have CT ground truth.
  10. Zero hardware cost, a few weeks of signal processing work, and it tells us whether there's unexploited temporal information in data we already have.
  11. Third, I'd start the conversation with a Bayesian inference specialist — ideally someone from a robotics SLAM or geophysics inversion background.
  12. Not to build the full framework yet, but to design the minimum viable 2-modality fusion architecture that we'll test once the photodiode and acoustic data starts flowing.
  13. The fusion framework is the long-term competitive platform, and designing it now ensures the sensor data formats and feature extraction pipelines are compatible from day one.
  14. The critical decision point comes at 6 months: we'll have photodiode and acoustic data from 10-20 builds with CT ground truth.
  15. If the acoustic background noise is manageable (>10 dB effective SNR), we have two complementary modalities with anti-correlated failure modes — the foundation for >85% fused PoD.
  16. If the acoustic noise is too high, we pivot to OCT as the primary keyhole monitoring channel and retain the acoustic sensors for process-level monitoring.
  17. Either way, the photodiode array provides the baseline monitoring capability from day one.
  18. One thing I would NOT do: chase the 90% PoD target with in-situ monitoring alone.
  19. The NASA MSFC-STD-3716 hybrid pathway exists for a reason<sup>[9]</sup>.
  20. Getting to 70-80% in-situ PoD and using it to target post-build NDE to the 10-20% of the build volume that matters most is more achievable, more defensible in qualification, and more economically rational than trying to eliminate post-build NDE entirely.

By continuing, you agree to our use of cookies to improve your experience.