A Novel Spatter Detection Algorithm for Real-Time Quality Control in Laser-Directed Energy Deposition-Based Additive Manufacturing
Bibliographic record
Abstract
Laser-Directed Energy Deposition (LDED) has recently been widely used for 3D-printing metal components and repairing high-value parts. One key performance indicator of the LDED process is represented by melt pool stability and spatter behavior. In this research study, an off-axis vision monitoring system is employed to characterize spatter formation based on different anomalies in the process. This study utilizes a 1 kW fiber laser-based LDED system equipped with a monochrome high-dynamic-range (HDR) vision camera and an SP700 Near-IR/UV Block visible bandpass filter positioned at various locations. To extract meaningful features from the original images, a novel image processing algorithm is developed to quantify spatter counts, orientation, area, and distance from the melt pool under harsh conditions. Additionally, this study analyzes the average number of spatters for different laser power settings, revealing a strong positive correlation. Validation experiments confirm over 93% detection accuracy, underscoring the robustness of the image processing pipeline. Furthermore, spatter detection is employed to assess the impact of spatter formation on deposition continuity. This research study provides a method for detecting spatters, correlating them with LDED process parameters, and predicting deposit quality.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".