USING MACHINE LEARNING TO PREDICT MECHANICAL PROPERTIES OF LONG FIBER THERMOPLASTICS BASED ON MANUFACTURING PROCESS PARAMETERS
Bibliographic record
Abstract
Long Fiber Thermoplastic Direct Extrusion Compression Molding (LFT-D) is an effective manufacturing process for semi-structural composite parts. LFT-D requires the user to know the influence each process parameter (e.g., temperature setpoints, rotational machinery speed, twin screw extruder configurations, matric flow rates, etc.) has on the resulting mechanical property of the manufactured part. This case study highlights the LFT-D manufacturing of carbon and glass fiber reinforced PA6 (CFRP, GFRP) at the Fraunhofer Innovation Platform (FIP) at the University of Western Ontario in London, Ontario, Canada. Data was collected for forty-six trials conducted over three years, varying fiber concentrations, fiber volume weights, screw configurations, temperatures, torques, forces, and pressures. The mechanical properties were measured and recorded in zero- and ninety-degree fiber directions. Machine Learning (ML) models like linear regression, random forest regression, ridge regressor, and lasso regressor were used to predict mechanical properties like Young's modulus and tensile strength of the part based on the process parameters as inputs. Data preprocessing and cleaning techniques were used to reduce the dimensionality of the dataset and to reduce the number of inputs to the model. These models were then evaluated using cross-validation to select the best model. Once the model was selected, the validation and testing datasets were used to determine the accuracy of the model. A sensitivity analysis was also conducted to determine how the variation in the output of each model can be attributed to the variation in input parameters. With this information, models can be further refined to obtain a more accurate prediction of the outputs and determine which inputs are essential when in the design phase of a product. The application of machine learning in the manufacturing process will ultimately accelerate composite product development and reduce the costly and iterative manufacturing process.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| 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 | 0.000 |
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".