Artificial Intelligence-based optimization of Variable Blank Holder Force to reduce residual stress and improve formability; Experimental and statistical analysis
Bibliographic record
Abstract
Abstract Many contributory factors can influence the quality of the deep drawing process, among which Blank Holder Force (BHF) plays a decisive role. Therefore, controlling the BHF during the deep drawing process can bring many advantages and act as a deterrent against process failures, including tearing, wrinkling, and fatigue due to excessive residual stress and cyclic loads. Variable Blank Holder Force (VBHF), in which the BHF varies along the punch stroke, has recently been a popular method for improving sheet metal quality in the deep drawing process. In this study, VBHF was optimized to improve the formability of the process and reduce the residual stress using two different methods of Artificial Intelligence (AI) and Response Surface Method (RSM). The main purpose of this research is to introduce a new approach based on AI for VBHF optimization and compare the result of which with that of previous methods (Statistical methods). To reach this aim, BHFs in seven different stages of punch stroke were considered as the inputs of the process, and drawn depth at the tearing moment in addition to residual stresses were considered as the outputs of this optimization process. The optimization was carried out in two forms, single and multi-objective optimization to yield the desired results. The deep drawing process was numerically simulated using Abaqus/Explicit Software, with heavy modeling calculations performed on the supercomputer, Simorgh, and the experimental studies were carried out to verify FEM simulation. Additionally, to optimize VBHF using AI methods, Artificial Neural Network (ANN) was used to define a correlation function between inputs and outputs, and a Genetic Algorithm (GA) was used to optimize the function trained by ANN. Optimization results demonstrated that although the trend of optimized VBHF using AI and RSM were considerably similar to each other, the AI results were better than that of RSM in both cases of residual stress reduction and draw ability improvement. The FEM model of deep drawing process was shown to be reliable due to its excellent agreement with experimental studies.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".