Model Identification of Coupled Electromagnetic-Thermal Model of Heterogeneous Structures Using Artificial Neural Networks
Bibliographic record
Abstract
In recent years with the development of computational tools there have been significant advances in coupled/Multiphysics models that are widely applicable in numerous fields. With the continuous need for miniaturization of many engineering solutions these models become significantly complicated as the reduction of dimensions requires more advance stochastic models that account for probabilistic nature of many electromagnetic phenomena. This is especially valid In manufacturing of highly-integrated electronic circuits as we slowly move towards micro and nano dimensions. In this field thermal effects may play important role, as in the case of wire bonding in which complicated physics law interplay in order to achieve high-speed accurate ultrasound driven pressure/melting process that connects elements to a wafer. Electromagnetic-thermal modelng mainly relies on a combination of steady-state electromagnetic analysis and transient thermal analysis [1], [2]. In a previous study [3], a Physics-Informed Neural Network (PINN) [4] was utilized as the thermal solver for electromagnetic-thermal simulations, significantly improving computational efficiency compared to a conventional finite difference solver. In this paper we propose a combined thermos-electromagnetic artificial neural network solver that identifies the underlying Multiphysics model and calculates the response of the heterogeneous structure to both electromagnetic and/or thermal stimuli. We first demonstrate applicability of our model to identify the object properties i.e., calculate the response of the object to the stimuli and then demonstrate how the particular ANN can be used to detect parameter change over the time. In particular we demonstrate ability to combine information obtained from microwave and infrared images to estimate conductivity properties and identify different scatterers present in the object.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 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".