End‐To‐End Deep Learning Temperature Prediction Algorithms of a Phase Change Materials From Experimental Photos
Bibliographic record
Abstract
ABSTRACT A Phase‐change material (PCM) experiences irregular shape and nonlinear temperature changes at different locations during the melting process; these parameters provide valuable information on the characteristics of the PCM. Traditional explicit image processing, statistics, and mathematical techniques may be used to estimate the temperature of the PCM photos, but these methods have limitations such as high inaccuracy, no generalization, and complexity. Here, temperatures at different locations inside the PCM have been calculated by using the shape of melting PCM with the aid of deep learning. An experimental setup was built to melt the PCM under constant wall temperature and a conventional digital camera took temporal photos of the phase change. Four end‐to‐end networks have been developed to use the captured photos as input and report temperatures of the PCM as output. Initially, the networks were built using different convolutional layers and weights for feature extraction, and then the fully connected layers extracted the temperature profiles of the PCM. Comparison of the networks shows that MobileNets based Weights IV – Deep Neural Network (WIV‐ DNN) detects the temperature at different locations of the PCM successfully with an average error of less than 0.9% during the whole melting process in 0.03 s. This temperature measurement method is cost‐effective, independent of thermographic cameras, accurate, fast response, and can be updated for other related applications in industries and scientific studies. All programs and datasets are available on GitHub.
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 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".