Predicting the Wood Mean Moisture Content in a Conventional Kiln-based Drying Process: A Data-driven Approach
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
The quality of the production process is the biggest concern of a company to retain their clients and be competitive on the market. In the wood production industry, the wood moisture content is one of the most important criteria to define the final quality, price, and reliability of the lumbers. After the trees have been sawn into lumbers, the latter are dried using a conventional kiln to decrease the percentage of humidity in the wood. Thus, to control the quality of the process, the moisture content should be monitored all along the drying so it can be stopped at the right moisture content. Our approach consists of using machine learning techniques to predict the mean moisture content in the kiln throughout the drying process with a lag of ten hours. Using this lag, we will be able to know exactly when to stop the drying while giving more time for the logistics preparations. The data of real time sensor's measurements, the drying conditions and some other key performance indicators were used as inputs to predict the mean moisture content in the kiln within ten hours for every five minutes. After the feature engineering, the final inputs are selected using a hybrid Forward-Backward Stepwise Selection, and then fed to a Convolutional Bidirectional LSTM recurrent neural network which has been chosen after evaluating multiple machine learning models. The final model choice is based on its theoretical performance with an R2 of 95.24% and an MAE of 3.61% on the test dataset, and several discussions with the experts of the domain to reflect the operational perspective.
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.
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 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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 it