Sequential Domain-Adaptation Extreme Learning Machine (ELM) Combined with Principle Component Analysis (PCA) for Process Fault Diagnosis
Bibliographic record
Abstract
In the context of industrial process modelling and fault diagnosis, deep neural networks (DNNs) face challenges such as long training times, high computational costs, and limited interpretability, hampering their efficiency and applicability. Meanwhile, various multivariate data analysis techniques, nonlinear regression methods, and shallow neural networks have found wide applications, from anomaly detection to root cause fault diagnosis. In this paper, the application of extreme learning machine (ELM, a type of single feed-forward layer network) based algorithms in process modeling and diagnostics will be explored. A recursive transformation will be derived for the domain-adaptation ELM (DAELM) to present the sequential DAELM (S-DAELM). The proposed sequential DAELM can easily transform into the Regularized ELM (RELM) and DAELM form. The ridge parameter and sequential switch in the proposed S-DAELM algorithm will be set according to the problem statement, and correspondingly the RELM, DAELM or Sequential DAELM mode can be realized. Finally the SDAELM is used as an unsupervised modeling tool to reconstruct the process variables. Once the reconstruction is completed, the PCA algorithm is applied after the S-DAELM layer to automatically analyze the reconstruction residuals for efficient fault detection and root cause analysis.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| 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".