k-Nearest Neighbours Fault Diagnosis of Proton Exchange Membrane Fuel Cell
Bibliographic record
Abstract
In this paper, a fault diagnosis of a Proton Exchange Membrane Fuel Cell (PEMFC) is presented. The aim of this tool is to avoid non reversible degradations of a fuel cell system linked to fault occurrence. The damage incurred by the fuel cell depends on the nature of the fault and its duration time. Some faults are non-reversibles for the fuel cell after few seconds. Some experiments are performed on an in-lab test bench considering a forty - cell stack. The electrode has an active area of 220cm² and a nominal power of 3.8 kW. The aim is to reproduce different operating conditions and especially possible fault states. The fuel cell system was operated at different conditions such as oxygen starvation, electrical short-circuit at the output of the fuel cell stack and heating of the cooling system. All these states will be compared to the nominal operating conditions defined, beforehand, by test specifications and are used as database for the algorithm inputs. The purpose is to be able to detect if the fuel cell is in abnormal operating conditions and also to isolate the fault. The diagnosis is here based on Electrochemical Impedance Spectroscopy (EIS) that measures the impedance of the stack over a large band of frequencies from 100 mHz to 5 kHz. Some relevant points are extracted from the EIS in order to be used as inputs of the classification algorithm. Depending on the application, different constraints have to be taken into account when building a diagnosis tool of fuel cell systems. One of the most constraining limitations is to be as least intrusive as possible. Indeed, it is preferable to use as less costly sensors as possible when considering industrial implementation. The second constraint is linked to the computation time of the diagnosis approach which should be fast enough to allow the implementation of an online diagnosis of fuel cell systems. These two factors motivate the choice of the k-NN algorithm, which is well known for its efficiency and simplicity of implementation. Results will be detailed in the final presentation.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| 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".