Machine Learning-Based Fault Detection and Diagnosis of Internal Combustion Engines Using an Optical Crank Angle Encoder
Bibliographic record
Abstract
Abstract Fault Detection and Diagnosis (FDD) in internal combustion engines is an important tool for better performance, safety, reliability, and instrument to reduce maintenance costs. Early detection of engine faults can help avoid abnormal event progression to failure. This study is carried out to develop two FDD algorithms to detect and diagnose internal combustion engine faults using an optical crank angle encoder. Experiments were carried out on a 2018 Ford Gen 3, 5.0L, V8, Coyote engine to achieve these goals. The engine head was modified to access the combustion chamber of specific cylinders for in-cylinder pressure measurement and, subsequently, combustion analysis. During this project, three engine faults were introduced: EGR valve failure, cylinder leakage, and spark plug degradation. In the first method, Fast Fourier Transform (FFT) is applied to the data collected using the optical crank angle encoder. FFT converts the crank angle domain data to the frequency domain. Then, the data dimension is reduced using Principal Component Analysis (PCA). The dataset with reduced dimensions is used as Multi-layer Perceptron (MLP) inputs. 10-fold cross-validation is used to determine the number of hidden layers in the MLP. The MLP model detects and diagnoses severities of cylinder leaks and EGR faults with a relatively high success rate (92%). The second method developed a classification model using the Random Forest (RF) classifier and Curve Descriptive (CD) Features. The performance of the MLP model and the Curve Descriptive features with Random Forest (CD-RF) models for detecting and diagnosing misfire faults are compared. Results show that the MLP model and CD-RF model accuracy for classifying misfire faults are 86.67% and 88,89%, respectively.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| 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".