EngineFaultDB: A Novel Dataset for Automotive Engine Fault Classification and Baseline Results

Ingeniería y ciencia de los materiales

• Engines 92%
• Logistic regression 54%
• Feedforward neural networks 53%
• Random forests 51%
• Exhaust gases 50%
• Gas emissions 49%
• Internal combustion engines 47%
• Decision trees 47%
• Network architecture 45%
• Fuel consumption 44%
• Data acquisition 41%
• Support vector machines 38%
• Classifiers 34%
• Neural networks 29%
• Gases 27%

Química

• Classifier 100%
• Gas 76%
• Fuel 59%