Simultaneous faults diagnosis for automotive ignition patterns

Many practical applications have the property that different possible faults may appear at one time. Simultaneous faults diagnosis is referred to accurately diagnose the possible faults based on the symptoms from an observed pattern. There are two key challenges in this kind of problem: 1) the symptoms of different faults are mixed or combined into one (input) pattern which makes accurate diagnosis difficult, 2) the preparation of a large amount of training patterns because there are many different combinations of faults. We proposed a framework to effectively resolve these challenges using feature extraction and multi-label probabilistic classification. This framework has been applied and verified in the domain of automotive ignition patterns.