Application of Multi-Label Convolutional Neural Networks on Enhancement of Reliability of Classification, a Case Study on Bearing Fault Diagnostics

In contrast to the multi-class classification where one and only one class would be assigned to each instance, multi-label classification allows for more flexible classification and possibility of having multiple labels for instance. This property enables us to model the dependencies between the classes such as effect of one label on the probability of the occurrence of another label. Considering these connections between the classes can help us to enhance the reliability of classifiers and handle contradictory predictions. Much like how we can assign multiple classes to an instance, we can also have an instance that remains unlabelled. This class is typically referred to as the "neutral" label, allowing us to bluntly state that we lack sufficient information to label the instance with adequate certainty. Leveraging these properties, a 1D convolutional neural network (CNN) has been proposed to classify common faults occurring in the bearings. The network has the capability to assign a confidence level between 0 to 1 to each class independently. Later, a threshold has been set on each class to identify the instance labels if any. Subsequently, instances with contradictory predicted labels have been flagged as undetermined and removed from the predicted result. Thus, the remaining classified instances can be labelled with sufficient confident. In the end, the multi-label CNN model performance has been compared with equivalent multi-class CNN model. The technique has been evaluated using MAFAULDA open dataset which is composed of vibration signals from experimentally simulated different bearing conditions. A data reduction scheme has been performed on the dataset to make the diagnostic more challenging and to evaluate the performance of CNN in more realistic condition with insufficient data.