Deep Learning with Dynamically Weighted Loss Function for Sensor-Based Prognostics and Health Management

Abstract

Deep learning has been employed to prognostic and health management of automotive and aerospace with promising results. Literature in this area has revealed that most contributions regarding deep learning is largely focused on the model’s architecture. However, contributions regarding improvement of different aspects in deep learning, such as custom loss function for prognostic and health management are scarce. There is therefore an opportunity to improve upon the effectiveness of deep learning for the system’s prognostics and diagnostics without modifying the models’ architecture. To address this gap, the use of two different dynamically weighted loss functions, a newly proposed weighting mechanism and a focal loss function for prognostics and diagnostics task are investigated. A dynamically weighted loss function is expected to modify the learning process by augmenting the loss function with a weight value corresponding to the learning error of each data instance. The objective is to force deep learning models to focus on those instances where larger learning errors occur in order to improve their performance. The two loss functions used are evaluated using four popular deep learning architectures, namely, deep feedforward neural network, one-dimensional convolutional neural network, bidirectional gated recurrent unit and bidirectional long short-term memory on the commercial modular aero-propulsion system simulation data from NASA and air pressure system failure data for Scania trucks. Experimental results show that dynamically-weighted loss functions helps us achieve significant improvement for remaining useful life prediction and fault detection rate over non-weighted loss function predictions.

Predictive Maintenance for Pump Systems and Thermal Power Plants: State-of-the-Art Review, Trends and Challenges

“…Advantage Limitation [32]. ANN have enabled machine learning to complete more complex tasks that were not previously possible or were difficult by nature.…”

“…In Tabel 2 a set of application areas was defined. A large proportion was identified as being experimental [30,32,38,48,50,54]. Meaning that a component was investigated in an experimental setting and hence not necessarily attached to a manufacturer or plant.…”

Cross-Entropy as a Metric for the Robustness of Drone Swarms

“…Cross-entropy is one of the standard loss functions, specifically regarding multi-label classification [ 31 ]. Such a loss function can be extended to include some penalties for mislabelling [ 32 , 33 ], making it attractive for some real-world cases where misclassification should be penalised [ 6 ].…”

Automated Detection of Presymptomatic Conditions in Spinocerebellar Ataxia Type 2 Using Monte Carlo Dropout and Deep Neural Network Techniques with Electrooculogram Signals

“…Medical tasks have been modeled over the years by nature-inspired algorithms, especially artificial neural networks and the more recent and popular DL, that brought the much needed support in terms of time efficient diagnosis and clinical feature identification [6][7][8][9][10][11][12][13][14][15][16]. At the other end, data coming from different types of sensors have been also effectively analyzed by neural techniques [17][18][19][20][21][22]. At the intersection, medical data provided by sensors, such as ECG and EOG, have also been successfully tackled by DNN architectures that are able to handle temporal data [3,23,24].…”