Abstract
Deep learning methods have promoted the vibration-based machinery fault diagnostics from manual feature extraction to an end-to-end solution in the past few years and exhibited great success on various diagnostics tasks. However, this success is based on the assumptions that sufficient labeled data are available, and that the training and testing data are from the same distribution, which is normally difficult to satisfy in practice. To overcome this issue, we propose a multistage deep convolutional transfer learning method (MSDCTL) aimed at transferring vibration-based fault diagnostics capabilities to new working conditions, experimental protocols and instrumented devices while avoiding the requirement for new labeled fault data. MSDCTL is constructed as a one-dimensional convolutional neural network (CNN) with double-input structure that accepts raw data from different domains as input. The features from different domains are automatically learned and a customized layer is designed to compute the distribution discrepancy of the features. This discrepancy is further minimized such that the features learned from different domains are domain-invariant. A multistage training strategy including pre-train and fine-tuning is proposed to transfer the weight of a pre-trained model to new diagnostics tasks, which drastically reduces the requirement on the amount of data in the new task. The proposed model is validated on three bearing fault datasets from three institutes, including one from our own. We designed nine transfer tasks covering fault diagnostics transfer across diverse working conditions and devices to test the effectiveness and robustness of our model. The results show high diagnostics accuracies on all the designed transfer tasks with strong robustness. Especially for transfer to new devices the improvement over state of the art is very significant.
Highlights
Bearings are the key rotating components in many mechanical systems
The great success of deep learning methods in the field of fault diagnostics of rotating machinery in the past few years is based on the following two constraints, i.e., that sufficient labeled data are available and that the training and testing data are from the same distribution
These two constraints are typically difficult to satisfy in practice, and hinder the deep learning-based fault diagnostics methods being more widely employed in the industry
Summary
Bearings are the key rotating components in many mechanical systems. They are the leading cause of failure in essential industrial equipment, such as induction motors, wheelset of railway bogie, aero-engines, wind-turbine power generation plants, steel mills, etc., where bearing faults account for 51% of all failures [1]. Motivated by the practical demand of the industry and the potential for improving the diagnostic accuracy for the ‘‘different devices’’ problem, inspired by the concept of transfer learning, we propose a multistage deep convolutional transfer learning framework (MSDCTL), which achieves the tasks of transfer fault diagnostics across multiple working conditions as well as different devices with high diagnostic accuracy, nearly 100%. We propose the MSDCTL (multistage deep convolutional transfer learning) framework to address the transfer tasks of bearing fault diagnostics across different working conditions and devices with high diagnostics accuracy. After four blocks of convolution-pooling operation, a highdimension feature map containing several column vectors is obtained by the feature extraction module These column vectors represent features extracted from the input segment xIn from different perspectives and they should be concatenated to form a complete overview of xIn such that the classification module can ‘‘identify’’ it. The total loss function is L1 when the model is single-input structure while it is L1+ L2 when the model is double-input structure
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
