… Inspired by the idea of unsupervised feature learning, we present a new framework of
intelligent fault diagnosis, as shown in Fig. 1(b). In this framework, the features are directly learned …

… of machinery fault diagnosis and is able to learn invariant features based on the convolution
and pooling architecture. Different from traditional CNN, a discriminative learning scheme …

… features from diverse types of data in an efficient manner, this work presents a spatiotemporal
feature learning … data in complex systems and learn spatiotemporal features. The learnt …

… the feature learning ability of DNN just meet the requirements of an adaptive feature extraction
method for mechanical fault diagnosis. … and its feature learning ability for fault diagnosis of …

… is a great challenge for rotating machinery fault diagnosis. In this paper, a novel deep
autoencoder feature learning method is developed to diagnose rotating machinery fault. Firstly, the …

… The GDBM is applied as a deep statistical feature learning tool for fault diagnosis in this
paper. The methodologies used are introduced in this section. In Section 2.1, some classical …

… feature extraction scheme for machine fault diagnosis, several experiments were studied in
this paper and the experimental data with multiple faults are … Single point faults of size 0.007, …

… The high-precision fault diagnosis performance in this paper has proven that CNN has
strong feature learning ability. Therefore, the diagnostic accuracy can be guaranteed as long as …

… for feature learning and bearing fault diagnosis. Many DNNS have been applied for feature
learning … on the multi-level features fusion in DNNs for bearing fault diagnosis. Moreover, an …

… The proposed method for bearing intelligent fault diagnosis … for bearing intelligent fault
diagnosis. It involves four parts: SBTDA model for deep feature learning, feature identification by …