A Novel Mechanical Fault Diagnosis Based on Transfer Learning with Probability Confidence Convolutional Neural Network Model

Abstract

For fault diagnosis, convolutional neural networks (CNN) have been performing as a data-driven method to identify mechanical fault features in forms of vibration signals. However, because of CNN’s ineffective and inaccurate identification of unknown fault categories, we propose a model based on transfer learning with probability confidence CNN (TPCCNN) to model the fault features of rotating machinery for fault diagnosis. TPCCNN includes three major modules: (1) feature engineering to perform a series of data pre-processing and feature extraction; (2) transferring learning features of heterogeneous datasets for different datasets to have better generality in model training and reduce the time for modeling and parameter tuning; and (3) building a PCCNN model to classify known and unknown fault categories. In addition to solving the problem of an imbalanced sample size, TPCCNN self-learns and retrains by iterating with unknown classes to the original model. This model is verified with the use of the open-source datasets CWRU and Ottawa. The experimental results showing the feature transfer of heterogeneous datasets are of average accuracy rates of 99.2% and 93.8% respectively for known and unknown categories, and TPCCNN is then proven effectively in training heterogeneous datasets. Likewise, similar feature sets can also be applied to reduce the training of predicting models by 34% and 68% of the time.

Enhancing Crypto Success via Heatmap Visualization of Big Data Analytics for Numerous Variable Moving Average Strategies

“…However, disposition effects [4,5], stock price overreaction [6,7], and even clustering behaviors [8,9] appear to challenge this viewpoint. As a result, some investors might predict future prices by taking diverse technical trading indicators into account because different approaches might be appropriate for some technical indicators due to the overreaction hypothesis [10][11][12][13], or momentum approaches might be suitable for other technical indicators because of excessive self-confidence [14][15][16][17].…”