Search

Domain-transfer learning is a machine learning task to explore a source domain data set to help the learning problem in a target domain. Usually, the source domain has sufficient labeled data, while the target domain does not. In this paper, we propose a novel domain-transfer convolutional model by mapping a target domain data sample to a proxy in the source domain and applying a source domain model to the proxy for the purpose of prediction. In our framework, we firstly represent both source and target domains to feature vectors by two convolutional neural networks and then construct a proxy for each target domain sample in the source domain space. The proxy is supposed to be matched to the corresponding target domain sample convolutional representation vector well. To measure the matching quality, we proposed to maximize their squared-loss mutual information (SMI) between the proxy and target domain samples. We further develop a novel neural SMI estimator based on a parametric density ratio estimation function. Moreover, we also propose to minimize the classification error of both source domain samples and target domain proxies. The classification responses are also smoothened by manifolds of both the source domain and proxy space. By minimizing an objective function of SMI, classification error, and manifold regularization, we learn the convolutional networks of both source and target domains. In this way, the proxy of a target domain sample can be matched to the source domain data and thus benefits from the rich supervision information of the source domain. We design an iterative algorithm to update the parameters alternately and test it over benchmark data sets of abnormal behavior detection in video, Amazon product reviews sentiment analysis, etc. [ABSTRACT FROM AUTHOR]

It is crucial to carry out the fault diagnosis of rotating machinery by extracting the features that contain fault information. Many previous works using a deep convolutional neural network (CNN) have achieved excellent performance in finding fault information from feature extraction of detected signals. They, however, may suffer from time-consuming and low versatility. In this paper, a CNN integrated with the adaptive batch normalization (ABN) algorithm (ABN-CNN) is developed to avoid high computing resource requirements of such complex networks. It uses a large-scale convolution kernel at the grassroots level and a multidimensional 3 × 1 small convolution nuclear. Therefore, a fast convergence and high recognition accuracy under noise and load variation environment can be achieved for bearing fault diagnosis. The performance results verify that the proposed model is superior to Support Vector Machine with Fast Fourier Transform (FFT-SVM) and Multilayer Perceptron with Fast Fourier Transform (FFT-MLP) models and Deep Neural Network with Fast Fourier Transform (FFT-DNN). [ABSTRACT FROM AUTHOR]

As one of the most vital parts of rotating equipment, it is an essential work to diagnose rolling bearing failure. The traditional signal processing-based rolling bearing fault diagnosis algorithms rely on artificial feature extraction and expert knowledge. The working condition of rolling bearings is complex and changeable, so the traditional algorithm is slightly lacking adaptability. The damage degree also plays a crucial role in fault monitoring. Different damage degrees may take different remedial measures, but traditional fault-diagnosis algorithms roughly divide the damage degree into several categories, which do not correspond to the continuous value of the damage degree. To solve the abovementioned two problems, this paper proposes a fault-diagnosis algorithm based on "end-to-end" one-dimensional convolutional neural network. The one-dimensional convolution kernel and the pooling layer are directly applied to the original time domain signal. Feature extraction and classifier are merged together, and the extracted features are used to judge the damage degree at the same time. Then, the generalization ability of the model is studied under a variety of conditions. Experiments show that the algorithm can achieve more than 99% accuracy and can accurately give the damage degree of the bearing. It has good performance under different speeds, different types of motors, and different sampling frequencies, and so it has good generalization ability. [ABSTRACT FROM AUTHOR]