Fault diagnosis of chemical process data becomes one of the most important directions in research and practice. Conventional fault diagnosis and classification methods firstly extract features from the raw process data. Then certain classifiers are adopted to make diagnosis. However, these conventional methods suffer from expertise of feature extraction and classifier design. They also lack the adaptive processing of the dynamic information in raw data. This paper proposes a fault diagnosis method based on long short-term memory (LSTM) neural network. The novel method can directly classify the raw process data without specific feature extraction and classifier design. It is also able to adaptively learn the dynamic information in raw data. Firstly, raw process data are used to train the LSTM neural network until the cost function of LSTM converges below certain predefined small positive value. In this step, the dynamic information of raw process data is adaptively learned by LSTM. Then testing data are used to obtain the diagnosis results of the trained LSTM neural network. The application of LSTM to fault identification and analysis is evaluated in the Tennessee Eastman (TE) benchmark process. Extensive experimental results show LSTM can better separate different faults and provide more promising fault diagnosis performance.

In the traditional fault diagnosis task, it is difficult to collect training samples to exhaust all fault classes. There are massive target faults that can not be collected in advance, which may restrict the performance of fault diagnosis methods. In this paper, a novel method named semantic-consistent embedding (SCE) is proposed for zero-shot industrial fault diagnosis. SCE tries to classify unseen class faults only by using seen class faults for training. The fault samples and their human-specified attribute vectors are embedded into a semantic-consistent space and then reconstructed from that space. A specific Barlow matrix is designed to measure the consistency between the embedding of fault samples and the embedding of attribute vectors. The diagonal elements and the off-diagonal elements of the Barlow matrix encode the within-dimension consistency and between-dimension consistency of the cross-modal embeddings, respectively. Through optimizing the Barlow matrix to an identity matrix, SCE learns a significant space where the cross-modal embeddings have consistent representation while reducing the redundant components. Extensive experiments show that SCE gets significant superiority on the three-phase transmission system (26.9% gains) and the Tennessee Eastman process (15.5% gains). Moreover, SCE even gets competitive results with supervised learning methods. The code of SCE can be found at https://github.com/htz-ecust/Semantic-consistent-Embedding .

Since both visible and infrared images have their own advantages and disadvantages, RGBT tracking plays an important role in intelligent transportation systems. The key points of RGBT tracking lie in feature extraction and fusion of visible and infrared images. Current RGBT tracking methods mostly pay attention to both individual features (features extracted from images of a single camera) and common features (features extracted and fused from an RGB camera and a thermal camera). Still, they pay less attention to different and dynamic contributions of the individual and common features for different sequences of registered image pairs. This paper proposes a novel RGBT tracking method, called Dynamic Fusion Network (DFNet), which adopts a two-stream structure, in which two non-shared convolution kernels are employed in each layer to extract individual features. Besides, DFNet has shared convolution kernels for each layer to extract common features. Since non-shared and shared convolution kernels are adaptively weighted and summed according to different image pairs, DFNet can deal with different contributions for different sequences. DFNet has a fast speed, which is 28.658 FPS. The experimental results show that when DFNet only increases the Mult-Adds by 0.02% compared with the non-shared-convolution-kernel-based fusion method, Precision Rate (PR) and Success Rate (SR) reach 88.1% and 71.9%, respectively. The model and dataset are available at https://github.com/PengJingchao/DFNet .

In this paper, a face spoofing detection method called the Fully Convolutional Network with Domain Adaptation and Lossless Size Adaptation (FCN-DA-LSA) is proposed. As its name suggests, the FCN-DA-LSA includes a lossless size adaptation preprocessor followed by an FCN based pixel-level classifier embedded with a domain adaptation layer. The FCN local classifier makes full use of the basic properties of face spoof distortion namely ubiquitous and repetitive. The domain adaptation (DA) layer improves generalization across different domains. The lossless size adaptation (LSA) preserves the highfrequent spoof clues caused by the face recapture process. The ablation study shows that both DA and the LSA are necessary for high-accuracy face spoofing detection. The FCN-LSA obtains competitive performance among the state-of-the-art methods. With the help of small-sample external data in the target domain (2/50, 2/50, and 1/20 subjects for CASIA-FASD, Replay-Attack, and OULU-NPU respectively), the FCN-DA-LSA further improves the performance and outperforms the existing methods.