22 April 2021 in Applied Intelligence
29 January 2024 in Applied Mathematics and Computation
19 February 2019 in IEEE Access
17 July 2024 in IEEE Transactions on Industrial Informatics
Few-shot new faults are constantly emerging due to the dynamic environments and operations in the industrial process. It is a challenge for existing fault diagnosis methods to diagnose few-shot new faults without forgetting old faults by fine tuning the base model. This article defines this challenge as few-shot fault incremental learning problem, and proposes a multiview shapelet prototypical network to solve this problem. First, a multiview metalearning framework that simulates true incremental tasks and combines multiview information is proposed in this article to build a generalizable feature space for unseen classes. Second, a multiview shapelet prototypical classifier is proposed to enhance the generalization ability of shapelets in adapting new faults with few samples. Third, multiview metacalibration modules based on transformers are proposed to fuse multiview information and calibrate prototypes and embedded features into a distinguishable space. Finally, experiments are conducted on the benchmark Tennessee Eastman process and the real-world aluminum electrolysis process. Experimental results illustrate that the proposed method is better than the existing methods in terms of interpretability, alleviating catastrophic forgetting, and reducing time complexity.
28 December 2023 in IEEE Transactions on Cybernetics
Early classification predicts the class of the incoming sequences before it is completely observed. How to quickly classify streaming time series without losing interpretability through early classification method is a challenging problem. A novel memory shapelet learning framework for early classification is proposed in this article. First, a memory distance matrix is introduced to store the historical characteristics of streaming time series, which can alleviate repetitive calculations caused by the growing length of time series. Second, early interpretable shapelets are extracted in the proposed method by optimizing both accuracy objective and earliness objective simultaneously. The proposed method employs end-to-end learning, which allows the model to directly learn early shapelets without the necessity of searching for numerous candidate shapelets. Third, an objective function of memory shapelet learning is proposed by overall considering accuracy and earliness, which can be optimized by gradient descent algorithm. Finally, experiments are conducted on benchmark dataset UCR, Tennessee Eastman process, and real-world aluminum electrolysis process in China. Comparable results with other state-of-the-art methods demonstrate the superior performance of the proposed method in interpretability, accuracy, earliness, and time complexity.
1 January 2017 in Journal of Control Science and Engineering
This paper proposes a model predictive control of open irrigation canals with constraints. The Saint-Venant equations are widely used in hydraulics to model an open canal. As a set of hyperbolic partial differential equations, they are not solved explicitly and difficult to design optimal control algorithms. In this work, a prediction model of an open canal is developed by discretizing the Saint-Venant equations in both space and time. Based on the prediction model, a constrained model predictive control was firstly investigated for the case of one single-pool canal and then generalized to the case of a cascaded canal with multipools. The hydraulic software SICC was used to simulate the canal and test the algorithms with application to a real-world irrigation canal of Yehe irrigation area located in Hebei province.