Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fa...Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.展开更多
In this paper, observation data in 25 GPS reference stations of China have been analyzed by calculating GPS position coordinate time-series with GIPSY. Result shows there is an obvious trend variation in such time-ser...In this paper, observation data in 25 GPS reference stations of China have been analyzed by calculating GPS position coordinate time-series with GIPSY. Result shows there is an obvious trend variation in such time-series. The trend variations of time series along the longitude and latitude coordinate reflect the motion of each position in the global-plate, in which the trend variation in the vertical direction reveals some large-scale construction information or reflects the local movement around the positions. The analysis also shows that such time-series have a variation cycle of nearly 1.02 a, but the reason still remains to be further studied. At the end of this paper, response of the time-series to MS=8.1 Kunlunshan earthquake was analyzed, and the seismogenic process of MS=8.1 Kunlunshan earthquake, according to the time proceeding and the feature of anomaly, was divided into 3 phases-changes in blocks with forces, strain accumulation, quick accumulation and slow release of energy. At the initial stage of seismogenic process of MS=8.1 earthquake and at the imminent earthquake, coseismic process as well as during the post earthquake recovery, anomaly in vertical direction is always in a majority. The anomalous movement in vertical direction at the initial stage resulted in a blocking between faults, while at the middle stage of seismogenic process, the differential movement between blocks are in a majority, which is the major reason causing energy accumulating at the blocking stage of faults.展开更多
The rapid growth of unlabeled time-series data in domains such as wireless communications,radar,biomedical engineering,and the Internet of Things(IoT)has driven advancements in unsupervised learning.This review synthe...The rapid growth of unlabeled time-series data in domains such as wireless communications,radar,biomedical engineering,and the Internet of Things(IoT)has driven advancements in unsupervised learning.This review synthe-sizes recent progress in applying autoencoders and vision transformers for un-supervised signal analysis,focusing on their architectures,applications,and emerging trends.We explore how these models enable feature extraction,anomaly detection,and classification across diverse signal types,including electrocardiograms,radar waveforms,and IoT sensor data.The review high-lights the strengths of hybrid architectures and self-supervised learning,while identifying challenges in interpretability,scalability,and domain generaliza-tion.By bridging methodological innovations and practical applications,this work offers a roadmap for developing robust,adaptive models for signal in-telligence.展开更多
Purpose-The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations(NSS).Because the conventional methods for the prediction of NSS,such as support vect...Purpose-The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations(NSS).Because the conventional methods for the prediction of NSS,such as support vector machine,particle swarm optimization,etc.,lack accuracy,robustness and efficiency,in this study,the authors propose a new method for the prediction of NSS based on recurrent neural network(RNN)with gated recurrent unit.Design/methodology/approach-This method extracts internal and external information features from the original time-series network data for the first time.Then,the extracted features are applied to the deep RNN model for training and validation.After iteration and optimization,the accuracy of predictions of NSS will be obtained by the well-trained model,and the model is robust for the unstable network data.Findings-Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models.Although the deep RNN models need more time consumption for training,they guarantee the accuracy and robustness of prediction in return for validation.Originality/value-In the prediction of NSS time-series data,the proposed internal and external information features are well described the original data,and the employment of deep RNN model will outperform the state-of-the-arts models.展开更多
基金supported by the National Natural Science Foundation of China(62073140,62073141)the Shanghai Rising-Star Program(21QA1401800).
文摘Fault diagnosis is important for maintaining the safety and effectiveness of chemical process.Considering the multivariate,nonlinear,and dynamic characteristic of chemical process,many time-series-based data-driven fault diagnosis methods have been developed in recent years.However,the existing methods have the problem of long-term dependency and are difficult to train due to the sequential way of training.To overcome these problems,a novel fault diagnosis method based on time-series and the hierarchical multihead self-attention(HMSAN)is proposed for chemical process.First,a sliding window strategy is adopted to construct the normalized time-series dataset.Second,the HMSAN is developed to extract the time-relevant features from the time-series process data.It improves the basic self-attention model in both width and depth.With the multihead structure,the HMSAN can pay attention to different aspects of the complicated chemical process and obtain the global dynamic features.However,the multiple heads in parallel lead to redundant information,which cannot improve the diagnosis performance.With the hierarchical structure,the redundant information is reduced and the deep local time-related features are further extracted.Besides,a novel many-to-one training strategy is introduced for HMSAN to simplify the training procedure and capture the long-term dependency.Finally,the effectiveness of the proposed method is demonstrated by two chemical cases.The experimental results show that the proposed method achieves a great performance on time-series industrial data and outperforms the state-of-the-art approaches.
基金National Natural Science Foundation of China (40074024 and 40304002).
文摘In this paper, observation data in 25 GPS reference stations of China have been analyzed by calculating GPS position coordinate time-series with GIPSY. Result shows there is an obvious trend variation in such time-series. The trend variations of time series along the longitude and latitude coordinate reflect the motion of each position in the global-plate, in which the trend variation in the vertical direction reveals some large-scale construction information or reflects the local movement around the positions. The analysis also shows that such time-series have a variation cycle of nearly 1.02 a, but the reason still remains to be further studied. At the end of this paper, response of the time-series to MS=8.1 Kunlunshan earthquake was analyzed, and the seismogenic process of MS=8.1 Kunlunshan earthquake, according to the time proceeding and the feature of anomaly, was divided into 3 phases-changes in blocks with forces, strain accumulation, quick accumulation and slow release of energy. At the initial stage of seismogenic process of MS=8.1 earthquake and at the imminent earthquake, coseismic process as well as during the post earthquake recovery, anomaly in vertical direction is always in a majority. The anomalous movement in vertical direction at the initial stage resulted in a blocking between faults, while at the middle stage of seismogenic process, the differential movement between blocks are in a majority, which is the major reason causing energy accumulating at the blocking stage of faults.
文摘The rapid growth of unlabeled time-series data in domains such as wireless communications,radar,biomedical engineering,and the Internet of Things(IoT)has driven advancements in unsupervised learning.This review synthe-sizes recent progress in applying autoencoders and vision transformers for un-supervised signal analysis,focusing on their architectures,applications,and emerging trends.We explore how these models enable feature extraction,anomaly detection,and classification across diverse signal types,including electrocardiograms,radar waveforms,and IoT sensor data.The review high-lights the strengths of hybrid architectures and self-supervised learning,while identifying challenges in interpretability,scalability,and domain generaliza-tion.By bridging methodological innovations and practical applications,this work offers a roadmap for developing robust,adaptive models for signal in-telligence.
基金supported by the funds of Ningde Normal University Youth Teacher Research Program(2015Q15)The Education Science Project of the Junior Teacher in the Education Department of Fujian province(JAT160532).
文摘Purpose-The purpose of this paper is to solve the shortage of the existing methods for the prediction of network security situations(NSS).Because the conventional methods for the prediction of NSS,such as support vector machine,particle swarm optimization,etc.,lack accuracy,robustness and efficiency,in this study,the authors propose a new method for the prediction of NSS based on recurrent neural network(RNN)with gated recurrent unit.Design/methodology/approach-This method extracts internal and external information features from the original time-series network data for the first time.Then,the extracted features are applied to the deep RNN model for training and validation.After iteration and optimization,the accuracy of predictions of NSS will be obtained by the well-trained model,and the model is robust for the unstable network data.Findings-Experiments on bench marked data set show that the proposed method obtains more accurate and robust prediction results than conventional models.Although the deep RNN models need more time consumption for training,they guarantee the accuracy and robustness of prediction in return for validation.Originality/value-In the prediction of NSS time-series data,the proposed internal and external information features are well described the original data,and the employment of deep RNN model will outperform the state-of-the-arts models.
