Accurately and promptly detecting the pipeline anomaly is crucial to the safe operation of pipeline systems, while a difficulty lies in that many existing methods require massive data for training models. However, pip...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
Accurately and promptly detecting the pipeline anomaly is crucial to the safe operation of pipeline systems, while a difficulty lies in that many existing methods require massive data for training models. However, pipelines are running under normal state for the most of the time, and labeled pipeline anomaly data is usually scarce. Among the commonly used sensors, vibration sensors are widely utilized in pipeline detection because of their advantages such as easy installation and high sensitivity. However, the vibration signal shows non-stationary characteristics when anomalies occur, and are contaminated by noises, making it difficult to represent the actual state with features extracted from either the time or frequency domain. Accordingly, this paper proposes a pipeline anomaly detection method based on the KPCA (kernel principal component analysis) and cosine distance prototypical network. First, features are extracted from original signals; then, the feature dimension is reduced by KPCA; last, the cosine distance is introduced to the prototypical network for anomaly detection. The effectiveness of the proposed method is demonstrated by case studies involving experimental data.
Efficiently fulfilling coverage tasks in non-convex regions has long been a significant challenge for multi-agent systems (MASs). By leveraging conformal mapping, this paper introduces a novel sectorial coverage formu...
详细信息
Dear editor,Networked controlsystems(NCSs) have attracted widespread attention in some fields because they offer the advantages of reduced cabling, greater resource sharing,and ease of installation and maintenance [1...
Dear editor,Networked controlsystems(NCSs) have attracted widespread attention in some fields because they offer the advantages of reduced cabling, greater resource sharing,and ease of installation and maintenance [1]. However, in an unreliable network environment, network constraints can significantly limit the performance of NCSs.
Lithology identification serves as a crucial foundation for the precise exploration and safe exploitation of geological resources. However, challenges arise from the inherent imbalance and overlap present in logging d...
详细信息
Lithology identification serves as a crucial foundation for the precise exploration and safe exploitation of geological resources. However, challenges arise from the inherent imbalance and overlap present in logging data, making the accurate identification of lithology a complex task. Addressing these challenges effectively, this paper introduces a novel algorithm,the Error Correcting Output Code algorithm based on Hierarchical Clustering(HC-ECOC). The proposed algorithm initially formulates a coding matrix using distance and overlap measures between class clusters. Subsequently, it extends the length of the coding matrix by considering both the accuracy of the integrated classifier and the diversity among base classifiers. To evaluate the efficacy of the proposed method, comparisons were conducted with alternative algorithms using UCI datasets and an authentic lithology dataset. The results unequivocally demonstrate the superior performance of our algorithm.
This study extracted the main factors from a questionnaire,measurement results,and the analysis of sEMG signals to establish a method of evaluating muscle *** measured factors(rating of perceived exertion,heart rate,m...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
This study extracted the main factors from a questionnaire,measurement results,and the analysis of sEMG signals to establish a method of evaluating muscle *** measured factors(rating of perceived exertion,heart rate,mileage) and five factors obtained from the analysis of sEMG signals(root mean square,mean absolute value,variance,times of zero crossing,median frequency) were *** the F-test,the correlation analysis,and the principal component analysis,we finally extracted six factors as the main factors that have a big influence on muscle fatigue.
This paper proposes the modeling and tracking control methods for the dielectric elastomer actuator (DEA). A dynamic model of the DEA is built, which is composed of an asymmetric hysteresis model, a creep model and a ...
详细信息
Real-time environmental monitoring using a multi-agent system (MAS) has long been a focal point of cooperative control. It is still a challenging task to provide cost-effective services for potential emergencies in su...
详细信息
This paper focuses on the problem of stability analysis for Takagi-Sugeno systems with time-varying delays. Firstly,a suitable Lyapunov-Krasovskii functional(LKF) containing fuzzy line-integral Lyapunov functional is ...
This paper focuses on the problem of stability analysis for Takagi-Sugeno systems with time-varying delays. Firstly,a suitable Lyapunov-Krasovskii functional(LKF) containing fuzzy line-integral Lyapunov functional is constructed, which can introduce membership functions information while avoiding emerging the time-derivatives of membership functions. Then, a generalized free-matrix-based integral inequality is applied to estimate the derivative of the LKF. As a result, a less conservative stability criterion is obtained. Finally, a numerical example is carried out to illustrate the effectiveness and merits of our method.
This paper concerns with the exponential stability of delayed neural networks via Lyapunov-Krasovskii functional(LKF) method. Initially, an improved augmented delay-product-type LKF containing an additional double int...
This paper concerns with the exponential stability of delayed neural networks via Lyapunov-Krasovskii functional(LKF) method. Initially, an improved augmented delay-product-type LKF containing an additional double integral state is established, which introduces more delayed states and has less conservatism. In the LKF's derivative, the function has high order of delay due to the existence of exponent. Thus, in order to obtain tractable linear matrix inequalities, three state vectors are used to reduce the order of the function to cubic. Secondly, to achieve the negative-definiteness requirement, a negative-determination lemma for cubic functions with less conservatism is employed. Then, a less conservative delay-dependent stability criterion for neural networks with time-varying delays is established. Finally, the validity of the proposed delay-dependent stability criterion is illustrated by two numerical examples.
This paper is concerned with H performance state estimation of static neural networks with a time-varying ***, a PI estimator with exponential term is used to estimate neuron states based on output measurement. Second...
This paper is concerned with H performance state estimation of static neural networks with a time-varying ***, a PI estimator with exponential term is used to estimate neuron states based on output measurement. Second, an augmented Lyapunov-Krasovskii functional(LKF) containing delay-product-type non-integral terms and single integral terms is constructed by introducing negative definite terms. After that, a criterion with less conservatism is derived based on extended reciprocally convex matrix inequality. Finally, a numerical example is provided to reveal the effectiveness of the proposed approach.
暂无评论