Currently, with the increasing scale of industrial systems, multisensor monitoring data exhibit large-scale dynamic Gaussian and non-Gaussian concurrent complex characteristics. However, the traditional principal component analysis method is based on Gaussian distribution and uncorrelated assumptions, which are greatly limited in practice. Therefore, developing a new fault detection method for large-scale Gaussian and non-Gaussian concurrent dynamic systems is one of the urgent challenges to be addressed. To this end, a double-layer distributed and integrated data-driven strategy based on Laplacian score weighting and integrated Bayesian inference is proposed. Specifically, in the first layer of the distributed strategy, we design a Jarque-Bera test module to divide all multisensor monitoring variables into Gaussian and non-Gaussian blocks, successfully solving the problem of different data distributions. In the second layer of the distributed strategy, we design a dynamic augmentation module to solve dynamic problems, a K-means clustering module to mine local similarity information of variables, and a Laplace scoring module to quantitatively evaluate the structural retention ability of variables. Therefore, this double-layer distributed strategy can simultaneously combine the different distribution characteristics, dynamism, local similarity, and importance of variables, comprehensively mining the local information of the multisensor data. In addition, we develop an integrated Bayesian inference strategy based on detection performance weighting, which can emphasize the differential contribution of local models. Finally, the fault detection results for the Tennessee Eastman production system and a diesel engine working system validate the superiority of the proposed method.

Download full-text PDF

Source
http://www.ncbi.nlm.nih.gov/pmc/articles/PMC11507364PMC
http://dx.doi.org/10.3390/e26100815DOI Listing

Publication Analysis

Top Keywords

double-layer distributed
12
fault detection
12
gaussian non-gaussian
12
distributed strategy
12
distributed integrated
8
industrial systems
8
multisensor monitoring
8
non-gaussian concurrent
8
strategy based
8
integrated bayesian
8

Similar Publications

Molecule-electrode interactions are critical for determining transport mechanisms and device functionalities in both single-molecule electrochemistry and electronics. Crucial factors such as anchoring groups and local fields have been studied, but the role of electrolytes and interfacial charge distribution remains largely underexplored. The present research focuses on how the interfacial charge distribution in the electric double layer (EDL) controls single-molecule junctions anchored by azulene.

View Article and Find Full Text PDF

Length-dependent water permeation through a graphene channel.

Phys Chem Chem Phys

December 2024

MIIT Key Laboratory of Semiconductor Microstructure and Quantum Sensing, and Department of Applied Physics, Nanjing University of Science and Technology, Nanjing 210094, China.

Water confined in two-dimensional channels exhibits unique properties, such as rich morphology, specific phase transition and a low dielectric constant. In this work, molecular dynamics simulations have been used to study the water transport in two-dimensional graphene channels. The structures and dynamics of water under confinement show strong dependence on the channel length and thickness of the channels.

View Article and Find Full Text PDF

The Application of Porous Carbon Derived from Furfural Residue as the Electrode Material in Supercapacitors.

Polymers (Basel)

December 2024

Department of New Energy Science and Engineering, School of Energy and Power Engineering, Huazhong University of Science and Technology, Wuhan 430074, China.

Resource use is crucial for the sustainable growth of energy and green low-carbon applications since the improper handling of biomass waste would have a detrimental effect on the environment. This paper used nano-ZnO and ammonium persulfate ((NH)SO, APS) as a template agent and heteroatom dopant, respectively. Using a one-step carbonization process in an inert atmosphere, the biomass waste furfural residue (FR) was converted into porous carbon (PC), which was applied to the supercapacitor electrode.

View Article and Find Full Text PDF

Flexible and diverse manipulation of electromagnetic (EM) waves in half space (reflection or transmission) has facilitated strong aspiration toward full-space wave control. However, it remains challenging to achieve independent amplitude and phase control, which seriously hinder the real-world applications. Herein, an innovative strategy of trifunctional metasurface is proposed to independently and simultaneously manipulate the amplitude and phase of circular polarized waves in full space.

View Article and Find Full Text PDF

Functionalised biphenylene and graphenylene: excellent choices for supercapacitor electrodes.

Phys Chem Chem Phys

December 2024

Department of Physics, University of Calcutta, 92 Acharya Prafulla Chandra Road, Kolkata-700009, India.

Quantum capacitance () is a crucial parameter that reflects the energy storage capacity of supercapacitors. In this work, we extensively investigate the effect of vacancy induced defects on quantum capacitance of well studied biphenylene (BPN) and graphenylene (GPN) monolayers. Based on density functional theory (DFT), we have systematically studied the consequence of vacancies on structural stability, charge distribution, electronic band structure of pristine systems, and correlated this with the variation of quantum capacitance with applied voltage.

View Article and Find Full Text PDF

Want AI Summaries of new PubMed Abstracts delivered to your In-box?

Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!