Article
Engineering, Mechanical
Qiangqiang Li, Zhiyong Chen, Wenku Shi
Summary: A novel state estimation approach based on the variational Bayesian adaptive Kalman filter (VBAKF) and road classification is proposed for a suspension system with time-varying and unknown noise covariance. The proposed approach uses the VB approach to infer the time-varying noise covariance and optimize the state estimation accuracy. A new road classification algorithm based on multi-objective optimization and the linear classifier is also proposed to identify the unknown noise covariance. Simulation results demonstrate that the proposed approach outperforms other filters in state estimation accuracy.
Article
Automation & Control Systems
Ke Li, Shunyi Zhao, Fei Liu
Summary: This paper presents a method for joint estimation of state and unknown measurement noise covariance for nonlinear state-space models. By using variational Bayesian inference and weighted particle generation, the proposed approach can provide more satisfactory estimation performance when measurement noise covariance is unavailable.
INTERNATIONAL JOURNAL OF ADAPTIVE CONTROL AND SIGNAL PROCESSING
(2021)
Article
Environmental Sciences
Kasper Skjold Tollose, Jens Havskov Sorensen
Summary: In the event of a hazardous release of radioactive matter to the atmosphere, such as from a nuclear power plant accident, atmospheric dispersion models are used to predict the spread of radioactive particles and gases. However, in the early stages of an accident, there may be limited information available about the release. Therefore, a source term estimation method is needed for operational use shortly after an accident. A Bayesian inverse method has been developed to estimate the source term of a radioactive release from a nuclear power plant, providing a probabilistic estimate based on early observations of air concentration and gamma dose rate. This method is intended for use in the absence of a reliable source term estimate. It has been demonstrated how this probabilistic formulation can be used to estimate the amounts of each radionuclide released and future gamma dose rates. The method has been applied to an artificial case study of a radioactive release from a nuclear power plant in Finland, showing that limited air concentration measurement data may be available shortly after the release, requiring reliance on gamma dose rate observations from a dense monitoring network. Furthermore, it was shown that information about the nuclear power plant's core inventory can be used to constrain the release rates of certain radionuclides, reducing the number of free parameters of the source term.
Article
Environmental Sciences
Hongyuan Jia, Hideki Kikumoto
Summary: This paper proposes a line source estimation method that combines Bayesian inference with the super-Gaussian function, which can effectively estimate the geometric information of pollution sources. Experimental results demonstrate the performance of this method, indicating that geometry estimation is necessary for STE.
ENVIRONMENTAL RESEARCH
(2021)
Article
Automation & Control Systems
Yichun Niu, Li Sheng, Ming Gao, Donghua Zhou
Summary: This article investigates the problem of state estimation for stochastic descriptor linear systems with inaccurate noise covariance matrices. A novel adaptive moving horizon estimator based on variational Bayesian inference method is designed for descriptor systems.
IEEE TRANSACTIONS ON INDUSTRIAL ELECTRONICS
(2023)
Article
Environmental Sciences
Jilin Wang, Bin Wang, Juanjuan Liu, Wei Cheng, Jiping Zhang
Summary: This study established an inverse method for estimating the source term of unknown releases, which proved to be computationally efficient and relatively stable to uncertainties. It provides a perspective for emergency response to a toxic gas leak or terrorist attack.
ATMOSPHERIC ENVIRONMENT
(2021)
Article
Construction & Building Technology
Hua Bai, Zhijiang Du, Hongbiao Zhu, Pengchao Ding, Gongcheng Wang, Han Wang, Wenda Xu, Weidong Wang
Summary: When hazardous sources pose a threat to the environment, it is important to estimate the source term. Robotics offers a secure solution but faces challenges in uncertain environments. Rapidly inferring source parameters is crucial for unmanned source search. However, when there are multiple sources, the sensor can only measure the intensity of the coupled field.
BUILDING AND ENVIRONMENT
(2023)
Article
Automation & Control Systems
Shuanghu Qiao, Yunsheng Fan, Guofeng Wang, Dongdong Mu, Zhiping He
Summary: An improved strong tracking maximum correntropy criterion variational-Bayesian adaptive Kalman filter is proposed in this paper to address the performance degradation of current state estimation in the presence of slow-varying noise statistics. The inverse-Wishart distribution is adopted to model the unknown and time-varying measurement and process noise covariances. The varia-tional Bayesian method is used to estimate the noise covariances and system state, and the maximum correntropy criterion is employed to correct the filtering gain, improving the filtering performance of the proposed algorithm. Simulation results demonstrate that the proposed filter outperforms existing algorithms in terms of accuracy and convergence performance.
JOURNAL OF THE FRANKLIN INSTITUTE-ENGINEERING AND APPLIED MATHEMATICS
(2023)
Article
Engineering, Electrical & Electronic
Liang Yu, Zening Gong, Ning Chu, Yue Ning, Yuling Zheng, Peng Hou
Summary: This article proposes a subspace iteration integrated variational Bayesian (SVB) method to realize adaptive imaging of different sound sources, significantly improving calculation speed and robustness.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Computer Science, Artificial Intelligence
Teemu Sahlstrom, Tanja Tarvainen
Summary: There is a growing interest in using machine learning methods for inverse problems and imaging. However, most of the research has focused on image reconstruction problems, and there are limited studies on the complete solution of the inverse problem. In this study, we explore a machine learning-based approach for the Bayesian inverse problem of photoacoustic tomography. We propose a method for estimating the posterior distribution in photoacoustic tomography using a variational autoencoder, and evaluate it through numerical simulations and comparison with a Bayesian approach for solving the inverse problem.
SIAM JOURNAL ON IMAGING SCIENCES
(2023)
Article
Automation & Control Systems
Nicola Forti, Lin Gao, Giorgio Battistelli, Luigi Chisci
Summary: Point source estimation is a method that aims to detect and localize a concentrated diffusive source, estimate its intensity and induced field, based on pointwise measurements of sensors. It uses an advection-diffusion-reaction partial differential equation (ADR PDE) model and applies a finite element (FE) method for spatial discretization. The source identifiability is analyzed in a system-theoretic framework and a novel finite element multiple model (FE-MM) filtering approach is presented for source estimation. Simulation experiments demonstrate the effectiveness of the proposed algorithm.
Article
Construction & Building Technology
Jianjie Zhu, Xuanyi Zhou, Beihua Cong, Hideki Kikumoto
Summary: Bayesian inference coupled with computational fluid dynamics is used to estimate the source parameters, including location, release rate, and turn-on time, by considering the time-varying characteristics of the flow field. The predicted concentrations are calculated to obtain accurate results. It is found that reducing the sampling time interval decreases the uncertainties of the estimations, and using measured information in the developing stage of dispersion is crucial for predicting the turn-on time accurately.
BUILDING AND ENVIRONMENT
(2023)
Article
Acoustics
Jieyi Lu, Yixin Yang, Long Yang
Summary: In this paper, an efficient DOA estimation method based on inverse-free sparse Bayesian learning is proposed. The estimation of the statistics of interest is achieved by utilizing the variational expectation-maximization method. The proposed method shows good accuracy and improved computational efficiency compared to other state-of-art methods.
Article
Automation & Control Systems
Shuanghu Qiao, Yunsheng Fan, Guofeng Wang, Dongdong Mu, Zhiping He
Summary: In this article, a modified strong tracking slide window variational adaptive Kalman filter algorithm is proposed to address the issues of time-varying and unknown noise statistics in measurements. The algorithm integrates multiple fading factors and uses an improved adaptive slide window method with variational Bayesian Kalman filtering, improving estimation accuracy and computational efficiency. The inverse Wishart distribution is used to model process and measurement noise, and the state vector and noise statistics are inferred using the VB technique without prior noise covariance information. Simulation results demonstrate the robustness of the proposed filter algorithm in handling measurement and process noise uncertainties.
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS
(2023)
Article
Engineering, Marine
Feilong Ding, Cheng Chi, Yu Li, Haining Huang
Summary: In passive sonars, time delay estimations affect the accuracy of distance and depth estimation of underwater targets. This paper proposes a grid-less method for time delay estimation using variational Bayesian inference, which performs estimation continuously in the time domain. Unlike existing grid-less methods, this method automatically estimates the number of time delays, noise variance, and amplitude variance without parameter adjustment. Simulation results demonstrate that the proposed method outperforms state-of-the-art time delay estimation methods.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Article
Environmental Sciences
Sarvesh Kumar Singh, Raj Rani
ATMOSPHERIC ENVIRONMENT
(2015)
Article
Environmental Sciences
Pramod Kumar, Amir-Ali Feiz, Pierre Ngae, Sarvesh Kumar Singh, Jean-Pierre Issartel
ATMOSPHERIC ENVIRONMENT
(2015)
Article
Meteorology & Atmospheric Sciences
Sarvesh Kumar Singh, Gregory Turbelin, Jean-Pierre Issartel, Pramod Kumar, Amir Ali Feiz
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
(2015)
Article
Meteorology & Atmospheric Sciences
Pramod Kumar, Amir-Ali Feiz, Sarvesh Kumar Singh, Pierre Ngae, Gregory Turbelin
JOURNAL OF GEOPHYSICAL RESEARCH-ATMOSPHERES
(2015)
Article
Environmental Sciences
Pramod Kumar, Sarvesh Kumar Singh, Amir-Ali Feiz, Pierre Ngae
ATMOSPHERIC ENVIRONMENT
(2016)
Article
Astronomy & Astrophysics
Sarvesh Kumar Singh, Pramod Kumar, Raj Rani, Gregory Turbelin
EARTH AND SPACE SCIENCE
(2017)
Article
Environmental Sciences
Sarvesh Kumar Singh, Raj Rani
ATMOSPHERIC ENVIRONMENT
(2014)
Article
Meteorology & Atmospheric Sciences
Sarvesh Kumar Singh, Maithili Sharan, Jean-Pierre Issartel
BOUNDARY-LAYER METEOROLOGY
(2013)
Article
Meteorology & Atmospheric Sciences
Sarvesh Kumar Singh, Maithili Sharan, Amit Kumar Singh
QUARTERLY JOURNAL OF THE ROYAL METEOROLOGICAL SOCIETY
(2015)
Article
Meteorology & Atmospheric Sciences
Gregory Turbelin, Sarvesh Kumar Singh, Jean-Pierre Issartel
JOURNAL OF ADVANCES IN MODELING EARTH SYSTEMS
(2014)
Article
Astronomy & Astrophysics
Gregory Turbelin, Sarvesh Singh, Pierre Ngae, Pramod Kumar
EARTH AND SPACE SCIENCE
(2018)
Article
Astronomy & Astrophysics
Sarvesh Kumar Singh, Maithili Sharan
EARTH AND SPACE SCIENCE
(2019)
Article
Astronomy & Astrophysics
Sarvesh Kumar Singh, Gregory Turbelin, Jean-Pierre Issartel
EARTH AND SPACE SCIENCE
(2019)
Article
Environmental Sciences
Sarvesh Kumar Singh, Pramod Kumar, Gregory Turbelin, Raj Rani
ATMOSPHERIC ENVIRONMENT
(2017)
