A multivariate descriptor method for change-point detection in nonlinear time series

Balestrassi, Pedro Paulo; Paiva, Anderson Paulo de; Souza, Antônio Carlos Zambroni de; Turrioni, João Batista; Popova, Elmira

doi:10.1080/02664760903406496

Cited by 9 publications

(3 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…over time. 22 The purpose of this paper is to establish a nonlinear time series model to describe the nonlinear characteristics of acceleration time series data in time domain and determine the location of nonlinear damage sources by damage indicators. Therefore, this paper firstly proposes a nonlinear damage identification method for a transmission tower based on GNAR model and Itakura distance.…”

Section: Introductionmentioning

confidence: 99%

Nonlinear damage identification method of transmission tower structure based on general expression for linear and nonlinear autoregressive model and Itakura distance

Heng

Guo

2022

Structural Health Monitoring

View full text Add to dashboard Cite

Fatigue cracks and bolt looseness are two kinds of common nonlinear damage in a transmission tower structure. However, due to the complexity of the transmission tower structure, it is difficult to identify the nonlinear damage accurately by using traditional damage identification methods. To solve this problem effectively, a time domain damage identification method based on general expression for linear and nonlinear autoregressive model (GNAR model) and Itakura distance is proposed. To describe the stochastic characteristics of time series more concisely and accurately, the optimized structure of GNAR model was selected by the stochastic pruning algorithm based on greedy strategy. And Itakura distance was used as a damage indicator for nonlinear damage identification. The nonlinear damage experiment of three-story frame model in Los Alamos laboratory was used to verify the effectiveness of the proposed method, and this method was applied to the nonlinear damage identification experiment of a transmission tower steel frame model. In the transmission tower model experiment, two kinds of nonlinear damage types are considered: component breathing cracks and joint bolt loosening. The results show that the proposed nonlinear damage identification method can easily identify the nonlinear damage of the frame model and the transmission tower model effectively. The change of floor mass barely has effects on the damage identification results. The damage probability of the damaged stories calculated by the proposed method is significantly higher than that of the undamaged stories, so that it is helpful to find the location of the nonlinear damage source efficiently. And the proposed method is a damage identification method based on sub-structure story, which can identify the transmission tower model with two nonlinear damage sources at the same time.

show abstract

Section: Introductionmentioning

confidence: 99%

Nonlinear damage identification method of transmission tower structure based on general expression for linear and nonlinear autoregressive model and Itakura distance

Heng

Guo

2022

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…As energy issues have become increasingly prominent, it is very important to find ways to save energy, scientifically and rationally allocate power, improve the grid security and the reliability of power supply. The ongoing demand of electricity imposes power companies to estimate the state of network load and then produce voltage magnitudes and angles correspondingly [1], or detect substantial changes in the underlying processes and then make necessary adjustments in time [2]. One way of the state estimation is to obtain the load profiles through the load samples of customers or areas.…”

Section: Introductionmentioning

confidence: 99%

Variational Bayesian inference for the probabilistic model of power load

Dong

Wang

Zhao

2014

IET Generation, Transmission & Distribution

View full text Add to dashboard Cite

“…2012) with sixteen citations that refers to 11.76% of the citations, with ten citations, corresponding to 7.35% of the citations received,Machado, Costa and Marins (2009) andCosta et al (2015) with eight citations each, corresponding to 5.88% of the citations,Sitoe et al (2017) with six citations corresponding to 4.41% of the total citations, and finally,Balestrassi et al (2011),Rocha and Poppi (2011),Moraes et al (2014),Tôrres, Grangeiro Junior and Fragoso (2015), andSitoe et al (2016) with five citations each, which corresponds to 3.67% of the total citations.…”

mentioning

confidence: 99%

Systematic literature review of Brazilian research on multivariate control charts

Ueda

Rosa²,

Silva³

et al. 2021

GEPROS

View full text Add to dashboard Cite

Purpose – This paper aims to present a Systematic Literature Review (SLR) of studies in Brazil with applications of multivariate control charts indexed in journals on the Web of Science. Design/methodology/approach – The following steps were carried out: a detailed synthesis was performed on the general characteristics of the corpus, co-citation and collaboration networks analyzed; and a co-occurrence of terms in the text corpus was verified. A Systematic Literature Review was carried out using the protocols set out by Biolchini et al. (2007), Kitchenham (2004) and Tranfield, Denyer and Smart (2003). Papers were selected from the Web of Science database, and after applying filters, results for 29 articles were given to compose the corpus. Findings – A tendency was found for an increase in publications, along with more international research on the issue. The journal most used for publication was the Microchemical Journal. This analysis provided relevant authors for research in this area: Harold Hotelling, Douglas Montgomery, and John Frederick MacGregor. Important Brazilian researchers were highlighted who work mainly in the pharmaceutical and biodiesel industry. Originality/value – No articles were found that had carried out a Systematic Literature Review of Brazilian research on multivariate control charts. The main contributions to this manuscript related to an increase in scientific know-how in the area of multivariate and bibliometric analysis. Keywords - Multivariate Control Charts. Systematic literature review. Bibliometric analysis.

show abstract

A multivariate descriptor method for change-point detection in nonlinear time series

Cited by 9 publications

References 22 publications

Nonlinear damage identification method of transmission tower structure based on general expression for linear and nonlinear autoregressive model and Itakura distance

Nonlinear damage identification method of transmission tower structure based on general expression for linear and nonlinear autoregressive model and Itakura distance

Variational Bayesian inference for the probabilistic model of power load

Systematic literature review of Brazilian research on multivariate control charts

Contact Info

Product

Resources

About