Markov chain-based mass estimation method for loose part monitoring system and its performance

Shin, Sung Hwan; Park, Jin Ho; Yoon, Doo Byung; Han, Soon Woo; Ting, Kang

doi:10.1016/j.net.2017.05.005

Cited by 5 publications

(1 citation statement)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Seong-In Moon, To Kang, and Soon-Woo Han [7] obtained the impact parameters by establishing the impact finite element model of the loose part and used the convolutional neural network to establish the impact parameter prediction model of the loose part mass estimation model to realize the mass estimation. Sung-Hwan Shin, Jin-Ho Park, Doo-Byung Yoon, Soon-Woo Han, and To Kang [8] proposed a mass estimation method based on the Markov chain and verified the method in a 1/8 scaled pressure vessel model. Seong-In Moon, To Kang, and Soon-Woo Han [7] simulated the flexural wave propagation process through a finite element model and established a metal ball signal map for mass estimation.…”

Section: Introductionmentioning

confidence: 99%

Mass estimation method of loose parts based on function model

Lin

Tan

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

The nuclear main pump has a complex structure and contains a large number of components. With the continuous flow of the primary circuit coolant, there is a risk of loosening and falling off of the components in the reactor. The existence of loose parts in the reactor makes the reactor operation a safety hazard. Accurate mass estimation of the loose parts is conductive to quickly judge the degree of the failure of loose parts, provide effective suggestions for the subsequent maintenance of the reactor and ensure the safety of reactor operation. The existing mass estimation methods have problems of large errors and poor consistency. This article proposes a method for estimating the mass of loose parts by establishing a functional relationship model based on signal characteristic value. The characteristic value of the signal is constructed by extracting the Root Mean Square value and the main frequency of the shock signal, and then the functional relationship between the quality of the loose part and the characteristic value of the signal is established, which is used to estimate the mass of the loose part. The experimental results show that the method proposed in this paper has the characteristics of small estimation error and good consistency, which can meet the needs of practical engineering applications.

show abstract

Section: Introductionmentioning

confidence: 99%