Unknown impact force localisation and reconstruction in experimental plate structure using time-series analysis and pattern recognition

Qiu, Bingsen; Zhang, Meng; Xu, Liang; Qu, Xianqiang; Fu-shan, Tong

doi:10.1016/j.ijmecsci.2019.105231

Cited by 32 publications

(18 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…As there are some secondary impulses after the main impulse, T3 is introduced to signify the end time of the secondary impulses. Refer to the paper of Qiu et al 10 ; if the MAE of positions is greater than √2/2 times the side length of the grid, it can be considered as a misjudgment, and M means the amount of misjudgment samples.…”

Section: Proposed Feature Learning-based Methodsmentioning

confidence: 99%

“…6,7 Many indirect identification methods have been used to solve these two problems, which can generally be divided into frequencydomain methods and time-domain methods. [8][9][10] Generally, there are two types of frequency-domain methods: one is the frequency response function matrix inversion method and the other is the modal coordinate transformation method. 9 Hollandsworth et al 11 integrated the acceleration response value to obtain the velocity, and then the velocity is substituted into the frequency response function matrix for impact load reconstruction.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A feature learning-based method for impact load reconstruction and localization of the plate-rib assembled structure

Chen

Guo

Duan

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

Impact load is the load that machines frequently experienced in engineering applications. Its time-history reconstruction and localization are crucial for structural health monitoring and reliability analysis. However, when identifying random impact loads, conventional inversion methods usually do not perform well because of complex formula derivation, infeasibility of nonlinear structure, and ill-posed problem. Deep learning methods have great ability of feature learning and nonlinear representation as well as comprehensive regularization mechanism. Therefore, a new feature learning-based method is proposed to conduct impact load reconstruction and localization. The proposed method mainly includes two parts. The first part is designed to reconstruct impact load, named convolutional-recurrent encoder–decoder neural network (ED-CRNN). The other part is constructed to localize impact load, called deep convolutional-recurrent neural network (DCRNN). The ED-CRNN utilizes the one-dimensional (1-D) convolutional encoder–decoder to obtain low-dimension feature representations of input signals. Two long short-term memory (LSTM) layers and a bidirectional LSTM (BiLSTM) layer are uniformly distributed in this network to learn the relationship between input features and the output load in time steps. The DCRNN is constructed mainly by two 1-D convolutional neural network (CNN) layers and two BiLSTM layers to learn high-hidden-level spatial as well as temporal features. The fully connected layers are placed at the end to localize an impact load. The effectiveness of the proposed method was demonstrated by two numerical studies and two experiments. The results reveal that the proposed method has the ability to accurately and quickly reconstruct and localize the impact load of complex assembled structure. Furthermore, the performance of the DCRNN is related to the number of sensors and the architecture of the network. Meanwhile, the strategy of alternating layout is proposed to reduce the number of training locations.

show abstract

Section: Proposed Feature Learning-based Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A feature learning-based method for impact load reconstruction and localization of the plate-rib assembled structure

Chen

Guo

Duan

et al. 2021

Structural Health Monitoring

View full text Add to dashboard Cite

show abstract

“…Kuvvet tanımlama esas olarak hasarla doğrudan ilişkili anlık, şiddetli (itki) kuvvetlerin konumu tespitinde [27,28] önem arz etmektedir. Ayrıca, etki eden kuvvetin şekil ve büyüklüğünün de tahmini de üzerinde araştırmaların devam ettiği önemli bir konudur [29,30]. Fakat çevresel titreşimlere has kuvvet konumunun tespitine yönelik yazında bir çalışmaya rastlanmamıştır.…”

Section: Kuvvet Tanımlamaunclassified

Kiriş Benzeri Sistemler için Kuvvet Tanı ve Sistem Tanımlama için Yeni Bir Yaklaşım: Mod Tarif

TUFAN¹

2021

El-Cezeri Fen Ve Mühendislik Dergisi

View full text Add to dashboard Cite

Yapı sağlığı izleme yöntemleri yapının işleyişi sırasında çevresel titreşimlere maruz iken, sistemi tanımayı ve tanımladığı sistemde mevcut hasarı tespit etmeyi hedefler. Farklı iki noktadan etkiyen kuvvet konumuna göre mod değişkenlerinin hesaplanmayı hedefleyen mod tarif yöntemi, sistem tanımlama adımında modal plan yöntemini kullanır. Modal planlar bu çalışmada serbest titreşimde uygulanan bir yöntem ile üretilmiştir. Serbest titreşim altında sistem tanımlaması için kullanılan bir yöntem çevresel titreşimler altındaki sistem için de kullanılabileceği bu çalışmada gösterilmiştir. Çevresel titreşim analizlerinde yapıya etkiyen kuvvetler ölçülmez. Fakat kuvvetin hangi noktalardan yapıya etki ettiğini bilmek hasar tespiti için önemli olabilecek bir bilgidir. Çünkü bu bölgelere yakın konumlarda hasar oluşma ihtimali daha yüksektir. Kiriş benzeri sistemlerde modal planlar kullanılarak, kuvvet ölçümü yapmadan kuvvet konumunun tahmini çevresel titreşimler altında yapılabileceği gösterilmiştir. Sistem tanımlama adımındaki muhtemel hatanın en aza indirilebilmesi için kuvvet etkime konumunun çözümleme yapılan serbestlik derecesine yakın olmasının ve hedef frekans aralığına göre veri örnekleme sıklığının belirlenmesinin önemi vurgulanmıştır.

show abstract

“…Qiu et al [ 42 ] proposed a method to quickly acquire the positions of random impacts by using the cosine similarity of the structural stress responses, which significantly reduced the computational effort and improved the localisation accuracy. Furthermore, the PRMCSM method was verified by a model experiment and a new similarity metric index was presented with the same properties as the cosine similarity [ 43 ].…”

Section: Introductionmentioning

confidence: 99%

“…In this study, an innovative hybrid algorithm is proposed to localise random unknown impact forces. To localise impact forces rapidly, the feasibility of the PRMCSM method has been demonstrated by numerical simulation [ 42 ] and model experiment [ 43 ]. However, according to the experimental data, the localisation of the impact forces is not completely satisfactory.…”

Section: Introductionmentioning

confidence: 99%

Experimental Research on a Hybrid Algorithm for Localisation and Reconstruction of the Impact Force Applied to a Rectangular Steel Plate Structure

Qiu

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Impact force is the most common form of load which acts on engineering structures and presents a great hidden risk to the healthy operation of machinery. Therefore, the identification or monitoring of impact forces is a significant issue in structural health monitoring. The conventional optimisation scheme based on inversion techniques requires a significant amount of time to identify random impact forces (impact force localisation and time history reconstruction) and is not suitable for engineering applications. Recently, a pattern recognition method combined with the similarity metric, PRMCSM, has been proposed, which exhibits rapidity in practical engineering applications. This study proposes a novel scheme for identifying unknown random impact forces which hybridises two existing methods and combines the advantages of both. The experimental results indicate that the localisation accuracy of the proposed algorithm (100%) is higher than that of PRMCSM (92%), and the calculation time of the hybrid algorithm (179 s) for 25 validation cases is approximately one nineteenth of the traditional optimisation strategy (3446 s).

show abstract

Unknown impact force localisation and reconstruction in experimental plate structure using time-series analysis and pattern recognition

Cited by 32 publications

References 34 publications

A feature learning-based method for impact load reconstruction and localization of the plate-rib assembled structure

A feature learning-based method for impact load reconstruction and localization of the plate-rib assembled structure

Kiriş Benzeri Sistemler için Kuvvet Tanı ve Sistem Tanımlama için Yeni Bir Yaklaşım: Mod Tarif

Experimental Research on a Hybrid Algorithm for Localisation and Reconstruction of the Impact Force Applied to a Rectangular Steel Plate Structure

Contact Info

Product

Resources

About