Structural damage identification using the similarity measure of the cloud model and response surface-based model updating considering the uncertainty

Luo, Yongpeng; Zheng, Jin-ling; Ye, Meng; Wang, Lin-kun; Guo, Xu; Liu, Jing-liang

doi:10.1007/s13349-022-00598-w

Cited by 6 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To this end, the concept of Kullback–Leibler divergence (KLD) is introduced on the basis of the MCM to better quantify severe structural damage. 36,37 For two CMs, C 1 and C 2 , the KLD is defined as followswhere c 1 ( x ) and c 2 ( x ) are the density functions of two CMs C 1 and C 2, respectively.…”

Section: Unsupervised Structural Damage Detection Methods Based On Ga...mentioning

confidence: 99%

Unsupervised structural damage detection based on an improved generative adversarial network and cloud model

Luo

Guo

Wang

et al. 2023

Journal of Low Frequency Noise, Vibration and Active Control

Self Cite

View full text Add to dashboard Cite

The measurements derived from damaged conditions are difficult to acquire in actual structures, which limits the applicability of supervised damage detection methods. In this study, an unsupervised damage detection method that leverages an improved generative adversarial network (IGAN) and cloud model (CM) is proposed. This method only needs the data in the healthy state of the structure for model training, which can solve the above problems. Firstly, an IGAN model is established, which uses the encoder-decoder-encoder generative network to encode, reconstruct and re-encode the structural response in healthy state. The essential features hidden in complex data are learned by minimizing the distance between the real response and the reconstructed response, and the distance between the latent vectors obtained after two different encodings. During the test phase, when unknown state data is input into the model, the differences of the latent features of the two different codes can be used to preliminarily judge whether the structure is damaged. In addition, CM theory is used to further quantify structural damage and solve the problem of damage misjudgment caused by measurement noise, model parameters, feature selection, and other uncertain factors. The effectiveness of the proposed damage detection method is verified by Phase I IASC-ASCE benchmark structure and a bridge health monitoring benchmark model. The results prove that the proposed method can accurately detect the damage that has occurred.

show abstract

Section: Unsupervised Structural Damage Detection Methods Based On Ga...mentioning

confidence: 99%

Unsupervised structural damage detection based on an improved generative adversarial network and cloud model

Luo

Guo

Wang

et al. 2023

Journal of Low Frequency Noise, Vibration and Active Control

Self Cite

View full text Add to dashboard Cite

show abstract

“…After several years of exploration and development, the cloud model has become completer and more universal ( Wang, Li & Yang, 2019 ). The cloud model has been successfully applied and developed in many fields, such as in the statistical representation of engineering parameters ( Chen et al, 2020 ; Luo et al, 2022 ), system evaluation and decision-making ( Tong & Srivastava, 2022 ; Su & Yu, 2020 ; Wu et al, 2020 ), data mining ( Shehab, Badawy & Ali, 2022 ; Zarinbal, Zarandi & Turksen, 2014 ), image processing ( Li, Li & Du, 2018 ; Tversky & Kahneman, 1992 ), and decision making problems ( Yu et al, 2021 ; Wang, Huang & Cai, 2020 ; Zhou, Chen & Ming, 2022 ). It should be noted that the practical applications of cloud model theory (such as data mining and decision analysis) all involve the similarity measurement ( Zhang, Zhao & Li, 2004 ).…”

Section: Introductionmentioning

confidence: 99%

“…Cloud models express the uncertainty of data intuitively and provide a method with which to analyze qualitative concepts similarly to that of human cognition. The randomness and fuzziness of the cloud model make it more advantageous in dealing with uncertain problems such as data clustering ( Sheng et al, 2019 ), data classification ( Wang et al, 2021 ), and similarity searches ( Luo et al, 2022 ). Cloud models have been developed and improved over time, resulting in the development of various similarity measurement methods.…”

Section: Introductionmentioning

confidence: 99%

“… Zhang et al (2021) put forward a new similarity measurement method (MSCM) for multi-dimensional cloud models based on fuzzy similarity principle. Luo et al (2022) proposed a new structural damage identification method (MCM) based on a cloud model similarity measurement of response surface model updating. A brief summary is given in Table 1 to illustrate the shortcomings of the existing methods.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A novel similarity measurement for triangular cloud models based on dual consideration of shape and distance

Yang

Han

Wan

et al. 2023

PeerJ Computer Science

View full text Add to dashboard Cite

It is important to be able to measure the similarity between two uncertain concepts for many real-life AI applications, such as image retrieval, collaborative filtering, risk assessment, and data clustering. Cloud models are important cognitive computing models that show promise in measuring the similarity of uncertain concepts. Here, we aim to address the shortcomings of existing cloud model similarity measurement algorithms, such as poor discrimination ability and unstable measurement results. We propose an EPTCM algorithm based on the triangular fuzzy number EW-type closeness and cloud drop variance, considering the shape and distance similarities of existing cloud models. The experimental results show that the EPTCM algorithm has good recognition and classification accuracy and is more accurate than the existing Likeness comparing method (LICM), overlap-based expectation curve (OECM), fuzzy distance-based similarity (FDCM) and multidimensional similarity cloud model (MSCM) methods. The experimental results also demonstrate that the EPTCM algorithm has successfully overcome the shortcomings of existing algorithms. In summary, the EPTCM method proposed here is effective and feasible to implement.

show abstract

A novel similarity algorithm for triangular cloud models based on exponential closeness and cloud drop variance

Yang,

Han,

Wan

et al. 2024

Complex Intell. Syst.

View full text Add to dashboard Cite

Cloud model similarity algorithm is an important part of cloud modelling theory. Most of the existing cloud model similarity algorithms suffer from poor discriminability, poor classification, unstable results, and low time efficiency. In this paper, a new similarity algorithm is proposed that considers the triangular cloud model distance and shape. First, according to the $${{D}}_{\text{T}}$$ D T distance formula, a new exponential closeness measure is defined, with which the distance similarity of cloud models is characterized. Then, the shape similarity is calculated according to the variance of the cloud model cloud drops. Finally, the two similarities are synthesized to define a similarity algorithm for determining the distance from the $${{D}}_{\text{T}}$$ D T distance formula and shape based on the triangular cloud model (DDTSTCM). In this paper, discriminability, stability, efficiency and theoretical interpretability are taken as the evaluation indices. Equipment security system capability evaluation experiment, cloud model differentiation simulation experiment and time series classification accuracy experiment are set up to verify the effectiveness of the algorithm in terms of the four above aspects. The experimental results show that DDTSTCM has good differentiation and excellent classification effects. In the classification experiment for the time series, the average classification accuracy of DDTSTCM reaches 91.78%, which is at least 2.78% higher than those of the other seven commonly used algorithms. The CPU running efficiency of DDTSTCM is also extremely high, and the average CPU running time of group training is always on the order of milliseconds, which effectively reduces the time cost. Finally, a case study is conducted to analyse a risk assessment problem for China’s island microgrid industry, and the evaluation results based on DDTSTCM are in line with human cognition and have good value for engineering applications. Graphical abstract

show abstract

Structural damage identification using the similarity measure of the cloud model and response surface-based model updating considering the uncertainty

Cited by 6 publications

References 21 publications

Unsupervised structural damage detection based on an improved generative adversarial network and cloud model

Unsupervised structural damage detection based on an improved generative adversarial network and cloud model

A novel similarity measurement for triangular cloud models based on dual consideration of shape and distance

A novel similarity algorithm for triangular cloud models based on exponential closeness and cloud drop variance

Contact Info

Product

Resources

About