Data mining in sloshing experiment database and application of neural network for extreme load prediction

Ahn, Yangjun; Kim, Yonghwan

doi:10.1016/j.marstruc.2021.103074

Cited by 18 publications

(5 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Then, using neural networks, their training and prediction of variable values is performed [5,14]. In the course of training, the error obtained on the training set is calculated and compared to the error calculated for the control set [15,16] and the model is adjusted.…”

Section: Models and Methodsmentioning

confidence: 99%

“…However, if there is a need for in-depth data analysis, then adaptive, self-adaptive models need to be developed within the technology KDD (Knowledge Discovery in Databases) [3]. This technology uses the techniques of Data Mining [4,5] that enable the transformation of data into knowledge, the identification of hidden patterns in the large volumes of data contained in the data warehouse, and the interpretation of the data in a way that is understandable to the decision maker. Implementing methods Data Mining The use of these two approaches to analyze the causes of defects is obviously maximized by the combined use of these two approaches.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Data mining and forecasting of pavement strength depending on the composition of asphalt concrete mix

Vasiliev

Николаев²,

Fineeva³

et al. 2023

E3S Web Conf.

View full text Add to dashboard Cite

The article substantiates the need for widespread introduction of computer technology and information systems in the mix production process at ACF and their quality control, which is determined by the presence of a significant number of control objects, a large array of monitored indicators, high labor and material costs of testing, low efficiency and quality of processing complex multidimensional data. It is proposed to use Data Mining methods for intelligent data analysis and prediction of pavement durability depending on the composition of asphalt mix which enable to solve the tasks of classification, regression, clustering and forecasting using artificial intelligence methods. The algorithm of intellectual data analysis and prediction of durability of the mix depending on its composition is offered and the actions at each its stage, using additional methods of data analysis, are described. The example of real raw data processing obtained from the quality control laboratory of one of the asphalt plants using Data Mining tools of STATISTICA package according to the developed algorithm is given. The prospects of using modern data processing technologies in the field of asphalt concrete quality control are evaluated. It is shown that to assess the quality of the mix and pavement durability, it is necessary to move to complex quality indicators, taking into account pavement operating conditions.

show abstract

Section: Models and Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Data mining and forecasting of pavement strength depending on the composition of asphalt concrete mix

Vasiliev

Николаев²,

Fineeva³

et al. 2023

E3S Web Conf.

View full text Add to dashboard Cite

show abstract

“…Refs. [22,23] introduced the use of artificial neural network for real-time prediction of the sloshing loads in cargo containers. Considering the black box nature of the system under consideration, input-output data from high-fidelity numerical simulations (CFD) or experiments with varying frequencies and amplitudes are likely to be the most useful for implementing this technique.…”

Section: Introductionmentioning

confidence: 99%

Experimental Validation of Neural-Network-Based Nonlinear Reduced-Order Model for Vertical Sloshing

Pizzoli

Saltari

Coppotelli

et al. 2022

AIAA SCITECH 2022 Forum

View full text Add to dashboard Cite

In this paper, a nonlinear reduced order model based on neural networks is introduced in order to model vertical sloshing for use in fluid-structure interaction simulations. A box partially filled with water, representative of a wing tank, is first tested to identify a neural network model and then attached to a cantilever beam to test the effectiveness of the neural network in predicting the sloshing forces when coupled with the structure. The experimental set-up is equipped with accelerometers and load cells at the interface between the tank and an electrodynamic shaker, which provides vertical acceleration to the tank. Accelerations and interface forces measured during the experimental tests are employed to identify a recurrent network able to return the vertical sloshing forces when the tank is set on vertical motion. The identified model is then experimentally tested and assessed by its integration on the tip of a cantilever beam. The free response of the experimental setup are compared with those obtained by simulating an equivalent virtual model in which the identified reduced-order model is integrated to account for the effects of vertical sloshing.

show abstract

“…The objective of the present research activity is the achievement of sloshing simulations inside ship LNG tanks characterized by 3-hours real-time duration with realistic severe sea-state forcing. To this aim the tank model of Hyundai Heavy has been adopted and the experimental campaigns performed at Seoul National University (see Ahn (2019) and further studies in Kim et al (2017); Ahn et al (2019); Ahn and Kim (2021)) has been taken as reference. The numerical model adopted is an enhanced Smoothed Particle Hydrodynamics (SPH) model described in section 4.1.…”

Section: Introductionmentioning

confidence: 99%

SPH method for long-time simulations of sloshing flows in LNG tanks

Pilloton

Bardazzi

Colagrossi

et al. 2022

European Journal of Mechanics - B/Fluids

View full text Add to dashboard Cite

Data mining in sloshing experiment database and application of neural network for extreme load prediction

Cited by 18 publications

References 11 publications

Data mining and forecasting of pavement strength depending on the composition of asphalt concrete mix

Data mining and forecasting of pavement strength depending on the composition of asphalt concrete mix

Experimental Validation of Neural-Network-Based Nonlinear Reduced-Order Model for Vertical Sloshing

SPH method for long-time simulations of sloshing flows in LNG tanks

Contact Info

Product

Resources

About