Application of an Artificial Neural Network in the Modelling of Heat Curing Effects on the Strength of Adhesive Joints at Elevated Temperature with Imprecise Adhesive Mix Ratios

Szabelski, Jakub; Karpiński, Robert; Machrowska, Anna

doi:10.3390/ma15030721

Cited by 19 publications

(16 citation statements)

References 51 publications

(45 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…AutoML is also available for modelling and prediction problems (Machrowska et al, 2020), e.g. using LSTM method (Szabelski, Karpiński & Machrowska, 2022). In this paper the text classification will performed, but classification of images (Kłosowski et al, 2021) is also available with such toolkits.…”

Section: The Proposed Solutionmentioning

confidence: 99%

Detection of Source Code in Internet Texts Using Automatically Generated Machine Learning Models

Badurowicz

2022

acs

View full text Add to dashboard Cite

In the paper, the authors are presenting the outcome of web scraping software allowing for the automated classification of source code. The software system was prepared for a discussion forum for software developers to find fragments of source code that were published without marking them as code snippets. The analyzer software is using a Machine Learning binary classification model for differentiating between a programming language source code and highly technical text about software. The analyzer model was prepared using the AutoML subsystem without human intervention and fine-tuning and its accuracy in a described problem exceeds 95%. The analyzer based on the automatically generated model has been deployed and after the first year of continuous operation, its False Positive Rate is less than 3%. The similar process may be introduced in document management in software development process, where automatic tagging and search for code or pseudo-code may be useful for archiving purposes.

show abstract

Section: The Proposed Solutionmentioning

confidence: 99%

Detection of Source Code in Internet Texts Using Automatically Generated Machine Learning Models

Badurowicz

2022

acs

View full text Add to dashboard Cite

show abstract

“…By employing the computational prowess of numerical modeling methods [6][7][8][9] (e.g., Finite Element Method (FEM) [10][11][12][13][14] or Boundary Element Method (BEM) [15][16][17] or machine learning [18][19][20]) in conjunction with experimental research [21][22][23][24] we have developed a detailed understanding of the actual behavior of engineering structures and their optimization. What has emerged from the extensive laboratory research [25,26], theoretical analyzes [27][28][29] and FEM simulations [30][31][32] conducted to date on the subject is that the pullout anchor strength, also referred to as its load-carrying capacity, is affected by a number of other factors, such as mechanical parameters of concrete (e.g., [33][34][35][36]), effective embedment depth [37], the breakout anchor design [38,39], the anchor head geometry [40][41][42][43][44], or concrete reinforcement [45][46][47][48]…”

Section: Introductionmentioning

confidence: 99%

The Effect of Undercut Anchor Diameter on the Rock Failure Cone Area in Pullout Tests

Jonak¹,

Karpiński²,

Wójcik³

et al. 2022

Adv. Sci. Technol. Res. J.

View full text Add to dashboard Cite

The numerical analysis was conducted using the FEM ABAQUS software to establish the impact of various undercut anchor diameters on the rock breakout cone formation. The central focus of the investigations was on the rock breakout prism, which tends to be approximated to a cone or a quadrilateral pyramid, including its characteristic parameter, the angle of failure cone α. Assuming that the embedment depth and the undercut anchor head angle were constant for the considered range of anchor head diameters, it remains unclear, however, precisely how the anchor head diameter affects the value of the failure cone angle, and thus the surface area of the full breakout prism. This conclusion stands in confirmation of our former considerations regarding the impact of the anchor head angle on the size of the breakout surface. Furthermore, it is supported by the results obtained from the mechanical model simulation of the anchor-rock system, where the anchor head angle and the effective embedment depth were determined as significant factors affecting the assumed rock breakout failure. The underlying aspect of the reported investigation was to evaluate the effectiveness of the non-conventional rock breakout technology performed with an undercut anchor, whose primary factors were both the pullout force and the assumed volume of the rock cone.

show abstract

“…Conducting a large number of destructive experimental tests is often not possible due to time and economic constraints. The methods for solving such a problem can include the implementation of mathematical modelling [ 21 , 22 ], computer methods such as the finite element method (FEM) [ 23 , 24 , 25 , 26 , 27 , 28 ], the boundary element method (BEM) [ 29 , 30 ], the application of predictive models [ 31 , 32 , 33 ], machine learning methods [ 33 , 34 , 35 , 36 ] and analytical data analysis [ 37 , 38 ]. The models developed by this approach allow the most important relationships between individual parameters and mechanical properties to be determined.…”

Section: Introductionmentioning

confidence: 99%

Adhesive Joint Degradation Due to Hardener-to-Epoxy Ratio Inaccuracy under Varying Curing and Thermal Operating Conditions

et al. 2022

Self Cite

View full text Add to dashboard Cite

This paper presents the results of an experimental study of adhesive joint strength with consideration of the inaccuracy of the hardener dosage, in the context of evaluating the degradation of joints when used either at ambient or elevated temperatures. The butt joint strength characteristics were assessed for two types of adhesives—rigid and flexible—and two curing scenarios—with and without heat curing. An excess hardener was shown to be significantly more unfavourable than its deficiency, which can ultimately be considered as a recommendation for forming epoxy adhesive joint assemblies. In order to fully understand the relationship between the analysed mechanical properties of the material and the influence of component ratio excesses and heating, a process of fitting basic mathematical models to the obtained experimental data was also performed.

show abstract

Application of an Artificial Neural Network in the Modelling of Heat Curing Effects on the Strength of Adhesive Joints at Elevated Temperature with Imprecise Adhesive Mix Ratios

Cited by 19 publications

References 51 publications

Detection of Source Code in Internet Texts Using Automatically Generated Machine Learning Models

Detection of Source Code in Internet Texts Using Automatically Generated Machine Learning Models

The Effect of Undercut Anchor Diameter on the Rock Failure Cone Area in Pullout Tests

Adhesive Joint Degradation Due to Hardener-to-Epoxy Ratio Inaccuracy under Varying Curing and Thermal Operating Conditions

Contact Info

Product

Resources

About