Investigation of Nonlinear Vibrational Analysis of Circular Sector Oscillator by Using Cascade Learning

Khan, Naveed Ahmad; Sulaiman, Muhammad; Seidu, Jamel; Alshammari, Fahad Sameer

doi:10.1155/2022/1898124

Cited by 3 publications

(1 citation statement)

References 51 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Some possible applications of machine learning algorithms include the transition of disturbances due to changes in braking and acceleration in traffic flows 25 , heat transfer in a micropolar fluid with isothermal and isoflux boundary conditions 26 , stiffness solutions for polytropic. gas spheres and electric circuit models 27 , linearization of circular sector oscillator inelastic vibration analysis 28 and inclined longitudinal porous trapezoidal and rectangular trapezoidal fin heat transfer analysis.…”

Section: Introductionmentioning

confidence: 99%

Machine learning-based prediction of heat transfer performance in annular fins with functionally graded materials

Sulaiman,

Khalaf,

Khan

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

This paper presents a study investigating the performance of functionally graded material (FGM) annular fins in heat transfer applications. An annular fin is a circular or annular structure used to improve heat transfer in various systems such as heat exchangers, electronic cooling systems, and power generation equipment. The main objective of this study is to analyze the efficiency of the ring fin in terms of heat transfer and temperature distribution. The fin surfaces are exposed to convection and radiation to dissipate heat. A supervised machine learning method was used to study the heat transfer characteristics and temperature distribution in the annular fin. In particular, a feedback architecture with the BFGS Quasi-Newton training algorithm (trainbfg) was used to analyze the solutions of the mathematical model governing the problem. This approach allows an in-depth study of the performance of fins, taking into account various physical parameters that affect its performance. To ensure the accuracy of the obtained solutions, a comparative analysis was performed using guided machine learning. The results were compared with those obtained by conventional methods such as the homotopy perturbation method, the finite difference method, and the Runge–Kutta method. In addition, a thorough statistical analysis was performed to confirm the reliability of the solutions. The results of this study provide valuable information on the behavior and performance of annular fins made from functionally graded materials. These findings contribute to the design and optimization of heat transfer systems, enabling better heat management and efficient use of available space.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine learning-based prediction of heat transfer performance in annular fins with functionally graded materials

Sulaiman,

Khalaf,

Khan

et al. 2024

Sci Rep

Self Cite

View full text Add to dashboard Cite

show abstract

An improved water strider algorithm for solving the inverse Burgers Huxley equation

Mazraeh,

Parand,

Hosseinzadeh

et al. 2024

Sci Rep

View full text Add to dashboard Cite

In this paper, we introduce an improved water strider algorithm designed to solve the inverse form of the Burgers-Huxley equation, a nonlinear partial differential equation. Additionally, we propose a physics-informed neural network to address the same inverse problem. To demonstrate the effectiveness of the new algorithm and conduct a comparative analysis, we compare the results obtained using the improved water strider algorithm against those derived from the original water strider algorithm, a genetic algorithm, and a physics-informed neural network with three hidden layers. Solving the inverse form of nonlinear partial differential equations is crucial in many scientific and engineering applications, as it allows us to infer unknown parameters or initial conditions from observed data. This process is often challenging due to the complexity and nonlinearity of the equations involved. Meta-heuristic algorithms and neural networks have proven to be effective tools in addressing these challenges. The numerical results affirm the efficiency of our proposed method in solving the inverse form of the Burgers-Huxley equation. The best results were obtained using the improved water strider algorithm and the physics-informed neural network with 10,000 iterations. With this iteration count, the mean absolute error of these algorithms is . Additionally, the improved water strider algorithm is nearly four times faster than the physics-informed neural network. All algorithms were executed on a computing system equipped with an Intel(R) Core(TM) i7-7500U processor and 12.00 GB of RAM, and were implemented in MATLAB.

show abstract

A Complete Deep Support Vector Data Description for One Class Learning

Jiang,

Yang,

Zhao

2023

IEEE Access

View full text Add to dashboard Cite

In recent years, Deep Support Vector Data Description (Deep SVDD) has emerged as a leading method in the field of anomaly detection. However, inaccuracies in parameter solving have been identified as a limitation of this approach, which negatively affects its accuracy and efficiency. To address this issue, we propose a new method, called Complete Deep Support Vector Data Description (CD-SVDD). Our CD-SVDD is constructed with a traditional deep neural network and utilizes a modified SVDD as its last layer. Its parameters are solved by an alternate iteration algorithm that ensures both high precision and fast convergence of solutions. By keeping the network weights fixed, we solve the center and radius of the modified SVDD based on its convex dual optimization problem. We then update the parameters of the neural network by backpropagation. This approach enables us to maintain the ν-property found in shallow SVDD, which is beneficial for parameter selection and model interpretability. To evaluate the performance of CD-SVDD, we conducted extensive numerical experiments with five existing methods on two image datasets, CIFAR-10 and CIFAR-100, as well as five recorded benchmark datasets. Our results demonstrate that CD-SVDD achieves superior accuracy and efficiency in the detection of anomalies.

show abstract

Investigation of Nonlinear Vibrational Analysis of Circular Sector Oscillator by Using Cascade Learning

Cited by 3 publications

References 51 publications

Machine learning-based prediction of heat transfer performance in annular fins with functionally graded materials

Machine learning-based prediction of heat transfer performance in annular fins with functionally graded materials

An improved water strider algorithm for solving the inverse Burgers Huxley equation

A Complete Deep Support Vector Data Description for One Class Learning

Contact Info

Product

Resources

About