Results 91 to 100 of about 6,478,030 (244)

Wear Measuring and Wear Modelling Based on Archard, ASTM, and Neural Network Models [PDF]

, 2015
The wear measuring and wear modelling are a fundamental issue in the industrial field, mainly correlated to the economy and safety. Therefore, there is a need to study the wear measurements and wear estimation.
Pislaru, Crinela, Shebani, Amer
core   +2 more sources

Application of Gradient Optimization Methods in Defining Neural Dynamics

Axioms
Applications of gradient method for nonlinear optimization in development of Gradient Neural Network (GNN) and Zhang Neural Network (ZNN) are investigated.
Predrag S. Stanimirović, Nataša Tešić, Dimitrios Gerontitis, Gradimir V. Milovanović, Milena J. Petrović, Vladimir L. Kazakovtsev, Vladislav Stasiuk   +6 more
doaj   +1 more source

A Q‐Learning Algorithm to Solve the Two‐Player Zero‐Sum Game Problem for Nonlinear Systems

International Journal of Adaptive Control and Signal Processing, Volume 39, Issue 3, Page 566-581, March 2025.
A Q‐learning algorithm to solve the two‐player zero‐sum game problem for nonlinear systems. ABSTRACT This paper deals with the two‐player zero‐sum game problem, which is a bounded L2$$ {L}_2 $$‐gain robust control problem. Finding an analytical solution to the complex Hamilton‐Jacobi‐Issacs (HJI) equation is a challenging task.
Afreen Islam, Anthony Siming Chen, Guido Herrmann   +2 more
wiley   +1 more source

Soft sensor modeling method and application based on TSECIT2FNN-LSTM

Scientific Reports
To address the issue of low accuracy in soft sensor modeling of key variables caused by multi-variable coupling and parameter sensitivity in complex processes, this paper introduces a TSK-type-based self-evolving compensatory interval type-2 fuzzy Long ...
Huangtao Dai, Taoyan Zhao, Jiangtao Cao, Ping Li   +3 more
doaj   +1 more source

Observer‐Based Adaptive Event‐Triggered Tracking Control for Fuzzy TS Systems With Premise Mismatch

International Journal of Adaptive Control and Signal Processing, EarlyView.
This paper presents an adaptive logistic event‐triggered observer‐based tracking controller for Takagi‐Sugeno fuzzy systems under constrained inputs and network delays. Leveraging a hybrid LMI and Secretary Bird Optimization approach, this strategy significantly minimizes communication overhead and computational burden while ensuring optimal reference ...
Oussama Djadane, Salama Makni, Mourad Kchaou, Ahmed El Hajjaji   +3 more
wiley   +1 more source

A predictive model for post-thoracoscopic surgery pulmonary complications based on the PBNN algorithm

Scientific Reports
We constructed an early prediction model for postoperative pulmonary complications after thoracoscopic surgery using machine learning and deep learning algorithms.
Cheng-Mao Zhou, Qiong Xue, HuiJuan Li, Jian-Jun Yang, Yu Zhu   +4 more
doaj   +1 more source

A Numerical–Experimental Approach for Multi‐Matrix Fiber‐Reinforced Plastics Characterization Using Finite Element Model Updating

Advanced Engineering Materials, EarlyView.
A numerical–experimental framework is developed for characterizing multi‐matrix fiber‐reinforced polymers (MM‐FRPs) combining epoxy and polyurethane matrices. Harmonic bending tests are integrated with finite element model updating (FEMU) to simultaneously identify elastic and viscoelastic material parameters.
Rodrigo M. Dartora, Tales V. Lisbôa, Axel Spickenheuer, Rogério J. Marczak, Jakson M. Vassoler   +4 more
wiley   +1 more source

Gradient Routing: Masking Gradients to Localize Computation in Neural Networks

CoRR
Neural networks are trained primarily based on their inputs and outputs, without regard for their internal mechanisms. These neglected mechanisms determine properties that are critical for safety, like (i) transparency; (ii) the absence of sensitive information or harmful capabilities; and (iii) reliable generalization of goals beyond the training ...
Alex Cloud, Jacob Goldman-Wetzler, Evzen Wybitul, Joseph Miller, Alexander Matt Turner   +4 more
openaire   +3 more sources

Investigation of Resonance Characteristics of More Than 10 000 Metal‐Coated Silicon MEMS Cantilevers Using Machine Learning

Advanced Engineering Materials, EarlyView.
More than 10 000 metal‐coated silicon MEMS cantilevers are fabricated and characterized to build a large‐scale experimental dataset spanning multiple vibrational modes. Machine learning algorithms are benchmarked to predict resonance frequency and quality factor, with ensemble based models achieving accuracy approaching experimental uncertainty.
Sina Zare Pakzad, Saurabh Thorat, Andre Loch Gesing, Dominik Huber, Christopher Zellner, Patrick Egger, Georg Pfusterschmied, Ulrich Schmid, Michael Schneider   +8 more
wiley   +1 more source

Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield [PDF]

A particular type of “Artificial neural network (ANN)â€, viz. Multilayered feedforward artificial neural network (MLFANN) has been described. To train such a network, two types of learning algorithms, namely Gradient descent algorithm (GDA) and ...
Prajneshu, Singh, Rama Krishna
core