1-20 of 116 Search Results for

neural networks

Follow your search
Access your saved searches in your account

Would you like to receive an alert when new items match your search?
Close Modal
Sort by
Image
Published: 01 December 2009
Fig. 1 Schematic models of artificial neural networks for simulation and prediction of various correlations in titanium alloys. (a) Time-temperature transformation (TTT) diagrams. (b) Mechanical properties of conventional titanium alloys. (c) Fatigue stress life diagrams. (d) Mechanical More
Series: ASM Handbook
Volume: 22A
Publisher: ASM International
Published: 01 December 2009
DOI: 10.31399/asm.hb.v22a.a0005416
EISBN: 978-1-62708-196-2
... Abstract Neural networks permit the discovery of fundamental relationships and quantitative structure within vast arrays of ill-understood data. This article provides an overview of neural network modeling method, describing its overfitting nature. It discusses the use of neural networks...
Series: ASM Handbook
Volume: 22A
Publisher: ASM International
Published: 01 December 2009
DOI: 10.31399/asm.hb.v22a.a0005407
EISBN: 978-1-62708-196-2
... Abstract Neural-network (NN) modeling is most suitable for simulations of correlations that are hard to describe or cannot be accurately predicted by physical models. This article describes the principles and procedures of NN modeling. It discusses the use of NN modeling in general organization...
Image
Published: 01 January 2006
Fig. 15 Structure of a neural network More
Image
Published: 31 December 2017
Fig. 44 (a) Illustration of a three-layered neural network for draft prediction for chisel plows. (b) Relationship between measured and neural network predicted draft. Adapted from Ref 81 More
Image
Published: 01 December 2009
Fig. 7 Comparison of the predictions of a neural-network model (central curve) with experimental data that were not included in the creation of the model. The modeling uncertainty is indicated by the upper and lower error bounds (broken lines). Source: Ref 6 , 8 More
Image
Published: 01 January 1993
Fig. 5 Neural network system for automated welding. (a) User interface of WELDBEAD neural network weld model for a GTAW weld in thin-section stainless steel. (b) Macrograph of the resulting test weld corresponding to the prediction by the WELDBEAD neural network, shown in (a) More
Image
Published: 01 January 1993
Fig. 9 Neural-network-based seam-tracking system. (a) System utilizing a CCD array camera tracking a clear image. (b) System utilizing a CCD array camera tracking an image with simulated smoke and spatter from a FCAW process More
Image
Published: 01 January 2003
Fig. 22 Schematic of a single processor or neuron in an artificial neural network More
Image
Published: 01 January 2003
Fig. 23 Four-layer neural network architecture (one input, one output, and two middle computing hidden layers) for the prediction of stress-corrosion cracking (SCC) risk of austenitic stainless steels in industrial processes More
Image
Published: 01 January 2003
Fig. 24 Four-layer neural network architecture (one input, one output, and two middle computing hidden layers) for the prediction of pitting of aluminum as a function of water chemistry variables More
Image
Published: 01 December 2009
Fig. 2 Graphical user interfaces of artificial neural-network software for simulation and prediction of various correlations in titanium alloys. (a) Time-temperature transformation (TTT) diagrams. (b) Mechanical properties of conventional titanium alloys. (c) Fatigue stress life diagrams. (d More
Image
Published: 01 December 2009
Fig. 4 Algorithm of computer program for creation of neural-network model More
Image
Published: 01 December 2009
Fig. 6 Regression coefficients between the neural-network predictions and the experimental data for various numbers of neurons in the hidden layer using Levenberg-Marquardt training (a) without and (b) with Bayesian regularization More
Image
Published: 01 December 2009
Fig. 15 Use of a neural-network model for optimization of alloy composition in the Ti-Al-Fe system to maximize room-temperature yield strength More
Image
Published: 01 December 2009
Fig. 17 Use of a neural-network model for optimization of the processing procedure More
Image
Published: 01 December 2009
Fig. 19 Neural network (NN) for stress-intensity factor (SIF) calculation. “Type” refers to crack type, including center-cracked geometry, double-cracked geometry, and single-cracked geometry; w , crack width; a , crack length; and σ applied , applied stress. Source: Ref 32 More
Image
Published: 30 June 2023
Fig. 21 Data-driven inverse design. NN, neural network; FEM, finite-element modeling. Source: Ref 116 More
Series: ASM Handbook
Volume: 6A
Publisher: ASM International
Published: 31 October 2011
DOI: 10.31399/asm.hb.v06a.a0005553
EISBN: 978-1-62708-174-0
..., and control. The article describes the commonly applied sensing techniques for arc welding control: arc sensing and nonimaging and imaging optics. It reviews the physics-based, empirically-derived, and neural network models for arc welding control. The article also discusses the research and development...
Series: ASM Handbook
Volume: 14B
Publisher: ASM International
Published: 01 January 2006
DOI: 10.31399/asm.hb.v14b.a0005153
EISBN: 978-1-62708-186-3
... ). The basic format of the ARMA model can be found in Ref 8 and Ref 9 . It is also useful to note that having these mathematical models also makes tuning a PID controller much easier. Neural Network Control Another approach in control is to use neural network control. The concept of neural network...