Skip Nav Destination
1-17 of 17
Keywords: neural networksClose
Proc. ASME. IDETC-CIE2021, Volume 2: 41st Computers and Information in Engineering Conference (CIE), V002T02A037, August 17–19, 2021
Paper No: DETC2021-69259
... harness the abundance of data to discover effective control designs. In this paper, we investigate the efficacy of a data-driven approach towards in-situ modeling of melt-pool geometry. Specifically, we propose a new methodology that uses a deep neural network architecture to predict melt pool geometries...
Proc. ASME. IDETC-CIE2021, Volume 3B: 47th Design Automation Conference (DAC), V03BT03A035, August 17–19, 2021
Paper No: DETC2021-66898
... multiple Functional Reasoning, Neural Networks, Product Development, approaches to thinking about design. In Systematic Engineering Product Design Design , establishing a functional structure with the goal of identifying the overall function of a system is the paramount goal of design practice...
Proc. ASME. IDETC-CIE2021, Volume 10: 33rd Conference on Mechanical Vibration and Sound (VIB), V010T10A022, August 17–19, 2021
Paper No: DETC2021-70375
... differential equation of time-domain elastodynamics with a moving load. Time-domain correlation function-based features are built in order to train classifiers such as Artificial Neural Networks and Support-Vector Machines and perform damage detection. The method is tested on a bridge-shaped structure...
Proc. ASME. IDETC-CIE2021, Volume 1: 23rd International Conference on Advanced Vehicle Technologies (AVT), V001T01A015, August 17–19, 2021
Paper No: DETC2021-71062
... and local buckling) are taken into account. The developed finite-element based model of the wheel is used to train a set of neural networks to approximate the objective functions and the design constraints to reduce the computational effort. A multi-objective genetic algorithm is adopted to obtain...
Proc. ASME. IDETC-CIE2021, Volume 1: 23rd International Conference on Advanced Vehicle Technologies (AVT), V001T01A017, August 17–19, 2021
Paper No: DETC2021-68469
... vehicles. The proposed approach exploits a Genetic of the highly non-linear battery characteristics . To this end, Algorithm (GA) in combination with Artificial Neural Networks an effective BMS may extend the battery life and prevent the (ANNs) for SOC estimation. Specifically, the training parameters...
Proc. ASME. IDETC-CIE2021, Volume 2: 41st Computers and Information in Engineering Conference (CIE), V002T02A031, August 17–19, 2021
Paper No: DETC2021-71266
... Proceedings of the ASME 2021 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference IDETC-CIE2021 August 17-19, 2021, Virtual, Online DETC2021-71266 HYBRID MODELING OF MELT POOL GEOMETRY IN ADDITIVE MANUFACTURING USING NEURAL NETWORKS...
Proc. ASME. DETC90, 16th Design Automation Conference: Volume 1 — Computer Aided and Computational Design, 305-310, September 16–19, 1990
Paper No: DETC1990-0037
..., gearboxes, MCAE, neural networks INTRODUCTION Novice engineers are often assigned projects which, to them, incorporate new or vaguely familiar design skills and practices. So where does this leave the engineer? First, design handbooks must be consulted for basic design 305 equations and rules of thumb...
Proc. ASME. DETC94, 4th Flexible Assembly Conference, 29-33, September 11–14, 1994
Paper No: DETC1994-0367
...Abstract Abstract The problem of inverse kinematics in Robotics, is a nonlinear mapping from a given cartesian coordinates to the desirable joint coordinates of the robot arm. It is found that an appropriately designed neural network can be trained to learn the non-linearity of the Inverse...
Proc. ASME. DETC97, Volume 3: 9th International Design Theory and Methodology Conference, V003T30A008, September 14–17, 1997
Paper No: DETC97/DTM-3881
...Proceedings of DETC 97 1997 ASME Design Engineering Technical Conferences September 14-17, 1997, Sacramento, California E U a e te 3 ology, Taguchi methods, neural networks, inductive learning, and krig ing des statisti analysi approp and how KE method inductiv 1 INTR Mu comple design (outpu expens...
Proc. ASME. DETC99, Volume 7A: 17th Biennial Conference on Mechanical Vibration and Noise, 1297-1301, September 12–16, 1999
Paper No: DETC99/VIB-8329
...Proceedings of The 1999 ASME Design Engineering Technical Conferences September 12-15,1999, Las Vegas, Nevada DETC99AZIB-8329 GEARBOX FAULT DETECTION USING NEURAL NETWORKS TECHNOLOGY Sun Qiao Department of Mechanical Engineering The University of Alabama, Tuscaloosa, AL 35487-0276 Li Xiaolei Xu...
Proc. ASME. IDETC-CIE2020, Volume 2: 16th International Conference on Multibody Systems, Nonlinear Dynamics, and Control (MSNDC), V002T02A029a, August 17–19, 2020
Paper No: DETC2020-22358
...Abstract Abstract In this paper a data-driven approach for model-free control of nonlinear systems with slow dynamics is proposed. The system behavior is described using a local model respectively a neural network. The network is updated online based on a Kalman filter. By predicting the system...
Proc. ASME. IDETC-CIE2020, Volume 9: 40th Computers and Information in Engineering Conference (CIE), V009T09A042, August 17–19, 2020
Paper No: DETC2020-22335
...AUTOMATED CLASSIFICATION OF COMPONENTS FOR MANUFACTURING PLANNING: SINGLE-VIEW CONVOLUTIONAL NEURAL NETWORK FOR GLOBAL SHAPE IDENTIFICATION Andrew Barclay1, Jonathan Corney 1Department of Design, Manufacturing, and Engineering Management University of Strathclyde, Glasgow, UK ABSTRACT...
James L. Mathieson, Aravind Shanthakumar, Chiradeep Sen, Ryan Arlitt, Joshua D. Summers, Robert Stone
Proc. ASME. IDETC-CIE2011, Volume 9: 23rd International Conference on Design Theory and Methodology; 16th Design for Manufacturing and the Life Cycle Conference, 55-64, August 28–31, 2011
Paper No: DETC2011-47481
.... This program is then used to predict the value of the final four products. The results of this approach demonstrate that complexity metrics can be used as inputs to neural networks to establish an accurate mapping from function structure design representations to market values to within the distribution...
Proc. ASME. IDETC-CIE2004, Volume 2: 28th Biennial Mechanisms and Robotics Conference, Parts A and B, 95-104, September 28–October 2, 2004
Paper No: DETC2004-57031
... 30 06 2008 The authors present a new approach using genetic algorithms, neural networks and nanorobotics concepts applied to the problem of control design for nanoassembly automation and its application in medicine. As a practical approach to validate the proposed design, we have...
Proc. ASME. IDETC-CIE2002, Volume 1: 22nd Computers and Information in Engineering Conference, 129-136, September 29–October 2, 2002
Paper No: DETC2002/CIE-34399
.... Such formulation makes it possible to use well ssion algorithms, such as neural networks. aper, we develop a neural network based inverse heet forming process, and compare its performance linear model. Both models are used in two modes, mode and a function estimation mode, to investi- antage of re-formulating...
Proc. ASME. IDETC-CIE2002, Volume 1: 22nd Computers and Information in Engineering Conference, 857-863, September 29–October 2, 2002
Paper No: DETC2002/CIE-34507
.... We have described our ongoing research work on developing an intelligent inference strategy based on artificial neural networks for implementing machining process selection for rotationally symmetric parts. Computer-Aided Process Planning artificial intelligence neural networks machining...
Proc. ASME. IDETC-CIE2006, Volume 2: 30th Annual Mechanisms and Robotics Conference, Parts A and B, 539-545, September 10–13, 2006
Paper No: DETC2006-99067
... cannot be obtained by conventional techniques. This paper presents neural networks based approach to solve this problem. Experiments conducted to prove the principle have been verified with theoretical results and finite element analysis of the loaded specimens. The technique, if fully developed, can...