Representation: Extracting Mate Complexity From Assembly Models to Automatically Predict Assembly Times

2012 ◽  
Author(s):  
Eric Owensby ◽  
Essam Z. Namouz ◽  
Aravind Shanthakumar ◽  
Joshua D. Summers
Keyword(s):  
Neural Networks ◽  
New Method ◽  
Training Algorithm ◽  
Training Set ◽  
Assembly Time ◽  
Target Time ◽  
Complexity Metrics ◽  
Time Prediction ◽  
Relationship Model ◽  
Assembly Models

The work in this paper uses neural networks to develop a relationship model between assembly times and complexity metrics applied to defined mate connections within SolidWorks assembly models. This model is then used to develop a Design for Assembly (DFA) automation tool that can predict a product’s assembly time using defined mate connections within SolidWorks assembly models. The development of this new method consists of: creating a SolidWorks (SW) Add-in to automatically extract the mate connections from SW assembly models, parsing the mate connections into graphs, implementing a new complexity training algorithm to predict assembly times based on mate graphs, and evaluating the effectiveness of the new method. The motivation, development, and evaluation of the new automated DFA method are presented in this paper. Ultimately, the method that is trained on both fully defined and partially defined assembly models is shown to provide assembly time prediction results that are typically within 25% of target time, but with one outlier at 95% error, suggesting that a more robust training set is needed.

Evaluating the Use of Artificial Neural Networks, Graph Theory, and Complexity Theory to Predict Automotive Assembly Defects

2016 ◽  
Author(s):  
Apurva Patel ◽  
Patrick Andrews ◽  
Joshua D. Summers
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Prediction Models ◽  
Assembly Model ◽  
Training Set ◽  
Automotive Assembly ◽  
Artificial Neural ◽  
Training Set Selection ◽  
Selection Of ◽  
Assembly Models

Artificial Neural Networks (ANNs) have been used to predict assembly time and market value from assembly models. This was done by converting the assembly models into bipartite graphs and extracting 29 graph complexity metrics which were used to train the ANN prediction models. This paper presents the use of sub-assembly models instead of the entire assembly model to predict assembly quality defects at an automotive OEM. The size of the training set, order of the bipartite graph, selection of training set, and defect type were experimentally studied. With a training size of 28 parts, an interpolation focused training set selection, and second order graph seeding, over 70% of the predictions were within 100% of the target value. The study shows that with an increase in training size and careful selection of training sets, assembly defects can be predicted reliably from sub-assemblies complexity data.

The Convergence of Backpropagation Trained Neural Networks for Various Weight Update Frequencies

1997 ◽  
Vol 08 (03) ◽  
pp. 263-277
Author(s):  
Jim Torresen
Keyword(s):  
Neural Networks ◽  
Learning Rate ◽  
Training Algorithm ◽  
Training Set ◽  
Feed Forward ◽  
Parallel Implementations ◽  
Feed Forward Neural Networks ◽  
Update Frequency

One of the problems concerning the backpropagation training of feed-forward neural networks is the effect of the weight update frequency. This aspect influences the efficiency of parallel implementations of the training algorithm where the training vectors are distributed among processors. In this paper the convergence of two applications for various weight update intervals is reported. Further, several models are proposed for describing convergence and learning rate aspects in the context of a set of weight update intervals. The results show that the convergence by updating the weights after each training vector leads to about 10 times less number of training iterations compared to updating the weights only ones for the whole training set.

scholarly journals Firearm Classification using Neural Networks on Ring of Firing Pin Impression Images

2013 ◽  
Vol 1 (3) ◽  
pp. 27-34 ◽  
Author(s):  
SAADI Bin Ahmad Kamaruddin ◽  
Nor AZURA MD Ghanib ◽  
Choong-Yeun Liong ◽  
Abdul AZIZ Jemain
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Transfer Functions ◽  
Training Algorithm ◽  
Backpropagation Neural Network ◽  
Training Set ◽  
Classification Result ◽  
Image Region ◽  
Geometric Moments ◽  
Validation Set

This paper implements two layer neural networks with different feedforward backpropagation algorithms for better performance of firearm classification us-ing numerical features from the ring image. A total of 747 ring images which are extracted from centre of the firing pin impression have been captured from five different pistols of the Parabellum Vector SPI 9mm model. Then, based on finding from the previous studies, the six best geometric moments numerical fea-tures were extracted from those ring images. The elements of the dataset were further randomly divided into the training set (523 elements), testing set (112 el-ements) and validation set (112 elements) in accordance with the requirement of the supervised learning nature of the backpropagation neural network (BPNN). Empirical results show that a two layer BPNN with a 6-7-5 configura-tion and tansig/tansig transfer functions with ‘trainscg’ training algorithm has produced the best classification result of 98%. The classification result is an improvement compared to the previous studies as well as confirming that the ring image region contains useful information for firearm classification.

An Improved Training Algorithm for Quantum Neural Networks

2014 ◽  
Vol 35 (7) ◽  
pp. 1630-1635
Author(s):  
Yi-peng Zhang ◽  
Liang Chen ◽  
Huan Hao
Keyword(s):  
Neural Networks ◽  
Training Algorithm

scholarly journals Inequalities and pth moment exponential stability of impulsive delayed Hopfield neural networks

2021 ◽  
Vol 2021 (1) ◽  
Author(s):  
Yutian Zhang ◽  
Guici Chen ◽  
Qi Luo
Keyword(s):  
Neural Networks ◽  
Lyapunov Function ◽  
Exponential Stability ◽  
Hopfield Neural Networks ◽  
New Method ◽  
Integral Inequalities ◽  
Delay Function ◽  
Pth Moment Exponential Stability ◽  
Moment Exponential Stability

AbstractIn this paper, the pth moment exponential stability for a class of impulsive delayed Hopfield neural networks is investigated. Some concise algebraic criteria are provided by a new method concerned with impulsive integral inequalities. Our discussion neither requires a complicated Lyapunov function nor the differentiability of the delay function. In addition, we also summarize a new result on the exponential stability of a class of impulsive integral inequalities. Finally, one example is given to illustrate the effectiveness of the obtained results.

A new method of NIR face recognition using kernel projection DCV and neural networks

2013 ◽  
Author(s):  
Ya Qiao ◽  
Yuan Lu ◽  
Yun-song Feng ◽  
Feng Li ◽  
Yongshun Ling
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
New Method

TRAINING ALGORITHM OF UNIFORM PARZEN WINDOW NEURAL NETWORKS

2008 ◽  
Vol 1 (3) ◽  
pp. 178-187
Author(s):  
Chao-Yin Hsiao ◽  
Shan-Hung Hsieh
Keyword(s):  
Neural Networks ◽  
Training Algorithm ◽  
Parzen Window
Sign in / Sign up

Export Citation Format

Share Document