A Multidisciplinary Design and Optimization Methodology for Ball Grid Array Packages Using Artificial Neural Networks

2004 ◽  
Vol 127 (3) ◽  
pp. 306-313 ◽  
Author(s):  
Hamid Hadim ◽  
Tohru Suwa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Ball Grid Array ◽  
System Level ◽  
Computational Time ◽  
Design Parameters ◽  
Design And Optimization ◽  
Trade Offs ◽  
Artificial Neural ◽  
Optimization Methodology

A systematic multidisciplinary electronics packaging design and optimization methodology, which takes into account the complexity of multiple design trade-offs, operated in conjunction with the artificial neural networks (ANNs) technique is presented. To demonstrate its capability, this method is applied to a plastic ball grid array package design. Multidisciplinary criteria including thermal, structural, electromagnetic leakage, and cost are optimized simultaneously using key design parameters as variables. A simplified routability criterion is also considered as a constraint. ANNs are used for thermal and structural performance predictions which resulted in large reduction in computational time. The present methodology is able to provide the designers a tool for systematic evaluation of the design trade-offs which are represented in the objective function. This methodology can be applied to any electronic product design at any packaging level from the system level to the chip level.

A Multidisciplinary Design and Optimization Methodology in Electronics Packaging: Application to BGA Design

2003 ◽  
Author(s):  
Hamid Hadim ◽  
Tohru Suwa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Objective Function ◽  
Thermal Strain ◽  
Design Parameters ◽  
Design And Optimization ◽  
Trade Offs ◽  
Artificial Neural ◽  
Optimization Methodology ◽  
The Individual

In this manuscript a systematic multidisciplinary electronic packaging design and optimization methodology based on the artificial neural networks technique is presented. This method is applied to a Ball Grid Array (BGA) package design as an example. Multidisciplinary criteria including thermal, structural (thermal strain), electromagnetic leakage, and cost are optimized simultaneously. A simplified routability criterion is also considered as a constraint. The artificial neural networks technique is used for thermal and structural performance predictions. Large calculation time reduction is achieved using the artificial neural networks, which also provide enough information to specify the individual weights for each design discipline within the objective function used for optimization. This methodology is able to provide the designers a clear view of the design trade-offs, which are represented in the objective function using various design parameters. This methodology can be applied to any electronic product design at any packaging level.

scholarly journals Applying Artificial Neural Networks In Construction

2020 ◽  
Vol 143 ◽  
pp. 01029
Author(s):  
Anna Doroshenko
Keyword(s):  
Neural Networks ◽  
Pattern Recognition ◽  
Artificial Neural Networks ◽  
Construction Industry ◽  
Structural Design ◽  
Soil Mechanics ◽  
Construction Materials ◽  
Construction Engineering ◽  
Design And Optimization ◽  
Artificial Neural

Currently, artificial neural networks (ANN) are used to solve the following complex problems: pattern recognition, speech recognition, complex forecasts and others. The main applications of ANN are decision making, pattern recognition, optimization, forecasting, data analysis. This paper presents an overview of applications of ANN in construction industry, including energy efficiency and energy consumption, structural analysis, construction materials, smart city and BIM technologies, structural design and optimization, application forecasting, construction engineering and soil mechanics.

Integrated Thermomechanical Design and Optimization of BGA Packages Using Genetic Algorithm

Volume 4 ◽  
2004 ◽  
Author(s):  
Hamid A. Hadim ◽  
Tohru Suwa
Keyword(s):  
Genetic Algorithm ◽  
Thermal Strain ◽  
System Level ◽  
Multidisciplinary Design ◽  
Design Stage ◽  
Computational Time ◽  
Design Parameters ◽  
Package Design ◽  
Early Design Stage ◽  
Design And Optimization

A new multidisciplinary design and optimization methodology in electronics packaging is presented. A genetic algorithm combined with multi-disciplinary design and multi-physics analysis tools are used to optimize key design parameters. This methodology is developed to improve the electronic package design process by performing multidisciplinary design and optimization at an early design stage. To demonstrate its capability, the methodology is applied to a Ball Grid Array (BGA) package design. Multidisciplinary criteria including thermal, thermal strain, electromagnetic leakage, and cost are optimized simultaneously. A simplified routability analysis criterion is treated as a constraint. The genetic algorithm is used for systematic design optimization while reducing the total computational time. The present methodology can be applied to any electronics product design at any packaging level from the chip level to the system level.

An Optimal Design Method for Artificial Neural Networks by Using the Design of Experiments

2007 ◽  
Vol 11 (6) ◽  
pp. 593-599 ◽  
Author(s):  
Eiichi Inohira ◽  
◽  
Hirokazu Yokoi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Optimal Design ◽  
Design Method ◽  
Feedforward Neural Networks ◽  
Learning Rate ◽  
Design Parameters ◽  
Approximation Accuracy ◽  
Artificial Neural ◽  
Trained Neural Network

This paper presents a method to optimally design artificial neural networks with many design parameters using the Design of Experiment (DOE), whose features are efficient experiments using an orthogonal array and quantitative analysis by analysis of variance. Neural networks can approximate arbitrary nonlinear functions. The accuracy of a trained neural network at a certain number of learning cycles depends on both weights and biases and its structure and learning rate. Design methods such as trial-and-error, brute-force approaches, network construction, and pruning, cannot deal with many design parameters such as the number of elements in a layer and a learning rate. Our design method realizes efficient optimization using DOE, and obtains confidence of optimal design through statistical analysis even though trained neural networks very due to randomness in initial weights. We apply our design method three-layer and five-layer feedforward neural networks in a preliminary study and show that approximation accuracy of multilayer neural networks is increased by picking up many more parameters.

Hybrid Model of an Evaporative Gas Turbine Power Plant Utilizing Physical Models and Artificial Neural Networks

2003 ◽  
Author(s):  
Pernilla Olausson ◽  
Daniel Ha¨ggsta˚hl ◽  
Jaime Arriagada ◽  
Erik Dahlquist ◽  
Mohsen Assadi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gas Turbine ◽  
Hybrid Model ◽  
Power Plants ◽  
Computational Time ◽  
Process Identification ◽  
Calculation Time ◽  
Artificial Neural

Traditionally, when process identification, monitoring and diagnostics are carried out for power plants and engines, physical modeling such as heat and mass balances, gas path analysis, etc. is utilized to keep track of the process. This type of modeling both requires and provides considerable knowledge of the process. However, if high accuracy of the model is required, this is achieved at the expense of computational time. By introducing statistical methods such as Artificial Neural Networks (ANNs), the accuracy of the complex model can be maintained while the calculation time is often reduced significantly reduced. The ANN method has proven to be a fast and reliable tool for process identification, but the step from the traditional physical model to a pure ANN model is perhaps too wide and, in some cases, perhaps unnecessary also. In this work, the Evaporative Gas Turbine (EvGT) plant was modeled using both physical relationships and ANNs, to end up with a hybrid model. The type of architecture used for the ANNs was the feed-forward, multi-layer neural network. The main objective of this study was to evaluate the viability, the benefits and the drawbacks of this hybrid model compared to the traditional approach. The results of the case study have clearly shown that the hybrid model is preferable. Both the traditional and the hybrid models have been verified using measured data from an existing pilot plant. The case study also shows the simplicity of integrating an ANN into conventional heat and mass balance software, already implemented in many control systems for power plants. The access to a reliable and faster hybrid model will ultimately give more reliable operation, and ultimately the lifetime profitability of the plant will be increased. It is also worth mentioning that for diagnostic purposes, where advanced modeling is important, the hybrid model with calculation time well below one second could be used to advantage in model predictive control (MPC).

Multiple objective crashworthiness optimization of circular tubes with functionally graded thickness via artificial neural networks and genetic algorithms

2016 ◽  
Vol 231 (11) ◽  
pp. 2005-2016 ◽  
Author(s):  
Adil Baykasoğlu ◽  
Cengiz Baykasoğlu
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Artificial Neural Networks ◽  
Functionally Graded ◽  
Design Parameters ◽  
Multiple Objective ◽  
Circular Tubes ◽  
Crashworthiness Optimization ◽  
Artificial Neural ◽  
Graded Thickness

The objective of this paper is to develop a multiple objective optimization procedure for crashworthiness optimization of circular tubes having functionally graded thickness. The proposed optimization approach is based on finite element analyses for construction of sample design space and verification; artificial neural networks for predicting objective functions values (peak crash force and specific energy absorption) for design parameters; and genetic algorithms for generating design parameters alternatives and determining optimal combination of them. The proposed approach seaminglesly integrates artificial neural networks and genetic algorithms. Artificial neural network acts as an objective function evaluator within the multiple objective genetic algorithms. We have shown that the proposed approach is able to generate Pareto optimal designs which are in a very good agreement with the finite element results.

scholarly journals Optimization of Running Blade Prosthetics Utilizing Crow Search Algorithm Assisted by Artificial Neural Networks

2021 ◽  
Vol 67 (3) ◽  
pp. 88-100
Author(s):  
Rosel Solís Manuel Javier ◽  
José Omar Dávalos Ramírez ◽  
Javier Molina Salazar ◽  
Juan Antonio Ruiz Ochoa ◽  
Antonio Gómez Roa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Carbon Fibre ◽  
Failure Criterion ◽  
Search Algorithm ◽  
Acrylonitrile Butadiene Styrene ◽  
Sensitivity Study ◽  
Design Parameters ◽  
Artificial Neural ◽  
Important Design

A crow search algorithm (CSA) was applied to perform the optimization of a running blade prosthetics (RBP) made of composite materials like carbon fibre layers and cores of acrylonitrile butadiene styrene (ABS). Optimization aims to increase the RBP displacement limited by the Tsai-Wu failure criterion. Both displacement and the Tsai-Wu criterion are predicted using artificial neural networks (ANN) trained with a database constructed from finite element method (FEM) simulations. Three different cases are optimized varying the carbon fibre layers orientations: –45°/45°, 0°/90°, and a case with the two-fibre layer orientations intercalated. Five geometric parameters and a number of carbon fibre layers are selected as design parameters. A sensitivity analysis is performed using the Garzon equation. The best balance between displacement and failure criterion was found with fibre layers oriented at 0°/90°. The optimal candidate with –45°/45° orientation presents higher displacement; however, the Tsai-Wu criterion was less than 0.5 and not suitable for RBP design. The case with intercalated fibres presented a minimal displacement being the stiffer RBP design. The damage concentrates mostly in the zone that contacts the ground. The sensitivity study found that the number of layers and width were the most important design parameters.

scholarly journals Prediction of Sound Insulation of Sandwich Partition Panels by Means of Artificial Neural Networks

2017 ◽  
Vol 42 (4) ◽  
pp. 643-651
Author(s):  
Naveen Garg ◽  
Siddharth Dhruw ◽  
Laghu Gandhi
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Optimization Technique ◽  
Back Propagation ◽  
National Research Council ◽  
Sound Insulation ◽  
Ann Model ◽  
Back Propagation Algorithm ◽  
Design And Optimization ◽  
Artificial Neural

Abstract The paper presents the application of Artificial Neural Networks (ANN) in predicting sound insulation through multi-layered sandwich gypsum partition panels. The objective of the work is to develop an Artificial Neural Network (ANN) model to estimate the Rw and STC value of sandwich gypsum constructions. The experimental results reported by National Research Council, Canada for Gypsum board walls (Halliwell et al., 1998) were utilized to develop the model. A multilayer feed-forward approach comprising of 13 input parameters was developed for predicting the Rw and STC value of sandwich gypsum constructions. The Levenberg-Marquardt optimization technique has been used to update the weights in back-propagation algorithm. The presented approach could be very useful for design and optimization of acoustic performance of new sandwich partition panels providing higher sound insulation. The developed ANN model shows a prediction error of ±3 dB or points with a confidence level higher than 95%.

Sign in / Sign up

Export Citation Format

Share Document