A New Optimization Strategy for Chemical Mechanical Polishing Process

2000 ◽  
Author(s):  
Gou-Jen Wang ◽  
Jau-Liang Chen ◽  
Ju-Yi Hwang
Keyword(s):  
Neural Network ◽  
Taguchi Method ◽  
Signal To Noise Ratio ◽  
Global Optimum ◽  
Optimum Process ◽  
Local Optimum ◽  
Optimization Strategy ◽  
Two Stage ◽  
Chemical Mechanical Polishing Process ◽  
Trained Neural Network

Abstract In this paper, a systematic approach to achieve global optimum CMP process is carried out. In this new approach, orthogonal array technique adopted from the Taguchi method is used for efficient experiment design. The neural network (NN) technique is then applied to model the complex CMP process. Signal to Noise Ratio (S/N) Analysis (ANOVA) technique used in the conventional Taguchi method is also implemented to obtain the local optimum process parameters. Successively, the global optimum parameters are acquired in terms of the trained neural network. In order to increase the CMP throughput, a two-stage optimal strategy is also proposed. Experimental results demonstrate that the two-stage strategy can perform better then the original approach even though the polishing time is reduced by 1/6.

Improving the effectiveness of traditional education based on computer artificial intelligence and neural network system

2020 ◽  
pp. 1-11
Author(s):  
Wenjuan Ma ◽  
Xuesi Zhao ◽  
Yuxiu Guo
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Education Reform ◽  
Traditional Education ◽  
Machine Learning Algorithms ◽  
Local Optimum ◽  
Optimization Strategy ◽  
Fish School ◽  
Tlbo Algorithm ◽  
Neural Network System

The application of artificial intelligence and machine learning algorithms in education reform is an inevitable trend of teaching development. In order to improve the teaching intelligence, this paper builds an auxiliary teaching system based on computer artificial intelligence and neural network based on the traditional teaching model. Moreover, in this paper, the optimization strategy is adopted in the TLBO algorithm to reduce the running time of the algorithm, and the extracurricular learning mechanism is introduced to increase the adjustable parameters, which is conducive to the algorithm jumping out of the local optimum. In addition, in this paper, the crowding factor in the fish school algorithm is used to define the degree or restraint of teachers’ control over students. At the same time, students in the crowded range gather near the teacher, and some students who are difficult to restrain perform the following behavior to follow the top students. Finally, this study builds a model based on actual needs, and designs a control experiment to verify the system performance. The results show that the system constructed in this paper has good performance and can provide a theoretical reference for related research.

Expected range of the output response for the optimum input parameters utilizing the modified Taguchi approach

2019 ◽  
Vol 15 (2) ◽  
pp. 508-522 ◽  
Author(s):  
Rajyalakshmi K. ◽  
Nageswara Rao Boggarapu
Keyword(s):  
Taguchi Method ◽  
Measurement Errors ◽  
Signal To Noise Ratio ◽  
Optimum Process ◽  
Taguchi Approach ◽  
Test Results ◽  
Content Type ◽  
Output Response ◽  
Input Parameters ◽  
Optimum Input

Purpose Scatter in the outcome of repeated experiments is unavoidable due to measurement errors in addition to the non-linear nature of the output responses with unknown influential input parameters. It is a standard practice to select an orthogonal array in the Taguchi approach for tracing optimum input parameters by conducting a few number of experiments and confirm them through additional experimentation (if necessary). The purpose of this paper is to present a simple methodology and its validation with existing test results in finding the expected range of the output response by suggesting modifications in the Taguchi method. Design/methodology/approach The modified Taguchi approach is proposed to find the optimum process parameters and the expected range of the output response. Findings This paper presents a simple methodology and its validation with existing test results in finding the expected range of the output response by suggesting modifications in the Taguchi method. Research limitations/implications Adequacy of this methodology should be examined by considering the test data on different materials and structures. Originality/value The introduction of Chauvenet’s criterion and opposing the signal-to-noise ratio transformation on repeated experiments of each test run will provide fruitful results and less computation burden.

scholarly journals Improvement of weld heat affected zone (HAZ) using Taguchi method

2021 ◽  
Vol 2 (1) ◽  
pp. 027-033
Author(s):  
Nweze Stephanie ◽  
Achebo J
Keyword(s):  
Taguchi Method ◽  
Process Parameters ◽  
Heat Affected Zone ◽  
Gas Flow ◽  
Signal To Noise Ratio ◽  
Human Life ◽  
Optimum Process ◽  
Weld Quality ◽  
Input Parameters ◽  
Structural Failures

Heat Affected Zone (HAZ) is the area on a weldment mostly affected by the intensity of the applied heat without melting. This area mostly deteriorates faster due to microstructural changes that occur due to the intensity of the applied heat during welding operations. Weld structural failures can be catastrophic and unpredictable at times. When there is no loss of human life involved, damages as a result of weld failure usually takes more time and cost more to repair/replace. For these reasons, a weld with good quality integrity cannot be over-emphasized. The larger the HAZ, the wider the area with microstructural alteration, the lesser the quality integrity of the weldment. In this study, extensive research was conducted to reduce weld HAZ using the Taguchi method. This method makes use of signal to noise ratio of responses to achieve optimality. From applying this model, it was observed that the best input parameters, that improved the weld quality was achieved. These input parameters were current of 120A, voltage of 10V and gas flow rate of 144L/min. From the analysis of variance (ANOVA), it was found that current contributed about 9.58% to the weld quality, which was the most influential process parameters. The confirmation test done, shows that the weldment produced by using the optimum process parameters had an improvement of 1.37db and 0.88mm reduction in HAZ, over the weldment made by existing parameters.

scholarly journals Research of Single Image Rain Removal Algorithm Based on LBP-CGAN Rain Generation Method

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Ping Xue ◽  
Hai He
Keyword(s):  
Neural Network ◽  
Network Model ◽  
Signal To Noise Ratio ◽  
Image Data ◽  
Texture Features ◽  
Generative Adversarial Network ◽  
Average Value ◽  
Adversarial Network ◽  
Negative Effect ◽  
Trained Neural Network

Rain has an undesirable negative effect on the clarity of the collected images. In situation where images are captured in rain, it can lead to a loss of information and disability in reflecting real images of the situation. Consequently, rain has become an obstacle in outdoor scientific research studies. The reason why images captured in rain are difficult to process is due to the indistinguishable interactions between the background features and rain textures. Since current image data are only processed with the CNN (convolutional neural network) model, a trained neural network to remove rain and obtain clear images, the resulted images are either insufficient or excessive from standard results. In order to achieve more ideal results of clearer images, series of additional methods are taken place. Firstly, the LBP (local binary pattern) method is used to extract the texture features of rain in the image. Then, the CGAN (conditional generative adversarial network) model is constructed to generate rain datasets according to the extracted rain characteristics. Finally, the existing clear images, rain datasets generated by CGAN, as well as the images with rain are used for convolution operation to remove rain from the images, and the average value of PSNR (peak signal to noise ratio) can reach 38.79 by using this algorithm. Moreover, a large number of experiments are done and have proven that this joint processing method is able to successfully and effectively generate clear images despite the rain.

scholarly journals Prediction of Wave-induced Liquefaction using Artificial Neural Network and Wide Genetic Algorithm

2017 ◽  
pp. 1
Author(s):  
Dwi Kristianto ◽  
Chastine Fatichah ◽  
Bilqis Amaliah ◽  
Kriyo Sambodho
Keyword(s):  
Neural Network ◽  
Genetic Algorithm ◽  
Artificial Neural Network ◽  
Prediction Accuracy ◽  
Back Propagation ◽  
Global Optimum ◽  
Population Diversity ◽  
Local Optimum ◽  
Artificial Neural ◽  
Wave Induced

The hassle of analytical and numerical solution for liquefaction modeling, repetitive laboratory testing and expensive field observations, have opened opportunities to develop simple, practical, inexpensive and valid prediction of wave-induced liquefaction. In this study, Artificial Neural Network (ANN) regression modeling is used to predict the depth of liquefaction. Despite of using Back Propagation (BP) to train ANN, a modified Genetic Algorithm (called as Wide GA, WGA) is used as ANN training method to improve ANN prediction accuracy and to overcome BP weaknesses such as premature convergence and local optimum. WGA also aim to avoid conventional GA weaknesses such as low population diversity and narrow search coverage. Key WGA operations are Wide Tournament Selection, Multi-Parent BLX-? Crossover, Aggregate Mate Pool Mutation and Direct Fresh Mutation-Crossover. ANN prediction accuracy measured by Median APE (MdAPE). Global optimum solution of WGA is best ANN connections weights configuration with smallest MdAPE.

Numerical Control Interpolation Algorithm of Aspheric Surface Based on the Genetic Algorithms and Neural Network

2007 ◽  
Vol 364-366 ◽  
pp. 25-29
Author(s):  
Fei Hu Zhang ◽  
D.J. Chen ◽  
L.J. Li
Keyword(s):  
Neural Network ◽  
Genetic Algorithms ◽  
Global Optimum ◽  
Numerical Control ◽  
Local Optimum ◽  
Interpolation Algorithm ◽  
Aspheric Surfaces ◽  
The Neural Network ◽  
Circular Curves ◽  
Circular Curve

When the Neural Network model is used to interpolate the non-circular curves, there are shortcomings of converging slowly and getting into the local optimum easily. A novel numerical control interpolation algorithm based on the GA (Genetic Algorithms) and NN (Neural Network) was introduced for the ultra-precision machining of aspheric surfaces. The algorithm integrated the global searching of GA with the parallel processing of NN, enhanceed the convergence speed and found the global optimum. At the end, the quintic non-circular curve was taken as an example to do the emulation and experiment. The results prove that this algorithm can fit the non-circular curve accurately, improve the precision of numerical control interpolation and reduce the number of calculating and interpolation cycles.

Damage Identification of Mechanical System with Artificial Neural Networks

2008 ◽  
Vol 385-387 ◽  
pp. 877-880
Author(s):  
Li Juan Cao ◽  
Shou Ju Li ◽  
Zi Chang Shangguan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Global Optimum ◽  
Fast Convergence ◽  
Mode Shapes ◽  
Local Optimum ◽  
Marquardt Algorithm ◽  
Artificial Neural

The inverse problem of structure damage detection is formulated as an optimization problem, which is then solved by using artificial neural networks. Based on the hybrid optimization strategy, the parameter identification algorithm was presented according to the measured data of vibrating frequency and mode shapes in the damaged structure. The proposed algorithm combines the local optimum method having fast convergence ability with the neural networks having global optimum ability. By doing this, the local minimization problem of the local optimum method can be solved, and the convergence speed of the global optimum method can be improved. The investigation shows that to identify the location and magnitude of the damaged structure by using an artificial neural network is feasible and a well trained artificial neural network by Levenberg-Marquardt algorithm reveals an extremely fast convergence and a high degree of accuracy.

scholarly journals Using the modified k-mean algorithm with an improved teaching-learning-based optimization algorithm for feedforward neural network training

2021 ◽  
Vol 11 (6) ◽  
pp. 5277
Author(s):  
Morteza Jouyban ◽  
Mahdie Khorashadizade
Keyword(s):  
Neural Network ◽  
Global Optimum ◽  
Feedforward Neural Network ◽  
Initial Population ◽  
Training Algorithm ◽  
Optimization Strategy ◽  
Basic Algorithm ◽  
Starting Point ◽  
Teaching Learning Based Optimization ◽  
Teaching Learning

In this paper we proposed a novel procedure for training a feedforward neural network. The accuracy of artificial neural network outputs after determining the proper structure for each problem depends on choosing the appropriate method for determining the best weights, which is the appropriate training algorithm. If the training algorithm starts from a good starting point, it is several steps closer to achieving global optimization. In this paper, we present an optimization strategy for selecting the initial population and determining the optimal weights with the aim of minimizing neural network error. Teaching-learning-based optimization (TLBO) is a less parametric algorithm rather than other evolutionary algorithms, so it is easier to implement. We have improved this algorithm to increase efficiency and balance between global and local search. The improved teaching-learning-based optimization (ITLBO) algorithm has added the concept of neighborhood to the basic algorithm, which improves the ability of global search. Using an initial population that includes the best cluster centers after clustering with the modified k-mean algorithm also helps the algorithm to achieve global optimum. The results are promising, close to optimal, and better than other approach which we compared our proposed algorithm with them.

Two-stage optimization of lens grinding parameters for multi-quality target combining Taguchi method and neural network software

2009 ◽  
Vol 16 (3) ◽  
pp. 276-282
Author(s):  
Rong Seng Chang ◽  
Dong Ru Chiang ◽  
Sha-Wei Wang ◽  
Ching Huang Lin
Keyword(s):  
Neural Network ◽  
Taguchi Method ◽  
Two Stage ◽  
Grinding Parameters ◽  
Network Software
Sign in / Sign up

Export Citation Format

Share Document