Jinn-Tsong Tsai

Optimal Design of SAW Gas Sensing Device by Using Improved Adaptive Neuro-Fuzzy Inference System

A Taguchi-based-genetic algorithm (TBGA) is used in an adaptive neuro-fuzzy inference system (ANFIS) to optimize design parameters for surface acoustic wave (SAW) gas sensors. The Taguchi method is used to reduce the number of experiments and collect performance data for an SAW gas sensor. The TBGA has two optimization roles. In the ANFIS, the TBGA selects appropriate membership functions and optimizes both the premise and the consequent parameters by minimizing the performance criterion of the root mean squared error. Another role of the TBGA is optimizing design parameters for an SAW gas sensor. Simulated experimental application of the proposed TBGA-based ANFIS approach showed that, in terms of both resonant frequency shift and precision performance, this systematic design approach obtains far superior results compared with the conventional trial-and-error design methods and other Taguchi-based design methods.

Optimized Positional Compensation Parameters for Exposure Machine for Flexible Printed Circuit Board

A soft-computing technology is proposed for optimizing the positional compensation parameters for an exposure machine for flexible printed circuit boards (FPCBs). The proposed technology integrates a full-factorial experimental design, a multilayer perceptron (MLP) artificial neural network, and the Taguchi-based genetic algorithm (TBGA). First, a full-factorial experimental design is used to conduct experiments and to accumulate data that represent the positional compensation parameters of an exposure machine. The MLP is then used to build a positioning model of an exposure machine by minimizing the performance criterion of mean-squared error (mse). Finally, the TBGA is used to optimize the positional compensation parameters for the exposure machine. The experimental results demonstrate the excellent performance of the MLP-TBGA approach in obtaining positional compensation parameters for decreasing the number of iterations and the alignment time. For example, in 50 independent runs, the average number of iterations for precision positioning decreased from 4.5 to 3.2, and the alignment time decreased by 41%, if the required positional accuracy was 3 μm. In another experimental application for precision positioning in which the required positional accuracy was 5 μm, the average number of iterations required in 50 practical experiments decreased from 3.3 to 2.1, and the alignment time decreased by 57%. The main advantage of the proposed soft-computing approach is its potential use for solving related problems in widely varying industries.

Designing Micro-Structure Parameters for Backlight Modules by Using Improved Adaptive Neuro-Fuzzy Inference System

A Taguchi-based genetic algorithm (TBGA) is adopted in an adaptive neuro-fuzzy inference system (ANFIS) to optimize the micro-structure parameters of backlight modules (BLMs) in liquid-crystal displays. The method reduces the number of experiments and accumulates the data that indicate performance quality of the modules. The TBGA selects appropriate membership functions and optimizes the premise and consequent parameters by minimizing the performance criterion of root-mean-squared error. The results indicate that the ANFIS with TBGA is significantly superior to ANFIS with particle swarm optimization, ANFIS with GA, and conventional ANFIS for designing the BLM model. Another role of the TBGA is optimizing micro-structure parameters for the backlight module. The results confirm excellent outcome of the TBGA-based ANFIS approach in terms of prediction accuracy, cost reduction, and luminance uniformity. Far more superior results were obtained when compared with those reported in the literature using conventional trial-and-error design methods and even Taguchi-based design methods. Fuzzy model in nature, our approach is applicable generally to industrial product designs and, thus, offers an effective route to solving problems in various industries.

Modeling and Optimizing Tensile Strength and Yield Point on a Steel Bar Using an Artificial Neural Network With Taguchi Particle Swarm Optimizer

A Taguchi particle swarm optimization (TPSO) with a three-layer feedforward artificial neural network (ANN) is used to model and optimize the chemical composition of a steel bar. The novel contribution of a TPSO is the use of a Taguchi method mechanism to exploit better solutions in the search space through iterations, the use of the conventional non-linear PSO to increase convergence speed, and the use of random movement for particle diversity. The exploration and exploitation capability of the TPSO were confirmed by performance comparisons with other PSO-based algorithms in solving high-dimensional global numerical optimization problems. Experiments in this paper showed that the TPSO provides higher computational efficiency and higher robustness when solving problems involving seven non-linear benchmark functions, including three unimodal functions, one multimodal functions, two rotated functions, and one shifted functions. The results for the computational experiments show that the TPSO outperforms other PSO-based algorithms reported in the literature. Finally, the results obtained by a TPSO-based ANN model of the chemical composition of the steel bar were consistent with the actual data. That is, the proposed TPSO with three-layer feedforward ANN can be used in practical applications.

Performance comparisons between PCA-EA-LBG and PCA-LBG-EA approaches in VQ codebook generation for image compression

The aim of this study is to generate vector quantisation (VQ) codebooks by integrating principle component analysis (PCA) algorithm, Linde-Buzo-Gray (LBG) algorithm, and evolutionary algorithms (EAs). The EAs include genetic algorithm (GA), particle swarm optimisation (PSO), honey bee mating optimisation (HBMO), and firefly algorithm (FF). The study is to provide performance comparisons between PCA-EA-LBG and PCA-LBG-EA approaches. The PCA-EA-LBG approaches contain PCA-GA-LBG, PCA-PSO-LBG, PCA-HBMO-LBG, and PCA-FF-LBG, while the PCA-LBG-EA approaches contain PCA-LBG, PCA-LBG-GA, PCA-LBG-PSO, PCA-LBG-HBMO, and PCA-LBG-FF. All training vectors of test images are grouped according to PCA. The PCA-EA-LBG used the vectors grouped by PCA as initial individuals, and the best solution gained by the EAs was given for LBG to discover a codebook. The PCA-LBG approach is to use the PCA to select vectors as initial individuals for LBG to find a codebook. The PCA-LBG-EA used the final result of PCA-LBG as an initial individual for EAs to find a codebook. The search schemes in PCA-EA-LBG first used global search and then applied local search skill, while in PCA-LBG-EA first used local search and then employed global search skill. The results verify that the PCA-EA-LBG indeed gain superior results compared to the PCA-LBG-EA, because the PCA-EA-LBG explores a global area to find a solution, and then exploits a better one from the local area of the solution. Furthermore the proposed PCA-EA-LBG approaches in designing VQ codebooks outperform existing approaches shown in the literature.

PCA-Based Fast Search Method Using PCA-LBG-Based VQ Codebook for Codebook Search

A fast search method based on principle component analysis (PCA) is proposed to search codewords using vector quantization (VQ) codebooks obtained by PCA with Linde-Buzo-Gray (LBG) algorithms. The PCA sorts vectors of a test image and codewords of a PCA-LBG-based VQ codebook. The first search starts from the first codeword in the sorted codebook, and the next search starts from the previous best-matching codeword position in the sorted codebook. Both forward and backward searches are performed within the set search range until the best-matching codewords for all vectors of the test image are found in a sorted codebook. Because PCA efficiently distinguishes both test image vectors and codebook codewords, the proposed PCA-based fast search method outperforms the conventional algorithms in a codebook search. In particular, the experimental results show that, by using PCA-LBG-based VQ codebooks, the proposed PCA-based fast search method outperforms other methods in terms of peak signal-to-noise ratio for the compressed image, number of codewords searched, and runtime.

Adaptive neuro-fuzzy inference system with evolutionary algorithm for designing process parameters of color filter

The orthogonal array, signal-to-noise ratio, adaptive network-based fuzzy inference system (ANFIS), and hybrid Taguchi-genetic evolutionary algorithm (HTGEA) is combined to optimize the process parameters for chemical mechanical polishing process of color filter (CMPPCF). The HTGEA in the ANFIS not only find the most suitable membership function types but also find the optimal premise and consequent parameters.

Performance Prediction and Sensitivity Analysis of SAW Gas Sensors

An improved adaptive neuro-fuzzy inference system (IANFIS) is proposed to build a model to predict the resonant frequency shift performance of surface acoustic wave (SAW) gas sensors. In the proposed IANFIS, by directly minimizing the root-mean-squared-error performance criterion, the Taguchi-genetic learning algorithm is used in the ANFIS to find both the optimal premise and consequent parameters and to simultaneously determine the most suitable membership functions. The five design parameters of SAW gas sensors are considered to be the input variables of the IANFIS model. The input variables include the number of electrode finger pairs, the electrode overlap, the separation distance of two interdigital transducers on the substrate, the dimensions of the stable temperature-cut (ST-cut) quartz substrate, and the electrode thickness. The output variable of the IANFIS model is composed of the resonant frequency shift performance. The results predicted by the proposed IANFIS are compared with those obtained by the back-propagation neural network. The comparison has shown that the performance prediction of resonant frequency shift using the proposed IANFIS is effective. In addition, the sensitivity analyses of the five design parameters have also shown that both the electrode overlap and the dimensions of the ST-cut quartz substrate have the most influence on the resonant frequency shift performance.

Optimal Parameter Design for IC Wire Bonding Process by Using Fuzzy Logic and Taguchi Method

Fuzzy logic Taguchi method (FLTM) is used to optimize parameters for wire bonding process. The proposed FLTM integrates orthogonal arrays, signal-to-noise ratios, response tables, analysis of variance (ANOVA), fuzzy logic, and multiple performance characteristics index. The main process parameters for wire bonding are ultrasonication time, ultrasonication power, bond force, bond force time, and search force. The output responses include ball shear and ball size. The orthogonal arrays, signal-to-noise ratios, and response tables reduce the number of experiments needed to find the best factor-level combinations. The significant control factors are determined by ANOVA. In engineering practice, ball size increases as ball shear increases, but an excessively large ball size causes a short circuit, whereas an excessively small ball size cannot provide enough ball shear. Due to the two contradictory output responses, the FLTM is used to find the best process parameters. The experimental results show that the process parameters obtained by the FLTM result in a smaller ball size and a larger ball shear compared with those obtained by statistical methods, artificial intelligence techniques, and previous designs.

Intelligent Hybrid Taguchi-Genetic Algorithm for Multi-Criteria Optimization of Shaft Alignment in Marine Vessels

An intelligent hybrid Taguchi-genetic algorithm (IHTGA) is used to optimize bearing offsets and shaft alignment in a marine vessel propulsion system. The objectives are to minimize normal shaft stress and shear force. The constraints are permissible reaction force, bearing stress, shear force, and bending moment in the shaft thrust flange under cold and hot operating conditions. Accurate alignment of the shaft for a main propulsion system is important for ensuring the safe operation of a vessel. To obtain a set of acceptable forces and stresses for the bearings and shaft under operating conditions, the optimal bearing offsets must be determined. Instead of the time-consuming classical local search methods with some trial-and-error procedures used in most shipyards to optimize bearing offsets, this paper used IHTGA. The proposed IHTGA performs Taguchi method between the crossover operation of the conventional GA. Incorporating the systematic reasoning ability of Taguchi method in the crossover operation enables intelligent selection of genes used to achieve crossover, which enhances the performance of the IHTGA in terms of robustness, statistical performance, and convergence speed. A penalty function method is performed using the fitness function as a pseudo-objective function comprising a linear combination of design objectives and constraints. A finite-element method is also used to determine the reaction forces and stresses in the bearings and to determine normal stresses, bending moments, and shear forces in the shaft. Computational experiments in a 2200 TEU container vessel show that the results obtained by the proposed IHTGA are significantly better than those obtained by the conventional local search methods with some trial-and-error procedures.