Optimizing the auto-brazing process quality via a Taguchi-neural network approach in the automotive industry

Lin, Hsuan-Liang; Chou, Chung-Hsien

doi:10.1109/ieem.2009.5373032

Cited by 2 publications

(2 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Researches on Taguchi method have been conducted in various applications. These researches can be used as the guidelines to optimize ANN [10][11][12][13][14][15]. Comparative studies between heuristic method network and optimized network using Taguchi were conducted to evidently show that Taguchi method works in optimizing the ANN.…”

Section: Introductionmentioning

confidence: 99%

The Taguchi- Artificial Neural Network approach for the detection of incipient faults in oil-filled power transformer

Zakaria

Johari

Musirin

2013

2013 IEEE 7th International Power Engineering and Optimization Conference (PEOCO)

View full text Add to dashboard Cite

This paper presents hybrid Taguchi-ArtificialNeural Network to detect incipient faults in oil-immersed power transformer. It involved the development of Artificial Neural Network (ANN) designs and embedding Taguchi methodology to fine tune the parameters of a backpropagation feed-forward ANN. Detection of incipient faults in power transformer is essential because it is one of the fundamental equipments in the power system. Dissolved gas analysis technique was used as it has been found as a reliable technique to detect incipient faults as it provides wealth of information in analyzing transformer condition. This study is based on IEC 60599 (2007) standard and historical data were used in the training and testing processes. Comparative studies were conducted between heuristic ANN design and optimized hybrid Taguchi-Neural Network. The results show the effectiveness of the optimized neural network using Taguchi methodology.

show abstract

Section: Introductionmentioning

confidence: 99%

The Taguchi- Artificial Neural Network approach for the detection of incipient faults in oil-filled power transformer

Zakaria

Johari

Musirin

2013

2013 IEEE 7th International Power Engineering and Optimization Conference (PEOCO)

View full text Add to dashboard Cite

show abstract

“…Traditionally, the design of brazing parameters and processes is based on long-time practical experience or trial-and-error approaches which are time consuming and could be sub-optimal. To avoid these problems, several research works have developed a computer-aided system based on some optimization techniques [3,4] to predict the optimum welding parameters from experimental data. In this study, we have applied the Taguchi-Neural Network technigue to optimally select the brazing parameters in our auto-brazing process.…”

Section: Introductionmentioning

confidence: 99%

Optimization of Induction Brazing Parameters for Stellite Strip of Steam Turbine Blade Using Taguchi-Neural Network

Muangsong

Sarawan

2013

KEM

View full text Add to dashboard Cite

To repair the damaged of steam turbine blades, the method of increasing wear resistance of the blade leading edge with brazing of stellite plates by induction heating has been addressed in this work. Induction brazing of a Cobalt-based alloy to SUS410Cb steam turbine blades in an electrical power plant has been carried out. Ag-Cu-Zn based material was chosen to be the filler metal sandwiched between the stellite strip and the turbine blade. In order to cope with the large size of blades, an automatic brazing process which used moving induction coils has been developed. In the proposed brazing process, there are three parameters that significantly affect the quality of the brazing joints including coil distance, moving coil speed, and power of induction heating. In this work, the optimum choice of brazing parameters is obtained by using a Taguchi-neural network technique. According to the results of our previous work, it is recommended to attain the temperature distribution at around 750°C for maximum strength and good quality brazing in the brazed components. The objective for the evaluation of brazing quality is therefore a function of this temperature and defined as the temperature deviation from the best brazing temperature. The design is verified and confirmed by the manufacturing of brazed joint applying suggested parameters. The experimental results showed that the Taguchi-Neural network method resulted in a better brazed quality than when using only the Taguchi method.

show abstract

Optimizing the auto-brazing process quality via a Taguchi-neural network approach in the automotive industry

Cited by 2 publications

References 5 publications

The Taguchi- Artificial Neural Network approach for the detection of incipient faults in oil-filled power transformer

The Taguchi- Artificial Neural Network approach for the detection of incipient faults in oil-filled power transformer

Optimization of Induction Brazing Parameters for Stellite Strip of Steam Turbine Blade Using Taguchi-Neural Network

Contact Info

Product

Resources

About