|
The development of supplier comparison using lower process capability index for Weibull distribute on model |
|---|---|
| รหัสดีโอไอ | |
| Creator | 1. Erawin Thavorn 2. Prapaisri Sudasna-na-Ayudthya |
| Title | The development of supplier comparison using lower process capability index for Weibull distribute on model |
| Publisher | Faculty of Engineering, Khon Kaen University |
| Publication Year | 2564 |
| Journal Title | Engineering and Applied Science Research |
| Journal Vol. | 48 |
| Journal No. | 3 |
| Page no. | 295-306 |
| Keyword | Supplier comparison, Process capability indices, Weibull distribution, Durability, Lifetime |
| URL Website | https://www.tci-thaijo.org/index.php/easr/index |
| Website title | Engineering and Applied Science Research |
| ISSN | 2539-6161 |
| Abstract | Durability, one of the dimensions of quality, is the important criterion for comparing suppliers. In many industries, durability is widely measured by lifetime data modeled with Weibull distribution because of its flexible shape. The process capability indices (PCIs) is an appropriate tool for comparing suppliers regarding quality aspect. Many methods for comparing suppliers using the PCIs are developed to correspond to manufacturing conditions. However, the methods cannot apply with the lifetime data since they are developed under the normality assumption. The mentioned violation leads to probably misleading results in comparison. To consider the lifetime, this paper proposes the new supplier comparison using the PCIs for Weibull distribution model. Two parameters (scale and shape) of the Weibull distribution are studied. Since the shape parameter is sensitive to the PCIs estimation, this paper emphasizes on various shape parameters, e.g. symmetric, right, and left skewed. Regarding the lifetime, this paper studies single quality characteristic and the lower PCIs (Cpl). The producer's risk and the power of test obtained from Monte Carlo simulation are used to evaluate the performance of the proposed method. This method is compared with supplier comparison methods applying percentile PCIs and Box-Cox transformation for the PCIs estimation. |
