|
| << vorige | volgende >> |
Tijdschrift beschrijving
Alle jaargangen van het bijbehorende tijdschrift
Alle afleveringen van het bijbehorende jaargang
Alle artikelen van de bijbehorende aflevering
Details van artikel 22 van 36 gevonden artikelen
| Titel: |
Multi-Quality Prediction Model of CNC Turning Using Back-Propagation Network |
| Auteur: |
Tian-Syung Lan Chih-Yao Lo Ming-Yung Wang Yen-An Yu |
| Verschenen in: |
Information technology journal |
| Paginering: | Jaargang 7 (2008) nr. 6 pagina's 911-917 |
| Jaar: |
2008 |
| Inhoud: |
In this study, the four cutting parameters (cutting depth, feed rate, speed and tool nose runoff) with three levels (low, medium and high) are selected to determined the 34 = 81 sets of full experimental combinations. The ECOCA-PC3807 CNC lathe is utilized to diameter finishing turn the S45C. The surface roughness (Ra), tool wear ratio (μm-2) and cutting force are additionally measured as quality objectives. The BPN is moreover introduced to learn the selected 45 sets of experimental results. The remaining 36 sets of experimental results are furthermore used to verify and construct a multiple quality predictor of CNC turning. Considering the learning rate as 1 and momentum factor as 0.5, the results of 4000 times of BPN training through a hidden layer indicated that the prediction of surface roughness reached 95.87% of accuracy, the quality objective of tool wear ratio reached 94.32% of accuracy, the quality of cutting force reached 92.29% accuracy and the overall prediction accuracy of the multiple quality process predictor could reach 94.16%. The results not only provide the CNC turning operations with an economic and prospective multiple quality analytic method but also establish machining references for CNC turning industry with profound insight. Under the considerations of multiple qualities, this study definitely explored, expanded and realized the prediction mechanism and values of cutting parameters. |
| Uitgever: |
Asian Network for Scientific Information, Pakistan (provided by DOAJ) |
| Bronbestand: |
Elektronische Wetenschappelijke Tijdschriften |
Details van artikel 22 van 36 gevonden artikelen
| << vorige | volgende >> |