Effect of Heat on Computer‟s Processor Failures
Amal El-Berry1, Afrah Al-Bossly2
1Dr. Amal El-Berry, Department of Mechanical Engineering, National Research Center, Cairo, Egypt and Faculty of Engineering &Computer Science, Salman Bin Abdulaziz University, KSA.
2Dr. Afrah Al-Bossly, Department of Mathematics, Faculty of Science and Humanities Studies, Salman Bin Abdulaziz University, KSA.
Manuscript received on 06 March 2015 | Revised Manuscript received on 26 March 2015 | Manuscript Published on 30 March 2015 | PP: 57-60 | Volume-4 Issue-10, March 2015 | Retrieval Number: F0049031615/15©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: This paper presents the effect of heat on computer’s processor speed. There were two types of temperature variation that affect system performance: global temperature variations and local temperature variations. The disparity in power dissipation between active units and inactive units could result in severe hot spots on a chip, creating large temperature variations which could reduce functionality or caused timing failure. The goal of the analysis to understand the failure rate behavior of a particular item, Weibull++standard folio had been used to perform life data analysis. Degradation analysis was useful for tests performed on highly reliable products. This analysis consists of two steps: first, the failure times of the units on test were extrapolated using measurements of their degradation overtime and second, once these failure times were obtained, life data analysis is used to estimate the reliability of the product. Degradation was used to analyze the measurements of a computer processor decreasing performance. Then the failure time plot to compare the failure times that are expected from a design with a specified reliability to the actual failure times that are observed during a test. Data obtained from field failures could provide valuable information about how a product actually performs in the real world. The results indicated that the system will fail if any of the modes occurred and failure rate behavior for each failure mode was known and could been described with a life distribution and parameters. In life data analysis, it was assumed that the components being analyzed were non-repairable; that was. They were either discarded or replaced upon failure. However, for complex systems such as computers will be repaired (not discarded) upon failure. Failures were recurring events in the life of a repairable system, and data from such a system are known as recurrent event data. Weibull++ includes a choice of two methods for analyzing recurrent event data: parametric and non-parametric analysis. Event logs, or maintenance logs, capture information about a piece of equipment’s failures and repairs, such as the date/time the equipment failed and the date/time the equipment was restored. This information was useful for helping companies achieve productivity goals by giving insight about the failure modes, frequency of outages, repair duration, uptime/downtime and availability of the equipment.
Keywords: Reliability, maintenance, failures, Weibull++, thermal and lifetime.
Scope of the Article: Structural Reliability Analysis