A New Model for Evaluating the Volume of Laptop Spare Parts Depending on Users’ Intentions Related to Laptop Use Time

Abstract

This paper is a continuing studying about the volume of laptop spare parts, and it takes into account the users' repair intentions. We found that when a laptop is no longer working, whether it will be repaired is determined by the user's intention. The user's intention is related to the number of times that his laptop fails and to its use time, i.e., how long the laptop has been used. Therefore, this paper focuses on the volume of laptop spare parts calculation equation. First, we assume the failure process of laptop parts is a Poisson process, and the failure probability of laptop spare parts can calculate at different times. We deduce the transition probability formula of users' repair intention related to laptop use time. Finally, the equation to calculate the volume of spare parts is presented in this paper and is verified by simulation. The simulation results agree with the theoretical values. From the simulation curve, we know that the volume of spare parts will decrease sharply when the laptop use time is long. After having used a laptop for five years, a user is less likely to have a broken laptop repaired. Therefore, laptop factories could reduce the inventories of spare parts.

Forecasting spare part demand with installed base information: A review

“…The part replacement probability is also discussed by Lu & Wang (2015), who assume that the repair willingness of a customer decreases with the cumulative number of breakdowns the product as a whole has experienced in the past. Lu & Hjelle (2016) extend this idea by evaluating whether users will have their product repaired depending on both the number of past failures and the use time. Yamashina (1989) includes new product installations, which are added to the installed base, together with product survival, where products leave the installed base, over time, and thus addresses the entire product life cycle.…”

“…Besides, we find that most methods are concerned with the estimation of many parameters, and as such they necessitate data collection and analysis. This might be a challenge Paper Failure process Shaunty & Hare Jr (1960) Constant failure rate Ritchie & Wilcox (1977) Constant failure rate Fortuin (1984) Exponential time-to-failure distribution Yamashina (1989) Exponential time-to-failure distribution Petrovic & Petrovic (1992) Constant failure rate Ghodrati & Kumar (2005b) Weibull time-to-failure distribution Ghodrati & Kumar (2005a) Exponential time-to-failure distribution Deshpande et al (2006) No distribution specified Ghodrati et al (2007) Exponential time-to-failure distribution Hong et al (2008) Exponential time-to-failure distribution Jin & Liao (2009) Exponential and Weibull time-to-failure distribution Lanza et al (2009) Weibull time-to-failure distribution Ghodrati (2011) Exponential and Weibull time-to-failure distribution Minner 2011Bernoulli process, probability dependent on part age Wang & Syntetos (2011) Weibull time-to-failure distribution Barabadi (2012) Weibull time-to-failure distribution Ghodrati et al (2012) Exponential time-to-failure distribution Jin & Tian 2012Exponential time-to-failure distribution Hong & Meeker (2013) Weibull time-to-failure distribution Barabadi et al (2014) No distribution specified Hellingrath & Cordes (2014) No distribution specified Chou et al (2015) No distribution specified Hu et al 2015Weibull time-to-failure distribution Kontrec et al (2015) Rayleigh time-to-failure distribution Lu & Wang (2015) Exponential time-to-failure distribution Chou et al (2016) No distribution specified Gharahasanlou et al (2016) Weibull time-to-failure distribution Liu & Tang (2016) Weibull time-to-failure distribution Lu & Hjelle (2016) Exponential time-to-failure distribution Kim et al (2017)...…”

“…Such approaches, as presented by Jalil et al (2011) and Romeijnders et al (2012), allow to apply a simple method that requires little (advanced) data and enrich it with installed base information. Installed base information could thus be used to adjust Paper Replacement probability Ritchie & Wilcox (1977) Exponential replacement probability distribution Hong et al (2008) Exponential replacement probability distribution Chou et al (2015) Exponential replacement probability distribution Lu & Wang (2015) Probabilities based on survey data, no distribution specified Chou et al (2016) Exponential replacement probability distribution Lu & Hjelle (2016) Probabilities based on survey data, no distribution specified Table 10: Assumptions on the replacement probability traditional methods, whilst reducing the need for a complex forecasting method.…”

“…Kontrec et al (2015) No evaluation/validation of method performance. Lu & Wang (2015); Lu & Hjelle (2016) (1) Estimates of user repair willingness necessary, (2) conclusions not necessarily true for capital goods. Chou et al (2016) (1) Estimate of combined replacement-discard probability necessary, (2) many data observations necessary for valid regression.…”

The value of installed base information for spare part inventory control

“…Some works (additionally) consider the anticipation of potential future discards, decreasing the number of active machines (see for example Chou et al, 2015Chou et al, , 2016Kim et al, 2017;Minner, 2011;Stormi et al, 2018;, or expiring service contracts (Pince et al, 2015) as a source of IBI. Similarly, Hong et al (2008), Lu and Hjelle (2016), Lu and Wang (2015), and Ritchie and Wilcox (1977) also include in their forecasts the probability of a future failed part not being replaced, based on, for example, the active machine being too old.…”