Forecasting and Purchasing Planning for Shelf Life-Limited Instruments Equipment Spare Parts

Main Article Content

Sasithorn Kitti-udomporn Suwitchaporn Witchakul


         Forecasting and Purchasing Planning for Shelf Life-Limited Instruments Equipment Spare Parts with a case study of company, purchasing spare parts from factories by selecting a forecasting method and applying a mathematical model. The purposes of this research are to improve the inventory quantity to be suitable for customers’ demand, to reduce holding cost and to minimize the total inventory cost. In the past, the company operations didn’t have purchasing planning strategy in the case study, the purchasing would be ordered when the inventory level is 0 that result shortage spare parts sometimes and the company had the policy about the spare parts with a limited 5-years lifetime. There were 17 items or 80% of total expired spare parts value that would be taken for forecasting and purchasing planning in this case study. We propose a new strategy about applying a mathematical model for purchasing planning spare parts that minimize the total inventory cost by using a new safety stock (SS) and customers’ demand that is the most accurate forecasting method with the lowest Mean Absolute Deviation (MAD) from 5 forecasting methods: 1) Moving Average, 2) Single Exponential Smoothing, 3) Double Exponential Smoothing, 4) Holt-Winters Smoothing, 5) Monte Carlo Simulation. From experiments, 17 items of the spare parts were the most suitable with Moving Average, Single Exponential Smoothing and Double Exponential Smoothing Method. In addition, this study calculated the new safety stock level at 95% confident level for new purchasing planning next year. Finally, The results of this study were found that the mathematical model for purchasing planning spare parts, could prevent the inventory shortage, reduce holding cost and minimize the total inventory cost from the current purchases of all items by 8,384,223 baht or decrease the average cost of 493,189.59 baht/year that is 17.55%


Article Details

Research Article


[1] P. Lalitaphorn, “Inventory Management in Supply Chains,” Bangkok: Technology Promotion Association (Thailand-Japan), 2016.
[2] W. Chaimee, “Supply Chain Management and Operations,” Bangkok: TPIM, 2009.
[3] S. Rungmaneerat, W. Panyangam, and P. Wangphanitcharoen, “The Application of the Advanced Purchasing Planning for Raw Material with the Dynamic Model,” Industrial Engineering Network Conference, Phetchaburi, Oct. 17-19, 2012.
[4] W. Phupha, “The Application of Monte Carlo Simulation Model to Determine Suitable Order Quantity: A Case Study of Raw Material Purchasing in Food Processing Factory,” vol. 88, 2014, pp. 41-56.
[5] K. Phabu, W. Panyangam, and N. Choomrit, “The Determination of Suitable Order Quantity with Dynamic Model: A Case Study of Rice Inventory at the Sample Rice Mill,” Industrial Engineering Network Conference, Phetchaburi, Oct. 2012, pp. 1899-1904.
[6] H.M. Wagner, and T.M. Whitin, “Dynamic Version of the Economic Lot Size Models,” Management science, 1958, pp. 89-96.
[7] J.R. Evans, “An Efficient Implementation of the Wagner-Whitin Algorithm for Dynamic Lot-Sizing,” Journal of Operations Management, Vol. 5, 1985, pp. 229-235.
[8] J.J. Gonzalez, and R. Tullous, “The Lot Size Ordering Problem Using the Wagner-Whitin Model: A Spreadsheet Version,” Proceedings of the POMS, 2002.
[9] Z. Hu, and G. Hu, “A two-stage stochastic programming model for lot-sizing and scheduling under uncertainty,” Int. J. Production Economics, vol. 180, 2016, pp.198-207.
[10] G. Relph, and M. Newton, “Both Pareto and EOQ have limitation combining them delivers a powerful management tool for MRP and Beyond,” Int. J. Production Economics, vol. 157, 2014, pp. 24-30.