An integrated replenishment and production control policy under inventory inaccuracy and time-delay
Introduction
In enterprise resource planning (ERP) or supply chain management (SCM) systems, the inventory records of raw materials, work-in-process (WIP), or final goods inventory might deviate from their real quantities. DeHoratius and Raman (2008) show that the inaccuracy of inventory record happens due to theft, miscounting, misplacing, deteriorating, etc. It has been reported in literature that inventory inaccuracy may worsen the performance of inventory management and production control. For example, French (1980) finds that the WIP inventory inaccuracy distorts the effectiveness of materials requirement planning (MRP) system. Disney et al. (2000) show that the WIP inventory inaccuracy in a shop floor causes a time-delay in the WIP feedback loop in the production and inventory control system, which makes it difficult to construct a good control policy. Kang and Gershwin (2005) point out that a very severe out-of-stock may be caused by a very small rate of undetected stock loss. DeHoratius and Raman (2008) report that inaccuracies cost retailers as much as 10% of their profit.
Therefore, for a production/inventory system, inventory inaccuracy has a significant negative impact on the performance of raw materials replenishment and production control. However, existing research on replenishment and production control usually focuses on the system whose inventory data is completely accurate. The replenishment and production control problem for a production/inventory system with inventory inaccuracy has not been investigated sufficiently. So it is necessary to develop a robust replenishment and production control policy that can hedge against the negative impact of inventory inaccuracy, or in other words, that is insensitive to the inaccurate records of inventory. We have focused on this issue for recent years. Wang and Yu (2012) investigate the robust production control problem for a single machine and single part-type manufacturing system with inaccurate WIP inventory, and propose a robust policy that is insensitive to the observation error of inventory. Chan and Wang (2014) extend this research to the case of multiple machines and multiple product-types manufacturing system, but without considering the lead-time of replenishment. Wang and Chan (2015) study the robust replenishment and production problem for a single-stage production/inventory system with inventory inaccuracy and lead-time for replenishment, which, however, only produces one type of product. In this paper, we extend the research on the optimal replenishment and production control problem under inventory inaccuracy to a more complicated situation and propose a new solution. The main differences between this paper and the previous three works (Wang and Yu, 2012, Chan and Wang, 2014, Wang and Chan, 2015) are on the following three aspects:
- (1)
Refined model. In the previous three works, inventory inaccuracy is modeled as observation error, i.e., the observed inventory equals the physical inventory plus the observation error at any time. Inventory inaccuracy is assumed to be independent over time horizon. In this situation, the difference between the recorded inventory and the physical inventory level may change sharply from one period to another, which is not realistic. In this paper, a new model is provided, in which we assume that inventory inaccuracy occurs due to theft, misplacing, damage, etc., and that the events resulting in inventory inaccuracy only affect the physical inventory but are not reflected in the inventory record. Moreover, in this paper, we consider the accumulation of inventory inaccuracy, which is more realistic.
- (2)
More complicated system. The system studied in this paper is more complicated than those in our previous works. Compared to Wang and Yu (2012) and Wang and Chan (2015), in which only one type of product is manufactured, in this paper we consider an inventory/production system that orders and consumes multiple kinds of raw materials and produces multiple types of products on multiple machines. Compared to Chan and Wang (2014), in which lead-time for replenishment is not considered, in this paper the lead-time for replenishment is also taken into consideration. Therefore, in this paper, we investigate a production/inventory system with multiple product-types, multiple machines, lead-time for replenishment, and inaccurate inventory record.
- (3)
New solution. In the previous works, the robust production control policy generates the production rate (i.e., the decision variable) only based on the inventory record. This idea works based on an unrealistic assumption that the discrepancy between the inventory record and the physical inventory is independent from one period to another. Since more realistic factors are considered and new mathematical model is constructed in this paper, the idea of the previous works does not work any more. We develop a new solution and construct a new replenishment and production control policy based on the conditional expectation of the physical inventory level, which is not difficult to estimate.
The rest of this paper is organized as follows: In Section 2, a literature review of existing research is given. In Section 3, we develop the mathematical formulation of the problem of optimal replenishment and production control for a multiple machines and multiple product-types production/inventory system under inventory inaccuracy and time-delay. In Section 4, a new conditional expectation-based replenishment and production control policy is proposed for such a system. In Section 5, numerical experiments are conducted to examine the performance of the proposed policy. In Section 6, main contributions of this research are summarized and some problems for future research are presented.
Section snippets
Literature review
In this section, we give a brief review on the work related to this research from three perspectives, i.e. inventory inaccuracy, robust production scheduling under uncertainty and optimization problems under partial information.
Problem description
In this section, we define and model the robust replenishment and production control problem for a multiple machines and multiple product-types production/inventory system with inventory inaccuracy and lead-time of replenishment. This system is composed of a replenishment process, a production process and a demand satisfying process. In the replenishment process, the system places orders for all type of raw materials from specific raw material suppliers to replenish the stocks, which are
The integrated replenishment / production policy
The replenishment and production control problem Eqs. (1)–(12) is solved in two steps. First, we consider a multiple machines and multiple product-types production/inventory system without inventory inaccuracy, then construct the model of its optimal replenishment and production control problem, and propose a simplified replenishment and production control policy for this system. Finally, based on structure of the simplified policy and the conditional probability distribution of physical
Numerical experiments
In this section, for a multiple machines and multiple product-types production/inventory system with inventory inaccuracy and time-delay, four numerical experiments are conducted to examine the performance of the proposed conditional expectation-based replenishment and production control policy (which is named Robust Policy for short, i.e., Eqs (27) and (28)) by comparing with the Simplified Policy Eq. (20) and (23).
Conclusion
In this paper, we study the robust replenishment and production control problem for a multiple machines and multiple product-types production/inventory system with inventory inaccuracy and time-delay.
Firstly, we study the optimal replenishment and production control problem for a multiple machines and multiple product-types production/inventory system without inventory inaccuracy. The problem is solved based on the principle of dynamic programming and an approximate optimal replenishment and
Acknowledgement
This research is supported by the National Natural Science Foundation of China under Grant 61374198, the Project Funded by the Priority Academic Program Development of Jiangsu Higher Education Institutions and the Suzhou University Research Foundation (2016jb07, SZXYQNL2017006).
References (37)
- et al.
ERP and SCM systems integration: The case of a valve manufacturer in China
Inf. Manage.
(2008) - et al.
The effect of inventory record inaccuracy in information exchange supply chains
Eur. J. Oper. Res.
(2015) - et al.
Optimal radio frequency identification deployment in a supply chain network
Int. J. Prod. Econ.
(2010) - et al.
Genetic algorithm optimisation of a class of inventory control systems
Int. J. Prod. Econ.
(2000) - et al.
Inventory inaccuracy and supply chain performance: a simulation study of a retail supply chain
Int. J. Prod. Econ.
(2005) - et al.
A new robust optimization approach for scheduling under uncertainty: II. Uncertainty with known probability distribution
Comput. Chem. Eng.
(2007) - et al.
Evaluation of cycle-count policies for supply chains with inventory inaccuracy and implications on RFID investments
Eur. J. Oper. Res.
(2014) - et al.
A new robust optimization approach for scheduling under uncertainty: I. Bounded uncertainty
Comput. Chem. Eng.
(2004) Inventory inaccuracies in the wholesale supply chain
Int. J. Prod. Econ.
(2011)- et al.
Inventory inaccuracy in retail stores due to theft: an analysis of the benefits of RFID
Int. J. Prod. Econ.
(2009)
Assessing the impact of inventory inaccuracies within a newsvendor framework
Eur. J. Oper. Res.
A hierarchical model of the impact of RFID practices on retail supply chain performance
Exp. Syst. Appl.
Comparing improvement strategies for inventory inaccuracy in a two-echelon supply chain
Euro. J. Oper. Res.
A capacity constrained production-inventory system with stochastic demand and production times
Int. J. Prod. Res.
Production‐inventory systems with imperfect advance demand information and updating
Nav. Res. Logist.
Partial-information state-based optimization of partially observable Markov decision processes and the separation principle
IEEE Trans. Autom. Control
Robust production control policy for a multiple machines and multiple product-types manufacturing system with inventory inaccuracy
Int. J. Prod. Res.
Inventory record inaccuracy: an empirical analysis
Manage. Sci.
Cited by (13)
IACPPO: A deep reinforcement learning-based model for warehouse inventory replenishment
2024, Computers and Industrial EngineeringApplication of maximum principle to optimization of production and storage costs
2021, Archives of Control SciencesOptimal control policy to production and inventory system with promotion effort dependent demand in segmented market
2021, Yugoslav Journal of Operations ResearchSimulation-based optimisation of replenishment policy in supply chains
2021, International Journal of Logistics Systems and Management