Order-based material management system

• US 6,516,301 B1
• Filed: 05/03/1999
• Issued: 02/04/2003
• Est. Priority Date: 05/03/1999
• Status: Expired due to Term

• Current Assignee: WSOU Investments, LLC (WSOU Holdings, LLC)
• Original Assignee: Lucent Technologies, Inc. (Nokia Corporation)
• Inventors: Aykin, Turgut
• Primary Examiner(s): Choi, Kyle J.
• Assistant Examiner(s): Reagan, James A.
• Application Number:
  US09/304,294
• Time in Patent Office: 1,373 Days
• Field of Search: 705/10, 705/8
• US Class Current: 705/7.25
• CPC Class Codes: G06Q 10/06315 Needs-based resource requirements planning or analysis
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 30/0202 Market predictions or forecasting for commercial activities

Abstract

An Order Based Materials Management (OBMM) method using forecasts of actual customer orders to determine component stocking levels. There may be several types of orders and several types of customer demand forecasts for them. Each order type is specified by a variable Bill Of Materials called an “order profile”—a multivariate probability distribution with each random variable representing the uncertain number of units of a component or subassembly that may be needed to build a customer order of that type. The profile of an order type is represented by a multivariate probability distribution of all components/subassemblies that may be needed for an order of that type, including the correlation between the numbers of units of different components needed for an order in the analysis. Using i) the desired order fill rate, ii) component lead times, iii) forecasts, and iv) forecast error variances and their distributions, OBMM determines a target number of orders for each order type over the lead times (plus one review period) for which to maintain materials. To determine component level orders and inventory quantities to achieve the desired order fill rate, target numbers and order profiles are then combined to obtain a joint multivariate distribution of components that may be needed for the target numbers of orders. Order-up-to periodic inventory policies (including safety stocks) for components and subassemblies are developed recursively from this combined multivariate distribution.

Claims

1. An order-based material management method for managing a plurality of customer orders of a plurality of order types, each order comprising a plurality of components that vary from one order to another, the method comprising the steps of:

a) setting a desired order fill rate, wherein said order fill rate is an average percentage of the times all components needed for an order will be available in inventory in required quantities when the order arrives;

b) establishing order profiles for each type of order to describe order-to-order variability, wherein said order profiles are represented by ajoint normal probability distribution of a plurality of variables, wherein each random variable represents an uncertain number of units of a component that may be needed to build a customer order of that type;

c) determining a lead time for each component required by each type of order and arranging the lead times in order by length of time;

d) choosing a component having the longest lead time;

e) forecasting a quantity of expected customer orders for each type of order over the lead time of the chosen component plus one review period;

f) computing a target number of orders for each of the order types at the order fill rate;

g) computing available quantities over the lead time of the chosen component plus one review period of components having lead times greater than the chosen component;

h) computing a component requirements distribution for the target number of orders determined in step (f) for each of the order types;

i) combining, through augmentation and transformation, the components requirements distributions for all of the order types determined in step (h) into a components requirements distribution for all order types;

j) determining needed component inventory levels over the lead time of the chosen component plus one review period for all components having a lead time which is the same as or less than the chosen component, using the component inventory levels of all components having lead times greater than the chosen component;

k) ordering components required to attain the inventory levels determined in step (j) for the chosen component and all other components with the same lead time; and

l) choosing another component, having a lead time less than the chosen component;

m) repeating the method from steps (e) through (l), until all components have been chosen.

2. The order-based material management method of claim 1, further comprising the steps, after step (m) of

n) evaluating actual lead times and order levels during a predetermined period;

o) revising the forecasts in accordance with the evaluation of step (n); and

p) repeating the method from step (e).

3. The order-based material management method of claim 1, in which the predetermined period is a period comprising a lead time plus a review period.

4. The order-based material management method of claim 3, in which the lead times for the components are used in step (h) as a factor in computing the component requirements distribution.

5. The order-based material management method of claim 4, in which the order profile includes at least one factor giving a correlation between the numbers of units of every two different components needed for an order type.

6. The order-based material management method of claim 1, in which the target number of orders is calculated as:

7. The order-based material management method of claim 6, in which the order profile includes at least one factor giving a correlation between the numbers of every two units of different components needed for an order type.

8. The order-based material management method of claim 6, in which the target number of orders is calculated for each order type.

9. The order-based material management method of claim 1, in which the component requirements distribution of step (h) for each order type k is determined by the steps of:

$\begin{array}{c}\mathrm{calculating}<br><br>\text{\hspace{1em}<br><br>}<br><br>a<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{mean}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{vector}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}^k<br><br>\text{;<br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}_{\mathrm{TNO}}^k=\text{\hspace{1em}<br><br>}<br><br>\underset{i=1}{\overset{{\mathrm{TNO}}_{t,\left(R+L\right)}^k}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}^k\\ =\text{\hspace{1em}<br><br>}<br><br>\left({\mathrm{TNO}}_{t,\left(R+L\right)}^k\right)<br><br>{\mathrm{\mu <br><br>}}^k;<br><br>\end{array}$$\begin{array}{c}\mathrm{calculating}<br><br>\text{\hspace{1em}<br><br>}<br><br>a<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{covariance}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{matrix}<br><br>\text{\hspace{1em}<br><br>}<br><br>V<br><br>\text{;<br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>V_{\mathrm{TNO}}^k=\text{\hspace{1em}<br><br>}<br><br>\underset{i=1}{\overset{{\mathrm{TNO}}_{t,\left(R+L\right)}^k}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>V^k\\ =\text{\hspace{1em}<br><br>}<br><br>\left({\mathrm{TNO}}_{t,\left(R+L\right)}^k\right)<br><br>V^k;<br><br>\end{array}$

combining said requirements distribution for different order types through an augmented distribution of demand vectors;

where TNO^k_t,(R+L) is the forecast total number of orders, made at time t of the number of orders of type k during the next (R+L) periods, where L is the lead time and R is the review period.

10. The order-based material management method of claim 9, in which the order-up-to levels of step (e) are determined from the augmented distribution of demand vectors and the desired order fill rate.

11. The order-based material management method of claim 9, in which the component inventory levels of step (j) are determined from the augmented distribution of demand vectors and a predetermined order fill rate.

12. The order-based material management method of claim 9, further comprising, after the substep of combining said requirements distribution for different order types through an augmented distribution of demand vectors, the substep of transforming said requirements distribution of said demand vectors to obtain an overall component distribution.

13. An order-based material management method for managing a plurality of customer orders of a plurality of order types, each order comprising a plurality of components that vary from one order to another, the method comprising the steps of:

a) setting a desired order fill rate, wherein said order fill rate is an average percentage of the times all components needed for an order will be available in inventory in required quantities when the order arrives;

b) establishing order profiles for each type of order to describe order-to-order variability, wherein said order profiles are represented by a joint normal probability distribution of a plurality of variables, wherein each random variable represents an uncertain number of units of a component that may be needed to build a customer order of that type;

c) forecasting a quantity of expected customer orders for each type of order for a predetermined period;

d) combining the forecast quantities of customer orders with the associated order profiles to determine an overall multivariate component demand distribution for the plurality of components; and

e) from the multivariate component distribution, determine order-up-levels for each of the components to achieve the desired order fill rate.

14. The order-based material management method of claim 13, further comprising the step of:

f) ordering at least one of the components based on the order-up-to level from step (e) and an on hand inventory and an on order quantity for the component.

15. The order-based material management method of claim 13, further comprising the step of determining a lead time for each component in the order profile for each type of order.

16. The order-based material management method of claim 15, in which the lead times for the components are used in step (d) as a factor in computing the component demand distribution.

17. The order-based material management method of claim 16, which the components are ordered by their associated lead times, and the order-up-to levels determined in step (e) are computed iteratively using the ordered lead times of the components.

18. The order-based material management method of claim 13, in which the order profile includes a correlation between the numbers of units of every two different components needed for an order type.

19. The order-based material management method of claim 13, in which the component demand distribution of step (d) for each order type k is determined by the steps of:

$\begin{array}{c}\mathrm{calculating}<br><br>\text{\hspace{1em}<br><br>}<br><br>a<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{mean}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{vector}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}^k<br><br>\text{;<br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}_{\mathrm{TNO}}^k=\text{\hspace{1em}<br><br>}<br><br>\underset{i=1}{\overset{{\mathrm{TNO}}_{t,\left(R+L\right)}^k}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>{\mathrm{\mu <br><br>}}^k\\ =\text{\hspace{1em}<br><br>}<br><br>\left({\mathrm{TNO}}_{t,\left(R+L\right)}^k\right)<br><br>{\mathrm{\mu <br><br>}}^k;<br><br>\end{array}$$\begin{array}{c}\mathrm{calculating}<br><br>\text{\hspace{1em}<br><br>}<br><br>a<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{covariance}<br><br>\text{\hspace{1em}<br><br>}<br><br>\mathrm{matrix}<br><br>\text{\hspace{1em}<br><br>}<br><br>V<br><br>\text{;<br><br>}<br><br>\text{\hspace{1em}<br><br>}<br><br>V_{\mathrm{TNO}}^k=\text{\hspace{1em}<br><br>}<br><br>\underset{i=1}{\overset{{\mathrm{TNO}}_{t,\left(R+L\right)}^k}{\sum <br><br>}}<br><br>\text{\hspace{1em}<br><br>}<br><br>V^k\\ =\text{\hspace{1em}<br><br>}<br><br>\left({\mathrm{TNO}}_{t,\left(R+L\right)}^k\right)<br><br>V^k;<br><br>\end{array}$

combining said requirements distribution for different order types through an augmented disribution of demand vectors;

where TNO^k_t,(R+L) is the forecast total number of orders, made at time t of the number of orders of type k during the next (R+L) periods, where L is the lead time and R is the review period.

20. The order-based material management method of claim 19, in which the order-up-to levels of step (e) are determined from the augmented distribution of demand vectors and the desired order fill rate.