Virtual production control system and method and computer program product thereof

• US 8,515,793 B2
• Filed: 03/16/2010
• Issued: 08/20/2013
• Est. Priority Date: 08/11/2009
• Status: Active Grant

• Current Assignee: National Cheng KUNG University (Government of The Republic of China)
• Original Assignee: National Cheng KUNG University (Government of The Republic of China)
• Inventors: Yang, Haw-Ching, Cheng, Fan-Tien, Chen, Ying-Liang
• Primary Examiner(s): Miller, Alan S
• Application Number:
  US12/724,553
• Publication Number:
  US 20110040596A1
• Time in Patent Office: 1,253 Days
• Field of Search: 705 711- 742, 700 40-117, 706 1- 62
• US Class Current: 705/7.11
• CPC Class Codes: G06Q 10/04 Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem" market predictions or forecasting for commercial activities G06Q30/0202
• CPC Class Codes: G06Q 10/087 Inventory or stock management, e.g. order filling, procurement or balancing against orders
• CPC Class Codes: G06Q 50/04 Manufacturing
• CPC Class Codes: Y02P 90/30 Computing systems specially adapted for manufacturing

Abstract

A virtual production control system (VPCS), and a virtual production control method and a computer program product thereof are provided. At first, the VPCS processes historical work-in-process (WIP) information and a current shipping plan sent from a supplier side, thereby obtaining a plurality of sets of WIP input/output historical data and a goods output schedule. Then, the VPCS performs an integer programming (IP) method to find the latest output schedule in accordance to the current shipping plan; uses a genetic algorithm (GA) to fit the historical distributed-parameters; adopts a neural network (NN) method to predict the future distributed-parameters of production; and finally utilizes a Petri Nets to simulate and obtain a latest feasible input schedule and a latest feasible output schedule.

Claims

1. A virtual production control method for effectively conjecturing delivery capability of a real factory at a supplier side, the virtual production control method comprising:

processing a current shipping plan and a plurality of sets of historical WIP (Work-In-Process) data respectively belonging to a plurality of historical production cycles sent from the supplier side, thereby obtaining a plurality of historical input schedules and a plurality of historical output schedules belonging to said historical production cycles, an expected production capacity limit of a next production cycle following said historical production cycles, and an loss rate of the most recent one of said historical production cycles;

performing an integer programming method by a computer using said current shipping plan and one of said historical input schedules belonging to the most recent one of said historical production cycles, to compute a latest ideal input schedule and a latest ideal output schedule belonging to said next production cycle; and

simulating and obtaining a latest feasible input schedule and a latest feasible output schedule belonging to said next production cycle by using said historical input schedules, said historical output schedules, and said latest ideal output schedule belonging to said next production cycle in accordance with a distributed-parameters estimation method, a neural network method and Petri Nets.

2. The virtual production control method as claimed in claim 1, further comprising:

generating an inventory profile in accordance with said expected production capacity limit, said loss rate, said latest feasible input schedule, said latest feasible output schedule and said current shipping plan, said inventory profile comprising the most updated production status and WIP quantity, and estimated inventory turnover rate and idle material.

3. The virtual production control method as claimed in claim 1, further comprising:

generating a delivery profile in accordance with said expected production capacity limit, said loss rate, said latest feasible output schedule and said current shipping plan, said delivery profile comprising estimated production date and quantity, an estimated order-fill rate, an estimated delayed delivery quantity, delayed delivery reasons and production capacity bottlenecks.

4. The virtual production control method as claimed in claim 1, further comprising:

said integer programming uses a delivery method achieving a maximum order-fill rate as an objective to conjecture a output schedule and a input schedule, and is limited by an actual production capacity of said supplier side, and is restricted by a safe inventory strategy of said supplier side.

5. The virtual production control system as claimed in claim 1, further comprising:

conjecturing a plurality of sets of historical input distributed-parameters data, a plurality of sets of historical output distributed-parameters data by using said historical input schedules and said historical output schedules in accordance with said distributed-parameters estimation method;

predicting a set of estimated input distributed-parameters data, a set of estimated output distributed-parameters data of said next production cycle by using said sets of historical input distributed-parameters data, and said sets of historical output distributed-parameters data in accordance with said neural network method; and

simulating and obtaining said latest feasible input schedule and said latest feasible output schedule belonging to said next production cycle by using said latest ideal output schedule, said set of estimated input distributed-parameters data, said set of estimated output distributed-parameters data belonging to said next production cycle in accordance with said Petri Nets.

6. The virtual production control method as claimed in claim 5, wherein said distributed-parameters estimation method comprises:

a Kolmogorov-Smirnov test used for testing the maximum absolute error between a fitted value and an expected value; and

a genetic algorithm used for combining said F-test and said Kolmogorov-Smirnov test.

7. The virtual production control method as claimed in claim 1, further comprising:

providing a material requirements plan by said manufacturer side to said supplier side; and

fabricating said current shipping plan by said supplier side in accordance with said material requirements plan.

8. A computer program product stored on a non-transitory tangible computer readable recording medium, which, when executed, performs a virtual production control method for effectively conjecturing delivery capability of a real factory at a supplier side, the virtual production control method comprising:

processing a current shipping plan and a plurality of sets of historical WIP information respectively belonging to a plurality of historical production cycles sent from a supplier side, thereby obtaining a plurality of historical input schedules and a plurality of historical output schedules belonging to said historical production cycles, an expected production capacity limit of a next production cycle following said historical production cycles, and an loss rate of the most recent one of said historical production cycles;

performing an integer programming by using said current shipping plan and one of said historical input schedules belonging to the most recent one of said historical production cycles, thereby computing a latest ideal input schedule and a latest ideal output schedule belonging to said next production cycle; and

simulating and obtaining a latest feasible input schedule and a latest feasible output schedule belonging to said next production cycle by using said historical input schedules, said historical output schedules, and said latest ideal output schedule belonging to said next production cycle in accordance with a distributed-parameters estimation method, a neural network method and Petri Nets.

9. The computer program product as claimed in claim 8, wherein the method further comprises:

conjecturing a plurality of sets of historical input distributed-parameters data, a plurality of sets of historical output distributed-parameters data by using said historical input schedules and said historical output schedules in accordance with said distributed-parameters estimation method;

predicting a set of estimated input distributed-parameters data, a set of estimated output distributed-parameters data of said next production cycle by using said sets of historical input distributed-parameters data, and said sets of historical output distributed-parameters data in accordance with said neural network method; and

simulating said latest feasible input schedule and said latest feasible output schedule belonging to said next production cycle by using said latest ideal output schedule, said set of estimated input distributed-parameters data, said set of estimated output distributed-parameters data belonging to said next production cycle in accordance with said Petri Nets.

10. The computer program product as claimed in claim 8, wherein said distributed-parameters estimation method comprises:

a Kullback-Leibler Distance used for determining a distance between two probabilistic models;

a Kolmogorov-Smirnov test used for testing the maximum absolute error between a fitted value and an expected value; and

a genetic algorithm used for combining said F-test and said Kolmogorov-Smirnov test.