Machine maintenance optimization with dynamic maintenance intervals

Patent metadata

Field	Value
Publication number	US-9977787-B2
Application number	US-201615013188-A
Country	US
Kind code	B2
Filing date	Feb 2, 2016
Priority date	Feb 2, 2016
Publication date	May 22, 2018
Grant date	May 22, 2018

Abstract

The present description provides data analysis for machine maintenance scheduling. For example, dynamic maintenance intervals are assigned for each machine being scheduled. Then, a system is provided for implementing a particle swarm optimization for finding an optimized maintenance schedule. In the optimization, an objective function is defined for maximizing production while minimizing relative maintenance cost.

First claim

What is claimed is:

1. A computer program product, the computer program product being tangibly embodied on a non-transitory computer-readable storage medium and comprising instructions that, when executed, are configured to cause at least one computing device to:
access a demand database storing a plurality of demands for maintenance schedules, each demand specifying a plurality of components for maintenance, at least one initial maintenance interval for each component of the plurality of components, and a maintenance time window;
access a component database to obtain component data for the plurality of components;
access a machine database storing a plurality of machines composed of the plurality of components;
execute scheduling iterations for determining an optimized maintenance schedule for the plurality of demands and the plurality of components, in which each initial maintenance interval is dynamically adjustable at each iteration in conjunction with optimizing an optimization variable, and wherein the executing includes
calculating updated particles within a solution space of allowable maintenance schedules, based on a position and velocity of each particle from a preceding iteration, each particle representing an allowable maintenance schedule for a corresponding component of the plurality of components of an associated demand,
calculating an updated optimization variable for each particle,
calculating an updated velocity of each particle within the solution space, and

upon completion of a maximum number of iterations, select the optimized maintenance schedule from the executed scheduling iterations, based on a highest-obtained value of the optimization variable during the iterations.

2. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to execute a scheduling iteration of the scheduling iterations, including:
calculating, for a current iteration of the scheduling iterations, a best particle position for a particle within the solution space, as compared to particle positions of preceding iterations for the particle, and judged using its corresponding optimization variable in the solution space.

3. The computer program product of claim 2 , wherein the instructions, when executed, are further configured to cause the at least one computing device to execute a scheduling iteration of the scheduling iterations, including:
calculating, for a current iteration of the scheduling iterations, a global best particle position for all particles within the solution space, as compared to particle positions of preceding iterations for all particles and judged using optimization variables for all particles in the solution space.

4. The computer program product of claim 3 , wherein the instructions, when executed, are further configured to cause the at least one computing device to execute a scheduling iteration of the scheduling iterations, including:
calculating the updated velocity of each particle, based on the best particle position and the global best particle position corresponding thereto.

5. The computer program product of claim 1 , wherein the optimization variable is calculated in terms of a production predicted to be achieved by a corresponding component in conjunction with a corresponding maintenance schedule, relative to a maintenance cost associated therewith.

6. The computer program product of claim 5 , wherein the production is predicted based on a machine interference of downtime of a corresponding machine during maintenance of the corresponding component.

7. The computer program product of claim 5 , wherein the production is predicted based on an impact of delaying a maintenance occurrence for a component due to the dynamically adjustable maintenance interval on a production efficiency associated with the component.

8. The computer program product of claim 1 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:
define the plurality of particles including encoding each position vector as a component subvector having a maximum number of dimensions based on a maximum number of maintenance occurrences within the maintenance time window, defined with respect to the initial maintenance interval.

9. The computer program product of claim 8 , wherein the instructions, when executed, are further configured to cause the at least one computing device to:
filter a calculated maintenance occurrence of the component subvector that falls outside of the maintenance time window.

10. A computer-implemented method for executing instructions stored on a non-transitory computer readable storage medium, the method comprising:
accessing a demand database storing a plurality of demands for maintenance schedules, each demand specifying a plurality of components for maintenance, at least one initial maintenance interval for each component of the plurality of components, and a maintenance time window;
accessing a component database to obtain component data for the plurality of components;
accessing a machine database storing a plurality of machines composed of the plurality of components;
executing scheduling iterations for determining an optimized maintenance schedule for the plurality of demands and the plurality of components, in which each initial maintenance interval is dynamically adjustable at each iteration in conjunction with optimizing an optimization variable, and wherein the executing includes
calculating updated particles within a solution space of allowable maintenance schedules, based on a position and velocity of each particle from a preceding iteration, each particle representing an allowable maintenance schedule for a corresponding component of the plurality of components of an associated demand,
calculating an updated optimization variable for each particle,
calculating an updated velocity of each particle within the solution space, and

upon completion of a maximum number of iterations, selecting the optimized maintenance schedule from the executed scheduling iterations, based on a highest-obtained value of the optimization variable during the iterations.

11. The method of claim 10 , comprising:
calculating, for a current iteration of the scheduling iterations, a best particle position for a particle within the solution space, as compared to particle positions of preceding iterations for the particle, and judged using its corresponding optimization variable in the solution space.

12. The method of claim 11 , comprising:
calculating, for a current iteration of the scheduling iterations, a global best particle position for all particles within the solution space, as compared to particle positions of preceding iterations for all particles and judged using optimization variables for all particles in the solution space.

13. The method of claim 12 , comprising:
calculating the updated velocity of each particle, based on the best particle position and the global best particle position corresponding thereto.

14. The method of claim 10 , wherein the optimization variable is calculated in terms of a production predicted to be achieved by a corresponding component in conjunction with a corresponding maintenance schedule, relative to a maintenance cost associated therewith.

15. The method of claim 10 , comprising
defining the plurality of particles including encoding each position vector as a component subvector having a maximum number of dimensions based on a maximum number of maintenance occurrences within the maintenance time window, defined

Assignees

• Sap Se

Inventors

• Zhou Wenjun
• Li Wen-Syan

Classifications

• G06F12/0813

  with a network or matrix configuration · CPC title

• G06F12/0804

  with main memory updating (G06F12/0806 takes precedence) · CPC title

• G06F17/30082

  Physics · mapped topic

• G06F17/30132

  Physics · mapped topic

• G06F17/30174 Primary

  Physics · mapped topic