Process scheduling optimization method

• US 8,260,648 B2
• Filed: 09/09/2009
• Issued: 09/04/2012
• Est. Priority Date: 09/09/2009
• Status: Expired due to Fees

• Current Assignee: King Fahd University of Petroleum & Minerals (Government of Saudi Arabia)
• Original Assignee: King Fahd University Of Petroleum And Minerals
• Inventors: Abdel-Wahhab, Osama, Elazouni, Ashraf M. A.
• Primary Examiner(s): Jasmin, Lynda
• Assistant Examiner(s): FEENEY, BRETT A
• Application Number:
  US12/585,237
• Publication Number:
  US 20110060624A1
• Time in Patent Office: 1,091 Days
• Field of Search: None
• US Class Current: 705/7.13
• CPC Class Codes: G06Q 10/06 Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling

Abstract

The design and process scheduling optimization method is a technique that circumvents problems encountered in previous optimization techniques. The method performs comparison against multiple possible outcomes rather than a single-valued benchmark. Pattern Recognition (PR) techniques are utilized to classify the work planned at specified cut-off dates during the planning stage. Classification is used to monitor and evaluate the progress during the construction stage. The PR technique generalizes a virtual benchmark to represent the whole project based on multiple possible outcomes generated at a given cut-off date. The generalization feature offers a potential tool to overcome the problem of variation in the quality of data collected. Patterns are constructed to encode work of the project at different cut-off dates. The present invention utilizes a robust pattern recognition method applied to Critical Path Method (CPM) procedures to monitor and evaluate progress of construction projects.

Claims

1. A computer software product that includes a non-transitory storage medium readable by a processor, the non-transitory storage medium having stored thereon a set of instructions for performing design and process monitoring optimization, the instructions comprising:

(a) a first set of instructions which, when loaded into main memory and executed by the processor, causes the processor to build a critical path method schedule of a project;

(b) a second set of instructions which, when loaded into main memory and executed by the processor, causes the processor to map, during a planning stage of said project, pattern sets of cut-off dates of said project to said critical path method schedule;

(c) a third set of instructions which, when loaded into main memory and executed by the processor, causes the processor to identify, during said planning stage, project cut-off date weeks corresponding to the pattern sets of the project cut-off dates;

(d) a fourth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to input a portion of said pattern sets and the corresponding project cut-off date weeks into a neural network to train the neural network to perform pattern recognition in classifying work planned at specified cut-off dates;

(e) a fifth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to use the remaining pattern sets to test the neural network pattern recognition after it has been trained;

(f) a sixth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to monitor the project, during the construction stage of said project, at said same cut-off dates;

(g) a seventh set of instructions which, when loaded into main memory and executed by the processor, causes the processor to prepare, at any desired cut-off date, a corresponding descriptive pattern, said corresponding descriptive pattern describing actual work accomplishments during a time period defined by said any desired cut-off date;

(h) an eighth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to input said descriptive pattern to said neural network which, responsively, declares a week of convergence that said descriptive pattern input tends to converge; and

(i) a ninth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to compare said week of convergence declared by said neural network pattern recognition to said cut-off date week of said associated cut-off date pattern set thereby indicating whether actual progress of the project is on schedule, ahead of schedule, or behind schedule.

2. The computer software product according to claim 1, wherein said neural network pattern recognition utilizes a single hidden layer.

3. The computer software product according to claim 2, wherein only ten neurons are utilized in said single hidden layer.

4. The computer software product according to claim 1, further comprising a tenth set of instructions which, when loaded into main memory and executed by the processor, causes the processor to benchmark the entire project based on multiple possible outcomes generated by said neural network pattern recognition at each said cut-off date.

5. The computer software product according to claim 1, further comprising an additional set of instructions which, when loaded into main memory and executed by the processor, causes the processor to associate an output pattern, said output pattern including a vector having a number of elements which equals the total number of project weeks, with each input pattern.

6. The computer software product according to claim 1, further comprising an additional set of instructions which, when loaded into main memory and executed by the processor, causes the processor to construct additional patterns at each cut-off date, said additional patterns being generated by randomly assigning values to the activities'"'"' start times within a range of an early start time (EST) and a late start time (LST), while maintaining a sequence of said activities, said additional patterns representing multiple possible patterns which will lead to the same project duration;

and

wherein sets of random patterns at all the specified cut-off dates along with their corresponding weeks constitute inputs to feed to the neural network.

7. The computer software product according to claim 1, wherein the training of the fourth set of instructions further comprises constructing a plurality of training pattern groups, each training pattern group of the plurality of training pattern groups being uniquely associated with each interval of the longest time period shown in the critical path method schedule, said training pattern groups being split further into a first number of sub-groups and a second number of sub-groups, individual patterns of the first number of sub-groups being used for updating said neural network weights and biases while being entered randomly to said neural network, said second number of sub-groups being used for a validating step.

8. The computer software product according to claim 7, further comprising an additional set of instructions which, when loaded into main memory and executed by the processor, causes the processor to validate said neural network pattern recognition, said validation including a stopping criterion such that when a pattern recognition error first begins to increase, the training session is stopped, and weights and biases of the neural network pattern recognition corresponding to a minimum pattern recognition error value are returned.