Patent Application Number: 2006201792
This discussion forum is available to allow the community of reviewers to collaborate and discuss this patent application.
Discussion that is posted on this page will not be forwarded to IP Australia. If you wish to make comment on a prior art reference and wish that comment to be considered by the patent examiner, please do so by clicking on the relevant prior art reference.
Here are some tips to facilitate discussion.
- Flagging a post as an 'action item' signals that further research is required.
- Flagging SPAM and ABUSE helps to manage discussion
- Placing double brackets around a reference to a claim or prior art will create a hyperlink to the original, for example: [[claim 1]] and [[prior art 2]].
Facilitator's Comment 
Action Item Show without Noise
United States
The application provides specific details on the method and system involved in order to create the predictive models from historical operational data (Fig. 3), use multiple models to find the Pareto Frontier and the optimised results (Fig. 8), and update the models using new data (Fig. 9).
Claims 1-5 describe the entire method. Claims 6-10 describe a system that implements the method described in claims 1-5.
1. Method for performing multi-objective predictive modelling, monitoring and update for an asset:
Step 1: Determine the status of all the predictive models for an asset (there are at least two models). Each model uses one or more of the following statuses:
• Acceptable performance values (see claim 2)
• Validating model (see claim 3)
• Unacceptable performance values
Step 2: Based upon the status of each model, do one or more of the following:
• Stop using the model
• Generate an alert on the status of the model
• Update the model (see claim 4)
2. “Acceptable performance values” = where predicted performance values coincide with actual performance values
3. “Validating model status” = validation process is ongoing for the model
4. Updating = providing a new data set, performing prediction, calculating error, creating a training data set from all the data, update each model using the training data set, and deleting the new data set.
5. If error exceeds specified threshold, perform incremental learning of each model