Appeal No. 1999-1856
Application No. 08/686,792
OPINION
In reaching our decision in this appeal, we have given careful consideration to the
appellants’ specification and claims, to the applied prior art references, and to the
respective positions articulated by the appellants and the examiner. As a consequence
of our review, we make the determinations which follow.
With respect to appellants’ grouping of claims set forth in the brief at pages 4-5, we
note that appellants merely argue the limitations of independent claims 15 and 16 and
rely upon these arguments for patentability of the dependent claims at pages 11-14 of
the brief. Therefore, we will address only independent claims 15 and 16 with respect to
Samad and Broese since appellants do not specifically address the other references.
With respect to the combination of Samad and Broese, appellants argue that neither
reference nor the combination of teachings concerns the use of different training sets of
data for the control network and the background network. (See brief at page 7.) We do
not find this argument persuasive since independent claim 15 does not recite “different”
data. Claim 15 merely sets forth “training the control network using current process
data to generate a current process model” and “training the background network using
representative process data to generate an averaged process model of the industrial
process over a predetermined time period.” There is no express limitation that the
current process data cannot also be representative process data or from the same
sampling period. Therefore, the data sets may be the same data or different data from
4
Page: Previous 1 2 3 4 5 6 7 Next
Last modified: November 3, 2007