GENERAL ELECTRIC COMPANY

Patent Trials and Appeals Board

Jun 2, 2021

2020003247 (P.T.A.B. Jun. 2, 2021)

UNITED STATES PATENT AND TRADEMARK OFFICE
UNITED STATES DEPARTMENT OF COMMERCE
United States Patent and Trademark Office
Address: COMMISSIONER FOR PATENTS
P.O. Box 1450
Alexandria, Virginia 22313-1450
www.uspto.gov
APPLICATION NO. FILING DATE FIRST NAMED INVENTOR ATTORNEY DOCKET NO. CONFIRMATION NO.
14/863,946 09/24/2015 Honggang WANG 19441-1441 (277171_3) 2521
13077 7590 06/02/2021
Eversheds Sutherland GE
Suite 2300
999 Peachtree Street
Atlanta, GA 30309
EXAMINER
SASAKI, SHOGO
ART UNIT PAPER NUMBER
1798
NOTIFICATION DATE DELIVERY MODE
06/02/2021 ELECTRONIC
Please find below and/or attached an Office communication concerning this application or proceeding.
The time period for reply, if any, is set in the attached communication.
Notice of the Office communication was sent electronically on above-indicated "Notification Date" to the
following e-mail address(es):
patentdocket@eversheds-sutherland.com
PTOL-90A (Rev. 04/07)

UNITED STATES PATENT AND TRADEMARK OFFICE
____________

BEFORE THE PATENT TRIAL AND APPEAL BOARD
____________

Ex parte HONGGANG WANG, LIHAN HE, ZHILIN WU, YAO CHEN,
WEI ZHOU, GUANG XU, and DAVID KELLY MOYEDA

Appeal 2020-003247
Application 14/863,946
Technology Center 1700
____________

Before MICHAEL P. COLAIANNI, LILAN REN, and
MERRELL C. CASHION, JR., Administrative Patent Judges.

COLAIANNI, Administrative Patent Judge.

DECISION ON APPEAL

Pursuant to 35 U.S.C. § 134(a), Appellant1 appeals from the
Examiner’s decision to reject claims 11–17, and 20–22. We have
jurisdiction under 35 U.S.C. § 6(b).
We REVERSE.

1 “Appellant” refers to “applicant” as defined in 37 C.F.R. § 1.42. Appellant
identifies the real party in interest as General Electric Company. Appeal Br.
2.
Appeal 2020-003247
Application 14/863,946

2
Appellant’s invention is directed to a system for combustion tuning of
a boiler (Claim 11).
Claim 11 is representative of the subject matter on appeal:
11. A system for combustion tuning of a boiler, comprising:
a plurality of adjustable actuators arranged to control a variable input
parameter of the boiler;
an optimization system configured to receive operating data from the
boiler indicative of the current boiler condition, the optimation [sic,
optimization] system in signal communication with the plurality of
adjustable actuators;
a sensor array disposed in an exhaust zone of the boiler, configured to
measure a parameter indicative of a combustion status of the boiler, the
sensor array configured to generate a signal indicative of the value of the
measured parameter; and
a trigger in signal communication with the sensor array and the
optimization system, the trigger configured to receive the generated signal
and to determine, based on the generated signal, the value of the measured
parameter and whether the value of the measured parameter matches a preset
target, and, in response to a determination that the determined value of the
measured parameter does not match the preset target, the trigger is
configured to trigger operation of an optimization system,
wherein the optimization system comprises:
a model repository comprising a plurality of selectable models, each
model of the plurality of models corresponding to a respective relationship
between a value of at least one model input variable and the determined
value of the measured parameter;
a model selector configured to select a model from the plurality of
models based on the data indicative of the current boiler condition;
an optimizer configured to determine the value of the model input
variable based on the selected model; and
an adjuster configured to adjust the actuators of the boiler based on
the determined value of the model input variable.

Appellant appeals the following rejection:
Claims 11–17, and 20–22 are rejected under 35 U.S.C. § 103 as
unpatentable over Badami (US 2007/0240648, published Oct. 18, 2007).
Appeal 2020-003247
Application 14/863,946

3

Appellant’s arguments focus on the subject matter of claim 11 only.
(Appeal Br. 4–6). Therefore, claims 12–17, and 20–22 will stand or fall
with our analysis of the rejection of claim 11.

FINDINGS OF FACT & ANALYSIS
The dispositive issue in this appeal is whether the Examiner has
established that Badami teaches a system for combustion tuning of a boiler
comprising, inter alia, an optimization system that comprises “a model
selector configured to select a model from the plurality of models based on
the data indicative of the current boiler condition.”
Appellant contends the Examiner interpretation of model selector is
unreasonable. (Reply Br. 2–3). The Examiner interprets model selector as
including “any switch capable of selecting a model for use (e.g.: a cursor on
a user interface monitor).” (Ans. 26; Advisory Act. 3). The Examiner finds
that, “the claim does not say that the selecting is performed autonomously by
automating device(s) or manually by an operator.” (Ans. 26). The
Examiner, however, has not indicated that “model selector” has been
interpreted in light of the Specification. The Specification discloses that,
“the model selector may be a rule-based and/or quantitative selector, which
is designed to select an appropriate model from the model repository to fit
the current boiler condition” (¶ 27). The Specification further discloses that,
“[t]he model selector 131 selects the model based on the available model
input variables, in such a manner that unavailable model input variables are
leaved [sic left] out of the model selection . . ..” (¶ 28). Based on the
Specification disclosure, the Examiner’s interpretation of model selector as
Appeal 2020-003247
Application 14/863,946

4
being any switch including “a cursor on a user interface monitor” appears to
be unreasonably broad.
The Examiner does not direct us to where Badami teaches or would
have suggested a model selector. (Final Act. 4–16). The Examiner’s
rejection consists of a copy of various paragraphs in Badami, but does not
include much explanation of how Badami’s disclosures map to the claim.
(Final Act. 4–16). In particular, there is no explicit mapping of Badami’s
disclosures to the claimed “model selector” or explanation of how Badami’s
teaching are being read as teaching a model selector. Id. Appellant argues
that Badami does not select models because it uses predictive models such
that any of the models could be used (i.e., there is no model selection)
(Appeal Br. 6). The Examiner does not respond specifically to Appellant’s
argument regarding Badami’s predictive models. (Ans. 26–27).
Badami teaches that predictive models may be based on Neural
Networks or could be combination of Neural Networks and first-principles
based on CFD (computation fluid dynamics) models that are used to model
boiler system behavior in terms of stack emissions such as NOx or CO and
in terms of performance parameters such as efficiency (¶ 38). The predictive
models need to be adapted to match the boiler system performance, such as
presenting the neural network based predictive models with appropriate
training data, which represents boiler behavior (¶ 38). Badami teaches that
upon learning the training set, the model should be able to predict the boiler
behavior with required accuracy so that the multi-objective optimizer can
then be used to optimize boiler level objective functions (¶ 38). Badami
further discloses that the optimization hierarchical system uses predictive
models (i.e., data driven models such as Neural Networks or first principles
Appeal 2020-003247
Application 14/863,946

5
based models such as CFD) to map boiler inputs to outputs that need to be
optimized utilizing a combination of optimization algorithms (¶ 35). It
appears that Badami’s models are optimized through an iterative process
based on data rather than using a model selector to select a particular model
to use to tune the combustion in the boiler as recited in claim 11.
The Examiner has not established that Badami would have rendered
obvious the subject matter of claim 11. We reverse the Examiner’s § 103
rejection over Badami.

DECISION
In summary:

Claims
Rejected
35 U.S.C. § Reference(s)/Basis Affirmed Reversed
11–17, 20–22 103 Badami 11–17,
20–22

REVERSED