Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Claim Rejections - 35 USC § 102
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-20 is/are rejected under 35 U.S.C. 102(a)(2) as being anticipated by UACJ (WO2022059753).
Claim 1-20 are rejected as disclosed and substantially similar to those presented in WO2022059753. It is unclear, due to the publishing in another language, no formal translation provided, and no readily apparent indication of the inventors/assignee/case association, whether the application WO2022059753 which has a filing date prior to the priority date of this application is ‘by another’ or ‘names another inventor’ or entity is different than the instant application.
Claim(s) 1, 6, 15, 19 is/are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Santos et al (hereinafter Santos) (Supervised Learning Classification for Dross Prediction in Ductile Iron Casting Production)
As per Claim 1, 6, 15, 19, Santos discloses, “A method of generating a trained prediction model for predicting an amount of dross occurring in a melting furnace, comprising: a step of acquiring one or more process state parameters of different attributes for every single charge spanning from a loading of raw materials to a completion of melting” The acceptance/rejection criterion of the studied models resembles the one applied by the final requirements of the customer. Cast parts flawed with defects must be rejected due to the very restrictive quality standards (which is an imposed practice by the automotive industry). To this end, we labelled each possible segment within the castings with its defects. A whole dataset that contained records from the most important processing variables involved in a heavy-section casting foundry process was created. 120 different parameters related with raw materials, chemical composition of melt, thermal analysis data, inoculation, magnesium treatment, pouring time and pouring temperature, etc. were collected in addition to the output data. In this last case, the volume affected by Dross measured by ultrasound inspection on each produced cast part was selected as output variable. Next, we evaluate the precision of the machine-learning method to predict the value of Dross. P1753 Col 1 (V. Empirical Validation) “wherein each process state parameter is defined by a continuous aggregate of chronological data that is acquired based on an output from one of a variety of sensors provided in the melting furnace;” An effective combination of machine-learning tools and the available processing data coming from foundries must lead to a deeper understanding about how the processing parameters and cast parts characteristics affect Dross formation. Besides, a prediction tool for this parameter would lead foundries to lower reject rates and the subsequent cost and time saving. Successful machine-learning approaches related with other foundry problems have been previously reported in [11]–[18]. Against this background, we present here the first machine learning based tool that has been developed and, then, successfully applied to predict and to prevent Dross defects in cast iron parts. The data base used contained experimental processing parameters and defect evaluation on parts as output data. In summary, our main contributions are: • We study the variables to represent the Dross formation as a machine learning classification task. • We adapt the machine-learning algorithms for the Dross prediction We show that our method is capable of predicting Dross with a high accuracy. P1749 and 1750 Col 2 and Col 1 (I. Introduction) and (II Manufacture of Heavy Section Cast Parts) a step of performing preprocessing by applying machine learning to a data set of the one or more process state parameters acquired through m charges (where m is an integer of 2 or greater), the preprocessing comprising extracting n-dimensional features (where n is an integer of 1 or greater) from each process state parameter containing an aggregate of chronological data acquired for every single charge; A whole dataset that contained records from the most important processing variables involved in a heavy-section casting foundry process was created. 120 different parameters related with raw materials, chemical composition of melt, thermal analysis data, inoculation, magnesium treatment, pouring time and pouring temperature, etc. were collected in addition to the output data. In this last case, the volume affected by Dross measured by ultrasound inspection on each produced cast part was selected as output variable. Next, we evaluate the precision of the machine-learning method to predict the value of Dross. The final level of Dross was discretized in 5 different categories in order to apply classification techniques: Dross ≤ 2.5 2.5 < Dross ≤ 3.5 3.5 < Dross ≤ 4.5 4.5 < Dross ≤ 5.5 5.5 < Dross ≤ 6.5 Dross > 6.5 Hereafter, by means of the dataset, we conducted the following methodology to evaluate the proposed method: • Cross validation: This method is generally applied in machine-learning evaluation [32]. In our experiments, we performed a K-fold cross validation with k=10. In this way, our dataset is 10 times split into 10 different sets of learning (90% of the total dataset) and testing (10% of the total data). • Learning the model: For each fold, we accomplished the learning step of each algorithm using different parameters p1753 Col 1 a step of generating a learning data set based on the extracted n-dimensional features, the learning data set at least containing one or more process target parameters representing process fundamental information that is set for every single charge; and a step of training a prediction model by using the generated learning data set to generate the trained prediction model that predicts the amount of dross generation. Learning the model: For each fold, we accomplished the learning step of each algorithm using different parameters for the learning algorithms depending on the specific model. In particular, we used the following models:– Bayesian networks (BN): With regards to Bayesian networks, we utilize different structural learning algorithms: K2 [33] and Tree Augmented Naïve (TAN) [34]. Moreover, we also performed experiments with a Naïve Bayes Classifier [32]. – Support Vector Machines (SVM): We performed experiments with a polynomial kernel [31], a normalised polynomial Kernel [35], a Pearson VII function-based universal kernel [36] and a radial basis function (RBF) based kernel [37]. – K-nearest neighbour (KNN): We performed experiments with k=1, k=2, k=3, k=4, and k=5. – Decision Trees (DT): We performed experiments with J48 (the Weka [27] implementation of the C4.5 algorithm [28]) and Random Forest [26], an ensemble of randomly constructed decision trees. In particular, we tested random forest with a variable number of random trees N, N=10, N=20, N=30, N=40, and N=50. • Testing the model: To test the approach, we evaluated the percent of correctly classified instances and the area under the ROC curve (AUC), which establishes the relation between false negatives and false positives [38]. P 1753 Col 1 and 2
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to KENNETH M LO whose telephone number is (571)272-9774. The examiner can normally be reached M-F 830a - 6pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, John Cottingham can be reached at 571-272-9877. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
KENNETH M. LO
Supervisory Patent Examiner
Art Unit 2136
/KENNETH M LO/ Supervisory Patent Examiner, Art Unit 2116
Prosecution Insights