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 .
Claims 1-20 are pending, of which claims 1 and 14 are independent claims.
Priority
Receipt is acknowledged of certified copies of papers required by 37 CFR 1.55 for Application No. 10-2024-0023559 filed on February 19, 2024.
Information Disclosure Statement
The references cited in the information disclosure statements (IDS) submitted on September 3, 2024 have been considered by the examiner.
Abstract
The Abstract is objected to because of the following informalities: according to MPEP 608.01(b), the form and legal phraseology often used in patent claims should be avoided in the abstract of the disclosure. In this instance, the abstract includes legal phraseology such as “consisting of”, which should be avoided.
Appropriate correction is required.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter, which the inventor or a joint inventor regards as the invention.
Claims 1-20 are rejected under 35 U.S.C. 112(b), as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Independent claim 1 recites, in part, “predicting a set of process conditions with a high relative density for a specific metal powder using the trained machine learning model and random search”. The term “high relative density” is unclear and indefinite as it is a relative term without clearly defining the intended scope of the relative density. See MPEP 2173.05(b) Paragraph [0052] of the published Specification is the closest scope of the meaning of “high relative density” as being set to 98%. For purposes of examination, the term “high relative density” will be construed “as a “high relative density exceeding 98%”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 7 recites, in part, “selecting sets of process conditions with sigmoid functions values close to 1.” However, the term “close to 1” is unclear and indefinite. A person of ordinary skill in the art would not be able to ascertain how close the sigmoid functions values have to be to 1. The standard or degree of how close to 1 is not clear. Upon review of the Specification, the Office is unable to clearly ascertain the intended meaning of “close to 1”. Therefore, the Office is unable to properly examine the claim for lack of clarity. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 8 recites, in part, “inputting other options such as the number of sets of process conditions to be generated and a maximum number of repetitions”. The intended meaning of “such as” is indefinite. If additional options are to be included, the claim should recite those options. Otherwise, the claim should be clear that the other options are a number of sets of process conditions. The Office also notes that neither independent claim 1 nor claim 7 provide antecedent support for “the number of sets of process conditions”. If this term is newly introduced, it is recommended that the claim be amended to recite “a number of sets of process conditions”. For purposes of examination, the inputting limitation will be construed as “inputting other options including a number of sets of process conditions to be generated and a maximum number of repetitions”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 10 recites, in part “selecting sets of process conditions with high sigmoid function values from the remaining sets of process conditions after removing the sets of process conditions with the low sigmoid function values.” However, none of claims 1, 7, 8, and 9 recite remaining sets of process conditions. Therefore, the recitation of claim 10 providing “the remaining sets of process conditions” is unclear. For purposes of examination, the inputting limitation will be construed as “selecting sets of process conditions with high sigmoid function values from remaining sets of process conditions after removing the sets of process conditions with the low sigmoid function values”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 12 recites, “if the maximum number of repetitions has been reached, finalizing the selected set of process conditions as the final set of process conditions.” However, none of claims 1, 7, 8, and 11 recite final set of process conditions. Therefore, the recitation of claim 12 providing “the final set of process conditions” is unclear. For purposes of examination, the inputting limitation will be construed as “if the maximum number of repetitions has been reached, finalizing the selected set of process conditions as a final set of process conditions”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 13 recites, “reached the maximum number of repetitions, determining whether the set of process conditions selected in the previous step is identical to the set of process conditions selected in the current step, and wherein if the two sets of process conditions are identical to each other, the set of process conditions selected in the current step is finalized as the final set of process conditions.” However, none of claims 1, 7, 8, and 11 recite “previous step” and recite final set of process conditions. Therefore, the recitation of claim 13 providing “the previous step” and “the final set of process conditions” is unclear. For purposes of examination, the inputting limitation will be construed as “reached the maximum number of repetitions, determining whether the set of process conditions selected in a previous step is identical to the set of process conditions selected in the current step, and wherein if the two sets of process conditions are identical to each other, the set of process conditions selected in the current step is finalized as a final set of process conditions”. Appropriate correction through claim amendment is respectfully requested.
In view of their dependencies to a rejected base claim, claims 2-6, 9, and 11 are also rejected as being indefinite.
Independent claim 14 recites, in part, “predicting a set of process conditions with a high relative density for a metal powder, which is not used in the training of the machine learning model, using the trained machine learning model and random search”. For similar reasons as those provided with respect to the rejection of independent claim 1, the term “high relative density” is unclear and indefinite as it is a relative term without clearly defining the intended scope of the relative density. For purposes of examination, the term “high relative density” will be construed “as a “high relative density exceeding 98%”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 15 recites, in part, “selecting the sets of process conditions as many bas the number of sets of process conditions with high sigmoid function values;” The claim is unclear and indefinite because the Office is unable to appreciate what “as many bas” is intended to be. The Specification does not provide a meaning to “as many bas”.
Also, the recitation “high sigmoid function values” is indefinite for “high” being a relative term. According to paragraph [0052] of the published Specification, if the relative density is 98%, the sigmoid function value is 0.5. Therefore, as dependent claim 15 depends from independent claim 14, which is construed as a high relative density exceeding 98%, the recitation of dependent claim 15 is construed as “high sigmoid function values of 0.5”. Appropriate correction through claim amendment is respectfully requested.
Dependent claim 19 recites, in part, “after comparing the similar sets of process conditions, selecting sets of process conditions with high sigmoid function values from the remaining sets of process conditions;” The recitation “high sigmoid function values” is indefinite for “high” being a relative term. According to paragraph [0052] of the published Specification, if the relative density is 98%, the sigmoid function value is 0.5. Therefore, as dependent claim 15 depends from independent claim 14, which is construed as a high relative density exceeding 98%, the recitation of dependent claim 15 is construed as “high sigmoid function values of 0.5”. Appropriate correction through claim amendment is respectfully requested.
In addition, the recitation of claim 19 providing “the remaining sets of process conditions” is indefinite because none of claims 14 and 15 recite remaining sets of process conditions. Therefore, the recitation of claim 19 providing “the remaining sets of process conditions” is unclear. For purposes of examination, the remaining sets of process conditions will be construed as “a remaining sets of process conditions”. Appropriate correction through claim amendment is respectfully requested.
In view of their dependencies to a rejected base claim, claims 16-18 and 20 are also rejected as being indefinite.
The following is a quotation of the first paragraph of 35 U.S.C. 112(a):
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
Claims 7-13 and 15-19 are rejected under 35 U.S.C. 112(a) or 35 U.S.C. 112 (pre-AIA ), first paragraph, as failing to comply with the written description requirement.
The claim(s) contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, or for pre-AIA the inventor(s), at the time the application was filed, had possession of the claimed invention. The disclosure does not provide adequate structure to perform the claimed function recited in claim 7 of “selecting sets of process conditions with sigmoid functions values close to 1.” The specification does not demonstrate that applicant has made an invention that achieves the claimed functions because the invention is not described with sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor had possession of the claimed invention.
In view of their dependencies to a rejected base claim, claims 8-13 are also rejected as failing to comply with the written description requirement.
Furthermore, the disclosure does not provide adequate structure to perform the claimed function recited in claim 15 of “as many bas” The specification does not demonstrate that applicant has made an invention that achieves the claimed functions because the invention is not described with sufficient detail such that one of ordinary skill in the art can reasonably conclude that the inventor had possession of the claimed invention.
In view of their dependencies to a rejected base claim, claims 16-19 are also rejected as failing to comply with the written description requirement.
Allowable Subject Matter and Relevant Prior Art cited by Examiner
The following prior art made of record and not relied upon is cited to establish the level of skill in the applicant’s art and those arts considered reasonably pertinent to Applicant’s disclosure. See MPEP 707.05(c).
Independent claim 1
Regarding independent claim 1,
A method of predicting optimal process conditions, comprising the steps of:
US Patent Publication No. 2020/0198230 A1 to Lo et al. (“Lo”) teaches: Paragraph [0002] (“…a method of performing powder bed fusion process. More particularly, the present invention relates to an additive manufacturing method using selective laser melting (SLM) with optimal SLM parameters.”)
training a machine learning model based on properties of a metal powder, process conditions, and relative density; and
US Patent Publication No. 2020/0198230 A1 to Lo et al. (“Lo”): Paragraph [0052] (“In the systematic methodology, at first, an optimal range of a powder layer thickness is determined. In an embodiment of the present invention, a modified sequential addition model and a ray-tracing simulation approach are used to determine the powder layer thickness based on calculated packing density and absorptivity of a powder bed. Subsequently, several combinations of the laser power and scanning speed in a designed space of the considered SLM system is used to determine peak temperature and dimensions of a melt pool by using a heat transfer model. Then, the simulation results are used to train artificial neural networks (ANNs) for surrogate models to predict the dimensions of the melt pool and the peak temperature, respectively, for numerous combinations of the laser power and scanning speed. Subsequently, several combinations of the hatch space and the scan length are used to predict melt pool features, which include the peak temperature, depth and overlap rate, by a three-dimensional (3D) finite element model. Similarly, the simulation results are used to train ANNs for surrogate models to predict the melt pool features for numerous combinations of the hatch space and the scan length within the design space.”)
Lu et al. (CN 116796630 A) (“Lu”): Page 3, second paragraph to twelfth paragraph (“The additive manufacturing preparation method of the high-performance part based on machine learning comprises the following steps: s1, establishing a data set; wherein the data set is divided into a training set and a testing set; the training set contains a plurality of groups of training data, and each group of training data comprises a first technological parameter, a first powder particle size distribution characteristic parameter and first workpiece performance data; s2, establishing a GBDT initial model of powder particle size distribution characteristic parameter-process parameter-workpiece performance by utilizing the training set; wherein the first powder particle size distribution characteristic parameter comprises at least one of a particle size distribution range and an average particle size; s3, optimizing the GBDT initial model to obtain a GBDT optimal model; s4, inputting a plurality of groups of preset process parameters into the GBDT optimal model aiming at any group of preset powder particle size distribution characteristic parameters to obtain first prediction data of the properties of a plurality of groups of components corresponding to the plurality of groups of preset process parameters; s5, determining optimal technological parameters according to the first predicted data of the performances of the multiple groups of components; s6, adopting the powder with the bimodal particle size distribution as a raw material, and carrying out additive manufacturing by utilizing the optimal technological parameters to obtain the finished product. Further, the first process parameter comprises at least one of laser power, scanning speed, scanning interval and powder spreading layer thickness; the first article performance data includes at least one of density, hardness, tensile strength, elongation. Further, the test set contains a plurality of groups of test data, and each group of test data comprises a second process parameter, a second powder particle size distribution characteristic parameter and second workpiece performance data; preferably, the second powder particle size distribution characteristic parameter includes at least one of a particle size distribution range and an average particle size.”)
US Patent Publication No. 2021/0362242 A1 to Storck et al. (“Storck”): Paragraph [0060] (“In this case, machine learning models, such as neural networks or other regression-based methods, can be trained to approximate the relationship between build input parameters (such as power, hatch, speed) and material properties (such as porosity and surface roughness). Moreover, the processing space about a particular optimum can be determined to provide an end user with information concerning the stability of the process associated with a particular feedstock chemistry and additive manufacturing device.”)
US Patent Publication No. 2023/0264264 A1 to Prentice et al. (“Prentice”): Paragraph [0031] (“Defects induced by the AM equipment may result from, for example, beam scanning, build chamber including protective atmosphere, feed material handling and deposition and the baseplate. Defects induced by the AM process may result from, for example, control settings (such as laser power, scan speed and hatch distance which determine energy density) and scan strategies (which may determine temperature distribution and residual stresses, for example). Defects induced by the AM model may result from design errors, supports and sacrificial components and orientation of the article the respect of base plate. Defects induced by the AM feed material may result from purity and contaminants and for powders, from powder morphology, particle size distribution, flowability and apparent density.”) US Patent Publication No. 2023/0264264 A1 to Prentice (“Prentice”): Paragraph [0064] (“In one example, obtaining the set of in-process parameters of the AM of the article comprises sourcing input parameters of the AM of the article and/or readback parameters during the AM of the article. Generally, input parameters include desired control settings, such as desired laser power, desired scan speed and desired hatch distance, while readback parameters include actual control settings, such as actual laser power, actual scan speed and actual hatch distance. For example, while the desired laser power may be constant, the actual laser power may vary during the AM.”) Prentice: (“The third aspect provides a method of training a machine learning, ML, algorithm, the method implemented, at least in part, by a computer comprising a processor and a memory, the method comprising: providing training data comprising sets of in-process parameters of AM of a set of articles including a first article and corresponding sets of properties of the set of articles; and training the ML algorithm using the provided training dataset.”)
predicting a set of process conditions with a high relative density for a specific metal powder using the trained machine learning model and random search.
Eshkabilov, S., Ara, I. and Azarmi, F., 2022. A comprehensive investigation on application of machine learning for optimization of process parameters of laser powder bed fusion-processed 316L stainless steel. The International Journal of Advanced Manufacturing Technology, 123(7), pp.2733-2756. (“Eshkabilov”) Section 1.3, page 2737, first column: (“… a methodology for the unsupervised and supervised machine learning algorithms to classify and predict mechanical properties including yield strength of LPBF-processed specimens in connection with the LPBF process parameters based on LPBF-manufactured 316L SS data from published literature. Finally, the accuracy and validity of the proposed machine learning algorithms and models were experimentally validated by printing several 316L SS samples with a random set of the LPBF process parameter values. The physical and mechanical properties of the printed samples were experimentally measured and compared to those predicted by the developed machine learning algorithms and models.”) Eshkabilov: Section 3.1, pages 2738-2739, second column to first column (“In the present study, we have tried several algorithms by providing input data (process parameters) and the output results (materials properties) were compared in terms of the accuracy of predicted response variables.”) Eshkabilov: Section Step 1. Data collection, page 2739, first and second columns (“In addition, five process parameters, namely, laser power, laser energy density, scanning speed, hatching distance, and layer thickness, were evaluated here. It is worth noting that machine type and material quality such as powder particle size and type can also influence on the final material properties.”) Eshkabilov: Section Step 2. Data categorization, page 2739 to page 2740, second and first columns (“The collected data was sorted into two subsets: (a) a numerical display format of input data predictors consisting of process parameters such as laser power, laser density, scanning speed, and hatching distance and (b) output responses consisting of hardness, yield strength, ultimate tensile strength, and relative density.”) Eshkabilov: Section Step 5. Simulation, page 2740, first column (“The selected machine learning algorithm with selected parameters was simulated with the training data set, and its performance was assessed, and its response prediction accuracy monitored, taking into account its missed/misclassified responses. This step was an iterative process run for a number of times (greater than 50) until the chosen model showed no more improvement in terms its accuracy coefficient of determination (R2), root mean squared error (RMSE), mean absolute error (MAE), and accuracy in predicting the response values or accuracy reached greater than 85%.”) Eshkabilov: Section 3.2, page 2740, second column (“A wide range of process parameter values was also considered here to ensure that the present model globally covers the effect of processing parameters on the properties for a wide variation of material properties... As it was mentioned in Sect. 1.1, the process parameters with a significant effect on the properties of the final product in the LPBF process were identified as laser power in W, laser energy density in J/mm3, scanning speed in mm/s, hatching distance in mm, and layer thickness in mm. In addition to the density, mechanical properties such as ultimate tensile strength (MPa), yield strength (MPa), hardness (HV), and relative density (%) were also evaluated in this study….After removing the outliers, the data sets were split into two subsets of data—model training and model validation—by selecting the data points using a uniform random number generator function.”)
However, the combination of Eshkabilov, S., Ara, I. and Azarmi, F., 2022. A comprehensive investigation on application of machine learning for optimization of process parameters of laser powder bed fusion-processed 316L stainless steel. The International Journal of Advanced Manufacturing Technology, 123(7), pp.2733-2756.; US Patent Publication No. 2023/0264264 A1 to Prentice et al.; US Patent Publication No. 2020/0198230 A1 to Lo et al.; US Patent Publication No. 2021/0362242 A1 to Storck et al.; Lu et al. (CN 116796630 A); and additional teaching of the prior art of record, do not expressly teach or suggest “predicting a set of process conditions with a high relative density for a specific metal powder using the trained machine learning model and random search”, as recited in independent claim 1.
Claims 2-13 are dependent claims of claim 1. Independent claim 1 is allowable over prior art, and therefore, provided that the indefiniteness rejection to claims 1-13 are overcome, claims 1-13 would be allowable.
Claim 14
Independent claim 14 includes similar limitations and reasons for allowance as independent claim 1. In particular, the combination of Eshkabilov, S., Ara, I. and Azarmi, F., 2022. A comprehensive investigation on application of machine learning for optimization of process parameters of laser powder bed fusion-processed 316L stainless steel. The International Journal of Advanced Manufacturing Technology, 123(7), pp.2733-2756.; US Patent Publication No. 2023/0264264 A1 to Prentice et al.; US Patent Publication No. 2020/0198230 A1 to Lo et al.; US Patent Publication No. 2021/0362242 A1 to Storck et al.; Lu et al. (CN 116796630 A); and additional teaching of the prior art of record, do not expressly teach or suggest “predicting a set of process conditions with a high relative density for a metal powder, which is not used in the training of the machine learning model, using the trained machine learning model and random search”, as recited in independent claim 14.
Claims 15-19 are dependent claims of independent claim 14. Independent claim 14 is allowable over prior art, and therefore, claims 15-19 are allowable, provided that the indefiniteness rejection of claims 14-19 is overcome.
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
US Patent Publication No. 2023/0410412 A1 to Roychowdhury et al. describes that AM-based processes are diverse and include powder bed fusion, material extrusion, and material jetting. For example, powder bed fusion uses either a laser or an electron beam to melt and fuse the material together to form a 3D structure. Powder bed fusion can include multi jet fusion (MJF), direct metal laser sintering (DMLS), direct metal laser melting (DMLM), electron beam melting (EBM), selective laser sintering (SLS), among others. For example, DMLM uses lasers to melt ultra-thin layers of metal powder to create the 3D object, with the object built directly from a CAD file (e.g., .STL file) generated using CAD data. Using a laser to selectively melt thin layers of metal particles permits objects to exhibit homogenous characteristics with fine details. A variety of materials can be used to form 3D objects using additive manufacturing, depending on the intended final application (e.g., prototyping, medical devices, aviation parts, etc.). For example, the DMLM process can include the use of titanium, stainless steel, superalloys, and aluminum, among others. For example, titanium can withstand high pressures and temperatures, superalloys (e.g., cobalt chrome) can be more appropriate for applications in jet engines (e.g., turbine and engine parts) and the chemical industry, while 3D printed parts formed from aluminum can be used in automotive and thermal applications.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ALICIA M. CHOI whose telephone number is (571)272-1473. The examiner can normally be reached on Monday - Friday 7:30 am to 5:00 pm.
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, Robert Fennema can be reached on 571-272-2748. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications is available through Private PAIR only. For more information about the PAIR system, see http://pair-direct.uspto.gov. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/ALICIA M. CHOI/Primary Patent Examiner, Art Unit 2117
Prosecution Insights