Prosecution Insights
Last updated: April 19, 2026
Application No. 17/875,453

METHOD FOR PREDICTING COAXIALITY OF PARTS OF ROTARY EQUIPMENT BASED ON GA-PSO-BP NEURAL NETWORK

Non-Final OA §101§112
Filed
Jul 28, 2022
Examiner
HUANG, MIRANDA M
Art Unit
2124
Tech Center
2100 — Computer Architecture & Software
Assignee
Harbin Institute of Technology
OA Round
1 (Non-Final)
59%
Grant Probability
Moderate
1-2
OA Rounds
4y 7m
To Grant
99%
With Interview

Examiner Intelligence

Grants 59% of resolved cases
59%
Career Allow Rate
149 granted / 253 resolved
+3.9% vs TC avg
Strong +54% interview lift
Without
With
+53.5%
Interview Lift
resolved cases with interview
Typical timeline
4y 7m
Avg Prosecution
22 currently pending
Career history
275
Total Applications
across all art units

Statute-Specific Performance

§101
14.6%
-25.4% vs TC avg
§103
47.9%
+7.9% vs TC avg
§102
23.3%
-16.7% vs TC avg
§112
9.0%
-31.0% vs TC avg
Black line = Tech Center average estimate • Based on career data from 253 resolved cases

Office Action

§101 §112
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 . This office action is in response to application filed 7/8/2022. Claims 1-4 are pending. Claim priority date: 6/17/2022 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. The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph: The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention. Claims 1-4 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention. In claim 1, the scope of multiple terms or phrases are unclear: Step 1. What is “a coaxiliaty error source”? What is the function(s) to which the error source is the input? Step 2. What is an individual in “real number coding of individuals” and what is “a corresponding evolution algebra”? Step 3. How is the probability distribution related to the selection of individuals from low to high according to the fitness? The claim may be amended to clarify that selection from low to high is based on the normalization of fitness. Step 5. Is the optimal offspring individuals generated from step 3? With respect to “decoding”, is GA representation of the weights and bias considered as the encoding? Step 6. The term ‘swarm’ is introduced, but not clear how it is related to other claim limitations. The claim may be amended to describe how the swarm affects other concepts (e.g., hyperparameters, GA optimization). Step7. Are the ranges determined by the swarm? Step 8. Is the introduced “a” genetic algorithm same as or different from that described in steps 2 – step 5? Is the MSE different from the “error” in step 5? Step 9. Regarding “into the BP neural network for training”, does the training use the input given in step 1 as training data? Step 10. The scope of the term “comprehensively” is not well defined. A metric may be provided. In claim 2, terms, such as genes and chromosomes, lack antecedent basis. The term “better than” is indefinite as a comparison criterion is not provided. In claim 3, the terms pbest and gbest are not defined. In claim 4, it is not clear how a “sample” is generated and whether the sample is related to the input, individuals or population. Because of plurality of ambiguity in claim language, the scope of the claim cannot be ascertained. Clarification or correction is needed. Claim Rejections - 35 USC § 101 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. 35 U.S.C. 101 reads as follows: Whoever invents or discovers any new and useful process, machine, manufacture, or composition of matter, or any new and useful improvement thereof, may obtain a patent therefor, subject to the conditions and requirements of this title. Claims 1-4 are rejected under 35 U.S.C. 101 because the claimed invention is directed to an abstract idea without significantly more. Claim 1: Step 1. The claim recites a process. Step 2a, prong 1. The claim recites an abstract idea. The steps, generating an initial population of genetic algorithm solutions, taking an error between a predicted value and an actual value of the BP neural network as a fitness function, and selecting the individuals from low to high, according to the fitness function performing crossover and mutation operations to generate a new population, initializing a particle swarm, comprising a swarm size, and a position and of each particle, introducing a genetic algorithm to optimize the BP neural network, and performing solving with MSE as an objective function to find an optimal hyperparameter combination, introducing the optimal initial weight and threshold and the optimal hyperparameter combination into the BP neural network for training, fall under math concepts. The step determining solution ranges of three hyperparameters, comprising a maximum number of times of training, a learning rate, and a regularization coefficient, falls under mental processing. Step 2a, prong 2. This judicial exception is not integrated into a practical application. The additional element, a predicting a coaxiality of parts of rotary equipment, a genetic algorithm-particle swarm optimization-back propagation (GA-PSO-BP) neural network, and performing data preprocessing with a coaxiality error source as an input. The coaxiality equipment is included merely to indicate a data source and does not apply judicial exception beyond generally linking to a particular technological environment (MPEP 2106.05(h)). The genetic algorithm-particle swarm optimization-back propagation (GA-PSO-BP) neural network is a math model. Adding an abstract idea (e.g., a math model) to another abstract idea does not make the claim non-abstract (RecogniCorp). The step performing data preprocessing with a coaxiality error source as an input is an extra solution data collection activity. Step 2b. The claim does not include additional elements that are sufficient to amount to significantly more than the judicial exception. The inclusion of rotary equipment does not improve the functioning of a computer or other technology as it is merely used as a tool to provide data, as broadly recited. Neither does inclusion of the GA-PSO-BP model, a math concept, improves the functioning of a computer. The step performing data preprocessing as an input is a well understood or WURC activity (Umbrajkaar: e.g., Abstract, preparing to collect the vibration signals). Therefore, claim 1 is not eligible. Dependent claims recite further claim limitations, in claim 2, the crossover operation (math concept), in claim 3, swarm optimization (math concept), in claim 4, MSE definition (math concept). Claims 2-4 are not eligible. Examiner Note Claims 1-4 do not have prior art rejection. Reference Umbrajkaar et al. teaches analyzing shaft misalignment based on vibration signals using machine learning approaches. Jiang et al. teaches optimizing RNN based on gravitational search, comprising multiple features of GA and PSO. Jin et al. teaches generating a design parameter model by training a BP using genetic algorithm and particle swarm algorithm for optimization. Combination of references does not expressly disclose claim limitations of claim 1, such as introducing a genetic algorithm to optimize the BP neural network, and performing solving with MSE as an objective function to find an optimal hyperparameter combination and introducing the optimal initial weight and threshold and the optimal hyperparameter combination into the BP neural network for training. Conclusion The prior art made of record and not relied upon is considered pertinent to applicant's disclosure, e.g., reference Tran et al. teaches supply chain management based on anomaly detection using neural networks and refence Chen et al. teaches resource capacity management for multiple users with multiple host controllers. Any inquiry concerning this communication or earlier communications from the examiner should be directed to LiWu Chang whose telephone number is (571)270-3809. The examiner can normally be reached on M-F. 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, Miranda Huang can be reached on (571)270-7092. 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. /LI WU CHANG/Primary Examiner, Art Unit 2124 August 13, 2025
Read full office action

Prosecution Timeline

Jul 28, 2022
Application Filed
Aug 14, 2025
Non-Final Rejection — §101, §112 (current)

Precedent Cases

Applications granted by this same examiner with similar technology

Patent 12603182
INTERPRETATION OF MACHINE LEARNING CLASSIFICATIONS IN CLINICAL DIAGNOSTICS USING SHAPELY VALUES AND USES THEREOF
2y 5m to grant Granted Apr 14, 2026
Patent 12596583
COMPUTE AND MEMORY BASED ARTIFICIAL INTELLIGENCE MODEL PARTITIONING USING INTERMEDIATE REPRESENTATION
2y 5m to grant Granted Apr 07, 2026
Patent 12596917
OPTIMIZING LOW PRECISION INFERENCE MODELS FOR DEPLOYMENT OF DEEP NEURAL NETWORKS
2y 5m to grant Granted Apr 07, 2026
Patent 12592783
OPTICAL ROUTING NETWORK-BASED QUANTUM ARRAY CONTROL
2y 5m to grant Granted Mar 31, 2026
Patent 12591810
NETWORK-ACCESSIBLE MACHINE LEARNING MODEL TRAINING AND HOSTING SYSTEM
2y 5m to grant Granted Mar 31, 2026
Study what changed to get past this examiner. Based on 5 most recent grants.

AI Strategy Recommendation

Get an AI-powered prosecution strategy using examiner precedents, rejection analysis, and claim mapping.
Powered by AI — typically takes 5-10 seconds

Prosecution Projections

1-2
Expected OA Rounds
59%
Grant Probability
99%
With Interview (+53.5%)
4y 7m
Median Time to Grant
Low
PTA Risk
Based on 253 resolved cases by this examiner. Grant probability derived from career allow rate.

Sign in with your work email

Enter your email to receive a magic link. No password needed.

Personal email addresses (Gmail, Yahoo, etc.) are not accepted.

Free tier: 3 strategy analyses per month