17528122. Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof simplified abstract (Capital One Services, LLC)
Contents
- 1 Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof
- 1.1 Organization Name
- 1.2 Inventor(s)
- 1.3 Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof - A simplified explanation of the abstract
- 1.4 Simplified Explanation
- 1.5 Potential Applications
- 1.6 Problems Solved
- 1.7 Benefits
- 1.8 Original Abstract Submitted
Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof
Organization Name
Inventor(s)
Donald Gennetten of McLean VA (US)
Fatma Ben Yemna of McLean VA (US)
Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof - A simplified explanation of the abstract
This abstract first appeared for US patent application 17528122 titled 'Computer-Based Systems Involving Pipeline and/or Machine Learning Aspects Configured to Generate Predictions for Batch Automation/Processes and Methods of Use Thereof
Simplified Explanation
The patent application describes a system and method for using machine learning to predict future failures or anomalies in batch processes. Here are the key points:
- The system collects historical data from previous batch processes.
- A machine learning model is trained using this data to predict future failures or flags in the execution of future batch processes.
- Descriptive analytics related to the batch processes are generated and collected.
- The trained machine learning model and descriptive analytics are used to predict future failures or flags in the batch processes.
Potential Applications
This technology can be applied in various industries and sectors where batch processes are used, such as:
- Manufacturing: Predicting failures in production processes to minimize downtime and optimize efficiency.
- Pharmaceuticals: Identifying potential issues in the manufacturing of drugs to ensure quality and safety.
- Energy: Anticipating failures in power generation processes to prevent outages and reduce maintenance costs.
- Chemicals: Predicting anomalies in batch reactions to improve product quality and reduce waste.
Problems Solved
The technology addresses the following problems:
- Unplanned downtime: By predicting failures in advance, organizations can take preventive measures to minimize unplanned downtime and associated costs.
- Quality control: Identifying potential issues in batch processes allows for timely interventions to ensure product quality and avoid waste or rework.
- Efficiency optimization: Anticipating anomalies or flags in execution helps optimize resource allocation and improve overall process efficiency.
Benefits
Implementing this technology offers several benefits:
- Cost savings: By avoiding unplanned downtime and reducing waste, organizations can save on maintenance, production losses, and material costs.
- Improved productivity: Predicting failures or anomalies allows for proactive maintenance and process optimization, leading to increased productivity.
- Enhanced quality control: Early identification of potential issues helps maintain product quality and avoid recalls or customer dissatisfaction.
- Data-driven decision making: The use of machine learning and descriptive analytics provides valuable insights for informed decision making and process improvement.
Original Abstract Submitted
Systems and methods involving provision of machine-learning-based prediction of future failure, anomaly, etc. in execution of batch processes are disclosed. In one illustrative implementation, an exemplary method may comprise obtaining historical data from prior execution of one or more batch processes, training a machine learning model to predict one or more future failure(s) and/or future flag(s) in execution of a future batch process, generating and/or collecting descriptive analytics pertinent to execution of the batch processes, and predicting a future failure and/or future flag in execution of the batch processes using the trained machine learning model and/or the descriptive analytics.
