Machining Workflow Prediction with Similarity Metrics and Inference Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The manufacturing planning process for machines, such as CNC milling, is time-consuming and lacks standardization, especially for one-off jobs, and fails to capture user behavior changes due to machine wear, operating conditions, and other factors.
Innovation Solution
A system comprising a processor and memory that determines similarity metrics for task characteristics, clusters process progressions, and creates inference models to predict machining workflows by matching new tasks with similar characteristics, allowing for standardized process progression predictions and continuous learning from user preferences.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual planning processes are used for programming machines to perform tasks, then flexibility to handle different operating conditions and machine wear is maintained, but substantial amount of time is required for planning especially for one-off jobs
Solution Approach 1:
The system performs preliminary action by automatically capturing and storing process progressions from previously executed tasks during normal operations. This pre-captured data is then reused for future similar tasks, eliminating the need for manual replanning and significantly reducing planning time for one-off jobs while maintaining adaptability to changing conditions.
Solution Approach 2:
The system creates copies of process progressions from previously executed tasks and applies them to new tasks with similar characteristics. By encoding task characteristics and matching them with historical data, the system replicates successful process plans without requiring manual recreation, thus improving productivity while preserving the ability to adapt to different operating conditions.
2Stability of the object's composition
If standardized processes are implemented across users, then consistency is improved, but ability to capture user behavior changes due to machine wear and operating conditions is reduced
Solution Approach 1:
The system implements dynamics by continuously updating the stored process progressions as users execute tasks under varying conditions. The captured data reflects actual user behavior changes due to machine wear and operating conditions, allowing the standardized processes to evolve dynamically rather than remaining static. This enables the system to maintain standardization while adapting to changing circumstances.
Solution Approach 2:
The system incorporates feedback by automatically capturing process progression data from executed tasks and using it to update future predictions. This continuous feedback loop ensures that standardized processes remain current and reflect actual user behavior and machine conditions, balancing standardization with adaptability to changing operating conditions.
3Manufacturing precision
If detailed process planning is performed manually, then precision in defining steps, tools, and parameters is achieved, but time consumption increases significantly
Solution Approach 1:
The system performs self-service by automatically capturing process progression data including steps, tools, and parameters from previously executed tasks without requiring manual documentation. This self-captured detailed information is then reused for future tasks, maintaining manufacturing precision while eliminating the time-consuming manual planning process.
Solution Approach 2:
The system replaces the mechanical manual planning process with an automated computational system that encodes task characteristics and matches them with historical data. This substitution maintains the precision of detailed process definition while dramatically reducing planning time by eliminating manual intervention in data capture and analysis.
4Productivity
If automated prediction systems are implemented, then planning time is reduced, but complexity of the system increases
Solution Approach 1:
The system achieves universality by using a single automated prediction framework that handles multiple tasks with different characteristics through encoding and matching. This multi-functional approach reduces planning time across various task types while avoiding the need for separate complex systems for each task type, thereby managing overall system complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Systems, devices, and methods for executing a model preparation component for training a system and a model query component for querying the system are disclosed. In the preparation stage, the system determines a set of process clusters based on a set of similarity metrics for task characteristics using a set of encoded task characteristics and associated process progressions. The system may also create a set of inference models using the determined set of process clusters. In the query stage, the system may identify an encoded task characteristic and a process progression candidate by matching the encoded task characteristics with the closest similarity metric. The system may then determine a process progression prediction based on at least one of the process progression candidate using the similarity metric and/or calculating a new process progression by an inference calculator using the created set of inference models.