Assembly Line Digital Twin for Production Prediction and Fault Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Modern manufacturing assembly lines with numerous configurable machines face challenges in monitoring operations, making adjustments, and repairing faults without affecting overall production.
Innovation Solution
The development of systems and methods for modeling manufacturing assembly lines, including training predictive models to predict production levels, optimize configuration, and evaluate faults, using cell data, line production data, and machine learning techniques.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a large number of highly configurable machines are used in the assembly line, then the manufacturing capability and product complexity are improved, but the difficulty of monitoring operations and making adjustments increases
Solution Approach 1:
The patent creates a digital twin (virtual model) of the physical assembly line that replicates the behavior and state of all machines. This virtual copy allows operators to monitor, analyze, and optimize the complex system without directly interfering with the physical line, thus resolving the monitoring difficulty while preserving the high manufacturing capability.
Solution Approach 2:
The patent introduces a predictive model and simulation engine as an intermediary between the physical assembly line and the operators. This intermediary layer processes the complex data from multiple configurable machines, translates it into actionable insights, and enables monitoring and adjustment without requiring direct observation of the complex physical system.
2Adaptability or versatility
If a large number of highly configurable machines are used in the assembly line, then the manufacturing capability is improved, but the complexity of the system increases
Solution Approach 1:
By creating a virtual digital twin of the assembly line, the patent externalizes the system complexity into a separate virtual environment. The physical system remains complex and configurable, while the virtual copy provides a simplified interface for analysis, monitoring, and optimization, effectively managing the system complexity.
Solution Approach 2:
The patent segments the complex assembly line system into discrete machines and processes, each represented in the virtual model. This segmentation allows the complex system to be broken down into manageable components that can be individually analyzed, simulated, and optimized while maintaining the overall system's high manufacturing capability.
3Ease of operation
If adjustments and repairs are made to the assembly line, then the operational flexibility is improved, but the overall production is affected
Solution Approach 1:
The patent uses the virtual digital twin to perform preliminary actions - testing adjustments, repairs, and configuration changes in the virtual model before applying them to the physical assembly line. This allows operational flexibility to be improved through simulation and prediction without affecting actual production, as potential issues are identified and resolved beforehand.
Solution Approach 2:
The patent implements a feedback mechanism where the predictive model continuously monitors the virtual model's response to proposed changes and provides feedback on the expected impact on production. This allows operators to make informed decisions about adjustments and repairs that improve operational flexibility while minimizing negative impacts on overall production.
Data Source
AI summary
Various systems and methods for modeling a manufacturing assembly line are disclosed herein. Some embodiments relate to operating a processor to receive cell data and line production data, determine one or more production associations between the cell data and the line production data; evaluate the one or more production associations to identify one or more critical production associations; retrieve the cell data and the line production data associated with the one or more critical production associations; and train a predictive model with the retrieved cell data and the retrieved line production data to predict the production level of the manufacturing assembly line.