Digital Twin Quality Control for Manufacturing Influencing Factors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing industrial processes face challenges in controlling and optimizing influencing factors that affect the quality of work products and machine health, such as vibration, wind flow, and dust, which are not effectively addressed by current simulation methods.
Innovation Solution
A computer-implemented system dynamically monitors influencing factors, generates a digital twin of manufacturing processes, analyzes their impact, identifies upper limits, and outputs recommendations to control these factors, using AI to simulate and proactively manage environmental conditions to maintain product quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If digital twin simulation is used to analyze influencing factors, then work product quality and machine health can be improved, but the system complexity and computational resources required increase
Solution Approach 1:
The patent creates a digital twin (virtual copy) of the physical manufacturing system including machines, work products, and influencing factors. This virtual model allows analysis and simulation without affecting the actual system, enabling quality improvement while isolating complexity to the simulation environment. The digital twin copies essential characteristics and behaviors of the physical system to perform what-if analyses.
Solution Approach 2:
The system segments the manufacturing system into distinct components: machines, work products, and influencing factors. Each component is modeled separately in the digital twin, allowing independent analysis and management. This segmentation enables targeted quality improvement by focusing on specific factors affecting work products without requiring complete system redesign.
2Manufacturing precision
If real-time monitoring of influencing factors is implemented, then product quality can be maintained, but the cost and complexity of the monitoring system increase
Solution Approach 1:
The digital twin serves multiple functions: it monitors influencing factors, simulates their effects on work products, identifies quality risks, and generates recommendations. This multi-functionality consolidates what would otherwise require separate monitoring, simulation, and analysis systems into a single unified platform, reducing overall system complexity while maintaining real-time quality oversight.
Solution Approach 2:
The system continuously monitors influencing factors and feeds this data back to the digital twin for real-time simulation and analysis. This feedback loop enables dynamic adjustment and early warning of quality issues, allowing preventive actions before defects occur. The feedback mechanism automates quality management without requiring complex manual monitoring procedures.
3Reliability
If comprehensive analysis of all influencing factors is performed, then quality issues can be prevented, but the time and computational resources required increase
Solution Approach 1:
The digital twin performs preliminary simulations and analyses to identify potential quality issues before they occur in the actual manufacturing process. By pre-analyzing the effects of various influencing factors and their combinations, the system can predict quality risks and prepare preventive measures in advance, reducing the need for time-consuming reactive investigations.
Solution Approach 2:
The system analyzes influencing factors selectively based on their relevance to specific work products and current process conditions. Rather than uniformly analyzing all possible factors at all times, the digital twin focuses computational resources on the most critical factors that have the greatest impact on quality, achieving effective prevention without excessive analysis time.
Data Source
AI summary
In an approach to improve manufacturing quality, embodiments of the present invention dynamically monitor a degree of influencing factors in a predetermined area, and identify one or more machines used in a predetermined manufacturing process. Further, embodiments generate a digital twin of a predetermined final product associated with the predetermined manufacturing process, and analyze an effect of the influencing factors on the identified one or machines or the predetermined final product. Additionally, embodiments identify upper limit of the influencing facts, and output proposed changes to prevent the effects of the influencing factors based on the identified upper limit.