Machine Learning Splice Tolerance Prediction for Tire Manufacturing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Manufacturing plants face challenges in efficiently producing products like tires without defects or resource waste due to complex product requirements and strict tolerances, with out-of-tolerance splices triggering alarms and potentially resulting in defective tires.
Innovation Solution
Implementing a machine learning-based system that uses data processing systems with sensors, processors, and a machine learning engine to predict splice tolerance metrics, adjust equipment parameters, and prevent out-of-tolerance splices during the tire manufacturing process.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional splice detection methods are used, then defective tires can be identified, but production time is lost due to equipment alarms and shutdowns
Solution Approach 1:
The machine learning model predicts splice tolerance metrics before the splice is completed, allowing equipment parameters to be adjusted in advance. This preliminary prediction prevents out-of-tolerance splices before they occur, eliminating the need for shutdowns and alarms while maintaining high production rates.
Solution Approach 2:
The system continuously monitors manufacturing parameters and splice metrics in real-time, using machine learning to predict future splice quality. This feedback loop enables dynamic adjustment of equipment parameters to maintain splice tolerance within specifications, preventing defects while keeping production flowing without interruptions.
2Manufacturing precision
If equipment parameters are manually adjusted to fix splice tolerance issues, then splice quality improves, but production time increases due to equipment deactivation
Solution Approach 1:
The machine learning system automatically predicts splice tolerance issues and triggers automatic adjustment of equipment parameters without requiring manual intervention or equipment shutdown. The system serves itself by continuously monitoring, predicting, and correcting splice parameters in real-time, maintaining both precision and continuous production.
Solution Approach 2:
The system dynamically changes equipment parameters based on machine learning predictions of splice tolerance metrics. By continuously adjusting parameters like temperature, pressure, or speed in response to predicted splice quality, the system maintains manufacturing precision without stopping production, as parameters are modified during normal operation rather than requiring equipment deactivation.
3Reliability
If out-of-tolerance splices are detected after assembly, then defective tires can be identified, but resource waste increases
Solution Approach 1:
The machine learning model predicts splice tolerance metrics before the tire assembly is completed, allowing defective splices to be identified and corrected in advance. This preliminary detection prevents defective tires from being manufactured, eliminating the waste of materials that would otherwise be consumed in producing unusable products.
Solution Approach 2:
The system uses machine learning to convert the potential harm of undetected out-of-tolerance splices into a benefit by predicting splice quality issues before they result in defective tires. The predictive capability transforms what would be a quality failure into a preventive action, ensuring materials are not wasted on defective products while maintaining high tire quality standards.
Data Source
AI summary
A system to manufacture a tire includes one or more processors and one or more memories storing instructions executable by the one or more processors and causing the one or more processors to receive, from one or more sensors of one or more pieces of tire manufacturing equipment, one or more values corresponding to manufacturing of a tire, generate a matrix based on the one or more values, predict, via input of the matrix into a machine learning model, a value for a splice tolerance metric for the tire, determine, based on the value for the splice tolerance metric, a first parameter of a first piece of the one or more pieces of tire manufacturing equipment to adjust, and provide a command to adjust the first parameter of the first piece of equipment responsive to determining the value of the splice tolerance metric.