Cold Expansion Quality Assessment Using Pressure and Piston Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in the mechanical processing of materials lies in the difficulty of verifying and quantifying the residual stress field induced by split-sleeve hole cold expansion, which is crucial for enhancing fatigue life but is hard to measure and verify post-process.
Innovation Solution
A hole cold expansion tool system that monitors key parameters during the process using real-time data processing, enabling enhanced quality control and verification through hydraulic pressure and piston location analysis, and employs machine-learning techniques like deep neural networks to assess the quality and predict fatigue life.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of stationary object
If split-sleeve hole cold expansion is performed to induce residual stress, then fatigue life is significantly increased, but measurement and verification of the residual stress field becomes difficult and expensive
Solution Approach 1:
The patent implements real-time feedback monitoring during the cold expansion process by measuring hydraulic pressure and piston location, and using machine learning models to assess whether the process achieved the desired residual stress state. This feedback mechanism allows verification without post-process measurement of the residual stress itself.
Solution Approach 2:
The patent uses hydraulic pressure and piston location as intermediary measurable parameters that correlate with the residual stress state. Instead of directly measuring the difficult-to-access residual stress, the system measures these intermediary parameters and uses machine learning to infer the residual stress quality.
2Measurement precision
If post-process verification methods are used to quantify residual stress, then assessment is possible, but the process becomes difficult and expensive
Solution Approach 1:
The patent replaces complex mechanical post-process verification systems with a machine learning-based assessment system that uses readily available process data (hydraulic pressure and piston location) to evaluate residual stress quality, significantly reducing device complexity and cost.
Solution Approach 2:
The patent creates a virtual model of the residual stress state through machine learning algorithms that replicate the relationship between process parameters and residual stress outcomes, allowing assessment without physical measurement of the residual stress field.
3Manufacturing precision
If real-time monitoring of hydraulic pressure and piston location is implemented, then quality control is enhanced, but device complexity increases
Solution Approach 1:
The patent makes the monitoring system multi-functional by using the same hydraulic pressure and piston location data for both process control and quality assessment purposes. The machine learning model serves multiple functions including real-time assessment, predictive analytics, and process optimization.
Solution Approach 2:
The system performs self-assessment of quality by automatically analyzing its own process data through machine learning algorithms, eliminating the need for separate verification equipment and reducing overall system complexity.
Data Source
AI summary
Automated assessment of material-processing operations employs a deep feature-recognition network engine including a multilayer architecture. An input layer includes a plurality of nodes operative to receive measurement data comprising a work-profile data set representing a mechanical response over a displacement to a cold-working material-processing operation effecting the displacement, by a target portion of a workpiece. A plurality of layers are operative to produce activations of nodes based on feature sets derived from the measurement data, and to further produce an output based on the activations. The output represents an assessment of performance of the cold-working material-processing operation.