Assembly Line Limit Adjustment Using Failure-Correlation Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing manufacturing processes struggle to optimize manufacturing limits on assembly lines, leading to unnecessary rework, resource wastage, and high field failure rates due to inadequate tolerance settings and process control.
Innovation Solution
A computer system analyzes historical data from assembly units to derive correlations between visual and non-visual features and failure rates, generating prompts to adjust tolerance limits and manufacturing processes to improve yield and reduce resource allocation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If manufacturing limits are set strictly to ensure quality, then field failure rate decreases, but productivity decreases due to unnecessary rework
Solution Approach 1:
The system performs preliminary analysis of historical manufacturing data and feature correlations before setting manufacturing limits. By pre-identifying which features strongly correlate with field failures versus those that don't, the system can set appropriate limits in advance, avoiding both overly strict limits that cause unnecessary rework and overly loose limits that cause field failures.
Solution Approach 2:
The system dynamically adjusts manufacturing limits based on data-driven insights. By analyzing correlations between visual features and field failures, the system modifies tolerance parameters selectively - tightening limits only for features that strongly predict field failures while maintaining or relaxing limits for features that don't correlate with failures, thereby optimizing both quality and productivity.
2Productivity
If manufacturing limits are relaxed to increase productivity, then resource allocation improves, but field failure rate increases
Solution Approach 1:
The system selectively modifies manufacturing limit parameters based on empirical data. By calculating correlations between visual features and field failures, the system identifies which parameters can be relaxed without impacting quality and which must be maintained strictly, achieving optimal resource allocation while preserving reliability.
Solution Approach 2:
The system continuously monitors field failure data and uses it to refine manufacturing limits. By feeding back actual field performance information into the limit-setting process, the system learns which relaxed limits are safe and which need to be tightened, progressively optimizing the balance between productivity and reliability.
3Manufacturing precision
If strict tolerance settings are applied to all features, then manufacturing precision is maintained, but resource wastage increases due to unnecessary rework
Solution Approach 1:
The system applies different tolerance strictness levels to different features based on their individual correlation with field failures. Instead of uniformly applying strict tolerances to all features, the system identifies and applies strict controls only to locally critical features while allowing more flexibility for non-critical features, reducing resource wastage while maintaining necessary precision.
Solution Approach 2:
The system dynamically adjusts tolerance parameters for each visual feature based on its correlation strength with field failures. Features with high correlation coefficients receive tighter tolerance control, while features with low or no correlation receive relaxed tolerances, optimizing the balance between manufacturing precision and resource efficiency.
4Reliability
If comprehensive testing is performed on all assembly units, then field failure detection improves, but productivity decreases due to increased inspection time
Solution Approach 1:
The system focuses testing and inspection efforts on specific visual features that have been identified as strongly correlated with field failures. By concentrating inspection resources on critical features rather than uniformly inspecting all features, the system achieves effective field failure detection while minimizing inspection time and maintaining productivity.
Solution Approach 2:
The system performs partial testing focused on the most critical features rather than comprehensive testing of all features. By applying inspection action selectively to features with high failure correlation, the system achieves sufficient reliability monitoring without the productivity penalty of exhaustive testing.
Data Source
AI summary
A method includes accessing feature values representing a historical population of assembly units assembled on an assembly line; and accessing a failure status of the assembly unit at a target test on the assembly line. The method also includes, for each feature: deriving a correlation between values of the feature and failure status at the target test; deriving an effective limit of the feature based on scope of feature values in the historical population of assembly units; and calculating an action score for the feature based on the correlation and a width of the effective limit. The method further includes: selecting a particular feature exhibiting greatest action score; defining a preemptive test for the particular feature upstream of the target test during a next assembly period; and assigning a target limit, narrower than an effective limit of the particular feature, to the preemptive test.