BoM Revision Recommendations Using Structural and Temporal Patterns
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Assessing and revising product-component structures, particularly in the form of bill of materials (BoM), is challenging due to the complexity and depth of these structures, and manual revisions by domain experts are inefficient and prone to late recognition, leading to potential negative impacts on product and cost performance.
Innovation Solution
An automated framework that learns patterns from historical BoM data using a pattern learning module, calculates confidence values for these patterns, and applies them to forecast revisions, providing recommendations for updating BoM by adding or replacing components.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual revision by domain experts is used, then accuracy of bill of materials revision is maintained, but productivity is reduced and time consumption increases
Solution Approach 1:
An automated assessment system acts as an intermediary between historical bill of materials data and domain experts. The system learns temporal and structural patterns from historical data, generates revision recommendations with confidence values, and presents these to experts for verification. This intermediary processing layer filters and pre-processes revision needs, allowing experts to focus on critical decisions rather than manual assessment of all potential revisions.
Solution Approach 2:
The system performs preliminary assessment of bill of materials revision needs by analyzing historical data and identifying patterns before presenting recommendations to domain experts. By pre-processing the assessment work through automated pattern recognition and confidence value calculation, the system prepares structured recommendations that reduce the time experts need to spend on each revision decision.
2Productivity
If automated pattern learning is implemented, then productivity of bill of materials revision is improved, but device complexity increases
Solution Approach 1:
The automated assessment system is divided into distinct functional modules: a data storage module for historical bill of materials, a pattern learning module that discovers temporal and structural patterns, a recommendation generation module that applies patterns to current data, and a user interface module. This segmentation allows each component to be developed and maintained independently, managing overall system complexity while enabling automated productivity improvements.
Solution Approach 2:
The system incorporates feedback mechanisms where domain experts can verify and correct automated recommendations. This feedback loop allows the system to learn from expert corrections and improve its pattern recognition accuracy over time. The feedback also helps manage complexity by providing a validation layer that ensures automated decisions meet quality standards.
3Reliability
If historical data analysis is performed, then reliability of revision recommendations is improved, but loss of time for data processing increases
Solution Approach 1:
The system performs preliminary pattern learning from historical bill of materials data during off-peak times or in batch processing mode. By pre-extracting temporal and structural patterns and storing them for later use, the system reduces real-time processing requirements when generating recommendations, thereby maintaining high reliability while minimizing time loss during actual revision activities.
Solution Approach 2:
The system applies confidence value thresholds to filter recommendations, focusing on high-probability revisions rather than analyzing every possible change. By setting appropriate confidence thresholds, the system achieves sufficient reliability for critical decisions without processing all possible revision scenarios, thus reducing overall data processing time while maintaining recommendation quality.
Data Source
AI summary
For providing recommendations for bill of materials revision, a database is storing bills of materials for a set of products. A pattern learning module processes the stored bills of materials to learn patterns. Embodiments for learning structural and temporal patterns are provided. A pattern application module applies the patterns to a current bill of materials for a product of interest and forecasts recommendations, with each recommendation indicating how the current bill of materials should be updated. A user interface outputs the recommendations along with the applied patterns and their confidence values. The method and system provide an automized framework that forecasts revision for products. That framework helps to boost product quality by avoiding late recognition of change needs that would most likely negatively impact product and cost performance. Automatically assessing the change needs reduces hours spent by domain experts on these tasks, which saves internal costs.