Manufacturing Operation Model for Key Performance Indicator Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Complex manufacturing systems face challenges in efficiently estimating key performance indicators for different product variants due to their adaptable and flexible nature, which traditional production efficiency models cannot effectively handle, especially in producing small lots of diverse product variants within a product family.
Innovation Solution
A computer-implemented method that provides predictions of key performance indicators by creating a manufacturing operation model for each product variant, learning model parameters from collected data, and updating production efficiency models to calculate predictions based on process context and execution data, allowing for efficient evaluation of production viability and optimal variant selection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If traditional production efficiency models are used for rigid production execution flows and predefined work schedules, then manufacturing precision and stability are maintained, but adaptability and versatility deteriorate when producing small lots of different product variants
Solution Approach 1:
The patent segments the complex manufacturing system into multiple manufacturing operation models, each representing a specific operation type. This segmentation allows the system to handle different product variants by combining appropriate operation models, thereby improving adaptability without overwhelming complexity in the overall efficiency assessment framework.
Solution Approach 2:
The patent creates a universal production efficiency model that can assess efficiency across multiple product variants and operation types. By designing the model to be variant-agnostic and focusing on operation-level characteristics, it achieves multi-functionality that improves adaptability while maintaining manageable complexity through standardized assessment criteria.
2Measurement precision
If manufacturing operation models are created for each operation type and updated through automated learning, then measurement precision of key performance indicators improves, but device complexity increases due to data collection and model updating mechanisms
Solution Approach 1:
The manufacturing operation models automatically update themselves through automated learning from collected process data. This self-service mechanism improves measurement precision over time without requiring manual intervention, while the system complexity is managed by automating rather than manually orchestrating the data collection and model updating processes.
Solution Approach 2:
The system implements feedback loops where collected process context data and execution data are used to automatically learn and update model parameters. This feedback mechanism continuously improves measurement precision of key performance indicators, while the automated nature of the feedback process manages complexity by eliminating manual model updating steps.
3Productivity
If automated learning is used to update model parameters based on collected process data, then productivity improves through faster efficiency assessment, but loss of information increases due to reliance on automated data processing
Solution Approach 1:
The patent performs preliminary actions by collecting and storing process context data and execution data before the actual efficiency assessment is needed. This preparatory data collection enables fast automated learning and model updating when assessments are required, improving productivity while minimizing information loss by having data readily available in organized formats.
Solution Approach 2:
The system dynamically adapts model parameters based on collected data while maintaining the ability to preserve and reference original process data. This dynamic updating improves productivity by using current information for assessments, while the system manages information retention by maintaining historical data and allowing verification of automated learning results.
Data Source
AI summary
A method provides predictions of key performance indicators of a product variant of a product family manufactured by a complex manufacturing system in a manufacturing process. The method provides a manufacturing operation model for each manufacturing operation type used to manufacture a product variant of the product family. Via the complex manufacturing system measured contributions to key performance indicators, process context data and process execution data of manufacturing operations, are provided. The model parameters of the provided manufacturing operation models are learned automatically based on collected process context data, collected process execution data, and measured contributions to key performance indicators, to update the manufacturing operation models. An updated production efficiency model combining updated manufacturing models including the updated manufacturing operation models, to calculate the predictions of the key performance indicators, of the product variant, to be manufactured, depending on a product configuration of the respective product variant, is evaluated.