Motor Drive Virtual Metrology with Hierarchical Diagnosis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional virtual metrology techniques face challenges in simultaneously achieving immediacy and accuracy in quality measurement, struggle to distinguish between external force disturbances and mechanism-related aging issues, and incur high hardware costs due to aggregate calculation architectures, limiting their ability to predict product quality and adjust processing strategies effectively.
Innovation Solution
A production system with a hierarchical processing structure and a drive that includes real and virtual system driving modules, quality measurement, and mechanism diagnosis parameter processing modules, allowing for immediate quality prediction, external force disturbance identification, and mechanism diagnosis, while reducing data transfer and computing burdens and hardware costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If conventional virtual metrology technique is used to predict product quality, then immediacy is achieved, but accuracy deteriorates
Solution Approach 1:
The patent segments the calculation architecture into distributed computing nodes instead of a single aggregate server. Each node processes local data independently, enabling immediate local predictions while maintaining accuracy through distributed computation. This segmentation resolves the contradiction by allowing fast local responses without burdening a central system.
Solution Approach 2:
The patent transitions from a single-level aggregate calculation architecture to a multi-dimensional hierarchical structure with edge devices, local servers, and cloud platforms operating at different levels. This dimensional change enables simultaneous immediate predictions at edge levels and accurate comprehensive analysis at higher levels, resolving the immediacy-accuracy trade-off.
2Measurement precision
If conventional virtual metrology technique is used to ensure accuracy, then measurement precision is improved, but immediacy deteriorates
Solution Approach 1:
The patent implements preliminary action by pre-processing and caching data at edge devices and local servers before comprehensive analysis is needed. This allows immediate predictions using pre-computed data, while accurate comprehensive analysis can be performed subsequently without time penalty, resolving the accuracy-immediacy contradiction.
3Reliability
If aggregate calculation architecture is used for virtual metrology, then comprehensive analysis is achieved, but hardware cost and computing burden increase
Solution Approach 1:
The patent segments the centralized aggregate calculation architecture into distributed computing nodes at multiple levels (edge devices, local servers, cloud platforms). Each segment handles appropriate computations locally, reducing the hardware burden on any single system while maintaining comprehensive analysis capability through coordinated distributed processing.
Solution Approach 2:
The patent creates a universal hierarchical architecture where computing nodes at different levels can perform multiple functions - local predictions, data caching, comprehensive analysis, and model training. This multi-functionality reduces overall hardware costs by eliminating the need for specialized dedicated systems for each function.
4Measurement precision
If conventional virtual metrology technique is used to evaluate product quality, then quality measurement is achieved, but ability to distinguish external force disturbance from mechanism aging deteriorates
Solution Approach 1:
The patent introduces intermediary components - virtual sensors and diagnostic algorithms - that mediate between raw measurement data and quality evaluation. These intermediaries analyze patterns and distinguish whether deviations originate from external force disturbances or mechanism aging, preserving critical information that would otherwise be lost in conventional quality evaluation.
Data Source
AI summary
A production system, a drive and an operating method provide the functions of quality measurement and mechanism diagnosis. The production system has a hierarchical processing structure. The drive includes a real system driving module and a virtual system driving module. The real system driving module generates a mechanism real operation parameter information. In a system identification mode, the drive creates at least one virtual mechanism model. The drive generates a mechanism stimulation operation parameter information according to a processing strategy of a controller, the mechanism real operation parameter information and the at least one virtual mechanism model. The controller performs a quality measurement operation, performs a mechanism diagnosis operation and/or adjusts the processing strategy according to the mechanism real operation parameter information and the mechanism stimulation operation parameter information.