Sensor-to-Workpiece Calibration for Hard-to-Measure Machined Features
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods require direct measurement of workpieces with dedicated tools, which is time-consuming and difficult for inaccessible features, especially with long tools, and do not efficiently utilize sensor data from intelligent tools for inference.
Innovation Solution
A method to infer workpiece measurement data from sensor data using sensor-to-workpiece data calibration information, derived from sensor data during machining, allowing inference of workpiece features that are hard to measure directly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a measurement device is used to measure workpiece information, then measurement capability is provided, but the device requires frequent calibration which consumes time and resources
Solution Approach 1:
The patent creates virtual copies of calibration objects using image processing technology. Instead of using physical calibration objects that require manual handling and setup, the system captures images of real calibration objects and generates virtual calibration objects from these images. These virtual copies can be repeatedly used for calibration without physical wear or setup time, significantly reducing calibration time while maintaining measurement precision.
Solution Approach 2:
The patent replaces the mechanical calibration process with an optical and computational approach. Instead of physically positioning and measuring calibration objects using mechanical measurement devices, the system uses image capture devices to obtain images, processes these images computationally to generate virtual calibration objects, and uses these virtual objects for calibration. This substitution eliminates mechanical wear and reduces calibration time while maintaining calibration accuracy.
2Measurement precision
If calibration is performed frequently to maintain measurement accuracy, then measurement precision is improved, but productivity decreases due to time loss
Solution Approach 1:
By creating virtual calibration objects from images, the system enables rapid, repeated calibration operations. The virtual calibration objects can be instantly generated and used multiple times without the time-consuming setup and physical handling required for traditional calibration objects. This maintains calibration accuracy while minimizing productivity loss.
Solution Approach 2:
The system performs preliminary actions by capturing images of calibration objects and generating virtual calibration objects in advance. These virtual calibration objects are stored and can be quickly loaded for calibration operations, eliminating the need for repeated physical setup and preparation during actual measurement operations, thus maintaining both accuracy and productivity.
3Measurement precision
If physical calibration objects are used for calibration, then calibration accuracy is achieved, but the process requires manual operation and consumes resources
Solution Approach 1:
The patent creates virtual calibration objects that are digital copies of physical calibration objects. These virtual objects contain all the necessary calibration information extracted from images of the physical objects. Using virtual calibration objects eliminates the need for manual handling, positioning, and setup of physical calibration objects, significantly improving ease of operation while maintaining calibration accuracy through the preserved geometric and measurement properties of the original objects.
Solution Approach 2:
The system enables self-service calibration by automatically capturing images of calibration objects, processing these images to extract calibration information, and generating virtual calibration objects without requiring manual intervention. The automated image processing and virtual object generation eliminate the need for operators to manually set up and manage physical calibration objects, reducing operational complexity while maintaining calibration accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method comprising: a) causing a tool mounted on a machine tool to work on a workpiece, and at least one sensor, which is configured to measure one or more aspects of the tool and/or machine tool, collecting sensor data during said working; b) a measurement device inspecting the part of the workpiece that was worked on at step a) to obtain measurement data; and c) calculating sensor-to-workpiece data calibration information from the sensor data and the measurement data.