Virtual Metrology for Machine Tool Quality Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for measuring machining quality in machine tools either sacrifice accuracy for promptness or incur significant costs, as they either require frequent off-machine measurements with long sampling intervals or on-machine measurements that divert machining time and are costly to implement across all factory-wide tools.
Innovation Solution
A virtual metrology-based method that correlates product accuracy items with machine tool operation paths, using sensors to collect and de-noise data, which is then converted into feature data to establish a predictive model for timely and accurate machining quality assessment, allowing for prompt recognition of machining quality without the drawbacks of traditional methods.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If off-machine measurement approach is used, then measurement accuracy is improved, but measurement promptness deteriorates due to long sampling intervals
Solution Approach 1:
The patent introduces sensing data (vibration, acoustic emissions) as an intermediary indicator that correlates with workpiece quality without requiring direct physical measurement of every workpiece. This mediator enables real-time quality assessment while avoiding the time loss of frequent off-machine measurements.
Solution Approach 2:
The patent replaces the mechanical measurement system (CMM, probes) with a sensor-based detection system that uses vibration and acoustic emission sensors to predict workpiece quality. This substitution enables continuous monitoring without the time and cost constraints of traditional mechanical measurement methods.
2Loss of time
If on-machine measurement approach is used, then measurement promptness is improved, but machining time is reduced and cost increases
Solution Approach 1:
The patent extracts quality prediction from the machining process itself by collecting sensing data during normal operation. Instead of stopping machining for measurement, the system extracts vibration and acoustic emission signals that contain quality information, allowing continuous production without time loss.
Solution Approach 2:
The machining process itself generates the measurement data through vibration and acoustic emissions during normal operation. The system uses the inherent physical phenomena of the machining process to provide self-monitoring without requiring separate measurement operations, thus maintaining full productivity.
3Loss of time
If on-machine measurement with probes is used, then measurement promptness is improved, but implementation cost increases significantly
Solution Approach 1:
The patent uses inexpensive vibration and acoustic emission sensors instead of expensive precision measuring devices like CMM or tactile probes. These sensors are low-cost, easy to install, and can be deployed across multiple machine tools without significant investment, making the system economically viable for factory-wide implementation.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
Enables the accurate and timely prediction of machining quality for every workpiece, overcoming the limitations of conventional off-machine and on-machine measurement approaches by providing a cost-effective and efficient method to recognize machining quality in real-time.
Implementation Method 1
sets of sample sensing data (such as vibration and/or acoustic data) are obtained from at least one sensor (such as accelerometers and/or acoustic emission (AE) sensors) installed on the machining tool
Implementation Method 2
sets of sample sensing data (such as vibration and/or acoustic data) are obtained from at least one sensor (such as accelerometers and/or acoustic emission (AE) sensors) installed on the machining tool
Data Source
AI summary
A virtual metrology based method for predicting machining quality of a machine tool is provided. In this method, each product accuracy item is correlated with operation paths of the machine tool. During a modeling stage, the machine tool is operated to process workpiece samples, and sample sensing data of the workpiece samples associated with the operation paths are collected during the operation of the machine tool. The sample sensing data of each workpiece sample is de-noised and converted into the sample feature data corresponding to each feature type. The workpiece samples are measured with respect to the product accuracy item and integrated into the feature data for building a predictive model, thereby obtaining quality predicted data for each product accuracy item. During a usage stage, accuracy item values of a workpiece are predicted using the feature data during processing the workpiece in accordance with the predictive models.