SVM Steady State Detection in Manufacturing via NIR Spectroscopy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for monitoring manufacturing processes, such as continuous manufacturing, struggle to accurately detect when a process transitions from an unsteady state to a steady state, especially with multivariate spectral data.
Innovation Solution
A device utilizing a support vector machine (SVM) classification model is trained with spectral data to predict transition times from unsteady to steady states, generating multiple iterations of the model to determine a final classification model for real-time process monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing monitoring techniques are used for manufacturing processes, then the system is simple to operate, but the accuracy of detecting steady state transitions is insufficient
Solution Approach 1:
The patent segments the manufacturing process into distinct states (unsteady state and steady state) and uses an iterative SVM classification model to detect transitions between these segments. The model processes spectral data in iterations, progressively improving detection accuracy by dividing the complex detection task into manageable classification steps.
Solution Approach 2:
The patent employs a dynamic, iterative SVM classification model that adapts to the evolving spectral data during the manufacturing process. The model iteratively refines its classification boundaries based on incoming spectral data, allowing it to dynamically detect steady state transitions with high accuracy while managing complexity through controlled iteration.
2Measurement precision
If multiple iterations of SVM classification model are generated, then the detection accuracy improves, but the processing time increases
Solution Approach 1:
The patent performs preliminary actions by pre-processing spectral data and establishing the iterative SVM framework before actual steady state detection. The model structure and iteration protocol are predetermined, allowing for efficient processing during actual detection while maintaining high accuracy through the pre-established iterative refinement approach.
Solution Approach 2:
The patent maintains continuous useful action by implementing an iterative SVM model that continuously processes spectral data without interruption. The iterations proceed seamlessly, with each iteration building on previous results, ensuring continuous detection capability while optimizing the balance between accuracy improvement and processing time through efficient iteration management.
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
This approach enhances the accuracy and robustness of detecting steady states in manufacturing processes by considering multiple variables, thereby improving process control and efficiency.
Implementation Method 1
Endpoint detection in manufacturing process by near infrared spectroscopy and machine learning techniques
Data Source
Figure 1A
Figure 1B
Figure 1C
AI summary
A method may comprises identifying, by a device, a support vector machine (SVM) classification model for determining whether a manufacturing process has reached a steady state; receiving, by the device and from one or more spectrometers, multivariate spectral data measured during a performance of the manufacturing process; determining, by the device, based on the multivariate spectral data, and using the SVM classification model, whether the manufacturing process is at the steady state at a particular time; and providing, by the device and after determining whether the manufacturing process is at the steady state at the particular time, an indication that the manufacturing process has reached the steady state.