Thermal Spray Control Using Acoustic and Image Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional thermal spray systems face challenges in accurately controlling coating characteristics due to variations in process control parameters and equipment degradation, leading to inconsistent coating quality and increased costs from re-coating and delays.
Innovation Solution
A system utilizing acoustic and image sensors to generate time-dependent data signals, which are analyzed by a computing device with a machine learning module to determine relationships between control parameters and process outputs, allowing for real-time adjustment of process outputs to maintain predetermined operating ranges.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If conventional thermal spray systems are used without advanced monitoring, then the system structure remains simple, but coating quality consistency deteriorates due to process parameter variations and equipment degradation
Solution Approach 1:
The patent implements feedback control by continuously monitoring acoustic signals from the thermal spray process and using machine learning models to adjust process parameters in real-time, maintaining coating quality despite equipment degradation or parameter variations
Solution Approach 2:
The patent replaces traditional mechanical monitoring and manual adjustment systems with acoustic sensing and machine learning-based automated control, reducing the need for physical sensors and human intervention while improving coating consistency
2Reliability
If real-time monitoring and adjustment systems are implemented, then coating quality control improves, but system complexity and initial costs increase
Solution Approach 1:
The system performs self-diagnosis and self-adjustment by using acoustic signal analysis to detect process anomalies and automatically modifying spray parameters through machine learning algorithms, reducing the need for external monitoring infrastructure
Solution Approach 2:
The acoustic monitoring system serves multiple functions simultaneously: process characterization, quality prediction, anomaly detection, and control parameter adjustment, replacing the need for multiple separate monitoring systems
3Manufacturing precision
If manual operator intervention is used to adjust process parameters, then the system remains simple to operate, but coating consistency deteriorates due to human variability and reaction time delays
Solution Approach 1:
The system implements closed-loop feedback control where acoustic signals continuously inform the machine learning model of process state, which automatically adjusts parameters without human intervention, eliminating reaction time delays and human variability
Solution Approach 2:
The machine learning model is trained in advance on historical process data to learn optimal parameter adjustments for various acoustic signal patterns, enabling proactive control adjustments before quality defects occur
4Productivity
If traditional process control methods are used, then the control system remains simple, but productivity decreases due to re-coating operations and process delays
Solution Approach 1:
Real-time acoustic monitoring provides continuous feedback on coating formation quality, enabling immediate parameter adjustments that prevent defects and eliminate re-coating operations, significantly improving productivity
Solution Approach 2:
The system rapidly identifies and corrects process deviations using acoustic signal analysis and machine learning, quickly returning the process to optimal parameters and minimizing downtime or re-work cycles
Data Source
AI summary
An example system includes at least one acoustic sensor and one optical sensor to monitor a thermal spray system controlled by a plurality of control parameters and performing a process associated with a plurality of process outputs. The system includes a computing device including a machine learning module and a control module. The machine learning module is configured to determine, based on at least the plurality of control parameters, an at least one time-dependent acoustic data signal, an at least one image data signal, and the plurality of process outputs, a relationship between the plurality of control parameters and the plurality of process outputs by machine learning. The control module is configured to control the thermal spray system to adjust the plurality of process outputs toward a plurality of respective operating ranges.