Closed-Loop SMT Control for Predictive Solder Defect Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current SMT manufacturing systems are limited in their ability to accurately inspect and correct solder paste orientation, viscosity, solder flux type, and inter-metallic compound presence, leading to defects and increased manufacturing costs due to scrap and rework.
Innovation Solution
An AI-enhanced, self-correcting and closed-loop SMT manufacturing system that employs an AI/ML analysis engine for real-time feedback control, using a Markov decision process model to predict and prevent defects by correlating data from screen printing, inspection, placement, and reflow processes, and providing automatic adjustments to maintain process control.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional SPI systems are used to inspect solder paste, then basic orientation can be detected, but the system cannot identify component pitch, solder flux type, solder viscosity, or provide real-time corrective feedback
Solution Approach 1:
The AI/ML analysis engine is designed to perform multiple inspection functions simultaneously: detecting solder paste orientation, identifying component pitch, determining solder flux type through color analysis, measuring solder viscosity, and providing real-time feedback control. This multi-functional system replaces multiple separate inspection systems with a single unified platform that captures and analyzes comprehensive process data.
Solution Approach 2:
The system implements a closed-loop feedback mechanism where the AI/ML analysis engine receives real-time data from sensors and inspection systems, analyzes the information using trained machine learning models, and automatically sends corrective feedback signals to adjust screen printing parameters, reflow oven settings, and other process variables to maintain optimal manufacturing conditions.
2Reliability
If manual inspection and adjustment methods are used, then process parameters can be monitored, but the process cannot provide real-time predictive analytics or automatic self-correction
Solution Approach 1:
The system uses trained AI/ML models to perform preliminary analysis of process data and predict potential defects before they occur. By analyzing trends in solder paste deposition, component placement patterns, and reflow temperature profiles, the system can anticipate quality issues and automatically adjust process parameters in advance to prevent defects, rather than reacting after problems occur.
Solution Approach 2:
The manufacturing system implements self-service through automatic self-correction capabilities. The AI/ML analysis engine continuously monitors process parameters and automatically adjusts screen printing settings, pick-and-place machine parameters, and reflow oven conditions without human intervention. This self-regulating system maintains optimal process conditions and corrects deviations automatically, eliminating the need for manual inspection and adjustment.
3Manufacturing precision
If comprehensive inspection of all solder paste parameters is performed, then manufacturing precision improves, but device complexity and cost increase
Solution Approach 1:
The system replaces complex mechanical inspection equipment with AI/ML-based analytical models that process data from existing sensors and cameras. Instead of adding numerous specialized mechanical inspection devices, the solution uses machine learning algorithms to extract multiple parameters (orientation, pitch, flux type, viscosity) from standard vision systems and process sensors, significantly reducing hardware complexity while maintaining high measurement precision.
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
The system enables real-time monitoring and predictive analytics to prevent defects, reducing waste and improving PCB quality by automatically adjusting process parameters, eliminating the need for human intervention and enhancing reliability and yield.
Implementation Method 1
The PCB then enters a high temperature zone where the temperature is high enough to melt the solder particles in the solder paste, such as 260° C., which bonds the component leads to the solder pads on the PCB.
Implementation Method 2
The PCB is then sent to a reflow soldering oven that includes a pre-heat zone, where the temperature of the PCB is gradually and uniformly raised. The PCB then enters a high temperature zone where the temperature is high enough to melt the solder particles
Implementation Method 3
The surface tension of the molten solder helps keep the components in place, and if the solder pad geometries are correctly designed, the surface tension automatically aligns the components on their pads.
Data Source
AI summary
An AI enhanced self-correcting and closed loop SMT manufacturing system for fabricating PCBAs. The system includes a screen printer for depositing solder paste on solder pads on a RGB, an SRI sub-system for inspecting the solder paste deposited on the PCB to identify defects, a pick-and-place machine for placing circuit components on the solder paste, an AOI sub-system for inspecting the PCB after the circuit components are placed on the PCB, and a reflow soldering oven for bonding component leads both electrically and mechanically to the pads on the PCB. An AI/ML analysis engine is responsive to process data and variables from each of the screen printer, the SPI sub-system, the pick-and-place machine, the AOI sub-system and the reflow soldering oven and provides downstream feedback signals to each of the screen printer, the SPI sub-system, the pick-and-place machine, the AOI sub-system and the reflow soldering oven for self-correction purposes.