Factory of the Future Needs AI
The machine-to-machine (M2M) communications, guided in part by Industry 4.0, are quickly changing the manufacturing process by aggregating process data such as first pass yield and throughput. What’s more, Artificial Intelligence (AI) has enormous potential across a variety of industries, including the manufacturing sector too. By using the right mixture of AI technologies, manufacturers can boost their efficiency, improve flexibility, speed up processes, and even achieve self-optimizing processes. Equipment providers like Koh Young are enabling the Smart Factory of the Future by adopting AI to generate “knowledge” from “experience.”
3D Data Accuracy Value
Data is the most crucial element of the success of the AI solutions. Deep learning effectiveness is linked to the quality and quantity of the input data to address many different requirements from numerous fields. The use of AI to provide smarter inspection systems has been desired by every inspection provider. However, it has been difficult to realize due to the limitations of 2D imaging, which was the de facto standard for the past 25 years. Every aspect of 2D inspection relies on 2D features like contrast; thus, it is extremely challenging to correlate with to the quantitative measurement of 3D objects.
Increasingly Accurate Measurement
So how do we use AI? It begins with solving inspection challenges of SMT assemblies. The solder and components on finished boards have many specular surfaces, which will reflect some light back to camera, while creating strong inter-reflection with other lighting reflections. Since some of the reflected light does not reach the camera, they generate false signals which may cause measurement value errors. This specular reflection issue is becoming more troublesome, in relation with increasing board density and decreased component spacing. Using AI can prevent measurement errors by incorporating learning in the product. The hybrid fusion of an analytic approach utilizing a mathematical measurement model and AI used for learning abnormal symptoms from the combination of good and bad measurement data, allows the system to detect and eliminate abnormal measurements, which reduces false calls and escapes. Through the hybrid fusion approach, the measurement accuracy only gets better against many different challenges.
Improve yield and process optimization
With improving inspection quality is paramount to the manufacturing industry. It requires more computational power, which then yields even better inspection solutions. AI implies improvements can be fulfilled quicker with machines that continuously learn to solve the latest problems. Harnessing the power of its own AI solution, Koh Young has developed Koh Young Process Optimizer (KPO) solution.
Innovative SPI Solutions
KPO is the Koh Young smart factory solution driven by AI to control and optimize the printing and mounting operations. KPO heavily relies on accurate 3D measurements data and error detection from SPI and AOI machines, which sets the stage for smart factory solutions.
The KPO printing solution includes three interlinking modules that exercise complex algorithms to develop closed-loop print process recommendations to help diagnose, analyze, and optimize. By combining real-time printing and SPI measurement data, the enhanced AI engine actively adjusts the printing process. While each module provides inherent standalone process benefits, the combined power of the three modules ensures the highest process reliability and production flexibility while reducing dedicated resources and expertise.
While solder defects are associated with the printing process, these defects pose serious concerns to the industry, especially with the component miniaturization trend. Manufacturers cannot scrap boards or the components due to procurement challenges and costs. However, if the manufacturer does not repair the issue, the board is susceptible to failure. Implementing new innovations like integrated solder dispensing tools to repair defective solder depositions improve quality.
In addition to the AI-based solutions, “in situ” solder dispensing solutions that automatically identify and repair defects within the Solder Paste Inspection (SPI) system can further improve production quality. The 3D SPI system can accurately measure for defects, thanks in part, to its precisely engineered mechanical structure and a “stop and shoot” image capture Moiré technique. The process eliminates vibration and image stitching. Once the solder is measured, the optional Auto Repair tool can automatically add more solder and measure again without ever leaving the work area. This eliminates operator interaction improves production yield.
The design is highly flexible and considers many production variables. For example, imagine a hundred different board layouts with different components – each component type requires a unique solder paste amount. The system can be an effective solution, especially for small BGAs and microchips. It can dispense solder to repair insufficient errors to a wide range of component sizes, including 0402M microchips with a pad-to-pad distance of over 100-microns. Additionally, dynamic z-axis tracking automatically adjusts the distance between the head and the board surface to maintain the ideal focal range and prevent false calls due to PCB warp. Such flexibility allows users to readily improve yields and efficiency in their SMT assembly lines.
Figure: Comparison when using Auto Repair system. BGA Pad – (Left) Insufficient: Before was 2.57% Volume with 16.25% Area (Right) After Auto Repair was 62.79% volume with 86.54% area. Capacitor Pad – (Left) Insufficient: Before was 58.92% volume with 73.66% area (Right) After Auto Repair was 89.21% Volume with 95.9% Area
Future of Smart Factory
What is next for the SPI Auto Repair system in a future smart factory? In the ideal future, connected systems should remove inefficiency from the start, so there may not be anything to repair. Will manufacturers still need an Auto Repair system? The answer may be “yes,” as this is not going to happen soon. Indeed, the Smart Factory will not replace rework applications, instead it will enhance the functionality. Auto Repair powered by AI may be able to recognize complex patterns of solder pads, synthesize information, draw conclusions, and provide recommendations to optimize the solder paste printing process.
Looking forward, Industry 4.0 is rapidly gaining traction among manufacturers. The factory is not a static place, it is a dynamic zone where machines work together to execute complex tasks. In fact, the Koh Young’s Auto Repair system already addresses Industry 4.0 in many aspects. By integrating 3D inspection and repair, it establishes a closed-loop process and eliminates unnecessary board cleaning or scrap. Additionally, it integrates a real-time process dashboard, so operators can quickly verify rework performance and make the right decisions by comparing with previous results.
Artificial Intelligence and its associated benefits will help advance the manufacturing industry confront challenges like the lack of skilled manpower and cost reduction. Koh Young is focusing on using an AI-based solution as the primary vehicle to enable the future of manufacturing for SPI, AOI, and beyond.