Artificial intelligence is one of the driving forces in today’s semiconductor industry, with more traditional market drivers like high performance compute and smart phones continuing to play important roles. This situation is unlikely change in the years ahead as chip makers continue their quest to create the most advanced nodes. With 3nm nodes in production and 2nm nodes on the horizon, the importance of film measurement only grows in significance as fabs seek to maintain the performance and reliability of cutting-edge devices.
Film metrology is an essential part of semiconductor manufacturing, whether you are dealing with material discovery, technology development, equipment or process control. In a typical semiconductor device manufacturing cycle, there are hundreds of film deposition and removal steps. In addition, film deposition and removal are also commonly used to monitor equipment health. Many of these steps use film measurement tools to ensure that equipment and processes are meeting production requirement.
In the semiconductor industry, digital twins are the focus of a lot of attention, with substantial investments from industry players and governments alike. This year the European Union and the United States have pledged hundreds of millions of dollars in grants and funding opportunities, including the new CHIPS Digital Twin Manufacturing USA Institute. Ultimately, many people see great value in innovating, commercializing and scaling digital twin technology.
As with many trends, digital twins are the subject of speculation and fervor. Unfortunately, this enthusiasm can drive well intentioned users and organizations to choose solutions they don’t need – or spend too much time and money before arriving at reliable ones.
Whether the discussion is about smart manufacturing or digital transformation, one of the biggest conversations in the semiconductor industry today centers on the tremendous amount of data fabs collect and how they utilize that data.
While chip makers are accumulating petabytes of data across the entire semiconductor process, a question arises: how much of that information is being fully utilized? The answer may be around 20%, according to the Semiconductor Engineering article “Too Much Fab and Test Data, Low Utilization.” Unfortunately, this poses a challenge because fab end customers are demanding highly reliable chips, in other words, chips with zero escaping defects and which offer manufacturers clear genealogy and traceability.
Many of you reading this work for companies that have started or are planning digital transformations. To do this, these companies will need to better integrate the data they collect — and that includes data from materials, products, processes, factory subsystems and equipment.
For smart manufacturing to truly live up to its potential, manufacturers will need inline automation that takes complete advantage of the analytics their monitoring systems generate, analytics which can be fed back to the process tools, manufacturing execution systems and other factory systems in real time. Working in concert, these integrated systems are essential to creating a zero defect manufacturing environment.
In the world of smart manufacturing, manufacturers will be tasked with providing timely total solutions to detect and classify defects using inspection and metrology tools, conduct root cause analysis to determine the source of said defects and, finally, employ process control and equipment monitoring using run-to-run and fault detection and classification software solutions to prevent defects from reoccurring.
In this blog, the first in our three-part series “Achieving Zero Defect Manufacturing,” we will focus on detecting and classifying defects. We will start by looking at solutions at the defect level before moving on to the die level and the wafer level.
The United States is seeking to breathe new life into its domestic semiconductor packaging sector with the National Advanced Packaging Manufacturing Program (NAPMP), an initiative to “establish and accelerate domestic capacity for advanced packaging substrates and substrate materials,” according to a Commerce Department announcement from earlier this year [1]. In part, this program is the result of two very distinct trends, both of which are high-priority pursuits for governments and manufacturers. On the one hand, many nations like the U.S. are looking to shore up their semiconductor manufacturing capabilities to better protect themselves from potential geopolitical complications. Still another consideration is today’s rapidly growing demand for high-end applications like artificial intelligence (AI) and high performance computing (HPC) that are driving the need for advanced packages with 2.5 and 3D architectures. Such structures are built upon advanced integrated circuit substrates (AICS). Furthermore, the coming era of glass core substrates in advanced packaging will offer another level of challenges. The future is coming, and few want to be left behind.
Automated optical inspection (AOI) is a cornerstone in semiconductor manufacturing, assembly and testing facilities, and as such, it plays a crucial role in yield management and process control. Traditionally, AOI generates millions of defect images, all of which are manually reviewed by operators. This process is not only time-consuming but error prone due to human involvement and fatigue, which can negatively impact the quality and reliability of the review.
In the Industry 4.0 era, the integration of a deep learning-based automatic defect classification (ADC) software solution marks a significant advancement in manufacturing automation. For one, ADC solutions reduce manual workload – meaning less chance of human error and higher accuracy – and, two, they are poised to lower the costs associated with high-volume manufacturing (HVM).
Deep learning, a branch of machine learning based on artificial neural networks, is at the core of these ADC solutions. It mimics the human brain’s ability to learn and make decisions; this enables the system to recognize complex patterns in data without explicit programming. Compared to traditional methods, this approach offers a significant leap in processing efficiency and accuracy.