Making the Invisible Visible: Automated Defect Detection Improves Sapphire Yields
Sapphire is a precious gemstone, consisting of aluminum oxide (α-Al2O3) with occasional traces of other elements such as iron, titanium, chromium, vanadium or magnesium. While sapphire stones found in nature mostly go to jewelry applications, the lab-grown sapphire – produced in a scale of up to several hundred tons per year – is widely used by the electronic industry. Now one can hardly find a branch of technology where this crystal is not used.
Sapphires are mainly applied in infrared optical components, high-durability windows, wristwatch crystals, and the very thin electronic wafers used as the insulating substrates of solid-state electronics. High thermal conductivity, low reactivity, and appropriate unit cell size make sapphire an ideal material for a wide range of such electronic substrates for manufacturing of components such as LEDs and CMOS chips.
SEMI spoke with Ivan Orlov, CEO of Scientific Visual, after his presentation at SEMI Strategic Materials Conference at SEMICON Europa, 12-15 November, 2019 in Munich, Germany, to learn more about the future of sapphire.
SEMI: Why is sapphire an ideal material for a wide range of electronic substrates?
Orlov: Sapphire undoubted advantages are its chemical inertness and ability to withstand high temperature, radiation and mechanical loads. In addition, it exhibits low dielectric loss and very good electrical insulation that makes sapphire a good candidate for substrates for LEDs and laser diodes or wafers for epitaxial growth. However, the most important advantage is that sapphire crystal lattice does very well matching materials deposited to its surface, in particular nitrides of group III elements.
To plainly benefit from these features, the grown sapphire must have as few macro- and micro-defects as possible, as substrate defects are inherited by semiconductors layers grown on the substrate surface. Hence the importance to detect defects in the raw sapphire material. This is the area where our team at Scientific Visual contributes.
SEMI: Flaws are usually identified only after costly wafering and polishing steps, because rough surface of raw crystals prevents detection of the defects. What can be done to prevent defects?
Orlov: Today, major players are investing in growing larger crystals without mastering in depth the growth process. Let’s face it, the semiconductor substrate industry, which is primarily based in Asia, is using empirical research methods. The raw sapphire boules are still inspected manually, and this qualitative assessment is exploited in two folds. The first step is to further process the boule. Furnace operators then adjust the growing parameters depending on the results of the manual inspection.
Due to the lack of visibility into internal crystal defects, the crystal growth and its downstream processing remain an art rather than a science. The primary reasons are the difficulty to measure, locate and quantify precisely the defects in the full crystal volume. Scientific Visual equipment enables defects in raw boules to be fully quantified and categorized. With such objective measurements and knowing the full set of growth parameters, the Process Engineering (PE) team can, with the assistance of deep learning algorithms, considerably improve the growing process. Our quality control tools give Process Engineering team the “eyes” to see complete defect distribution in raw crystals, enabling it to make minor modifications in the growth process to improve yields, reduce costs and shorten the time to market for products.
SEMI: What lead to those advancements and what problems did your team set out to solve?
Orlov: Breakthroughs in immersion tomography, machine vision and parallel computing drove advancements in automated quality control technology. Previously crystal inspection accuracy was limited by the acuity of the operator’s eye and subjective bias. Light distortion and the diffusion of crystals made it impossible to accurately identify internal defects.
Scientific Visual equipment give operators an undistorted 3D view of all defects in a crystal boule or ingot. However, only deep learning technology can correlate a hundred thousand growth data points to identify a final defect pattern.
Defect pattern in non-processed item cored from EFG sapphire plate. Well visible istypical wavy pattern of surface layers and sandwich structure in the volume. Color code marks sapphire defect density: from deep blue (non-defective material) to deep red (highest defectiveness.)
SEMI: What challenges are addressed by your approach?
Orlov: Increasing the yield of semiconductor substrates like Sapphire, Gallium Nitride and Silicon Carbide is paramount to reducing the price of wafers while increasing their quality. The upstream growth and downstream wafering processes are not deterministic. So far, most of the producers can only determine the quality during the late stages of the process. This condition creates huge constraints for teams in charge of production and processing. Automated Quality Control (QC) at the early stage of the production chain relieves all the unknowns, ultimately reduce the cost of material.
SEMI: And what are the main opportunities?
Orlov: There are massive opportunities to increase the yield and to ease the full processing chain from growth to the wafering process. Objective Quality Control (OQC) paves the way to industry-wide standards that categorize crystal quality at each step of growth to enable full certification of the defectiveness of the material and facilitate its trade and exchange.
SEMI: What’s one of your predictions for the future of new materials?
Orlov: The explosion of e-mobility and electric vehicles and the development of other green technologies will drive rising demand for low-defect sapphire, silicon carbide and gallium nitride substrates thanks to the streamlining of the full processing chain. Manual quality control will soon give way to full automation as quality control in sapphire and other raw crystals production is the only missing link in a fully automated semiconductor production chain. I believe that in five years, automated raw crystal inspection will become standard in the industry. Our mission is to empower every crystal grower to achieve this important milestone.
Dr. Ivan Orlov obtained a Ph.D. in Crystallography from the Federal University of Technology in Switzerland and an MSc in Solid-State Physics in Moscow, Russia. Ivan co-founded Scientific Visual in 2010 to answer the challenge of the synthetic crystals industry struggling with high defect yield. Prior to this he worked in a company specialized in diamond optics. He has more than 10 years of experience in R&D with focus on optical materials, industrial crystals and non-destructive quality control technologies. Dr. Orlov was a SEMI Task Force member for sapphire standard development in China and collaborates with ISO committee in Switzerland to establish industry-wide sapphire quality standards.
Serena Brischetto is a marketing and communications manager at SEMI Europe.