#Computer vision in wafer inspection

[einnosyssecsgem]

Machine learning applications in semiconductor manufacturing

Machine Learning Applications in Semiconductor Manufacturing: Revolutionizing the Industry

The semiconductor industry is the backbone of modern technology, powering everything from smartphones and computers to autonomous vehicles and IoT devices. As the demand for faster, smaller, and more efficient chips grows, semiconductor manufacturers face increasing challenges in maintaining precision, reducing costs, and improving yields. Enter machine learning (ML)—a transformative technology that is revolutionizing semiconductor manufacturing. By leveraging ML, manufacturers can optimize processes, enhance quality control, and accelerate innovation. In this blog post, we’ll explore the key applications of machine learning in semiconductor manufacturing and how it is shaping the future of the industry.

Predictive Maintenance

Semiconductor manufacturing involves highly complex and expensive equipment, such as lithography machines and etchers. Unplanned downtime due to equipment failure can cost millions of dollars and disrupt production schedules. Machine learning enables predictive maintenance by analyzing sensor data from equipment to predict potential failures before they occur.

How It Works: ML algorithms process real-time data from sensors, such as temperature, vibration, and pressure, to identify patterns indicative of wear and tear. By predicting when a component is likely to fail, manufacturers can schedule maintenance proactively, minimizing downtime.

Impact: Predictive maintenance reduces equipment downtime, extends the lifespan of machinery, and lowers maintenance costs.

Defect Detection and Quality Control

Defects in semiconductor wafers can lead to significant yield losses. Traditional defect detection methods rely on manual inspection or rule-based systems, which are time-consuming and prone to errors. Machine learning, particularly computer vision, is transforming defect detection by automating and enhancing the process.

How It Works: ML models are trained on vast datasets of wafer images to identify defects such as scratches, particles, and pattern irregularities. Deep learning algorithms, such as convolutional neural networks (CNNs), excel at detecting even the smallest defects with high accuracy.

Impact: Automated defect detection improves yield rates, reduces waste, and ensures consistent product quality.

Process Optimization

Semiconductor manufacturing involves hundreds of intricate steps, each requiring precise control of parameters such as temperature, pressure, and chemical concentrations. Machine learning optimizes these processes by identifying the optimal settings for maximum efficiency and yield.

How It Works: ML algorithms analyze historical process data to identify correlations between input parameters and output quality. Techniques like reinforcement learning can dynamically adjust process parameters in real-time to achieve the desired outcomes.

Impact: Process optimization reduces material waste, improves yield, and enhances overall production efficiency.

Yield Prediction and Improvement

Yield—the percentage of functional chips produced from a wafer—is a critical metric in semiconductor manufacturing. Low yields can result from various factors, including process variations, equipment malfunctions, and environmental conditions. Machine learning helps predict and improve yields by analyzing complex datasets.

How It Works: ML models analyze data from multiple sources, including process parameters, equipment performance, and environmental conditions, to predict yield outcomes. By identifying the root causes of yield loss, manufacturers can implement targeted improvements.

Impact: Yield prediction enables proactive interventions, leading to higher productivity and profitability.

Supply Chain Optimization

The semiconductor supply chain is highly complex, involving multiple suppliers, manufacturers, and distributors. Delays or disruptions in the supply chain can have a cascading effect on production schedules. Machine learning optimizes supply chain operations by forecasting demand, managing inventory, and identifying potential bottlenecks.

How It Works: ML algorithms analyze historical sales data, market trends, and external factors (e.g., geopolitical events) to predict demand and optimize inventory levels. Predictive analytics also helps identify risks and mitigate disruptions.

Impact: Supply chain optimization reduces costs, minimizes delays, and ensures timely delivery of materials.

Advanced Process Control (APC)

Advanced Process Control (APC) is critical for maintaining consistency and precision in semiconductor manufacturing. Machine learning enhances APC by enabling real-time monitoring and control of manufacturing processes.

How It Works: ML models analyze real-time data from sensors and equipment to detect deviations from desired process parameters. They can automatically adjust settings to maintain optimal conditions, ensuring consistent product quality.

Impact: APC improves process stability, reduces variability, and enhances overall product quality.

Design Optimization

The design of semiconductor devices is becoming increasingly complex as manufacturers strive to pack more functionality into smaller chips. Machine learning accelerates the design process by optimizing chip layouts and predicting performance outcomes.

How It Works: ML algorithms analyze design data to identify patterns and optimize layouts for performance, power efficiency, and manufacturability. Generative design techniques can even create novel chip architectures that meet specific requirements.

Impact: Design optimization reduces time-to-market, lowers development costs, and enables the creation of more advanced chips.

Fault Diagnosis and Root Cause Analysis

When defects or failures occur, identifying the root cause can be challenging due to the complexity of semiconductor manufacturing processes. Machine learning simplifies fault diagnosis by analyzing vast amounts of data to pinpoint the source of problems.

How It Works: ML models analyze data from multiple stages of the manufacturing process to identify correlations between process parameters and defects. Techniques like decision trees and clustering help isolate the root cause of issues.

Impact: Faster fault diagnosis reduces downtime, improves yield, and enhances process reliability.

Energy Efficiency and Sustainability

Semiconductor manufacturing is energy-intensive, with significant environmental impacts. Machine learning helps reduce energy consumption and improve sustainability by optimizing resource usage.

How It Works: ML algorithms analyze energy consumption data to identify inefficiencies and recommend energy-saving measures. For example, they can optimize the operation of HVAC systems and reduce idle time for equipment.

Impact: Energy optimization lowers operational costs and reduces the environmental footprint of semiconductor manufacturing.

Accelerating Research and Development

The semiconductor industry is driven by continuous innovation, with new materials, processes, and technologies being developed regularly. Machine learning accelerates R&D by analyzing experimental data and predicting outcomes.

How It Works: ML models analyze data from experiments to identify promising materials, processes, or designs. They can also simulate the performance of new technologies, reducing the need for physical prototypes.

Impact: Faster R&D cycles enable manufacturers to bring cutting-edge technologies to market more quickly.

Challenges and Future Directions

While machine learning offers immense potential for semiconductor manufacturing, there are challenges to overcome. These include the need for high-quality data, the complexity of integrating ML into existing workflows, and the shortage of skilled professionals. However, as ML technologies continue to evolve, these challenges are being addressed through advancements in data collection, model interpretability, and workforce training.

Looking ahead, the integration of machine learning with other emerging technologies, such as the Internet of Things (IoT) and digital twins, will further enhance its impact on semiconductor manufacturing. By embracing ML, manufacturers can stay competitive in an increasingly demanding and fast-paced industry.

Conclusion

Machine learning is transforming semiconductor manufacturing by enabling predictive maintenance, defect detection, process optimization, and more. As the industry continues to evolve, ML will play an increasingly critical role in driving innovation, improving efficiency, and ensuring sustainability. By harnessing the power of machine learning, semiconductor manufacturers can overcome challenges, reduce costs, and deliver cutting-edge technologies that power the future.

This blog post provides a comprehensive overview of machine learning applications in semiconductor manufacturing. Let me know if you’d like to expand on any specific section or add more details!

[solarinfoai]

The Next Frontier in Solar O&M: Beyond RGB and Thermal with Advanced Drone Sensors

For years, the gold standard in solar panel drone inspection has been the combination of high-resolution RGB (visual) cameras and radiometric thermal imagers. This powerful duo has revolutionized Operations & Maintenance (O&M) for solar farms, enabling rapid identification of physical damage and thermal anomalies like hotspots, bypass diode failures, and string outages. Yet, as the solar industry matures and pushes the boundaries of efficiency and asset longevity, the need for even deeper, more nuanced insights into module health has become paramount.

The next frontier in drone-based solar inspection lies in the integration of advanced sensor technologies that go far beyond what the human eye or a standard thermal camera can perceive. These cutting-edge payloads, coupled with sophisticated AI automation and solar computer vision, are unlocking a new era of predictive maintenance, unparalleled quality assurance, and maximized energy yields.

The Foundation: RGB and Thermal (And Their Limits)

Before we delve into the future, let's briefly acknowledge the foundational role of RGB and thermal cameras:

RGB (Visual) Cameras: These provide high-resolution images of the solar array, essential for detecting macroscopic physical defects such as shattered glass, delamination, severe soiling, bird nests, and vegetation encroachment. They are crucial for visual documentation and contextual understanding.

Radiometric Thermal Imagers: These are the workhorses for performance diagnostics. They measure infrared radiation emitted by the panels, translating it into temperature maps. Hotspots (caused by faulty cells, shunts, or bypass diode failures), string outages (entire sections appearing cold), and overall panel underperformance are readily visible.

While incredibly effective, RGB and thermal inspections have their limitations. They primarily identify symptoms of problems that are already manifesting as thermal signatures or visible damage. They often cannot peer inside the solar cell or detect degradation mechanisms at their earliest, most subtle stages. This is where the next generation of sensors comes into play.

Diving Deeper: Next-Generation Sensor Technologies

The advancements in miniaturization and sensor technology are now allowing drones to carry payloads that were once confined to laboratories or ground-based testing.

1. Electroluminescence (EL) & Photoluminescence (PL) Imaging

Imagine an X-ray for your solar panel. That's essentially what EL and PL imaging offer.

How they work:

Electroluminescence (EL): During an EL inspection, a controlled electrical current is applied to the solar modules (often requiring temporary disconnection from the inverter). This causes the silicon cells to emit a faint infrared light.

Photoluminescence (PL): Similar to EL, PL involves exciting the solar cells, but instead of an electrical current, an external light source (e.g., a laser) is used.

What they reveal: Both EL and PL cameras capture this emitted light. Anomalies in the light emission directly correspond to internal defects within the silicon cells that are often invisible to standard thermal or RGB cameras. These can include:

Micro-cracks: Tiny fissures in the silicon wafer, often caused by manufacturing stress, shipping impacts, or thermal cycling. These can propagate over time, leading to significant power loss.

Shunts: Areas where current bypasses the normal circuit, leading to power loss and potential hotspots.

Inactive cell areas: Regions of a cell that are no longer contributing to power generation.

Finger line defects: Issues with the metallic grid lines on the cell surface.

Potential Induced Degradation (PID): A phenomenon where voltage differences between the cells and grounded module frame cause power loss.

Drone Integration: Historically, EL/PL required darkroom conditions or night-time ground operations. However, advancements in highly sensitive SWIR (Short-Wave Infrared) cameras and sophisticated biasing tools are now enabling drone-based, even daylight, EL/PL inspections, albeit with specific operational considerations. This is a game-changer for detailed, pre-commissioning QA and pinpointing root causes of elusive performance issues.

2. Hyperspectral Imaging

While RGB cameras see in three broad bands (red, green, blue), and multispectral cameras see in a few more, hyperspectral imaging captures data across hundreds of very narrow, contiguous spectral bands.

How it works: Each material has a unique spectral "fingerprint" – how it absorbs and reflects light at different wavelengths. Hyperspectral cameras capture this detailed fingerprint for every pixel in an image.

What it reveals: By analyzing these unique spectral signatures, hyperspectral imaging can detect:

Early-stage material degradation: Changes in encapsulant material (e.g., EVA browning) or backsheet degradation before they become visually apparent.

Moisture ingress: Subtle signs of water penetration that can lead to delamination or corrosion.

Contaminant identification: Differentiating between types of soiling (dust, pollen, organic matter) based on their chemical composition, which can inform more effective cleaning strategies.

Defects related to cell chemistry: Detecting subtle changes in cell material properties that indicate performance issues or manufacturing flaws.

Drone Integration: Miniaturized hyperspectral sensors are increasingly available for drone platforms, offering unprecedented material-level insights over large areas.

3. LiDAR (Light Detection and Ranging)

Unlike cameras that capture reflected light, LiDAR uses pulsed lasers to measure distances, creating highly accurate 3D representations of the environment.

How it works: A LiDAR sensor emits laser pulses and measures the time it takes for them to return after hitting an object. This data is used to generate a dense "point cloud" that accurately maps the topography and any objects within the scanned area.

What it reveals (for solar): While not directly for panel defects, LiDAR is invaluable for:

Precise 3D Modeling and Digital Twins: Creating highly accurate digital replicas of the solar farm, including terrain, module heights, and surrounding structures. This is crucial for planning, simulations, and future expansions.

Accurate Shading Analysis: Identifying and quantifying even subtle shading from adjacent modules, structures, or vegetation, which can significantly impact energy production.

Vegetation Management: Precisely mapping vegetation encroachment and growth rates around the solar array, allowing for targeted and efficient clearing.

Structural Integrity Monitoring: Detecting ground subsidence, panel tilt changes, or racking system deformities that could lead to long-term issues.

Drone Integration: Drones equipped with LiDAR can rapidly map large solar farms, even in complex terrains or areas with dense vegetation, providing unparalleled topographical and volumetric data.

The Synergy of Sensor Fusion and AI

The true power of these advanced sensors is unleashed when their data is combined and analyzed through sensor fusion techniques, powered by sophisticated AI automation and solar computer vision.

Imagine identifying a thermal hotspot (from a thermal camera). Now, cross-reference that exact location with EL data showing a micro-crack, hyperspectral data indicating material degradation, and LiDAR data confirming a slight structural sag. This multi-layered approach allows O&M teams to:

Uncover Root Causes: Go beyond the symptom to understand why a panel is underperforming.

Predict Failures More Accurately: Detect subtle indicators of degradation that, when combined, signal an impending failure.

Prioritize Repairs: Understand which anomalies are most critical based on comprehensive data, ensuring resources are allocated effectively.

Strengthen Warranty Claims: Present irrefutable, multi-faceted evidence of manufacturing or installation defects.

Optimize Asset Lifespan: Proactively address issues before they cause significant, irreversible damage.

Challenges and the Bright Future

Integrating advanced sensors brings challenges, including higher payload costs, increased data volume (necessitating robust data management solutions), and the complexity of processing multi-modal data. However, as the technology matures and costs decrease, the benefits of these deeper insights far outweigh the challenges.

The future of solar O&M is undeniably intelligent, data-rich, and drone-powered. By moving beyond traditional RGB and thermal inspections to embrace these next-generation sensor technologies, solar asset owners and O&M providers can unlock unprecedented levels of efficiency, reliability, and profitability, ensuring solar farms operate at their peak for decades to come.

[team-ombrulla]

How does AI Quality Control  Redefines Product Quality and Reliability in Fast-Paced Manufacturing ?

AI Quality Control leverages machine learning (ML), computer vision, and predictive analytics to detect defects, optimize processes, and ensure consistent product excellence even in the fastest production environments. This article explores how AI is transforming quality control and setting new benchmarks for product reliability.

The Limitations of Traditional Quality Control

Conventional QC methods face several challenges:

Human Error & Fatigue – Manual inspections are prone to inconsistencies due to human limitations.

Slow Processing Speeds – Traditional systems cannot match the real-time demands of high-speed production lines.

Reactive Rather Than Proactive – Defects are often detected too late, leading to costly recalls and waste.

AI-driven quality control overcomes these hurdles by introducing automation, real-time monitoring, and predictive capabilities.

How AI Enhances Quality Control in Manufacturing

1. Automated Defect Detection with Computer Vision

AI-powered computer vision systems with advanced AI defect detection capabilities use deep learning to analyze thousands of products per minute with superhuman accuracy. These systems can:

Detect microscopic defects invisible to the human eye.

Classify defects by type and severity for immediate corrective action.

Adapt to new product designs without extensive reprogramming.

Companies like Tesla and Foxconn use AI vision systems to inspect electronic components and automotive parts at unprecedented speeds.

2. Predictive Quality Analytics

AI doesn’t just detect defects—it predicts and prevents them. By analyzing historical production data, AI models can:

Identify patterns leading to defects (e.g., machine wear, temperature fluctuations).

Recommend adjustments before defects occur.

Reduce scrap rates and improve yield.

For example, semiconductor manufacturers use AI to predict wafer defects, saving millions in rejected batches.

3. Real-Time Process Optimization

AI continuously monitors production lines and adjusts parameters in real time to maintain optimal quality. This includes:

Automatically calibrating machinery for precision.

Detecting anomalies in sensor data (vibrations, pressure, etc.).

Reducing variability in output for consistent product quality.

The Impact of AI on Manufacturing Quality Standards

✔ Higher Accuracy & Fewer Defects

AI reduces human error, ensuring near-perfect defect detection rates (often >99% accuracy).

✔ Faster Inspections & Increased Throughput

Automated AI systems inspect products in milliseconds, keeping pace with high-speed production without bottlenecks.

✔ Cost Savings & Waste Reduction

Early defect detection minimizes rework, scrap, and recalls, leading to significant cost reductions.

✔ Improved Compliance & Traceability

AI maintains detailed logs of inspections, helping manufacturers comply with stringent industry regulations (e.g., ISO, FDA).

The Future of AI in Quality Control

As AI evolves, we can expect:

Generative AI for Synthetic Defect Training – Simulating rare defects to improve detection models.

Edge AI for On-Device Processing – Faster inspections without cloud dependency.

AI-Driven Supplier Quality Management – Automating QC across supply chains.

Conclusion

AI-powered quality control is revolutionizing manufacturing by setting new standards for speed, accuracy, and reliability. By automating inspections, predicting defects, and optimizing processes in real time, AI ensures that manufacturers can deliver flawless products at scale.

Manufacturers who embrace AI-driven QC today will lead the market tomorrow with higher quality, lower costs, and unmatched efficiency.

[gis2080]

🧠 AI + Semiconductors = Predicting the Future of Tech Like Never Before!

AI for Predictive Semiconductor Trends Market : The semiconductor industry is evolving rapidly, and Artificial Intelligence (AI) is playing a crucial role in forecasting market trends, optimizing chip design, and enhancing manufacturing efficiency. AI-driven predictive analytics helps semiconductor companies stay ahead by identifying emerging technology shifts, market demands, and supply chain disruptions before they occur.

To Request Sample Report :https://www.globalinsightservices.com/request-sample/?id=GIS32975 &utm_source=SnehaPatil&utm_medium=Linkedin

How AI is Transforming Semiconductor Trend Prediction

AI-powered systems leverage machine learning, deep learning, and big data analytics to analyze vast amounts of semiconductor industry data. Key AI applications include:

✔ Market Demand Forecasting — AI models predict global semiconductor demand based on economic indicators, consumer behavior, and technological advancements. ✔ Design Optimization — AI accelerates chip design simulations, reducing time-to-market for next-gen processors and SoCs. ✔ Predictive Supply Chain Analytics — AI-driven forecasting minimizes component shortages and disruptions in semiconductor manufacturing. ✔ Defect Detection & Yield Optimization — AI-based computer vision improves wafer inspection and enhances production yield.

Key Benefits of AI in Semiconductor Trend Prediction

📌 Early Trend Identification — AI detects upcoming shifts in semiconductor demand for AI chips, 5G, IoT, and automotive electronics. 📌 Data-Driven Decision Making — AI-driven insights enable chipmakers to adapt production strategies and R&D investments. 📌 Improved Manufacturing Efficiency — AI optimizes fab operations, reducing defects and energy consumption. 📌 Enhanced Supply Chain Resilience — AI models forecast raw material availability, geopolitical risks, and logistics delays.

AI-Powered Trends Shaping the Semiconductor Industry

🔹 AI-Driven Chip Design — AI is revolutionizing EDA (Electronic Design Automation) for faster and more efficient semiconductor design. 🔹 Edge AI & Neuromorphic Computing — AI predicts the rise of brain-inspired processors for real-time AI applications. 🔹 Quantum Computing Integration — AI anticipates breakthroughs in quantum semiconductors for next-gen computing. 🔹 Sustainability & Green Semiconductors — AI forecasts trends in low-power and eco-friendly chip manufacturing.

Future Trends in AI-Powered Semiconductor Insights

🔸 Generative AI for Chip Innovation — AI models will autonomously design and optimize semiconductor architectures. 🔸 AI for Silicon Photonics — Predicting the rise of optical computing for ultra-fast data processing. 🔸 AI-Powered Semiconductor Market Analytics — Advanced AI algorithms will refine demand prediction accuracy. 🔸 AI in 3D & Advanced Packaging — AI-driven insights will shape chiplet-based architectures and heterogeneous integration.

As AI continues to transform predictive semiconductor analytics, chipmakers gain a strategic edge in forecasting industry trends, boosting innovation, efficiency, and market competitiveness.

#artificialintelligence #semiconductors #ai #predictiveanalytics #machinelearning #chipdesign #bigdata #eda #supplychain #iot #aihardware #5g #neuromorphiccomputing #quantumcomputing #siliconphotonics #waferinspection #smartmanufacturing #futuretechnology #autonomoussystems #generativeai #fabautomation #deeptech #aiinsupplychain #nextgensemiconductors #predictivemaintenance #datacenters #hardwareacceleration #sustainability #lowpowerchips

[icorekorea]

Auto Focus Module based on Optical Triangulation Principle| iCore

World-class machine vision researchers at iCORE have expertise in the areas of analogue circuit design, precision instrument optics, lightning design, and machine vision. By integrating technologies related to electrical, electronic, optical, precision control, FPGA, firmware, and software, they offer creative machine vision solutions. High-power LED strobe lighting is made possible by the LED light strobe controller that iCore provides. It generates and regulates the current pulses. Optical triangulation is the basis for iCore's real-time auto focus module.

FPGA-based real-time auto focus model using the principle of optical triangulation:

This is utilized in the automatic optical inspection (AOI) of a high magnification optical system that tracks the movement of the target item in real time and adjusts the optical picture to immediately discover flaws of 1 μm or less in semiconductor and display testing.

Auto focus function to focus automatically on optical triangulation:

Because of the short depth of field (DOF) with high magnification optical systems, altering the height of the object may cause it to go out of focus. The distance between the optical system and the target object is measured and maintained constant in real time by iCore.

Features of optical triangulation iFocus:

Optical triangulation is used by the iFocus auto focus module, where the AF camera records the displacement of the laser beam reflected off the target object. The AF camera's non-contact distance measuring sensor ensures homogeneous image quality throughout the image region in addition to high-speed and high-precision measurement. It also performs real-time motor control and computes changes in pixel lengths surrounding the focus spot. iFocus's module contains an FPGA, which allows it to quickly control the AF camera.

Applications:

FCPB Inspection

Review Inspection

Glass Inspection

Semiconductor wafer inspection

OLED, Micro LED inspection

If you are looking for optical triangulation in Korea, you can find it on iCORE

Click here to contact iCORE

View more: Auto Focus Module based on Optical Triangulation Principle

[andapt-pmic]

AI Integrated Electronics for Competitive Advantage

AI applications store and process massive amounts of data. This impacts both, design and production, of semiconductors. The architecture of semiconductors needs changes inorder to meet the demands of AI integrated circuits. Improvements are required to address the performance of the semiconductors in terms of high speed of data movement in and out of the memory and efficient memory systems.

One way to meet these requirements is to use neural networks in the design of chips. These work like synapses in human brain sending data only when needed. The demand of AI algorithms can be met by using System on Chip (SoC) processors that combine processor logic with a non-volatile memory. Constant need for improvements poses many challenges for the manufacturers. In this article we will look at how they can have a competitive advantage.

Integrated Circuits: The Growing Challenge

High capital requirements make the semi-conductor market highly competitive. Manufacturers constantly work at shortening product life cycles and bringing innovative products to the market quickly to stay on top. With new technology node, there is the expense of research and design investments and then the costs of production equipment.  McKinsey indicates that research and design costs for the development of a chip increased from about $28 million at the 65 nanometer (nm) node to about $540 million at the leading-edge 5 nm node and fab construction costs for the same nodes increased from $400 million to $5.4 billion. AI/ ML is turning into a necessary tool as companies race reduce the time to market for products while trying to increase research productivity, design chips and also manufacture them. As is obvious the edge created by using AI/ML tools cannot be ignored.

Deployment of AI Chips: Two Use Cases

As manufacturers move towards adopting AI to meet the challenges they face, manufacturing, and research and design may be two areas that might benefit the most. We will look at the use cases in these two areas below:

1.     AI in Manufacturing

Manufacturing is the semiconductor industry’s largest cost driver and AI/ML use cases will deliver most value here.They can reduce costs, improve yields, or increase a fab’s throughput. We will look at two examples of use cases in semiconductor manufacturing that uses AI/ML.

The first is adjusting tool parameters for increased output. Companies typically define one specific time frame for each step in a manufacturing process. But individual wafers may demonstrate variations in the time frame required. Because of this, a process may go on after the desired outcome have been met, damaging the chip or increasing timelines. Machine learning models can capture this non-linear relationship that might exist between process time and process outcomes. The data collected can then be used to implement differentiated process time increasing throughput.

Another example is the use of wafer inspection systems. Cameras, microscopes and electron microscopes help in detecting flaws in the front-end and back-end production processes. This early detection process to identify any potential defects is done by scanning images manually leaving room for errors and backlogs. Systems can be trained using deep learning to detect defects and classify them automatically and accurately. Training of computer vision algorithms is automated and all these factors together allow for quicker piloting, scalability and real-time detection. Potential process or tool deviations can be identified, which support early detection of any defects and help in higher yields and lowering costs.

2. AI in Research and design

Research and design is another area in which AI can have a powerful impact. AI/ML can be used to improve efficiency in research and design of the chips.

The process of physical layout design for a chip can be time consuming. By using AI tools  any defects and errors can be eliminated. AI tools can also be trained to optimize the process steps involved or eliminate them as required. Potentially all the processes for all chip designs can be accelerated using AI/ML.

If there are any slips or errors during the design phase of Integrated Circuit, then correcting them can be challenging. They may need multiple iterations based on feedback received from manufacturing. This can be avoided by using ML algorithms to predict potential failure in any new design and also to propose layouts that are optimized to improve yield.

 Integrated Electronics Soon to Deliver Brain-Like Functionality

Researchers have developed an artificial intelligence technology that mimics the way the human brain processes any visual information. The software needed for the artificial intelligence and the hardware required to capture images are combined together. The nanodevice is light driven and can be further developed to be used in drones, robotics, wearables and possibly artificial retinas. Different functions such as imaging and memory storage can be achieved by focussing light of different colours on the chip. These devices using light-based technology are considered to be faster and more energy efficient than currently used technologies.

To summarize

AI is likely to be the next catalyst that will lead to tremendous growth in the semiconductor industry The need for instant computing, connectivity and sensing is expected to drive the demand for AI integrated semiconductors.

[georgecmatthews]

Robots can take over when work is too dangerous, dirty, dull or dear

Like many other trends, the shift to automation, and the use of robotics, has accelerated during the global pandemic. Even though unemployment has risen dramatically, particularly in the US, the move to automation is continuing because of the value it brings. Robots can complement work done by humans or perform tasks humans would prefer not to because the work falls into one of the four D’s – dangerous, dirty, dull, or dear (as in expensive.)

At home and at work

Who will be our future companions at work and at home?  Hunter-Gatherers accepted grey wolves into their tribes 15,000 years ago, and this domestication process has led to the pets we know as dogs today.  These wolves were additive to the tribe, as their superior sense of smell increased the productivity of hunting, with the added benefit of being able to detect strangers in the vicinity. But can you imagine the committee meetings about this idea?  We’re going to bring vicious predators into our tribes that we have to feed with part of our hunting haul, all good?  The productivity and security benefits outweighed these concerns, and clearly this partnership between human and wolf has proven to be successful.

Like welcoming a wolf into your tribe, many people may have some trepidations about bringing a robot into their home. As time goes on, however, people are starting to see the benefits of getting some mechanical help at home. iRobot’s Roomba, the vacuum-cleaning robot, was the first such machine than many people welcomed under their roof. Since its release in 2002, iRobot has steadily improved the quality and navigational capabilities of each successive generation of Roomba and have built a nice market share in the vacuum industry. Vacuuming is certainly a dull, repetitive task, and people clearly value having a robot keep their floors clean.

While the company experienced some challenges because its manufacturing plants had been shut down during the early days of the crisis, demand for the Roomba increased because people are at home more, creating more dirt in the house. iRobot also now has a product that does mopping – the Braava. They have also developed Terra, a lawnmowing robot, though that launch was delayed because of the disruption of the current pandemic.

The pandemic has increased the number of jobs that are seen as dangerous. There have been reports of large outbreaks of the virus in meat processing plants, for instance. Tyson Foods has been testing robots in some of their plants and have highlighted advancements in robustness and robotic vision as reasons that robots may be able to help in their meat plants.  Meat processing requires a lot of washing and disinfecting steps, which older robots could not withstand.    

Two of the companies in the Invesco Oppenheimer Global Opportunities Fund have contributed to advances in computer vision, Basler and Cognex.�� Basler makes small, robust, and high precision cameras that can be integrated into robots as well as placed around factories for security and monitoring uses. Cognex has advanced software that analyzes the information acquired by cameras. This allows fast inspection of parts that are being manufactured, and allows robots to deal with non-standardized shapes, such as animal carcasses.  

The automotive industry has led the way in automating production, as for certain tasks where the robots see identical parts and require identical motions every time, older generations of robots could function quite well. But these older robots may not do so well with more complicated tasks, such as sorting through a box of nuts and bolts and being able to grasp a bolt no matter the orientation in the box. Yaskawa Electric makes robots with the finer motor skills needed for this task. Yaskawa robots have a delicate enough touch to grasp strawberries and place them on top of cakes.

The increased precision of robots and factory automation has led to more industries adopting them.  The semiconductor industry has taken to using more robots in their inline processing of chips. Moving silicon wafers requires extreme precision, with as little vibration as possible.  Any defect in the production steps can ruin a wafer full of semiconductor chips, each possibly costing tens of thousands of dollars. THK is the leader in linear motion guides, tools that can enable robotic arms or machines parts to move in swinging arcs or straight lines and stop exactly when needed to perform delicate, precise tasks.

Nidec is the leader in small motors, historically used in hard disk drives and home appliances. Today, they are finding more uses for these in robots and factory automation. These motors need to produce smooth motion without jerks.  Nidec has also started production of reduction gears, which function as robot joints, and are essential for smooth movement and precision stopping action with no spring-back motion.

Core to our investment philosophy is to seek out big changes going on in the world, and then invest in the industries and individual companies that can benefit the most from these changes. The increasing prevalence of automation and robotics has been a consistent feature of the global economy since the industrial revolution, and the very first attempts at mechanizing laundry in the late 1700’s.  We see this structural trend being accelerated in the age of COVID-19, as robots can navigate through the world untroubled by fears of a pandemic.  In addition, facilitating the rise of automation has been recent advancements in the area of cognitive assistance, but that is a topic for another day. Stay tuned for more!

About this series

People have a remarkable capacity for adapting to change, but COVID-19 changed everything at once: How we live and work. How we shop and play. In this series, Invesco experts explore what the world may look like over the next few years. Join us as we imagine the possibilities together.

As of 6/30/20, Invesco Oppenheimer Global Opportunities Fund (Class A shares) had the following percent of assets invested in: iRobot: 1.08% Tyson Foods: 0.00% Basler: 0.57% Cognex: 1.02% Yaskawa Electric: 0.99% THK: 0.70% Nidec: 0.57% Holdings are subject to change and are not buy/sell recommendations.

About Risk

An issuer may be unable to meet interest and/or principal payments, thereby causing its instruments to decrease in value and lowering the issuer’s credit rating.

In general, stock values fluctuate, sometimes widely, in response to activities specific to the company as well as general market, economic and political conditions.

The risks of investing in securities of foreign issuers can include fluctuations in foreign currencies, political and economic instability, and foreign taxation issues.

Junk bonds involve a greater risk of default or price changes due to changes in the issuer’s credit quality. The values of junk bonds fluctuate more than those of high quality bonds and can decline significantly over short time periods.

Interest rate risk refers to the risk that bond prices generally fall as interest rates rise and vice versa.

Stocks of small and medium-sized companies tend to be more vulnerable to adverse developments, may be more volatile, and may be illiquid or restricted as to resale.

The fund is subject to certain other risks. Please see the prospectus for more information regarding the risks associated with an investment in the fund.

Important Information

Blog Header Information: AlexLMX / Getty

The mention of specific companies, industries or sectors does not constitute a recommendation and is not intended as investment advice or to predict or depict performance of any investment.

Before investing, investors should carefully read the prospectus and/or summary prospectus and carefully consider the investment objectives, risks, charges and expenses. For this and more complete information about the fund(s), investors should ask their investment professional for a prospectus/summary prospectus or visit invesco.com/fundprospectus.

The opinions referenced above are those of the authors as of August 19, 2020. These comments should not be construed as recommendations, but as an illustration of broader themes. Forward-looking statements are not guarantees of future results. They involve risks, uncertainties and assumptions; there can be no assurance that actual results will not differ materially from expectations.

This does not constitute a recommendation of any investment strategy or product for a particular investor. Investors should consult a financial advisor/financial consultant before making any investment decisions. Invesco does not provide tax advice. The tax information contained herein is general and is not exhaustive by nature. Federal and state tax laws are complex and constantly changing. Investors should always consult their own legal or tax professional for information concerning their individual situation. The opinions expressed are those of the authors, are based on current market conditions and are subject to change without notice. These opinions may differ from those of other Invesco investment professionals.

from Expert Investment Views: Invesco Blog https://www.blog.invesco.us.com/robots-can-take-over-when-work-is-too-dangerous-dirty-dull-or-dear/?utm_source=rss&utm_medium=rss&utm_campaign=robots-can-take-over-when-work-is-too-dangerous-dirty-dull-or-dear

[expomahal-blog]

Marine Fuels 360 China 2019 at China(Beijing) 2019-June

rigid pcbs companies, multi-layered pcbs companies list, semiconductor packaging pcbs business opportunities, pcb materials B2B Opportunities, shield board B2C opportunities, insulating material B2B ideas, ic packaging ? assembly equipment (bonders contact info, molding machines contact info, resin coating machines) events, analysis/simulation software companies contacts, and packages (csp Trade Shows, bga Exhibitors, mcm Shows, wafer level csp) contact links, electronic components ? condenser/capacitor Expos, inductor/coil network, magnetic contactors/circuit breakers companies contacts, esd protection components thermal design components B2B ideas, electronics manufacturing services/contract manufacturing services ? electronics manufacturing /production services Exhibitors, consulting services Trade Shows, soldering - soldering machines companies, fluxers network, soldering materials / flux Exhibitors, material handling equipment and system for smt ? loaders Trade Shows, unloaders events, conveyers B2C opportunities, automatic guided vehicles contacts list, racks contacts list, mobile racks contact info, trays Events, cabinets Shows, clean/esd protection - clean room system & supplies Meetings, clean booths Events, air showers companies, accessories (filtration unit Exhibitors, solvent recovery unit contacts list, drainage treatment apparatus contact list, etc.) B2B Opportunities, inspection ? board vision inspection equipment contact info, in-circuit testers B2C ideas, inspection jig/ test fixtures/probes/testing stages business, 2d/3d inspection. B2C ideas, home appliances Exhibitors, audio companies contacts, visual equipment Fairs, aircraft contact list, vessel equipment directory, mobile communication systems equipment Fairs, industrial control Meetings, factory automation B2B ideas, medical device Business events, personal computer peripheral B2B Opportunities, office equipment B2C ideas, test Business events, inspection equipment companies contacts, optical instrument Events, semiconductor assembly Exhibitors, transportation equipment. Shows 2019, June, Morocco, Casablanca

Morocco Beauty Expo 2019 at Morocco(Casablanca) 2019-June

Morocco Beauty Expo 2019 trade show event mainly focuses on:

rigid pcbs companies contacts, multi-layered pcbs Shows, semiconductor packaging pcbs Events, pcb materials contact info, shield board network, insulating material contact list, ic packaging ? assembly equipment (bonders Exhibitors Directory, molding machines companies list, resin coating machines) business ideas, analysis/simulation software B2B Opportunities, and packages (csp business ideas, bga events, mcm Events, wafer level csp) events, electronic components ? condenser/capacitor events, inductor/coil network, magnetic contactors/circuit breakers events, esd protection components thermal design components directory, electronics manufacturing services/contract manufacturing services ? electronics manufacturing /production services Exhibitions, consulting services contact list, soldering - soldering machines business, fluxers Shows, soldering materials / flux companies contacts, material handling equipment and system for smt ? loaders Meetings, unloaders Fairs, conveyers B2C opportunities, automatic guided vehicles B2B ideas, racks contacts list, mobile racks Exhibitions, trays business, cabinets Events, clean/esd protection - clean room system & supplies Fairs, clean booths directory, air showers business opportunities, accessories (filtration unit B2C opportunities, solvent recovery unit business contacts, drainage treatment apparatus business ideas, etc.) contact links, inspection ? board vision inspection equipment directory, in-circuit testers Shows, inspection jig/ test fixtures/probes/testing stages B2B ideas, 2d/3d inspection. Trade Fairs, home appliances Business events, audio contact info, visual equipment Events, aircraft companies contacts, vessel equipment Trade Fairs, mobile communication systems equipment companies list, industrial control contact list, factory automation business ideas, medical device contact info, personal computer peripheral Trade Fairs, office equipment B2B Opportunities, test business opportunities, inspection equipment companies list, optical instrument Trade Shows, semiconductor assembly contact info, transportation equipment. contact list

related products/services/industry/business. This trade show opens top business opportunities to exhibit products and services from rigid pcbs business contacts, multi-layered pcbs B2B ideas, semiconductor packaging pcbs contact links, pcb materials directory, shield board contact info, insulating material B2B Opportunities, ic packaging ? assembly equipment (bonders companies contacts, molding machines info, resin coating machines) info, analysis/simulation software companies contacts, and packages (csp B2B ideas, bga contact links, mcm Events, wafer level csp) directory, electronic components ? condenser/capacitor Meetings, inductor/coil Trade Shows, magnetic contactors/circuit breakers network, esd protection components thermal design components directory, electronics manufacturing services/contract manufacturing services ? electronics manufacturing /production services Expos, consulting services B2C ideas, soldering - soldering machines B2C opportunities, fluxers business ideas, soldering materials / flux Exhibitions, material handling equipment and system for smt ? loaders companies contacts, unloaders Exhibitors Directory, conveyers B2C opportunities, automatic guided vehicles Exhibitors Directory, racks companies contacts, mobile racks network, trays companies, cabinets Expos, clean/esd protection - clean room system & supplies business ideas, clean booths business opportunities, air showers business contacts, accessories (filtration unit contacts list, solvent recovery unit business ideas, drainage treatment apparatus network, etc.) business opportunities, inspection ? board vision inspection equipment business opportunities, in-circuit testers Business events, inspection jig/ test fixtures/probes/testing stages business opportunities, 2d/3d inspection. Trade Fairs, home appliances contacts list, audio Exhibitors, visual equipment B2C ideas, aircraft Exhibitors Directory, vessel equipment contact links, mobile communication systems equipment contact list, industrial control companies contacts, factory automation Exhibitions, medical device contact list, personal computer peripheral directory, office equipment contacts list, test B2C ideas, inspection equipment contact links, optical instrument B2B ideas, semiconductor assembly info, transportation equipment. contact info industry.

Find More Details about Morocco Beauty Expo 2019 event...

We help you to grow your business by providing the required contact details of all companies participating in this event and you can download the same data in excel format using the above links. Location of the Event:Morocco(Casablanca) Year-Month:2019-June Official Website:Event Website source https://www.expomahal.com/2019/08/marine-fuels-360-china-2019-at.html

[gis2080]

🤖 Future Unlocked: How Robots Are Revolutionizing Semiconductor Sorting!

Robotic Semiconductor Sorting Systems Market : In the fast-paced semiconductor industry, robotic semiconductor sorting systems are transforming the efficiency, precision, and scalability of wafer and chip processing. These cutting-edge systems leverage AI-driven automation, machine vision, and high-speed robotic arms to ensure defect-free semiconductor manufacturing.

To Request Sample Report : https://www.globalinsightservices.com/request-sample/?id=GIS32684 &utm_source=SnehaPatil&utm_medium=Linkedin

How Robotic Sorting Works

Robotic semiconductor sorters integrate machine vision cameras, deep learning algorithms, and precision robotic actuators to categorize wafers, dies, and chips based on quality, size, and electrical characteristics. The system consists of: ✔ Automated Pick-and-Place Robots — High-speed robotic arms with micro-level accuracy move chips efficiently. ✔ AI-Powered Inspection — Deep learning-based vision systems detect defects and classify components in real time. ✔ High-Throughput Handling — Advanced sorting algorithms optimize wafer handling, minimizing downtime. ✔ Real-Time Data Analytics — IoT-enabled robots provide live performance insights, improving yield and quality control.

Key Benefits of Robotic Sorting Systems

📌 Precision & Accuracy — Sub-micron level accuracy ensures reliable sorting of chips for high-performance applications. 📌 Speed & Throughput — AI algorithms combined with robotic systems enhance processing speeds beyond human capabilities. 📌 Cost Reduction — Automation lowers labor costs and reduces waste by improving defect detection. 📌 Scalability — Easily adapts to different chip sizes and packaging types for future semiconductor demands.

Future Trends in Semiconductor Sorting Robotics

🔹 AI-Driven Predictive Maintenance — Machine learning models predict failures before they happen. 🔹 5G & Edge Computing Integration — Faster data processing for real-time sorting optimization. 🔹 Collaborative Robotics (Cobots) — Safer human-robot interaction for hybrid automation. 🔹 Quantum Chip Sorting — Next-gen robotic sorters designed for ultra-precise quantum computing components.

With semiconductor manufacturing pushing toward sub-5nm nodes and AI-driven fabs, robotic sorting systems are crucial for achieving the next level of automation. The future is autonomous, data-driven, and highly efficient!

#robotics #semiconductors #automation #ai #machinelearning #visioninspection #pickandplace #chipmanufacturing #waferhandling #industry40 #smartmanufacturing #autonomousrobots #deeplearning #roboticautomation #microelectronics #highprecision #iot #predictivemaintenance #cobots #5g #nanotechnology #edgecomputing #intelligentautomation #yieldoptimization #defectdetection #chipquality #electronicsmanufacturing #waferfabrication #cleanroomtechnology #advancedmanufacturing #integratedcircuits #artificialintelligence #siliconchips #manufacturingautomation #quantumcomputing

[icorekorea]

Auto Focus Module based on Optical Triangulation Principle| iCore

iCORE has world class researchers in the field of machine vision with analog circuit design technology, precision instruments optics and lightning design technology, provides innovative machine vision solutions by internalizing electrical, electronic, optical, precision control, FPGA, firmware and software technologies. The LED light strobe controller provided by iCore generates and controls the current pulses, enabling stable and precise strobe lighting of high-power LEDs. A real-time auto focus module of iCore uses the principle of optical triangulation.

FPGA-based real-time auto focus model using the principle of optical triangulation: This is used in the automatic optical inspection (AOI) of a high magnification optical system that instantly detects faults of 1 μm or less in semiconductor and display testing by tracking the movement of the target object in real time and adjusting the optical picture.

Auto focus function to focus automatically on optical triangulation: In high magnification optical systems, the depth of field (DOF) is quite shallow, hence adjusting the object's height could result in out-of-focus. iCore offers a real-time solution that measures and keeps the distance between the optical system and the target item constant.

Features of optical triangulation iFocus: The iFocus auto focus module uses optical triangulation, where the displacement of the laser beam reflected off the target object is captured by the AF camera. The AF camera does real-time motor control and computes the changes in pixel lengths around the focus spot.Its non-contact distance measuring sensor guarantees homogeneous image quality throughout the image region in addition to high-speed and high-precision measurement. With an FPGA integrated into its module, iFocus can swiftly control the AF camera.

Applications:  Semiconductor wafer inspection  OLED, Micro LED inspection  FCPB Inspection  Review Inspection  Glass Inspection

If you are looking for optical triangulation in Korea, you can find it on iCORE

Click here to contact iCORE

View more: Auto Focus Module based on Optical Triangulation Principle