📷 Making automated visual-inspection systems practical
Using supervised learning to train anomaly localization models has major drawbacks compared to images of defect-free products, images of defective products are scarce; and labeling defective-product images is expensive. Consequently, our benchmarking framework doesn’t require any anomalous images in the training phase. Instead, from the defect-free examples, the model learns a distribution of typical image features.
We have released our benchmark in the hope that other researchers will expand on it, to help bridge the gap between the impressive progress on anomaly localization in research and the challenges of real-world implementation.
Pipe inspection using guided acoustic wave sensors integrated with mobile robots
In this paper we propose an approach to inspect pipelines that can be applied for multiple robots or a single robot with integrated acoustical sensors with high resolution detection and good localization accuracy. The approach is demonstrated by the successful inspection of multiple defects on a steel pipe using manually manipulated guided acoustic wave sensors. The approach was divided into two stages: defect detection and localization. In the detection stage the receiver operating characteristic defines a detection amplitude threshold and a detection zone of a single sensor in which a reference defect (for example, randomly chosen 8.5 mm diameter through thickness circular hole) could be present and requested to screen. The size of this zone decides the sensor sampling pitch distance to ensure 100% detection coverage of an entire pipe. This leads to the successful detection of the reference and other defects. In the localization stage, for each sensor location showing defect detection, five further measurements were made to locate the defect within the detection zone and this led to measured defect location errors less than 30 mm for the reference defect that agrees well with predictions from Monte Carlo simulations. The density-based algorithm for discovering clusters was successfully used to identify and combine multiple measurements on the reference defect.
Eliminating Defects with AR Technology
L3Harris Technologies implemented LightGuide AR software to ensure standardization across a variety of complex processes. Following the implementation of LightGuide on a line with 17 variants of one product, visually guided workflows helped consolidate parts, which eliminated changeover per variant and resulted in zero assembly-related defects. Since these results, L3Harris has implemented LightGuide on complex manual lines at multiple locations.
According to one Engineering Manager at the L3Harris, the system uses infrared and 3D sensing to know where an operator’s hand is within an inch in any direction. The cues highlighting what pieces go where allow operators to focus on the task at hand, not where they are in the process; further, the system will notify the operator via visual cues and messaging and stop instruction if they skip a step or reach for the wrong component.
Automating 3D Printing with AI Vision: PrintPal’s PrintWatch System
PrintPal is a startup company launched in 2021 that has been developing a machine learning-based vision system for 3D printer monitoring. The PrintWatch concept is that a camera feed of the print surface is relayed to an AI analysis system that can classify artifacts at 93% accuracy within each image in only 5ms. Defects are automatically detected and allow the operator to stop failing jobs before they waste additional material or worse, damage the equipment PrintWatch runs 24/7, removing any need for a human operator to monitor print progress, and can do so better than humans who often stray elsewhere to work on other things.
AI Keeps Assembly Conveyor Rolling
The overhead conveyor is the backbone of the plant. It handles almost 1,250 cars per day during a three-shift operation. There is no back-up equipment, so failure is not an option. The conveyor’s parts are exposed to relatively high forces, causing them to wear in a relatively short time. Given that the conveyor is several meters above the floor, it is difficult to access for inspection.
ŠKODA engineers developed the Magic Eye to continuously monitor the condition of the conveyor’s moving parts without the need for maintenance personnel to climb ladders and physically do the job.
Six cameras are mounted on the conveyor frame at strategic locations to monitor the condition of various conveyor elements. Rapid assessment of each trolley’s condition is carried out as the conveyor is running. Images collected by the camera are transmitted via WiFi to a central database, where they are analyzed by artificial intelligence algorithms. The software detects wear by comparing each new image of the trolley with previously collected images. If an anomaly is detected, the software sends an alert to maintenance personnel, who can fix the trolley before it can create unexpected downtime.
AI In-situ Monitoring Detects Fusion Flaws in L-PBF Metal 3D Printing
In-situ process monitoring is the key for validating the quality of AM-made parts and minimizing the need for post quality control. In this collaborative research, in-situ datasets collected from a co-axial photodiode installed in an EOS M 290 were subject to a set of correction factors to remove chromatic and monochromatic distortions from the signal. The corrected datasets were then analyzed using statistical and machine learning algorithms. These algorithms were systematically tuned and customized to detect lack of fusion flaws.
Plastic Bottles Defect Inspection Using Omron FH Vision System with AI
Smart Devices, Smart Manufacturing: Pegatron Taps AI, Digital Twins
Today, Pegatron uses Cambrian, an AI platform it built for automated inspection, deployed in most of its factories. It maintains hundreds of AI models, trained and running in production on NVIDIA GPUs. Pegatron’s system uses NVIDIA A100 Tensor Core GPUs to deploy AI models up to 50x faster than when it trained them on workstations, cutting weeks of work down to a few hours. Pegatron uses NVIDIA Triton Inference Server, open-source software that helps deploy, run and scale AI models across all types of processors, and frameworks.
Taking another step in smarter manufacturing, Pegatron is piloting NVIDIA Omniverse, a platform for developing digital twins “In my opinion, the greatest impact will come from building a full virtual factory so we can try out things like new ways to route products through the plant,” he said. “When you just build it out without a simulation first, your mistakes are very costly.”
Industrial CT Scanning: Automated Defect Detection for Turbine Blades | Synopsys
Visual Anomaly Detection: Opportunities and Challenges
Clarifai is pleased to announce pre-GA product offering of PatchCore-based visual anomaly detection model, as part of our visual inspection solution package for manufacturing which also consists of various purpose-built visual detection and segmentation models, custom workflows and reference application templates.
Users only need a few hundred images of normal examples for training, and ~10 anomalous examples for each category for calibration & testing only, especially with more homogeneous background and more focused region-of-interest.
Smart Manufacturing at Audi
Some 5,300 spot welds are required to join the parts that make up the body of an Audi A6. Until recently, production staff used ultrasound to manually monitor the quality of spot welds based on random sampling. Now, however, engineers are testing a smarter way of determining weld quality. They are using AI software to detect quality anomalies automatically in real time. The robots collect data on current flow and voltage on every weld. An AI algorithm continuously checks that those values fall within predetermined standards. Engineers monitor the weld data on a dashboard. If a fault is detected, they can then perform manual checks.
Startup’s Vision AI Software Trains Itself — in One Hour — to Detect Manufacturing Defects in Real Time
NVIDIA Metropolis member Covision creates GPU-accelerated software that reduces false-negative rates for defect detection in manufacturing by up to 90% compared with traditional methods. In addition to identifying defective pieces at production lines, Covision software offers a management panel that displays AI-based data analyses of improvements in a production site’s quality of outputs over time — and more.
“It can show, for example, which site out of a company’s many across the world is producing the best metal pieces with the highest production-line uptime, or which production line within a factory needs attention at a given moment,” Tschimben said.
Why AI software companies are betting on small data to spot manufacturing defects
The deep-learning algorithms that have come to dominate many of the technologies consumers and businesspeople interact with today are trained and improved by ingesting huge quantities of data. But because product defects show up so rarely, most manufacturers don’t have millions, thousands or even hundreds of examples of a particular type of flaw they need to watch out for. In some cases, they might only have 20 or 30 photos of a windshield chip or small pipe fracture, for example.
Because labeling inconsistencies can trip up deep-learning models, Landing AI aims to alleviate the confusion. The company’s software has features that help isolate inconsistencies and assist teams of inspectors in coming to agreement on taxonomy. “The inconsistencies in labels are pervasive,” said Ng. “A lot of these problems are fundamentally ambiguous.”
Mariner Speeds Up Manufacturing Workflows With AI-Based Visual Inspection
Traditional machine vision systems installed in factories have difficulty discerning between true defects — like a stain in fabric or a chip in glass — and false positives, like lint or a water droplet that can be easily wiped away.
Spyglass Visual Inspection, or SVI, helps manufacturers detect the defects they couldn’t see before. SVI uses AI software and NVIDIA hardware connected to camera systems that provide real-time inspection of pieces on production lines, identify potential issues and determine whether they are true material defects — in just a millisecond.
In situ infrared temperature sensing for real-time defect detection in additive manufacturing
Melt pool temperature is a critical parameter for the majority of additive manufacturing processes. Monitoring of the melt pool temperature can facilitate the real-time detection of various printing defects such as voids, over-extrusion, filament breakage, clogged nozzle, etc. that occur either naturally or as the result of malicious hacking activity. This study uses an in situ, multi-sensor approach for monitoring melt pool temperature in which non-contact infrared temperature sensors with customized field of view move along with the extruder of a fused deposition modeling-based printer and sense melt pool temperature from a very short working distance regardless of its X-Y translational movements. A statistical method for defect detection is developed and utilized to identify temperature deviations caused by intentionally implemented defects.
Fabs Drive Deeper Into Machine Learning
For the past couple decades, semiconductor manufacturers have relied on computer vision, which is one of the earliest applications of machine learning in semiconductor manufacturing. Referred to as Automated Optical Inspection (AOI), these systems use signal processing algorithms to identify macro and micro physical deformations.
Defect detection provides a feedback loop for fab processing steps. Wafer test results produce bin maps (good or bad die), which also can be analyzed as images. Their data granularity is significantly larger than the pixelated data from an optical inspection tool. Yet test results from wafer maps can match the splatters generated during lithography and scratches produced from handling that AOI systems can miss. Thus, wafer test maps give useful feedback to the fab.
AI tool locates and classifies defects in wind turbine blades
Using image enhancement, augmentation methods and the Mask R-CNN deep learning algorithm, the system analyses images, highlights defect areas and labels them.
After developing the system, the researchers tested it by inputting 223 new images. The proposed tool is said to have achieved around 85 per cent test accuracy for the task of recognising and classifying wind turbine blade defects.
Automated Defect Detection (complete pipeline and demo)
Quality Check (QC) is an integral part of each manufacturing process. Every serious manufacturing team performs multiple quality checks both during and at the end of the production process. The good news is that, recent advances in Artificial Intelligence (AI) made a lot of visual inspection tasks possible to automate. Now, AI models can even surpass human performance in some visual inspection problems.