- Community Home
- >
- Solutions
- >
- Tech Insights
- >
- Enhance production quality with AI-powered video a...
Categories
Company
Local Language
Forums
Discussions
Forums
- Data Protection and Retention
- Entry Storage Systems
- Legacy
- Midrange and Enterprise Storage
- Storage Networking
- HPE Nimble Storage
Discussions
Discussions
Discussions
Forums
Discussions
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
- BladeSystem Infrastructure and Application Solutions
- Appliance Servers
- Alpha Servers
- BackOffice Products
- Internet Products
- HPE 9000 and HPE e3000 Servers
- Networking
- Netservers
- Secure OS Software for Linux
- Server Management (Insight Manager 7)
- Windows Server 2003
- Operating System - Tru64 Unix
- ProLiant Deployment and Provisioning
- Linux-Based Community / Regional
- Microsoft System Center Integration
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Discussion Boards
Community
Resources
Forums
Blogs
- Subscribe to RSS Feed
- Mark as New
- Mark as Read
- Bookmark
- Receive email notifications
- Printer Friendly Page
- Report Inappropriate Content
Enhance production quality with AI-powered video analytics
For today’s manufacturers, success relies on the quality of their products. An AI platform for manufacturing quality assurance from HPE, NVIDIA and trusted partners enables manufacturers to transform their quality management with faster, more accurate inspection processes. HPE's Carolyn Cairns and NVIDIA's Piyush Modi explain how.
The need for smarter, faster insights is skyrocketing as manufacturers respond to demands for new and diverse products that deliver exceptional quality. Rising customer expectations and regulatory mandates are putting pressure on you to increase accuracy and efficiency at each stage of production. Without doing so, you risk losing profits and ceding to the competition.
As products become smarter and more connected (think about the number of sensors in today’s automobiles, jet engines or electronic devices), manual inspection processes can be time-consuming, costly and error-prone. But with the rise of AI-enabled object detection technology and video analytics, manufacturers such as Seagate can now automate taking inefficiency out of production processes, bring in high-speed consistency, and produce high-quality products. With these capabilities, companies can get closer to achieving zero defects.
In addition to driving quality improvements, AI-based video analytics provides manufacturers with increased visibility and control across assembly lines and factories in multiple locations. Companies that invest in computer vision can transform your operating environments in key ways:
- Fueling the efficiency of production with automation
- Replacing long visual inspection processes with AI insight
- Driving the accuracy of quality assessment throughout production
- Rapidly detecting and resolving issues with complex products
- Eliminating unnecessary rework
The cost of quality in manufacturing is projected at 15-to-20% of annual sales revenue, sometimes reaching as high as 40% of total operations. Poor production quality can be a billion-dollar problem. The exorbitant costs stem from issues on and off the assembly line – ranging from waste, scrap, defects, rework, and failure analysis to repairs and servicing, warranty claims, customer complaints and returns.
Manufacturers are looking for a new breed of intelligent solutions that can improve overall quality assurance. AI-based video analytics enables manufacturers to analyze video and image data at the edge, as the products make their way down the line, which lets employees instantly make changes and solve problems before the issues impact an entire production run. Consider leather seats in a luxury automobile. If the leather is scratched or the stitching is off, and such issues are not detected until well along the assembly line, the leather must be scrapped, and the impacted vehicles diverted for rework. Hi-tech manufacturer Foxconn deployed an AI-based solution that integrates customer enterprise resource planning data, manufacturing execution systems data and real-time video analytics data to automate the end-of-line inspection process. The results speak for themselves. Algorithms and model training time were reduced from weeks to days. The solution saves 96 seconds of inspection time per server. Most importantly, the number of defective products reaching customers was reduced by 25%.
Enhancing product quality with breakthrough AI
HPE and NVIDIA are launching a new generation of quality assurance solutions powered by AI. We offer end-to-end solutions that are engineered for deep insight, including the latest breakthroughs in accelerated computing and computer vision technology. These innovations help manufacturers monitor and manage the entire production cycle with extreme precision.
To further enhance production quality, HPE and NVIDIA are delivering a scalable AI platform for quality assurance. The platform is designed to support AI video and image analytics across disparate operating environments, enabling manufacturers to overcome the challenges of production and move toward the future of zero defects. These technologies provide significant advantages at any scale:
- Increase product yield while reducing scrap
- Enable consistent quality under varying conditions
- Optimize costs and minimize downstream waste with fewer false negatives
- Improve test sensitivity to avoid manual reinspection
We built the AI platform on HPE systems that are NVIDIA-Certified, enabling GPU-accelerated applications for automating quality assurance procedures. Manufacturers can choose from a robust selection of HPE systems that are engineered for AI and powered by NVIDIA GPUs to unleash greater speed and accuracy throughout production.
To optimize workflows for AI model development, deployment and maintenance for accelerated workflows in manufacturing, customers can leverage the NVIDIA AI Enterprise software suite, an end-to-end, cloud-native suite of AI and data science tools, which runs on NVIDIA-Certified Systems from HPE. NVIDIA AI Enterprise runs on VMware vSphere and includes key enabling technologies and software from NVIDIA for rapid deployment, management and scaling of AI workloads in the modern hybrid cloud on virtual machines and with Kubernetes containers. This includes support for computer vision workloads that enable smarter, safer manufacturing.
To accelerate the quality assurance process, HPE and NVIDIA’s AI platform comes equipped with NVIDIA Metropolis application frameworks and toolkits. This turnkey software stack brings visual data and AI together to ramp up safety, yield and operational efficiency for our most important spaces and assets. NVIDIA Metropolis offers a powerful combination of pretrained models, optimization tools, deployment software development kits, CUDA-X libraries, and an extensive developer ecosystem to simplify the development and scaling of AI applications for video and image analytics. This allows manufacturers to harness data from smart and connected devices while operationalizing insights in real time.
Manufacturers are just beginning to harness the full value of data. With product quality being a key driver in overall factory productivity, AI-based video analytics can help improve quality inspection processes, reduce defects, and improve customer satisfaction while minimizing scrap.
Related content
Read the Foxconn case study: Making Zero Defects a Reality
Watch the Seagate video: Increasing Throughput with AI-based Video Analytics
Learn more about how HPE and NVIDIA solutions can improve product quality with AI-based video analytics
Meet our Insights Experts bloggers
Carolyn Cairns is responsible for developing marketing strategy, content, and priority solutions for the Manufacturing and industrial sectors at HPE. Her diverse business experience includes business development, product management and marketing roles in the telecommunications, public sector and IT technology and services industries. She has supported numerous pursuits and accounts within the food & beverage, oil & gas, and industrial sectors. She holds an Honours BA from the University of Toronto.
Piyush Modi is responsible for global business development and strategy for the industrial sector at NVIDIA. He is actively engaged with major industrial customers to advance repeatable and deployment-ready industrial AI technology and solutions. Previously, over 20+ years, he held CTO, senior VP and head of research lab positions at companies including Sentient, GE Global Research, BT, Ribbit, IP Unity, and AT&T Bell Labs. Piyush holds a PhD in electrical and computer engineering (speech recognition) from Rutgers, an M.S. in computer science from the University of Tennessee, and a B.Tech. in electrical engineering from IIT, Varanasi.
Insights Experts
Hewlett Packard Enterprise
twitter.com/HPE_AI
linkedin.com/showcase/hpe-ai/
hpe.com/us/en/solutions/artificial-intelligence.html
- Back to Blog
- Newer Article
- Older Article
- Amy Saunders on: Smart buildings and the future of automation
- Sandeep Pendharkar on: From rainbows and unicorns to real recognition of ...
- Anni1 on: Modern use cases for video analytics
- Terry Hughes on: CuBE Packaging improves manufacturing productivity...
- Sarah Leslie on: IoT in The Post-Digital Era is Upon Us — Are You R...
- Marty Poniatowski on: Seamlessly scaling HPC and AI initiatives with HPE...
- Sabine Sauter on: 2018 AI review: A year of innovation
- Innovation Champ on: How the Internet of Things Is Cultivating a New Vi...
- Bestvela on: Unleash the power of the cloud, right at your edge...
- Balconycrops on: HPE at Mobile World Congress: Creating a better fu...
-
5G
2 -
Artificial Intelligence
101 -
business continuity
1 -
climate change
1 -
cyber resilience
1 -
cyberresilience
1 -
cybersecurity
1 -
Edge and IoT
97 -
HPE GreenLake
1 -
resilience
1 -
security
1 -
Telco
108