-
NPI: A How To Guide for Engineers & Their Leaders
-
Leading from the Front
-
Marcel Tremblay: The Olympic Mindset & Engineering Leadership
-
Anurag Gupta: Framework to Accelerate NPI
-
Kyle Wiens on Why Design Repairability is Good for Business
-
Nathan Ackerman on NPI: Do The Hard Thing First
-
JDM Operational Excellence in NPI
-
Building the Team
-
Quality is Set in Development & Maintained in Production
-
3 Lessons from Tesla’s Former NPI Leader
-
Maik Duwensee: The Future of Hardware Integrity & Reliabilitypopular
-
Reject Fake NPI Schedules to Ship on Time
-
Leadership Guidance for Failure to Meet Exit Criteria
-
-
Screws & Glue: Getting Stuff Done
-
Choosing the best CAD software for product design
-
Screws vs Glues in Design, Assembly, & Repair
-
Design for Instrumental - Simple Design Ideas for Engineers to Get the Most from AI in NPI
-
Best Practices for Glue in Electronics
-
A Practical Guide to Magnets
-
Inspection 101: Measurements
-
A Primer on Color Matching
-
OK2Fly Checklists
-
Developing Your Reliability Test Suite
-
Guide to DOEs (Design of Experiments)
-
Ten Chinese phrases for your next build
-
-
NPI Processes & Workflows
-
-
Production: A Primer for Operations, Quality, & Their Leaders
-
Leading for Scale
-
Greg Reichow’s Manufacturing Process Performance Quadrants
-
8D Problem Solving: Sam Bowen Describes the Power of Stopping
-
Cut Costs by Getting Your Engineers in the Field
-
Garrett Bastable on Building Your Own Factory
-
Oracle Supply Chain Leader Mitigates Risk with Better Relationships
-
Brendan Green on Working with Manufacturers
-
Surviving Disaster: A Lesson in Quality from Marcy Alstott
-
-
Ship It!
-
Production Processes & Workflows
-
Failure Analysis Methods for Product Design Engineers: Tools and Techniques
-
-
Thinking Ahead: How to Evaluate New Technologies
-
How to Buy Software (for Hardware Leaders who Usually Don’t)
-
Adopting AI in the Aerospace and Defense Electronics Space
-
Build vs Buy: A Guide to Implementing Smart Manufacturing Technology
-
Leonel Leal on How Engineers Should Frame a Business Case for Innovation
-
Saw through the Buzzwords
-
Managed Cloud vs Self-Hosted Cloud vs On-Premises for Manufacturing Data
-
AOI, Smart AOI, & Beyond: Keyence vs Cognex vs Instrumentalpopular
-
Visual Inspection AI: AWS Lookout, Landing AI, & Instrumental
-
Manual Inspection vs. AI Inspection with Instrumentalpopular
-
Electronics Assembly Automation Tipping Points
-
CTO of ASUS: Systems Integrators for Manufacturing Automation Don't Scale
-
-
ROI-Driven Business Cases & Realized Value
-
Automated Optical Inspection (AOI) is a camera system that uses a CAD reference to identify surface mount assembly (SMA) defects in real time on the line. You won’t find an SMA line without one because they provide valuable yield protection for the rest of the assembly process.
While ubiquitous in electronics manufacturing, this technology has its faults – expensive, high false call rate, and difficulty programming. The term is so embedded in the electronics manufacturing canon that it’s been overloaded to also describe machine vision inspection in other applications throughout an assembly process – any real-time camera judgment could be called an AOI.
Over $3B in industrial cameras are sold yearly, and Keyence and Cognex are two of the biggest. Conventional AOI uses decades-old computer vision algorithms. “Smart AOI” adds AI models that expand their inspection capability to include defects that are difficult to write rules around, such as cable routing and glue inspection.
This article will discuss the benefits, limitations, and costs of this expanded “AOI” that encompasses manufacturing inspection beyond SMA, including Smart AOI and related systems like Instrumental.
The benefits and limitations of AOI
How Instrumental leverages AOI as part of a larger quality control platform
Key differentiators between AOI and Instrumental
Costs of AOI, Smart AOI, and Instrumental
The Benefits and Limitations of AOI for Electronics Inspection
While initially only referring to the component placement inspection on PCBs, the term AOI now encompasses nearly any automated optical inspection capable of providing real-time judgment. Keyence and Cognex are two common vendors for AOI outside the SMA line – for component, sub-assembly, and final assembly inspection.
AOI’s key use cases are real-time judgment for presence/absence, measurements (like gaps or concentricity), and keep-in/keep-out verification.
Key Benefits of AOI
The benefits of AOI depend on your use case and how successful your implementation is. The top benefits of AOI when compared to manual inspection are:
- Automate inspection operations to reduce headcount.
- Apply the same rules-based inspection consistently across multiple lines.
- Provide yield protection for downstream processes.
Those pesky details matter, though. Typical implementations of industrial camera inspection tend to be “one issue, one camera” – meaning one camera only does one measurement or one key inspection. While these cameras can conduct more inspections within a single image, it’s not what happens in practice (hardware companies want to sell more cameras). As a result, only the highest ROI applications have AOI – and there’s still a lot of manual inspection in electronics manufacturing.
Key Limitations of AOI & “Smart AOI”
Key limitations when considering Keyence, Cognex, and Cognex Vidi systems:
Challenging Setup Requiring Specialists. Setting up and programming these systems to operate on your line requires a specialist or professional services via a systems integrator. These are not DIY systems.
Rules Break When Line Changes. These systems are rigid, but line processes and parts are not. AOI is practically useless in New Product Introduction (NPI) where there are rapid changes. Still, even in production, cost-down improvements and operator turnover can yield changes that result in broken algorithms. Each system only achieves ROI when it can replace a human inspector in mass production: it needs to be carefully (and constantly) tuned.
Must Be Programmed On-Site. AOI equipment is “on-premises,” and all programming and configuration needs to happen machine by machine and site by site. A massive drawback of AOI equipment is that all fleet training, replicating, updating, and maintaining must happen on-site. Even “smart AOI” like Cognex Vidi, which can be run on a local server and deployed to up to 4 devices simultaneously, doesn’t have remote administration.
Low Resolution and Paying Extra for Color. Keyence and Cognex have spent significant research dollars on creating excellent optics, something they want to charge for. But the smartphone revolution has miniaturized and scaled small, high-quality camera sensors and it’s possible to buy “dumb cameras”, full color, with 20 MP resolution for $200-400 that have optics that rival Keyence and Cognex’s $8,000-$50,000 offerings.
Cannot Discover New Issue Types. AOI and “smart AOI” can only identify defects it's explicitly programmed to find. Unanticipated issues and novel defects will “pass” these inspections, causing costs down the line. Novel issue discovery is critical to a QC process, and Instrumental is the only automated offering on the market for novel issue discovery.
Instrumental: Leveraging AOI to Maximize Business Value
AOI and pass/fail judgment is just the first step in multi-step quality control systems where process, quality, mechanical, and other engineers execute daily on the assembly line. The more effectively and efficiently those engineers can do their jobs, the more direct value the technology can deliver to their organization.
For example:
- Standard AOI can be setup to catch the poor concentricity of a camera lens to a cosmetic opening.
- An Instrumental machine learning manufacturing system will catch the poor concentricity too, but it will already have flagged the misplaced component upstream. You can choose whether Instrumental:
- Intercepts the misplaced camera module and other anomalies on the line, preventing the downstream failure in the first place; or
- Flags this and other anomalies in the cloud, enabling rapid failure analysis via virtual teardowns, visual correlations, and deep visual search.
AOI is just the base layer of a complex workflow – Instrumental provides that and builds on top. Engineers leverage Instrumental to improve first-pass yield, eliminate field failures, reduce engineering and inspector time, and improve product margins.
Key Differentiators of Instrumental Compared to AOI
Instrumental’s manufacturing AI and data platform offers distinct advantages compared to Keyence and Cognex:
- Easy to Deploy. You can deploy Instrumental anywhere in the world in two to six weeks without IT or software engineering support. Once it starts ingesting data, Discover AI automatically detects anomalies on Day 1. Your engineering and operations teams can set up pass/fail tests to intercept defects on the line in minutes.
- Easy to Learn. Instrumental is intuitive to use and doesn’t require extensive training, enabling you to put data and insights in the hands of your frontline engineers so they can work more efficiently.
Intercept Known Defects & Discover Novel Defect Types. In addition to AOI functionality to intercept known defects, Instrumental is the only offering on the market that will automatically discover and intercept novel defects that weren’t on your SIP – preventing future yield fallout or field issues.
- Intercept Tricky Issue Types. AI inspection can intercept issues that rules-based AOI struggles with, including cable routing, glue/coating deposition, foreign material and many others.
- Access, Program, Update, and Administrate Remotely. Instrumental is a secure, cloud-based platform that can be accessed and updated from anywhere in the world. This enables remote administration of your fleet of Instrumental inspection stations and algorithms without setting foot in the factory.
- One Camera for Many Issues = Higher ROI. In addition to your known inspection items, Discover AI is constantly scanning and learning, enabling you to add hundreds of inspections to each camera – increasing the overall value your cameras provide to your line.
- 100% Traceability and Retroactive Analysis. Instrumental is a software product that can process images from any camera (from Keyence, Cognex, X-ray, IR, and other cameras), including images it has already processed, looking for new insights or defects.
Cost of Automated Inspection Solutions: Keyence, Cognex, and Instrumental
ROI and Cost of AOI & Smart AOI Systems
Keyence and Cognex AOI systems offer presence/absence inspection and gap/concentricity measurements. The main value for organizations is headcount replacement and the reduction in inspection errors from tired inspectors.
All in with these legacy systems, expect to spend at least $20,000 in capital expenses and one-time costs per camera and an additional $10,000-$15,000 in annual fees for service and re-programming. Most customers will spend far more if they need systems integration, though large-scale deployments may reduce per-camera costs.
Capital Expense Cost: A singular Keyence camera costs anywhere from $20,000 to $50,000 while Cognex offers hardware for $8,000 to $20,000.
Non-Recurring Engineering (NRE): Integration will be a significant portion of the price tag. Systems integrators will charge hefty fees to implement as part of automation equipment – expect to pay NRE costs of $20,000-$150,000, depending on the complexity of your requirements. A simple setup may be possible to DIY with a specially trained team, but plan on it taking many weeks to get up and running.
Operational Expense Cost: Both solutions come with ongoing maintenance and service plans – an additional 10-15% on top of the yearly cost. Cognex ViDi is SaaS on top of the hardware. According to ViDi customers we’ve spoken to, its fees can range from $2,000 to $12,000 per year for licenses to the software. This low price point reflects the limited utility of the Smart AOI software and hefty training requirements (hundreds of units).
Recurring NRE: Remember, these systems need to be re-programmed and updated after every part and process change on the line. Leave additional budget or headcount allocation for this ongoing NRE.
Cost of Instrumental
Instrumental has a different business model and provides additional benefits over strictly AOI systems, so an apples-to-apples cost comparison is not possible. Instrumental’s focus is on ROI – we deliver a minimum of 3X ROI, with the first proof of value within 90 days. You can read more about the ROI our customers have experienced in our case studies.
Whereas AOI is a hardware product, Instrumental is a software subscription with hardware as a service – and the pricing scales with data consumption and the AI licenses needed for your specific use cases.
Our most basic offering is Trace, which provides a 100% data record of both visual and functional test data for the cost of a simple integration and a data plan. Customers can then layer on licenses as needed for their use cases:
- Discover, which leverages Discover AI to find new issues – an offering unique to Instrumental not provided by any other AOI or Smart AOI player on the market.
- Operate, which provides tools for monitoring ongoing production – containing AOI features as well as remote oversight on line yields with proactive alarms for drift.
- Solve, which leverages Correlations AI to identify relationships that point to the root cause – another offering unique to Instrumental.
Instrumental is the best in the world at what we do: discovering and intercepting novel and known issues and providing a powerful toolset to actually solve them.
Learn more about Instrumental’s product offerings here.