How does vision inspection catch double seam defects on a canning line?

Why does manual seam sampling miss defects?

The line in this article is a food canning line running 600 cans per minute. Its seams were checked the usual way: operators pulled a can every 100 to 1,000 cans and measured the seam by hand.

Manual sampling like this is normal practice. For low-acid canned foods, FDA's rule at 21 CFR 113.60^[1] calls for a visual seam check on a can from each seaming head at intervals that should not exceed 30 minutes, and a teardown examination at intervals that should not exceed 4 hours. The rule sets how often seams are examined and what gets measured. The dimensional limits come from the can maker.

The weak point is arithmetic. At 600 cans per minute, a sample every 100 to 1,000 cans means one measured can every 10 seconds at best and every 100 seconds at worst. At 1 in 1,000, 999 cans pass without anyone measuring them. A seam that drifts just after a check runs unmeasured until the next one.

Why do double seams drift out of spec?

A double seam is formed in two steps. A first-operation roller curls the end's edge around the can body's flange, and a second-operation roller presses the fold tight, with the chuck holding the end from inside. Rollers wear, settings shift, and a chuck can wear or get damaged. It rarely happens all at once; seam dimensions creep.

According to AFDO's guide to can defects^[2], a worn or badly set second-operation roll can leave a loose seam that may leak, and a worn chuck is a listed cause of sharp seams, cut-overs and spinners. A seam that is too tall or too short is a sign the fold didn't form right and may not seal.

What did JM Automated Solutions install on this line?

The system JM Automated Solutions built for this line has five cameras:

• Four side cameras, spaced around the can, so together they see the full 360° of the seam.
• One top camera, looking down on the end to check that the seam is circular.
• A custom dark-field light. Dark-field lighting comes in at a low angle, so flat surfaces stay dark and edges light up. On a seam, that makes the top and bottom edges of the fold stand out sharply, which is what a repeatable measurement needs.

The pass/fail metric is seam height, measured in thousandths of an inch around the whole seam and compared with the can maker's limits. Each can maker sets the target and tolerance for its own can and end. As a reference point, one published industry table^[3] lists a standard seam length (another name for seam height) of 0.115 in. (2.90 mm). Too short fails. Too tall fails. A failed can goes to the encoder-tracked air reject, and the image and measurement are saved with a timestamp and the reason.

Exposure is set per task. A typical strobed exposure on this kind of station is about 60 microseconds, short enough to keep motion blur to roughly a pixel at 600 cans per minute^[7]. Across JM Automated Solutions systems, 1,200 cans per minute is the ceiling for code-reading-type tasks such as defect detection, barcode reading and OCR; any single task can run slower depending on its lighting and inspection type.

What can a camera measure on a double seam, and what can't it?

On this line, the cameras measure from outside:

• Seam height around the full circumference
• Seam uniformity, so a seam that varies around the can stands out
• Circularity, from the top view
• Visible outside defects such as droops, sharp seams and cut-overs, the kind of gross closure defects listed in FDA's canning inspection guide^[4]

A camera cannot see inside the seam. Body hook, cover hook, overlap and tightness are internal dimensions. They still need a teardown, done by a qualified person on the schedule in the plant's closure program. The vision system supports, and does not replace, the required teardowns. It adds a check on every can between them.

How is the system calibrated?

Against a reference can whose seam was measured by teardown. The plant's seam inspector measures that can by hand, those values become the system's reference, and the system is re-checked against the same can at changeover. If the camera and the teardown disagree, the teardown wins and the system is corrected.

How does a run of rejects signal seamer wear?

One rejected can is a bad can, and the reject handles it. Several rejects in a row mean something else: the seamer itself is failing.

The system watches for that pattern. When it sees a run of consecutive rejects, it alerts maintenance to check the rollers and chuck, and the crew can fix the cause before the next scheduled teardown finds it.

That is why catching the run early matters. A failing seamer keeps making bad cans until someone stops it, so the sooner the line catches the run, the sooner it stops making bad cans.

What does a food recall cost?

A joint industry survey by GMA, FMI and GS1 US put the average direct cost of a food recall at about $10 million^[5][6], before lost sales and brand damage. That is the risk a seam check helps reduce.

A seam defect on its own does not decide how FDA classifies a recall. FDA looks at whether the product is actually adulterated: leaking, swollen, or carrying viable microorganisms^[8]. Recall classes, from Class I down to Class III, depend on how likely and how serious the health risk is^[9]. A seam that doesn't seal can let contaminants in after processing, including the organisms that cause botulism. Catching the cans with bad seams, and the seamer drift behind them, is how the inspection helps keep that product off the shelf.