Free tools

AQL sampling plan calculator (ANSI/ASQ Z1.4)

Enter your lot size, inspection level and AQL; get the sample size and accept/reject numbers from the published single sampling tables. Free, runs in your browser.

Pieces presented as one lot
General II is the default for most inspection
2.5 is a common major-defect AQL
Inspection severity
Normal unless your switching history says otherwise
Nothing you type leaves your browser.
VoraControl
This calculator answers one lot. VoraControl captures every inspection against your released control plans and keeps the evidence where the next audit can find it.
Start free trialBook a demo
The idea

What AQL actually means

AQL is the acceptable quality limit: the worst average nonconforming level that a sampling scheme will still routinely accept across a series of lots. It describes the behaviour of the scheme over time. It is not a target, a tolerance, or a statement about the lot in front of you.

A lot accepted at AQL 2.5 has not been shown to be free of defects. It has only failed to produce enough nonconforming pieces in the sample to reach the reject number. A rejected lot has not been proven bad either. Small samples carry real risk in both directions, and both risks are published: the operating characteristic curve for each plan shows the probability of acceptance at any true defect rate.

Tightening the AQL or moving to a larger sample changes the shape of that curve. It never removes the risk, and no sampling plan can turn a sample result into a statement about every piece in the lot. An accepted lot does not tell you the true defect rate of the lot, whether the process that made it is stable or capable, or whether the defects that are present matter to the customer who receives them.

Setting up

How to choose an inspection level

The level decides how much of the lot you look at. It is a business decision about how much inspection you are willing to pay for, made before you pick an AQL. If a drawing, a control plan or a purchase order names a level, that one wins.

General II
The default. Use it unless you have a reason not to.
General I
Roughly 40 percent of the sample of level II, with less power to separate a good lot from a poor one. Reasonable when inspection is slow or destructive and the process history is long and quiet.
General III
A larger sample and sharper discrimination. Worth the cost for a new tool, a new supplier, a first article follow-up, or the lots that come after a containment.
Special S-1 to S-4
Very small samples for checks that cost real money per piece, such as salt spray, cross section or full layout. They are a screen, not a sort, and their acceptance probabilities are wide. Do not use them for routine visual checks.
Table I

The sample size code letter table

Find the row for your lot size, read across to your inspection level and take the letter. That letter plus the AQL and the severity picks the row in the single sampling table, which is where the sample size and the accept and reject numbers come from.

ANSI/ASQ Z1.4 Table I: sample size code letters by lot size band and inspection level
Lot sizeS-1S-2S-3S-4IIIIII
2 to 8AAAAAAB
9 to 15AAAAABC
16 to 25AABBBCD
26 to 50ABBCCDE
51 to 90BBCCCEF
91 to 150BBCDDFG
151 to 280BCDEEGH
281 to 500BCDEFHJ
501 to 1,200CCEFGJK
1,201 to 3,200CDEGHKL
3,201 to 10,000CDFGJLM
10,001 to 35,000CDFHKMN
35,001 to 150,000DEGJLNP
150,001 to 500,000DEGJMPQ
500,001 and overDEHKNQR

Run the calculator above and the cell it used is marked here. On a phone, swipe the table sideways for the special levels.

Severity

Normal, tightened and reduced: the switching rules

Z1.4 is a scheme, not a single plan. Severity is meant to move with the evidence: a supplier who keeps failing gets looked at harder, and a supplier with a long clean record can be looked at less. The rules are mechanical, and they depend on your lot history, which is exactly the part a one-shot calculator cannot see.

Normal
Where you start

Every new product, tool or supplier begins here, and every return from tightened or reduced lands here.

Tightened
2 rejects in 5 lots

Switch when 2 of 5 consecutive lots are rejected on original inspection. Return to normal after 5 consecutive lots are accepted. If 5 lots are rejected while on tightened, the standard says to discontinue inspection under Z1.4 until the process is fixed.

Reduced
Optional, with conditions

Allowed when the last 10 lots were accepted on original inspection, the total nonconforming is under the Table VIII limit, production is steady and the responsible authority agrees.

Under reduced inspection the accept and reject numbers are not consecutive. If the count lands in the gap between them, you accept the lot and go back to normal inspection for the next one. This calculator returns the plan for whichever severity you select; it does not track your history and it does not switch severity for you.

Lineage

Z1.4, MIL-STD-105E and ISO 2859-1

MIL-STD-105E was the United States military standard for attribute sampling until it was withdrawn in 1995. ANSI/ASQ Z1.4 carries the same tables forward as a civilian standard. ISO 2859-1 is the international line of the same family, with the same code letters and the same single sampling tables.

Drawings and purchase orders in the field still name all three, often for the same plan. For the general levels and the common AQLs, the sample size and the accept and reject numbers line up. The differences show up around the edges: the wording on switching, the treatment of limiting quality, and how each document handles reduced inspection. Read the clause in the contract before you treat the three names as interchangeable.

This calculator covers SINGLE sampling only. Double and multiple sampling plans, which let you take a second or later sample before deciding, are not included. The AQL columns above 10, expressed as defects per 100 units rather than percent nonconforming, are out of scope too.

FAQ

Questions inspectors ask

Does an accepted lot mean there are no defects in it?
No. It means the sample you took did not reach the reject number. A lot can hold nonconforming pieces and still be accepted, which is why the standard talks about acceptance and not about quality guarantees.
Which AQL should I use?
The one the customer specified. If nothing is specified, most shops run separate AQLs by defect class, often a tight value for critical characteristics, something near 1.0 or 1.5 for major, and a looser value for minor. Agree it in writing before the first shipment, not after a reject.
What is the difference between Ac and Re?
Ac is the highest number of nonconforming pieces in the sample that still allows you to accept the lot. Re is the lowest number that requires you to reject it. Under normal and tightened single sampling the two are consecutive; under reduced inspection they are not.
What does an arrow in the sampling table mean?
It means there is no plan at that combination of code letter and AQL. Follow the arrow to the first plan below or above it and use the sample size that belongs to the letter you land on, not the letter Table I gave you. The calculator does this for you and says so in the result.
What if the sample size is bigger than the lot?
Then you inspect every piece. This happens on small lots at tight AQLs, and it is the honest answer: the plan is asking for more parts than the lot contains.
Does it matter how I pick the pieces?
Yes, more than the arithmetic does. The tables assume a random sample drawn from the whole lot. Taking the top layer off a pallet, or the parts nearest the door, breaks that assumption, and the published risks stop describing what you just did.
VoraControl
This calculator answers one lot. VoraControl captures every inspection against your released control plans and keeps the evidence where the next audit can find it.
Start free trialBook a demo
AQL calculator: ANSI/ASQ Z1.4 sampling plans | VoraSuite