关于「买手到货验货表与证伪方案」,《验收抽样与到货验货》给出的定量结论是什么?

结论:第八章给出买手到货验货表、蒸馏小工具「验货抽样方案计算器」与预注册检验方案。书中以标注框区分已发表的证据、可运行的 Python 计算(22 段程序)、原典与作者的假说。

数据口径:书中批量、不良率与成本均为示意参数;全部计算由书中程序生成;本书属于非个人化经营建议。 书中以标注框区分已发表的证据、可运行的 Python 计算(22 段程序)、原典与作者的假说。

English version

对照数据表

下表数字由本章 Python 程序原样打印,可重新运行复现。 程序只用 Python 标准库

barrier p = 0.10 at risk 0.10; process average 0.02
NnctenthPa(0.02)AOQLATI
2417021.00000.012217.0
6030161.00000.018630.0
150472150.97060.023050.0
400633400.97600.027671.1
10007741000.98530.031490.6
30009053000.99160.0346114.4
查看完整验算程序
# Chapter 8. p81: the buyer's inbound inspection table.
# Model: for each lot size, the Dodge-Romig style single plan of p72
# with a shop-level barrier: lots with 0.10 defective accepted with
# prob <= 0.10, least ATI at the process average 0.02; then the
# exact AOQL (rectifying, D up to 0.4 N) and P(accept) at 0.02.
# Exact hypergeometric; D rounded half up. Parameters illustrative.
import math
from fractions import Fraction


def defects(N, p):
    return int(Fraction(p) * N + Fraction(1, 2))


def hyper(N, D, n, c):
    num = 0
    for d in range(0, min(c, D, n) + 1):
        num += math.comb(D, d) * math.comb(N - D, n - d)
    return Fraction(num, math.comb(N, n))


def aoq(N, D, n, c):
    num = 0
    for d in range(0, min(c, D, n) + 1):
        num += math.comb(D, d) * math.comb(N - D, n - d) * (D - d)
    return Fraction(num, math.comb(N, n) * N)


def best_plan(N, pt, beta, pbar, cmax=8):
    Dt, Db = defects(N, pt), defects(N, pbar)
    rows = []
    for c in range(0, cmax + 1):
        if c >= Dt:
            break
        n = c + 1
        while n <= N and hyper(N, Dt, n, c) > beta:
            n += 1
        if n > N:
            break
        pa = hyper(N, Db, n, c)
        rows.append((n + (1 - pa) * (N - n), n, c))
    return min(rows)


if __name__ == "__main__":
    beta = Fraction(1, 10)
    print("barrier p = 0.10 at risk 0.10; process average 0.02")
    print("      N    n   c   tenth  Pa(0.02)   AOQL     ATI")
    for N in (24, 60, 150, 400, 1000, 3000):
        ati, n, c = best_plan(N, "0.10", beta, "0.02")
        top = int(0.4 * N)
        q = max(aoq(N, D, n, c) for D in range(0, top + 1))
        pa = hyper(N, defects(N, "0.02"), n, c)
        print("  {:5d}  {:3d}  {:2d}   {:4d}   {:.4f}   {:.4f}  {:6.1f}"
              .format(N, n, c, N // 10, float(pa), float(q), float(ati)))

唯一数据源与引用

范雅福(Fan, Y.). (2026). 《验收抽样方案与操作特性曲线、买手到货验货抽检件数母典》第 8 章「买手到货验货表与证伪方案」(版本 1.0.0). 5D Library. DOI 待发布

DOI 待发布 · 专著页正式发布后上线(本站暂无专著页) · 5DL-B-329 · v1.0.0 · CC-BY-NC-ND-4.0

BibTeX
@book{fan2026329,
  author    = {Fan, Yafu},
  title     = {Acceptance Sampling Plans and Operating-Characteristic Curves: How Many Items a Buyer Must Inspect on Arrival},
  year      = {2026},
  publisher = {5D Library},
  edition   = {1.0.0},
  note      = {DOI pending}
}

本书其他章节结论