关于「实证闭环:水质适配周度台账、实战工具与检查器规格、预注册检验」,《硬水、螯合与泡沫》给出的定量结论是什么?
结论:第八章给出水质适配周度台账、蒸馏小工具「硬水折损与螯合配比试算器」、四件套检查器规格与预注册检验,三角检验检出 pd = 0.3 需 42 人次,顺滑度评分登记 64 名评价员。书中参数为示意,全部计算由书中程序生成。本书不是配方安全评估,也不是法规意见:任何配方须由合格人员做稳定性、相容性、防腐挑战、斑贴与毒理安全评估,法规以官方现行文本为准;不写在家自制,不点名评价任何品牌,不对皮肤与发丝作泡沫与触感以外的任何宣称。书中以标注框区分已发表的证据、可运行的 Python 计算(20 段程序)、原典与作者的假说。
数据口径:钙镁离子先压低临界胶束浓度,只在冲洗稀释的中间段才析出钙盐,折损按表活体系分档:皂基最重,烷基硫酸盐次之,酰基谷氨酸盐居中,醚硫酸盐与两性、非离子表活几乎不受影响;示意 W4 水里,烷基硫酸盐在冲洗初段的折损份额为 0.632。 螯合剂按摩尔一比一结合钙镁,示意剂量下一次用量只软化 10.5 毫升硬水,连起泡兑水都覆盖不全;全部软化一次淋浴需要配方含量的 1,524 倍,一整瓶只够花洒流约 3.16 秒。
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 标准库与结论吻合的打印值: 0.3, 20, 42
| alpha 0.05 one-sided; n = first / stable | ||||
| pd | triangle 80% | triangle 90% | paired 80% | paired 90% |
| 0.2 | 87/94 | 117/124 | 158/169 | 213/224 |
| 0.3 | 40/42 | 53/57 | 69/76 | 93/102 |
| 0.4 | 23/25 | 30/34 | 37/42 | 53/58 |
| 0.5 | 16/16 | 20/22 | 23/28 | 33/35 |
| triangle n = 60: reject chance at 27 or more correct |
查看完整验算程序
# Chapter 8. p82: panel sizes for triangle and paired-comparison tests.
# Model: guessing model with a proportion pd of true discriminators.
# Triangle: P(correct) = pd + (1 - pd) / 3, chance 1/3. Paired
# directional comparison: P(correct) = pd + (1 - pd) / 2, chance 1/2.
# For each n the exact one-sided binomial critical count at alpha = 0.05
# is found and the exact power computed (math.comb, math.fsum). The
# table gives the smallest n reaching the target power and, because
# exact power saw-tooths, the smallest n from which every larger n up
# to n + 30 also reaches it.
import math
def pmf(n, p):
return [math.comb(n, k) * p ** k * (1 - p) ** (n - k)
for k in range(n + 1)]
def crit(n, p0, alpha):
probs = pmf(n, p0)
lo, hi = 0, n + 1 # tail(c) falls as c rises
while lo < hi:
mid = (lo + hi) // 2
if math.fsum(probs[mid:]) <= alpha:
hi = mid
else:
lo = mid + 1
return lo
def power(n, p0, p1, alpha=0.05):
c = crit(n, p0, alpha)
return math.fsum(pmf(n, p1)[c:]) if c <= n else 0.0
def sizes(p0, pd, target):
p1 = pd + (1 - pd) * p0
ok = [power(n, p0, p1) >= target for n in range(1, 331)]
first = ok.index(True) + 1
stable = next(n for n in range(1, 301)
if all(ok[n - 1:n + 30]))
return first, stable
if __name__ == "__main__":
print("alpha 0.05 one-sided; n = first / stable")
print(" pd triangle 80% triangle 90% paired 80% paired 90%")
for pd in (0.2, 0.3, 0.4, 0.5):
cells = []
for p0 in (1 / 3, 1 / 2):
for target in (0.8, 0.9):
a, b = sizes(p0, pd, target)
cells.append("{:>4}/{:<4}".format(a, b))
print(" {:.1f} {:>12} {:>12} {:>10} {:>10}".format(pd, *cells))
n, p0 = 60, 1 / 3
c = crit(n, p0, 0.05)
print("triangle n = 60: reject chance at {} or more correct".format(c))唯一数据源与引用
范雅福(Fan, Y.). (2026). 《洗护配方水质硬度化学、钙镁离子螯合软化与表活泡沫沉积增效母典》第 8 章「实证闭环:水质适配周度台账、实战工具与检查器规格、预注册检验」(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-389 · v1.0.0 · CC-BY-NC-ND-4.0
BibTeX
@book{fan2026389,
author = {Fan, Yafu},
title = {Water-Hardness Chemistry in Personal-Care Formulations, Calcium-Magnesium Chelation and Surfactant Foam-Deposition Enhancement},
year = {2026},
publisher = {5D Library},
edition = {1.0.0},
note = {DOI pending}
}