update at 2026-10-12 14:26:51

This commit is contained in:
douboer
2026-10-12 14:26:51 +08:00
parent ae1c774606
commit 7a225ff2b1
51 changed files with 13426 additions and 8 deletions

View File

@@ -0,0 +1,145 @@
"""寿命拟合:非线性最小二乘(单/双指数)、对数线性、稳健拟合(仅依赖 numpy/scipy.optimize)。
算法对比设计见 docs/实现方案.md §7.5:
- 对数线性需先扣基线,对数变换使低信噪比尾部噪声权重失真(教学点);
- NLS 为基准算法:理想无噪数据应零偏差复现设定寿命(对应原项目"标准拟合"验证)。
"""
import numpy as np
from scipy.optimize import curve_fit, least_squares
def _single_exp(t, A, tau, B):
return A * np.exp(-t / tau) + B
def _double_exp(t, A1, tau1, A2, tau2, B):
return A1 * np.exp(-t / tau1) + A2 * np.exp(-t / tau2) + B
def initial_guess_single(t, y):
"""单指数自动初值:尾段均值作基线、首点定幅度、半衰点定 tau。"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
tail_n = max(1, len(y) // 5)
B0 = float(np.mean(y[-tail_n:]))
A0 = float(y[0] - B0)
if A0 <= 0:
A0 = max(float(np.max(y) - B0), 1e-9)
half = B0 + A0 / 2.0
below = np.where(y <= half)[0]
t_half = float(t[below[0]]) if len(below) else float(t[len(t) // 2])
tau0 = max(t_half / np.log(2.0), 1e-3)
return [A0, tau0, B0]
def fit_single_exp_nls(t, y, p0=None):
"""单指数 + 常数基线的非线性最小二乘拟合。"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
if p0 is None:
p0 = initial_guess_single(t, y)
popt, pcov = curve_fit(
_single_exp, t, y, p0=p0,
bounds=([0.0, 1e-9, -np.inf], [np.inf, np.inf, np.inf]),
maxfev=50000,
)
resid = y - _single_exp(t, *popt)
perr = np.sqrt(np.abs(np.diag(pcov)))
return {
"model": "single_exp_baseline",
"A": float(popt[0]), "tau": float(popt[1]), "B": float(popt[2]),
"A_err": float(perr[0]), "tau_err": float(perr[1]), "B_err": float(perr[2]),
"rmse": float(np.sqrt(np.mean(resid ** 2))),
"residual": resid,
"popt": [float(v) for v in popt],
}
def fit_log_linear(t, y, tail_frac=0.2, b=None):
"""对数线性拟合:ln(I−B) 对 t 线性回归 → tau = −1/slope。
b=None 时用尾段均值估计基线(注意:对 B=0 的纯信号,尾段估计本身
就引入偏差——这正是"基线估计误差"教学点,见 docs/实现方案.md §7.5);
b 已知时直接使用(此时对数线性与 NLS 在理想数据上数学等价)。
返回剔除的非正点数(对数前需 I−B>0),供教学观察。
"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
if b is None:
tail_n = max(1, int(len(y) * tail_frac))
B = float(np.mean(y[-tail_n:]))
baseline_estimated = True
else:
B = float(b)
baseline_estimated = False
yy = y - B
mask = yy > 0
dropped = int(np.sum(~mask))
if mask.sum() < 2:
return {"model": "log_linear", "tau": None, "A": None, "B_est": B,
"baseline_estimated": baseline_estimated,
"dropped_points": dropped, "n_used": int(mask.sum())}
slope, intercept = np.polyfit(t[mask], np.log(yy[mask]), 1)
tau = -1.0 / slope if slope < 0 else None
return {
"model": "log_linear",
"tau": float(tau) if tau else None,
"A": float(np.exp(intercept)),
"B_est": B,
"baseline_estimated": baseline_estimated,
"dropped_points": dropped,
"n_used": int(mask.sum()),
}
def fit_double_exp_nls(t, y, p0=None):
"""双指数 + 常数基线 NLS(M4 复现蒙特卡洛用)。
初值策略:先单指数拟合,快成分取 0.2·A、0.1·tau。
"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
if p0 is None:
s = fit_single_exp_nls(t, y)
p0 = [0.2 * s["A"], max(0.1 * s["tau"], 1e-3), 0.8 * s["A"], s["tau"], s["B"]]
popt, pcov = curve_fit(
_double_exp, t, y, p0=p0,
bounds=([0, 1e-6, 0, 1e-6, -np.inf], [np.inf, np.inf, np.inf, np.inf, np.inf]),
maxfev=100000,
)
resid = y - _double_exp(t, *popt)
perr = np.sqrt(np.abs(np.diag(pcov)))
return {
"model": "double_exp_baseline",
"A1": float(popt[0]), "tau1": float(popt[1]),
"A2": float(popt[2]), "tau2": float(popt[3]), "B": float(popt[4]),
"tau1_err": float(perr[1]), "tau2_err": float(perr[3]),
"rmse": float(np.sqrt(np.mean(resid ** 2))),
"residual": resid,
"popt": [float(v) for v in popt],
}
def fit_single_exp_robust(t, y, loss="soft_l1", f_scale=None):
"""稳健拟合(扩展功能):least_squares + huber/soft_l1 损失。"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
p0 = initial_guess_single(t, y)
if f_scale is None:
f_scale = max(float(np.std(np.diff(y))) * 2.0, 1e-9)
def resid_fn(p):
A, tau, B = p
return A * np.exp(-t / tau) + B - y
res = least_squares(
resid_fn, p0, bounds=([0.0, 1e-9, -np.inf], [np.inf, np.inf, np.inf]),
loss=loss, f_scale=f_scale, max_nfev=50000,
)
return {
"model": f"single_exp_robust_{loss}",
"A": float(res.x[0]), "tau": float(res.x[1]), "B": float(res.x[2]),
"rmse": float(np.sqrt(np.mean(res.fun ** 2))),
"success": bool(res.success),
}