update at 2026-10-12 16:25:51

This commit is contained in:
douboer
2026-10-12 16:25:51 +08:00
parent db63516781
commit a484c7914f
67 changed files with 30357 additions and 193 deletions

View File

@@ -1,5 +1,5 @@
"""算法核心层:signal / fiber / acquisition / fitting(全部 Pyodide 兼容)。"""
"""算法核心层:signal / fiber / acquisition / calibration / fitting / statistics(全部 Pyodide 兼容)。"""
from . import signal, fiber, acquisition, fitting
from . import signal, fiber, acquisition, calibration, fitting, statistics
__all__ = ["signal", "fiber", "acquisition", "fitting"]
__all__ = ["signal", "fiber", "acquisition", "calibration", "fitting", "statistics"]

View File

@@ -99,3 +99,81 @@ def run_single_channel(t_cont, y_cont, params, rng):
"jitter_ns": jitter,
"bandwidth_sigma_ns": float(p.get("bandwidth_sigma_ns", 0.0) or 0.0),
}
def _interp_signal(s_times, t_cont, y_cont):
"""在等效时间 s 处取值;s<0(信号未到达)按 0 处理(触发前无信号)。"""
s = np.asarray(s_times, dtype=float)
y = np.interp(s, t_cont, y_cont) # 先按边界插值(s<0 → y(0))
y = np.where(s < 0, 0.0, y) # s<0 → 0(激发关断前无荧光)
return y
def run_multi_channel(t_cont, y_cont, params, rng):
"""四通道光纤延时等效采样(M2 起)。
物理模型:四路信号副本经光纤延时 δk;同一 ADC 从触发时刻起以 Δt 采样,
第 k 路第 m 个样本采样到的是 x(t_m − δk),等效时间 s = t_m − δk。
params(在 M0 单通道参数基础上增加):
delays 名义延时列表(ns),如 [0, 47.5, 95.0, 142.5]
gain_errors 各通道相对增益误差(0 为理想)
delay_errors 各通道延时误差(ns,0 为理想)
baselines 各通道基线偏置(相对峰值,0 为理想)
返回 dict(纯数据)。
"""
p = dict(params)
t_cont = np.asarray(t_cont, dtype=float)
y_cont = np.asarray(y_cont, dtype=float)
delays = [float(d) for d in p["delays"]]
n_ch = len(delays)
gain_err = p.get("gain_errors", [0.0] * n_ch)
delay_err = p.get("delay_errors", [0.0] * n_ch)
base_frac = p.get("baselines", [0.0] * n_ch)
dt = float(p.get("dt_ns", 10.0))
t0 = float(p.get("t0_ns", 0.0))
window = float(p.get("window_ns", t_cont[-1] - t_cont[0]))
n_samples = int(round(window / dt))
y_bw = gaussian_response(t_cont, y_cont, p.get("bandwidth_sigma_ns", 0.0))
peak = float(np.max(y_bw)) if np.max(y_bw) > 0 else 1.0
snr_db = p.get("snr_db")
sigma = snr_to_sigma(snr_db, peak) if snr_db is not None else 0.0
bits = p.get("bits")
ts_m = t0 + dt * np.arange(n_samples) # ADC 绝对采样时刻
channels = []
for k in range(n_ch):
d_eff = delays[k] + delay_err[k] # 实际延时(含误差)
s = ts_m - d_eff # 等效时间(相对触发)
y_clean = _interp_signal(s, t_cont, y_bw)
y_clean = y_clean * (1.0 + gain_err[k]) + base_frac[k] * peak
y_meas = y_clean + (rng.normal(0.0, sigma, size=n_samples) if sigma > 0 else 0.0)
if bits is not None:
fs = p.get("fullscale") or 2.0 * peak
y_meas = quantize_adc(y_meas, bits, fs)
channels.append({
"index": k,
"delay_ns": delays[k],
"delay_eff_ns": d_eff,
"gain": 1.0 + gain_err[k],
"baseline": base_frac[k] * peak,
"t_adc": ts_m,
"s_equiv": s, # 等效时间(校准前:用设计延时)
"y_clean": y_clean,
"y_samples": y_meas,
})
return {
"n_channels": n_ch,
"dt_ns": dt,
"t0_ns": t0,
"n_samples": n_samples,
"sigma": sigma,
"snr_db": snr_db,
"bits": bits,
"peak": peak,
"channels": channels,
}

View File

@@ -0,0 +1,154 @@
"""通道校准:基线扣除、增益归一化、延时校准与时间重建(仅依赖 numpy)。
校准三步对应 docs/实现方案.md §7.3:
1. 基线扣除(尾段均值 / 显式传入);
2. 增益归一化(参考通道峰值对齐);
3. 延时校准——两种方法供教学比较:
- "标定值":使用外部标定得到的延时(模拟器可提供真实延时 + 可调标定残差,
对应原项目误差机制表中"延时标定误差");
- "互相关":仅用采样数据互相关估计(只能分辨 Δt 整数周期,
亚采样相位无法恢复——教学点:互相关校准的粒度限制)。
"""
import numpy as np
def estimate_baseline(y, tail_frac=0.2):
"""尾段均值估计基线(若衰减尾部未归零则高估——教学点)。"""
y = np.asarray(y, dtype=float)
tail_n = max(1, int(len(y) * tail_frac))
return float(np.mean(y[-tail_n:]))
def subtract_baseline(y, baseline=None, tail_frac=0.2):
"""扣除基线;返回 (去基线序列, 基线值)。"""
b = baseline if baseline is not None else estimate_baseline(y, tail_frac)
return np.asarray(y, dtype=float) - b, float(b)
def normalize_gain(y, ref_peak):
"""以参考峰值对齐通道幅度;返回 (归一化序列, 增益系数)。"""
y = np.asarray(y, dtype=float)
peak = float(np.max(np.abs(y)))
if peak <= 0:
return y, 1.0
g = ref_peak / peak
return y * g, g
def estimate_delay_cross_corr(ref_y, sig_y, dt_ns):
"""互相关估计相对延时:只能得到 Δt 整数倍的滞(教学点)。"""
ref = np.asarray(ref_y, dtype=float)
sig = np.asarray(sig_y, dtype=float)
m = min(len(ref), len(sig))
cc = np.correlate(sig[:m], ref[:m], mode="full")
lag = int(np.argmax(cc) - (m - 1))
return float(lag) * dt_ns, int(lag)
def rebuild(t_adc, y, delay_used, dt_ns):
"""时间重建(Redis):u = t_adc − delay,合并后按时间排序。
delay_used 为每通道使用的延时(名义 / 标定 / 互相关估计)。
"""
t_all, y_all = [], []
for k in range(len(t_adc)):
u = np.asarray(t_adc[k], dtype=float) - float(delay_used[k])
mask = u >= 0
t_all.append(u[mask])
y_all.append(np.asarray(y[k], dtype=float)[mask])
if not t_all:
return np.array([]), np.array([])
t_re = np.concatenate(t_all)
y_re = np.concatenate(y_all)
order = np.argsort(t_re)
return t_re[order], y_re[order]
def calibrate_channels(channels, dt_ns, delay_est_ns=None, method="nominal",
tail_frac=0.2, do_baseline=True, do_gain=True,
baseline_known=None):
"""三步校准(基线 → 增益 → 延时)并重建统一时间轴。
参数:
channels acquisition.run_multi_channel 返回的 channels 列表(dict)
dt_ns 采样间隔
delay_est_ns 各通道校准延时(长度=通道数);None 时按 method 选择
method "nominal"(设计延时)/ "cross_corr"(互相关整数粒度)
do_baseline 是否做基线扣除(False → 原始信号直接重建,模拟"不校准")
do_gain 是否做增益归一(False → 不归一)
baseline_known 每通道已知基线(None → 尾段估计;传 0 表示"标定已知无基线")
返回 dict:baselines、gains、delay_used_ns、t_rebuilt、y_rebuilt、
n_points、continuity(相邻点跳变统计)。
"""
n = len(channels)
t_adc = [ch["t_adc"] for ch in channels]
y_meas = [ch["y_samples"] for ch in channels]
# 1) 基线
baselines = []
debased = []
for k, y in enumerate(y_meas):
if not do_baseline:
baselines.append(0.0)
debased.append(np.asarray(y, dtype=float))
elif baseline_known is not None:
b = float(baseline_known[k])
baselines.append(b)
debased.append(np.asarray(y, dtype=float) - b)
else:
d, b = subtract_baseline(y, tail_frac=tail_frac)
baselines.append(b)
debased.append(d)
# 2) 增益归一化(参考通道 = index 0)
ref_peak = float(np.max(np.abs(debased[0]))) if n else 1.0
gains = []
normed = []
for d in debased:
if not do_gain:
gains.append(1.0)
normed.append(d)
else:
g, fact = normalize_gain(d, ref_peak)
gains.append(fact)
normed.append(g)
# 3) 延时
if delay_est_ns is not None:
d_used = [float(v) for v in delay_est_ns]
elif method == "cross_corr":
d_used = [0.0]
for k in range(1, n):
d, _ = estimate_delay_cross_corr(normed[0], normed[k], dt_ns)
d_used.append(d)
else: # nominal:各通道设计延时(含真实误差需另行传入才体现)
d_used = [float(ch["delay_ns"]) for ch in channels]
# 4) 重建
t_re, y_re = rebuild(t_adc, normed, d_used, dt_ns)
return {
"n_channels": n,
"baselines": baselines,
"gains": gains,
"delay_used_ns": d_used,
"t_rebuilt": t_re,
"y_rebuilt": y_re,
"n_points": int(len(t_re)),
"continuity": continuity_metrics(t_re, y_re),
}
def continuity_metrics(t, y):
"""重建曲线不连续度:相邻点归一化跳变的最大/平均统计。"""
t = np.asarray(t, dtype=float)
y = np.asarray(y, dtype=float)
if len(t) < 2:
return {"max_jump": 0.0, "mean_jump": 0.0, "rms_jump": 0.0}
amp = float(np.max(np.abs(y))) if np.max(np.abs(y)) > 0 else 1.0
jumps = np.abs(np.diff(y)) / amp
return {
"max_jump": float(np.max(jumps)),
"mean_jump": float(np.mean(jumps)),
"rms_jump": float(np.sqrt(np.mean(jumps ** 2))),
}

View File

@@ -0,0 +1,88 @@
"""统计分析:蒙特卡洛重复、参数扫描、置信区间、失败率(仅依赖 numpy/scipy)。
对应 docs/实现方案.md §7.6 与 §8。
gen_fn 为可调用对象:gen_fn(seed, **params) -> tau_hat(float),
由调用方(pipeline)注入,保证本模块与具体模型解耦(Pyodide 兼容)。
"""
import numpy as np
def failure_rate(tau_hats, tau_true, tol=0.05):
"""失败率:|τ̂−τ|/τ > tol 的比例。"""
arr = np.asarray(tau_hats, dtype=float)
if tau_true is None or tau_true == 0 or len(arr) == 0:
return 0.0
rel = np.abs(arr - tau_true) / tau_true
return float(np.mean(rel > tol))
def confidence_interval(tau_hats, level=0.95):
"""正态近似置信区间(大样本/教学用);附标准差。"""
arr = np.asarray(tau_hats, dtype=float)
n = len(arr)
if n < 2:
return {"mean": None, "std": None, "ci_lo": None, "ci_hi": None}
mean = float(np.mean(arr))
std = float(np.std(arr, ddof=1))
z = 1.96 if level >= 0.95 else 1.645
return {
"mean": mean,
"std": std,
"ci_lo": float(mean - z * std / np.sqrt(n)),
"ci_hi": float(mean + z * std / np.sqrt(n)),
"level": level,
}
def monte_carlo(gen_fn, repeats=200, seed=0, tau_true=None, tol=0.05):
"""蒙特卡洛重复:不同种子运行 repeats 次,统计 τ̂ 分布。
gen_fn 返回 None 表示本次拟合失败(欠采样/不收敛),计入 n_failed 跳过。
"""
tau_hats = []
n_failed = 0
for i in range(int(repeats)):
v = gen_fn(seed + i)
if v is None:
n_failed += 1
else:
tau_hats.append(float(v))
n_ok = len(tau_hats)
result = {
"n": int(repeats),
"n_ok": n_ok,
"n_failed": n_failed,
"failure_rate_fit": n_failed / int(repeats) if repeats else 0.0,
"tau_hats": tau_hats,
"tau_true": tau_true,
}
if n_ok >= 2:
ci = confidence_interval(tau_hats)
result.update({
"mean": ci["mean"],
"std": ci["std"],
"rel_std": (ci["std"] / ci["mean"]) if ci["mean"] else None,
"ci_lo": ci["ci_lo"],
"ci_hi": ci["ci_hi"],
})
if tau_true is not None:
result["bias"] = (result["mean"] - tau_true) / tau_true
result["failure_rate"] = failure_rate(tau_hats, tau_true, tol)
return result
def sweep(gen_fn, param_name, values, repeats=20, seed=0, tau_true=None, tol=0.05):
"""参数扫描:对每个参数值做蒙特卡洛(小样本),输出趋势表。
返回 [{param, mean, std, rel_std, bias, failure_rate}, ...]。
"""
rows = []
for i, v in enumerate(values):
st = monte_carlo(gen_fn, repeats=repeats, seed=seed + i * 1000,
tau_true=tau_true, tol=tol)
row = {param: float(v)}
for key in ("mean", "std", "rel_std", "bias", "failure_rate", "tau_true"):
row[key] = st.get(key)
rows.append(row)
return {"param": param, "values": [float(v) for v in values], "rows": rows}