|
|
@@ -0,0 +1,153 @@
|
|
|
+#!/usr/bin/env python3
|
|
|
+"""Look back over the previous 1-2 valid data segments before each event.
|
|
|
+
|
|
|
+Many repairs have no data immediately before them (machine stopped long before
|
|
|
+the repair was recorded). This groups the days that actually contain an
|
|
|
+indicator cycle into segments and inspects the last one or two segments before
|
|
|
+the event: peer-relative levels and within-segment drift, plus a comparison
|
|
|
+between the two segments to expose a per-cylinder divergence. Read-only.
|
|
|
+"""
|
|
|
+from __future__ import annotations
|
|
|
+
|
|
|
+import argparse
|
|
|
+import csv
|
|
|
+from collections import defaultdict
|
|
|
+from datetime import datetime
|
|
|
+from pathlib import Path
|
|
|
+
|
|
|
+import numpy as np
|
|
|
+
|
|
|
+EVENTS = [
|
|
|
+ ("7", "2025-01-10", "活塞"),
|
|
|
+ ("7", "2025-08-08", "气阀"),
|
|
|
+ ("7", "2025-10-07", "气阀"),
|
|
|
+ ("7", "2026-05-21", "气阀"),
|
|
|
+ ("8", "2025-02-17", "气阀"),
|
|
|
+ ("8", "2025-12-06", "活塞"),
|
|
|
+ ("8", "2026-03-10", "十字头"),
|
|
|
+ ("8", "2026-03-29", "气阀"),
|
|
|
+ ("8", "2026-04-01", "气阀"),
|
|
|
+ ("9", "2026-01-18", "活塞"),
|
|
|
+]
|
|
|
+CYLINDERS = ("一", "二", "三", "四", "五", "六")
|
|
|
+SIDES = ("盖侧", "轴侧")
|
|
|
+FEATURES = ("p_discharge", "pressure_ratio", "efficiency")
|
|
|
+
|
|
|
+
|
|
|
+def load(path):
|
|
|
+ rows = []
|
|
|
+ for row in csv.DictReader(open(path, encoding="utf-8-sig")):
|
|
|
+ row["day"] = row["sample_time"][:10]
|
|
|
+ for name in FEATURES:
|
|
|
+ try:
|
|
|
+ row[name] = float(row[name])
|
|
|
+ except (TypeError, ValueError):
|
|
|
+ row[name] = None
|
|
|
+ rows.append(row)
|
|
|
+ return rows
|
|
|
+
|
|
|
+
|
|
|
+def segments(days, gap=10):
|
|
|
+ days = sorted(set(days))
|
|
|
+ out = []
|
|
|
+ for day in days:
|
|
|
+ if out and (datetime.strptime(day, "%Y-%m-%d") - datetime.strptime(out[-1][-1], "%Y-%m-%d")).days <= gap:
|
|
|
+ out[-1].append(day)
|
|
|
+ else:
|
|
|
+ out.append([day])
|
|
|
+ return out
|
|
|
+
|
|
|
+
|
|
|
+def peer_relative(rows, feature):
|
|
|
+ by_ts = defaultdict(dict)
|
|
|
+ for row in rows:
|
|
|
+ if row[feature] is not None:
|
|
|
+ by_ts[(row["day"], row["side"])][row["cylinder"]] = row[feature]
|
|
|
+ out = defaultdict(dict)
|
|
|
+ for (day, side), members in by_ts.items():
|
|
|
+ clean = {c: v for c, v in members.items() if v is not None}
|
|
|
+ if len(clean) < 2:
|
|
|
+ continue
|
|
|
+ med = float(np.median(list(clean.values())))
|
|
|
+ if abs(med) < 1e-9:
|
|
|
+ continue
|
|
|
+ for cylinder, value in clean.items():
|
|
|
+ out[(cylinder, side)][day] = (value - med) / med
|
|
|
+ return out
|
|
|
+
|
|
|
+
|
|
|
+def seg_summary(rows, seg):
|
|
|
+ seg_rows = [r for r in rows if r["day"] in set(seg)]
|
|
|
+ peer = {feature: peer_relative(seg_rows, feature) for feature in ("p_discharge", "pressure_ratio")}
|
|
|
+ summary = {}
|
|
|
+ drift = {}
|
|
|
+ for feature, series in peer.items():
|
|
|
+ for key, daily in series.items():
|
|
|
+ summary[(key[0], key[1], feature)] = (float(np.median(list(daily.values()))), len(daily))
|
|
|
+ days = sorted(daily)
|
|
|
+ if len(days) >= 8:
|
|
|
+ x = np.array([(datetime.strptime(d, "%Y-%m-%d") - datetime.strptime(days[0], "%Y-%m-%d")).days for d in days], dtype=float)
|
|
|
+ y = np.array([daily[d] for d in days], dtype=float)
|
|
|
+ if x[-1] > 0:
|
|
|
+ slope = float(np.polyfit(x, y, 1)[0])
|
|
|
+ scale = float(np.median(np.abs(y - np.median(y)))) * 1.4826 or float(np.std(y))
|
|
|
+ if scale > 1e-9:
|
|
|
+ drift[(key[0], key[1], feature)] = float(slope * x[-1] / scale) # total drift in MADs
|
|
|
+ return summary, drift
|
|
|
+
|
|
|
+
|
|
|
+def main():
|
|
|
+ parser = argparse.ArgumentParser(description="事件前 1~2 个有效数据段观察")
|
|
|
+ parser.add_argument("--data-dir", default=str(Path(__file__).resolve().parents[1] / "cache" / "indicator"))
|
|
|
+ parser.add_argument("--segments", type=int, default=2)
|
|
|
+ args = parser.parse_args()
|
|
|
+
|
|
|
+ cache = {}
|
|
|
+ for unit in ("7", "8", "9"):
|
|
|
+ path = Path(args.data_dir) / f"all_{unit}_2025_2026.csv"
|
|
|
+ cache[unit] = load(path) if path.is_file() else []
|
|
|
+
|
|
|
+ for unit, date, kind in EVENTS:
|
|
|
+ rows = cache[unit]
|
|
|
+ all_days = sorted({r["day"] for r in rows})
|
|
|
+ segs = [s for s in segments(all_days) if s[-1] < date]
|
|
|
+ print(f"\n== {unit}号机 {date} {kind} 事件前有效段 {len(segs)}，取最近 {args.segments}")
|
|
|
+ chosen = segs[-args.segments:]
|
|
|
+ summaries = []
|
|
|
+ for i, seg in enumerate(reversed(chosen), start=1):
|
|
|
+ summary, drift = seg_summary(rows, seg)
|
|
|
+ summaries.append((seg, summary))
|
|
|
+ print(f" 段{i} {seg[0]}~{seg[-1]} ({len(seg)}天) peer相对 p_discharge | pressure_ratio")
|
|
|
+ for cylinder in CYLINDERS:
|
|
|
+ cells = []
|
|
|
+ for side in SIDES:
|
|
|
+ pd = summary.get((cylinder, side, "p_discharge"))
|
|
|
+ pr = summary.get((cylinder, side, "pressure_ratio"))
|
|
|
+ if pd is None and pr is None:
|
|
|
+ continue
|
|
|
+ pd_s = f"{pd[0]*100:+.0f}%" if pd else "-"
|
|
|
+ pr_s = f"{pr[0]*100:+.0f}%" if pr else "-"
|
|
|
+ cells.append(f"{side}:Pd{pd_s}/R{pr_s}")
|
|
|
+ if cells:
|
|
|
+ print(f" {cylinder}缸 " + " ".join(cells))
|
|
|
+ strong = [(k, v) for k, v in sorted(drift.items(), key=lambda kv: -abs(kv[1])) if abs(v) >= 2.0][:4]
|
|
|
+ if strong:
|
|
|
+ print(" 段内漂移(>=2MAD): " + "; ".join(f"{k[0]}缸{k[1]} {k[2]} {v:+.1f}" for k, v in strong))
|
|
|
+ if len(summaries) == 2:
|
|
|
+ (seg_prev, sum_prev), (seg_last, sum_last) = summaries[1], summaries[0]
|
|
|
+ changes = []
|
|
|
+ for key in set(sum_prev) & set(sum_last):
|
|
|
+ cylinder, side, feature = key
|
|
|
+ delta = sum_last[key][0] - sum_prev[key][0]
|
|
|
+ # only peer-relative, ignore tiny absolute
|
|
|
+ if abs(delta) >= 0.05:
|
|
|
+ changes.append((abs(delta), f"{cylinder}缸{side} {feature}: {sum_prev[key][0]*100:+.1f}% -> {sum_last[key][0]*100:+.1f}%"))
|
|
|
+ changes.sort(reverse=True)
|
|
|
+ if changes:
|
|
|
+ print(" 两段对比（变化>=5%）：")
|
|
|
+ for _, text in changes[:6]:
|
|
|
+ print(" " + text)
|
|
|
+
|
|
|
+
|
|
|
+if __name__ == "__main__":
|
|
|
+ main()
|
