|
|
@@ -0,0 +1,112 @@
|
|
|
+#!/usr/bin/env python3
|
|
|
+"""Scan where indicator-diagram cycles actually exist (read-only).
|
|
|
+
|
|
|
+For each point it samples a few files per day *without* an rpm filter (rpm is
|
|
|
+unreliable for wave_file) and checks whether a valid first cycle exists in
|
|
|
+wave_sample_one with a real pressure span. This finds the last data segment
|
|
|
+before a fault, which may be weeks before the repair record.
|
|
|
+"""
|
|
|
+from __future__ import annotations
|
|
|
+
|
|
|
+import argparse
|
|
|
+import sys
|
|
|
+from collections import defaultdict
|
|
|
+from pathlib import Path
|
|
|
+
|
|
|
+import numpy as np
|
|
|
+import pymysql
|
|
|
+
|
|
|
+BACKEND = Path(__file__).resolve().parents[1]
|
|
|
+sys.path.insert(0, str(BACKEND))
|
|
|
+
|
|
|
+from app.config import settings # noqa: E402
|
|
|
+
|
|
|
+CYLINDERS = ("一", "二", "三", "四", "五", "六")
|
|
|
+SIDES = ("盖侧", "轴侧")
|
|
|
+MIN_SPAN = 0.3
|
|
|
+
|
|
|
+
|
|
|
+def connect():
|
|
|
+ return pymysql.connect(
|
|
|
+ host=settings.db_host, port=settings.db_port, user=settings.db_user,
|
|
|
+ password=settings.db_password, database=settings.db_name, charset="utf8mb4",
|
|
|
+ cursorclass=pymysql.cursors.DictCursor, connect_timeout=8, read_timeout=300,
|
|
|
+ )
|
|
|
+
|
|
|
+
|
|
|
+def point_name(unit, cylinder, side):
|
|
|
+ return f"{unit}号机组{cylinder}缸压力{side}"
|
|
|
+
|
|
|
+
|
|
|
+def sample_per_day(rows, per_day):
|
|
|
+ by_day = defaultdict(list)
|
|
|
+ for row in rows:
|
|
|
+ by_day[row["sample_time"].date()].append(row)
|
|
|
+ picked = []
|
|
|
+ for day in sorted(by_day):
|
|
|
+ day_rows = by_day[day]
|
|
|
+ if len(day_rows) <= per_day:
|
|
|
+ picked.extend(day_rows)
|
|
|
+ else:
|
|
|
+ idx = np.linspace(0, len(day_rows) - 1, per_day).round().astype(int)
|
|
|
+ picked.extend(day_rows[int(i)] for i in idx)
|
|
|
+ return picked
|
|
|
+
|
|
|
+
|
|
|
+def spans(connection, file_ids):
|
|
|
+ """Median pressure span of wave_sample_one per file_id."""
|
|
|
+ result = {}
|
|
|
+ with connection.cursor() as cursor:
|
|
|
+ for start in range(0, len(file_ids), 200):
|
|
|
+ chunk = file_ids[start:start + 200]
|
|
|
+ ph = ", ".join(["%s"] * len(chunk))
|
|
|
+ cursor.execute(
|
|
|
+ f"SELECT wave_file_id, COUNT(*) n, MIN(signal_value) mn, MAX(signal_value) mx "
|
|
|
+ f"FROM wave_sample_one WHERE wave_file_id IN ({ph}) GROUP BY wave_file_id",
|
|
|
+ tuple(chunk),
|
|
|
+ )
|
|
|
+ for row in cursor.fetchall():
|
|
|
+ mn, mx = row["mn"], row["mx"]
|
|
|
+ result[int(row["wave_file_id"])] = float(mx) - float(mn) if mn is not None and mx is not None else 0.0
|
|
|
+ return result
|
|
|
+
|
|
|
+
|
|
|
+def main():
|
|
|
+ parser = argparse.ArgumentParser(description="扫描功图周期实际存在的日期")
|
|
|
+ parser.add_argument("--unit", required=True, choices=("7", "8", "9"))
|
|
|
+ parser.add_argument("--cylinders", nargs="+", default=list(CYLINDERS), choices=CYLINDERS)
|
|
|
+ parser.add_argument("--sides", nargs="+", default=["盖侧"], choices=SIDES)
|
|
|
+ parser.add_argument("--start", required=True)
|
|
|
+ parser.add_argument("--end", required=True)
|
|
|
+ parser.add_argument("--per-day", type=int, default=2)
|
|
|
+ args = parser.parse_args()
|
|
|
+
|
|
|
+ connection = connect()
|
|
|
+ try:
|
|
|
+ for cylinder in args.cylinders:
|
|
|
+ for side in args.sides:
|
|
|
+ point = point_name(args.unit, cylinder, side)
|
|
|
+ with connection.cursor() as cursor:
|
|
|
+ cursor.execute(
|
|
|
+ "SELECT id, sample_time FROM wave_file WHERE point_name=%s AND measurement_type='压力' "
|
|
|
+ "AND sample_time >= %s AND sample_time < %s ORDER BY sample_time",
|
|
|
+ (point, args.start, args.end),
|
|
|
+ )
|
|
|
+ files = list(cursor.fetchall())
|
|
|
+ picked = sample_per_day(files, args.per_day)
|
|
|
+ span_by_id = spans(connection, [int(r["id"]) for r in picked])
|
|
|
+ by_day = defaultdict(list)
|
|
|
+ for row in picked:
|
|
|
+ by_day[row["sample_time"].date()].append(span_by_id.get(int(row["id"]), 0.0))
|
|
|
+ valid_days = [d for d, v in sorted(by_day.items()) if np.median(v) >= MIN_SPAN and len(span_by_id)]
|
|
|
+ all_days = sorted(by_day)
|
|
|
+ print(f"{point}: 文件 {len(files)}，抽样日 {len(all_days)}，其中有效日 {len(valid_days)}")
|
|
|
+ if valid_days:
|
|
|
+ print(f" 有效数据段: {valid_days[0]} ~ {valid_days[-1]} 共 {len(valid_days)} 天")
|
|
|
+ print(" 有效日:", ", ".join(str(d) for d in valid_days))
|
|
|
+ finally:
|
|
|
+ connection.close()
|
|
|
+
|
|
|
+
|
|
|
+if __name__ == "__main__":
|
|
|
+ main()
|
