add API doc

README.md

@@ -0,0 +1,102 @@
+# 污染物排放动态监测接口文档
+## 接口文档
+### Docker服务地址
+`124.16.151.196:8788/emission/`
+### 输入
+输入为json串，具体内容如下：
+```
+{
+    "key": "xxxx",
+    "data":{
+        "time": "",
+        "boiler": "",
+        ...  //以下省略
+    }
+}
+```
+其中`key`字段可用于并发时确认请求来源，`data`字段为传入的机组和排放参数，具体如下：
+|字段|类型|含义|是否由爬虫获取|
+|----|----|----|----|
+|time|str|时间，'yyyy-mm-dd hh:MM:ss'|是|
+|boiler|str|锅炉类型|否|
+|steam|str|汽轮机类型|否|
+|cold|str|冷却方式|否|
+|pressure|str|压力参数|否|
+|nox|float|氮氧化物($NO_x$)浓度数值($mg/m^3$)|是|
+|so2|float|二氧化硫($SO_2$)浓度数值($mg/m^3$)|是|
+|smoke|float|烟气浓度($mg/m^3$)|是|
+|flow|float|烟气流量($m^3/h$)|是|
+|o2|float|含氧量($O_2$, %)|是|
+|temp|float|温度(℃)|是|
+|evaporation|float|机组额定蒸发量(t/h)|否|
+|caloric|float|低位发热值(一般为10-30 GJ/t)|视情况而定|
+|lon|str|经度|否|
+|lat|str|纬度|否|
+
+### 输出
+输出为json串，包含如下字段
+```
+{
+    "code": 200,
+    "request_key": "xxxx",
+    "data": {...}    
+}
+```
+其中`key`字段可用于并发时确认请求来源，data字段对应模型返回的当前时刻的结果，具体如下：
+|字段|类型|含义|
+|----|----|----|
+|coal|float|该时刻对应的煤耗(t)|
+|co|float|一氧化碳排放量(kg)|
+|co2|float|二氧化碳排放量(kg)|
+|vocs|float|VOCs排放量(kg)|
+|pm25|float|PM2.5排放量(kg)|
+|pm10|float|PM10排放量(kg)|
+
+## 示例
+### 输入示例
+```
+{
+    "key": "123456",
+    "data": {
+        "time": "2023-01-02 03:04:05",
+        "boiler": "循环流化床锅炉",
+        "steam": "凝气式",
+        "cold": "水冷-开式循环",
+        "pressure": "超超临界",
+        "nox": "12",
+        "so2": "0.15",
+        "smoke": "12",
+        "flow": "5000000",
+        "o2": "23",
+        "temp": "55",
+        "evaporation": "123",
+        "caloric": "23",
+        "capacity": "234",
+        "lon": "122",
+        "lat": "33"
+    }
+}
+```
+### 输出示例（调用成功）
+```
+{
+    "code": 200,
+    "key": "123456",
+    "data": {
+        "coal": 31.213128645837465,
+        "co": 62.42625729167493,
+        "vocs": 67.42035787500893,
+        "pm25": 0.72,
+        "pm10": 2.7600000000000002,
+        "co2": 65.24910397752144
+    }
+}
+```
+### 输出示例（调用失败）
+```
+{
+    "code": 406,
+    "key": "123456",
+    "msg": "Input is None, please check!"
+}
+```

config/emission_factor.json

@@ -1,26 +1,26 @@
 {
-    "CO":{
+    "co":{
         "煤粉": 2,
         "循环流化床": 2,
         "自动炉排层燃炉": 15,
         "手动炉排层燃炉 ": 124.3,
         "default": 2
     },
-    "VOCs":{
+    "vocs":{
         "煤粉": 2.16,
         "循环流化床": 2.16,
         "自动炉排层燃炉": 2.16,
         "手动炉排层燃炉 ": 4.53,
         "default": 2.16
     },
-    "PM25":{
+    "pm25":{
         "煤粉": 0.06,
         "循环流化床": 0.07,
         "自动炉排层燃炉": 0.1,
         "手动炉排层燃炉 ": 0.07,
         "default": 0.06
     },
-    "PM10":{
+    "pm10":{
         "煤粉": 0.23,
         "循环流化床": 0.29,
         "自动炉排层燃炉": 0.3,

models/lgb_predict.py

@@ -28,18 +28,18 @@ def cal_coal_cost_emission(coal_cost, boiler, emission_factors):
     else:
         return emission_factors.get("default") * coal_cost
 
-def cal_PM(r_smoke, boiler, emission_factors):
+def cal_PM(c_smoke, boiler, emission_factors):
     factor = emission_factors.get(boiler)
     if factor is not None:
-        return r_smoke * factor
+        return c_smoke * factor / 1e6
     else:
-        return emission_factors.get("default") * r_smoke
+        return emission_factors.get("default") * c_smoke / 1e6
 
 def predict(his_data, input_data, model:lgb.Booster, object_cols, emission_factors):
     feature_names = model.feature_name()
     date = dt.datetime.strptime(input_data.get('time'), '%Y-%m-%d %H:%M:%S')
-    r_NOx = float(input_data.get('NOx'))
+    r_NOx = float(input_data.get('nox'))
-    r_SO2 = float(input_data.get('SO2'))
+    r_SO2 = float(input_data.get('so2'))
     r_smoke = float(input_data.get('smoke'))
     flow = float(input_data.get('flow'))
     c_NOx, c_SO2, c_smoke = flow * np.asarray([r_NOx, r_SO2, r_smoke])
@@ -61,7 +61,7 @@ def predict(his_data, input_data, model:lgb.Booster, object_cols, emission_facto
         "0_c_SO2": np.log1p(float(c_SO2)),
         "0_c_smoke": np.log1p(float(c_smoke)),
         "0_flow": np.log1p(float(flow)),
-        "0_O2": np.log1p(float(input_data.get("O2"))),
+        "0_O2": np.log1p(float(input_data.get("o2"))),
         "0_temp": np.log1p(float(input_data.get("temp"))),
         "额定蒸发量_t/h": np.log1p(float(input_data.get("evaporation"))),
         "低位发热量": np.log1p(caloric),
@@ -74,10 +74,10 @@ def predict(his_data, input_data, model:lgb.Booster, object_cols, emission_facto
     new_inputs = pd.get_dummies(total_data, columns=object_cols)
     new_inputs = new_inputs[feature_names].iloc[-1].values
     coal_cost = np.expm1(model.predict([new_inputs])[0])
-    co = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('CO'))
+    co = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('co'))
-    vocs = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('VOCs'))
+    vocs = cal_coal_cost_emission(coal_cost, input_data.get('boiler'), emission_factors.get('vocs'))
-    pm25 = cal_PM(r_smoke, input_data.get('boiler'), emission_factors.get('PM25'))
+    pm25 = cal_PM(c_smoke, input_data.get('boiler'), emission_factors.get('pm25'))
-    pm10 = cal_PM(r_smoke, input_data.get('boiler'), emission_factors.get('PM10'))
+    pm10 = cal_PM(c_smoke, input_data.get('boiler'), emission_factors.get('pm10'))
     co2 = cal_CO2(coal_cost, caloric)
     return {'coal': coal_cost, 'co':co, 'vocs':vocs, 'pm25':pm25, 'pm10':pm10, 'co2':co2}
 
@@ -93,11 +93,11 @@ if __name__ == '__main__':
         "steam": "凝气式",
         "cold": "水冷-开式循环",
         "pressure": "超超临界",
-        "NOx": "12",
+        "nox": "12",
-        "SO2":"0.15",
+        "so2":"0.15",
         "smoke":"12",
         "flow":"5000000",
-        "O2": "23",
+        "o2": "23",
         "temp": "55",
         "evaporation": "123",
         "caloric": "23",

run.py

@@ -24,20 +24,25 @@ def run_case_check():
     resp_info = dict()
     if request.method == "POST":
         data = request.json.get('data')
+        key = request.json.get('key')
+        resp_info['key'] = key
+        logger.info("request key: {key}")
         logger.info(data)
         if data is not None and len(data) != 0:
-            rst = predict(history_data, data, lgb_model, object_cols, emission_factors)
+            try:
-            resp_info["code"] = 200
+                rst = predict(history_data, data, lgb_model, object_cols, emission_factors)
-            resp_info["data"] = rst
+                resp_info["code"] = 200
+                resp_info["data"] = rst
+            except Exception as e:
+                resp_info["code"] = 406
+                resp_info["data"] = str(e)
         else:
-            resp_info["msg"] = "Input is None, please check !"
+            resp_info["msg"] = "Input is None, please check!"
             resp_info["code"] = 406
     resp = make_response(json.dumps(resp_info))
     resp.status_code = 200
     return resp
 
 
-
-
 if __name__ == '__main__':
     app.run(host='0.0.0.0', port=8788, debug=False)