WTOAAM/dataAnalysisBusiness/algorithm/faultAnalyst.py

import pandas as pd
import os
import plotly.graph_objects as go
from algorithmContract.confBusiness import *
from algorithmContract.contract import Contract
from behavior.analystNotFilter import AnalystNotFilter
from plotly.subplots import make_subplots

class FaultAnalyst(AnalystNotFilter):
    """
    风电机组故障分析
    """

    def typeAnalyst(self):
        return "fault"
    def selectColumns(self):
        return [Field_DeviceName,Field_FaultTime,Field_FaultDetail]


    def turbinesAnalysis(self,outputAnalysisDir, conf: Contract, turbineCodes):
        dictionary = self.processTurbineData(turbineCodes,conf,self.selectColumns())
        dataFrameMerge = self.userDataFrame(dictionary,conf.dataContract.configAnalysis,self)
        return self.get_result(dataFrameMerge, outputAnalysisDir, conf)

    def get_result(self, dataFrame: pd.DataFrame, outputAnalysisDir: str, conf: Contract):
        #---------------整个风场维度统计故障时长与次数---------------------------
        # 统计各种类型故障出现的次数
        fault_detail_count = dataFrame[Field_FaultDetail].value_counts().reset_index()
        fault_detail_count.columns = [Field_FaultDetail, 'count']

        # 统计每个 fault_detail 的时长加和
        fault_time_sum = dataFrame.groupby(Field_FaultDetail)[Field_FaultTime].sum().reset_index()
        fault_time_sum.columns = [Field_FaultDetail, 'fault_time_sum']

        # 合并两个 DataFrame
        fault_summary = pd.merge(fault_detail_count, fault_time_sum, on=Field_FaultDetail, how='inner')
        fault_summary_sorted = fault_summary.sort_values(by='fault_time_sum', ascending=False)

        # -------------按风机分组统计故障情况------------------------------------------
        grouped = dataFrame.groupby(Field_DeviceName)
        results= []

        for name, group in grouped:
            turbine_fault_summary = pd.DataFrame({
                Field_DeviceName: [name],
                'count': [len(group)],
                'fault_time': [group[Field_FaultTime].sum()]
            })
            results.append(turbine_fault_summary)

        # 合并所有风机的故障统计结果
        turbine_fault_summary = pd.concat(results, ignore_index=True)
        turbine_fault_sorted = turbine_fault_summary.sort_values(by='fault_time', ascending=False)
        # 故障类型前十名
        draw_results=turbine_fault_sorted.head(10)
        # 保存结果
        result_rows = []

        filePathOfturbinefault = os.path.join(outputAnalysisDir, f"turbine_fault_result{CSVSuffix}")
        turbine_fault_sorted.to_csv(filePathOfturbinefault, index=False,encoding='utf-8-sig')

        result_rows.append({
            Field_Return_TypeAnalyst: self.typeAnalyst(),
            Field_PowerFarmCode: conf.dataContract.dataFilter.powerFarmID,
            Field_Return_BatchCode: conf.dataContract.dataFilter.dataBatchNum,
            Field_CodeOfTurbine: "total",
            Field_Return_FilePath: filePathOfturbinefault,
            Field_Return_IsSaveDatabase: True
        })

        filePathOftotalfault = os.path.join(outputAnalysisDir, f"total_fault_result{CSVSuffix}")
        fault_summary_sorted.to_csv(filePathOftotalfault, index=False,encoding='utf-8-sig')

        result_rows.append({
            Field_Return_TypeAnalyst: self.typeAnalyst(),
            Field_PowerFarmCode: conf.dataContract.dataFilter.powerFarmID,
            Field_Return_BatchCode: conf.dataContract.dataFilter.dataBatchNum,
            Field_CodeOfTurbine: "total",
            Field_Return_FilePath: filePathOftotalfault,
            Field_Return_IsSaveDatabase: True
        })
        result_df = pd.DataFrame(result_rows)
        return result_df