CN115204669A - Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data - Google Patents

Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data Download PDF

Info

Publication number
CN115204669A
CN115204669A CN202210825017.5A CN202210825017A CN115204669A CN 115204669 A CN115204669 A CN 115204669A CN 202210825017 A CN202210825017 A CN 202210825017A CN 115204669 A CN115204669 A CN 115204669A
Authority
CN
China
Prior art keywords
data
sewage treatment
treatment plant
behavior
abnormal
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Pending
Application number
CN202210825017.5A
Other languages
Chinese (zh)
Inventor
魏阳
常晓青
徐厚东
唐伟
张凌浩
陈玉敏
严磊
蒙浩东
唐勇
李赋欣
刘洪利
刘雪原
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd
Original Assignee
Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd filed Critical Electric Power Research Institute of State Grid Sichuan Electric Power Co Ltd
Priority to CN202210825017.5A priority Critical patent/CN115204669A/en
Publication of CN115204669A publication Critical patent/CN115204669A/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
    • G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/21—Design, administration or maintenance of databases
    • G06F16/215—Improving data quality; Data cleansing, e.g. de-duplication, removing invalid entries or correcting typographical errors
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/10—Services
    • G06Q50/26—Government or public services

Landscapes

  • Business, Economics & Management (AREA)
  • Engineering & Computer Science (AREA)
  • Human Resources & Organizations (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Tourism & Hospitality (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Strategic Management (AREA)
  • Marketing (AREA)
  • General Business, Economics & Management (AREA)
  • Databases & Information Systems (AREA)
  • Quality & Reliability (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Data Mining & Analysis (AREA)
  • General Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Game Theory and Decision Science (AREA)
  • Operations Research (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)
  • Testing And Monitoring For Control Systems (AREA)

Abstract

The invention discloses a sewage treatment plant behavior abnormity judgment method and system based on electricity consumption data, and relates to the field of sewage treatment monitoring, wherein the judgment method comprises the following steps: acquiring historical data in a sewage treatment plant to be monitored, and performing data cleaning on the historical data to obtain historical cleaning data; calculating the weight coefficient of each index in the historical cleaning data, and selecting three indexes with the maximum weight coefficient as behavior indexes; constructing a behavior abnormity judgment model according to the behavior indexes; according to the judgment result of the behavior abnormity judgment model, the credibility index of the behavior abnormity judgment is established to obtain the credibility of the behavior abnormity judgment, so that the accuracy of the judgment result is improved, the behavior abnormity condition of the sewage treatment plant is mastered according to the electricity utilization condition of the sewage treatment plant, the situation of one operation is avoided, and the refinement level of monitoring is improved.

Description

基于用电数据的污水处理厂行为异常判定方法及系统Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data

技术领域technical field

本发明涉及污水处理监测，具体涉及基于用电数据的污水处理厂行为异常判定方法及系统。The invention relates to sewage treatment monitoring, in particular to a method and system for judging abnormal behavior of a sewage treatment plant based on electricity consumption data.

背景技术Background technique

随着城镇化建设进一步加快，乡镇环境污染问题日益突出，乡镇污水处理厂的有效运行是乡镇可持续发展的重要保障。With the further acceleration of urbanization, the problem of environmental pollution in townships has become increasingly prominent. The effective operation of township sewage treatment plants is an important guarantee for the sustainable development of townships.

现有污水处理厂异常运行判定方法“一刀切”，存在较大的局限性，仅考虑污水处理厂本身规模、处理工艺或全年污水处理总量等，对用电异常的污水处理厂无法辨识，无法根据污水处理厂的用电状况对异常运行情况进行判别，且结果准确性不高；由于不同区域、不同规模的污水处理厂用电习惯存在差异，部分污水处理厂存在不确定因素，导致异常运行的污水处理厂的用电特性有所差异，不能根据不同实际规模下的污水处理厂的用电水平、用电状况给出异常运行的临界值，实现对污水处理厂异常行为的准确判定。The existing method for judging abnormal operation of sewage treatment plants is "one size fits all", which has great limitations. Only considering the scale of the sewage treatment plant itself, the treatment process or the total amount of sewage treatment in the whole year, etc., it is impossible to identify sewage treatment plants with abnormal electricity consumption. It is impossible to judge the abnormal operation according to the electricity consumption of the sewage treatment plant, and the accuracy of the results is not high; due to the differences in the electricity consumption habits of sewage treatment plants of different regions and scales, some sewage treatment plants have uncertain factors, resulting in abnormal The power consumption characteristics of the operating sewage treatment plants are different, and the critical value of abnormal operation cannot be given according to the power consumption level and power consumption status of the sewage treatment plants under different actual scales, so as to accurately determine the abnormal behavior of the sewage treatment plant.

发明内容SUMMARY OF THE INVENTION

本发明所要解决的技术问题是提高判断污水处理厂运行异常的准确性，提高监测监管的精细化水平，目的在于提供基于用电数据的污水处理厂行为异常判定方法及系统，解决了传统判断污水处理厂运行异常的局限性，无法准确判断污水处理厂运行异常的问题。The technical problem to be solved by the present invention is to improve the accuracy of judging the abnormal operation of the sewage treatment plant, and improve the level of refinement of monitoring and supervision. Due to the limitations of abnormal operation of the treatment plant, it is impossible to accurately judge the abnormal operation of the sewage treatment plant.

本发明通过下述技术方案实现：The present invention is achieved through the following technical solutions:

第一方面提供基于用电数据的污水处理厂行为异常判定方法，包括以下步骤：The first aspect provides a method for judging abnormal behavior of a sewage treatment plant based on electricity consumption data, including the following steps:

获取待监测污水处理厂中的历史数据，将上述历史数据进行数据清洗，得到历史清洗数据；Obtain historical data in the sewage treatment plant to be monitored, perform data cleaning on the above historical data, and obtain historical cleaning data;

计算上述历史清洗数据中各指标的权重系数，选择权重系数最大的三个指标作为行为指标；Calculate the weight coefficients of each indicator in the above historical cleaning data, and select the three indicators with the largest weight coefficients as behavior indicators;

根据上述行为指标，构建行为异常判定模型；According to the above behavior indicators, construct a behavior abnormality judgment model;

根据上述行为异常判定模型的判定结果，建立行为异常判定的可信度指标，得到行为异常判定可信度。According to the judgment result of the above behavior abnormality judgment model, the reliability index of behavior abnormality judgment is established, and the reliability of behavior abnormality judgment is obtained.

根据上述污水处理厂的实际情况对各指标进行重要性分析，选择影响该污水处理厂行为异常较大的指标作为行为指标建立行为异常判定模型，根据该污水处理厂行为异常的严重程度，计算判定结果的可信度，实现对该污水处理厂行为异常情况的精准评估。According to the actual situation of the above sewage treatment plant, the importance of each index is analyzed, and the index that greatly affects the abnormal behavior of the sewage treatment plant is selected as the behavior index to establish a behavior abnormality judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the calculation and judgment The reliability of the results enables an accurate assessment of the abnormal behavior of the sewage treatment plant.

进一步的，上述各指标包括实际处理规模、全年污水处理总量、污水处理工艺、全年污水处理率、设计处理规模、累计完成污水管网长度、排放标准和建设运营状态。Further, the above indicators include the actual treatment scale, the total amount of sewage treatment in the year, the sewage treatment process, the annual sewage treatment rate, the designed treatment scale, the cumulative length of the sewage pipe network, the discharge standard and the construction and operation status.

进一步的，上述历史数据包括日用电量数据和每日的示值数据，对上述历史数据中的日用电量数据进行数据清洗包括步骤：Further, the above-mentioned historical data includes daily electricity consumption data and daily indication data, and performing data cleaning on the daily electricity consumption data in the above-mentioned historical data includes the steps:

判断上述日用电量数据是否存在缺失数据；Determine whether the above daily electricity consumption data has missing data;

若存在缺失数据，则对上述缺失数据进行标记，并获取当日示值数据，判断上述当日示值数据是否缺失，If there is missing data, mark the above-mentioned missing data, obtain the indication data of the day, and judge whether the above-mentioned indication data of the day is missing.

若上述当日示值数据缺失，则计算与上述日用电量数据相邻天数的日用电量数据均值，将上述均值记录于标记处，对上述缺失数据进行补齐，再返回上述判断日用电量数据是否存在缺失数据继续执行；If the indicated data on the current day is missing, calculate the average value of the daily electricity consumption data of the days adjacent to the above daily electricity consumption data, record the above average value at the mark, make up for the above-mentioned missing data, and then return to the above-mentioned judgment of daily electricity consumption. Continue to execute if there is missing data in the power data;

若上述当日示值数据未缺失，则计算上述当日示值数据的差值，将上述差值记录于标记处，对上述缺失数据进行补齐，再返回上述判断日用电量数据是否存在缺失数据继续执行；If the above-mentioned indication data of the current day is not missing, calculate the difference of the above-mentioned indication data of the day, record the above-mentioned difference at the mark, complete the above-mentioned missing data, and then return to the above-mentioned judgment whether there is any missing data in the daily electricity consumption data continue to execute;

若不存在缺失数据，则得到历史清洗数据。If there is no missing data, historical cleaning data is obtained.

根据上述历史数据中的日用电量数据掌握上述污水处理厂行为异常时的用电状态，避免一刀切，提高监测的精细化水平，对上述日用电量数据进行数据清洗，修正和补齐日用电量数据，提高了指标权重系数的精度，进而提高了判定结果的准确性。According to the daily electricity consumption data in the above historical data, we can grasp the electricity consumption status of the above-mentioned sewage treatment plants when the behavior is abnormal, avoid one-size-fits-all, improve the level of refinement of monitoring, clean the above daily electricity consumption data, correct and supplement the daily electricity consumption data. The power consumption data improves the accuracy of the index weight coefficient, thereby improving the accuracy of the judgment result.

进一步的，在计算上述历史清洗数据中各指标的权重系数之前，还需要修正或补齐实际处理规模的数据、全年污水处理总量的数据，包括以下步骤：Further, before calculating the weight coefficient of each indicator in the above-mentioned historical cleaning data, it is also necessary to correct or supplement the data of the actual treatment scale and the data of the total amount of sewage treatment throughout the year, including the following steps:

判断全年污水处理总量与实际处理规模是否满足条件，上述条件为：To judge whether the total amount of sewage treatment and the actual treatment scale of the whole year meet the conditions, the above conditions are:

Si×365＜Wi×0.8或Si×365＞Wi×1.2S i ×365<W i ×0.8 or S i ×365>W i ×1.2

其中，Si表示第i家污水处理厂的实际处理规模数据，Wi代表第i家污水处理厂的全年污水处理总量数据；Among them, Si represents the actual treatment scale data of the ith sewage treatment plant, and Wi represents the annual total sewage treatment data of the ith sewage treatment plant;

若Si和Wi有解，满足上述条件，则根据

Figure BDA0003746128580000021
修改上述实际处理规模数据；If there is a solution for Si and Wi , and the above conditions are satisfied, then according to
Figure BDA0003746128580000021
Modify the above-mentioned actual processing scale data;

若Si或Wi无解，不满足上述条件，则根据

Figure BDA0003746128580000022
补齐相应的上述实际处理规模数据或全年污水处理总量数据。If there is no solution for Si or Wi , and the above conditions are not met, then according to
Figure BDA0003746128580000022
Complete the corresponding data on the actual treatment scale above or the total annual sewage treatment data.

进一步的，根据上述各指标的权重系数，计算相对隶属度，对各指标进行权重排序，选择三个权重系数较大的指标作为行为指标。Further, according to the weight coefficients of the above indicators, the relative membership degree is calculated, the weights of the indicators are sorted, and three indicators with larger weight coefficients are selected as the behavior indicators.

进一步的，根据上述各指标的权重系数，计算相对隶属度，具体公式如下：Further, according to the weight coefficients of the above indicators, the relative membership degree is calculated, and the specific formula is as follows:

Figure BDA0003746128580000031
Figure BDA0003746128580000031

其中，in,

Figure BDA0003746128580000032
Figure BDA0003746128580000032

Figure BDA0003746128580000033
Figure BDA0003746128580000033

Figure BDA0003746128580000034
Figure BDA0003746128580000034

Figure BDA0003746128580000035
Figure BDA0003746128580000035

其中，uj为相对隶属度，Bp为特征矩阵，wi是第i指标的权重系数，Au为判断矩阵，aij是第i个指标对第j个指标的相对值，取值范围为[1，9]及其倒数，bij是第j个指标对第i个指标的得分，rij是第j个指标相对第i个指标的相对隶属度。Among them, u j is the relative membership degree, B p is the feature matrix, w i is the weight coefficient of the ith index, A u is the judgment matrix, a ij is the relative value of the ith index to the jth index, the value range is [1, 9] and its reciprocal, b ij is the score of the j-th index to the i-th index, and ri ij is the relative membership of the j-th index to the i-th index.

进一步的，上述行为异常判定模型包括一次或多次异常判定，包括以下步骤：Further, the above-mentioned behavior abnormality determination model includes one or more abnormality determinations, including the following steps:

判断上述污水处理厂中的日用电量数据是否全部为0；Determine whether the daily electricity consumption data in the above sewage treatment plant are all 0;

若全部为0，则该污水处理厂判定为日用电量异常；If all are 0, the sewage treatment plant determines that the daily electricity consumption is abnormal;

若不全部为0，则该污水处理厂判定为日用电量正常；If not all are 0, the sewage treatment plant determines that the daily electricity consumption is normal;

根据每日上述实际处理规模数据和日用电量数据，计算上述污水处理厂的吨水耗电量；Calculate the electricity consumption per ton of water of the above-mentioned sewage treatment plant according to the above-mentioned daily actual treatment scale data and daily electricity consumption data;

上述污水处理厂根据实际处理规模划分为多个类别，计算各类别下所有污水处理厂的吨水耗电量平均值；The above sewage treatment plants are divided into multiple categories according to the actual treatment scale, and the average power consumption per ton of water for all sewage treatment plants under each category is calculated;

判断该类别下污水处理厂的吨水耗电量是否连续小于0.8倍吨水耗电量平均值；Determine whether the electricity consumption per ton of water of the sewage treatment plant under this category is continuously less than 0.8 times the average value of electricity consumption per ton of water;

若是，则该污水处理厂判定为吨水耗电量异常；If so, the sewage treatment plant determines that the electricity consumption per ton of water is abnormal;

若不是，则该污水处理厂的吨水耗电量正常；If not, the power consumption per ton of water of the sewage treatment plant is normal;

计算该污水处理厂的日用电量数据的变异系数，判断上述变异系数是否大于0.36；Calculate the coefficient of variation of the daily electricity consumption data of the sewage treatment plant, and judge whether the above-mentioned coefficient of variation is greater than 0.36;

若大于，则该污水处理厂判定为日用电量波动异常；If it is greater than that, the sewage treatment plant determines that the daily electricity consumption fluctuates abnormally;

若不大于，则该污水处理厂的日用电量波动正常。If it is not greater than that, the daily electricity consumption of the sewage treatment plant fluctuates normally.

进一步的，上述判定结果包括日用电量异常、吨水耗电量异常和日用电量波动异常中一个或多个；Further, the above judgment result includes one or more of abnormal daily electricity consumption, abnormal electricity consumption per ton of water, and abnormal fluctuation of daily electricity consumption;

上述判定结果包括三个行为异常等级，上述日用电量异常为一级行为异常；The above judgment results include three levels of abnormal behavior, and the above abnormal daily electricity consumption is a level 1 abnormal behavior;

上述吨水耗电量异常和日用电量波动异常均异常，则为二级行为异常；The abnormality of the above-mentioned abnormal power consumption per ton of water and abnormal fluctuation of daily power consumption are abnormal, which are abnormal secondary behaviors;

上述吨水耗电量异常和日用电量波动异常任意一个异常，则为三级行为异常。Any abnormality in the above-mentioned abnormality of electricity consumption per ton of water and abnormal fluctuation of daily electricity consumption shall be regarded as a third-level behavior abnormality.

进一步的，判断上述污水处理厂的行为异常等级，根据上述污水处理厂的行为异常等级，计算行为异常判定可信度；Further, judging the abnormal behavior level of the above-mentioned sewage treatment plant, and calculating the reliability of abnormal behavior judgment according to the abnormal behavior level of the above-mentioned sewage treatment plant;

若上述污水处理厂为一级行为异常，则行为异常判定可信度为100％；If the above-mentioned sewage treatment plant has a first-level abnormal behavior, the reliability of the abnormal behavior judgment is 100%;

若上述污水处理厂为二级行为异常，则行为异常判定可信度的计算公式如下：If the above-mentioned sewage treatment plant is a secondary abnormal behavior, the calculation formula of the reliability of abnormal behavior judgment is as follows:

Figure BDA0003746128580000041
Figure BDA0003746128580000041

若上述污水处理厂为三级行为异常，则行为异常判定可信度的计算公式如下：If the above-mentioned sewage treatment plant has a third-level abnormal behavior, the calculation formula of the reliability of the abnormal behavior judgment is as follows:

Figure BDA0003746128580000042
Figure BDA0003746128580000042

其中，PTi表示在统计时间段T内第i家污水处理厂的异常判定可信度，SRTi表示在统计时间段T内第i家污水处理厂的实际处理规模与日用电量达到平衡状态下的均衡值，HTi表示在统计时间段T内第i家污水处理厂的吨水耗电量，Hmean表示该类别下吨水耗电量平均值，CvTi表示在统计时间段T内第i家污水处理厂的日用电量数据的变异系数。Among them, P Ti represents the reliability of the abnormal judgment of the ith sewage treatment plant in the statistical time period T, and SR Ti represents the balance between the actual treatment scale and the daily electricity consumption of the ith sewage treatment plant in the statistical time period T The equilibrium value in the state, H Ti represents the electricity consumption per ton of water of the ith sewage treatment plant in the statistical time period T, H mean represents the average power consumption per ton of water in this category, and Cv Ti represents the statistical time period T The coefficient of variation of the daily electricity consumption data of the ith sewage treatment plant in China.

上述行为异常判定可信度根据行为异常的不同等级采用相应的计算方式，提高了判定结果的准确性。The above behavior abnormality determination reliability adopts corresponding calculation methods according to different levels of behavior abnormality, which improves the accuracy of the determination result.

第二方面提供基于用电数据的污水处理厂行为异常判定系统，该判定系统用于实现上述基于用电数据的污水处理厂行为异常判定方法，该判定系统包括：A second aspect provides a system for judging abnormal behavior of a sewage treatment plant based on electricity consumption data. The judging system is used to implement the above-mentioned method for judging abnormal behavior of a sewage treatment plant based on electricity consumption data. The judging system includes:

采集单元，用于获取待监测污水处理厂中的历史数据；The acquisition unit is used to acquire historical data in the sewage treatment plant to be monitored;

处理单元，processing unit,

用于将上述历史数据进行数据清洗，得到历史清洗数据；It is used to perform data cleaning on the above-mentioned historical data to obtain historically cleaned data;

计算上述历史清洗数据中各指标的权重系数，选择权重系数最大的三个指标作为行为指标；Calculate the weight coefficients of each indicator in the above historical cleaning data, and select the three indicators with the largest weight coefficients as behavior indicators;

根据上述行为指标，构建行为异常判定模型；According to the above behavior indicators, construct a behavior abnormality judgment model;

根据上述行为异常判定模型的判定结果，建立行为异常判定的可信度指标，得到行为异常判定可信度；According to the judgment result of the above behavior abnormality judgment model, establish the reliability index of behavior abnormality judgment, and obtain the behavior abnormality judgment reliability;

输出单元，用于输出待监测污水处理厂的行为异常判定可信度。The output unit is used to output the reliability of the abnormal behavior judgment of the sewage treatment plant to be monitored.

通过上述采集单元采集污水处理厂的实际情况，在处理单元根据采集的数据对各指标进行重要性分析，选择影响该污水处理厂行为异常较大的指标作为行为指标建立行为异常判定模型，根据判定结果的行为异常等级，计算判定结果的行为异常判定可信度，提高了上述污水处理厂的行为异常判定的准确性。The actual situation of the sewage treatment plant is collected by the above collection unit, and the importance analysis of each index is carried out in the processing unit according to the collected data, and the index that greatly affects the abnormal behavior of the sewage treatment plant is selected as the behavior index to establish a behavior abnormality judgment model. The abnormal behavior level of the result is calculated, and the reliability of the abnormal behavior determination of the judgment result is calculated, which improves the accuracy of the abnormal behavior determination of the above-mentioned sewage treatment plant.

本发明与现有技术相比，具有如下的优点和有益效果：Compared with the prior art, the present invention has the following advantages and beneficial effects:

根据上述污水处理厂的实际情况对各指标进行重要性分析，选择影响该污水处理厂行为异常较大的指标作为行为指标建立行为异常判定模型，根据该污水处理厂行为异常的严重程度，计算判定结果的可信度，实现对该污水处理厂行为异常情况的精准评估；According to the actual situation of the above sewage treatment plant, the importance of each index is analyzed, and the index that greatly affects the abnormal behavior of the sewage treatment plant is selected as the behavior index to establish a behavior abnormality judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the calculation and judgment The credibility of the results, to achieve accurate assessment of the abnormal behavior of the sewage treatment plant;

相对于传统监测方式，本发明根据上述污水处理厂的用电情况掌握污水处理厂行为异常情况，避免一刀切，提高监测监管的精细化水平。Compared with the traditional monitoring method, the present invention grasps the abnormal behavior of the sewage treatment plant according to the power consumption of the sewage treatment plant, avoids one-size-fits-all, and improves the refinement level of monitoring and supervision.

附图说明Description of drawings

为了更清楚地说明本发明示例性实施方式的技术方案，下面将对实施例中所需要使用的附图作简单地介绍，应当理解，以下附图仅示出了本发明的某些实施例，因此不应被看作是对范围的限定，对于本领域普通技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他相关的附图。在附图中：In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the accompanying drawings required in the embodiments will be briefly introduced below. It should be understood that the following drawings only illustrate some embodiments of the present invention, Therefore, it should not be regarded as a limitation of the scope. For those of ordinary skill in the art, other related drawings can also be obtained from these drawings without any creative effort. In the attached image:

图1为实施例1提供的流程图；Fig. 1 is the flow chart that embodiment 1 provides;

图2为实施例2提供的系统框图。FIG. 2 is a system block diagram provided by Embodiment 2. FIG.

附图中标记及对应的零部件名称：The marks in the attached drawings and the corresponding parts names:

1-采集单元，2-处理单元，3-输出单元。1- Acquisition unit, 2- Processing unit, 3- Output unit.

具体实施方式Detailed ways

为使本发明的目的、技术方案和优点更加清楚明白，下面结合实施例和附图，对本发明作进一步的详细说明，本发明的示意性实施方式及其说明仅用于解释本发明，并不作为对本发明的限定。In order to make the purpose, technical solutions and advantages of the present invention clearer, the present invention will be further described in detail below with reference to the embodiments and the accompanying drawings. as a limitation of the present invention.

实施例1Example 1

本实施例1提供基于用电数据的污水处理厂行为异常判定方法，如图1所示，包括以下步骤：This embodiment 1 provides a method for judging abnormal behavior of a sewage treatment plant based on electricity consumption data, as shown in FIG. 1 , including the following steps:

S1、获取待监测污水处理厂中的历史数据，将上述历史数据进行数据清洗，得到历史清洗数据；S1. Obtain historical data in the sewage treatment plant to be monitored, and perform data cleaning on the above-mentioned historical data to obtain historical cleaning data;

S2、计算上述历史清洗数据中各指标的权重系数，选择权重系数较大的三个指标作为行为指标；S2. Calculate the weight coefficients of each indicator in the above historical cleaning data, and select three indicators with larger weight coefficients as behavior indicators;

S3、根据上述行为指标，构建行为异常判定模型；S3. According to the above behavior indicators, construct a behavior abnormality judgment model;

S4、根据上述行为异常判定模型的判定结果，建立行为异常判定的可信度指标，得到行为异常判定可信度。S4. According to the judgment result of the above-mentioned behavior abnormality judgment model, a reliability index of behavior abnormality judgment is established, and the reliability of behavior abnormality judgment is obtained.

根据上述污水处理厂的实际情况对各指标进行重要性分析，选择影响该污水处理厂行为异常较大的指标作为行为指标建立行为异常判定模型，根据该污水处理厂行为异常的严重程度，计算判定结果的可信度，实现对该污水处理厂行为异常情况的精准评估。According to the actual situation of the above sewage treatment plant, the importance of each index is analyzed, and the index that greatly affects the abnormal behavior of the sewage treatment plant is selected as the behavior index to establish a behavior abnormality judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the calculation and judgment The reliability of the results enables an accurate assessment of the abnormal behavior of the sewage treatment plant.

具体的实施例，上述各指标包括实际处理规模、全年污水处理总量、污水处理工艺、全年污水处理率、设计处理规模、累计完成污水管网长度、排放标准和建设运营状态。In a specific embodiment, the above-mentioned indicators include actual treatment scale, annual total sewage treatment volume, sewage treatment process, annual sewage treatment rate, designed treatment scale, cumulative completed sewage pipe network length, discharge standard, and construction and operation status.

具体的实施例，上述实际处理规模包括11个类别：大于1000吨/日，901-1000吨/日，801-900吨/日，701-800吨/日，601-700吨/日，501-600吨/日，401-500吨/日，301-400吨/日，201-300吨/日，101-200吨/日，小于100吨/日，上述污水处理厂的实际处理规模的数据与日用电量数据为正相关，实际处理规模越大，日用电量越大；In a specific example, the above-mentioned actual processing scale includes 11 categories: more than 1000 tons/day, 901-1000 tons/day, 801-900 tons/day, 701-800 tons/day, 601-700 tons/day, 501- 600 tons/day, 401-500 tons/day, 301-400 tons/day, 201-300 tons/day, 101-200 tons/day, less than 100 tons/day. The daily electricity consumption data is positively correlated, the larger the actual processing scale, the greater the daily electricity consumption;

污水处理工艺，工艺越复杂，处理时间越长，日用电量越高；Sewage treatment process, the more complex the process, the longer the treatment time, the higher the daily electricity consumption;

建设运营状态，根据区域特征，上述污水处理厂的运行情况分为：停运、调试及试运行、已完工、主体已完工、已开工、正式运行和正常运行。将已完工、主体已完工、已开工、正式运行和正常运行的视为行为正常；将停运、调运及试运行视为行为异常。The construction and operation status, according to the regional characteristics, the operation status of the above sewage treatment plants is divided into: shutdown, commissioning and trial operation, completed, main body completed, started, official operation and normal operation. The completed, the main body has been completed, the construction has been started, the official operation and the normal operation are regarded as normal behavior; the outage, commissioning and trial operation are regarded as abnormal behavior.

具体的实施例，上述历史数据包括日用电量数据和每日的示值数据，对上述历史数据中的日用电量数据进行数据清洗包括步骤：In a specific embodiment, the above-mentioned historical data includes daily electricity consumption data and daily indication data, and performing data cleaning on the daily electricity consumption data in the above-mentioned historical data includes the steps:

判断连续30天内上述日用电量数据是否存在缺失数据；Determine whether there is any missing data in the above daily electricity consumption data for 30 consecutive days;

若存在缺失数据，则对上述缺失数据进行标记，并获取当日示值数据，判断上述当日示值数据是否缺失，If there is missing data, mark the above-mentioned missing data, obtain the indication data of the day, and judge whether the above-mentioned indication data of the day is missing.

若上述当日示值数据缺失，则计算与上述日用电量数据相邻天数的日用电量数据均值，If the indicated value data of the above day is missing, calculate the average value of the daily electricity consumption data of the days adjacent to the above daily electricity consumption data,

将上述均值记录于标记处，对上述缺失数据进行补齐，再返回上述判断日用电量数据是否存在缺失数据继续执行，计算公式如下：Record the above average value at the mark, fill in the above missing data, and then return to the above to determine whether there is any missing data in the daily electricity consumption data to continue the execution. The calculation formula is as follows:

Rti＝Ah＝24-Ah＝0 R ti =A h = 24 -A h = 0

其中，Rti表示第i家污水处理厂第t天的日用电量数据，Ah＝24表示第t天第24小时时的示值数据，Ah＝0为第t天第0小时时的示值数据；Among them, R ti represents the daily electricity consumption data of the ith sewage treatment plant on the t day, A h=24 represents the indication data at the 24th hour on the t day, and A h=0 represents the 0 hour on the t day. the indication data;

若上述当日示值数据未缺失，则计算上述当日示值数据的差值，将上述差值记录于标记处，对上述缺失数据进行补齐，再返回上述判断该30天内日用电量数据是否存在缺失数据继续执行，计算公式如下：If the indication data of the day is not missing, calculate the difference of the indication data of the day, record the difference at the mark, make up for the missing data, and then return to the above to determine whether the daily electricity consumption data within 30 days is not Continue to execute if there are missing data, the calculation formula is as follows:

Figure BDA0003746128580000071
Figure BDA0003746128580000071

其中，Rti表示第i家污水处理厂第t天的日用电量数据，R(t-1)i表示第i家污水处理厂第t-1天的日用电量数据，R(t+1)i表示第i家污水处理厂第t+1天的日用电量数据；Among them, R ti represents the daily electricity consumption data of the ith sewage treatment plant on the t day, R (t-1)i represents the daily electricity consumption data of the ith sewage treatment plant on the t-1 day, R (t +1) i represents the daily electricity consumption data of the ith sewage treatment plant on the t+1th day;

若不存在缺失数据，则得到历史清洗数据。If there is no missing data, historical cleaning data is obtained.

根据上述历史数据中的日用电量数据掌握上述污水处理厂行为异常时的用电状态，避免一刀切，提高监测的精细化水平，对上述日用电量数据进行数据清洗，修正和补齐日用电量数据，提高了指标权重系数的精度，进而提高了判定结果的准确性。According to the daily electricity consumption data in the above historical data, we can grasp the electricity consumption status of the above-mentioned sewage treatment plants when the behavior is abnormal, avoid one-size-fits-all, improve the level of refinement of monitoring, clean the above daily electricity consumption data, correct and supplement the daily electricity consumption data. The power consumption data improves the accuracy of the index weight coefficient, thereby improving the accuracy of the judgment result.

具体的实施例，在计算上述历史清洗数据中各指标的权重系数之前，还需要修正或补齐实际处理规模的数据、全年污水处理总量的数据，包括以下步骤：In a specific embodiment, before calculating the weight coefficient of each indicator in the above-mentioned historical cleaning data, it is necessary to correct or supplement the data of the actual treatment scale and the data of the total amount of sewage treatment throughout the year, including the following steps:

判断全年污水处理总量与实际处理规模是否满足条件，上述条件为：To judge whether the total amount of sewage treatment and the actual treatment scale of the whole year meet the conditions, the above conditions are:

Si×365＜Wi×0.8或Si×365＞Wi×1.2S i ×365<W i ×0.8 or S i ×365>W i ×1.2

其中，Si表示第i家污水处理厂的实际处理规模数据，Wi代表第i家污水处理厂的全年污水处理总量数据；Among them, Si represents the actual treatment scale data of the ith sewage treatment plant, and Wi represents the annual total sewage treatment data of the ith sewage treatment plant;

若Si和Wi有解，满足上述条件，则根据

Figure BDA0003746128580000072
修改上述实际处理规模数据；If there is a solution for Si and Wi , and the above conditions are satisfied, then according to
Figure BDA0003746128580000072
Modify the above-mentioned actual processing scale data;

若Si或Wi无解，不满足上述条件，则根据

Figure BDA0003746128580000073
补齐相应的上述实际处理规模数据或全年污水处理总量数据。If there is no solution for Si or Wi , and the above conditions are not met, then according to
Figure BDA0003746128580000073
Complete the corresponding data on the actual treatment scale above or the total annual sewage treatment data.

理论上上述污水处理厂的实际处理规模数据与全年污水处理总量数据应该满足

Figure BDA0003746128580000074
但在实际上述污水处理厂中，因外界因素两个参数之间存在不对应的问题，对上述实际处理规模数据和全年污水处理总量数据进行修正、补齐操作，提高了指标权重系数的精度，进而提高了判定结果的准确性。Theoretically, the actual treatment scale data of the above-mentioned sewage treatment plant and the annual total sewage treatment data should meet the
Figure BDA0003746128580000074
However, in the actual sewage treatment plant mentioned above, due to the incompatibility between the two parameters of external factors, the above-mentioned actual treatment scale data and annual sewage treatment total data were revised and supplemented to improve the index weight coefficient. accuracy, thereby improving the accuracy of the judgment results.

具体的实施例，利用模糊层次分析法(FAHP)对影响上述污染处理厂行为异常因素的重要性进行分析，根据上述各指标的权重系数，计算相对隶属度，具体公式如下：In a specific embodiment, the fuzzy analytic hierarchy process (FAHP) is used to analyze the importance of the abnormal factors affecting the behavior of the above-mentioned pollution treatment plants, and the relative membership degree is calculated according to the weight coefficients of the above-mentioned indicators, and the specific formula is as follows:

Figure BDA0003746128580000075
Figure BDA0003746128580000075

其中，in,

Figure BDA0003746128580000081
Figure BDA0003746128580000081

Figure BDA0003746128580000082
Figure BDA0003746128580000082

Figure BDA0003746128580000083
Figure BDA0003746128580000083

Figure BDA0003746128580000084
Figure BDA0003746128580000084

其中，uj为相对隶属度，Bp为特征矩阵，wi是第i指标的权重系数，Au为判断矩阵，aij是第i个指标对第j个指标的相对值，取值范围为[1，9]及其倒数，bij是第j个指标对第i个指标的得分，rij是第j个指标相对第i个指标的相对隶属度。Among them, u j is the relative membership degree, B p is the feature matrix, w i is the weight coefficient of the ith index, A u is the judgment matrix, a ij is the relative value of the ith index to the jth index, the value range is [1, 9] and its reciprocal, b ij is the score of the j-th index to the i-th index, and ri ij is the relative membership of the j-th index to the i-th index.

根据相对隶属度，对各指标进行权重排序，选择前三个最重要的指标，即权重系数较大的指标作为行为指标。According to the relative membership degree, the weights of each indicator are sorted, and the first three most important indicators, that is, the indicator with a larger weight coefficient, are selected as the behavior indicator.

具体的实施例，上述行为异常判定模型包括一次或多次异常判定，包括以下步骤：In a specific embodiment, the above-mentioned behavior abnormality determination model includes one or more abnormality determinations, including the following steps:

判断上述污水处理厂中的日用电量数据是否连续30天全部为0；Determine whether the daily electricity consumption data in the above sewage treatment plant are all 0 for 30 consecutive days;

若连续30天全部为0，则该污水处理厂判定为日用电量异常；If all of them are 0 for 30 consecutive days, the sewage treatment plant determines that the daily electricity consumption is abnormal;

若连续30天不全部为0，则该污水处理厂判定为日用电量正常；If not all are 0 for 30 consecutive days, the sewage treatment plant determines that the daily electricity consumption is normal;

根据每日上述实际处理规模数据和日用电量数据，计算上述污水处理厂的吨水耗电量，计算公式如下：According to the above-mentioned daily actual treatment scale data and daily electricity consumption data, the electricity consumption per ton of water of the above-mentioned sewage treatment plant is calculated, and the calculation formula is as follows:

Hi＝Ri/Si H i =R i /S i

其中，Hi表示第i家污水处理厂的吨水耗电量，Ri表示第i家污水处理厂的日用电量数据，Si表示第i家污水处理厂的实际处理规模数据；Among them, Hi represents the electricity consumption per ton of water of the ith sewage treatment plant, R i represents the daily electricity consumption data of the ith sewage treatment plant, and Si represents the actual treatment scale data of the ith sewage treatment plant;

上述污水处理厂根据实际处理规模划分为多个类别，计算各类别下所有污水处理厂的吨水耗电量平均值；The above sewage treatment plants are divided into multiple categories according to the actual treatment scale, and the average power consumption per ton of water for all sewage treatment plants under each category is calculated;

判断该类别下污水处理厂的吨水耗电量是否连续7天小于0.8倍吨水耗电量平均值；Determine whether the electricity consumption per ton of water in the sewage treatment plant under this category is less than 0.8 times the average electricity consumption per ton of water for 7 consecutive days;

若是，则该污水处理厂判定为吨水耗电量异常；If so, the sewage treatment plant determines that the electricity consumption per ton of water is abnormal;

若不是，则该污水处理厂的吨水耗电量正常；If not, the power consumption per ton of water of the sewage treatment plant is normal;

计算该污水处理厂的日用电量数据的变异系数，判断上述变异系数是否大于0.36，计算公式如下：Calculate the coefficient of variation of the daily electricity consumption data of the sewage treatment plant, and judge whether the above-mentioned coefficient of variation is greater than 0.36. The calculation formula is as follows:

Figure BDA0003746128580000091
Figure BDA0003746128580000091

其中，Cvi表示第i家污水处理厂的日用电量数据的变异系数，T表示总时间(天数)，Rti表示第i家污水处理厂第t天的日用电量数据，μi表示第i家污水处理厂的日用电量算术平均值；Among them, Cvi represents the coefficient of variation of the daily electricity consumption data of the ith sewage treatment plant, T represents the total time (days), Rti represents the daily electricity consumption data of the ith sewage treatment plant on the t day, μ i Indicates the arithmetic mean of daily electricity consumption of the i-th sewage treatment plant;

若大于，则该污水处理厂判定为日用电量波动异常；If it is greater than that, the sewage treatment plant determines that the daily electricity consumption fluctuates abnormally;

若不大于，则该污水处理厂的日用电量波动正常。If it is not greater than that, the daily electricity consumption of the sewage treatment plant fluctuates normally.

具体的实施例，上述判定结果包括日用电量异常、吨水耗电量异常、日用电量波动异常中一个或多个；In a specific embodiment, the above determination result includes one or more of abnormal daily electricity consumption, abnormal electricity consumption per ton of water, and abnormal fluctuation of daily electricity consumption;

上述判定结果包括三个行为异常等级，上述日用电量异常为一级行为异常；The above judgment results include three levels of abnormal behavior, and the above abnormal daily electricity consumption is a level 1 abnormal behavior;

上述吨水耗电量异常和日用电量波动异常均异常，则为二级行为异常；The abnormality of the above-mentioned abnormal power consumption per ton of water and abnormal fluctuation of daily power consumption are abnormal, which are abnormal secondary behaviors;

上述吨水耗电量异常和日用电量波动异常任意一个异常，则为三级行为异常。Any abnormality in the above-mentioned abnormality of electricity consumption per ton of water and abnormal fluctuation of daily electricity consumption shall be regarded as a third-level behavior abnormality.

具体的实施例，判断上述污水处理厂的行为异常等级，根据上述污水处理厂的行为异常等级，计算行为异常判定可信度；In a specific embodiment, the abnormal behavior level of the above-mentioned sewage treatment plant is judged, and the reliability of abnormal behavior determination is calculated according to the abnormal behavior level of the above-mentioned sewage treatment plant;

若上述污水处理厂为一级行为异常，则行为异常判定可信度为100％；If the above-mentioned sewage treatment plant has a first-level abnormal behavior, the reliability of the abnormal behavior judgment is 100%;

若上述污水处理厂为二级行为异常，则行为异常判定可信度的计算公式如下：If the above-mentioned sewage treatment plant is a secondary abnormal behavior, the calculation formula of the reliability of abnormal behavior judgment is as follows:

Figure BDA0003746128580000092
Figure BDA0003746128580000092

若上述污水处理厂为三级行为异常，则行为异常判定可信度的计算公式如下：If the above-mentioned sewage treatment plant has a third-level behavioral abnormality, the calculation formula of the reliability of the behavioral abnormality judgment is as follows:

Figure BDA0003746128580000093
Figure BDA0003746128580000093

其中，PTi表示在统计时间段T内第i家污水处理厂的异常判定可信度，SRTi表示在统计时间段T内第i家污水处理厂的实际处理规模与日用电量达到平衡状态下的均衡值，HTi表示在统计时间段T内第i家污水处理厂的吨水耗电量，Hmean表示该类别下吨水耗电量平均值，CvTi表示在统计时间段T内第i家污水处理厂的日用电量数据的变异系数。Among them, P Ti represents the reliability of the abnormal judgment of the ith sewage treatment plant in the statistical time period T, and SR Ti represents the balance between the actual treatment scale and the daily electricity consumption of the ith sewage treatment plant in the statistical time period T The equilibrium value in the state, H Ti represents the electricity consumption per ton of water of the ith sewage treatment plant in the statistical time period T, H mean represents the average power consumption per ton of water in this category, and Cv Ti represents the statistical time period T The coefficient of variation of the daily electricity consumption data of the ith sewage treatment plant in China.

上述行为异常判定可信度根据行为异常的不同等级采用相应的计算方式，提高了判定结果的准确性，为上述污水处理厂的高效运行提供参考。The reliability of the above-mentioned abnormal behavior determination adopts a corresponding calculation method according to different levels of abnormal behavior, which improves the accuracy of the determination result and provides a reference for the efficient operation of the above-mentioned sewage treatment plant.

实施例2Example 2

本实施例2提供基于用电数据的污水处理厂行为异常判定系统，该判定系统用于实现上述基于用电数据的污水处理厂行为异常判定方法，该判定系统包括：This embodiment 2 provides a system for judging abnormal behavior of a sewage treatment plant based on electricity consumption data. The judging system is used to implement the above-mentioned method for judging abnormal behavior of a sewage treatment plant based on electricity consumption data. The judging system includes:

采集单元1，用于获取待监测污水处理厂中的历史数据；The acquisition unit 1 is used to acquire historical data in the sewage treatment plant to be monitored;

处理单元2，与上述采集单元1连接，The processing unit 2 is connected to the above-mentioned acquisition unit 1,

用于将上述历史数据进行数据清洗，得到历史清洗数据；It is used to perform data cleaning on the above historical data to obtain historically cleaned data;

计算上述历史清洗数据中各指标的权重系数，选择权重系数最大的三个指标作为行为指标；Calculate the weight coefficients of each indicator in the above historical cleaning data, and select the three indicators with the largest weight coefficients as behavior indicators;

根据上述行为指标，构建行为异常判定模型；According to the above behavior indicators, construct a behavior abnormality judgment model;

根据上述行为异常判定模型的判定结果，建立行为异常判定的可信度指标，得到行为异常判定可信度；According to the judgment result of the above behavior abnormality judgment model, the reliability index of behavior abnormality judgment is established, and the reliability of behavior abnormality judgment is obtained;

输出单元3，与上述处理单元2连接，用于输出待监测污水处理厂的行为异常判定可信度。The output unit 3 is connected to the above-mentioned processing unit 2, and is used for outputting the reliability of the abnormal behavior determination of the sewage treatment plant to be monitored.

通过上述采集单元1采集污水处理厂的实际情况，在处理单元2根据采集的数据对各指标进行重要性分析，选择影响该污水处理厂行为异常较大的指标作为行为指标建立行为异常判定模型，根据判定结果的行为异常等级，计算判定结果的行为异常判定可信度，提高了上述污水处理厂的行为异常判定的准确性。The actual situation of the sewage treatment plant is collected by the above collection unit 1, and the importance analysis of each index is carried out in the processing unit 2 according to the collected data, and the index that affects the abnormal behavior of the sewage treatment plant is selected as the behavior index to establish a behavior abnormality judgment model. According to the abnormal behavior level of the judgment result, the reliability of the abnormal behavior judgment of the judgment result is calculated, and the accuracy of the abnormal behavior judgment of the sewage treatment plant is improved.

以上所述的具体实施方式，对本发明的目的、技术方案和有益效果进行了进一步详细说明，所应理解的是，以上所述仅为本发明的具体实施方式而已，并不用于限定本发明的保护范围，凡在本发明的精神和原则之内，所做的任何修改、等同替换、改进等，均应包含在本发明的保护范围之内。The specific embodiments described above further describe the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above descriptions are only specific embodiments of the present invention, and are not intended to limit the scope of the present invention. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims (10)

1. The sewage treatment plant behavior abnormity judgment method based on electricity utilization data is characterized by comprising the following steps of:
acquiring historical data in a sewage treatment plant to be monitored, and performing data cleaning on the historical data to obtain historical cleaning data;
calculating the weight coefficient of each index in the historical cleaning data, and selecting three indexes with the maximum weight coefficients as behavior indexes;
constructing a behavior abnormity judgment model according to the behavior indexes;
and establishing a reliability index of the behavior abnormity judgment according to the judgment result of the behavior abnormity judgment model to obtain the reliability of the behavior abnormity judgment.
2. The method for judging the behavioral abnormality of the sewage treatment plant according to the electricity consumption data as claimed in claim 1, wherein the indexes include actual treatment scale, annual total sewage treatment amount, sewage treatment process, annual sewage treatment rate, design treatment scale, accumulated finished sewage pipe network length, discharge standard and construction operation state.
3. The method for determining the abnormal behavior of the sewage treatment plant based on the electricity consumption data as claimed in claim 2, wherein the historical data comprises daily electricity consumption data and daily indicating value data, and the step of performing data cleaning on the daily electricity consumption data in the historical data comprises the following steps:
judging whether the daily electric quantity data has missing data or not;
if the missing data exists, marking the missing data, acquiring the current date indicating data, judging whether the current date indicating data is missing or not,
if the daily indicating value data is missing, calculating the average value of the daily electricity quantity data of days adjacent to the daily electricity quantity data, recording the average value at a mark, supplementing the missing data, and returning to the step of judging whether the daily electricity quantity data has missing data for continuous execution;
if the daily indicating value data is not missing, calculating the difference value of the daily indicating value data, recording the difference value at a mark, supplementing the missing data, and returning to the step of judging whether the daily electric quantity data has the missing data for continuous execution;
and if the missing data does not exist, obtaining historical cleaning data.
4. The method for determining the behavioral abnormality of the sewage treatment plant according to the electricity consumption data of claim 3, wherein the data on the actual scale of the treatment and the data on the total annual sewage treatment amount are corrected or supplemented before the weight coefficient of each index in the historical cleaning data is calculated, and the method comprises the steps of:
judging whether the total annual sewage treatment amount and the actual treatment scale meet the conditions, wherein the conditions are as follows:
S i ×365＜W i x0.8 or S i ×365＞W i ×1.2
Wherein S is i Data showing the actual treatment scale of the i-th sewage treatment plant, W i Represents the annual total sewage treatment data of the ith sewage treatment plant;
if S i And W i If the solution meets the condition, then according to
Figure FDA0003746128570000021
Modifying the actual process size data;
if S i Or W i If no solution is available, the condition is not satisfied, then according to
Figure FDA0003746128570000022
And supplementing corresponding actual treatment scale data or annual total sewage treatment amount data.
5. The method for judging the behavioral abnormality of the sewage treatment plant based on the electricity consumption data according to claim 1, wherein the relative membership degree is calculated according to the weight coefficient of each index, the indexes are subjected to weight sorting, and three indexes with larger weight coefficients are selected as the behavioral indexes.
6. The method for judging the behavioral abnormality of the sewage treatment plant based on the electricity consumption data according to claim 5, wherein the relative membership degree is calculated according to the weight coefficient of each index, and the specific formula is as follows:
Figure FDA0003746128570000023
wherein,
Figure FDA0003746128570000024
Figure FDA0003746128570000025
Figure FDA0003746128570000026
Figure FDA0003746128570000027
wherein u is j Is a relative degree of membership, B p Is a feature matrix, w i Is the weight coefficient of the i-th index, A u To determine the matrix, a ij Is the relative value of the ith index to the jth index, and the value range is [1,9 ]]And reciprocal thereof, b ij Is the score of the j index to the i index, r ij Is the relative degree of membership of the jth index to the ith index.
7. The wastewater treatment plant behavior abnormality determination method based on electricity consumption data according to claim 4, characterized in that the behavior abnormality determination model includes one or more abnormality determinations, including the steps of:
judging whether all the daily electricity data in the sewage treatment plant is 0;
if all the electricity consumption values are 0, judging that the daily electricity consumption is abnormal by the sewage treatment plant;
if not all the daily electric quantity is 0, judging that the daily electric quantity is normal by the sewage treatment plant;
calculating the ton water power consumption of the sewage treatment plant according to the daily actual treatment scale data and daily electricity consumption data;
dividing the sewage treatment plants into a plurality of categories according to actual treatment scale, and calculating the average value of the ton water power consumption of all the sewage treatment plants under each category;
judging whether the ton water power consumption of the sewage treatment plant under the category is continuously less than the average value of 0.8 time of the ton water power consumption;
if yes, the sewage treatment plant judges that the power consumption per ton of water is abnormal;
if not, the power consumption per ton of water of the sewage treatment plant is normal;
calculating the variation coefficient of the daily electricity quantity data of the sewage treatment plant, and judging whether the variation coefficient is greater than 0.36;
if the current power consumption is larger than the preset power consumption, judging that the daily power consumption fluctuation is abnormal by the sewage treatment plant;
if the power consumption is not more than the preset value, the daily power fluctuation of the sewage treatment plant is normal.
8. The sewage treatment plant behavior abnormality determination method based on electricity consumption data according to claim 7, wherein the determination result includes one or more of abnormality of daily electricity consumption, abnormality of ton water electricity consumption, and abnormality of daily electricity fluctuation;
the judgment result comprises three behavioral anomaly levels, and the daily electricity consumption anomaly is a primary behavioral anomaly;
the abnormal electricity consumption per ton of water and the abnormal daily electricity fluctuation are both abnormal, and the abnormal second-level behavior is determined;
and if any one of the abnormality of the power consumption per ton of water and the abnormality of the daily power fluctuation is abnormal, the three-level behavior is abnormal.
9. The method for judging the behavioral abnormality of the sewage treatment plant based on the electricity consumption data according to claim 8, wherein the behavioral abnormality level of the sewage treatment plant is judged, and the behavioral abnormality judgment reliability is calculated according to the behavioral abnormality level of the sewage treatment plant;
if the sewage treatment plant is abnormal in primary behavior, the reliability of judging the abnormal behavior is 100 percent;
if the sewage treatment plant is abnormal in secondary behaviors, the calculation formula of judging the reliability of the abnormal behaviors is as follows:
Figure FDA0003746128570000031
if the sewage treatment plant is abnormal in third-level behaviors, the calculation formula of judging the credibility of the abnormal behaviors is as follows:
Figure FDA0003746128570000032
wherein, P Ti Represents the abnormal judgment reliability, SR, of the ith sewage treatment plant in the statistical time period T Ti Shows the equilibrium value H when the actual treatment scale and the daily electricity quantity of the ith sewage treatment plant reach the equilibrium state within the statistical time period T Ti Represents the ton water power consumption H of the ith sewage treatment plant in the statistical time period T mean Means of the ton water power consumption, cv, under this category Ti And the variation coefficient of the daily electricity consumption data of the ith sewage treatment plant in the statistical time period T is shown.
10. The system for judging the abnormal behavior of the sewage treatment plant based on the electricity consumption data is characterized by being used for realizing the method for judging the abnormal behavior of the sewage treatment plant based on the electricity consumption data according to any one of claims 1 to 9, and comprising the following steps:
the system comprises a collecting unit (1) and a monitoring unit, wherein the collecting unit is used for obtaining historical data in a sewage treatment plant to be monitored;
a processing unit (2),
the historical data is subjected to data cleaning to obtain historical cleaning data;
calculating the weight coefficient of each index in the historical cleaning data, and selecting the three indexes with the maximum weight coefficients as behavior indexes;
constructing a behavior abnormity judgment model according to the behavior indexes;
establishing a reliability index of the behavior abnormity judgment according to the judgment result of the behavior abnormity judgment model to obtain the reliability of the behavior abnormity judgment;
and the output unit (3) is used for outputting the judgment reliability of the abnormal behavior of the sewage treatment plant to be monitored.
CN202210825017.5A 2022-07-14 2022-07-14 Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data Pending CN115204669A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202210825017.5A CN115204669A (en) 2022-07-14 2022-07-14 Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202210825017.5A CN115204669A (en) 2022-07-14 2022-07-14 Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data

Publications (1)

Publication Number Publication Date
CN115204669A true CN115204669A (en) 2022-10-18

Family

ID=83579686

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202210825017.5A Pending CN115204669A (en) 2022-07-14 2022-07-14 Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data

Country Status (1)

Country Link
CN (1) CN115204669A (en)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115790723A (en) * 2023-02-06 2023-03-14 山东中都机器有限公司 Sewage purification abnormity detection method
CN118411085A (en) * 2024-07-02 2024-07-30 台州市污染防治技术中心有限公司 A sewage illegal discharge emergency response system and method

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115790723A (en) * 2023-02-06 2023-03-14 山东中都机器有限公司 Sewage purification abnormity detection method
CN115790723B (en) * 2023-02-06 2023-06-06 山东中都机器有限公司 Sewage purification abnormality detection method
CN118411085A (en) * 2024-07-02 2024-07-30 台州市污染防治技术中心有限公司 A sewage illegal discharge emergency response system and method

Similar Documents

Publication Publication Date Title
CN115204669A (en) Method and system for abnormal behavior determination of sewage treatment plant based on electricity consumption data
CN110210686A (en) A kind of electricity charge risk model construction method of electric power big data
CN110837866A (en) Evaluation method of defect degree of power secondary equipment based on XGBoost
CN114862139A (en) Data-driven transformer area line loss rate abnormity diagnosis method
CN113032454A (en) Interactive user power consumption abnormity monitoring and early warning management cloud platform based on cloud computing
CN105956788A (en) Dynamic management control method for cost of power transmission and transformation project
CN109389280B (en) Evaluation Method of Energy Meter Manufacturers Based on Multi-attribute Decision-Making Model
CN111612647B (en) Meter abnormal data detection method, device, meter and readable storage medium
CN113792939A (en) Method and device for reliability prediction of electric energy meter based on hybrid Weibull distribution
CN117394337A (en) Power grid load early warning method and system thereof
CN111967684B (en) Metering asset active distribution method based on big data analysis
CN111612019A (en) A method for abnormal identification and analysis of smart meter faults based on big data model
CN117391499A (en) Photovoltaic power station reliability evaluation method and device
CN106651093A (en) Smart re-check management and control method used for low voltage set copy system
CN106327359A (en) Electricity consumption mode analysis-based meter centralized reading data anomaly judgment method
CN113466520A (en) Method for on-line identifying misalignment electric energy meter
CN115204583A (en) Method, system and device for hierarchical management, control, evaluation and analysis of regional risks in chemical industry park
CN113868947A (en) Intelligent electric energy meter service life prediction method and device
CN106845748A (en) A kind of INTELLIGENT IDENTIFICATION method of low-voltage collecting meter reading system data deviation reason
CN110968703B (en) Method and system for constructing abnormal metering point knowledge base based on LSTM end-to-end extraction algorithm
CN105139287A (en) Comprehensive electric energy metering device state assessment method integrating safety domain
CN109409629B (en) Acquisition terminal manufacturer evaluation method based on multi-attribute decision model
CN117972842A (en) Bridge strain stress data prediction method based on Prophet+LSTM model
CN114091618A (en) Industrial equipment health state diagnosis management method and device and server
CN118586722A (en) A method for fault diagnosis of electromechanical equipment in smart power plants

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination