Method and system for determining abnormal behavior of sewage treatment plants based on electricity consumption data

Abstract

The present invention discloses a method and system for determining abnormal behavior of a sewage treatment plant based on electricity consumption data, which relates to the field of sewage treatment monitoring. The determination method comprises the following steps: obtaining historical data from the sewage treatment plant to be monitored, performing data cleaning on the historical data to obtain historical cleaned data; calculating the weight coefficient of each indicator in the historical cleaned data, and selecting the three indicators with the largest weight coefficients as behavior indicators; constructing a behavior abnormality determination model based on the behavior indicators; establishing a credibility index for behavior abnormality determination based on the determination results of the behavior abnormality determination model, and obtaining the credibility of behavior abnormality determination, thereby improving the accuracy of the determination results, grasping the abnormal behavior of the sewage treatment plant based on the electricity consumption of the sewage treatment plant, avoiding a one-size-fits-all approach, and improving the refinement level of monitoring.

Description

Technical Field

[0001] The present invention relates to sewage treatment monitoring, and in particular to a method and system for determining abnormal behavior of a sewage treatment plant based on electricity consumption data. Background Art

[0002] With the further acceleration of urbanization, the problem of environmental pollution in rural areas has become increasingly prominent. The effective operation of rural sewage treatment plants is an important guarantee for the sustainable development of rural areas.

[0003] The existing method for determining abnormal operation of sewage treatment plants is "one-size-fits-all" and has great limitations. It only considers the scale of the sewage treatment plant itself, the treatment process or the total amount of sewage treated throughout the year. It is unable to identify sewage treatment plants with abnormal electricity consumption, and is unable to judge abnormal operation based on the electricity consumption status of the sewage treatment plants, and the results are not accurate. Due to differences in electricity consumption habits among sewage treatment plants of different regions and sizes, and uncertainties in some sewage treatment plants, the electricity consumption characteristics of abnormally operating sewage treatment plants are different. It is impossible to give a critical value for abnormal operation based on the electricity consumption level and electricity consumption status of sewage treatment plants of different actual scales, and to accurately determine the abnormal behavior of sewage treatment plants. Summary of the Invention

[0004] The technical problem to be solved by the present invention is to improve the accuracy of judging abnormal operation of sewage treatment plants and improve the level of refinement of monitoring and supervision. The purpose is to provide a method and system for judging abnormal behavior of sewage treatment plants based on electricity consumption data, which solves the limitations of traditional judgment of abnormal operation of sewage treatment plants and the problem that it cannot accurately judge abnormal operation of sewage treatment plants.

[0005] The present invention is achieved through the following technical solutions:

[0006] A first aspect provides a method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data, comprising the following steps:

[0007] Acquire historical data from the sewage treatment plant to be monitored, and clean the historical data to obtain historical cleansed data;

[0008] Calculate the weight coefficient of each indicator in the above historical cleansing data, and select the three indicators with the largest weight coefficients as behavioral indicators;

[0009] Based on the above behavioral indicators, a behavioral abnormality determination model is constructed;

[0010] According to the determination result of the above-mentioned abnormal behavior determination model, a credibility index of abnormal behavior determination is established to obtain the credibility of abnormal behavior determination.

[0011] According to the actual situation of the above-mentioned sewage treatment plant, the importance of each indicator was analyzed, and the indicators that had a greater impact on the abnormal behavior of the sewage treatment plant were selected as behavioral indicators to establish a behavioral anomaly judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the credibility of the judgment result was calculated to achieve an accurate assessment of the abnormal behavior of the sewage treatment plant.

[0012] Furthermore, the above indicators include actual treatment scale, total annual sewage treatment volume, sewage treatment process, annual sewage treatment rate, designed treatment scale, cumulative completed sewage pipeline length, emission standards and construction and operation status.

[0013] Furthermore, the historical data includes daily electricity consumption data and daily indication data. Cleaning the daily electricity consumption data in the historical data includes the following steps:

[0014] Determine whether there is missing data in the above daily electricity consumption data;

[0015] If there is missing data, mark the missing data and obtain the value data of the day to determine whether the value data of the day is missing.

[0016] If the above-mentioned daily power consumption data is missing, calculate the average of the daily power consumption data of the days adjacent to the above-mentioned daily power consumption data, record the above-mentioned average at the mark, fill in the above-mentioned missing data, and then return to the above-mentioned determination of whether there is missing data in the daily power consumption data to continue execution;

[0017] If the above-mentioned daily indication data is not missing, then calculate the difference of the above-mentioned daily indication data, record the above-mentioned difference at the mark, fill in the above-mentioned missing data, and then return to the above-mentioned determination of whether there is missing data in the daily electricity consumption data to continue execution;

[0018] If there is no missing data, historical cleaned data is obtained.

[0019] Based on the daily electricity consumption data in the above historical data, we can grasp the electricity consumption status of the above sewage treatment plants when they behave abnormally, avoid a one-size-fits-all approach, improve the level of monitoring refinement, clean the above daily electricity consumption data, correct and complete the daily electricity consumption data, improve the accuracy of the indicator weight coefficient, and thus improve the accuracy of the judgment results.

[0020] Furthermore, before calculating the weight coefficients of each indicator in the above historical cleaning data, it is necessary to correct or supplement the data of the actual treatment scale and the total amount of sewage treated throughout the year, including the following steps:

[0021] Determine whether the total annual sewage treatment volume and the actual treatment scale meet the conditions. The above conditions are:

[0022] S i ×365<Wi ×0.8 or S i ×365>W i ×1.2

[0023] Among them, S i represents the actual treatment scale data of the i-th sewage treatment plant, W i Represents the total annual sewage treatment data of the i-th sewage treatment plant;

[0024] If S i and W i There is a solution, and the above conditions are met, then according to Modify the above actual processing scale data;

[0025] If S i or W i There is no solution, the above conditions are not met, then according to Complete the corresponding actual treatment scale data or annual sewage treatment volume data mentioned above.

[0026] Furthermore, the relative membership is calculated based on the weight coefficients of the above indicators, the indicators are ranked by weight, and three indicators with larger weight coefficients are selected as behavioral indicators.

[0027] Furthermore, the relative membership is calculated based on the weight coefficients of the above indicators. The specific formula is as follows:

[0028]

[0029] in,

[0030]

[0031]

[0032]

[0033]

[0034] Among them, u j is the relative membership, B p is the feature matrix, w i is the weight coefficient of the i-th indicator, A u is the judgment matrix, a ij is the relative value of the i-th index to the j-th index, and its value range is [1, 9] and its reciprocal, b ij is the score of the jth indicator to the ith indicator, r ij is the relative membership of the j-th indicator to the i-th indicator.

[0035] Furthermore, the above-mentioned behavior abnormality determination model includes one or more abnormality determinations, including the following steps:

[0036] Determine whether all daily electricity consumption data in the sewage treatment plant are 0;

[0037] If all are 0, the sewage treatment plant is judged to have abnormal daily electricity consumption;

[0038] If not all are 0, the sewage treatment plant is judged to have normal daily electricity consumption;

[0039] Calculate the electricity consumption per ton of water of the above-mentioned sewage treatment plants based on the above-mentioned actual treatment scale data and daily electricity consumption data;

[0040] The above-mentioned sewage treatment plants are divided into multiple categories according to their actual treatment scale, and the average electricity consumption per ton of water for all sewage treatment plants in each category is calculated;

[0041] 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 electricity consumption per ton of water;

[0042] If so, the sewage treatment plant is judged to have abnormal electricity consumption per ton of water;

[0043] If not, the electricity consumption per ton of water of the sewage treatment plant is normal;

[0044] Calculate the coefficient of variation of the daily electricity consumption data of the sewage treatment plant and determine whether the coefficient of variation is greater than 0.36;

[0045] If it is greater than, the sewage treatment plant is judged to have abnormal daily electricity consumption fluctuation;

[0046] If it is not greater than, the daily electricity consumption fluctuation of the sewage treatment plant is normal.

[0047] Furthermore, the above determination result includes one or more of abnormal daily power consumption, abnormal power consumption per ton of water, and abnormal daily power consumption fluctuation;

[0048] The above determination results include three levels of abnormal behavior, and the above abnormal daily power consumption is a level one abnormal behavior;

[0049] If both the abnormal power consumption per ton of water and the abnormal fluctuation of daily power consumption are abnormal, it is a secondary abnormal behavior;

[0050] Any of the above abnormalities in electricity consumption per ton of water and abnormal fluctuations in daily electricity consumption shall be deemed as Level 3 behavioral abnormality.

[0051] Further, determining the behavior abnormality level of the sewage treatment plant, and calculating the reliability of the behavior abnormality determination based on the behavior abnormality level of the sewage treatment plant;

[0052] If the above sewage treatment plant is a level one behavioral anomaly, the reliability of the behavioral anomaly determination is 100%;

[0053] If the above sewage treatment plant is a level 2 behavioral anomaly, the calculation formula for the behavioral anomaly determination reliability is as follows:

[0054]

[0055] If the above sewage treatment plant is a level 3 behavioral anomaly, the calculation formula for the behavioral anomaly determination reliability is as follows:

[0056]

[0057] Among them, P Ti It represents the reliability of abnormal judgment of the i-th sewage treatment plant in the statistical time period T, SR Ti It represents the equilibrium value when the actual treatment scale and daily electricity consumption of the i-th sewage treatment plant reach a balance state within the statistical time period T, H Ti It represents the electricity consumption per ton of water of the i-th sewage treatment plant in the statistical time period T, H mean Indicates the average electricity consumption per ton of water in this category, Cv Ti It represents the coefficient of variation of the daily electricity consumption data of the i-th sewage treatment plant within the statistical time period T.

[0058] The above-mentioned behavioral abnormality determination reliability adopts corresponding calculation methods according to different levels of behavioral abnormality, thereby improving the accuracy of the determination result.

[0059] A second aspect provides a sewage treatment plant behavior abnormality determination system based on electricity consumption data, the determination system being used to implement the above-mentioned sewage treatment plant behavior abnormality determination method based on electricity consumption data, the determination system comprising:

[0060] A collection unit, used to obtain historical data from the sewage treatment plant to be monitored;

[0061] processing unit,

[0062] Used to clean the above historical data to obtain historical cleansed data;

[0063] Calculate the weight coefficient of each indicator in the above historical cleansing data, and select the three indicators with the largest weight coefficients as behavioral indicators;

[0064] Based on the above behavioral indicators, a behavioral abnormality determination model is constructed;

[0065] According to the determination results of the above-mentioned abnormal behavior determination model, a credibility index of abnormal behavior determination is established to obtain the credibility of abnormal behavior determination;

[0066] The output unit is used to output the credibility of the abnormal behavior judgment of the sewage treatment plant to be monitored.

[0067] The actual situation of the sewage treatment plant is collected through the above-mentioned collection unit, and the importance of each indicator is analyzed in the processing unit based on the collected data. The indicators that have a greater impact on the abnormal behavior of the sewage treatment plant are selected as behavioral indicators to establish a behavioral anomaly judgment model. According to the behavioral anomaly level of the judgment result, the credibility of the behavioral anomaly judgment of the judgment result is calculated, thereby improving the accuracy of the behavioral anomaly judgment of the above-mentioned sewage treatment plant.

[0068] Compared with the prior art, the present invention has the following advantages and beneficial effects:

[0069] Based on the actual situation of the above-mentioned sewage treatment plant, the importance of each indicator was analyzed. The indicators with the greatest impact on the abnormal behavior of the sewage treatment plant were selected as behavioral indicators to establish a behavioral abnormality judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the credibility of the judgment result was calculated to achieve an accurate assessment of the abnormal behavior of the sewage treatment plant.

[0070] Compared with traditional monitoring methods, the present invention can grasp abnormal behavior of sewage treatment plants based on the electricity consumption of the above-mentioned sewage treatment plants, avoid a one-size-fits-all approach, and improve the level of refinement of monitoring and supervision. BRIEF DESCRIPTION OF THE DRAWINGS

[0071] In order to more clearly illustrate the technical solutions of the exemplary embodiments of the present invention, the following briefly introduces the drawings required for use in the examples. It should be understood that the following drawings only illustrate certain embodiments of the present invention and should not be considered as limiting the scope. A person of ordinary skill in the art can also derive other relevant drawings based on these drawings without inventive effort. In the drawings:

[0072] Figure 1 Flowchart provided for Example 1;

[0073] Figure 2 This is a system block diagram provided for Example 2.

[0074] Markings and corresponding parts names in the accompanying drawings:

[0075] 1-Acquisition unit, 2-Processing unit, 3-Output unit. DETAILED DESCRIPTION

[0076] In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with examples and drawings. The exemplary embodiments of the present invention and their descriptions are only used to explain the present invention and are not intended to limit the present invention.

[0077] Example 1

[0078] This embodiment 1 provides a method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data, such as Figure 1 As shown, the following steps are included:

[0079] S1. Obtain historical data from the sewage treatment plant to be monitored, and clean the historical data to obtain historical cleansed data;

[0080] S2. Calculate the weight coefficients of each indicator in the above historical cleansing data, and select the three indicators with the largest weight coefficients as behavioral indicators;

[0081] S3. Constructing a behavioral abnormality determination model based on the above behavioral indicators;

[0082] S4. Based on the determination result of the above-mentioned abnormal behavior determination model, a credibility index of abnormal behavior determination is established to obtain the credibility of abnormal behavior determination.

[0083] According to the actual situation of the above-mentioned sewage treatment plant, the importance of each indicator was analyzed, and the indicators that had a greater impact on the abnormal behavior of the sewage treatment plant were selected as behavioral indicators to establish a behavioral anomaly judgment model. According to the severity of the abnormal behavior of the sewage treatment plant, the credibility of the judgment result was calculated to achieve an accurate assessment of the abnormal behavior of the sewage treatment plant.

[0084] In a specific embodiment, the above indicators include actual treatment scale, total annual sewage treatment volume, sewage treatment process, annual sewage treatment rate, designed treatment scale, cumulative completed sewage pipe network length, emission standards and construction and operation status.

[0085] In a specific embodiment, the actual treatment scale includes 11 categories: greater than 1,000 tons / day, 901-1,000 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, and less than 100 tons / day. The actual treatment scale data of the sewage treatment plant is positively correlated with the daily electricity consumption data. The larger the actual treatment scale, the greater the daily electricity consumption.

[0086] The more complex the sewage treatment process, the longer the treatment time and the higher the daily electricity consumption;

[0087] Construction and operation status: Based on regional characteristics, the operation status of the above-mentioned sewage treatment plants is divided into the following categories: shutdown, commissioning and trial operation, completion, main structure completed, construction started, formal operation, and normal operation. Completed, main structure completed, construction started, formal operation, and normal operation are considered normal; shutdown, transfer, and trial operation are considered abnormal.

[0088] In a specific embodiment, the historical data includes daily electricity consumption data and daily indication data, and data cleaning of the daily electricity consumption data in the historical data includes the following steps:

[0089] Determine whether there is any missing data in the above daily electricity consumption data within 30 consecutive days;

[0090] If there is missing data, mark the missing data and obtain the value data of the day to determine whether the value data of the day is missing.

[0091] If the above-mentioned daily power consumption data is missing, the average of the daily power consumption data of the days adjacent to the above-mentioned daily power consumption data shall be calculated.

[0092] Record the above average value at the mark, fill in the missing data, and then return to the above method to determine whether there is missing data in the daily electricity consumption data. The calculation formula is as follows:

[0093] R ti =A h＝24 -A h＝0

[0094] Among them, R ti A represents the daily electricity consumption data of the i-th sewage treatment plant on the t-th day, h＝24 Indicates the indication data at the 24th hour of the tth day, A h＝0 It is the indication data at hour 0 on day t;

[0095] If the indicated data for the day is not missing, calculate the difference between the indicated data for the day, record the difference at the mark, fill in the missing data, and then return to the above step to determine whether there is missing data in the daily electricity consumption data within the 30 days. The calculation formula is as follows:

[0096]

[0097] Among them, R ti represents the daily electricity consumption data of the i-th sewage treatment plant on the t-th day, R (t-1)i represents the daily electricity consumption data of the i-th sewage treatment plant on day t-1, R (t+1)i represents the daily electricity consumption data of the i-th sewage treatment plant on day t+1;

[0098] If there is no missing data, historical cleaned data is obtained.

[0099] Based on the daily electricity consumption data in the above historical data, we can grasp the electricity consumption status of the above sewage treatment plants when they behave abnormally, avoid a one-size-fits-all approach, improve the level of monitoring refinement, clean the above daily electricity consumption data, correct and complete the daily electricity consumption data, improve the accuracy of the indicator weight coefficient, and thus improve the accuracy of the judgment results.

[0100] In a specific embodiment, before calculating the weight coefficients of the various indicators in the above historical cleaning data, it is necessary to correct or supplement the data of the actual treatment scale and the total amount of sewage treated throughout the year, including the following steps:

[0101] Determine whether the total annual sewage treatment volume and the actual treatment scale meet the conditions. The above conditions are:

[0102] S i ×365<W i ×0.8 or S i ×365>W i ×1.2

[0103] Among them, S i represents the actual treatment scale data of the i-th sewage treatment plant, W i Represents the total annual sewage treatment data of the i-th sewage treatment plant;

[0104] If S i and W i There is a solution, and the above conditions are met, then according to Modify the above actual processing scale data;

[0105] If S i or W i There is no solution, the above conditions are not met, then according to Complete the corresponding actual treatment scale data or annual sewage treatment volume data mentioned above.

[0106] Theoretically, the actual treatment scale data of the above sewage treatment plants and the total sewage treatment volume data for the whole year should meet However, in the actual sewage treatment plants mentioned above, there is a mismatch between the two parameters due to external factors. The above-mentioned actual treatment scale data and the annual sewage treatment volume data are corrected and supplemented, which improves the accuracy of the indicator weight coefficient and thus improves the accuracy of the judgment results.

[0107] In a specific embodiment, the importance of factors affecting the abnormal behavior of the above-mentioned pollution treatment plant is analyzed using the fuzzy analytic hierarchy process (FAHP). The relative membership degree is calculated based on the weight coefficient of each of the above-mentioned indicators. The specific formula is as follows:

[0108]

[0109] in,

[0110]

[0111]

[0112]

[0113]

[0114] Among them, u j is the relative membership, B p is the feature matrix, w i is the weight coefficient of the i-th indicator, A u is the judgment matrix, a ij is the relative value of the i-th index to the j-th index, and its value range is [1, 9] and its reciprocal, b ij is the score of the jth indicator to the ith indicator, r ij is the relative membership of the j-th indicator to the i-th indicator.

[0115] According to the relative degree of membership, the indicators are weighted and ranked, and the first three most important indicators, i.e., the indicators with larger weight coefficients, are selected as behavioral indicators.

[0116] In a specific embodiment, the above-mentioned behavior abnormality determination model includes one or more abnormality determinations, including the following steps:

[0117] Determine whether the daily electricity consumption data of the above sewage treatment plant is all zero for 30 consecutive days;

[0118] If the readings are all zero for 30 consecutive days, the sewage treatment plant is judged to have abnormal daily electricity consumption;

[0119] If the readings are not all zero for 30 consecutive days, the sewage treatment plant is judged to have normal daily electricity consumption;

[0120] Based on the above actual treatment scale data and daily electricity consumption data, the electricity consumption per ton of water of the above sewage treatment plants is calculated using the following formula:

[0121] H i =R i / S i

[0122] Among them, H i represents the electricity consumption per ton of water of the i-th sewage treatment plant, R i represents the daily electricity consumption data of the i-th sewage treatment plant, S i represents the actual treatment scale data of the i-th sewage treatment plant;

[0123] The above-mentioned sewage treatment plants are divided into multiple categories according to their actual treatment scale, and the average electricity consumption per ton of water for all sewage treatment plants in each category is calculated;

[0124] Determine whether the electricity consumption per ton of water of 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;

[0125] If so, the sewage treatment plant is judged to have abnormal electricity consumption per ton of water;

[0126] If not, the electricity consumption per ton of water of the sewage treatment plant is normal;

[0127] Calculate the coefficient of variation of the daily electricity consumption data of the sewage treatment plant and determine whether the coefficient of variation is greater than 0.36. The calculation formula is as follows:

[0128]

[0129] Among them, Cv i represents the coefficient of variation of the daily electricity consumption data of the i-th sewage treatment plant, T represents the total time (days), R ti represents the daily electricity consumption data of the i-th sewage treatment plant on the t-th day, μ i represents the arithmetic mean of daily electricity consumption of the i-th sewage treatment plant;

[0130] If it is greater than, the sewage treatment plant is judged to have abnormal daily electricity consumption fluctuation;

[0131] If it is not greater than, the daily electricity consumption fluctuation of the sewage treatment plant is normal.

[0132] In a specific embodiment, the above determination result includes one or more of abnormal daily power consumption, abnormal power consumption per ton of water, and abnormal daily power consumption fluctuation;

[0133] The above determination results include three levels of abnormal behavior, and the above abnormal daily power consumption is a level one abnormal behavior;

[0134] If both the abnormal power consumption per ton of water and the abnormal fluctuation of daily power consumption are abnormal, it is a secondary abnormal behavior;

[0135] Any of the above abnormalities in electricity consumption per ton of water and abnormal fluctuations in daily electricity consumption shall be deemed as Level 3 behavioral abnormality.

[0136] In a specific embodiment, the behavior abnormality level of the sewage treatment plant is determined, and the reliability of the behavior abnormality determination is calculated based on the behavior abnormality level of the sewage treatment plant;

[0137] If the above sewage treatment plant is a level one behavioral anomaly, the reliability of the behavioral anomaly determination is 100%;

[0138] If the above sewage treatment plant is a level 2 behavioral anomaly, the calculation formula for the behavioral anomaly determination reliability is as follows:

[0139]

[0140] If the above sewage treatment plant is a level 3 behavioral anomaly, the calculation formula for the behavioral anomaly determination reliability is as follows:

[0141]

[0142] Among them, P Ti It represents the reliability of abnormal judgment of the i-th sewage treatment plant in the statistical time period T, SR Ti It represents the equilibrium value when the actual treatment scale and daily electricity consumption of the i-th sewage treatment plant reach a balance state within the statistical time period T, H Ti It represents the electricity consumption per ton of water of the i-th sewage treatment plant in the statistical time period T, H mean Indicates the average electricity consumption per ton of water in this category, Cv Ti It represents the coefficient of variation of the daily electricity consumption data of the i-th sewage treatment plant within the statistical time period T.

[0143] The above-mentioned abnormal behavior determination credibility adopts corresponding calculation methods according to different levels of abnormal behavior, thereby improving the accuracy of the determination result and providing a reference for the efficient operation of the above-mentioned sewage treatment plant.

[0144] Example 2

[0145] This embodiment 2 provides a sewage treatment plant behavior abnormality determination system based on electricity consumption data. The determination system is used to implement the above-mentioned sewage treatment plant behavior abnormality determination method based on electricity consumption data. The determination system includes:

[0146] Collection unit 1, used to obtain historical data from the sewage treatment plant to be monitored;

[0147] The processing unit 2 is connected to the acquisition unit 1.

[0148] Used to clean the above historical data to obtain historical cleansed data;

[0149] Calculate the weight coefficient of each indicator in the above historical cleansing data, and select the three indicators with the largest weight coefficients as behavioral indicators;

[0150] Based on the above behavioral indicators, a behavioral abnormality determination model is constructed;

[0151] According to the determination results of the above-mentioned abnormal behavior determination model, a credibility index of abnormal behavior determination is established to obtain the credibility of abnormal behavior determination;

[0152] The output unit 3 is connected to the processing unit 2 and is used to output the credibility of the abnormal behavior determination of the sewage treatment plant to be monitored.

[0153] The actual situation of the sewage treatment plant is collected through the above-mentioned collection unit 1, and the importance of each indicator is analyzed in the processing unit 2 based on the collected data. The indicators that have a greater impact on the abnormal behavior of the sewage treatment plant are selected as behavioral indicators to establish a behavioral anomaly judgment model. According to the behavioral anomaly level of the judgment result, the credibility of the behavioral anomaly judgment of the judgment result is calculated, thereby improving the accuracy of the behavioral anomaly judgment of the above-mentioned sewage treatment plant.

[0154] The specific implementation methods described above further illustrate the objectives, technical solutions and beneficial effects of the present invention in detail. It should be understood that the above description is only a specific implementation method of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the scope of protection of the present invention.

Claims

1. A method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data, characterized in that: The following steps are involved: Acquiring historical data from the sewage treatment plant to be monitored, and performing data cleaning on the historical data to obtain historical cleansed data; Calculating the weight coefficient of each indicator in the historical cleansing data, and selecting the three indicators with the largest weight coefficients as behavioral indicators; Constructing a behavior abnormality determination model based on the behavior indicators; Establishing a credibility index for behavior abnormality determination based on the determination result of the behavior abnormality determination model to obtain the credibility of the behavior abnormality determination; Before calculating the weight coefficients of each indicator in the historical cleaning data, it is necessary to correct or supplement the data of the actual treatment scale and the total amount of sewage treated throughout the year, including the following steps: Determine whether the total annual sewage treatment volume and the actual treatment scale meet the conditions, which are: or in, Indicates the The actual treatment scale data of sewage treatment plants, Representative The total annual sewage treatment volume data of sewage treatment plants; like and There is a solution that meets the conditions, then according to Modifying the actual processing scale data; like and There is no solution, the conditions are not met, then according to Complete the corresponding actual treatment scale data or annual sewage treatment volume data; Calculate the relative membership according to the weight coefficient of each indicator, sort the indicators by weight, and select three indicators with larger weight coefficients as behavioral indicators; According to the weight coefficients of the above indicators, the relative membership is calculated. The specific formula is as follows: in, in, is the relative membership, is the feature matrix, It is The weight coefficient of the indicator, is the judgment matrix, It is The indicator for The relative value of an indicator ranges from [1, 9] and its reciprocal. It is The indicator for The score of the indicator, It is The relative index The relative membership of an indicator.

2. The method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data according to claim 1, characterized in that: The indicators include actual treatment scale, total annual sewage treatment volume, sewage treatment process, annual sewage treatment rate, designed treatment scale, cumulative completed sewage pipeline length, emission standards and construction and operation status.

3. The method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data according to claim 2, characterized in that: The historical data includes daily power consumption data and daily indication data. Cleaning the daily power consumption data in the historical data includes the following steps: Determine whether there is missing data in the daily electricity consumption data; If there is missing data, mark the missing data and obtain the value data of the day to determine whether the value data of the day is missing. If the daily indication data is missing, calculate the average of the daily electricity consumption data for the days adjacent to the daily electricity consumption data, record the average at the mark, fill in the missing data, and then return to the process of determining whether there is missing data in the daily electricity consumption data to continue execution; If the indicated data for the day is not missing, the difference of the indicated data for the day is calculated, the difference is recorded at the mark, the missing data is filled, and the process returns to the step of determining whether there is missing data in the daily power consumption data; If there is no missing data, historical cleaned data is obtained.

4. The method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data according to claim 1, characterized in that: The behavior abnormality determination model includes one or more abnormality determinations, including the following steps: Determining whether all daily electricity consumption data in the sewage treatment plant are 0; If all are 0, the sewage treatment plant is judged to have abnormal daily electricity consumption; If not all are 0, the sewage treatment plant is judged to have normal daily electricity consumption; Calculate the electricity consumption per ton of water of the sewage treatment plant based on the actual treatment scale data and daily electricity consumption data; The sewage treatment plants are divided into multiple categories according to their actual treatment scale, and the average power consumption per ton of water for all sewage treatment plants in each category is calculated; 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 electricity consumption per ton of water; If so, the sewage treatment plant is judged to have abnormal electricity consumption per ton of water; If not, the electricity consumption per ton of water of the sewage treatment plant is normal; Calculate the coefficient of variation of the daily electricity consumption data of the sewage treatment plant, and determine whether the coefficient of variation is greater than 0.36; If it is greater than, the sewage treatment plant is judged to have abnormal daily power consumption fluctuation; If it is not greater than, the daily electricity consumption fluctuation of the sewage treatment plant is normal.

5. The method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data according to claim 4 is characterized in that: The determination result includes one or more of abnormal daily power consumption, abnormal power consumption per ton of water, and abnormal daily power consumption fluctuation; The determination result includes three levels of abnormal behavior, and the abnormal daily power consumption is a level one abnormal behavior; If both the abnormal power consumption per ton of water and the abnormal fluctuation of daily power consumption are abnormal, it is a secondary abnormal behavior; Any one of the abnormalities in power consumption per ton of water and the abnormal fluctuation in daily power consumption is a level three behavioral abnormality.

6. The method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data according to claim 5, characterized in that: Determining a behavioral anomaly level of the sewage treatment plant, and calculating a behavioral anomaly determination reliability based on the behavioral anomaly level of the sewage treatment plant; If the sewage treatment plant is a level one behavioral anomaly, the credibility of the behavioral anomaly determination is 100%; If the sewage treatment plant is a secondary behavioral anomaly, the calculation formula for the behavioral anomaly determination reliability is as follows: If the sewage treatment plant is at level 3 behavioral abnormality, the calculation formula for the behavioral abnormality determination reliability is as follows: in, Indicates the statistical time period Neidi The reliability of abnormality judgment of sewage treatment plants, Indicates the statistical time period Neidi The actual treatment scale of the sewage treatment plant and the daily electricity consumption reach the equilibrium value in a balanced state. Indicates the statistical time period Neidi The electricity consumption per ton of water in sewage treatment plants, Indicates the average electricity consumption per ton of water in this category. Indicates the statistical time period Neidi The coefficient of variation of daily electricity consumption data of sewage treatment plants.

7. A sewage treatment plant behavior abnormality determination system based on electricity consumption data is characterized by: The determination system is used to implement the method for determining abnormal behavior of a sewage treatment plant based on electricity consumption data as described in any one of claims 1 to 6, and the determination system includes: An acquisition unit (1) for acquiring historical data from the sewage treatment plant to be monitored; Processing unit (2), Used to clean the historical data to obtain historical cleaned data; Calculating the weight coefficient of each indicator in the historical cleansing data, and selecting the three indicators with the largest weight coefficients as behavioral indicators; Constructing a behavior abnormality determination model based on the behavior indicators; Establishing a credibility index for behavior abnormality determination based on the determination result of the behavior abnormality determination model to obtain the credibility of the behavior abnormality determination; The output unit (3) is used to output the credibility of the abnormal behavior judgment of the sewage treatment plant to be monitored.

Images