Industrial electricity safety situation analysis method and system based on electric power data

Abstract

The invention relates to the field of power safety, in particular to an industrial power utilization safety situation analysis method and system based on power data, and the method comprises the steps: screening the abnormal types of power utilization abnormal enterprises to obtain a target abnormal type, and scoring the alarm rate of the target abnormal type to obtain an alarm rate score; comparing the power data of the enterprises in the current time period with the power consumption data of the same time period in the previous year to obtain the proportion of the number of enterprises with obviously increased power consumption, the proportion of the number of enterprises with obviously increased power consumption being greater than a preset value compared with the power consumption of the same time period in the previous year, and scoring the proportion of the number of enterprises with obviously increased power consumption to obtain the score of the proportion of the number of enterprises with obviously increased power consumption; and carrying out weighted summation on the alarm rate score and / or the proportion score of the number of enterprises with obviously increased power consumption and the power consumption change scores under different dimensions to obtain focus targets under different dimensions, thereby realizing enterprise security situation analysis. According to the invention, the verification and analysis of the safety situation of industrial electricity under different dimensions are realized, the consideration is comprehensive, and the calculation is simple.

Description

Technical Field

[0001] The present invention relates to the field of power safety analysis, and in particular to a method and system for analyzing industrial power safety situation based on power data. Background Art

[0002] The importance of enterprise safety production is unquestionable, especially for enterprises in high-risk industries such as coal mines, dangerous chemicals, fireworks and firecrackers, and dust explosions. The safety production of these industries has always been the focus of emergency management departments. Safety production is particularly important before, during and after holidays. Some enterprises have repeatedly engaged in illegal mining and illegal use of electricity. The current emergency management department analyzes the safety situation of these enterprises mainly through on-site verification and surprise inspections, but this method has poor timeliness and can only detect enterprises with superficial problems. The verification is not comprehensive, and cannot timely and accurately detect enterprises with potential problems, and thus cannot achieve timely control and guidance of potential problem enterprises.

[0003] Chinese patent CN113705229A discloses a method for identifying illegal production of high-risk enterprises based on power big data. The method constructs a high-risk enterprise identification model and an illegal production identification model, identifies high-risk enterprises through the high-risk enterprise identification model, constructs a power production characteristic feature library for high-risk enterprises, extracts and screens power characteristics, and uses the screened power production characteristics to establish and train an illegal production identification model to identify high-risk enterprises with illegal production. This method requires training of both models and requires the collection of a large amount of data, which is difficult to collect. In addition, the parameters of the trained model are fixed, and the production fluctuations of enterprises are large, especially before and after holidays. It is difficult for existing models to accurately predict enterprise data in special periods. If you want to predict enterprise data in special periods, you need to train a large amount of data, which is cumbersome to operate and has poor real-time performance. Summary of the invention

[0004] In order to solve the problems that the manual verification in the prior art is poor in timeliness and incomplete and untimely, and the existing machine learning model requires a large amount of verification data and requires frequent training, the present invention proposes an industrial power safety situation analysis method based on power data, including:

[0005] The abnormal types of enterprises with abnormal electricity consumption are screened to obtain target abnormal types, and the alarm rates of the target abnormal types are scored to obtain alarm rate scores;

[0006] Compare the electricity consumption data of the enterprise in the current period with the electricity consumption data of the same period in previous years, obtain the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the electricity consumption in the same period in previous years, and score the proportion of enterprises with obvious increase in electricity consumption to obtain the score of the proportion of enterprises with obvious increase in electricity consumption;

[0007] The alarm rate score and / or the score of the proportion of enterprises with a significant increase in electricity consumption, as well as the electricity consumption change scores in different dimensions are weighted and summed to obtain the key focus targets in different dimensions, thereby realizing enterprise security situation analysis.

[0008] Optionally, the dimension includes a regional dimension and an enterprise dimension, and the weighted sum of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, and the electricity consumption change scores under different dimensions to obtain the key focus targets under different dimensions include:

[0009] In the regional dimension, the warning rate score of the target abnormal type, the score of the proportion of enterprises with significantly increased electricity consumption, and the score of regional electricity consumption change are weighted and summed, and the region with a weighted sum value greater than the first preset value is the focus target;

[0010] In the enterprise dimension, the alarm rate score of the target abnormal type and the electricity consumption change score of the enterprise with obvious increase in electricity consumption are weighted and summed, and the enterprise whose weighted sum value is greater than the second preset value is the key focus target.

[0011] Optionally, in the regional dimension, the weight A1 of the warning rate score ranges from 0.2 to 0.4, the weight A2 of the score of the proportion of enterprises with significantly increased electricity consumption ranges from 0.4 to 0.6, and the weight A3 of the regional electricity consumption change score ranges from 0.2 to 0.3, wherein A1+A2+A3=1;

[0012] In the enterprise dimension, the weight B1 of the alarm rate score ranges from 0.2 to 0.5, and the weight B2 of the electricity consumption change score of enterprises with significantly increased electricity consumption ranges from 0.5 to 0.8, where B1+B2=1.

[0013] Optionally, the abnormal electricity consumption enterprise is obtained in the following ways:

[0014] Based on the electricity data of the enterprises in the current period, the electricity consumption behaviors of the enterprises are classified to obtain enterprises with abnormal electricity consumption.

[0015] Optionally, before classifying the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, the step further includes constructing a scoring database, wherein the scoring database includes one or more of the following types:

[0016] A regional electricity consumption change score database is used to characterize the scores corresponding to the regional electricity consumption change rates, wherein the greater the regional electricity consumption change rate, the higher the corresponding score;

[0017] The target anomaly type warning rate scoring database is used to characterize the corresponding scores of the target anomaly type warning rates, where the higher the warning rate, the greater the corresponding score;

[0018] The scoring database of the number of enterprises with a significant increase in electricity consumption is used to represent the corresponding scores of the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the same period in previous years. The larger the proportion of enterprises, the higher the corresponding score;

[0019] The enterprise electricity consumption change scoring database is used to characterize the corresponding score of each enterprise's electricity consumption change rate, where the greater the enterprise's electricity consumption change rate, the higher the corresponding score.

[0020] Optionally, the electricity consumption behavior of the enterprise is classified based on the electricity data of the enterprise in the current period, including:

[0021] The power data of enterprises in the current period are screened to obtain the enterprises in production, and the electricity consumption behaviors of the enterprises are classified based on the power data of the enterprises in production in the current period.

[0022] Optionally, the abnormal types include overload production, daytime shutdown and nighttime operation, and emergency production shutdown.

[0023] Optionally, the target abnormality type is overload production.

[0024] Optionally, the alarm rate is the number of times the target abnormality type occurs divided by the total number of days in the current period divided by the total number of enterprises.

[0025] The second aspect of the present application provides an industrial power safety situation analysis system based on power data, comprising:

[0026] The first acquisition module is used to screen the abnormal types of enterprises with abnormal electricity consumption to obtain a target abnormal type, and score the alarm rate of the target abnormal type to obtain an alarm rate score;

[0027] The second acquisition module is used to compare the electricity consumption data of the enterprise in the current period with the electricity consumption data of the same period in previous years, obtain the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the electricity consumption in the same period in previous years, and score the proportion of enterprises with obvious increase in electricity consumption to obtain the score of the proportion of enterprises with obvious increase in electricity consumption;

[0028] The analysis module is used to perform weighted summation of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, as well as the electricity consumption change scores in different dimensions to obtain key focus targets in different dimensions and realize enterprise security situation analysis.

[0029] Optionally, the dimensions in the analysis module include a regional dimension and an enterprise dimension, and the weighted sum of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, and the electricity consumption change scores under different dimensions to obtain the key focus targets under different dimensions includes:

[0030] In the regional dimension, the warning rate score of the target abnormal type, the score of the proportion of enterprises with significantly increased electricity consumption, and the score of regional electricity consumption change are weighted and summed, and the region with a weighted sum value greater than the first preset value is the focus target;

[0031] In the enterprise dimension, the alarm rate score of the target abnormal type and the electricity consumption change score of the enterprise with obvious increase in electricity consumption are weighted and summed, and the enterprise whose weighted sum value is greater than the second preset value is the key focus target.

[0032] Optionally, in the analysis module, under the regional dimension, the weight A1 of the alarm rate score ranges from 0.2 to 0.4, the weight A2 of the score of the proportion of enterprises with significantly increased electricity consumption ranges from 0.4 to 0.6, and the weight A3 of the regional electricity consumption change score ranges from 0.2 to 0.3, wherein A1+A2+A3=1;

[0033] In the enterprise dimension, the weight B1 of the alarm rate score ranges from 0.2 to 0.5, and the weight B2 of the electricity consumption change score of enterprises with significantly increased electricity consumption ranges from 0.5 to 0.8, where B1+B2=1.

[0034] Optionally, the enterprise with abnormal electricity consumption in the first acquisition module is obtained in the following manner:

[0035] Based on the electricity data of the enterprises in the current period, the electricity consumption behaviors of the enterprises are classified to obtain enterprises with abnormal electricity consumption.

[0036] Optionally, before the first acquisition module classifies the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, it also includes building a scoring database, and the scoring database includes one or more of the following types:

[0037] A regional electricity consumption change score database is used to characterize the scores corresponding to the regional electricity consumption change rates, wherein the greater the regional electricity consumption change rate, the higher the corresponding score;

[0038] The target anomaly type warning rate scoring database is used to characterize the corresponding scores of the target anomaly type warning rates, where the higher the warning rate, the greater the corresponding score;

[0039] The scoring database of the number of enterprises with a significant increase in electricity consumption is used to represent the corresponding scores of the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the same period in previous years. The larger the proportion of enterprises, the higher the corresponding score;

[0040] The enterprise electricity consumption change scoring database is used to characterize the corresponding score of each enterprise's electricity consumption change rate, where the greater the enterprise's electricity consumption change rate, the higher the corresponding score.

[0041] Optionally, the first acquisition module classifies the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, including:

[0042] The power data of enterprises in the current period are screened to obtain the enterprises in production, and the electricity consumption behaviors of the enterprises are classified based on the power data of the enterprises in production in the current period.

[0043] Optionally, the abnormality types in the first acquisition module include overload production, daytime shutdown and night operation, and emergency production shutdown.

[0044] Optionally, the target abnormality type in the first acquisition module is overload production.

[0045] Optionally, the alarm rate in the first acquisition module is the number of times the target abnormality type occurs divided by the total number of days in the current period divided by the total number of enterprises.

[0046] Compared with the prior art, the present invention has the following beneficial effects:

[0047] The present invention provides a method and system for analyzing the safety situation of industrial electricity consumption based on power data, the method comprising: screening the abnormal types of enterprises with abnormal electricity consumption to obtain target abnormal types, scoring the alarm rate of the target abnormal type to obtain an alarm rate score; comparing the electricity data of the enterprise in the current period with the electricity consumption data in the same period of previous years, obtaining the proportion of enterprises with significantly increased electricity consumption in the current period compared with the electricity consumption in the same period of previous years that is greater than a preset value, and scoring the proportion of enterprises with significantly increased electricity consumption to obtain a score for the proportion of enterprises with significantly increased electricity consumption; weightedly summing the alarm rate score and / or the score for the proportion of enterprises with significantly increased electricity consumption, as well as the electricity consumption change scores in different dimensions to obtain key focus targets in different dimensions, so as to realize enterprise safety situation analysis; the present application performs weighted summing of different scoring types in different dimensions to realize verification and analysis of the industrial electricity safety situation in different dimensions, with comprehensive consideration and simple calculation. BRIEF DESCRIPTION OF THE DRAWINGS

[0048] Figure 1 A flow chart of the enterprise security situation analysis method based on power data of the present invention;

[0049] Figure 2 It is a schematic diagram of the application of the enterprise security situation analysis method based on power data of the present invention;

[0050] Figure 3 It is a structural schematic diagram of the enterprise security situation analysis system based on power data of the present invention. DETAILED DESCRIPTION

[0051] The present invention proposes a method and system for analyzing enterprise safety situation based on power data, which can identify potential dangerous areas and enterprises based on the power data of the enterprise, and can realize enterprise safety inspection statistics and prediction during daily and holiday periods.

[0052] The Ministry of Emergency Management focuses on enterprises in high-risk industries such as hazardous chemicals, coal mines, non-coal mines, fireworks and firecrackers, key industrial and commercial trade, etc., based on the daily electricity consumption data of enterprises, abnormal electricity consumption behavior of enterprises (including overload production, daytime shutdown and night operation, emergency production shutdown, etc.), and enterprise electricity consumption change data. Based on the above data, the analysis indicators are determined, and the production and shutdown indicators such as enterprise production, shutdown, and production rate are sorted out, and warning indicators such as suspected overload, daytime shutdown and night operation, and emergency production shutdown are obtained. Based on the comparison with previous data, the number of enterprises with a significant increase in electricity consumption, the number of enterprises with a significant decrease in electricity consumption, and the number of enterprises that remain stable are obtained. These indicators are screened and scored to obtain key focus targets in different dimensions, and then assist the emergency management department in analyzing the daily and holiday production safety situation of enterprises.

[0053] Embodiment 1:

[0054] The emergency part focuses on high-risk industries such as hazardous chemicals, coal mines, non-coal mines, fireworks and firecrackers, key industrial and commercial trade, etc., and can conduct safety analysis of the situation before and after the holidays, such as the Spring Festival, May Day, National Day, etc. This embodiment takes the safety situation analysis of hazardous chemicals industry and coal mining industry enterprises before the Spring Festival in 2024 as an example to introduce the method in this application, such as Figure 1 As shown, the process includes the following steps S1 to S3.

[0055] S1: Screen the abnormal types of enterprises with abnormal electricity consumption to obtain a target abnormal type, and score the alarm rate of the target abnormal type to obtain an alarm rate score, wherein the alarm rate is the number of times the target abnormal type occurs divided by the total number of days in the current period divided by the total number of enterprises.

[0056] The abnormal electricity consumption enterprise is obtained in the following ways:

[0057] Based on the electricity data of the enterprise in the current period, the electricity consumption behavior of the enterprise is classified to obtain the enterprises with abnormal electricity consumption. The specific method is as follows.

[0058] Step 1: Determine the analysis date

[0059] The 2024 Spring Festival holidays are from 2024.2.10 to 2024.2.17. Based on the 2024 Spring Festival statutory holidays, we will analyze the safety production situation of enterprises before the festival and help emergency management departments to make arrangements and provide guidance for post-festival safety work. The pre-festival analysis period is (one week before the Spring Festival): 2024.2.3 to 2024.2.9.

[0060] The corresponding comparative analysis time period on the eve of the 2023 Spring Festival is: 2023.1.14-2024.1.20.

[0061] Step 2: Data preparation and cleaning

[0062] The electricity data of enterprises in the hazardous chemicals industry and coal mining industry for a total of 14 days, including the 7 days before the Spring Festival in 2024 and the 7 days before 2023, were sorted and processed, and enterprises whose daily electricity consumption was greater than the preset value were screened out. The purpose was to screen out the enterprises in production and obtain the scope of analyzed enterprises.

[0063] Calculate the production status of the enterprise on a daily basis to obtain the daily production and shutdown status of the enterprise, and make statistics on the information, including one or more of the following: enterprise name, province, city, county, industry type, date, or whether it is in production.

[0064] Based on the electricity data of the enterprise in the current period, the electricity consumption behavior of the enterprise is classified, especially the abnormal electricity consumption behavior of the enterprise is counted to obtain whether the enterprise has abnormal types such as overload production, daytime shutdown and night operation, emergency production shutdown, etc., and the data is counted, including one or more of the following: enterprise name, province, city, county, industry type, date, whether abnormal electricity consumption behavior occurs, and type of abnormal electricity consumption behavior.

[0065] Based on the above data, the overall electricity consumption changes are statistically analyzed:

[0066] The daily electricity consumption of enterprises is summarized and counted from the dimensions of industry, region, etc. to obtain the summarized electricity consumption by industry and region. The data information includes one or more of the following: industry type, region, electricity consumption in the 7 days before the Spring Festival in 2024, electricity consumption in the 7 days before the Spring Festival in 2023, and electricity consumption change ratio. Among them, the region includes each region and the total value.

[0067] Based on the above data, the production statistics by region and industry are as follows:

[0068] The total number of enterprises and the number of enterprises in production are counted from the dimensions of industry and region, and the total number of enterprises and the number of enterprises in production are obtained by industry and region. The calculation method is: the total number of enterprises and the number of enterprises in production are summarized from the dimensions of industry and region on a daily basis. The total number and the number of enterprises in production in the 7 days before the Spring Festival in 2024 and the total number and the number of enterprises in production in the 7 days before the Spring Festival in 2023 are the sum of 7 days and divided by 7, respectively. The production rate is: the number of enterprises in production divided by the total number of enterprises. The data information includes one or more of the following: industry type, region, the total number of enterprises in the 7 days before the Spring Festival in 2024, the average number of enterprises in production in the 7 days before the Spring Festival in 2024, the average production rate in the 7 days before the Spring Festival in 2024, the total number of enterprises in the 7 days before the Spring Festival in 2023, the average number of enterprises in production in the 7 days before the Spring Festival in 2023, and the average production rate in the 7 days before the Spring Festival in 2023. The region includes each region and the total value.

[0069] Based on the above data, statistics on abnormal electricity consumption behaviors of enterprises are conducted:

[0070] Statistics of enterprises with abnormal electricity consumption in the industry are conducted from the dimensions of industry, region, etc. First, the number of overload production, daytime shutdown and night operation, and emergency production shutdown in the two time periods of 7 days before the Spring Festival in 2024 and 2023 are counted respectively, and the sums are added up according to the type of abnormality; second, the number of enterprises with abnormal electricity consumption in the two time periods is counted respectively. The statistical rule is that as long as an enterprise has at least one overload production, it is counted as one enterprise, as long as an enterprise has at least one daytime shutdown and night operation, it is counted as one enterprise, and as long as an enterprise has at least one emergency production shutdown, it is counted as one enterprise. Therefore, the statistical data information includes one or more of the following: industry, region, number of overload production in the 7 days before the Spring Festival in 2024, number of overload production in the 7 days before the Spring Festival in 2023, number of daytime stops and night starts in the 7 days before the Spring Festival in 2024, number of daytime stops and night starts in the 7 days before the Spring Festival in 2023, number of emergency production stops in the 7 days before the Spring Festival in 2024, number of emergency production stops in the 7 days before the Spring Festival in 2023, number of entrepreneurs with overload production in the 7 days before the Spring Festival in 2024, number of entrepreneurs with overload production in the 7 days before the Spring Festival in 2023, number of entrepreneurs who stopped during the day and started at night in the 7 days before the Spring Festival in 2024, number of entrepreneurs who stopped during the day and started at night in the 7 days before the Spring Festival in 2023, number of entrepreneurs with emergency production stops in the 7 days before the Spring Festival in 2024, number of entrepreneurs with emergency production stops in the 7 days before the Spring Festival in 2023, among which, region includes all regions and the total value.

[0071] In a further preferred solution, before classifying the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, it also includes building a scoring database, and obtaining the warning rate score, the proportion score of the number of enterprises with obvious increase in electricity consumption, the regional electricity consumption change score and the enterprise electricity consumption change score based on the scoring database, wherein the scoring database includes one or more of the following types:

[0072] The regional electricity consumption change scoring database is used to characterize the scores corresponding to the regional electricity consumption change rates, wherein the greater the regional electricity consumption change rate, the higher the corresponding score, for example, as shown in the following Table 1:

[0073] Table 1: Regional electricity consumption change scoring criteria

[0074]

[0075]

[0076] The target abnormal type alarm rate scoring database is used to characterize the corresponding score of the target abnormal type alarm rate. The alarm rate is calculated as follows: the number of overload productions in the region during the current period divided by the total number of days in the current period divided by the total number of enterprises in the region * 100%. The higher the alarm rate, the greater the corresponding score, for example, as shown in Table 2 below:

[0077] Table 2: Target anomaly type warning rate scoring criteria

[0078]

[0079] The scoring database of the number of enterprises with a significant increase in electricity consumption is used to represent the corresponding scores of the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the same period in previous years. The larger the proportion of enterprises, the higher the corresponding score, for example, as shown in Table 3 below:

[0080] Table 3: Scoring criteria for the number of enterprises with significant increase in electricity consumption

[0081]

[0082] The enterprise electricity consumption change scoring database is used to characterize the corresponding score of each enterprise's electricity consumption change rate, wherein the greater the enterprise's electricity consumption change rate, the higher the corresponding score, for example, as shown in the following Table 4:

[0083] Table 4: Scoring criteria for enterprise electricity consumption change rate

[0084]

[0085] In this embodiment, the abnormal type of enterprises with potential dangers is mainly overload production. Therefore, overload production is used as the target abnormal type, and the alarm rate score is obtained by scoring based on the alarm rate of the target type. The specific scoring is based on the scoring criteria (Table 2) in the target abnormal type alarm rate scoring database.

[0086] S2: Compare the electricity consumption data of the enterprises in the current period with the electricity consumption data in the same period of previous years to obtain the proportion of enterprises whose electricity consumption in the current period is significantly higher than the preset value compared with the same period of previous years, and score the proportion of enterprises with significantly increased electricity consumption.

[0087] Calculate the change in enterprise electricity consumption and obtain the electricity consumption change data of each enterprise. The calculation method is: calculate the total electricity consumption sum1 of each enterprise in the 7 days before the Spring Festival in 2024, and then calculate the total electricity consumption sum2 of each enterprise in the 7 days before the Spring Festival last year. The electricity consumption change calculation formula is: (sum1-sum2) / sum2*100%. Mark the enterprise electricity consumption change value respectively. If the electricity consumption change is greater than the preset value (for example, 20%), the electricity consumption of the enterprise in the 7 days before the Spring Festival in 2024 is "significantly increased" compared with the electricity consumption in the 7 days before the Spring Festival last year. If the change in electricity consumption is less than -20%, the enterprise's electricity consumption in the seven days before the Spring Festival in 2024 will be "significantly lower" than that in the seven days before the Spring Festival last year. If it is between -20% and 20%, the enterprise's electricity consumption is "remaining stable". The above data are counted, including one or more of the following: enterprise name, province, city, county, industry type, electricity consumption in the seven days before the Spring Festival in 2024, electricity consumption in the seven days before the Spring Festival in 2023, electricity consumption change ratio, and change status, among which the change status is a significant increase, a significant decrease, or a stable status.

[0088] Furthermore, statistics on enterprises that have changed their electricity consumption are conducted from the dimensions of industry and region, and the number of enterprises in each industry and region that have increased significantly, decreased significantly, or remained stable is obtained. The data are counted, and the statistical categories include one or more of the following: industry, region, number of enterprises that have increased significantly, number of enterprises that have decreased significantly, number of enterprises that have remained stable, proportion of enterprises that have increased significantly, proportion of enterprises that have decreased significantly, and proportion of enterprises that have remained stable. Among them, region includes all regions and the total value. The calculation formulas for the proportion of enterprises that have increased significantly, the proportion of enterprises that have decreased significantly, and the proportion of enterprises that have remained stable are as follows:

[0089] The percentage of enterprises with obvious increase = the number of enterprises with obvious increase / (the number of enterprises with obvious increase + the number of enterprises with obvious decrease + the number of enterprises with stable performance) * 100%

[0090] The percentage of enterprises with obvious decline = the number of enterprises with obvious decline / (the number of enterprises with obvious increase + the number of enterprises with obvious decline + the number of enterprises with stable performance) * 100%

[0091] The percentage of enterprises that remain stable = the number of enterprises that remain stable / (the number of enterprises that increase significantly + the number of enterprises that decrease significantly + the number of enterprises that remain stable) * 100%

[0092] The key enterprises that affect safety are mainly those with a significant increase in electricity consumption. Therefore, it is necessary to score the proportion of enterprises with a significant increase in electricity consumption. The specific scoring can be based on the scoring criteria in the above-mentioned database for scoring the proportion of enterprises with a significant increase in electricity consumption.

[0093] S3: Perform a weighted summation of the alarm rate score and / or the score of the proportion of enterprises with a significant increase in electricity consumption, as well as the electricity consumption change scores in different dimensions to obtain key focus targets in different dimensions, so as to achieve enterprise security situation analysis.

[0094] In a further preferred solution, the dimension includes a regional dimension and an enterprise dimension, and in different dimensions, at least two of the alarm rate score, the enterprise number score, and the electricity consumption change score in the corresponding dimension are weighted to obtain the key focus target in the corresponding dimension, including:

[0095] In the regional dimension, the warning rate score, enterprise proportion score and regional electricity consumption change score of the target abnormal type are weighted and summed, and the region with a weighted value greater than the first preset value is the target focus region;

[0096] In the enterprise dimension, the warning rate score of the target abnormal type and the enterprise electricity consumption change score are weighted and summed, and the enterprise whose weighted value is greater than the second preset value is the target focus enterprise.

[0097] In a further preferred solution, in the regional dimension, the weight A1 of the alarm rate score ranges from 0.2 to 0.4, the weight A2 of the score of the proportion of enterprises with significantly increased electricity consumption ranges from 0.4 to 0.6, and the weight A3 of the regional electricity consumption change score ranges from 0.2 to 0.3, wherein A1+A2+A3=1;

[0098] In the enterprise dimension, the weight B1 of the alarm rate score ranges from 0.2 to 0.5, and the weight B2 of the electricity consumption change score of enterprises with significantly increased electricity consumption ranges from 0.5 to 0.8, where B1+B2=1.

[0099] For example, in the regional dimension, the weight coefficients of the target abnormality type alarm rate score, the percentage score of enterprises with obvious increase in electricity consumption, and the regional electricity consumption change score are 0.35, 0.4, and 0.25, respectively. Each region is weighted to obtain a comprehensive score of each region. The region with a comprehensive score greater than the first preset value is the target focus region, that is, the focus target. For example, the region with a comprehensive score greater than 7 is set as the focus target; in the enterprise dimension, the weight coefficients of the target abnormality type alarm rate score and the electricity consumption change score of enterprises with obvious increase in electricity consumption are 0.35 and 0. 65, weight each enterprise separately to get the comprehensive score of each enterprise, and the enterprise with a comprehensive score greater than the second preset value is the target enterprise, that is, the key focus target. For example, 7 days before the Spring Festival in 2024, the electricity consumption of enterprise A changed by 67%, corresponding to a score of 6, the number of overloads was 2, and the overload alarm rate was 28.6%, corresponding to a score of 2. The comprehensive score of the enterprise is: 6*0.65+2*0.35=4.6. The enterprise is ranked according to its comprehensive score, and the second preset value is set to 6. Enterprises with a score exceeding 6 are regarded as key focus enterprises with potential dangers.

[0100] Using the above method, we can obtain the overall number of enterprises in production by industry and region, information on production rates and changes, overall electricity consumption and changes in electricity consumption by industry and region, changes in abnormal production behaviors by industry and region, and changes in electricity consumption of enterprises by industry and region. At the same time, based on the above analysis results, we can obtain a list of key areas of concern and a list of key enterprises. The final analysis results and analysis reports will assist emergency management departments in conducting holiday production safety situation analysis and safety work deployment guidance. This application is conducive to the timely discovery of potential dangerous areas and enterprises, can assist in the analysis of daily safety situations, and provide guidance for future resumption of work and production. This analysis method is not only applicable to the analysis of holiday production safety situations of various high-risk industries such as coal mines, dangerous chemicals, non-coal mines, fireworks and firecrackers, but can also be used for other electricity-consuming production enterprises. Moreover, this analysis method can not only calculate the production safety situation during holidays, but also specify time periods for calculation and analysis according to the rules.

[0101] In the process, if Figure 2 As shown, the solution in this application mainly includes:

[0102] Step 1: Determine the analysis date to determine the time range for data collection;

[0103] Step 2: Data preparation and cleaning, determining the scope of enterprises in production and analysis;

[0104] Step 3: Calculate indicators, based on the cleaned data, calculate the enterprise's production data, overload production, daytime shutdown and night operation, emergency production shutdown, and enterprise electricity consumption change data statistics;

[0105] Step 4: Analyze the statistical results, including the production data by industry and region, the abnormal behavior data of overload production, daytime shutdown and night operation, and emergency production shutdown by industry and region, and the change data of enterprise electricity consumption by industry and region;

[0106] Step 5: Calculate the weighted scores. Under the region and enterprise dimensions, weight the key statistical results under the dimension to obtain the comprehensive scores under the corresponding dimensions. The regions or enterprises with comprehensive scores greater than the preset values ​​are the target focus regions or target focus enterprises.

[0107] Step 6: Conduct further comprehensive analysis on the target areas or target companies. For example, you can predict dangerous prospects based on existing data to prevent accidents.

[0108] Based on the enterprise electricity consumption analysis data, the present invention proposes a holiday enterprise safety production situation analysis method based on power data, conducts analysis on electricity consumption and illegal production of high-risk enterprises during and before and after holidays, assists the Ministry of Emergency Management in making good arrangements for holiday safety production and strengthens safety inspections for resumption of work and production after the holidays, innovates analysis techniques, solves the problems of large manual verification workload, long time consumption, incomplete verification, high verification labor costs, etc. during holidays, and better assists the modernization of emergency management systems and capabilities.

[0109] Embodiment 2:

[0110] The present invention based on the same inventive concept also provides an industrial power safety situation analysis system based on power data, such as Figure 3 As shown, including:

[0111] The first acquisition module is used to screen the abnormal types of enterprises with abnormal electricity consumption to obtain a target abnormal type, and score the alarm rate of the target abnormal type to obtain an alarm rate score;

[0112] The second acquisition module is used to compare the electricity consumption data of the enterprise in the current period with the electricity consumption data of the same period in previous years, obtain the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the electricity consumption in the same period in previous years, and score the proportion of enterprises with obvious increase in electricity consumption to obtain the score of the proportion of enterprises with obvious increase in electricity consumption;

[0113] The analysis module is used to perform weighted summation of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, as well as the electricity consumption change scores in different dimensions to obtain key focus targets in different dimensions and realize enterprise security situation analysis.

[0114] In a further preferred solution, the dimensions in the analysis module include regional dimensions and enterprise dimensions, and the weighted sum of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, and the electricity consumption change scores under different dimensions to obtain the key focus targets under different dimensions include:

[0115] In the regional dimension, the warning rate score of the target abnormal type, the score of the proportion of enterprises with significantly increased electricity consumption, and the score of regional electricity consumption change are weighted and summed, and the region with a weighted sum value greater than the first preset value is the focus target;

[0116] In the enterprise dimension, the alarm rate score of the target abnormal type and the electricity consumption change score of the enterprise with obvious increase in electricity consumption are weighted and summed, and the enterprise whose weighted sum value is greater than the second preset value is the key focus target.

[0117] In a further preferred solution, in the analysis module, under the regional dimension, the weight A1 of the alarm rate score ranges from 0.2 to 0.4, the weight A2 of the score of the proportion of enterprises with significantly increased electricity consumption ranges from 0.4 to 0.6, and the weight A3 of the regional electricity consumption change score ranges from 0.2 to 0.3, wherein A1+A2+A3=1;

[0118] In the enterprise dimension, the weight B1 of the alarm rate score ranges from 0.2 to 0.5, and the weight B2 of the electricity consumption change score of enterprises with significantly increased electricity consumption ranges from 0.5 to 0.8, where B1+B2=1.

[0119] In a further preferred solution, the enterprises with abnormal electricity consumption in the first acquisition module are obtained in the following manner:

[0120] Based on the electricity data of the enterprises in the current period, the electricity consumption behaviors of the enterprises are classified to obtain enterprises with abnormal electricity consumption.

[0121] In a further preferred solution, before the first acquisition module classifies the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, it also includes building a scoring database, and the scoring database includes one or more of the following types:

[0122] The regional electricity consumption change score database is used to characterize the scores corresponding to the regional electricity consumption change rates, where the greater the regional electricity consumption change rate, the higher the corresponding score;

[0123] The target anomaly type warning rate scoring database is used to characterize the corresponding scores of the target anomaly type warning rates, where the higher the warning rate, the greater the corresponding score;

[0124] The scoring database of the number of enterprises with a significant increase in electricity consumption is used to represent the corresponding scores of the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the same period in previous years. The larger the proportion of enterprises, the higher the corresponding score;

[0125] The enterprise electricity consumption change scoring database is used to characterize the corresponding score of each enterprise's electricity consumption change rate, where the greater the enterprise's electricity consumption change rate, the higher the corresponding score.

[0126] In a further preferred solution, the first acquisition module classifies the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, including:

[0127] The power data of enterprises in the current period are screened to obtain the enterprises in production, and the electricity consumption behaviors of the enterprises are classified based on the power data of the enterprises in production in the current period.

[0128] In a further preferred solution, the abnormality types in the first acquisition module include overload production, daytime shutdown and nighttime operation, and emergency production shutdown.

[0129] In a further preferred solution, the target abnormality type in the first acquisition module is overload production.

[0130] In a further preferred solution, the alarm rate in the first acquisition module is the number of times the target abnormality type occurs divided by the total number of days in the current period divided by the total number of enterprises.

[0131] The above are merely embodiments of the present invention and are not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention are included in the scope of the claims of the present invention to be approved.

Claims

1. A method for analyzing industrial power safety situation based on power data, characterized in that: include: The abnormal types of enterprises with abnormal electricity consumption are screened to obtain target abnormal types, and the alarm rates of the target abnormal types are scored to obtain alarm rate scores; Compare the electricity consumption data of the enterprise in the current period with the electricity consumption data of the same period in previous years, obtain the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the electricity consumption in the same period in previous years, and score the proportion of enterprises with obvious increase in electricity consumption to obtain the score of the proportion of enterprises with obvious increase in electricity consumption; The alarm rate score and / or the score of the proportion of enterprises with a significant increase in electricity consumption, as well as the electricity consumption change scores in different dimensions are weighted and summed to obtain the key focus targets in different dimensions, thereby realizing enterprise security situation analysis.

2. The industrial electricity safety situation analysis method according to claim 1 is characterized in that: The dimensions include regional dimensions and enterprise dimensions. The weighted sum of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, and the electricity consumption change scores under different dimensions is used to obtain the key focus targets under different dimensions, including: In the regional dimension, the warning rate score of the target abnormal type, the score of the proportion of enterprises with significantly increased electricity consumption, and the score of regional electricity consumption change are weighted and summed, and the region with a weighted sum value greater than the first preset value is the focus target; In the enterprise dimension, the alarm rate score of the target abnormal type and the electricity consumption change score of the enterprise with obvious increase in electricity consumption are weighted and summed, and the enterprise whose weighted sum value is greater than the second preset value is the key focus target.

3. The industrial electricity safety situation analysis method according to claim 2 is characterized in that: In the regional dimension, the weight A1 of the warning rate score ranges from 0.2 to 0.4, the weight A2 of the proportion of enterprises with significantly increased electricity consumption ranges from 0.4 to 0.6, and the weight A3 of the regional electricity consumption change score ranges from 0.2 to 0.3, where A1+A2+A3=1; In the enterprise dimension, the weight B1 of the alarm rate score ranges from 0.2 to 0.5, and the weight B2 of the electricity consumption change score of enterprises with significantly increased electricity consumption ranges from 0.5 to 0.8, where B1+B2=1.

4. The industrial electricity safety situation analysis method according to claim 1 is characterized in that: The abnormal electricity consumption enterprise is obtained in the following ways: Based on the electricity data of the enterprises in the current period, the electricity consumption behaviors of the enterprises are classified to obtain enterprises with abnormal electricity consumption.

5. The industrial electricity safety situation analysis method according to claim 4, characterized in that: Before classifying the electricity consumption behavior of the enterprise based on the electricity data of the enterprise in the current period, it also includes building a scoring database, and the scoring database includes one or more of the following types: A regional electricity consumption change score database is used to characterize the scores corresponding to the regional electricity consumption change rates, wherein the greater the regional electricity consumption change rate, the higher the corresponding score; The target anomaly type warning rate scoring database is used to characterize the corresponding scores of the target anomaly type warning rates, where the higher the warning rate, the greater the corresponding score; The scoring database of the number of enterprises with a significant increase in electricity consumption is used to represent the corresponding scores of the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the same period in previous years. The larger the proportion of enterprises, the higher the corresponding score; The enterprise electricity consumption change scoring database is used to characterize the corresponding score of each enterprise's electricity consumption change rate, where the greater the enterprise's electricity consumption change rate, the higher the corresponding score.

6. The industrial electricity safety situation analysis method according to claim 4, characterized in that: Classify the electricity consumption behavior of enterprises based on the electricity data of the enterprise in the current period, including: The power data of enterprises in the current period are screened to obtain the enterprises in production, and the electricity consumption behaviors of the enterprises are classified based on the power data of the enterprises in production in the current period.

7. The industrial electricity safety situation analysis method according to claim 1, characterized in that: The abnormal types include overload production, daytime shutdown and night operation, and emergency production shutdown.

8. The industrial electricity safety situation analysis method according to claim 1 or 7, characterized in that: The target abnormality type is overload production.

9. The industrial electricity safety situation analysis method according to claim 1, characterized in that: The alarm rate is the number of times the target abnormal type occurs divided by the total number of days in the current period divided by the total number of enterprises.

10. An industrial power safety situation analysis system based on power data, characterized in that: include: The first acquisition module is used to screen the abnormal types of enterprises with abnormal electricity consumption to obtain a target abnormal type, and score the alarm rate of the target abnormal type to obtain an alarm rate score; The second acquisition module is used to compare the electricity consumption data of the enterprise in the current period with the electricity consumption data of the same period in previous years, obtain the proportion of enterprises whose electricity consumption in the current period is greater than the preset value compared with the electricity consumption in the same period in previous years, and score the proportion of enterprises with obvious increase in electricity consumption to obtain the score of the proportion of enterprises with obvious increase in electricity consumption; The analysis module is used to perform weighted summation of the alarm rate score and / or the score of the proportion of enterprises with significantly increased electricity consumption, as well as the electricity consumption change scores in different dimensions to obtain key focus targets in different dimensions and realize enterprise security situation analysis.

Images