Storage medium, method and device for identifying groundwater pollution in production enterprises
By acquiring data from manufacturing enterprises, screening for pollution indicators of interest and establishing correction equations, and using partial least squares regression and VIP analysis to determine key monitoring indicators, the problem of insufficient accuracy in groundwater pollution identification in existing technologies has been solved, achieving efficient and accurate pollution identification and cost reduction.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- CHINA PETROLEUM & CHEMICAL CORP
- Filing Date
- 2024-11-28
- Publication Date
- 2026-05-29
AI Technical Summary
The accuracy of groundwater pollution identification in existing enterprises is poor, mainly because historical monitoring data has many detection items and inconsistent quality, resulting in insufficient prediction accuracy of the prediction model.
By acquiring relevant enterprise data, screening pollution indicators of concern, establishing indicator correction equations, and using partial least squares regression and variable projection importance (VIP) analysis, key online monitoring indicators that are easy to measure are identified, and groundwater pollution is identified based on benchmark values.
It improved the accuracy and effectiveness of groundwater pollution identification in operating enterprises, reduced the frequency and cost of manual monitoring, and achieved rapid and accurate pollution identification.
Smart Images
Figure CN122114332A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of pollution monitoring, and in particular to storage media, methods, devices and equipment for identifying groundwater pollution in operating enterprises. Background Technology
[0002] Identifying groundwater pollution in operating enterprises to clarify the sources and types of pollution indicators can provide strong support for relevant departments to implement corresponding groundwater pollution prevention and control measures, which is of great significance.
[0003] For a long time, manual sampling and monitoring, comparing pollution index monitoring results with groundwater background values or relevant standard values, has been the primary method for identifying groundwater pollution. Groundwater monitoring frequency for key monitored enterprises in operation is generally once per quarter to once per year.
[0004] To facilitate rapid identification of groundwater pollution, patent application CN114660254A discloses a site groundwater pollution stratification in-situ online monitoring system and prediction method. In this patent application, based on historical site monitoring data, principal component analysis (PCA) and Pearson correlation coefficient are used to explore the correlation between easily measurable groundwater pollution variables (on-site measurable indicators) and pollution indicator concentrations. Kalman filters are then applied to predict changes in groundwater pollution indicator concentrations.
[0005] The inventors discovered through research that existing online monitoring methods for groundwater pollution have at least the following drawbacks:
[0006] Because historical monitoring data contains many detection items and has varying data quality, the prediction accuracy of the prediction model is poor, resulting in poor accuracy in identifying groundwater pollution in operating enterprises.
[0007] The information disclosed in the background section is intended only to enhance the understanding of the overall background of the present invention and should not be construed as an admission or in any way implying that the information constitutes prior art known to those skilled in the art. Summary of the Invention
[0008] The purpose of this invention is to improve the accuracy of groundwater pollution identification in operating enterprises.
[0009] This invention provides a method for identifying groundwater pollution in operating enterprises, comprising the following steps:
[0010] S11. Obtain pollution-related data information from the producing enterprise; the data information includes the enterprise's layout, the raw and auxiliary materials and processes involved, the groundwater depth and flow direction of the site, and historical water quality monitoring data; the historical water quality monitoring data includes online monitoring and easily measurable index values obtained through a portable water quality analyzer, pollution index values corresponding to various pollution indicators, and related records including the instrument model of the portable water quality analyzer.
[0011] S12. Select pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are those with a detection rate greater than a preset value, determined based on historical water quality monitoring values.
[0012] S13. Based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment, respectively, the index correction equations corresponding to each online monitoring easy-to-measure index value are obtained.
[0013] S14. According to the correction equations for each of the aforementioned indicators, the online monitoring and measurable values of each of the pollution indicators of concern in the historical water quality monitoring data are corrected.
[0014] S15. Using the corrected online monitoring easily measurable index as the independent variable and the pollution index value of the pollution index of concern as the dependent variable, the key online monitoring easily measurable index that has a key impact on the value of the pollution index of concern in groundwater is determined by partial least squares regression and variable projection importance (VIP) analysis, and the pollution index of concern is grouped according to the different key online monitoring easily measurable indexes.
[0015] S16. Determine suitable installation locations for online monitoring equipment in the production enterprises, and determine the baseline values of each of the online monitoring indicators based on the monitoring results of the in-situ online monitoring of the easily measurable online indicators.
[0016] S17. Based on the benchmark value and the current monitoring results of the online monitoring equipment, the identification results of groundwater pollution are obtained.
[0017] In another aspect of the present invention, a groundwater pollution identification device for an operating enterprise is also provided, comprising:
[0018] The data acquisition unit is used to acquire pollution-related data information of the producing enterprise; the data information includes the enterprise's layout, the raw and auxiliary materials and processes involved, the groundwater depth and flow direction of the site, and historical water quality monitoring data; the historical water quality monitoring data includes online monitoring and easily measurable index values obtained by a portable water quality analyzer, pollution index values corresponding to various pollution indicators, and related records including the instrument model of the portable water quality analyzer.
[0019] The pollution indicator screening unit is used to screen out pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are pollution indicators whose detection rate is greater than a preset value, as determined based on historical water quality monitoring values.
[0020] The correction equation construction unit is used to obtain the index correction equations corresponding to each online monitoring easy-to-measure index value based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment.
[0021] The index value correction unit is used to correct the online monitoring and measurable index values of each of the pollution indicators of concern in the historical water quality monitoring data according to the index correction equations.
[0022] The grouping unit is used to determine the key online monitoring indicators that have a critical impact on the values of the pollution indicators of concern in groundwater by using the corrected online monitoring easy-to-measurable indicators as independent variables and the pollution index values of the pollution indicators of concern as dependent variables through partial least squares regression and variable projection importance (VIP) analysis, and to group the pollution indicators of concern according to the different key online monitoring easy-to-measurable indicators.
[0023] The benchmark value acquisition unit is used to determine the installation location of the online monitoring equipment suitable for the enterprise in production, and to determine the benchmark value of each of the online monitoring easy-to-measure indicators through the monitoring results of the in-situ online monitoring of the online monitoring easy-to-measure indicators;
[0024] The identification result generation unit is used to obtain the identification result of groundwater pollution based on the benchmark value and the current monitoring result of the online monitoring equipment.
[0025] In another aspect of the present invention, a groundwater pollution identification device for production enterprises is also provided, comprising:
[0026] Memory, used to store computer programs;
[0027] A processor is used to invoke and execute the computer program to implement the various steps of the groundwater pollution identification method for operating enterprises as described in any of the preceding claims.
[0028] In another aspect of the present invention, a storage medium is also provided, on which a computer program is stored, which, when executed by a processor, implements the various steps of the groundwater pollution identification method for operating enterprises as described in any of the preceding claims.
[0029] The groundwater pollution identification device for the producing enterprise includes a computer program stored on a medium. The computer program includes program instructions. When the program instructions are executed by the computer, the computer performs the methods described in the above aspects and achieves the same technical effect.
[0030] Compared with the prior art, the present invention has the following beneficial effects:
[0031] This invention pre-obtains test results of easily measurable online monitoring indicators using both historical portable water quality analyzers and current enterprise online monitoring equipment. Based on the relationship between these two sets of results, it establishes calibration equations for each easily measurable online monitoring indicator. Next, after correcting the historical data using these calibration equations, the invention further reduces multicollinearity caused by correlations among the easily measurable online monitoring indicators through partial least squares regression. Based on this, VIP analysis is used to obtain key easily measurable online monitoring indicators for different groups of pollution of concern in the groundwater of operating enterprise sites. Furthermore, this invention obtains baseline values for each easily measurable online monitoring indicator based on trial monitoring results obtained by the enterprise's online monitoring equipment over a preset time period.
[0032] When identifying groundwater pollution, this invention uses the baseline values of easily measurable online monitoring indicators and the current indicator values obtained from the enterprise's online monitoring equipment. By using preset rules, the current indicator values are compared with historical indicator values to obtain the identification results of groundwater pollution. This can provide effective prediction and guidance for manual monitoring, reduce the number of manual monitoring items, and lower costs.
[0033] Because the data in this invention is effectively corrected and the multicollinearity problem caused by the correlation between easily measurable online monitoring indicators is avoided, the accuracy and effectiveness of groundwater pollution identification in producing enterprises can be effectively improved.
[0034] The above description is merely an overview of the technical solution of the present invention. In order to better understand the technical means of the present invention and to implement it according to the contents of the specification, and to make the above and other objects, technical features and advantages of the present invention easier to understand, one or more preferred embodiments are listed below and described in detail with reference to the accompanying drawings. Attached Figure Description
[0035] To more clearly illustrate the technical solution of the present invention, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0036] Figure 1 This is a flowchart illustrating the steps of the groundwater pollution identification method for operating enterprises described in this invention;
[0037] Figure 2 This is a schematic diagram of the factor loading diagram described in this invention;
[0038] Figure 3 This is a schematic diagram of the VIP diagram of variable projection importance described in this invention;
[0039] Figure 4 This is a schematic diagram of the structure of the groundwater pollution identification device for enterprises in production as described in this invention;
[0040] Figure 5 This is a schematic diagram of the structure of the groundwater pollution identification equipment for enterprises in production as described in this invention. Detailed Implementation
[0041] The specific embodiments of the present invention will now be described in detail with reference to the accompanying drawings, but it should be understood that the scope of protection of the present invention is not limited to the specific embodiments.
[0042] Unless otherwise expressly stated, throughout the specification and claims, the term "comprising" or its variations such as "including" or "comprising" shall be understood to include the stated elements or components without excluding other elements or other components.
[0043] In this document, the terms "first," "second," etc., are used to distinguish two different elements or parts, and are not used to define specific positions or relative relationships. In other words, in some embodiments, the terms "first," "second," etc., can also be used interchangeably.
[0044] Example 1
[0045] To improve the accuracy of groundwater pollution identification in operating enterprises, such as Figure 1 As shown, this embodiment of the invention provides a method for identifying groundwater pollution in operating enterprises, including the following steps:
[0046] S11. Obtain pollution-related data from operating enterprises; the data includes the enterprise's layout, raw and auxiliary materials and processes involved, the depth and flow direction of groundwater in the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained through portable water quality analyzers, as well as relevant records of the portable water quality analyzer's instrument model.
[0047] The application scenario of this invention is as follows: before implementing groundwater pollution identification based on the enterprise's online monitoring equipment, the historical water quality monitoring data of the producing enterprise is obtained by a portable water quality analyzer, which contains the index values of various monitoring indicators. These monitoring indicators include various easily measurable online monitoring indicators. Thus, the historical water quality monitoring data will also include the values of various easily measurable online monitoring indicators and the pollution index data values corresponding to various pollution indicators.
[0048] In this embodiment of the invention, the pollution-related data information of the producing enterprise not only includes the index values of various monitoring indicators and the pollution index data values corresponding to various pollution indicators, but also needs to include various factors that affect the generation and diffusion of pollution indicators, such as the enterprise's layout, the raw and auxiliary materials and processes involved, the depth and flow direction of groundwater in the plot.
[0049] In addition, in this embodiment of the invention, the historical water quality monitoring data may also include relevant records such as the instrument model of the portable water quality analyzer used to collect the historical water quality monitoring data.
[0050] S12. Select pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are those with a detection rate greater than a preset value, determined based on historical water quality monitoring values.
[0051] In practical applications, pollution indicators with a detection rate of more than 10% to 30% in historical water quality monitoring data can be identified as pollution indicators of concern.
[0052] S13. Based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment, respectively, the index correction equations corresponding to each online monitoring easy-to-measure index value are obtained.
[0053] The historical water quality monitoring data in this embodiment of the invention is obtained based on a portable water quality analyzer. However, subsequent data, which cannot be directly used for polluted water identification, is based on the monitoring results of online monitoring equipment. Due to differences in measurement conditions and the sensors used, historical water quality monitoring data cannot be directly used. In this embodiment, monitoring results are obtained using two different devices, and then, based on the relationship between the two results, an index correction equation corresponding to the easily measurable index value of the online monitoring is constructed. Specific steps may include:
[0054] Based on the relevant records of historical groundwater quality monitoring, multiple groups of water samples were tested in parallel using online monitoring equipment and a portable water quality analyzer of the same model as the one used to obtain the historical monitoring data. The tests included easily measurable online monitoring indicators such as pH, dissolved oxygen, conductivity, redox potential, turbidity and water temperature, and the corresponding test values were obtained.
[0055] Based on the test values of the two devices, the least squares method is used to establish the correction equation: C i =k i A i +b i In the formula, C i Let A be the test value obtained using online monitoring equipment for the i-th easily measurable online monitoring indicator. i Let k be the test value obtained using a portable water quality analyzer for the i-th easily measurable online monitoring index.i b i is the correction coefficient for the i-th easily measurable online monitoring index.
[0056] S14. According to the correction equations for each of the aforementioned indicators, the online monitoring and measurable values of each of the pollution indicators of concern in the historical water quality monitoring data are corrected.
[0057] By using the index correction equation, historical water quality monitoring data originally obtained using portable water quality analyzers can be corrected to approximate the data obtained using online monitoring equipment.
[0058] S15. Using the corrected online monitoring easily measurable index as the independent variable and the pollution index value of the pollution index of concern as the dependent variable, the key online monitoring easily measurable index that has a key impact on the value of the pollution index of concern in groundwater is determined by partial least squares regression and variable projection importance (VIP) analysis, and the pollution index of concern is grouped according to the different key online monitoring easily measurable indexes.
[0059] S21. Standardizing the independent variable X and dependent variable Y yields the independent variable matrix E0 and the dependent variable matrix F0; the standardization formulas used include:
[0060]
[0061] In the formula, x ij Let X be the independent variable j The i-th monitoring value, For X j The average value, s xj For X j Standard deviation, y ij Let Y be the independent variable j The i-th monitoring value, For Y j The average value, s yj For Y j Standard deviation;
[0062] S22. Extract the first principal component t1 of E0 and the first principal component u1 of F0. t1 and u1 must satisfy the following conditions: their respective variances reach the maximum and their correlation reaches the maximum.
[0063] S23. Establish the linear regression equations of E0 and F0 on t1:
[0064] E0 = t1p1 + E1;
[0065] F0 = t1q1 + F1;
[0066] In the formula, p1 and q1 are regression coefficient vectors, and E1 and F1 are residual matrices of the regression equation;
[0067] S24. If the partial least squares model used does not achieve the preset accuracy, replace E0 and F0 with residual matrices E1 and F1 and repeat steps S52 and S53 to extract the second principal component t2 to the m-th principal component t. m ;
[0068] S25. Calculate the VIP value of each independent variable. The calculation formula is as follows:
[0069]
[0070] In the formula, VIP j Let t be the variable projection importance value of the j-th independent variable, k be the number of independent variables, and t be the variable projection importance value. h The principal components extracted from the independent variables, r 2 (y,t h ) represents the dependent variable and t h The correlation coefficient represents t h Explanatory power of the dependent variable, w ij For this independent variable in principal component t h Weights on;
[0071] VIP can reflect the explanatory power of independent variables on dependent variables. The mean of the sum of squares of the VIP values of all independent variables is 1. Generally, independent variables with VIP > 1 are considered to be significant influencing factors. Therefore, based on VIP analysis, in-situ online monitoring indicators that have a key impact on the content of groundwater pollution indicators of concern can be identified (i.e., key online monitoring indicators).
[0072] The pollution indicators of concern are divided into two groups. A PLSR model is established for each group of indicators, and the difference between the projected importance (VIP) of the variables and the results before grouping is examined. If the change in indicators with VIP > 1 does not meet the preset conditions, grouping continues according to the factor loading distribution until the indicators with VIP > 1 are basically stable compared to the previous step (i.e., meeting the preset conditions). The grouping ends at this point, thus obtaining the grouping results. The preset conditions include that the number of pollution indicators does not change before and after this grouping.
[0073] Preferably, the preset conditions also include that the types of pollution indicators do not change before and after this grouping;
[0074] S16. Determine suitable installation locations for online monitoring equipment in the production enterprises, and determine the baseline values of each of the online monitoring indicators based on the monitoring results of the in-situ online monitoring of the easily measurable online indicators.
[0075] Based on the enterprise's layout, raw materials, and processes, and combined with the groundwater flow field of the site, online monitoring equipment (i.e., installation points) is installed in monitoring wells downstream of devices, facilities, and areas with potential groundwater pollution risks. In-situ online monitoring of easily measurable indicators of groundwater is carried out, and the baseline values of the easily measurable indicators of groundwater in each area are obtained. The baseline value is the average value of historical monitoring indicator data within a preset time period after the initial installation of the online monitoring equipment.
[0076] Preferably, the online monitoring equipment can read monitoring data once per hour. The baseline value for easily measurable indicators of groundwater online monitoring in various regions is the average value of historical monitoring indicator data within 2 to 3 days after the initial installation of the online monitoring equipment.
[0077] S17. Based on the benchmark value and the current monitoring results of the online monitoring equipment, the identification results of groundwater pollution are obtained.
[0078] Based on the comparison between the baseline value and the current monitoring results of the online monitoring equipment, it can be determined whether the groundwater is currently polluted (i.e., the identification result of groundwater pollution is obtained).
[0079] Preferably, in order to simplify the testing items, reduce testing costs, and improve the efficiency and timeliness of groundwater pollution identification, the groundwater pollution identification process is further optimized in this embodiment of the invention, specifically including:
[0080] When the monitoring data of a certain easily detectable online monitoring indicator deviates from the benchmark value by more than a preset reasonable deviation range (e.g., ±20%) for three consecutive times, the online easily detectable online monitoring indicator exceeding the standard is identified as an abnormal indicator, and manual monitoring of the pollution indicator concentration based on the first preset rule is carried out. Specific steps may include:
[0081] S31. The pollution index group with the highest VIP value of the abnormal index is determined as the first identification object group. The current index value of all indicators in the first identification object group is manually detected, and groundwater pollution is identified by comparing the current index value with the historical index value. If the change between the current index value and the historical index value of any index is greater than the preset warning value, a groundwater pollution identification result is generated.
[0082] S32. If the changes in the current indicator value and the historical indicator value of the indicator are both less than the preset warning value, the pollution indicator group including the abnormal indicator will be determined as the second identification object group.
[0083] S33. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the second identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated.
[0084] Furthermore, when the monitoring data of multiple easily detectable online monitoring indicators deviate from the benchmark value for three consecutive times exceeding a preset reasonable deviation range (e.g., ±20%), the exceeding easily detectable online monitoring indicators will be identified as abnormal indicators, and manual monitoring of pollution indicator concentrations based on a second preset rule will be carried out. The specific steps include:
[0085] S41. All pollution indicator groups containing two or more abnormal indicators are identified as the third identification target group.
[0086] S42. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the third identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated.
[0087] S43. If the changes in the current indicator value and the historical indicator value of the indicator are both less than the preset warning value, the pollution indicator group that contains an abnormal indicator in other pollution indicator groups outside the third identification object group is determined as the fourth identification object group.
[0088] S44. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the fourth identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated.
[0089] In summary, this invention pre-obtains test results of easily measurable online monitoring indicators using both historical portable water quality analyzers and current enterprise online monitoring equipment. Based on the relationship between these two sets of results, it establishes calibration equations for each easily measurable online monitoring indicator. Next, after correcting the historical data using these calibration equations, this invention further reduces multicollinearity caused by correlations among the easily measurable online monitoring indicators through partial least squares regression. Based on this, VIP analysis is used to obtain key easily measurable online monitoring indicators for different groups of pollution of concern in the groundwater of operating enterprise sites. Furthermore, this invention also obtains baseline values for each easily measurable online monitoring indicator based on trial monitoring results obtained by the enterprise's online monitoring equipment over a preset time period.
[0090] In this embodiment of the invention, when identifying groundwater pollution, the groundwater pollution identification result is obtained by comparing the current indicator value with the historical indicator value based on the baseline value of each easily measurable online monitoring indicator and the current indicator value obtained by the enterprise's online monitoring equipment, according to preset rules.
[0091] Because the data in this embodiment of the invention has been effectively corrected, and the multicollinearity problem caused by the correlation between easily measurable indicators in online monitoring has been avoided through partial least squares and variable projection importance analysis, the accuracy and effectiveness of groundwater pollution identification in producing enterprises can be effectively improved.
[0092] Specific examples of the technical solutions based on the embodiments of the present invention are as follows:
[0093] A chemical plant in operation in the lower reaches of the Yangtze River can be divided into two parts: an inorganic chemical zone and an organic chemical zone. The inorganic chemical zone uses coal, salt, and sulfur as raw materials to produce synthetic ammonia, sulfuric acid, nitric acid, soda ash, caustic soda, and other inorganic chemical products; the organic chemical zone uses benzene as raw material to produce aniline, nitrobenzene, chlorobenzene, nitrochlorobenzene, and other organic chemical products. The strata within the plant area can be divided from top to bottom into Quaternary artificial fill (depth 0-2.5m), sand (depth 2.5-7.2m), and silty clay (depth 7.2-17m). The shallow groundwater within the site is phreatic water, mainly found in the Quaternary sand layer, with a stable water level depth of 4.76-12.57m, and the groundwater flows from northwest to southeast.
[0094] Historical water quality monitoring data related to groundwater pollution at the site of the operating chemical enterprise in 2020 and 2021 showed the following parameters: total hardness, total dissolved solids, volatile phenols, sulfate, fluoride, chloride, ammonia nitrogen, oxygen consumption, manganese, zinc, arsenic, lead, mercury, petroleum hydrocarbons (C6-C9), and petroleum hydrocarbons (C4-C5). 10 -C 40 The detection rate of 20 indicators, including benzene, aniline, nitrobenzene, chlorobenzene, and 1,2-dichloroethane, exceeded 30%. These indicators are pollution indicators of concern in the groundwater of this site.
[0095] Portable water quality analyzers and enterprise online monitoring equipment of the same model as those used in historical monitoring were selected to conduct parallel tests on 5 groups of water samples from different groundwater monitoring wells in the site. The tests included 6 easily measurable indicators of groundwater online monitoring: pH, dissolved oxygen, conductivity, redox potential, turbidity, and water temperature. Based on the relationship between the test results, the indicator correction equations were established, as shown in Table 1.
[0096] Table 1:
[0097]
[0098] Based on the above correction equation, the easily measurable index values of groundwater online monitoring in historical groundwater quality monitoring records were corrected to be consistent with the online monitoring equipment. Using the corrected index values as independent variables X and the concentrations of 20 pollution indicators of concern in enterprise groundwater as dependent variables Y, partial least squares regression and projected importance (VIP) analysis were performed in SIMCA software. The factor loading plot and projected importance VIP plot are shown below. Figure 2 and Figure 3 As shown.
[0099] according to Figure 2 The 20 pollution indicators of concern can be clearly divided into two groups (i.e., two pollution indicator groups), with each group containing a relatively large number of pollution indicators, 14 and 6 respectively. Partial least squares regression models were established for these two groups of pollution indicators, and the difference between the variable projection importance (VIP) and the results before grouping was examined. If the indicators with VIP > 1 changed significantly, the grouping was continued according to the factor loading distribution until the indicators with VIP > 1 were basically stable compared with the previous step. Finally, the 20 pollution indicators of concern can be divided into 7 groups, as shown in Table 2.
[0100] Table 2: Importance Values of Pollution Indicators Grouped and Projected Variables (VIP Values)
[0101]
[0102]
[0103] It should be noted that the key online monitoring indicators in each pollution indicator group in Table 2 are in bold.
[0104] As shown in Table 2, the key online monitoring indicators for pollution in groups 2 and 4 are pH, DO, and conductivity, with only a slight difference in order. Therefore, they are grouped together. The key online monitoring indicators affecting the other pollution indices vary. Based on this, a groundwater pollution identification scheme for the enterprise site can be designed: According to the enterprise's layout, raw materials, and processes, combined with the groundwater flow field, online monitoring equipment is installed in monitoring wells downstream of devices, facilities, and areas with potential groundwater pollution risks. In-situ online monitoring of the aforementioned easily measurable groundwater indicators is conducted. The average historical monitoring data within a preset time period after the initial installation of the online monitoring equipment is set as the baseline value. When the monitored values of easily measurable groundwater indicators deviate significantly from the baseline value, manual monitoring of pollution concentration is performed, specifically including:
[0105] First, identify the pollution indicator group with abnormal indicators as key influencing factors, and compare it with historical data to determine the changing trend of the pollution indicators in this group. Then, identify groundwater pollution and take corresponding measures to curb the further spread of pollution. If monitoring only the above pollution indicator group cannot achieve the purpose of judging the pollution trend, the scope of pollution indicators monitored manually can be further expanded. In this way, the purpose of groundwater pollution prevention can be achieved while reducing monitoring costs and improving monitoring efficiency.
[0106] Example 2
[0107] Corresponding to the method embodiment, another aspect of the present invention also provides a groundwater pollution identification device for operating enterprises. Figure 4 This diagram illustrates the structure of a groundwater pollution identification device for operating enterprises provided in an embodiment of the present invention. The groundwater pollution identification device for operating enterprises is... Figure 1 The device corresponding to the groundwater pollution identification method for operating enterprises described in the corresponding embodiment is implemented through a virtual device. Figure 1 In the corresponding embodiment of the method for identifying groundwater pollution in operating enterprises, the various virtual modules constituting the groundwater pollution identification device for operating enterprises can be executed by electronic devices, such as network devices, terminal devices, or servers. Specifically, the groundwater pollution identification device for operating enterprises in this embodiment of the invention includes:
[0108] Data acquisition unit 01 is used to acquire pollution-related data information of the producing enterprise; the data information includes the enterprise's layout, the raw and auxiliary materials and processes involved, the groundwater depth and flow direction of the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained by a portable water quality analyzer, as well as relevant records of the portable water quality analyzer's instrument model;
[0109] The pollution index screening unit 02 is used to screen out pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are pollution indicators with a detection rate greater than a preset value determined based on historical water quality monitoring values.
[0110] The correction equation construction unit 03 is used to obtain the index correction equations corresponding to each online monitoring easy-to-measure index value based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment.
[0111] The index value correction unit 04 is used to correct the online monitoring and measurable index values of each of the pollution indicators of concern in the historical water quality monitoring data according to the index correction equations.
[0112] Grouping unit 05 is used to determine the key online monitoring indicators that have a critical impact on the values of the pollution indicators of concern in groundwater by using the corrected online monitoring easy-to-measure index as the independent variable and the pollution index value of the pollution indicators of concern as the dependent variable through partial least squares regression and variable projection importance (VIP) analysis, and to group the pollution indicators of concern according to the different key online monitoring easy-to-measure indexes.
[0113] The benchmark value acquisition unit 06 is used to determine the installation location of the online monitoring equipment suitable for the enterprise in production, and to determine the benchmark value of each of the online monitoring easy-to-measure indicators through the monitoring results of the in-situ online monitoring of the online monitoring easy-to-measure indicators;
[0114] The identification result generation unit 07 is used to obtain the identification result of groundwater pollution based on the benchmark value and the current monitoring result of the online monitoring equipment.
[0115] It should be noted that the specific implementation method and technical effects of the groundwater pollution identification device for operating enterprises in the embodiments of the present invention can be referred to Figure 1 The corresponding methods for identifying groundwater pollution in operating enterprises will not be elaborated here.
[0116] Example 3
[0117] Corresponding to the method embodiments, this invention also provides a groundwater pollution identification device for operating enterprises, such as a terminal and a server. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, CDN, and big data and artificial intelligence platforms. The terminal can be a smartphone, tablet, laptop, desktop computer, etc., but is not limited to these.
[0118] An example diagram of the hardware structure block diagram of the groundwater pollution identification equipment for operating enterprises provided in this application is shown below. Figure 5 As shown, it may include:
[0119] Processor 1, communication interface 2, memory 3, and communication bus 4;
[0120] The processor 1, communication interface 2, and memory 3 communicate with each other via communication bus 4.
[0121] Optionally, communication interface 2 can be an interface of a communication module, such as the interface of a GSM module;
[0122] Processor 1 may be a central processing unit (CPU), an application-specific integrated circuit (ASIC), or one or more integrated circuits configured to implement the embodiments of this application.
[0123] Memory 3 may include high-speed RAM memory, and may also include non-volatile memory, such as at least one disk storage device.
[0124] Specifically, processor 1 is used to execute the computer program stored in memory 3 to perform the following steps:
[0125] S11. Obtain pollution-related data from operating enterprises; the data includes the enterprise's layout, raw and auxiliary materials and processes involved, the depth and flow direction of groundwater in the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained through portable water quality analyzers, as well as relevant records of the portable water quality analyzer's instrument model.
[0126] S12. Select pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are those with a detection rate greater than a preset value, determined based on historical water quality monitoring values.
[0127] S13. Based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment, respectively, the index correction equations corresponding to each online monitoring easy-to-measure index value are obtained.
[0128] S14. According to the correction equations for each of the aforementioned indicators, the online monitoring and measurable values of each of the pollution indicators of concern in the historical water quality monitoring data are corrected.
[0129] S15. Using the corrected online monitoring easily measurable index as the independent variable and the pollution index value of the pollution index of concern as the dependent variable, the key online monitoring easily measurable index that has a key impact on the value of the pollution index of concern in groundwater is determined by partial least squares regression and variable projection importance (VIP) analysis, and the pollution index of concern is grouped according to the different key online monitoring easily measurable indexes.
[0130] S16. Determine suitable installation locations for online monitoring equipment in the production enterprises, and determine the baseline values of each of the online monitoring indicators based on the monitoring results of the in-situ online monitoring of the easily measurable online indicators.
[0131] S17. Based on the benchmark value and the current monitoring results of the online monitoring equipment, the identification results of groundwater pollution are obtained.
[0132] The above-described product can execute the method provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the method. Technical details not described in detail in this embodiment can be found in the method for identifying groundwater pollution in operating enterprises provided in the embodiments of the present invention.
[0133] Example 4
[0134] In this embodiment of the invention, a storage medium is also provided, which can store a program suitable for execution by a processor, the program being used for:
[0135] S11. Obtain pollution-related data from operating enterprises; the data includes the enterprise's layout, raw and auxiliary materials and processes involved, the depth and flow direction of groundwater in the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained through portable water quality analyzers, as well as relevant records of the portable water quality analyzer's instrument model.
[0136] S12. Select pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are those with a detection rate greater than a preset value, determined based on historical water quality monitoring values.
[0137] S13. Based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment, respectively, the index correction equations corresponding to each online monitoring easy-to-measure index value are obtained.
[0138] S14. According to the correction equations for each of the aforementioned indicators, the online monitoring and measurable values of each of the pollution indicators of concern in the historical water quality monitoring data are corrected.
[0139] S15. Using the corrected online monitoring easily measurable index as the independent variable and the pollution index value of the pollution index of concern as the dependent variable, the key online monitoring easily measurable index that has a key impact on the value of the pollution index of concern in groundwater is determined by partial least squares regression and variable projection importance (VIP) analysis, and the pollution index of concern is grouped according to the different key online monitoring easily measurable indexes.
[0140] S16. Determine suitable installation locations for online monitoring equipment in the production enterprises, and determine the baseline values of each of the online monitoring indicators based on the monitoring results of the in-situ online monitoring of the easily measurable online indicators.
[0141] S17. Based on the benchmark value and the current monitoring results of the online monitoring equipment, the identification results of groundwater pollution are obtained.
[0142] Optionally, the refined and extended functions of the program can be found in the description above.
[0143] The above-described product can execute the methods provided in the embodiments of the present invention, and has the corresponding functional modules and beneficial effects for executing the methods. Technical details not described in detail in this embodiment can be found in the methods provided in other embodiments of the present invention.
[0144] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0145] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, and methods can be implemented in other ways. Furthermore, the couplings or direct couplings or communication connections shown or discussed may be indirect couplings or communication connections through interfaces, devices, or units, and may be electrical, mechanical, or other forms.
[0146] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0147] In addition, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.
[0148] It should be understood that in the embodiments of this application, the claims, various embodiments, and features can be combined with each other to solve the aforementioned technical problems.
[0149] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this application. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.
[0150] The above description of the disclosed embodiments enables those skilled in the art to make or use this application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this application. Therefore, this application is not to be limited to the embodiments shown herein, but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims
1. A method for identifying groundwater pollution in operating enterprises, characterized in that, Including the following steps: S11. Obtain pollution-related data information from the operating enterprise; the data information includes the enterprise's layout, the raw and auxiliary materials and processes involved, the groundwater depth and flow direction of the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained through a portable water quality analyzer, as well as relevant records of the portable water quality analyzer's instrument model. S12. Select pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are those with a detection rate greater than a preset value, determined based on historical water quality monitoring values. S13. Based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment, respectively, the index correction equations corresponding to each online monitoring easy-to-measure index value are obtained. S14. According to the correction equations for each of the aforementioned indicators, the online monitoring and measurable index values of each of the pollution indicators of concern in the historical water quality monitoring data are corrected. S15. Using the corrected online monitoring easily measurable index as the independent variable and the pollution index value of the pollution index of concern as the dependent variable, the key online monitoring easily measurable index that has a key impact on the value of the pollution index of concern in groundwater is determined by partial least squares regression and variable projection importance (VIP) analysis, and the pollution index of concern is grouped according to the different key online monitoring easily measurable indexes. S16. Determine suitable installation locations for online monitoring equipment in the production enterprises, and determine the baseline values of each of the online monitoring indicators based on the monitoring results of the in-situ online monitoring of the easily measurable online indicators. S17. Based on the benchmark value and the current monitoring results of the online monitoring equipment, the identification results of groundwater pollution are obtained.
2. The method for identifying groundwater pollution in operating enterprises according to claim 1, characterized in that, The pollution indicators of concern are those with a detection rate greater than 10% to 30%.
3. The method for identifying groundwater pollution in operating enterprises according to claim 2, characterized in that, Step S13 includes: Using online monitoring equipment and a portable water quality analyzer of the same model as the one used to obtain historical monitoring data, parallel tests were conducted on multiple groups of water samples to measure easily measurable online monitoring indicators, including pH, dissolved oxygen, conductivity, oxidation-reduction potential, turbidity, and water temperature, and the corresponding test values were obtained. Based on the test values of the two devices, the least squares method is used to establish the correction equation: C i =k i A i +b i In the formula, C i Let A be the test value obtained using online monitoring equipment for the i-th easily measurable online monitoring indicator. i Let k be the test value obtained using a portable water quality analyzer for the i-th easily measurable online monitoring index. i b i is the correction coefficient for the i-th easily measurable online monitoring index.
4. The method for identifying groundwater pollution in operating enterprises according to claim 3, characterized in that, Step S15 includes: S21. Standardizing the independent variable X and dependent variable Y yields the independent variable matrix E0 and dependent variable matrix F0; the standardization formulas used include: In the formula, x ij Let X be the independent variable j The i-th monitoring value, For X j The average value, s xj For X j Standard deviation, y ij Let Y be the independent variable j The i-th monitoring value, For Y j The average value, s yj For Y j Standard deviation; S22. Extract the first principal component t1 of E0 and the first principal component u1 of F0. t1 and u1 must satisfy the following conditions: their respective variances reach the maximum and their correlation reaches the maximum. S23. Establish the linear regression equations of E0 and F0 on t1: E0 = t1p1 + E1; F0 = t1q1 + F1; In the formula, p1 and q1 are regression coefficient vectors, and E1 and F1 are residual matrices of the regression equation; S24. If the partial least squares model used does not achieve the preset accuracy, replace E0 and F0 with residual matrices E1 and F1 and repeat steps S52 and S53 to extract the second principal component t2 to the m-th principal component t. m ; S25. Calculate the VIP value of each independent variable. The calculation formula is as follows: In the formula, VIP j Let t be the variable projection importance value of the j-th independent variable, k be the number of independent variables, and t be the variable projection importance value. h r is the principal component extracted from the independent variable. 2 (y,t h ) represents the dependent variable and t h The correlation coefficient represents t h Explanatory power of the dependent variable, w ij For this independent variable in principal component t h Weights on; The pollution indicators of concern are divided into two groups. A PLSR model is established for each group of pollution indicators of concern, and the difference between the projected importance of variables (VIP) and the results before grouping is examined. If the indicators with VIP > 1 do not meet the preset conditions, the grouping is continued according to the factor loading distribution until the indicators with VIP > 1 meet the preset conditions and the grouping ends. The preset conditions include that the number of pollution indicators does not change before and after this grouping.
5. The method for identifying groundwater pollution in operating enterprises according to claim 4, characterized in that, Step S16 includes: Based on the enterprise's layout, raw materials, and processes, and combined with the groundwater flow field of the site, online monitoring equipment is installed in monitoring wells downstream of devices, facilities, and areas with potential groundwater pollution risks.
6. The method for identifying groundwater pollution in operating enterprises according to claim 5, characterized in that, The benchmark value is the average value of the easily measurable online monitoring indicators within a preset time period after the initial installation of the online monitoring equipment.
7. The method for identifying groundwater pollution in operating enterprises according to claim 6, characterized in that, Step S17 includes: When the monitoring data of a certain online monitoring indicator deviates from the benchmark value by more than ±20% for three consecutive times, the online monitoring indicator that exceeds the standard will be identified as an abnormal indicator, and manual monitoring of the pollution indicator concentration based on the first preset rule will be carried out.
8. The method for identifying groundwater pollution in operating enterprises according to claim 7, characterized in that, Step S17 further includes: When the monitoring data of multiple online easily detectable indicators deviate from the benchmark value by more than ±20% for three consecutive times, the online easily detectable indicators that exceed the standard will be identified as abnormal indicators, and manual monitoring of the pollution indicator concentration based on the second preset rule will be carried out.
9. The method for identifying groundwater pollution in operating enterprises according to claim 7, characterized in that, The manual monitoring of pollution index concentrations based on a first preset rule includes: S31. The pollution index group with the highest VIP value of the abnormal index is determined as the first identification object group. The current index value of all indicators in the first identification object group is manually detected, and groundwater pollution is identified by comparing the current index value with the historical index value. If the change between the current index value and the historical index value of any index is greater than the preset warning value, a groundwater pollution identification result is generated. S32. If the changes in the current indicator value and the historical indicator value of the indicator are both less than the preset warning value, the pollution indicator group including the abnormal indicator will be determined as the second identification object group. S33. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the second identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated.
10. The method for identifying groundwater pollution in operating enterprises according to claim 8, characterized in that, The manual monitoring of pollution index concentrations based on the second preset rule includes: S41. All pollution indicator groups containing two or more abnormal indicators are identified as the third identification target group. S42. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the third identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated. S43. If the changes in the current indicator value and the historical indicator value of the indicator are both less than the preset warning value, the pollution indicator group that contains an abnormal indicator in other pollution indicator groups outside the third identification object group is determined as the fourth identification object group. S44. Groundwater pollution is identified for each key online monitoring and measurable indicator in each of the fourth identification object groups. If the change between the current indicator value and the historical indicator value of an indicator is greater than the preset warning value, a groundwater pollution identification result is generated.
11. A groundwater pollution identification device for an operating enterprise, characterized in that, include: The data acquisition unit is used to acquire pollution-related data and information from operating enterprises. The data information includes the enterprise's layout, the raw and auxiliary materials and processes involved, the groundwater depth and flow direction of the site, and historical groundwater quality monitoring data; the historical groundwater quality monitoring data includes pollution index values corresponding to various pollution indicators and easily measurable online monitoring index values obtained by portable water quality analyzers, as well as relevant records of the portable water quality analyzer's instrument model; The pollution indicator screening unit is used to screen out pollution indicators of concern based on the historical water quality monitoring data; the pollution indicators of concern are pollution indicators whose detection rate is greater than a preset value, as determined based on historical water quality monitoring values. The correction equation construction unit is used to obtain the index correction equations corresponding to each online monitoring easy-to-measure index value based on the online monitoring easy-to-measure index values obtained by the portable water quality analyzer and the online monitoring easy-to-measure index values obtained by the online monitoring equipment. The index value correction unit is used to correct the online monitoring and measurable index values of each of the pollution indicators of concern in the historical water quality monitoring data according to the index correction equations. The grouping unit is used to determine the key online monitoring indicators that have a critical impact on the values of the pollution indicators of concern in groundwater by using the corrected online monitoring easy-to-measurable indicators as independent variables and the pollution index values of the pollution indicators of concern as dependent variables through partial least squares regression and variable projection importance (VIP) analysis, and to group the pollution indicators of concern according to the different key online monitoring easy-to-measurable indicators. The benchmark value acquisition unit is used to determine the installation location of the online monitoring equipment suitable for the enterprise in production, and to determine the benchmark value of each of the online monitoring easy-to-measure indicators through the monitoring results of the in-situ online monitoring of the online monitoring easy-to-measure indicators; The identification result generation unit is used to obtain the identification result of groundwater pollution based on the benchmark value and the current monitoring result of the online monitoring equipment.
12. A groundwater pollution identification device for operating enterprises, characterized in that, include: Memory, used to store computer programs; A processor is configured to invoke and execute the computer program to implement the steps of the groundwater pollution identification method for operating enterprises as described in any one of claims 1-10.
13. A storage medium, characterized in that, Includes a software program adapted by a processor to perform the steps of the groundwater pollution identification method for operating enterprises as described in any one of claims 1-10.