Intelligent sampling monitoring system and method based on sewage index distribution characteristics

Abstract

The invention is suitable for the technical field of sewage monitoring, and provides an intelligent sampling monitoring system and method based on sewage index distribution characteristics, and the method comprises the following steps: carrying out real-time fuzzy sampling based on the Internet of Things, obtaining fuzzy sampling data, and determining an abnormal fuzzy index; calling a corresponding sewage index distribution characteristic according to a sampling site and time of the fuzzy sampling data, and performing contrast speculation on the sewage index distribution characteristic and an abnormal fuzzy index to determine an accurate sampling index; receiving accurate sampling data, determining an abnormal accurate index, calling a pollution source distribution condition, and determining potential pollution source information; and determining a monitoring site according to the potential pollution source information and the sampling site of the accurate sampling data. Only a low-cost sensor is deployed, all-directional monitoring of sewage, analysis of fuzzy sampling data and determination of abnormal fuzzy indexes are realized, accurate sampling indexes are determined in combination with sewage index distribution characteristics, and high cost and low efficiency of full-index accurate real-time sampling are avoided.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of sewage monitoring, in particular to an intelligent sampling monitoring system and method based on sewage index distribution characteristics. BACKGROUND

[0002] With the acceleration of industrialization and urbanization, the amount of sewage discharge has increased significantly, and its composition is complex and variable, containing heavy metals, organic matter, inorganic salts and other pollutants. The traditional sewage monitoring method usually relies on manual periodic sampling and laboratory analysis, and the manual sampling cycle is long (usually daily / weekly), which is difficult to capture the instantaneous mutation of sewage indicators, resulting in a lag in response to pollution events. Precise sewage detection includes dozens of specific indicators, and real-time monitoring of all indicators requires the deployment of high-precision sensor networks, which has high equipment purchase and maintenance costs. Therefore, it is necessary to provide an intelligent sampling monitoring system and method based on sewage index distribution characteristics to solve the above problems. SUMMARY

[0003] In view of the deficiencies in the prior art, the purpose of the present application is to provide an intelligent sampling monitoring system and method based on sewage index distribution characteristics to solve the problems in the background art.

[0004] The present application is implemented as follows: an intelligent sampling monitoring method based on sewage index distribution characteristics, the method comprising the following steps: Real-time fuzzy sampling based on the Internet of Things to obtain fuzzy sampling data, the fuzzy sampling indicators including conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity; Analyzing the fuzzy sampling data to determine abnormal fuzzy indicators, the fuzzy sampling data containing time information and location information; According to the sampling location and time of the fuzzy sampling data, the corresponding sewage index distribution characteristics are retrieved, and the sewage index distribution characteristics are compared with the abnormal fuzzy indicators to determine the precise sampling indicators; the sewage index distribution characteristics contain several sewage indicators, and each sewage indicator corresponds to an abnormal occurrence frequency; Receiving precise sampling data to determine abnormal precise indicators, retrieving pollution source distribution, and determining potential pollution source information; According to the potential pollution source information and the sampling location of the precise sampling data, the monitoring location is determined, and the pollution source is traced.

[0005] As a further scheme of the present application, the step of analyzing the fuzzy sampling data to determine abnormal fuzzy indicators specifically comprises: Retrieving the corresponding fuzzy indicator reference information according to the time information and the location information; Determining whether the fuzzy sampling data contains fuzzy sampling indicators beyond the reference range according to the fuzzy indicator reference information to determine abnormal fuzzy indicators; extracting the change trend of each fuzzy sampling index in the fuzzy sampling data, and determining the existing abnormal fuzzy index according to the change trend.

[0006] As a further scheme of the present application, the step of comparing the sewage index distribution characteristics with the abnormal fuzzy index to determine the accurate sampling index specifically comprises: determining the existing abnormal label according to the abnormal fuzzy index, the abnormal label including inorganic salt abnormality, organic matter abnormality, acid abnormality, alkali abnormality, oxidation abnormality, reduction abnormality and suspended matter abnormality; determining the attribute label corresponding to each sewage index in the sewage index distribution characteristics, the attribute label being inorganic salt, organic matter, acid, alkali, oxidation, reduction and suspended matter; matching the abnormal label with the attribute label to determine the accurate sampling index, and combining the sewage index distribution characteristics to determine the abnormal probability of each accurate sampling index.

[0007] As a further scheme of the present application, the step of matching the abnormal label with the attribute label to determine the accurate sampling index specifically comprises: determining a first label set according to the abnormal label, and determining a second label set of each sewage index according to the attribute label; sequentially determining whether each second label set belongs to a subset of the first label set, and when it belongs, regarding it as a matching success, and determining the corresponding sewage index as the accurate sampling index.

[0008] As a further scheme of the present application, the step of determining the abnormal probability of each accurate sampling index in combination with the sewage index distribution characteristics specifically comprises: calculating the matching degree of the matching successful sewage index according to the second label set and the first label set; calling the abnormal occurrence frequency of the sewage index, and determining the abnormal probability of each accurate sampling index according to the abnormal occurrence frequency and the matching degree; determining the accurate sampling range and the accurate sampling frequency of the corresponding sewage index according to the abnormal probability, the accurate sampling range including the time range and the place range.

[0009] As a further scheme of the present application, the step of determining the monitoring place according to the potential pollution source information and the sampling place of the accurate sampling data specifically comprises: determining the pollution source position according to the potential pollution source information, and calling the water flow map; determining the pollutant diffusion path according to the pollution source position, the sampling place and the water flow map; setting the monitoring place on the pollutant diffusion path, and the interval distance of the monitoring place being determined according to the abnormal degree of the accurate sampling data.

[0010] Another object of the present application is to provide an intelligent sampling monitoring system based on sewage index distribution characteristics, which comprises: A fuzzy sampling data module is configured to perform real-time fuzzy sampling based on the Internet of Things to obtain fuzzy sampling data, and the fuzzy sampling indexes include conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity. An abnormal fuzzy index module is configured to analyze the fuzzy sampling data to determine abnormal fuzzy indexes, and the fuzzy sampling data contains time information and location information. A precise sampling index module is configured to determine precise sampling indexes by comparing the sewage index distribution characteristics with the abnormal fuzzy indexes, and the sewage index distribution characteristics contain a plurality of sewage indexes, and each sewage index corresponds to an abnormal occurrence frequency. A pollution source information module is configured to receive precise sampling data, determine abnormal precise indexes, retrieve pollution source distribution, and determine potential pollution source information. A pollution tracing monitoring module is configured to determine monitoring locations according to the potential pollution source information and the sampling locations of the precise sampling data, and perform pollution tracing.

[0011] As a further scheme of the present application, the abnormal fuzzy index module comprises: A reference information retrieval unit is configured to retrieve corresponding fuzzy index reference information according to the time information and the location information. A first abnormal fuzzy unit is configured to determine whether the fuzzy sampling data contains fuzzy sampling indexes beyond the reference range according to the fuzzy index reference information, and determine abnormal fuzzy indexes. A second abnormal fuzzy unit is configured to extract the change trend of each fuzzy sampling index in the fuzzy sampling data, and determine the existing abnormal fuzzy indexes according to the change trend.

[0012] As a further scheme of the present application, the precise sampling index module comprises: An abnormal label determination unit is configured to determine the existing abnormal labels according to the abnormal fuzzy indexes, and the abnormal labels include inorganic salt abnormality, organic matter abnormality, acid abnormality, alkali abnormality, oxidation abnormality, reduction abnormality and suspended matter abnormality. An attribute label determination unit is configured to determine the attribute labels corresponding to each sewage index in the sewage index distribution characteristics, and the attribute labels are inorganic salt, organic matter, acid, alkali, oxidation, reduction and suspended matter. A precise index determination unit is configured to match the abnormal labels with the attribute labels to determine the precise sampling indexes, and determine the abnormal probability of each precise sampling index in combination with the sewage index distribution characteristics.

[0013] As a further scheme of the present application, the precision index determination unit comprises: a label set determination subunit configured to determine a first label set according to the abnormal label and determine a second label set of each sewage index according to the attribute label; a set matching subunit configured to determine whether each second label set belongs to a subset of the first label set in sequence, and when it belongs, it is considered as a matching success, and the corresponding sewage index is determined as a precision sampling index.

[0014] Compared with the prior art, the present application has the following beneficial effects: The present application implements all-round monitoring of sewage by deploying low-cost sensors to obtain fuzzy sampling data through the implementation of the phased strategy of “fuzzy sampling → abnormal fuzzy index screening → precision sampling → abnormal precision index determination → pollution tracing”. Then the fuzzy sampling data is analyzed to determine the abnormal fuzzy index, and the sewage index distribution characteristics are compared with the abnormal fuzzy index to determine the precision sampling index, so that precision sampling can be carried out more targetedly, the high cost and low efficiency of full-index accurate real-time sampling are avoided, and the present application is worth promoting. BRIEF DESCRIPTION OF DRAWINGS

[0015] Figure 1 A flowchart of the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0016] Figure 2 A flowchart of determining abnormal fuzzy indexes in the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0017] Figure 3 A flowchart of determining precision sampling indexes in the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0018] Figure 4 A flowchart of matching labels in the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0019] Figure 5 A flowchart of determining abnormal probabilities in the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0020] Figure 6 A flowchart of determining monitoring locations in the intelligent sampling monitoring method based on the distribution characteristics of sewage indexes.

[0021] Figure 7 A structural schematic diagram of the intelligent sampling monitoring system based on the distribution characteristics of sewage indexes. DETAILED DESCRIPTION

[0022] In order to make the purposes, technical solutions and advantages of the present application clearer, the present application will be further described in detail below in combination with the drawings and specific embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application.

[0023] The specific implementation of the present application is described in detail below in combination with specific embodiments.

[0024] As shown in Figure 1 The embodiment of the present application provides an intelligent sampling monitoring method based on sewage index distribution characteristics, which comprises the following steps: S100, real-time fuzzy sampling based on Internet of Things is performed to obtain fuzzy sampling data, and the fuzzy sampling indexes include conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity; S200, the fuzzy sampling data is analyzed to determine abnormal fuzzy indexes, and the fuzzy sampling data contains time information and location information; S300, the corresponding sewage index distribution characteristics are recalled according to the sampling location and time of the fuzzy sampling data, the sewage index distribution characteristics are compared with the abnormal fuzzy indexes for speculation, and the accurate sampling indexes are determined; the sewage index distribution characteristics contain a plurality of sewage indexes, and each sewage index corresponds to an abnormal occurrence frequency; S400, receiving accurate sampling data, determining abnormal accurate indexes, recalling pollution source distribution, and determining potential pollution source information; S500, determining the monitoring location according to the potential pollution source information and the sampling location of the accurate sampling data, and performing pollution tracing.

[0025] In the embodiment of the present application, in order to reduce the monitoring cost and improve the real-time performance of data, based on the Internet of Things technology and using low-cost and high-frequency online sensors, real-time fuzzy sampling is carried out. The fuzzy sampling indicators include conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity. The conductivity is used to monitor the injection of industrial wastewater and the change of salinity. The ultraviolet absorbance is used to monitor the concentration of organic matter (especially aromatic compounds) in water, which is strongly related to precise indicators such as COD and TOC. The pH value and oxidation-reduction potential are used to monitor the chemical equilibrium state of the water body. The discharge of acidic or alkaline wastewater and the inflow of reducing / oxidizing substances will cause a sharp change. The turbidity is used to monitor the suspended solid content and reflect the physical properties of the water body. In this way, only low-cost sensors are deployed, and real-time data transmission is achieved through the Internet of Things, which shortens the pollution response time and enables comprehensive monitoring of wastewater to obtain fuzzy sampling data. Then the fuzzy sampling data is analyzed to determine abnormal fuzzy indicators. The fuzzy sampling data collected by the sensor includes a timestamp and a sampling location. Next, the corresponding wastewater index distribution characteristics are retrieved according to the sampling location and time of the fuzzy sampling data. The wastewater index distribution characteristics are compared with the abnormal fuzzy indicators to determine the precise sampling indicators. In this way, precise indicators can still be monitored. The precise indicators are obtained through scientific speculation, avoiding the high cost and low efficiency of precise real-time sampling of all indicators. The wastewater index distribution characteristics include a plurality of wastewater indicators, each of which corresponds to an abnormal occurrence frequency. The wastewater index distribution characteristics are obtained based on historical data of each water area. A wastewater distribution library needs to be constructed based on historical data. The wastewater distribution library includes the wastewater index distribution characteristics of each water area location. Each wastewater index distribution characteristic is marked with a time season.

[0026] In the embodiment of the present application, after the precise sampling indicators are determined, they are issued to relevant staff. The staff will collect more precise wastewater indicators according to the corresponding location information, then obtain precise sampling data and upload it, and analyze it to obtain abnormal precise indicators. Next, the pollution source distribution is retrieved. The pollution source distribution includes the locations of all pollution sources, pollutant information and covered pollution water areas. The abnormal precise indicators and the corresponding sampling locations are compared with the pollution source distribution to obtain potential pollution source information. Then, the monitoring location is determined according to the potential pollution source information and the sampling location of the precise sampling data. The monitoring location is arranged on the path of pollutant diffusion to realize pollution tracing. In summary, the embodiment of the present application uses a phased strategy of "fuzzy sampling → abnormal fuzzy indicator screening → precise sampling → abnormal precise indicator determination → pollution tracing" to avoid the high cost and low efficiency of precise real-time sampling of all indicators. The spatiotemporal distribution characteristics of wastewater indicators are used to achieve efficient monitoring.

[0027] For example, Figure 2As shown in the preferred embodiment of the present invention, the step of analyzing the fuzzy sampling data and determining the abnormal fuzzy index specifically includes: S201, retrieve the corresponding fuzzy index benchmark information based on time and location information; S202, Determine whether there are any fuzzy sampling indicators in the fuzzy sampling data that exceed the benchmark range based on the fuzzy index benchmark information, and identify abnormal fuzzy indicators. S203, extract the changing trend of each fuzzy sampling index in the fuzzy sampling data, and determine the existing abnormal fuzzy indexes based on the changing trend.

[0028] In this embodiment of the invention, it is necessary to determine the fuzzy indicator benchmark information for each water area in each time season based on historical data beforehand. The fuzzy indicator benchmark information includes the reasonable benchmark range for each fuzzy indicator. This allows for the determination of whether there are fuzzy sampling indicators in the fuzzy sampling data that exceed the benchmark range. When the collected data of a certain fuzzy sampling indicator is not within the reasonable benchmark range, that fuzzy sampling indicator will be marked as an abnormal fuzzy indicator. In addition, the changing trend of each fuzzy sampling indicator in the fuzzy sampling data will be extracted, and abnormal fuzzy indicators will be determined based on the changing trend. For example, if the upward trend of a certain indicator is higher than the corresponding upward threshold, it will also be marked as an abnormal fuzzy indicator.

[0029] like Figure 3 As shown, in a preferred embodiment of the present invention, the step of comparing and inferring the distribution characteristics of wastewater indicators with abnormal fuzzy indicators to determine the precise sampling indicators specifically includes: S301, determine the existing abnormal labels based on the abnormal fuzzy index. The abnormal labels include inorganic salt abnormalities, organic matter abnormalities, acid abnormalities, alkali abnormalities, oxidation abnormalities, reduction abnormalities, and suspended matter abnormalities. S302, determine the attribute label corresponding to each wastewater index in the wastewater index distribution characteristics, wherein the attribute label is inorganic salts, organic matter, acids, alkalis, oxidizing agents, reducing agents, and suspended solids; S303: Match the anomaly label with the attribute label to determine the precise sampling index, and combine the distribution characteristics of the wastewater index to determine the anomaly probability of each precise sampling index.

[0030] In the embodiment of the present application, in order to better determine the accurate sampling index, first, the existing abnormal label is determined according to the abnormal fuzzy index. For example, the abnormal fuzzy index is that the conductivity is too high, the ultraviolet absorbance is too high, and the pH value is too low, and the abnormal label is inorganic salt abnormality, organic matter abnormality, and acid abnormality. In addition, the attribute label corresponding to each sewage index in the sewage index distribution characteristic is determined according to the physicochemical properties. The attribute label is inorganic salt, organic matter, acid, alkali, oxidation, reduction, and suspended matter. One sewage index can correspond to multiple attribute labels, and when the sewage index is abnormal, the corresponding attribute label will also be abnormal. Then, the abnormal label and the attribute label are matched, and the accurate sampling index can be further determined.

[0031] As shown in Figure 4 , as a preferred embodiment of the present application, the step of matching the abnormal label and the attribute label to determine the accurate sampling index specifically includes: S3031, determining a first label set according to the abnormal label, and determining a second label set of each sewage index according to the attribute label; S3032, judging whether each second label set belongs to a subset of the first label set in turn, and when it belongs, it is considered as a matching success, and the corresponding sewage index is determined as the accurate sampling index.

[0032] In the embodiment of the present application, first, the first label set is determined according to the abnormal label. For example, the abnormal label is inorganic salt abnormality, organic matter abnormality, and acid abnormality, and the first label set is {inorganic salt, organic matter, acid}. At the same time, the second label set of each sewage index is determined according to the attribute label. For example, the attribute label of a certain sewage index is organic matter and acid, and the second label set is {organic matter, acid}. Then, whether each second label set belongs to a subset of the first label set is judged in turn. For example, {organic matter, acid} is a subset of {inorganic salt, organic matter, acid}, which indicates that the matching is successful, and the corresponding sewage index is determined as the accurate sampling index.

[0033] As shown in Figure 5 , as a preferred embodiment of the present application, the step of determining the abnormal probability of each accurate sampling index in combination with the sewage index distribution characteristic specifically includes: S3033, calculating the matching degree of the matching successful sewage index according to the second label set and the first label set; S3034, calling the abnormal occurrence frequency of the sewage index, and determining the abnormal probability of each accurate sampling index according to the abnormal occurrence frequency and the matching degree; S3035, determining the accurate sampling range and the accurate sampling frequency of the corresponding sewage index according to the abnormal probability, and the accurate sampling range includes the time range and the place range.

[0034] In the embodiment of the present application, in order to better perform accurate sampling, the matching degree of the matching successful sewage index is also calculated according to the second label set and the first label set, for the first label set {inorganic salts, organic matter, acid} and the second label set {organic matter, acid}, the matching degree = 2 / 3 = 66.67%; then the abnormal occurrence frequency of the corresponding sewage index is called, and the abnormal probability of each accurate sampling index is determined according to the abnormal occurrence frequency and the matching degree, the abnormal probability = k1*abnormal occurrence frequency / frequency base number+k2*matching degree, the frequency base number is a fixed value set in advance, and k1 and k2 are constant coefficients. Finally, the accurate sampling range and the accurate sampling frequency of the corresponding sewage index are determined according to the abnormal probability. It is easy to understand that the higher the abnormal probability, the wider the accurate sampling range, and the higher the accurate sampling frequency.

[0035] As shown in Figure 6 As a preferred embodiment of the present application, the step of determining the monitoring site according to the potential pollution source information and the accurate sampling data specifically comprises: S501, determining the pollution source position according to the potential pollution source information, and calling a water flow map; S502, determining the pollutant diffusion path according to the pollution source position, the sampling site and the water flow map; S503, setting the monitoring site on the pollutant diffusion path, and the interval distance of the monitoring site is determined according to the abnormal degree of the accurate sampling data.

[0036] In the embodiment of the present application, the pollution source position, the sampling site and the water flow map are comprehensively determined to determine the pollutant diffusion path, and then the monitoring site is set on the pollutant diffusion path, and the interval distance of the monitoring site is determined according to the abnormal degree of the accurate sampling data. It is easy to understand that the greater the abnormal degree, the more densely the monitoring site is set. By setting the monitoring site, the diffusion of the pollutant can be well determined.

[0037] As shown in Figure 7 The embodiment of the present application further provides an intelligent sampling monitoring system based on the distribution characteristics of the sewage index, and the system comprises: The fuzzy sampling data module 100 is used for real-time fuzzy sampling based on the Internet of Things to obtain fuzzy sampling data, and the fuzzy sampling index includes conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity; The abnormal fuzzy index module 200 is used for analyzing the fuzzy sampling data to determine the abnormal fuzzy index, and the fuzzy sampling data contains time information and site information; The precise sampling index module 300 is used for calling corresponding sewage index distribution characteristics according to the sampling location and time of the fuzzy sampling data, comparing the sewage index distribution characteristics with the abnormal fuzzy index, and determining a precise sampling index; the sewage index distribution characteristics include a plurality of sewage indexes, and each sewage index corresponds to an abnormal occurrence frequency; The pollution source information module 400 is used for receiving the precise sampling data, determining an abnormal precise index, calling pollution source distribution, and determining potential pollution source information. The pollution source tracing monitoring module 500 is used for determining a monitoring location according to the potential pollution source information and the sampling location of the precise sampling data, and performing pollution source tracing.

[0038] As a preferred embodiment of the present application, the abnormal fuzzy index module 200 includes: The reference information calling unit is used for calling corresponding fuzzy index reference information according to the time information and the location information; The first abnormal fuzzy unit is used for determining whether the fuzzy sampling data has a fuzzy sampling index beyond the reference range according to the fuzzy index reference information, and determining an abnormal fuzzy index; The second abnormal fuzzy unit is used for extracting the change trend of each fuzzy sampling index in the fuzzy sampling data, and determining the existing abnormal fuzzy index according to the change trend.

[0039] As a preferred embodiment of the present application, the precise sampling index module 300 includes: The abnormal label determining unit is used for determining an existing abnormal label according to the abnormal fuzzy index, and the abnormal label includes inorganic salt abnormality, organic matter abnormality, acid abnormality, alkali abnormality, oxidation abnormality, reduction abnormality and suspended matter abnormality; The attribute label determining unit is used for determining an attribute label corresponding to each sewage index in the sewage index distribution characteristics, and the attribute label is inorganic salt, organic matter, acid, alkali, oxidation, reduction and suspended matter; The precise index determining unit is used for matching the abnormal label with the attribute label, determining a precise sampling index, and determining the abnormal probability of each precise sampling index in combination with the sewage index distribution characteristics.

[0040] As a preferred embodiment of the present application, the precise index determining unit includes: The label set determining subunit is used for determining a first label set according to the abnormal label, and determining a second label set of each sewage index according to the attribute label; The set matching subunit is used for sequentially determining whether each second label set belongs to a subset of the first label set, and when it belongs, it is regarded as a matching success, and the corresponding sewage index is determined as a precise sampling index.

[0041] The above only describes the preferred embodiments of the present application in detail, and does not limit the present application. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

[0042] It should be understood that although each step in the flowchart of each embodiment of the present application is shown in sequence according to the arrow, the steps are not necessarily executed in the order indicated by the arrow. Unless otherwise specified herein, the execution of the steps is not strictly limited in sequence, and the steps can be executed in other orders. Moreover, at least part of the steps in each embodiment can include multiple sub-steps or multiple stages, which are not necessarily executed at the same time, but can be executed at different times, and the execution order of the sub-steps or stages is not necessarily sequential, but can be executed in rotation or alternation with at least part of other steps or sub-steps or stages of other steps.

[0043] It can be understood by those skilled in the art that all or part of the processes in the above-mentioned embodiment methods can be completed by a computer program instructing related hardware, and the program can be stored in a non-volatile computer readable storage medium. When the program is executed, it can include the processes of the above-mentioned embodiments of each method. Any reference to memory, storage, database or other medium used in each embodiment provided by the present application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration but not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDR SDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0044] Other embodiments of the disclosure will be apparent to those skilled in the art from consideration of the specification and practice of the embodiments as described herein. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the disclosure being indicated by the following claims.

Claims

1. An intelligent sampling monitoring method based on the distribution characteristics of sewage indicators, characterized in that, The method comprises the following steps: Real-time fuzzy sampling based on the Internet of Things is performed to obtain fuzzy sampling data, and the fuzzy sampling indexes include conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity; The fuzzy sampling data is analyzed to determine abnormal fuzzy indexes, and the fuzzy sampling data contains time information and location information; According to the sampling location and time of the fuzzy sampling data, corresponding sewage index distribution characteristics are called, and the sewage index distribution characteristics are compared with the abnormal fuzzy indexes to determine accurate sampling indexes; the sewage index distribution characteristics contain a plurality of sewage indexes, and each sewage index corresponds to an abnormal occurrence frequency; The accurate sampling data is received to determine abnormal accurate indexes, the distribution of pollution sources is called, and potential pollution source information is determined; According to the potential pollution source information and the sampling location of the accurate sampling data, a monitoring location is determined, and pollution tracing is performed.

2. The intelligent sampling monitoring method based on sewage index distribution characteristics according to claim 1, characterized in that, The step of analyzing the fuzzy sampling data to determine abnormal fuzzy indexes comprises the following steps: According to the time information and the location information, corresponding fuzzy index reference information is called; According to the fuzzy index reference information, it is determined whether the fuzzy sampling data has fuzzy sampling indexes beyond the reference range, and the abnormal fuzzy indexes are determined; The change trend of each fuzzy sampling index in the fuzzy sampling data is extracted, and the existing abnormal fuzzy indexes are determined according to the change trend.

3. The intelligent sampling monitoring method based on sewage index distribution characteristics according to claim 1, characterized in that, The step of comparing the sewage index distribution characteristics with the abnormal fuzzy indexes to determine the accurate sampling indexes comprises the following steps: According to the abnormal fuzzy indexes, an abnormal label is determined, and the abnormal label includes inorganic salt abnormality, organic matter abnormality, acid abnormality, alkali abnormality, oxidation abnormality, reduction abnormality and suspended matter abnormality; The attribute label corresponding to each sewage index in the sewage index distribution characteristics is determined, and the attribute label is inorganic salt, organic matter, acid, alkali, oxidation, reduction and suspended matter; The abnormal label and the attribute label are matched to determine the accurate sampling indexes, and the abnormal probability of each accurate sampling index is determined in combination with the sewage index distribution characteristics.

4. The intelligent sampling monitoring method based on sewage index distribution characteristics according to claim 3, characterized in that, The step of matching the abnormal label and the attribute label to determine the accurate sampling indexes comprises the following steps: According to the abnormal label, a first label set is determined, and according to the attribute label, a second label set of each sewage index is determined; It is determined in turn whether each second label set belongs to a subset of the first label set, and when it belongs, it is considered as a successful match, and the corresponding sewage index is determined as the accurate sampling index.

5. The intelligent sampling monitoring method based on sewage index distribution characteristics according to claim 4, characterized in that, The step of determining the abnormal probability of each accurate sampling index in combination with the sewage index distribution characteristics comprises the following steps: According to the second label set and the first label set, the matching degree of the successfully matched sewage index is calculated; The abnormal occurrence frequency of the sewage index is called, and the abnormal probability of each accurate sampling index is determined according to the abnormal occurrence frequency and the matching degree; According to the abnormal probability, the accurate sampling range and the accurate sampling frequency of the corresponding sewage index are determined, and the accurate sampling range includes a time range and a location range.

6. The intelligent sampling monitoring method based on sewage index distribution characteristics according to claim 1, characterized in that, The step of determining the monitoring location according to the potential pollution source information and the sampling location of the accurate sampling data comprises the following steps: According to the potential pollution source information, the location of the pollution source is determined, and a water flow map is called. The pollution diffusion path is determined according to the pollution source position, the sampling site and a water area flow map; Monitoring sites are arranged on the pollution diffusion path, and the interval distance of the monitoring sites is determined according to the abnormality degree of the accurate sampling data.

7. An intelligent sampling monitoring system based on the distribution characteristics of sewage indicators, characterized in that, The system comprises: a fuzzy sampling data module for obtaining fuzzy sampling data through real-time fuzzy sampling based on the Internet of Things, the fuzzy sampling indexes including conductivity, ultraviolet absorbance, pH value, oxidation-reduction potential and turbidity; an abnormal fuzzy index module for analyzing the fuzzy sampling data to determine abnormal fuzzy indexes, the fuzzy sampling data containing time information and site information; an accurate sampling index module for determining accurate sampling indexes by comparing the abnormal fuzzy indexes with sewage index distribution characteristics corresponding to the sampling site and time of the fuzzy sampling data, the sewage index distribution characteristics containing a plurality of sewage indexes, each of which corresponds to an abnormal occurrence frequency; a pollution source information module for receiving accurate sampling data, determining abnormal accurate indexes, calling pollution source distribution information and determining potential pollution source information; a pollution tracing monitoring module for determining monitoring sites according to the potential pollution source information and the sampling site of the accurate sampling data to trace pollution sources.

8. The intelligent sampling monitoring system based on sewage index distribution characteristics according to claim 7, characterized in that, The abnormal fuzzy index module comprises: a reference information calling unit for calling corresponding fuzzy index reference information according to the time information and the site information; a first abnormal fuzzy unit for determining whether the fuzzy sampling data contains fuzzy sampling indexes beyond the reference range according to the fuzzy index reference information to determine abnormal fuzzy indexes; a second abnormal fuzzy unit for extracting the change trend of each fuzzy sampling index in the fuzzy sampling data and determining the existing abnormal fuzzy indexes according to the change trend.

9. The intelligent sampling monitoring system based on sewage index distribution characteristics according to claim 7, characterized in that, The accurate sampling index module comprises: an abnormal label determining unit for determining existing abnormal labels according to the abnormal fuzzy indexes, the abnormal labels including inorganic salt abnormality, organic matter abnormality, acid abnormality, alkali abnormality, oxidation abnormality, reduction abnormality and suspended matter abnormality; an attribute label determining unit for determining the attribute labels corresponding to each of the sewage indexes in the sewage index distribution characteristics, the attribute labels being inorganic salt, organic matter, acid, alkali, oxidation, reduction and suspended matter; an accurate index determining unit for matching the abnormal labels with the attribute labels to determine accurate sampling indexes and determining the abnormal probability of each accurate sampling index in combination with the sewage index distribution characteristics.

10. The intelligent sampling monitoring system based on sewage index distribution characteristics according to claim 9, characterized in that, The accurate index determining unit comprises: a label set determining subunit for determining a first label set according to the abnormal labels and determining a second label set of each of the sewage indexes according to the attribute labels; a set matching subunit for sequentially determining whether each second label set belongs to a subset of the first label set, and when it belongs, regarding it as a matching success and determining the corresponding sewage index as an accurate sampling index.

Images