A method, system and equipment for multi-parameter water quality monitoring of river water bodies

Abstract

This invention relates to the field of water quality monitoring technology, specifically to a multi-parameter water quality monitoring method, system, and equipment for river water bodies. The invention obtains the water quality stratification impact degree of each monitoring location at different depths at different times by analyzing the parameter data distribution at each monitoring location, as well as the parameter anomaly degree at each depth point; thereby obtaining the probability of black and odorous water at each monitoring location at each time; based on the multi-parameter data of each monitoring location at different depths at each time and the probability of black and odorous water at each monitoring location at each time, it obtains multiple pollution probabilities corresponding to each monitoring point at each time; and based on the probability of black and odorous water at each monitoring location within its neighborhood at the current time, the different pollution probabilities, and the number of pollution times, it obtains the pollution severity of each monitoring location at the current time. This invention improves the accuracy of water quality monitoring by accurately obtaining the pollution severity of each monitoring location.

Description

Technical Field

[0001] This invention relates to the field of water quality monitoring technology, specifically to a multi-parameter water quality monitoring method, system, and equipment for river water bodies. Background Technology

[0002] Urban rivers are the main discharge outlets for sewage outlets and combined sewer overflows. They are usually accompanied by the input of pollutants. Due to factors such as dam regulation and gentle river structure, the water flow in rivers is relatively slow and the oxygen content is low, making it difficult for pollutants to disperse and dilute. In particular, pollutants accumulated in rivers can ferment and decompose to form black and odorous water bodies, making water quality monitoring more necessary.

[0003] In existing technologies, the monitoring of black and odorous water bodies involves obtaining measured values ​​of multiple parameters. When a parameter exceeds a preset threshold based on experience, relevant warning information is output to the staff. However, in actual monitoring, due to the different river structures at each monitoring point, the water body is prone to temperature or density stratification. Existing methods ignore the interference of vertical stratification on the judgment of the biochemical characteristics of the water body at each monitoring point, resulting in inaccurate water quality monitoring of the river body. Summary of the Invention

[0004] To address the technical problem of inaccurate water quality monitoring of rivers caused by neglecting the interference of vertical stratification in the assessment of the biochemical characteristics of water bodies at each monitoring point, the present invention aims to provide a multi-parameter water quality monitoring method, system, and equipment for rivers. The specific technical solution adopted is as follows:

[0005] This invention proposes a multi-parameter water quality monitoring method for river water bodies, the method comprising:

[0006] Acquire multi-parameter data of each monitoring location at different depths in the river at each time point;

[0007] For any parameter, based on the parameter data distribution at different depths for each monitoring location at different times, the degree of water quality stratification impact at each monitoring location at each time is obtained; based on the parameter data distribution at the same depth for different monitoring locations at different times, the degree of parameter anomaly at each depth for each monitoring location at each time is obtained.

[0008] For all parameters, based on the distribution of parameter anomalies at different depths at different monitoring locations at different times, and the degree of influence of water quality stratification, the probability of black and odorous water bodies at each monitoring location at each time is obtained.

[0009] Based on the multi-parameter data of each monitoring position at different depth points at each time and the black and odorous water body possibility of each monitoring position at each time, a plurality of pollution probabilities of each monitoring point at each time are obtained; according to the black and odorous water body possibility of each monitoring position in the neighborhood range at the current time, different pollution probabilities and the number of pollution times, the pollution severity of each monitoring position at the current time is obtained.

[0010] Further, the method for obtaining the water quality stratification influence degree comprises:

[0011] For any parameter of each monitoring position at each time, the parameter data difference between each depth point and the previous depth point is divided by the relative distance between the corresponding depth points, as the parameter variation of each depth point; the ratio between the mean value of the parameter variation of all depth points and the fluctuation degree of the parameter variation is obtained and normalized, as the vertical fluctuation degree of each depth point;

[0012] The difference value of the vertical fluctuation degree between each depth point and the previous depth point is obtained, and the negative difference value between all depth points is selected as the negative difference value;

[0013] For the historical range at each time, the water quality stratification influence degree of each monitoring position at each time is obtained according to the mean value of the absolute value of all negative difference values, the number of negative difference values and the number of all depth points, the mean value of the absolute value of all negative difference values and the number of negative difference values are positively correlated with the water quality stratification influence degree, and the number of depth points is negatively correlated with the water quality stratification influence degree.

[0014] Further, the method for obtaining the parameter abnormality degree comprises:

[0015] For any parameter, the mean value of the parameter data of different monitoring positions at each same depth point in the local range at each time is obtained as the average parameter level of the corresponding depth point;

[0016] The difference between the parameter data of each monitoring position at the same depth point at each time and the corresponding average parameter level is obtained and normalized as the parameter abnormality degree of each monitoring position at the corresponding depth point at each time.

[0017] Further, the method for obtaining the black and odorous water body possibility comprises:

[0018] For any parameter at each time, if the parameter abnormality degree of any monitoring position at any depth point is greater than a preset abnormality threshold, the corresponding time is taken as an abnormal time, the corresponding parameter is taken as an abnormal parameter, and the monitoring position is taken as an abnormal position;

[0019] obtaining a water flow normal coefficient of each monitoring position at each time point according to the parameter abnormality degree distribution of the corresponding depth point of different monitoring positions at different time points, and a first abnormality coefficient;

[0020] obtaining a ratio average value of the number of abnormal time points and the number of all time points in different preset time point ranges, calculating a ratio of the ratio average value and the water flow normal coefficient as a second abnormality coefficient;

[0021] obtaining a product of the first abnormality coefficient, the second abnormality coefficient and the water quality stratification influence degree of each monitoring position at each time point as a black and odorous water body possibility of each monitoring position at each time point.

[0022] Further, the water flow normal coefficient obtaining method comprises:

[0023] for each time point, all adjacent abnormal positions form an abnormal area;

[0024] obtaining the maximum number of the same monitoring positions in the abnormal area between each time point and other time points, calculating a modulus value of a difference vector between the center coordinates of the abnormal area corresponding to the maximum time point and the center coordinates of the abnormal area corresponding to the minimum time point as a displacement of the abnormal area, and obtaining a cosine similarity between the angle between the difference vector direction and the water flow standard direction as a water flow deviation degree;

[0025] in the historical range of each time point, if each monitoring position is an abnormal position at multiple time points, obtaining a product of the displacement average value of the abnormal area corresponding to each monitoring position and the water flow deviation degree average value as the water flow normal coefficient of each monitoring position at each time point.

[0026] Further, the first abnormality coefficient obtaining method comprises:

[0027] for each time point, obtaining the abnormal parameter number ratio of each monitoring position at each depth point to all parameter numbers as an abnormal number ratio;

[0028] obtaining a product between the abnormal number ratio and the parameter abnormality degree average value of all abnormal parameters as a local abnormality coefficient of each depth point at each time point;

[0029] obtaining a ratio of the local abnormality coefficient average value of all depth points between the maximum abnormal time point and the minimum abnormal time point of each monitoring position in the historical range of each time point as the first abnormality coefficient.

[0030] Further, the pollution probability obtaining method comprises:

[0031] The CNN is inputted with multi-parameter data of each monitoring position at different depth points at each moment, and the possibility of black and odorous water body of each monitoring position at each moment is normalized as an initial attention weight value, so that a plurality of pollution probabilities corresponding to each monitoring point at each moment are obtained, including a black and odorous water body pollution probability, an algae pollution probability and a sudden pollution probability.

[0032] Further, the method for obtaining the pollution severity comprises:

[0033] For each moment, a minimum difference value between different pollution probabilities is obtained, a ratio of the corresponding pollution probability is calculated, and the sum of the corresponding pollution probabilities is greater than or equal to another pollution probability, so that it is judged that two kinds of pollution exist at the corresponding moment.

[0034] The product of the probability of sudden pollution of each monitoring position at the current moment and the product of the adjacent sudden pollution moments is obtained, and is negatively correlated and mapped as the sudden pollution recovery coefficient of each monitoring position at the current moment.

[0035] The product of the number of moments with two kinds of pollution in the historical range of the current moment, the average of the black and odorous water body pollution probability and the number of moments of the black and odorous water body pollution is obtained, the ratio of the product result and the sudden pollution recovery coefficient is calculated, and is normalized as the pollution severity of each monitoring position at the current moment.

[0036] The application further provides a multi-parameter water quality monitoring system for river water bodies, comprising a data acquisition module, a parameter anomaly analysis module, a black and odorous water body possibility module and a pollution severity evaluation module.

[0037] The data acquisition module acquires multi-parameter data of each monitoring position at different depth points in the river water body at each moment.

[0038] The parameter anomaly analysis module: for any parameter, the water quality stratification influence degree of each monitoring position at each moment is obtained according to the parameter data distribution of each monitoring position at different depth points at different moments, and the parameter anomaly degree of each monitoring position at each depth point is obtained according to the parameter data distribution of different monitoring positions at the same depth point at different moments.

[0039] The black and odorous water body possibility module: for all parameters, the black and odorous water body possibility of each monitoring position at each moment is obtained according to the parameter anomaly degree distribution of the corresponding depth points of different monitoring positions at different moments and the water quality stratification influence degree.

[0040] The pollution severity assessment module: based on the multi-parameter data of each monitoring position at different depth points at each time and the black and odorous water body possibility of each monitoring position at each time, a plurality of pollution probabilities corresponding to each monitoring point at each time are obtained; and based on the black and odorous water body possibility of each monitoring position in the neighborhood range at the current time, different pollution probabilities and the number of pollution times, the pollution severity of each monitoring position at the current time is obtained.

[0041] The application further provides a multi-parameter water quality monitoring device for river water bodies, which stores programs or instructions, and the programs or instructions are executed by a processor to realize the steps of the multi-parameter water quality monitoring method for river water bodies.

[0042] The application has the following beneficial effects:

[0043] The application obtains the water quality stratification influence degree of each monitoring position at each time, quantifies the significant degree of stratification, and the parameter abnormal degree of each depth point, analyzes the deviation degree of the parameter relative to the historical general level, and quantifies the abnormal level; and then obtains the black and odorous water body possibility of each monitoring position at each time, and preliminarily evaluates the degree of black and odorous water body characteristics; based on the multi-parameter data of each monitoring position at different depth points at each time and the black and odorous water body possibility of each monitoring position at each time, a plurality of pollution probabilities corresponding to each monitoring point at each time are obtained, the possible pollution conditions are analyzed, and the composite pollution phenomenon is effectively revealed; and based on the black and odorous water body possibility of each monitoring position in the neighborhood range at the current time, different pollution probabilities and the number of pollution times, the pollution severity of each monitoring position at the current time is obtained, and the water pollution condition is highly summarized and comprehensively evaluated. The application can accurately obtain the pollution severity of each monitoring position, and improve the accuracy of water quality monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0044] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, the following will briefly introduce the drawings needed in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can be obtained from these drawings without creative labor.

[0045] Figure 1 A flowchart of a multi-parameter water quality monitoring method for river water bodies provided by an embodiment of the present application;

[0046] Figure 2 A flowchart of a water quality stratification influence degree acquisition method provided by an embodiment of the present application;

[0047] Figure 3 A black and odorous water body possibility acquisition method flow chart provided by an embodiment of the present application;

[0048] Figure 4 A structural block diagram of a river water body multi-parameter water quality monitoring system provided by an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the following describes in detail the specific implementation, structure, features and effects of the river water body multi-parameter water quality monitoring method, system and device according to the present application, in combination with the accompanying drawings and preferred embodiments. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures or characteristics in one or more embodiments can be combined in any suitable form.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs.

[0051] The specific scheme of the river water body multi-parameter water quality monitoring method, system and device provided by the present application is specifically described below in combination with the accompanying drawings.

[0052] Please refer to Figure 1 which shows a flow chart of a river water body multi-parameter water quality monitoring method provided by an embodiment of the present application, and the specific method includes:

[0053] Step S1: acquiring multi-parameter data of each monitoring position at different depth points in the river water body at each time.

[0054] In an embodiment of the present application, considering that the structures of different positions of the river are different and there are differences in water depth, it is necessary to analyze the river water quality in combination with the vertical stratification. First, monitoring points are set at known sewage outlets, downstream of rain and sewage mixed discharge outlets, upstream of sluices and dams, etc. of the river, and each monitoring point is stratified monitored, i.e. depth points are uniformly set every 0.5 meters, multi-parameter water quality probes are installed at the depth points, time stamps of the acquired multi-parameters are aligned, and the multi-parameters include integrated dissolved oxygen content, water temperature, pH, conductivity, turbidity and flow rate sensors. Multi-parameter data of each monitoring position at different depth points in the river water body at each time is acquired.

[0055] It should be noted that in an embodiment of the present application, the interval between the times is set to 1 minute, i.e. data is acquired once every minute; in other embodiments of the present application, the interval between the times can be set according to specific conditions, which is not limited and described here.

[0056] It should be noted that, in the embodiments of the present application, in order to facilitate subsequent processing of data, the existing data cleaning methods such as time series smoothing and filtering are used to preliminarily clean the multi-parameter data, and abnormal data is eliminated; in order to avoid the differences between the units and the magnitude of the numerical values of the data, the data is standardized to eliminate the influence of the dimension in the data operation; the specific means are well known to those skilled in the art, and will not be described here.

[0057] Step S2: For any parameter, according to the parameter data distribution of each monitoring position at different depths at different times, the water quality stratification influence degree of each monitoring position at each time is obtained; according to the parameter data distribution of different monitoring positions at the same depth at different times, the parameter abnormality degree of each monitoring position at each depth at each time is obtained.

[0058] Since different regions are affected by the external environment to different degrees, for example, the surface temperature of the river region with strong solar radiation rises faster, which is easy to form a large temperature difference with the bottom layer of the river, and is more likely to promote the stratification phenomenon to occur, and there are certain differences in water depth and flow rate, and the degree of influence of the hydraulic state of different regions by stratification also exists differences, therefore, for any parameter, according to the parameter data distribution of each monitoring position at different depths at different times, the water quality stratification influence degree of each monitoring position at each time is obtained.

[0059] Preferably, in an embodiment of the present application, the method for obtaining the water quality stratification influence degree is as shown in Figure 2 , which shows a flow chart of a method for obtaining a water quality stratification influence degree, comprising:

[0060] Step S201: According to the parameter data distribution of each monitoring position at different depths at different times, the vertical fluctuation degree of each depth is obtained.

[0061] Preferably, if the parameter data measured by a certain monitoring position has a large difference at different depths, and the difference can be maintained stable for a long time and does not fluctuate obviously with the change of solar radiation, that is, the parameter consistently maintains a large difference change, the greater the vertical fluctuation degree; in an embodiment of the present application, the method for obtaining the vertical fluctuation degree comprises:

[0062] For any parameter of each monitoring position at each time, the parameter data difference between each depth point and the previous depth point is calculated, and the relative distance between the corresponding depth points is calculated as the parameter change of each depth point;

[0063] For each time in the history range, the ratio between the mean value of the parameter variation amount of each monitoring position at each depth point and the fluctuation degree of the parameter variation amount at each time is obtained, and normalized as the vertical fluctuation degree of each monitoring position at each depth point at each time.

[0064] Therefore, the parameter variation amount reflects the variation degree between the depth points, the greater the variation amount, the greater the difference between the depth points, and the greater the fluctuation; the fluctuation degree reflects the stability of the parameter variation amount, the smaller the fluctuation degree of the parameter variation amount, the more stable the variation amount, the greater the vertical fluctuation degree when the parameter changes greatly.

[0065] It should be noted that in the embodiments of the present application, the difference between the position coordinates of the depth points is calculated as the relative distance; wherein the difference represents the absolute value of the difference; the history range can be set according to specific conditions, and in an embodiment of the present application, the history range represents a time range formed by each time as a reference and all previous historical times.

[0066] It should be noted that in an embodiment of the present application, the standard deviation is calculated to reflect the fluctuation degree of the parameter variation amount, the greater the standard deviation, the greater the fluctuation degree of the variation, the more inconsistent the variation amount, the smaller the standard deviation, the smaller the fluctuation degree of the variation, and the more consistent the variation amount; in other embodiments of the present application, the fluctuation degree of the parameter variation amount can also be reflected by variance or range, and the specific means are well known to those skilled in the art, which will not be repeated here.

[0067] It should be noted that in some embodiments of the present application, linear normalization or normalization function is used for normalization, such as logistic function , and the specific means are well known to those skilled in the art, which will not be limited and repeated here.

[0068] Step S202: obtaining the difference value of the vertical fluctuation degree between each depth point and the previous depth point at each time for each monitoring position, and selecting all the difference values between the depth points as negative numbers as negative difference values.

[0069] The smaller the negative difference value, the smaller the vertical fluctuation degree of the point with greater depth, the less obvious the stratification change, the farther the distance from the water surface, the greater the depth point, the closer the vertical fluctuation degree, and the less obvious the stratification characteristics.

[0070] Step S203: for each monitoring position at each time, the water quality stratification influence degree of each monitoring position at each time is obtained according to the absolute value of all negative difference values, the number of negative difference values and the number of all depth points, the absolute value of negative difference value and the number of negative difference value are positively correlated with the water quality stratification influence degree, and the number of depth points is negatively correlated with the water quality stratification influence degree.

[0071] It should be noted that, considering the stratification stability, the closer to the surface layer of the water surface, the more obvious the stratification, the greater the vertical fluctuation; the absolute value of the negative difference value reflects the change of the vertical fluctuation degree between the depth points, the greater the absolute value, the more the vertical fluctuation degree changes, and the more the negative difference value, the smaller the vertical fluctuation degree changes with the increase of the depth, and the greater the influence of water quality stratification; the more the number of depth points, the higher the resolution of the vertical structure of the water body, and the smaller the influence of water quality stratification, therefore, the absolute value of the negative difference value, the number of negative difference values are positively correlated with the degree of influence of water quality stratification, and the number of depth points is negatively correlated with the degree of influence of water quality stratification.

[0072] In an embodiment of the present application, the absolute value of all negative difference values is calculated, the ratio of the number of negative difference values and the number of all depth points is calculated as the first influence coefficient; the product between the first influence coefficient and the absolute value is obtained as the degree of influence of water quality stratification, therefore, the correlation between the absolute value of the negative difference value, the number of negative difference values and the number of depth points and the degree of influence of water quality stratification is established based on the above basic mathematical operation, that is, the greater the absolute value of the negative difference value, the more the number of negative difference values, the more likely the stratification is obvious, and the smaller the number of depth points, the greater the degree of influence of water quality stratification.

[0073] Under normal circumstances, although there is a certain fluctuation in each monitoring parameter, the closer the stability degree of the depth points of the same horizontal plane, the closer the distribution of the parameter data of the same depth point, the more normal the parameter, on the contrary, the more different the distribution of the parameter data of the same depth point, the more abnormal the parameter reflects; according to the parameter data distribution of the same depth point at different time in different monitoring positions at different time, the parameter abnormality degree of each monitoring position at each depth point at each time is obtained.

[0074] Preferably, in an embodiment of the present application, the parameter abnormality degree obtaining method comprises:

[0075] For any parameter, the parameter data mean of each same depth point of different monitoring positions at each time within a preset time range at each time is obtained as the average parameter level of the corresponding depth point;

[0076] It should be noted that the overall parameter value of the same depth point in the local range is quantified by taking the mean value, which reflects the basic performance level of the parameter of the corresponding depth point, so as to be compared subsequently.

[0077] The difference between the parameter data of each monitoring position at the same depth point at each time and the corresponding average parameter level is obtained and normalized as the parameter abnormality degree of each monitoring position at the corresponding depth point at each time.

[0078] It should be noted that in an embodiment of the present application, the method for obtaining the preset time range at each time point is that all time points are divided according to a preset interval to obtain a plurality of preset time ranges, and the preset time range in which each time point is located is analyzed, wherein the preset interval is divided once every 12 hours; in other embodiments of the present application, the preset time range can be set according to specific conditions, which is not limited or described here.

[0079] Step S3: For all parameters, the possibility of black and odorous water body at each monitoring position at each time point is obtained according to the parameter abnormality degree distribution of the corresponding depth point at different monitoring positions at different time points and the water quality stratification influence degree.

[0080] The black and odorous water body is caused by the pollutants released by the sediments accumulated at the bottom of the river for a long time, the pollution range may spread to the surrounding but there is no long-distance migration pollution, the water quality changes greatly, and a certain degree of abnormality exists in multiple parameters of different monitoring positions; the water body stratification may have a certain influence on the formation of the black and odorous water body, the stratification effect provides conditions for the formation of the black and odorous water body, the more serious and stable the stratification is, the more easily the black and odorous water body is formed; for all parameters, the possibility of black and odorous water body at each monitoring position at each time point is obtained according to the parameter abnormality degree distribution of the corresponding depth point at different monitoring positions at different time points and the water quality stratification influence degree.

[0081] Preferably, in an embodiment of the present application, the method for obtaining the possibility of black and odorous water body can refer to Figure 3 which shows a flowchart of a method for obtaining the possibility of black and odorous water body, comprising:

[0082] Step S301: For any parameter at each time point, if the parameter abnormality degree of any depth point at any monitoring position is greater than a preset abnormality threshold, the corresponding time point is taken as an abnormal time point, the corresponding parameter is taken as an abnormal parameter, and the monitoring position is taken as an abnormal position.

[0083] It should be noted that in an embodiment of the present application, the preset abnormality threshold is set to 0.5; in other embodiments of the present application, the size of the preset abnormality threshold can be set according to specific conditions, which is not limited or described here.

[0084] Step S302: According to the parameter abnormality degree distribution of the corresponding depth point at different monitoring positions at different time points, the water flow normal coefficient of each monitoring position at each time point and the first abnormality coefficient are obtained.

[0085] Preferably, in an embodiment of the present application, the method for obtaining the water flow normal coefficient comprises:

[0086] For each time point, all adjacent abnormal positions form an abnormal area;

[0087] obtaining the maximum of the number of same monitoring positions in the abnormal area between each time and other subsequent different times, the difference vector of the center coordinates of the abnormal area corresponding to the maximum time and the center coordinates of the abnormal area corresponding to the minimum time, calculating the modulus value of the difference vector as the displacement of the abnormal area, and obtaining the cosine similarity between the included angle between the difference vector direction and the standard direction of the water flow as the water flow deviation degree;

[0088] In the historical range of each time, if there are multiple times when each monitoring position is an abnormal position, obtaining the product of the average of the displacement of each monitoring position in the abnormal area corresponding to each time and the average of the water flow deviation degree as the water flow normal coefficient of each monitoring position at each time.

[0089] Preferably, in an embodiment of the present application, the first abnormality coefficient acquisition method comprises:

[0090] For each time, obtaining the ratio of the number of abnormal parameters corresponding to each monitoring position at each depth point to the total number of parameters as the abnormality proportion;

[0091] obtaining the product of the abnormality proportion and the average of the parameter abnormality degree corresponding to all abnormal parameters as the local abnormality coefficient of each depth point at each time;

[0092] obtaining the ratio of the average of the local abnormality coefficients of all depth points between the maximum abnormal time and the minimum abnormal time of each monitoring position in the historical range of each time as the first abnormality coefficient.

[0093] Step S303: obtaining the average of the ratio of the number of abnormal times to the total number of times in different preset time ranges, calculating the ratio of the average ratio and the water flow normal coefficient as the second abnormality coefficient;

[0094] obtaining the product of the first abnormality coefficient, the second abnormality coefficient and the water quality stratification influence degree of each monitoring position at each time as the black and odorous water body possibility of each monitoring position at each time.

[0095] Based on this, the larger the first abnormality coefficient, the greater the abnormality degree of each monitoring position with the increase of time sequence, and the more likely it is a black and odorous water body possibility; the larger the second abnormality coefficient, the more the number of abnormal times, the smaller the water flow normal coefficient, the greater the water quality stratification influence degree, and the more likely it is to exhibit black and odorous water body characteristics.

[0096] Step S4: obtaining a plurality of pollution probabilities of each monitoring point at each time based on the multi-parameter data of each monitoring position at different depth points at each time and the black and odorous water body possibility of each monitoring position at each time, and obtaining a pollution severity of each monitoring position at the current time according to the black and odorous water body possibility of each monitoring position in the neighborhood range at the current time, different pollution probabilities and the number of pollution times.

[0097] The multi-parameter data of each monitoring position at different depth points at each time is input into a preset CNN model, and the black and odorous water body possibility of each monitoring position at each time is normalized by using softmax() as the initial attention weight of each monitoring position, and then a plurality of pollution probabilities of each monitoring position at each time are output, including the black and odorous water body pollution probability, the algae pollution probability and the sudden pollution probability. The specific means are well known to those skilled in the art and will not be described here.

[0098] It should be noted that the preset CNN model is a mapping model of data to a plurality of pollution probabilities obtained according to related historical data and a plurality of pollution probabilities.

[0099] In a real river, the water body at the same monitoring point may be polluted in multiple ways. The more the pollution, the more serious the pollution accumulation. The pollution severity of each monitoring position at the current time is obtained according to the black and odorous water body possibility of each monitoring position in the neighborhood range at the current time, different pollution probabilities and the number of pollution times.

[0100] Preferably, in an embodiment of the present application, the method for obtaining the pollution severity comprises:

[0101] For each time, the minimum value of the difference between different pollution probabilities is obtained. If the ratio result between the corresponding pollution probabilities is greater than a preset ratio threshold value, and the sum of the corresponding pollution probabilities is greater than or equal to another pollution probability, it is judged that there are two kinds of pollution at the corresponding time.

[0102] The product of the probability of sudden pollution of each monitoring position at the current time and the number of consecutive adjacent sudden pollution times is obtained, and a negative correlation mapping is performed to obtain a sudden pollution recovery coefficient of each monitoring position at the current time.

[0103] The product of the number of times of two kinds of pollution in the historical range at the current time, the average of the black and odorous water body pollution probability and the number of times of black and odorous water body pollution is obtained, the ratio of the product result and the sudden pollution recovery coefficient is calculated, and the ratio is normalized to obtain the pollution severity of each monitoring position at the current time.

[0104] It should be noted that in one embodiment of the present application, the size of the preset ratio threshold is set to 0.8; in other embodiments of the present application, the size of the preset ratio threshold can be set according to specific circumstances, which is not limited and described here.

[0105] It should be noted that in some embodiments of the present application, the reciprocal or exponential function with a natural constant as the base is used The negative correlation mapping is performed, wherein in order to avoid the denominator of the formula being 0 when taking the reciprocal, an artificially set threshold such as 0.01 is added; the specific means are well known to those skilled in the art, which are not described here.

[0106] Based on this, the pollution severity of each monitoring position at the current time is input into the GIS platform to realize early warning of different water pollution conditions: when there is black and odorous water body, the position coordinates of the corresponding monitoring point in the river channel are red and flicker, the sudden pollution is orange and flickers, and the algal pollution is yellow and flickers, which helps to improve the accuracy of water quality monitoring.

[0107] In summary, the present application obtains the water quality stratification influence degree of each monitoring position at each time and the parameter abnormality degree of each depth point, and then obtains the black and odorous water body possibility of each monitoring position at each time, based on the multi-parameter data of each monitoring position at each time at different depth points and the black and odorous water body possibility of each monitoring position at each time. The present application obtains the pollution probability of each monitoring point corresponding to multiple pollutions at each time, and obtains the pollution severity of each monitoring position at the current time according to the black and odorous water body possibility of each monitoring position, different pollution probabilities and the number of pollution times in the neighborhood range at the current time. The present application accurately obtains the pollution severity of each monitoring position, and improves the accuracy of water quality monitoring.

[0108] The present application proposes a multi-parameter water quality monitoring system for river water body, please refer to Figure 4 which shows a structural block diagram of a multi-parameter water quality monitoring system for river water body, including a data acquisition module 401, a parameter abnormality analysis module 402, a black and odorous water body possibility module 403 and a pollution severity evaluation module 404:

[0109] The data acquisition module 401 acquires multi-parameter data of each monitoring position at different depth points in the river water body at each time;

[0110] The parameter anomaly analysis module 402: for any parameter, according to the parameter data distribution of each monitoring position at different time instants at different depth points, the water quality stratification influence degree of each monitoring position at each time instant is obtained; according to the parameter data distribution of different monitoring positions at different time instants at the same depth point, the parameter anomaly degree of each monitoring position at each depth point at each time instant is obtained.

[0111] The black and odorous water possibility module 403: for all parameters, according to the parameter anomaly degree distribution of different monitoring positions at corresponding depth points at different time instants, and the water quality stratification influence degree, the black and odorous water possibility of each monitoring position at each time instant is obtained.

[0112] The pollution severity evaluation module 404: based on the multi-parameter data of each monitoring position at different depth points at each time instant and the black and odorous water possibility of each monitoring position at each time instant, the corresponding pollution probability of each monitoring position at each time instant is obtained; according to the black and odorous water possibility of each monitoring position in the neighborhood range at the current time instant, the different pollution probabilities and the pollution time instant quantity, the pollution severity of each monitoring position at the current time instant is obtained.

[0113] It should be understood that the multi-parameter water quality monitoring system for river water bodies provided in the embodiment is used to execute the above-mentioned bladder pressure information monitoring method, and thus has the same beneficial effects as the method adopted, run or implemented by the application program stored therein.

[0114] The application further provides a multi-parameter water quality monitoring device for river water bodies, which stores a program or instruction, and the program or instruction is executed by a processor to implement the steps of the above-mentioned multi-parameter water quality monitoring method for river water bodies.

[0115] It should be noted that the above-mentioned sequence of the embodiments of the application is only for description, and does not represent the advantages and disadvantages of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0116] Each embodiment in the specification is described in a progressive manner, and the same or similar parts between each embodiment can be referred to each other, and each embodiment mainly describes the difference from other embodiments.

Claims

1. A multi-parameter water quality monitoring method of a river water body, characterized in that, The method comprises: obtaining multi-parameter data of each monitoring position at different depth points in the river water body at each time point; for any parameter, obtaining the water quality stratification influence degree of each monitoring position at each time point according to the parameter data distribution of each monitoring position at different depth points at different time points, and obtaining the parameter anomaly degree of each monitoring position at each depth point at each time point according to the parameter data distribution of different monitoring positions at the same depth point at different time points; for all parameters, obtaining the black and odorous water body possibility of each monitoring position at each time point according to the parameter anomaly degree distribution of the corresponding depth points of different monitoring positions at different time points and the water quality stratification influence degree; based on the multi-parameter data of each monitoring position at different depth points at each time point and the black and odorous water body possibility of each monitoring position at each time point, obtaining the corresponding pollution probability of each monitoring point at each time point; and obtaining the pollution severity of each monitoring position at the current time point according to the black and odorous water body possibility, different pollution probabilities and the number of pollution time points of each monitoring position within the neighborhood range at the current time point; the method for obtaining the water quality stratification influence degree comprises: for any parameter of each monitoring position at each time point, calculating the parameter data difference between each depth point and the previous depth point over the relative distance between the corresponding depth points as the parameter variation of each depth point; obtaining the ratio between the mean value of the parameter variation of all depth points and the fluctuation degree of the parameter variation, and normalizing it as the vertical fluctuation degree of each depth point; obtaining the difference value of the vertical fluctuation degree between each depth point and the previous depth point, and selecting all the negative difference values between the depth points as negative difference values; for the historical range at each time point, obtaining the water quality stratification influence degree of each monitoring position at each time point according to the absolute value mean of all negative difference values, the number of negative difference values and the number of all depth points, the absolute value mean of negative difference values and the number of negative difference values are positively correlated with the water quality stratification influence degree, and the number of depth points is negatively correlated with the water quality stratification influence degree; the method for obtaining the parameter anomaly degree comprises: for any parameter, obtaining the mean value of the parameter data of different monitoring positions at each same depth point at all time points within the local range at each time point as the average parameter level of the corresponding depth point; obtaining the difference between the parameter data of each monitoring position at the same depth point at each time point and the corresponding average parameter level, and normalizing it as the parameter anomaly degree of each monitoring position at the corresponding depth point at each time point.

2. The multi-parameter water quality monitoring method of a river water body according to claim 1, characterized in that, the method for obtaining the black and odorous water body possibility comprises: for any parameter at each time point, if the parameter anomaly degree of any monitoring position at any depth point is greater than a preset abnormal threshold, the corresponding time point is taken as an abnormal time point, the corresponding parameter is taken as an abnormal parameter, and the monitoring position is taken as an abnormal position; obtaining the water flow normal coefficient of each monitoring position at each time point and the first abnormal coefficient according to the parameter anomaly degree distribution of the corresponding depth points of different monitoring positions at different time points. Obtain the average value of the ratio of the number of abnormal time points to the number of all time points in different preset time ranges, calculate the ratio of the average value of the ratio to the water flow normal coefficient, and take the ratio as a second abnormal coefficient; Obtain the product of the first abnormal coefficient, the second abnormal coefficient, and the water quality stratification influence degree of each monitoring position at each time point, as the black and odorous water body possibility of each monitoring position at each time point.

3. The method according to claim 2, wherein, The method for obtaining the water flow normal coefficient comprises: For each time point, all adjacent abnormal positions form an abnormal area; Obtain the maximum number of the same monitoring positions in the abnormal area between each time point and other time points thereafter, calculate the modulus of the difference vector between the center coordinates of the abnormal area corresponding to the maximum time point and the center coordinates of the abnormal area corresponding to the minimum time point as the displacement of the abnormal area, and obtain the cosine similarity between the included angle between the difference vector direction and the water flow standard direction as the water flow deviation degree; Within the historical range of each time point, if each monitoring position is an abnormal position at multiple time points, obtain the product of the average value of the displacement of the abnormal area corresponding to each monitoring position and the average value of the water flow deviation degree as the water flow normal coefficient of each monitoring position at each time point.

4. The multi-parameter water quality monitoring method of a river water body according to claim 2, characterized in that, The method for obtaining the first abnormal coefficient comprises: For each time point, obtain the ratio of the number of abnormal parameters corresponding to each depth point to the number of all parameters of each monitoring position as the abnormal parameter ratio; Obtain the product between the abnormal parameter ratio and the average value of the parameter abnormal degree corresponding to all abnormal parameters as the local abnormal coefficient of each depth point at each time point. Obtain the ratio of the average value of the local abnormal coefficient of all depth points between the maximum abnormal time point and the minimum abnormal time point within the historical range of each monitoring position at each time point as the first abnormal coefficient.

5. The method for multi-parameter water quality monitoring of a river water body according to claim 1, characterized in that, The method for obtaining the pollution probability comprises: Input the multi-parameter data of each monitoring position at each time point at different depth points into a preset CNN model, normalize the black and odorous water body possibility of each monitoring position at each time point as the initial attention weight, and obtain the corresponding multiple pollution probabilities of each monitoring point at each time point, wherein the multiple pollution probabilities include the black and odorous water body pollution probability, the algae pollution probability, and the sudden pollution probability.

6. The multi-parameter water quality monitoring method of a river water body according to claim 5, characterized in that, The method for obtaining the pollution severity comprises: For each time point, obtain the minimum difference between different pollution probabilities, calculate the ratio of the corresponding pollution probability, and determine that there are two kinds of pollution when the sum of the corresponding pollution probability is greater than or equal to another pollution probability; Obtain the product of the probability of sudden pollution of each monitoring position at the current time point and the continuous adjacent sudden pollution time, and perform negative correlation mapping as the sudden pollution recovery coefficient of each monitoring position at the current time point; Obtain the product of the number of time points with two kinds of pollution, the average value of the black and odorous water body pollution probability, and the number of time points with black and odorous water body pollution within the historical range of the current time point, calculate the ratio of the product result to the sudden pollution recovery coefficient, and perform normalization as the pollution severity of each monitoring position at the current time point.

7. A multi-parameter water quality monitoring system for a river water body, characterized in that, The method comprises a data acquisition module, a parameter abnormality analysis module, a black and odorous water body possibility module, and a pollution severity evaluation module. The data acquisition module acquires multi-parameter data of each monitoring position at different depth points in the river water body at each time; The parameter anomaly analysis module obtains the water quality stratification influence degree of each monitoring position at each time according to the parameter data distribution of each monitoring position at different depth points at different times; and obtains the parameter anomaly degree of each monitoring position at each depth point at each time according to the parameter data distribution of different monitoring positions at the same depth point at different times. The method for obtaining the water quality stratification influence degree comprises: For any parameter of each monitoring position at each time, the parameter variation of each depth point is calculated as the ratio of the parameter data difference between each depth point and the previous depth point to the relative distance between the corresponding depth points; the ratio between the mean value of the parameter variation of all depth points and the fluctuation degree of the parameter variation is obtained and normalized as the vertical fluctuation degree of each depth point; The difference value of the vertical fluctuation degree between each depth point and the previous depth point is obtained, and the negative difference value between all depth points is selected as the negative difference value; For the historical range at each time, the water quality stratification influence degree of each monitoring position at each time is obtained according to the absolute value mean of all negative difference values, the number of negative difference values and the number of all depth points, and the absolute value mean of all negative difference values and the number of negative difference values are positively correlated with the water quality stratification influence degree, and the number of depth points is negatively correlated with the water quality stratification influence degree. The method for obtaining the parameter anomaly degree comprises: For any parameter, the average parameter level of each corresponding depth point is obtained as the parameter data mean of different monitoring positions at each same depth point within the local range at each time; The difference between the parameter data of each monitoring position at the same depth point at each time and the corresponding average parameter level is obtained and normalized as the parameter anomaly degree of each monitoring position at the corresponding depth point at each time. The black and odorous water body possibility module obtains the black and odorous water body possibility of each monitoring position at each time according to the parameter anomaly degree distribution of the corresponding depth point of different monitoring positions at different times and the water quality stratification influence degree. The pollution severity evaluation module obtains the corresponding multi-pollution probability of each monitoring position at each time based on the multi-parameter data of each monitoring position at different depth points at each time and the black and odorous water body possibility of each monitoring position at each time; and obtains the pollution severity of each monitoring position at the current time according to the black and odorous water body possibility of each monitoring position, different pollution probabilities and the number of pollution times within the neighborhood range at the current time.

8. A multi-parameter water quality monitoring device for a river water body, characterized in that, The device stores programs or instructions, which are executed by the processor to realize the steps of the multi-parameter water quality monitoring method of the river water body according to any one of claims 1-6.

Images