Intelligent monitoring system for water quality of water supply network

Abstract

The application relates to the technical field of pipe network water quality monitoring, in particular to a water supply pipe network water quality intelligent monitoring system. The system comprises a spatial feature analysis module, which is used for collecting the water age of each monitoring point in the water supply pipe network and various water quality parameters at each time; the spatial consistency index of a target monitoring point at the same time is obtained by using the numerical change range of various water quality parameters of the target monitoring point and adjacent monitoring points upstream and downstream of the target monitoring point; a flow velocity adjustment factor acquisition module is used for acquiring the flow velocity adjustment factor of the target monitoring point at one time; a real anomaly index acquisition module is used for acquiring the real anomaly index of the target monitoring point at one time; and an anomaly score correction module is used for correcting the initial anomaly score of the target monitoring point at one time by using the flow velocity adjustment factor and the real anomaly index of the target monitoring point at one time to obtain a corrected anomaly score. The application can accurately monitor the water quality of the water supply pipe network.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of pipe network water quality monitoring, and in particular to an intelligent water quality monitoring system for a water supply pipe network. BACKGROUND

[0002] Water quality monitoring in a water supply pipe network is not only a basic measure to ensure the safety of residents' drinking water, but also an important link in the management of urban infrastructure and environmental protection. In this process, monitoring data, as basic information for assessing water quality, judging abnormal events, and driving intelligent scheduling, directly affects the operational efficiency and public safety of the system. If the monitoring data is false, false alarm, or missed, it may lead to misjudgment of water pollution or delay in disposal, resulting in water supply risks. On the other hand, frequent false alarms also cause unnecessary resource investment, increase operational and maintenance costs of on-site investigation and equipment maintenance, and reduce system response efficiency. Therefore, how to improve the accuracy and reliability of water quality monitoring data and reduce false alarms is a key goal to improve the performance of the monitoring system.

[0003] Under the traditional mode, in a water supply pipe network, the system usually arranges several water quality monitoring points at key locations such as the outlet of the water plant, the main pipeline, the regional boundary point, the terminal pipe network, and the key user area, for real-time collection of water quality parameter data such as pH, residual chlorine, turbidity, and conductivity. However, since the water supply pipe network usually covers the entire city or region, the monitoring points are distributed in various environments such as underground wells, pump stations, water tanks, and residential area junctions. These locations are subject to complex working conditions such as large temperature fluctuations, water pressure shocks, and electromagnetic interference, which easily lead to contamination, aging, signal loss, or drift of the sensor probe, causing the obtained data to exhibit similar changes to real water quality anomalies. The number of monitoring devices in a city water supply pipe network is large, but the sampling frequency is usually minute-level, and the device maintenance period is weeks or even months. When an instrument malfunctions, it is often impossible to check it on site in a timely manner, and relying solely on anomaly detection algorithms (such as Isolation Forest) may not effectively distinguish between data anomalies caused by real water pollution and those caused by monitoring instrument problems, ultimately resulting in false alarms and unnecessary operation and maintenance, increasing operational costs. SUMMARY

[0004] To solve the above technical problems, the present application aims to provide an intelligent water quality monitoring system for a water supply pipe network, and the technical solution adopted is as follows:

[0005] One embodiment of the present application provides an intelligent water quality monitoring system for a water supply pipe network, which comprises:

[0006] The spatial feature analysis module is configured to collect the water age and various water quality parameters of each monitoring point in the water supply network; obtain the numerical variation range of various water quality parameters of each monitoring point at each time, and obtain the spatial consistency index of the target monitoring point at the time by using the numerical variation range of various water quality parameters of the target monitoring point and its upstream and downstream adjacent monitoring points at the time.

[0007] The flow rate adjustment factor acquisition module is configured to obtain the flow rate adjustment factor of the target monitoring point at the time according to the spatial consistency index of the target monitoring point at the time, the water flow rate, and the water age of the target monitoring point, the upstream adjacent monitoring point of the target monitoring point, and the last monitoring point in the water supply network.

[0008] The real anomaly index acquisition module is configured to obtain the real anomaly index of the target monitoring point at the time according to various water quality parameters of the target monitoring point at the time, various water quality parameters of the target monitoring point at the time before the time, and various water quality parameters of the target monitoring point at a historical time.

[0009] The anomaly score correction module is configured to obtain the initial anomaly score of the target monitoring point at the time; and correct the initial anomaly score of the target monitoring point at the time by using the flow rate adjustment factor and the real anomaly index of the target monitoring point at the time to obtain the corrected anomaly score.

[0010] Preferably, the numerical variation range of various water quality parameters of each monitoring point at each time comprises:

[0011] The difference between the water quality parameter of a monitoring point at a time and the water quality parameter of the monitoring point at the time before the time is obtained as the numerical variation range of the water quality parameter of the monitoring point at the time.

[0012] Preferably, the spatial consistency index of the target monitoring point at the time is obtained by using the numerical variation range of various water quality parameters of the target monitoring point and its upstream and downstream adjacent monitoring points at the time, comprising:

[0013] The absolute value of the difference between the numerical variation range of a water quality parameter of an upstream adjacent monitoring point of the target monitoring point and the target monitoring point at the same time is obtained, and is recorded as the numerical variation range difference of the water quality parameter corresponding to the upstream adjacent monitoring point at the same time. The numerical variation range difference of each water quality parameter corresponding to each upstream adjacent monitoring point of the target monitoring point at the same time is summed to obtain an upstream cumulative difference. The absolute value of the difference between the numerical variation range of a water quality parameter of a downstream adjacent monitoring point of the target monitoring point and the target monitoring point at the same time is obtained, and is recorded as the numerical variation range difference of the water quality parameter corresponding to the downstream adjacent monitoring point at the same time. The numerical variation range difference of each water quality parameter corresponding to each downstream adjacent monitoring point of the target monitoring point at the same time is summed to obtain a downstream cumulative difference. The normalized value of the sum of the upstream cumulative difference and the downstream cumulative difference is obtained by subtracting the first preset value, to obtain the spatial consistency index of the target monitoring point at the same time.

[0014] Preferably, the flow rate adjustment factor of the target monitoring point at a time is obtained according to the spatial consistency index of the target monitoring point at the time, the water flow velocity, and the water age of the target monitoring point, the upstream adjacent monitoring point of the target monitoring point, and the last monitoring point in the water supply network, and includes:

[0015] The difference between the water age of the target monitoring point and the average value of the water ages of all upstream adjacent monitoring points of the target monitoring point is obtained, and then the sum of the water age of the last monitoring point in the water supply network and the super parameter is obtained to obtain a water age characteristic value. The sum of the water flow velocity of the target monitoring point at a time and the super parameter is obtained, and then the maximum value of the water flow velocities of all monitoring points at the time is obtained to obtain a water flow velocity characteristic value. The flow rate adjustment factor of the target monitoring point at the time is obtained by multiplying the spatial consistency index of the target monitoring point at the time by the ratio of the water age characteristic value to the water flow velocity characteristic value.

[0016] Preferably, the real anomaly index of the target monitoring point at a time is obtained according to the various water quality parameters at the time, the various water quality parameters at a time before the time, and the various water quality parameters at a historical time, and includes:

[0017] The difference between a water quality parameter of the target monitoring point at a time and the water quality parameter at a time before the time is obtained, and then the water quality parameter at a time before the time is obtained, and then the absolute value is obtained to obtain the growth rate of the water quality parameter at the time. The average growth rate corresponding to the time is obtained by averaging the growth rates of the various water quality parameters at the time. The absolute value of the difference between a water quality parameter of the target monitoring point at a time and the average value of the water quality parameter at each time in history is obtained to obtain the deviation degree of the water quality parameter at the time. The average deviation degree corresponding to the time is obtained by averaging the deviation degrees of the various water quality parameters at the time. The real anomaly index of the target monitoring point at the time is obtained by adding the average deviation degree and the average growth rate.

[0018] Preferably, the initial abnormality score of the target monitoring point at the moment is corrected by using the flow rate adjustment factor and the real abnormality index of the target monitoring point at the moment to obtain a corrected abnormality score, comprising:

[0019] The normalized value of the flow rate adjustment factor and the normalized value of the real abnormality index of the target monitoring point at the moment are added and averaged to obtain the real abnormality factor of the target monitoring point at the moment; the abnormality attribution function is constructed, and the real abnormality factor of the target monitoring point at the moment is brought into the abnormality attribution function to obtain an adjustment coefficient; and the initial abnormality score of the target monitoring point at the moment is obtained according to the adjustment coefficient and the initial abnormality score of the target monitoring point at the moment.

[0020] Preferably, the abnormality attribution function is specifically:

[0021]

[0022] Wherein, The adjustment coefficient is represented by a; The real abnormality factor of the target monitoring point A at the moment t is represented by a t; and a represents a set threshold value.

[0023] Preferably, the initial abnormality score of the target monitoring point at the moment is corrected by using the flow rate adjustment factor and the real abnormality index of the target monitoring point at the moment to obtain a corrected abnormality score, comprising:

[0024] The initial abnormality score at the moment is multiplied by the adjustment coefficient and normalized to obtain the corrected abnormality score at the moment.

[0025] The embodiment of the application has at least the following beneficial effects: the application collects the water age of each monitoring point in the water supply pipe network and various water quality parameters at each moment, and then obtains the numerical change amplitude of various water quality parameters of each monitoring point at each moment, and then analyzes the numerical change amplitude of the target monitoring point and its adjacent monitoring points to obtain the spatial consistency index of the target monitoring point at each moment; the flow rate adjustment factor of the target monitoring point at the moment is obtained according to the spatial consistency index of the target monitoring point at the moment, the water flow rate, and the water age of the target monitoring point and the water age of the adjacent monitoring point upstream; then the real abnormality index of the target monitoring point at the moment is obtained by analyzing various water quality parameters of the target monitoring point at each moment; finally, the initial abnormality score of the target monitoring point at the moment is obtained; the initial abnormality score of the target monitoring point at the moment is corrected by using the flow rate adjustment factor and the real abnormality index of the target monitoring point at the moment to obtain a corrected abnormality score. The application can effectively distinguish the real abnormality and the abnormality caused by the problem of the monitoring instrument, and improve the accuracy of water quality monitoring. BRIEF DESCRIPTION OF DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, and the advantages thereof, below will briefly introduce the drawings needed in the embodiments or 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 based on these drawings without creative effort.

[0027] Figure 1 A system block diagram of a water quality intelligent monitoring system for a water supply network provided by an embodiment of the present application. DETAILED DESCRIPTION

[0028] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined object, the specific embodiments, structure, features and effects of a water quality intelligent monitoring system according to the present application are described in detail below in combination with the 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.

[0029] 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.

[0030] The specific scheme of a water quality intelligent monitoring system for a water supply network provided by the present application is described in detail below in combination with the drawings.

[0031] Embodiment, the main application scenario of the present application is: the present application mainly analyzes the water quality of each monitoring point in the water supply network, and then achieves the purpose of water quality monitoring.

[0032] Please refer to Figure 1 which shows a system block diagram of a water quality intelligent monitoring system for a water supply network provided by an embodiment of the present application, the system includes the following modules:

[0033] The spatial feature analysis module is used to collect the water age and various water quality parameters at each time of each monitoring point in the water supply network; obtain the numerical change range of various water quality parameters at each time of each monitoring point, and obtain the spatial consistency index of the target monitoring point at this time by using the numerical change range of various water quality parameters of the target monitoring point and its upstream and downstream adjacent monitoring points at this time.

[0034] Obtain various water quality parameters of each monitoring point in the target area, obtain various water quality parameters through various monitoring sensors of the monitoring point, generally include the following conventional water quality monitoring parameters, such as: pH value, residual chlorine, turbidity, temperature, etc.; The sampling frequency of the monitoring points in the same area is usually the same, if there is a difference in the sampling frequency between the monitoring points, the sampling frequency is unified, such as once a day.

[0035] Further, obtain the water age of each monitoring point and update it periodically. Water age refers to the time that water spends in the water supply network from entering the water supply network to reaching a certain monitoring point. The specific update period can be set according to different scenes and actual needs. Water age usually changes slowly, and it can be updated once a week in water quality monitoring of the water supply network. If more accurate water age is needed, the update period can be shortened. The method of obtaining water age can also be obtained according to the actual scene. This application provides a conventional method for reference: establish a digital model of the water supply network through simulation software (such as EPANET), set the actual water supply network parameters such as the length, diameter, roughness of each pipe section, the topology of the network, the water flow of the water plant, and the node water demand, and obtain the water age of each monitoring point.

[0036] At the same time, the collected data needs to be processed, mainly including missing value processing and normalization processing. Missing value processing includes filling missing values through interpolation methods such as moving average. Normalization processing is used to ensure that various water quality parameters have the same data scale, avoiding distortion of subsequent analysis and calculation results. At the same time, the monitoring point to be analyzed is recorded as the target monitoring point.

[0037] In the water supply network, the water inside the pipeline is continuously flowing, and water pollutants will naturally spread along the water flow. Therefore, when water quality abnormalities occur, changes in water quality parameter data will not only occur at the target monitoring point, but also will have consistent trends at the upstream and downstream adjacent monitoring points of the target monitoring point based on the flow direction and continuity of water in the water supply pipe. The upstream and downstream adjacent monitoring points, such as A-B-C-D, the upstream adjacent monitoring point of monitoring point B is monitoring point A, and the downstream adjacent monitoring point is monitoring point C. In fact, there may be multiple adjacent upstream and downstream monitoring points for monitoring point B in the water supply network, but they all represent the adjacent monitoring points before and after monitoring point B.

[0038] And because the pipe network structure, water age, pressure head, etc. are different between each monitoring point, the water quality parameters are naturally inconsistent, such as the residual chlorine value is higher near the water plant and lower near the end point, and the static water quality data value (that is, the data value corresponding to a single moment) is affected by the spatial differences from the water supply pipe network, so the difference between a water quality parameter of a monitoring point at a moment and the same water quality parameter of the monitoring point at the previous moment is taken as the numerical change range of the water quality parameter, and then the difference between the numerical change range of the parameter of the adjacent downstream monitoring point and the target monitoring point and the difference between the numerical change range of the parameter of the adjacent upstream monitoring point and the target monitoring point are calculated, and the absolute values are summed, and the calculation formula of the adjacent downstream monitoring point and the target monitoring point is obtained, and the spatial consistency index of the water quality parameter of the target monitoring point is obtained.

[0039] The numerical change range of each water quality parameter of each monitoring point at each moment is obtained by: obtaining the difference between a water quality parameter of a monitoring point at a moment and the same water quality parameter of the monitoring point at the previous moment, as the numerical change range of the water quality parameter of the monitoring point at the moment.

[0040] Further, the spatial consistency index of the target monitoring point at the same moment is obtained by using the numerical change range of each water quality parameter of the target monitoring point and its adjacent upstream and downstream monitoring points. Specifically, the absolute value of the difference between the numerical change range of a water quality parameter of a target monitoring point and a numerical change range of the same water quality parameter of an adjacent upstream monitoring point of the target monitoring point at a moment is obtained, which is recorded as the numerical change range difference corresponding to the water quality parameter of the adjacent upstream monitoring point at the moment, and the numerical change range differences corresponding to various water quality parameters of all adjacent upstream monitoring points of the target monitoring point at the moment are summed to obtain an upstream cumulative difference; the absolute value of the difference between the numerical change range of a water quality parameter of the target monitoring point and a numerical change range of the same water quality parameter of an adjacent downstream monitoring point of the target monitoring point at the same moment is obtained, which is recorded as the numerical change range difference corresponding to the water quality parameter of the adjacent downstream monitoring point at the moment; the numerical change range differences corresponding to various water quality parameters of all adjacent downstream monitoring points of the target monitoring point at the moment are summed to obtain a downstream cumulative difference; and the spatial consistency index of the target monitoring point at the moment is obtained by subtracting the normalized value of the sum of the upstream cumulative difference and the downstream cumulative difference from the first preset value.

[0041] The specific calculation model of the spatial consistency index is:

[0042] ,

[0043] wherein, A represents the target monitoring point, represents the spatial consistency index of the water quality parameter at the t-th moment, N represents the number of water quality parameters currently participating in monitoring, Norm() represents normalization, limiting the output result to (0, 1), the spatial consistency index represents the consistency degree of the change trend of various water quality parameters of the target monitoring point and the change trend of the upstream and downstream monitoring points, reflecting whether the water quality of the target monitoring point presents spatial propagation characteristics in the water supply network, and the larger the output result is, the stronger the spatial consistency of the change of the water quality parameter is;

[0044] U represents the number of upstream adjacent monitoring points of the target monitoring point, represents the value change range of the j-th water quality parameter of the t-th moment of the target monitoring point, represents the value change range of the j-th water quality parameter of the t-th moment of the target monitoring point, represents the value change range of the j-th water quality parameter of the t-th moment of the target monitoring point, represents the value change range difference of the j-th water quality parameter corresponding to the t-th moment of the target monitoring point, represents the value change range difference of the j-th water quality parameter corresponding to the t-th moment of the target monitoring point, is the upstream cumulative difference;

[0045] D represents the number of downstream adjacent monitoring points of the target monitoring point, represents the value change range of the j-th water quality parameter of the t-th moment of the target monitoring point, represents the value change range of the j-th water quality parameter of the t-th moment of the target monitoring point, represents the value change range difference of the j-th water quality parameter corresponding to the t-th moment of the target monitoring point, represents the value change range difference of the j-th water quality parameter corresponding to the t-th moment of the target monitoring point, is the downstream cumulative difference. The upstream cumulative difference and the downstream cumulative difference are used to represent the consistency of the data change range of the upstream and downstream adjacent monitoring points and the target monitoring point, and the first preset value is 1. Thus, the spatial consistency index of the target monitoring point at the t-th moment can be obtained.

[0046] The flow rate adjustment factor acquisition module is configured to acquire the flow rate adjustment factor of the target monitoring point at a moment according to the spatial consistency index of the target monitoring point at the moment, the water flow rate, and the water age of the target monitoring point, the upstream adjacent monitoring points of the target monitoring point, and the last monitoring point in the water supply network.

[0047] In the water supply network, water quality parameters change with the flow of water in the network, especially due to natural decay processes such as residual chlorine consumption, microbial growth, etc. This decay process is closely related to the residence time of water in the network (i.e. water age increment). The longer the residence time of water in the network, the more the disinfectant (such as residual chlorine) added by the water supply system will naturally decay over time, and the more likely the water quality will be abnormal.

[0048] Therefore, the water age of the target monitoring point and the average water age of all upstream adjacent monitoring points thereof are analyzed, and the difference is calculated to reflect the water age increment of the target monitoring point in the network. At the same time, due to the differences in pipe diameter of the water supply network, and due to the complexity of the actual path and the instability of the flow state (such as local reflux, dead angle, turbulence), the water flow rate of each part may be quite different due to structural reasons, and a long water age increment may indicate that the water is slow, and it may also indicate that the path is long. However, if the current point has a fast flow rate, it means that the water body is in continuous update, and even if there is a certain water age increment, the possibility of water quality abnormality is still weak. Therefore, the ratio of the water flow rate of the target monitoring point to the maximum water flow rate in the network is used to reflect the relative size of the water flow rate of the target monitoring point, and the relative residence time of water in the network is compared. Coupling "water age increment" and "water flow rate" can reflect the credibility of the current monitoring point water quality abnormality.

[0049] According to the spatial consistency index of the target monitoring point at a moment, the water flow rate, and the water age of the target monitoring point, the upstream adjacent monitoring point of the target monitoring point, and the last monitoring point in the water supply network, the flow rate adjustment factor of the target monitoring point at the moment is obtained. Specifically, the difference between the water age of the target monitoring point and the average water age of all upstream adjacent monitoring points of the target monitoring point is obtained, and then the sum of the water age of the last monitoring point in the water supply network and the super parameter is obtained to obtain the water age characteristic value; the sum of the water flow rate of the target monitoring point at a moment and the super parameter is obtained, and then the maximum value in the water flow rate of all monitoring points at the moment is obtained to obtain the water flow rate characteristic value; the spatial consistency index of the target monitoring point at the moment is multiplied by the ratio of the water age characteristic value and the water flow rate characteristic value to obtain the flow rate adjustment factor of the target monitoring point at the moment.

[0050] The calculation model of the flow rate adjustment factor of the target monitoring point is specifically:

[0051] ,

[0052] Wherein, represents the flow rate adjustment factor of the target monitoring point A at moment t based on spatial consistency; represents the water age of the target monitoring point A, represents the average value of the water age of the i-th upstream adjacent monitoring point in all upstream adjacent monitoring points of the target monitoring point, Water age increment of the reaction water body at the target monitoring point, Water age of the last monitoring point in the entire water supply network, Water age characteristic value, alpha is a hyperparameter, which is a very small number to prevent the denominator from being zero, and the reference setting is Water age characteristic value reflects the proportion of the water age increment of the target monitoring point water body in the entire water supply network, and the ratio is positively correlated with the water age increment from the upstream adjacent monitoring point to the target monitoring point.

[0053] Water flow velocity of the target monitoring point A at time t, The maximum value of the water flow velocity of all monitoring points at time t, Water flow velocity characteristic value, which represents the proportion of the water flow velocity of the target monitoring point in the entire network.

[0054] The ratio of the two parts represents the water residence intensity corresponding to the water flow renewal capacity at the target monitoring point water flow velocity. The larger the result is, the easier the water body is to accumulate, the longer the residence time is, and the more likely the water quality is to have real anomalies.

[0055] However, the ratio of the two parts only evaluates the credibility of water quality anomalies from the perspective of hydraulic conditions. Even if the flow rate of a monitoring point is slow and the water age is high, it cannot be ruled out that the anomaly is caused by equipment drift, local disturbance, and other non-real water quality change factors. In order to further improve the recognition ability of real water quality anomalies, the spatial consistency index of the target monitoring point is multiplied to evaluate whether the water quality flow characteristics of the target monitoring point exist a coordinated trend in its upstream and downstream, and the final output result is obtained .

[0056] The real anomaly index acquisition module is configured to acquire the real anomaly index of the target monitoring point at a time according to various water quality parameters at the time, various water quality parameters at a time before the time, and various water quality parameters at a historical time.

[0057] The flow rate adjustment factor of the target monitoring point at time t is acquired, and further, the changes of multiple parameters of the target monitoring point are analyzed to obtain the real anomaly index.

[0058] The real anomaly index of the target monitoring point at the moment is obtained according to various water quality parameters of the target monitoring point at the moment, various water quality parameters at a moment before the moment and various water quality parameters at a historical moment. Specifically, the growth rate of a water quality parameter of the target monitoring point at the moment is obtained by comparing the difference between the water quality parameter at the moment and the water quality parameter at a moment before the moment with the water quality parameter at the moment before the moment and taking an absolute value; the average growth rate corresponding to the moment is obtained by averaging the growth rates of various water quality parameters at the moment; the deviation degree of the water quality parameter at the moment is obtained by taking the absolute value of the difference between the water quality parameter at the moment and the average of the water quality parameter at each moment in history; the average deviation degree corresponding to the moment is obtained by averaging the deviation degrees of various water quality parameters at the moment; and the real anomaly index of the target monitoring point at the moment is obtained by adding the average deviation degree and the average growth rate.

[0059] The calculation model of the real anomaly index is specifically as follows:

[0060] ,

[0061] Among them, represents the real anomaly index obtained by multi-parameter collaborative calculation of the target monitoring point A at the moment t, represents whether the remaining types of water quality parameters change in coordination with the type of water quality parameter when the type of water quality parameter is abnormal at the moment t, and the larger the output result is, the more dimensions of the multiple types of water quality parameters of the target monitoring point at the moment t have significant abnormal behaviors, and the more likely the abnormal behaviors have coordination among the multiple parameters, which is more likely to be an actual water quality problem;

[0062] N represents the number of types of water quality parameters, represents the jth type of water quality parameter of the target monitoring point at the moment t, represents the jth type of water quality parameter of the target monitoring point at the moment t-1, that is, the jth type of water quality parameter at the previous moment, The size of represents the fluctuation amplitude of the jth type of water quality parameter at the moment t and the previous moment, represents the growth rate of the jth type of water quality parameter at the moment t, because there are spatial and site differences in the water quality parameters in the water supply network structure, the simple numerical change cannot be directly compared between monitoring points, and the growth rate is compared with The growth rate is a calculation method of the growth rate, which is used to reflect the change of data; finally, the average growth rate corresponding to the moment is obtained by averaging the growth rates of various water quality parameters at the moment t The larger the value is, the more water quality parameters of the target monitoring point at the moment have obvious changes;

[0063] The average value of the jth water quality parameter of the target monitoring point at each time in history, that is, the average value of the jth water quality parameter at each time before t time; because the water quality parameter anomaly caused by water quality abnormal behavior is usually a gradual change process after the start, the change rate of the adjacent data in this stage may not be dramatic, that is, the output result of the last item can find the data change behavior of the anomaly start, but it may not be effective after the start. Therefore, by taking the mean value of the previous historical data, the jth water quality parameter in the normal state is represented as the regular mode, and then the difference between t time and the regular mode is calculated to reflect the data change after the start of the abnormal behavior. The historical data referred to in the present application is the historical data of the past month, which can be adjusted according to the actual situation. The deviation degree of the jth water quality parameter at t time, The average deviation degree corresponding to t time.

[0064] Thus, the real anomaly index of the target monitoring point at one time is obtained.

[0065] The anomaly score correction module is used to obtain the initial anomaly score of the target monitoring point at one time; the initial anomaly score of the target monitoring point at one time is corrected by using the flow rate adjustment factor and the real anomaly index of the target monitoring point at one time to obtain the corrected anomaly score.

[0066] The main purpose of the present application is to correct the initial anomaly score obtained by the isolation forest, so it is necessary to obtain the initial anomaly score of each monitoring point at each time by using the isolation forest. Specifically, various water quality parameters of a monitoring point at one time are taken as a sample, and then a plurality of isolated trees are constructed, the sample is divided in each tree, the path length of each sample in each tree is calculated, the average path length is obtained, and the initial anomaly score of each monitoring point at each time is calculated according to the average path length and the anomaly score calculation formula; it should be noted that this method is a known technology and will not be described in detail here.

[0067] The flow rate adjustment factor of the target monitoring point at one time is obtained, and the flow rate adjustment factor represents the degree of cooperative trend of the water quality flow characteristics of the target monitoring point at its upstream and downstream. At the same time, because the water quality parameter anomaly caused by the water quality itself usually shows the cooperative change of multiple water quality parameters, and the water quality parameter change caused by the monitoring instrument usually occurs only on a single water quality parameter data, the real anomaly index obtained by the multi-parameter cooperative calculation is combined with the flow rate adjustment factor to obtain the real anomaly factor of the water quality parameter at one time, and then the anomaly attribution function is constructed. The initial anomaly score is adjusted according to the function output result.

[0068] Thus, the initial abnormal score of the target monitoring point at the moment is corrected by using the flow rate adjustment factor and the real anomaly index of the target monitoring point at the moment to obtain a corrected abnormal score. Specifically, the normalized value of the flow rate adjustment factor and the normalized value of the real anomaly index of the target monitoring point at the moment are added and averaged to obtain the real anomaly factor of the target monitoring point at the moment; the real anomaly factor of the target monitoring point at the moment is brought into the abnormal attribution function to obtain an adjustment coefficient; and the initial abnormal score of the target monitoring point at the moment is obtained according to the adjustment coefficient and the initial abnormal score of the target monitoring point at the moment to obtain the corrected abnormal score of the target monitoring point at the moment.

[0069] The abnormal attribution function is specifically as follows:

[0070]

[0071] Among them, represents the output value of the abnormal attribution function, that is, the adjustment coefficient of the target monitoring point A at the moment t; represents the real anomaly factor of the target monitoring point A at the moment t; a represents a set threshold, and the reference value of the present application is 0.65. The implementer can adjust it according to the actual situation and actual demand.

[0072] Finally, the initial abnormal score of the target monitoring point at the moment t is obtained according to the adjustment coefficient and the initial abnormal score of the target monitoring point at the moment t to obtain the corrected abnormal score of the target monitoring point at the moment t. Specifically, the adjustment coefficient is multiplied by the initial abnormal score at the moment t and normalized to obtain the corrected abnormal score at the moment t; and the higher the abnormal score, the greater the possibility of water quality abnormality.

[0073] The real corrected abnormal score is obtained, the various water quality parameters of the target monitoring point in the actual water supply network are monitored through the corrected abnormal score, the recognition ability of the monitoring system for the data abnormal behavior caused by the real water quality abnormality is improved, the system false alarm caused by the abnormality of the monitoring equipment is reduced, unnecessary operation and maintenance caused by false alarm are effectively reduced, the operation cost is increased, the perception and judgment ability of the system for the real water quality pollution event is improved, and the water quality safety management and operation optimization are improved.

[0074] It should be noted that the above-mentioned embodiments of the present application are only for description, and do not represent the advantages and disadvantages of the embodiments. Moreover, 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 may be advantageous.

[0075] Each embodiment in the specification is described in a progressive manner, and the same or similar parts of each embodiment can be referred to each other. Each embodiment focuses on the difference from other embodiments.

[0076] The above description is only the preferred embodiment of the present application, and is not intended to 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.

Claims

1. A water quality intelligent monitoring system for a water supply network, characterized in that, The system comprises: a spatial feature analysis module, configured to collect water age and various water quality parameters at each monitoring point in the water supply network; obtain numerical variation amplitudes of various water quality parameters at each monitoring point at each time point, and obtain a spatial consistency index of a target monitoring point at a time point by using numerical variation amplitudes of various water quality parameters of the target monitoring point and its upstream and downstream adjacent monitoring points at the time point; a flow velocity adjustment factor acquisition module, configured to obtain a flow velocity adjustment factor of the target monitoring point at the time point according to the spatial consistency index of the target monitoring point at the time point, water flow velocity, and water age of the target monitoring point, an upstream adjacent monitoring point of the target monitoring point, and a last monitoring point in the water supply network; a real anomaly index acquisition module, configured to obtain a real anomaly index of the target monitoring point at the time point according to various water quality parameters of the target monitoring point at the time point, various water quality parameters of the target monitoring point at a time point before the time point, and various water quality parameters of the target monitoring point at a historical time point; an anomaly score correction module, configured to obtain an initial anomaly score of the target monitoring point at the time point, including: taking various water quality parameters of a monitoring point at a time point as a sample, constructing multiple isolated trees, dividing the sample in each tree, calculating a path length of each sample in each tree to obtain an average path length, and calculating the initial anomaly score of each monitoring point at each time point according to the average path length and an anomaly score calculation formula; and correcting the initial anomaly score of the target monitoring point at the time point by using the flow velocity adjustment factor and the real anomaly index of the target monitoring point at the time point to obtain a corrected anomaly score. 2.The water quality intelligent monitoring system for water supply network according to claim 1, characterized in that, The numerical variation amplitudes of various water quality parameters at each monitoring point at each time point include: obtaining a difference value of one kind of water quality parameter of a monitoring point at a time point and the kind of water quality parameter of the monitoring point at a time point before the time point as a numerical variation amplitude of the kind of water quality parameter of the monitoring point at the time point. 3.The water quality intelligent monitoring system for water supply network according to claim 1, characterized in that, The spatial consistency index of the target monitoring point at the time point obtained by using the numerical variation amplitudes of various water quality parameters of the target monitoring point and its upstream and downstream adjacent monitoring points at the time point includes: obtaining an absolute value of a difference value of a numerical variation amplitude of one kind of water quality parameter of an upstream adjacent monitoring point of the target monitoring point and the target monitoring point at the same time point, denoted as a numerical variation amplitude difference corresponding to the kind of water quality parameter of the upstream adjacent monitoring point at the time point, summing up numerical variation amplitude differences corresponding to various water quality parameters of all upstream adjacent monitoring points of the target monitoring point at the time point to obtain an upstream cumulative difference; obtaining an absolute value of a difference value of a numerical variation amplitude of one kind of water quality parameter of a downstream adjacent monitoring point of the target monitoring point and the target monitoring point at the same time point, denoted as a numerical variation amplitude difference corresponding to the kind of water quality parameter of the downstream adjacent monitoring point at the time point; summing up numerical variation amplitude differences corresponding to various water quality parameters of all downstream adjacent monitoring points of the target monitoring point at the time point to obtain a downstream cumulative difference; and obtaining a spatial consistency index of the target monitoring point at the time point by using a first preset value minus a normalized value of a sum of the upstream cumulative difference and the downstream cumulative difference. 4.The water quality intelligent monitoring system for water supply network according to claim 1, characterized in that, The flow velocity adjustment factor of the target monitoring point at the moment is obtained according to the spatial consistency index, the water flow velocity of the target monitoring point at the moment, the water age of the target monitoring point, the water age of the adjacent monitoring point upstream of the target monitoring point and the water age of the last monitoring point in the water supply network, and comprises the following steps: The difference between the water age of the target monitoring point and the average value of the water ages of all the adjacent monitoring points upstream of the target monitoring point is obtained, and then the sum of the water age of the last monitoring point in the water supply network and the super parameter is obtained to obtain the water age characteristic value; the sum of the water flow velocity of the target monitoring point at the moment and the super parameter is obtained, and then the maximum value of the water flow velocities of all the monitoring points at the moment is obtained to obtain the water flow velocity characteristic value; the flow velocity adjustment factor of the target monitoring point at the moment is obtained by multiplying the spatial consistency index of the target monitoring point at the moment by the ratio of the water age characteristic value and the water flow velocity characteristic value.

5. The water quality intelligent monitoring system for water supply network according to claim 1, characterized in that, The real anomaly index of the target monitoring point at the moment is obtained according to various water quality parameters at the moment, the various water quality parameters at the moment before the moment and the various water quality parameters at the historical moment, and comprises the following steps: The growth rate of a kind of water quality parameter of the target monitoring point at the moment is obtained by comparing the difference between the water quality parameter at the moment and the water quality parameter at the moment before the moment with the water quality parameter at the moment before the moment and taking the absolute value; the average growth rate corresponding to the moment is obtained by averaging the growth rates of various water quality parameters at the moment; the deviation degree of a kind of water quality parameter of the target monitoring point at the moment is obtained by taking the absolute value of the difference between the water quality parameter at the moment and the average value of the water quality parameter at each moment in history; the average deviation degree corresponding to the moment is obtained by averaging the deviation degrees of various water quality parameters at the moment; and the real anomaly index of the target monitoring point at the moment is obtained by adding the average deviation degree and the average growth rate. 6.The water quality intelligent monitoring system for water supply network according to claim 1, characterized in that, The initial anomaly score of the target monitoring point at the moment is corrected to obtain the corrected anomaly score by using the flow velocity adjustment factor and the real anomaly index of the target monitoring point at the moment, and comprises the following steps: The real anomaly factor of the target monitoring point at the moment is obtained by adding the normalized value of the flow velocity adjustment factor and the normalized value of the real anomaly index at the moment and averaging; the adjustment coefficient is obtained by inputting the real anomaly factor of the target monitoring point at the moment into the anomaly attribution function; and the corrected anomaly score of the target monitoring point at the moment is obtained according to the adjustment coefficient and the initial anomaly score of the target monitoring point at the moment.

7. The water quality intelligent monitoring system for water supply network according to claim 6, characterized in that, The anomaly attribution function is specifically: ， wherein, represents an adjustment coefficient; represents a target monitoring point A, a real abnormal factor at time t; a represents a set threshold. 8.The water quality intelligent monitoring system for water supply network of claim 6, characterized in that, The corrected anomaly score of the target monitoring point at the moment is obtained according to the adjustment coefficient and the initial anomaly score of the target monitoring point at the moment, and comprises the following steps: The corrected anomaly score at the moment is obtained by multiplying the adjustment coefficient and the initial anomaly score at the moment and normalizing.

Images