Sensor-based rural water supply water volume and pressure fluctuation monitoring method for mountain and hilly areas

Abstract

The present application relates to the field of water quantity and water pressure monitoring, and particularly relates to a sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas, which comprises: in a preset area, collecting first time sequence monitoring data of multiple water supply pipelines at different time points according to time sequence; performing data processing on the first time sequence monitoring data of the multiple water supply pipelines to obtain second time sequence monitoring data corresponding to each water supply pipeline; performing water pressure state recognition on the second time sequence monitoring data corresponding to each water supply pipeline to determine the water pressure state of each water supply pipeline at each time point; performing abnormal fluctuation recognition on the water pressure state of each water supply pipeline at each time point to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation; and performing analysis on the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation. The present application realizes real-time dynamic monitoring and intelligent abnormal management.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of water quantity and water pressure monitoring, and particularly relates to a sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas. BACKGROUND

[0002] The traditional water supply network inspection method is faced with great challenges such as long distance, low efficiency, high operation and maintenance labor cost, etc. due to the wide distribution and long distance of scattered users. Therefore, it has become an inevitable trend to improve the automation and management and maintenance level of water supply facilities in mountain and hilly areas by deploying sensors at the end of the water supply network to monitor water quantity and water pressure in real time and building an intelligent management system.

[0003] Although the intelligent monitoring technology has broad prospects, it still faces severe challenges in practical application in complex mountain and hilly terrain. In order to adapt to the undulating terrain, water supply pipelines have to use a large number of elbows, valves, reducers and other components, and are frequently laid on slopes. This complex pipeline layout brings two major problems: first, water quantity continuously loses energy due to local friction and turning, forming a normalized pipeline resistance; second, under the working conditions such as rapid opening and closing of valves, transient and severe water hammer phenomenon is easily generated. These two phenomena together cause the end monitoring data to be full of noise and frequent abnormal fluctuations, which seriously interferes with the effectiveness of monitoring, makes the baseline judgment of the steady-state operation pressure of the water supply system inaccurate, and causes it to be unable to effectively distinguish the real fault state (such as pipeline leakage, equipment damage, etc.) that needs to be handled urgently from the frequent pseudo-abnormalities, thereby greatly reducing the accuracy and practicality of abnormal monitoring. SUMMARY

[0004] In order to solve the technical problem that water hammer and local resistance frequently occur in the water supply system in mountain and hilly rural areas due to complex terrain, making it difficult for the abnormal detection algorithm to accurately distinguish between normal and abnormal states and affecting the effective identification and management of water supply system abnormalities, the purpose of the present application is to provide a sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas, and the technical solution adopted is as follows:

[0005] In a first aspect, the embodiments of the present application provide a sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas, which comprises:

[0006] In a preset area, a plurality of first time sequence monitoring data of water supply pipelines at different time points are collected according to time sequence order;

[0007] The first time sequence monitoring data of the plurality of water supply pipelines are subjected to data processing to obtain second time sequence monitoring data corresponding to each water supply pipeline;

[0008] water pressure state of each water supply pipeline at each time point is identified, to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation;

[0009] water pressure state of each water supply pipeline at each time point is identified, to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation;

[0010] water pressure state of each water supply pipeline at each time point is identified, to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation;

[0011] In a possible implementation manner of the first aspect, the data processing on the first time sequence monitoring data of the plurality of water supply pipelines to obtain the second time sequence monitoring data corresponding to each water supply pipeline comprises: performing noise reduction processing on the first time sequence monitoring data of the plurality of water supply pipelines according to a median filtering algorithm, to obtain the second time sequence monitoring data corresponding to each water supply pipeline after noise reduction.

[0012] In a possible implementation manner of the first aspect, the water pressure state of each water supply pipeline at each time point is identified, to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation, which comprises: calculating, according to the second time sequence monitoring data corresponding to the water pressure of each water supply pipeline, an instantaneous fluctuation feature at each time; obtaining a difference index at each time according to the instantaneous fluctuation feature at each time; determining a first time as a time corresponding to a difference index greater than 0, the first time being in a first water pressure state; determining a second time as a time corresponding to a difference index less than 0, the second time being in a second water pressure state; determining a third time as a time corresponding to a difference index equal to 0, the third time being in a water pressure state of a previous time; traversing all time points, and counting the first water pressure state and the second water pressure state, to obtain the water pressure state of each water supply pipeline at each time point.

[0013] With reference to the first aspect, in a possible implementation manner, the difference index of each time point is obtained according to the instantaneous fluctuation feature of each time point, including: performing sliding window division on the second time sequence monitoring data corresponding to each water supply pipeline to obtain sliding window data segments corresponding to each water supply pipeline, each sliding window data segment including a timestamp, a corresponding water supply pipeline number and second time sequence monitoring data of each water supply pipeline corresponding to the timestamp; obtaining a target sliding window data segment, the target sliding window data segment being a sliding window data segment of a previous time point corresponding to each time point; performing water pressure fluctuation calculation on the target sliding window data segment to obtain a water pressure fluctuation mean value of the target sliding window data segment; and obtaining the difference index of each time point according to the instantaneous fluctuation feature of each time point and the water pressure fluctuation mean value of the target sliding window data segment.

[0014] With reference to the first aspect, in a possible implementation manner, the water pressure state includes a first water pressure state and a second water pressure state, and the abnormal fluctuation identification of the water pressure state of each water supply pipeline at each time point is performed to obtain a water pressure fluctuation abnormality index corresponding to a water supply pipeline with fluctuation, including: obtaining a plurality of target time points in the first water pressure state; obtaining at least one first water pressure state period according to the plurality of target time points; performing revision calculation on water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain revised first target water pressure data corresponding to each water supply pipeline; in each first water pressure state period, performing abnormal analysis on the first target water pressure data corresponding to each water supply pipeline to obtain a first abnormal state duration period of a water supply pipeline with abnormal fluctuation; obtaining target data corresponding to the first abnormal state duration period, the target data including first target water pressure data and first water quantity data of the water supply pipeline with abnormal fluctuation, the first water quantity data being located in the second time sequence monitoring data corresponding to the water supply pipeline with abnormal fluctuation; performing correlation calculation on the target data corresponding to the first abnormal state duration period to obtain water quantity-water pressure correlation corresponding to the first abnormal state duration period; and performing abnormal fluctuation calculation according to the water quantity-water pressure correlation corresponding to the first abnormal state duration period to obtain the water pressure fluctuation abnormality index corresponding to the water supply pipeline with fluctuation.

[0015] With reference to the first aspect, in a possible implementation manner, the analyzing the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation comprises: obtaining a second abnormal state duration corresponding to each water pressure fluctuation anomaly index; obtaining a plurality of feature values corresponding to the second abnormal state duration; calculating the second abnormal state duration corresponding to each water pressure fluctuation anomaly index and the plurality of feature values corresponding to the second abnormal state duration to obtain a feature vector corresponding to each water pressure fluctuation anomaly index; performing density analysis on all the feature vectors corresponding to each water pressure fluctuation anomaly index according to a preset algorithm to obtain a local outlier factor corresponding to each feature vector; obtaining a target intermediate value according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation; and obtaining a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector.

[0016] With reference to the first aspect, in a possible implementation manner, the obtaining the plurality of feature values corresponding to the second abnormal state duration comprises: performing revised calculation on water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain second target water pressure data corresponding to each water supply pipeline after revision; obtaining second target water pressure data and second water quantity data corresponding to the second abnormal state duration; performing calculation on the second target water pressure data corresponding to the second abnormal state duration to obtain a first feature value and a second feature value; performing calculation on the second water quantity data to obtain a third feature value and a fourth feature value, and the plurality of feature values comprise the first feature value, the second feature value, the third feature value and the fourth feature value.

[0017] With reference to the first aspect, in a possible implementation manner, the obtaining a target intermediate value according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation comprises: obtaining all water pressure fluctuation anomaly indexes; and performing mean value calculation on the all water pressure fluctuation anomaly indexes to obtain the target intermediate value.

[0018] With reference to the first aspect, in a possible implementation manner, the obtaining a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector comprises: when the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation is greater than the target intermediate value, and the local outlier factor corresponding to each feature vector is greater than 1, determining that a current target abnormal type is a first abnormal type.

[0019] With reference to the first aspect, in a possible implementation manner, the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained according to the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector, and the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is determined as the second abnormal type when the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation is less than or equal to the target intermediate value, and the local outlier factor corresponding to each feature vector is less than or equal to 1.

[0020] In the second aspect, an embodiment of the present application provides a sensor-based water quantity and water pressure fluctuation monitoring device for rural water supply in mountain and hilly areas, which comprises:

[0021] The acquisition unit is configured to acquire, in a preset area, first time sequence monitoring data of a plurality of water supply pipelines at different time points according to a time sequence order.

[0022] The processing unit is configured to perform data processing on the first time sequence monitoring data of the plurality of water supply pipelines to obtain second time sequence monitoring data corresponding to each water supply pipeline.

[0023] The identification unit is configured to perform water pressure state identification on the second time sequence monitoring data corresponding to each water supply pipeline to determine water pressure states of the water supply pipelines at time points.

[0024] The identification unit is further configured to perform abnormal fluctuation identification on the water pressure states of the water supply pipelines at each time point to obtain a water pressure fluctuation abnormal index corresponding to a water supply pipeline with abnormal fluctuation.

[0025] The analysis unit is configured to analyze the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation.

[0026] In the third aspect, an electronic device is provided, which comprises a memory and a processor, the memory is connected to the processor, the processor is configured to execute one or more computer programs stored in the memory, and the processor, when executing the one or more computer programs, causes the electronic device to implement the sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas as described in the first aspect.

[0027] In the fourth aspect, a computer readable storage medium is provided, which stores a computer program, the computer program comprises program instructions, and the program instructions, when executed by a processor, cause the processor to execute the sensor-based water quantity and water pressure fluctuation monitoring method for rural water supply in mountain and hilly areas as described in the first aspect.

[0028] The present application has the following beneficial effects: the present application collects monitoring data of multiple water supply pipelines in time sequence, realizes real-time dynamic perception of the water supply system state, and timely grasps the water pressure change; the original monitoring data is processed to generate second time sequence data which is more representative and has analysis value, and the accuracy and reliability of subsequent analysis are improved; the water pressure state of each water supply pipeline at each time point is identified, which can accurately reflect the pipeline operation condition and timely discover abnormal water pressure fluctuation; through abnormal fluctuation identification, the pipeline with abnormal water pressure is quickly located, which provides basis for preventing and handling water supply abnormalities; the water pressure index of abnormal fluctuation is analyzed in depth, and the abnormal type is accurately classified, which is helpful for targetedly formulating maintenance and emergency measures, improving the stability and safety of the water supply system, realizing intelligent monitoring and abnormal management of the water supply network, and improving the reliability and operation efficiency of the water supply system. BRIEF DESCRIPTION OF DRAWINGS

[0029] In order to more clearly illustrate the technical solutions and advantages of the embodiments of the present application or the prior art, the following will briefly introduce the drawings needed to be used in the embodiments or the prior art description. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without any creative effort.

[0030] Figure 1 A flowchart of a sensor-based rural water supply water volume and water pressure fluctuation monitoring method in mountainous and hilly areas provided by an embodiment of the present application;

[0031] Figure 2 A structural schematic diagram of a sensor-based rural water supply water volume and water pressure fluctuation monitoring device in mountainous and hilly areas provided by an embodiment of the present application.

[0032] Figure 3 A structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0033] In order to further illustrate the technical means and effects adopted by the present application to achieve the predetermined invention purpose, the following describes the sensor-based rural water supply water volume and water pressure fluctuation monitoring method according to the present application, its specific implementation, structure, features and effects in detail 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.

[0034] 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.

[0035] The application provides a sensor-based rural water supply water volume and water pressure fluctuation monitoring method for a mountain and hilly area.

[0036] Please refer to Figure 1 The sensor-based rural water supply water volume and water pressure fluctuation monitoring method for a mountain and hilly area provided by the embodiment of the application is shown in the flowchart, and the method comprises the following steps:

[0037] S10, in a preset area, a plurality of first time sequence monitoring data of water supply pipelines at different time points are collected according to a time sequence order.

[0038] The preset area refers to a specific geographical range that needs to be monitored, for example, a village in a mountain and hilly area, a residential area or an industrial park. The area usually contains a complex water supply network composed of main pipelines, branch pipelines and household pipelines.

[0039] The water supply pipeline refers to a key pipe section in the network where a monitoring sensor is deployed. The water supply pipeline is usually the nerve ending of the water supply network, for example, the end of the household pipeline connected to each household or multiple households.

[0040] The first time sequence monitoring data is the original data directly obtained from the sensor without processing. It is a data stream containing a time stamp and a measurement value. The first time sequence monitoring data can include water volume, water pressure and water speed. The water volume usually exists in the form of a pulse signal; the water pressure usually exists in the form of a voltage or current signal (such as 4-20 mA). The first time sequence monitoring data also contains a real signal and various random noises.

[0041] Further, regarding the deployment of the sensor, a mechanical water meter with pulse output can be installed at the end of the user's water supply pipeline. For example, an electric pulse is generated every time the impeller in the water meter rotates one circle. The system can accurately calculate the water volume by recording the number of pulses. For example, if the water meter parameter is 1 pulse = 1 liter, and 10 pulses are recorded in 1 minute, it means that the water consumption in 1 minute is 10 liters. This method directly and reliably reflects the actual water consumption behavior of the user. Water pressure monitoring: a pressure sensor is installed at the same position (or a very close position). For example, the pressure sensor is screwed on a reserved interface of the pipeline, and the sensitive element directly senses the pressure of the water in the pipeline. When the water pressure changes, the sensor outputs a proportional electric signal. For example, 4 mA (corresponding to 0 MPa) is output when the static pressure is output, and 20 mA is output when the pressure rises to 1 MPa. When selecting the sensor, it must be ensured that the range can cover the highest static pressure (pressure when the system is not working) and the highest dynamic pressure (pressure when the system is working, which may be a momentary overpressure due to water hammer) of the position.

[0042] Specifically, the collection process is to read the water meter pulse and the pressure sensor signal at a fixed frequency (for example, once per second) at the same time according to the data collector (such as DTU, RTU or single-chip system), and to mark each set of data with an accurate time stamp. Note that this scheme is synchronous collection, and if the water pressure and water quantity data are not obtained at the same time, it will lose the meaning of analyzing the correlation between them subsequently.

[0043] It can be seen that in the embodiment, the water quantity and water pressure data of each monitoring point are continuously collected in time sequence (time sequence), forming a first time sequence monitoring data set. The data is dynamic and can reflect the running state of the water supply pipeline at different time points.

[0044] S20, data processing is performed on the first time sequence monitoring data of the plurality of water supply pipelines to obtain second time sequence monitoring data corresponding to each water supply pipeline.

[0045] The second time sequence monitoring data refers to data processed by a preset algorithm (such as noise reduction, smoothing and feature extraction), and reflects the water pressure and water quantity characteristics of the water supply pipeline at different time points. The second time sequence monitoring data has higher accuracy and stability, and is suitable for state recognition and anomaly detection.

[0046] It should be noted that, in order to facilitate calculation, all index data involved in the operation in the embodiment are preprocessed, and the dimension effect is cancelled. The means for removing the dimension effect are well known to those skilled in the art, and are not limited herein.

[0047] In an embodiment, the data processing on the first time sequence monitoring data of the plurality of water supply pipelines to obtain the second time sequence monitoring data corresponding to each water supply pipeline comprises: performing noise reduction processing on the first time sequence monitoring data of the plurality of water supply pipelines according to a median filter algorithm to obtain the second time sequence monitoring data corresponding to each water supply pipeline after noise reduction.

[0048] Specifically, median filtering is to replace the value of a data point with the median of all values in the neighborhood of the data point. It is particularly effective for eliminating impulse noise (i.e. a sharp peak signal that suddenly appears and quickly disappears).

[0049] In a specific implementation, a filter window (for example, a filter window with a width of 5) can be set. Assuming that the data at time point T is to be processed, the data points at T and the data points before and after T are taken to form a window containing 5 values. For example, the window is [D{T-2}, D{T-1}, DT, D{T+1}, D{T+2}]. The 5 values are sorted in ascending order, and the middle one is taken. The calculated median is used to replace the original DT value to obtain the data after noise reduction.

[0050] For example, the original water pressure data is [..., 0.42, 0.45, 0.38, 0.43, 0.44,...], at time T, the reading suddenly drops from 0.45 to 0.38, which is likely to be a noise spike caused by electromagnetic interference or instantaneous vibration, rather than a real water pressure collapse. The median filter is applied: the window data is [0.42, 0.45, 0.38, 0.43, 0.44], and after sorting, it becomes [0.38, 0.42, 0.43, 0.44, 0.45], and the median is 0.43. The clean data is generated: the original 0.38 is replaced by 0.43. The new data sequence becomes [..., 0.42, 0.45, 0.43, 0.43, 0.44,...]. Thus, the interference is effectively filtered, the data curve becomes smooth, and the sustained trend caused by real events (such as slow closing of the valve) is preserved.

[0051] As can be seen, in this embodiment, the median filter algorithm is used to perform noise reduction processing on the original data, which eliminates noise and ensures data quality and accuracy.

[0052] S30, water pressure state recognition is performed on the second time sequence monitoring data corresponding to each water supply pipeline, and the water pressure state of each water supply pipeline at each time point is determined.

[0053] The water pressure state includes a first water pressure state and a second water pressure state, and the first water pressure state can be a dynamic pressure state, and the second water pressure state can be a static pressure state.

[0054] The water pressure recognition process of S30 can refer to the specific description between S301-S302, which is not repeated here.

[0055] S301, in an embodiment, the water pressure state recognition is performed on the second time sequence monitoring data corresponding to each water supply pipeline, and the water pressure state of each water supply pipeline at each time point is determined, including: calculating the second time sequence monitoring data of the water pressure corresponding to each water supply pipeline to obtain the instantaneous fluctuation characteristics at each time; obtaining the difference index at each time according to the instantaneous fluctuation characteristics at each time; determining the time corresponding to the difference index greater than 0 as the first time, and the first time is in the first water pressure state; determining the time corresponding to the difference index less than 0 as the second time, and the second time is in the second water pressure state; determining the time corresponding to the difference index equal to 0 as the third time, and the third time is in the water pressure state of the previous time; traversing all time points, and counting the first water pressure state and the second water pressure state to obtain the water pressure state of each water supply pipeline at each time point.

[0056] The instantaneous fluctuation feature refers to a quantitative index of water pressure change of the water supply pipeline between two adjacent time points, and is used to reflect the severity and abnormal situation of water pressure change.

[0057] In the specific implementation process of calculating the instantaneous fluctuation feature of each time point according to the second time sequence monitoring data of the water pressure corresponding to each water supply pipeline, the following formula can be used:

[0058]

[0059] In the formula, is the instantaneous fluctuation feature of each time point, is the monitoring value of the pressure sensor at the ith time point, is the monitoring value of the pressure sensor at the (i+1)th time point, is the fluctuation change relationship of adjacent time points, the greater the value, the more obvious the water pressure change of the water supply pipeline at this time, is the average value of the monitoring water pressure at the ith time point and the (i+1)th time point, is the product of the fluctuation change relationship of adjacent time points and the inverse proportional coefficient of the average water pressure, which represents the overall performance characteristic value of the detection data in the adjacent time points, and can represent the water pressure change node characteristics existing in the water supply pipeline in the monitoring data. The norm function is used for normalization, represents a tuning factor, which is a safety value set to prevent the denominator from being 0. The value can be 1. It should be noted that the calculation error caused by supplementing the tuning factor at the denominator position is within an acceptable range.

[0060] The difference index refers to an index for judging whether the current water pressure fluctuation state is dynamic pressure fluctuation or static pressure fluctuation. The difference index is used to distinguish static pressure and dynamic pressure existing in the regional water supply process.

[0061] In this scheme, the difference index can be represented by Y. Therefore, the time point corresponding to the difference index greater than 0 is determined as the first time point, and the first time point is in the first water pressure state. The time point corresponding to the difference index less than 0 is determined as the second time point, and the second time point is in the second water pressure state. The time point corresponding to the difference index equal to 0 is determined as the third time point, and the third time point is in the water pressure state of the previous time point. All time points are traversed to count the first water pressure state and the second water pressure state, and the water pressure state of each water supply pipeline at each time point can be understood as follows: when the current fluctuation is in a dynamic pressure fluctuation state, when the current time monitoring abnormal state change belongs to static pressure fluctuation, and when the fluctuation state is divided into the fluctuation state of the water pressure value of the previous monitoring time point.

[0062] It can be seen that, in the embodiment, the water pressure fluctuation state of the water supply pipeline can be accurately judged through the instantaneous fluctuation feature and the difference index, so that the state monitoring and early warning of the water supply system are realized.

[0063] S302, in an embodiment, the difference index of each time is obtained according to the instantaneous fluctuation feature of each time, including: the second time sequence monitoring data corresponding to each water supply pipeline is divided by a sliding window to obtain the sliding window data segment corresponding to each water supply pipeline, each sliding window data segment includes a timestamp, a corresponding water supply pipeline number and the second time sequence monitoring data of each water supply pipeline corresponding to the timestamp; a target sliding window data segment is obtained, the target sliding window data segment is the sliding window data segment of the previous moment corresponding to each moment; the water pressure fluctuation of the target sliding window data segment is calculated to obtain the water pressure fluctuation mean value of the target sliding window data segment; the difference index of each time is obtained according to the instantaneous fluctuation feature of each time and the water pressure fluctuation mean value of the target sliding window data segment.

[0064] Among them, the sliding window is to divide the continuous time sequence data into fixed length time period (window), the window slides forward with time, which is used for local statistical analysis. The window length is usually expressed in time (such as 5 minutes) or data points.

[0065] Among them, the sliding window data segment refers to the data set contained in each sliding window, including timestamp, corresponding water supply pipeline number and second time sequence monitoring data in the time period.

[0066] Among them, the target sliding window data segment is the sliding window data segment corresponding to the previous moment (i-1) for the current moment i, which is used for comparison and analysis with the current moment data.

[0067] Among them, the water pressure fluctuation mean value refers to the average value of the instantaneous water pressure fluctuation characteristic value of all moments in the sliding window, which is used to reflect the overall water pressure fluctuation level in the time period.

[0068] Among them, the process of sliding window division is as follows: the second time sequence monitoring data of each water supply pipeline is divided according to the preset window length (such as 5 minutes) to form a plurality of sliding window data segments. Each sliding window data segment contains: timestamp range (window start and end time), water supply pipeline number, corresponding second time sequence monitoring data (filtered water pressure, water quantity, etc.) in the window. The window slides continuously with time, which ensures continuous coverage of the whole data sequence.

[0069] ​wherein the water pressure fluctuation calculation is performed on the target sliding window data segment to obtain the water pressure fluctuation mean value of the target sliding window data segment, and the difference value index of each time point is obtained according to the instantaneous fluctuation feature of each time point and the water pressure fluctuation mean value of the target sliding window data segment, which can be calculated according to the following formula:

[0070] wherein w is the number of time points of the sliding window data segment, k is the time length in the window, is the water pressure fluctuation mean value of the target sliding window data segment, is the monitoring change amount at the current time point i, which is compared with the historical mean value change amount difference value to analyze the feature state existing in the detection result.

[0071] Therefore, when the Y value is large and positive, it indicates that the instantaneous fluctuation feature of the current time point is significantly higher than the average fluctuation level in the historical sliding window, which represents that the valve opening and closing, flow rate mutation and other dynamic pressure fluctuation phenomena may occur in the pipeline; when the Y value is close to zero or negative, it indicates that the current water pressure fluctuation is similar to or lower than the historical average level, which represents that the system is in a relatively stable static pressure state.

[0072] It can be seen that in the embodiment, the sliding window is divided according to the second time sequence monitoring data, the difference value index is calculated by combining the instantaneous fluctuation feature and the water pressure fluctuation mean value in the sliding window, which can dynamically reflect the real-time change state of the water pressure of the water supply pipeline. The method effectively uses the historical data as a benchmark, highlights the abnormal fluctuation at the current time point, and helps to realize the accurate identification and analysis of the dynamic pressure fluctuation.

[0073] S40, the water pressure state of each water supply pipeline at each time point is subjected to abnormal fluctuation identification to obtain the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation.

[0074] wherein the specific implementation process of the abnormal fluctuation identification in S40 can refer to the detailed description of S401, which is not repeated here.

[0075] S401、In an embodiment, the water pressure state includes a first water pressure state and a second water pressure state, and the identification of abnormal fluctuations in the water pressure state of each water supply pipeline at each time point obtains a water pressure fluctuation anomaly index corresponding to a water supply pipeline with fluctuations, including: obtaining a plurality of target time points in the first water pressure state; obtaining at least one first water pressure state period according to the plurality of target time points; performing revision calculation on the water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain revised first target water pressure data corresponding to each water supply pipeline; in each first water pressure state period, performing abnormal analysis on the first target water pressure data corresponding to each water supply pipeline to obtain a first abnormal state duration period of a water supply pipeline with abnormal fluctuations; obtaining target data corresponding to the first abnormal state duration period, the target data including first target water pressure data and first water quantity data corresponding to the water supply pipeline with abnormal fluctuations, the first water quantity data being located in the second time sequence monitoring data corresponding to the water supply pipeline with abnormal fluctuations; performing correlation calculation on the target data corresponding to the first abnormal state duration period to obtain a water quantity-water pressure correlation corresponding to the first abnormal state duration period; performing abnormal fluctuation calculation according to the water quantity-water pressure correlation corresponding to the first abnormal state duration period to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with fluctuations.

[0076] Wherein, the first water pressure state is a dynamic pressure state. Therefore, the target time point is the time point at which all difference indicators Y exceed the threshold value, and the target time point indicates that the pipeline water pressure is in a dynamic pressure state.

[0077] Wherein, the first water pressure state period refers to a time interval composed of a plurality of target time points continuously or approximately continuously, representing the time interval during which the pipeline is in a dynamic pressure state.

[0078] Wherein, the abnormal state duration is the length of time during which continuous abnormal fluctuations are further identified in the dynamic pressure stage, which is used for anomaly detection.

[0079] Specifically, revision calculation refers to the need to unify the water pressure data benchmark due to the complex terrain of mountainous areas and large differences in monitoring point elevations. Through Bernoulli equation and friction pressure loss correction, the water pressure data of different monitoring points is corrected to a unified benchmark height, eliminating the influence of terrain on water pressure.

[0080] Specifically, in the process of obtaining a plurality of target time points in the first water pressure state (dynamic pressure state), the continuous target time points are combined to form one or more continuous time periods. For example, from 10:05:15 to 10:05:20, the Y value is always high, which forms a first water pressure state period (i.e., a dynamic pressure event).

[0081] Further, adjacent target time points in time and spaced no more than a set threshold (such as 1 minute) are merged into a continuous dynamic pressure period. The target time points are sorted in time. The interval between adjacent time points is determined, and if the interval is less than the threshold, the adjacent time points are merged to form one or more continuous dynamic pressure stages.

[0082] In the process of revising the water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain the revised first target water pressure data corresponding to each water supply pipeline, the following formula can be used:

[0083] ,

[0084] wherein is the revised first target water pressure data corresponding to each water supply pipeline, is the water density, is the acceleration of gravity, is the monitoring point height, is the reference height, is the friction pressure loss (calculated by the Darcy-Weisbach formula), is the water flow rate at the reference height, is the water flow rate at the monitoring point.

[0085] In the process of performing anomaly analysis on the first target water pressure data corresponding to each water supply pipeline in each first water pressure state period to obtain the first abnormal state duration of the water supply pipeline with abnormal fluctuations, in each dynamic pressure period, the revised water pressure data is applied to the DWA (dynamic window analysis) algorithm. The DWA algorithm identifies the core segment with the most severe water pressure fluctuations, which is the first abnormal state duration . is a dynamic window, and the length of the dynamic window is the duration of the abnormal event.

[0086] Specifically, in the implementation process of performing correlation calculation on the target data corresponding to the first abnormal state duration to obtain the water quantity and water pressure correlation corresponding to the first abnormal state duration, the Pearson correlation coefficient can be directly used for calculation, so as to obtain the correlation with a value range of [-1, 1], which is S.

[0087] Specifically, in the implementation process of performing abnormal fluctuation calculation on the water quantity and water pressure correlation corresponding to the first abnormal state duration to obtain the water pressure fluctuation anomaly index corresponding to the water supply pipeline with fluctuations, the following formula can be referred to, and the water pressure fluctuation anomaly index :

[0088]

[0089] wherein, is the first abnormal state duration, S represents the water quantity and water pressure correlation, is the difference between adjacent time points during the abnormal change of water pressure, the lower the value, the more stable the change of water pressure, and the lower the abnormality, is the abnormal state existing in the water supply pipeline during the abnormal state duration monitored by the monitoring data, the greater the value, the higher the abnormality reflected by the monitoring data processed by the characteristic data reflected by the monitoring data in the region.

[0090] Therefore, by introducing the elevation correction, the dynamic window mechanism and the water pressure fluctuation abnormality index Y, the water pressure of each monitoring point is uniformly corrected to the reference height according to the Bernoulli equation, which eliminates the interference of the inherent difference in elevation on the similarity analysis; further, the dynamic window is used to accurately capture the short and severe water hammer characteristics, and the Y index is used to quantify the abnormal duration and fluctuation intensity, so as to clearly separate the transient water hammer and the sustained terrain resistance at the feature level.

[0091] It can be seen that in the embodiment, the target time point is determined based on the difference index, the dynamic pressure stage is divided, and the revised water pressure data and the abnormal duration are combined to calculate the water quantity and water pressure correlation and the abnormality index, thereby realizing the accurate identification of the abnormality of the dynamic pressure state in the water supply pipeline in the complex terrain of the mountainous area. The method effectively distinguishes water hammer phenomenon from other abnormalities, and improves the safety guarantee capability of water supply.

[0092] S50, analyzing the water pressure fluctuation abnormality index corresponding to the water supply pipeline with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation.

[0093] The specific implementation process in S50 can refer to the detailed description of S501-S505, which will not be repeated here.

[0094] S501、In an embodiment, the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation is analyzed to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation, comprising: acquiring a second abnormal state duration corresponding to each water pressure fluctuation anomaly index; acquiring a plurality of feature values corresponding to the second abnormal state duration; calculating the second abnormal state duration corresponding to each water pressure fluctuation anomaly index and the plurality of feature values corresponding to the second abnormal state duration to obtain a feature vector corresponding to each water pressure fluctuation anomaly index; according to a preset algorithm, performing density analysis on all feature vectors corresponding to each water pressure fluctuation anomaly index to obtain a local outlier factor corresponding to each feature vector; obtaining a target intermediate value according to the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation; obtaining a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation according to the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector.

[0095] Wherein, the specific description of acquiring the plurality of feature values corresponding to the second abnormal state duration can refer to S502, which is not repeated here.

[0096] S502、In an embodiment, the plurality of feature values corresponding to the second abnormal state duration are acquired, comprising: performing revision calculation on the water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain revised second target water pressure data corresponding to each water supply pipeline; acquiring second target water pressure data and second water quantity data corresponding to the second abnormal state duration; calculating the second target water pressure data corresponding to the second abnormal state duration to obtain a first feature value and a second feature value; calculating the second water quantity data to obtain a third feature value and a fourth feature value, the plurality of feature values comprising the first feature value, the second feature value, the third feature value and the fourth feature value.

[0097] Wherein, the revision calculation is consistent with the revision calculation in S401, which is not repeated here.

[0098] Wherein, the second target water pressure data corresponding to the second abnormal state duration is calculated to obtain a first feature value and a second feature value, the first feature value can be the average change rate of the revised water pressure in the window, reflecting the trend and stability of the water pressure change, and the present scheme can be represented by The second feature value can be the standard deviation of the revised water pressure in the window, indicating the water pressure fluctuation intensity, and the present scheme can be represented by .

[0099] wherein, the second water quantity data is calculated to obtain a third characteristic value and a fourth characteristic value, the third characteristic value can be an average change rate of water quantity in a window, reflecting a water quantity change trend, and the fourth characteristic value can be a standard deviation of water quantity in the window, reflecting water quantity fluctuation intensity. . .

[0100] Specifically, in the process of calculating the second abnormal state duration corresponding to each water pressure fluctuation abnormality index and the plurality of characteristic values corresponding to the second abnormal state duration to obtain the characteristic vector corresponding to each water pressure fluctuation abnormality index, the following formula can be used, the characteristic vector .

[0101]

[0102] In the formula, , is an average change rate of the corrected water pressure and water quantity in a window, indicating trend change stability, , is a standard deviation of the water pressure and water quantity in a window, indicating fluctuation intensity, and B is an abnormal water pressure abnormality index in a window, reflecting change correlation and fluctuation degree between the water pressure and water quantity. The multi-dimensional characteristic of the monitoring point monitoring data is used to supply the characteristics of the water supply area.

[0103] In the process, the preset algorithm can be a local outlier factor (LOF) algorithm.

[0104] In the process of performing density analysis on the characteristic vector corresponding to each water pressure fluctuation abnormality index according to the preset algorithm, the local outlier factor of each characteristic vector is obtained.

[0105] ,

[0106] In the formula, n is a neighborhood size (total number of nodes in the region), is a neighbor point, is the n nearest neighbor points of the monitoring point, and N is a maximum distance relationship of the monitoring point and the adjacent point. , are data point density of the neighbor point and the monitoring point respectively, is a unit feature density ratio mean value in the region, when , the density of the monitoring point and the neighborhood is always the same, which is a common phenomenon, and when When the abnormal fluctuation exists, it is possible that the abnormal fluctuation is a burst anomaly.

[0107] Specifically, according to the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector, the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained, which can be referred to the specific description between S504-S5056.

[0108] S503, in an embodiment, the target intermediate value is obtained according to the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation, including: obtaining all water pressure fluctuation anomaly indexes; performing mean value calculation on all water pressure fluctuation anomaly indexes to obtain the target intermediate value.

[0109] Wherein, the target intermediate value can be represented by .

[0110] Optionally, all water pressure fluctuation anomaly indexes in the region are sorted according to size, and the value of the intermediate position is taken as the target intermediate value. The influence of extreme abnormal values can be effectively resisted, and the typical abnormal index level can be reflected.

[0111] Optionally, the 50th percentile (i.e. the median) can be taken, or other quantiles can be selected as the threshold according to requirements.

[0112] S504, in an embodiment, the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained according to the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector, including: when the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation is greater than the target intermediate value, and the local outlier factor corresponding to each feature vector is greater than 1, it is determined that the current target abnormal type is the first abnormal type.

[0113] Wherein, the first abnormal type can be water hammer phenomenon.

[0114] It can be understood that: when , the abnormal state is water hammer phenomenon.

[0115] S505、In an embodiment, the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained according to the water pressure fluctuation abnormality index corresponding to the water supply pipeline with abnormal fluctuation, the target intermediate value, and the local outlier factor corresponding to each feature vector, and the method comprises: when the water pressure fluctuation abnormality index corresponding to the water supply pipeline with abnormal fluctuation is less than or equal to the target intermediate value, and the local outlier factor corresponding to each feature vector is less than or equal to 1, the current target abnormal type is determined as the second abnormal type.

[0116] The second abnormal type can be terrain resistance abnormality.

[0117] It can be understood that when , the abnormal state is terrain resistance abnormality.

[0118] Optionally, except for the description between S504 and S505, the rest is normal.

[0119] It can be seen that, in the embodiment, the water hammer burst abnormality and the terrain resistance common mode can be accurately distinguished and recognized through the multi-feature vector and the improved LOF recognition mechanism, and the discrimination ability of the real abnormal state and the accuracy of the steady state judgment of the water supply system are significantly improved.

[0120] The application realizes real-time dynamic perception of the state of the water supply system by sequentially collecting monitoring data of a plurality of water supply pipelines, and timely grasps the water pressure change; the original monitoring data is processed to generate second time sequence data with more representativeness and analysis value, and the accuracy and reliability of subsequent analysis are improved; the water pressure state of each water supply pipeline at each time point is recognized, the pipeline operation condition can be accurately reflected, and abnormal water pressure fluctuation can be timely found; through abnormal fluctuation recognition, the pipeline with abnormal water pressure is quickly located, which provides a basis for preventing and handling water supply abnormality; the water pressure index of abnormal fluctuation is deeply analyzed, and the abnormal type is accurately classified, which is helpful for targetedly formulating maintenance and emergency measures, improving the stability and safety of the water supply system, realizing intelligent monitoring and abnormal management of the water supply network, and improving the reliability and operation efficiency of the water supply system.

[0121] 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.

[0122] 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.

[0123] As another aspect of the embodiments of the present application, the embodiments of the present application provide a sensor-based water volume and pressure fluctuation monitoring device for rural water supply in mountain and hilly areas. The sensor-based water volume and pressure fluctuation monitoring device for rural water supply in mountain and hilly areas can be a software module, which includes a plurality of instructions stored in a memory, and a processor can access the memory to call the instructions for execution to complete the sensor-based water volume and pressure fluctuation monitoring method for rural water supply in mountain and hilly areas described in the above various embodiments.

[0124] Referring to Figure 2 , Figure 2 is a structural schematic diagram of a sensor-based water volume and pressure fluctuation monitoring device for rural water supply in mountain and hilly areas provided by the embodiments of the present application. As Figure 2 indicated, the sensor-based water volume and pressure fluctuation monitoring device 200 for rural water supply in mountain and hilly areas includes:

[0125] The acquisition unit 201 is configured to acquire first time sequence monitoring data of a plurality of water supply pipelines at different time points in a preset area according to a time sequence order.

[0126] The processing unit 202 is configured to perform data processing on the first time sequence monitoring data of the plurality of water supply pipelines to obtain second time sequence monitoring data corresponding to each water supply pipeline.

[0127] The identification unit 203 is configured to perform water pressure state identification on the second time sequence monitoring data corresponding to each water supply pipeline to determine the water pressure state of each water supply pipeline at each time point.

[0128] The identification unit 203 is further configured to perform abnormal fluctuation identification on the water pressure state of each water supply pipeline at each time point to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with abnormal fluctuation.

[0129] The analysis unit 204 is configured to analyze the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation.

[0130] The present application has the following beneficial effects: the present application collects monitoring data of multiple water supply pipelines in a time sequence, realizes real-time dynamic perception of the state of the water supply system, and timely grasps the water pressure change; the original monitoring data is processed to generate second time sequence data with more representativeness and analysis value, and the accuracy and reliability of subsequent analysis are improved; the water pressure state of each water supply pipeline at each time point is identified, the pipeline operation condition can be accurately reflected, and abnormal water pressure fluctuation can be timely found; through abnormal fluctuation identification, the pipeline with abnormal water pressure is quickly located, which provides a basis for preventing and handling water supply abnormalities; the water pressure index of abnormal fluctuation is analyzed in depth, and the abnormal type is accurately classified, which is helpful for targetedly formulating maintenance and emergency measures, improving the stability and safety of the water supply system, realizing intelligent monitoring and abnormal management of the water supply network, and improving the reliability and operation efficiency of the water supply system.

[0131] In an embodiment, in the data processing of the first time sequence monitoring data of the multiple water supply pipelines, the processing unit 202 is further configured to: according to a median filter algorithm, perform noise reduction processing on the first time sequence monitoring data of the multiple water supply pipelines to obtain the second time sequence monitoring data corresponding to each water supply pipeline after noise reduction.

[0132] In an embodiment, in the water pressure state identification of the second time sequence monitoring data corresponding to each water supply pipeline to determine the water pressure state of each water supply pipeline at each time point, the identification unit 203 is further configured to: according to the second time sequence monitoring data corresponding to the water pressure of each water supply pipeline, calculate the instantaneous fluctuation characteristics at each time; according to the instantaneous fluctuation characteristics at each time, obtain the difference index at each time; determine the time corresponding to the difference index greater than 0 as the first time, the first time is in the first water pressure state; determine the time corresponding to the difference index less than 0 as the second time, the second time is in the second water pressure state; determine the time corresponding to the difference index equal to 0 as the third time, the third time is in the water pressure state of the previous time; traverse all time points, and count the first water pressure state and the second water pressure state to obtain the water pressure state of each water supply pipeline at each time point.

[0133] In an embodiment, in the obtaining of the difference index of each time point according to the instantaneous fluctuation feature of each time point, the identification unit 203 is further configured to: divide the second time sequence monitoring data corresponding to each water supply pipeline into sliding window segments to obtain sliding window data segments corresponding to each water supply pipeline, each sliding window data segment including a timestamp, a corresponding water supply pipeline number, and second time sequence monitoring data of each water supply pipeline corresponding to the timestamp; obtain a target sliding window data segment, the target sliding window data segment being a sliding window data segment of a previous time point corresponding to each time point; perform water pressure fluctuation calculation on the target sliding window data segment to obtain a water pressure fluctuation mean value of the target sliding window data segment; and obtain the difference index of each time point according to the instantaneous fluctuation feature of each time point and the water pressure fluctuation mean value of the target sliding window data segment.

[0134] In an embodiment, the water pressure state includes a first water pressure state and a second water pressure state, and the identifying of the water pressure state of each water supply pipeline at each time point to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipeline with fluctuation includes: obtaining a plurality of target time points in the first water pressure state; obtaining at least one first water pressure state period according to the plurality of target time points; performing revision calculation on water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain revised first target water pressure data corresponding to each water supply pipeline; performing anomaly analysis on the first target water pressure data corresponding to each water supply pipeline in each first water pressure state period to obtain a first anomaly state duration of a water supply pipeline with abnormal fluctuation; obtaining target data corresponding to the first anomaly state duration, the target data including first target water pressure data and first water quantity data corresponding to the water supply pipeline with abnormal fluctuation, the first water quantity data being located in the second time sequence monitoring data corresponding to the water supply pipeline with abnormal fluctuation; performing correlation calculation on the target data corresponding to the first anomaly state duration to obtain water quantity-water pressure correlation corresponding to the first anomaly state duration; and performing abnormal fluctuation calculation according to the water quantity-water pressure correlation corresponding to the first anomaly state duration to obtain the water pressure fluctuation anomaly index corresponding to the water supply pipeline with fluctuation.

[0135] In an embodiment, in the analysis of the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuations, the analysis unit 204 is further configured to: obtain a second abnormal state duration corresponding to each water pressure fluctuation anomaly index; obtain a plurality of feature values corresponding to the second abnormal state duration; calculate a feature vector corresponding to each water pressure fluctuation anomaly index according to the second abnormal state duration corresponding to each water pressure fluctuation anomaly index and the plurality of feature values corresponding to the second abnormal state duration; perform density analysis on all the feature vectors corresponding to each water pressure fluctuation anomaly index according to a preset algorithm to obtain a local outlier factor corresponding to each feature vector; obtain a target intermediate value according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuations; and determine a target abnormal type corresponding to each water supply pipeline with abnormal fluctuations according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuations, the target intermediate value, and the local outlier factor corresponding to each feature vector.

[0136] In an embodiment, in the obtaining of the plurality of feature values corresponding to the second abnormal state duration, the analysis unit 204 is further configured to: perform revised calculation on the water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline to obtain revised second target water pressure data corresponding to each water supply pipeline; obtain second target water pressure data and second water quantity data corresponding to the second abnormal state duration; calculate the first feature value and the second feature value according to the second target water pressure data corresponding to the second abnormal state duration; and calculate the third feature value and the fourth feature value according to the second water quantity data, wherein the plurality of feature values include the first feature value, the second feature value, the third feature value, and the fourth feature value.

[0137] In an embodiment, in the obtaining of the target intermediate value according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuations, the analysis unit 204 is further configured to: obtain all the water pressure fluctuation anomaly indexes; and perform mean value calculation on all the water pressure fluctuation anomaly indexes to obtain the target intermediate value.

[0138] In an embodiment, in the determination of the target abnormal type corresponding to each water supply pipeline with abnormal fluctuations according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuations, the target intermediate value, and the local outlier factor corresponding to each feature vector, the analysis unit 204 is further configured to: when the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuations is greater than the target intermediate value and the local outlier factor corresponding to each feature vector is greater than 1, determine that the current target abnormal type is a first abnormal type.

[0139] In an embodiment, in the target abnormal type corresponding to each water supply pipeline with abnormal fluctuation, the analysis unit 204 is further configured to: when the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation is less than the target intermediate value, and the local outlier factor corresponding to each feature vector is less than or equal to 1, determine that the current target abnormal type is the second abnormal type.

[0140] It should be noted that the above-mentioned sensor-based rural water supply water volume and water pressure fluctuation monitoring device in mountainous and hilly areas can execute the sensor-based rural water supply water volume and water pressure fluctuation monitoring method provided by the embodiments of the present application, and has the corresponding function modules and beneficial effects of executing the method. Technical details not described in detail in the sensor-based rural water supply water volume and water pressure fluctuation monitoring device in mountainous and hilly areas can be referred to the sensor-based rural water supply water volume and water pressure fluctuation monitoring method provided by the embodiments of the present application.

[0141] Referring to Figure 3 , Figure 3 is a structural schematic diagram of an electronic device provided by an embodiment of the present application. As Figure 3 shown, the electronic device 300 includes a processor 301 and a memory 302. The processor 301 is in communication connection with the memory 302.

[0142] The processor 301 is configured to support the electronic device to perform the corresponding functions in the sensor-based rural water supply water volume and water pressure fluctuation monitoring method in the above-mentioned method embodiments. The processor 301 can be a central processing unit (CPU), a network processor (NP), a hardware chip or any combination thereof. The above-mentioned hardware chip can be an application specific integrated circuit (ASIC), a programmable logic device (PLD) or a combination thereof. The above-mentioned PLD can be a complex programmable logic device (CPLD), a field-programmable gate array (FPGA), a generic array logic (GAL) or any combination thereof.

[0143] In particular, the processor 301 can include a transmitting card, a receiving card, and a driving chip.

[0144] The memory 302 is configured to store program codes and the like. The memory 302 can include a volatile memory (VM), such as a random access memory (RAM), and / or a non-volatile memory (NVM), such as a read-only memory (ROM), a flash memory, a hard disk drive (HDD), or a solid-state drive (SSD), and / or a combination thereof.

[0145] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program. The computer program includes program instructions, and the program instructions, when executed by a computer, cause the computer to perform the method for monitoring water volume and pressure fluctuation of rural water supply in mountain and hilly areas based on a sensor.

[0146] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiments can be completed by a computer program instructing related hardware. The program can be stored in a computer readable storage medium, and when executed, the program can include the processes of the above-mentioned embodiments. The storage medium can be a magnetic disc, an optical disc, a read-only memory (ROM), a random access memory (RAM), or the like.

[0147] The above only describes the preferred embodiments of the present application, and of course cannot limit the scope of the present application.

Claims

1. A sensor-based monitoring method for water volume and pressure fluctuations in rural mountain and hilly area water supply, characterized by, The method comprises: In a preset area, a plurality of first time sequence monitoring data of water supply pipes at different time points are collected according to a time sequence order; Data processing is performed on the first time sequence monitoring data of the plurality of water supply pipes to obtain second time sequence monitoring data corresponding to each water supply pipe; Water pressure state recognition is performed on the second time sequence monitoring data corresponding to each water supply pipe to determine the water pressure state of each water supply pipe at each time point; Abnormal fluctuation recognition is performed on the water pressure state of each water supply pipe at each time point to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipe with abnormal fluctuation; Analysis is performed on the water pressure fluctuation anomaly index corresponding to the water supply pipe with abnormal fluctuation to obtain a target abnormal type corresponding to each water supply pipe with abnormal fluctuation; The water pressure state comprises a first water pressure state and a second water pressure state, and the determination method of the water pressure fluctuation anomaly index comprises: A plurality of target time points in the first water pressure state are obtained; At least one first water pressure state period is obtained according to the plurality of target time points; Revision calculation is performed on water pressure data in the second time sequence monitoring data corresponding to each water supply pipe to obtain first target water pressure data corresponding to each water supply pipe after revision; In each first water pressure state period, abnormal analysis is performed on the first target water pressure data corresponding to each water supply pipe to obtain a first abnormal state duration period of a water supply pipe with abnormal fluctuation; Target data corresponding to the first abnormal state duration period is obtained, wherein the target data comprises first target water pressure data and first water quantity data corresponding to the water supply pipe with abnormal fluctuation, and the first water quantity data is located in the second time sequence monitoring data corresponding to the water supply pipe with abnormal fluctuation; Correlation calculation is performed on the target data corresponding to the first abnormal state duration period to obtain a water quantity-water pressure correlation corresponding to the first abnormal state duration period; Abnormal fluctuation calculation is performed according to the water quantity-water pressure correlation corresponding to the first abnormal state duration period to obtain a water pressure fluctuation anomaly index corresponding to a water supply pipe with fluctuation.

2. The sensor-based rural water supply fluctuation monitoring method for mountain and hilly areas according to claim 1, characterized in that, The data processing on the first time sequence monitoring data of the plurality of water supply pipes to obtain the second time sequence monitoring data corresponding to each water supply pipe comprises: According to a median filter algorithm, noise reduction processing is performed on the first time sequence monitoring data of the plurality of water supply pipes to obtain second time sequence monitoring data corresponding to each water supply pipe after noise reduction.

3. The sensor-based rural water supply fluctuation monitoring method for mountain and hilly areas according to claim 1, characterized in that, The water pressure state recognition on the second time sequence monitoring data corresponding to each water supply pipe to determine the water pressure state of each water supply pipe at each time point comprises: Calculation is performed on the second time sequence monitoring data corresponding to the water pressure of each water supply pipe to obtain an instantaneous fluctuation feature at each time point; A difference index at each time point is obtained according to the instantaneous fluctuation feature at each time point; A time point corresponding to a difference index greater than 0 is determined as a first time point, and the first time point is in a first water pressure state; A time point corresponding to a difference index less than 0 is determined as a second time point, and the second time point is in a second water pressure state; The time point corresponding to the difference index equal to 0 is determined as a third time point, and the third time point is in the water pressure state of the previous time point; All time points are traversed, and the first water pressure state and the second water pressure state are counted to obtain the water pressure state of each water supply pipeline at each time point.

4. The sensor-based rural water supply fluctuation monitoring method for mountain and hilly areas according to claim 3, characterized in that, The difference index of each time point is obtained according to the instantaneous fluctuation characteristics of each time point, including: The second time sequence monitoring data corresponding to each water supply pipeline is divided into a sliding window to obtain a sliding window data segment corresponding to each water supply pipeline, and each sliding window data segment includes a timestamp, a corresponding water supply pipeline number and second time sequence monitoring data of each water supply pipeline corresponding to the timestamp; A target sliding window data segment is obtained, and the target sliding window data segment is a sliding window data segment of a previous time point corresponding to each time point; The water pressure fluctuation of the target sliding window data segment is calculated to obtain a water pressure fluctuation average value of the target sliding window data segment; The difference index of each time point is obtained according to the instantaneous fluctuation characteristics of each time point and the water pressure fluctuation average value of the target sliding window data segment.

5. The sensor-based rural water supply fluctuation monitoring method for hilly and mountainous areas according to claim 1, characterized in that, The target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained by analyzing the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation, including: A second abnormal state duration corresponding to each water pressure fluctuation abnormal index is obtained; A plurality of feature values corresponding to the second abnormal state duration are obtained; A feature vector corresponding to each water pressure fluctuation abnormal index is obtained by calculating the second abnormal state duration corresponding to each water pressure fluctuation abnormal index and the plurality of feature values corresponding to the second abnormal state duration; A local outlier factor corresponding to each feature vector is obtained by performing density analysis on all feature vectors corresponding to each water pressure fluctuation abnormal index according to a preset algorithm; A target intermediate value is obtained according to the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation; The target abnormal type corresponding to each water supply pipeline with abnormal fluctuation is obtained according to the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation, and the target intermediate value and the local outlier factor corresponding to each feature vector.

6. The sensor-based rural water supply fluctuation monitoring method for mountain hilly areas according to claim 5, characterized in that, The plurality of feature values corresponding to the second abnormal state duration are obtained, including: The water pressure data in the second time sequence monitoring data corresponding to each water supply pipeline is revised to obtain second target water pressure data corresponding to each water supply pipeline after revision; Second target water pressure data and second water quantity data corresponding to the second abnormal state duration are obtained; The second target water pressure data corresponding to the second abnormal state duration is calculated to obtain a first feature value and a second feature value; The second water quantity data is calculated to obtain a third feature value and a fourth feature value, and the plurality of feature values include the first feature value, the second feature value, the third feature value and the fourth feature value.

7. The sensor-based rural water supply fluctuation monitoring method for mountain and hilly areas according to claim 5, characterized in that, The target intermediate value is obtained according to the water pressure fluctuation abnormal index corresponding to the water supply pipeline with abnormal fluctuation, including: All water pressure fluctuation abnormal indexes are obtained; The water pressure fluctuation anomaly indexes are averaged to obtain the target intermediate value.

8. The sensor-based rural water supply fluctuation monitoring method for mountain hilly areas according to claim 5, characterized in that, The target intermediate value and the local outlier factors corresponding to each feature vector are used to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation. When the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation is greater than the target intermediate value, and the local outlier factor corresponding to each feature vector is greater than 1, it is determined that the current target abnormal type is a first abnormal type.

9. The sensor-based rural water supply fluctuation monitoring method for mountain hilly areas according to claim 5, characterized in that, The target intermediate value and the local outlier factors corresponding to each feature vector are used to obtain a target abnormal type corresponding to each water supply pipeline with abnormal fluctuation according to the water pressure fluctuation anomaly indexes corresponding to the water supply pipelines with abnormal fluctuation. When the water pressure fluctuation anomaly index corresponding to the water supply pipeline with abnormal fluctuation is less than or equal to the target intermediate value, and the local outlier factor corresponding to each feature vector is less than or equal to 1, it is determined that the current target abnormal type is a second abnormal type.

Images