A monitoring method and system for water conservancy projects

Abstract

The present invention relates to the field of data processing technology, and in particular to a monitoring method and system for water conservancy projects. The method comprises the steps of: collecting monitoring data, performing a first iterative clustering on the monitoring data, obtaining the degree of outliers of each monitoring data of each clustering cluster in each round in the first iterative clustering result; obtaining the degree of isolation of each monitoring data according to the degree of outliers, eliminating the monitoring data with a larger degree of isolation to obtain the remaining monitoring data, and then clustering the remaining monitoring data to obtain the second iterative clustering result. According to the average level of the degree of outliers of each remaining monitoring data in the second iterative clustering result, the degree of abnormality of each remaining monitoring data is obtained, and according to the degree of abnormality, it is judged whether the water conservancy facility has an abnormality. The present invention eliminates the influence of noise data on the clustering result, so that the abnormality judgment result of subsequent data is more accurate.

Description

Technical Field

[0001] The present invention relates to the technical field of data processing, and in particular to a monitoring method and system for water conservancy projects. Background Art

[0002] With the global climate change and the increasing demand for water resources management, water conservancy projects play a vital role in ensuring the rational use of water resources, flood prevention and disaster relief, and ecological environment protection. Water conservancy facilities such as reservoirs, rivers, dams, and sluice gates are important components of national infrastructure. Their smooth operation is directly related to the economic development of society, and water conservancy projects need to be monitored.

[0003] The patent application document with the publication number CN113191555A currently discloses an iterative self-organizing clustering combination algorithm based on an improved cultural algorithm, including: S1, a clustering algorithm, in which the iterative self-organizing algorithm obtains a more reasonable classification; S2, a cultural algorithm, performs a gene evolution operation, evaluates individuals with a fitness function, inputs excellent samples provided by them, explicitly describes and stores the hidden information of the samples, guides the population evolution and updates the function, guides the evolution of population individuals, until the optimal solution is obtained; S3, evaluates individuals in the population space, and generates an initial belief space; S4, mutates each parent individual in the population space to generate corresponding child individuals; S5, sets a receiving function, and updates the belief space; S6, if the termination condition is not met, repeats step S4, otherwise ends, and obtains the optimal classification.

[0004] Due to the reasons of the water level meter and flow meter themselves, there may be some noise data in the monitoring data of the water conservancy facilities collected by the sensor. The difference between these noise data and other monitoring data is large. When the collected monitoring data are clustered using the iterative self-organizing clustering algorithm, all monitoring data participate in the clustering. Therefore, the noise data in the monitoring data affects the accuracy of the clustering center iteration, thereby affecting the accuracy of the clustering results, and thus affecting the accuracy of the subsequent monitoring data abnormality judgment. Summary of the invention

[0005] In order to solve the technical problem that when an iterative self-organizing clustering algorithm is used to cluster the monitoring data of water conservancy facilities, the noise data in the monitoring data affects the accuracy of the iteration of the clustering center, thereby affecting the accuracy of the clustering results and affecting the accuracy of the subsequent abnormal judgment of the monitoring data, the present invention provides a monitoring method and system for water conservancy projects.

[0006] In a first aspect, the present invention provides a monitoring method for a water conservancy project, which adopts the following technical solution: A monitoring method for a water conservancy project comprises the following steps: Collect monitoring data; perform the first iteration clustering on the monitoring data, obtain the outlier degree of each monitoring data in each clustering cluster of each round in the first iteration clustering result; obtain the isolation degree of each monitoring data: , represents the degree of isolation of the mth monitoring data; T represents the first clustering round; Represents the degree of outlier of the mth monitoring data in the i-th round in the first iterative clustering result; represents the mean of the outlier degree of the mth monitoring data in all rounds in the first iteration clustering result; || represents the absolute value symbol; norm() represents the normalization function; The remaining monitoring data are obtained after eliminating the monitoring data with a large degree of isolation; the remaining monitoring data are iteratively clustered to obtain the second iterative clustering result; the abnormality degree of each remaining monitoring data is obtained, and the abnormality degree is the average of the outlier degree of each remaining monitoring data in each round in the second iterative clustering result; according to the abnormality degree, whether the water conservancy facility is abnormal is judged.

[0007] The innovation of the present invention lies in obtaining the degree of isolation of each monitoring data according to the degree to which each monitoring data deviates from the clustering cluster during the iterative clustering process, and obtaining the remaining monitoring data after eliminating the monitoring data with a larger degree of isolation; after iteratively clustering the remaining monitoring data again, obtaining the degree of abnormality of each remaining monitoring data to monitor the water conservancy equipment, reducing the influence of noise data in the monitoring data on the accuracy of cluster center iteration, making the clustering result more accurate, and thus improving the accuracy of subsequent monitoring data abnormality judgment, and can accurately monitor abnormal conditions of water conservancy engineering facilities.

[0008] Preferably, the process of performing the first iterative clustering on the monitoring data includes: A first clustering round T is preset, and according to the first clustering round T, the monitoring data is clustered using an iterative self-organizing clustering algorithm to obtain a first iterative clustering result, wherein the first iterative clustering result includes each clustering cluster of each round.

[0009] It is convenient to analyze the degree to which each monitoring data deviates from the clustering cluster during the iterative clustering process to obtain noise data.

[0010] Preferably, the step of obtaining the outlier degree of each monitoring data of each cluster in each round in the first iterative clustering result includes: ; In the formula, represents the outlier degree of the kth monitoring data of the jth cluster in the i-th round; Represents the Euclidean distance between the kth monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; Represents the number of monitoring data of the jth cluster in the i-th round; Represents the mean of the Euclidean distances between all monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; norm() represents the normalization function.

[0011] The greater the degree of outliers, the more likely it is noise data, which makes it easier to obtain noise data later.

[0012] Preferably, the process of eliminating the monitoring data with a greater degree of isolation to obtain the remaining monitoring data includes: An isolation threshold T1 is preset. For any monitoring data, if the isolation degree of the monitoring data is greater than the isolation threshold, the monitoring data is noise data. All noise data in the monitoring data is deleted to obtain the remaining monitoring data.

[0013] The influence of noise data on subsequent clustering results is eliminated.

[0014] Preferably, the process of iteratively clustering the remaining monitoring data to obtain a second iterative clustering result includes: A second clustering round T2 is preset, and according to the second clustering round T2, an iterative self-organizing clustering algorithm is used to iteratively cluster the remaining monitoring data to obtain a second iterative clustering result, wherein the second iterative clustering result includes each clustering cluster of each round.

[0015] Preferably, the process of judging whether the water conservancy facility has an abnormality according to the abnormality degree includes: The abnormality level threshold T3 is preset. If the average abnormality level of all remaining monitoring data is greater than or equal to the abnormality level threshold T3, there is an abnormality in the water conservancy facility, and the system issues an early warning to the staff.

[0016] Can accurately monitor abnormalities in water conservancy facilities.

[0017] Preferably, the collecting monitoring data includes: Set every two minutes as a sampling time, install water level meters and flow meters in the water conservancy facilities, collect water level data and flow data in turn each time, and collect data for a total of five hours. Use the water level data and flow data at each collection time as a monitoring data.

[0018] In a second aspect, the present invention provides a monitoring system for a water conservancy project, which adopts the following technical solution: A monitoring system for a water conservancy project comprises: a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, the above-mentioned monitoring method for a water conservancy project is implemented.

[0019] By adopting the above technical solution, the above-mentioned monitoring method for water conservancy projects is generated into a computer program and stored in a memory so as to be loaded and executed by a processor, thereby making a terminal device based on the memory and the processor for easy use.

[0020] The present invention has the following technical effects: the purpose of the present invention is to obtain the degree of isolation of each monitoring data according to the degree to which each monitoring data deviates from the clustering cluster in the iterative clustering process, and obtain the remaining monitoring data after eliminating the monitoring data with a large degree of isolation; after iteratively clustering the remaining monitoring data again, the degree of abnormality of each remaining monitoring data is obtained to monitor the water conservancy facilities, thereby reducing the influence of noise data in the monitoring data on the accuracy of cluster center iteration, making the clustering results more accurate, thereby improving the accuracy of subsequent monitoring data abnormality judgment, and can accurately monitor the abnormalities of water conservancy facilities. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present invention will become readily understood. In the accompanying drawings, several embodiments of the present invention are shown in an exemplary and non-restrictive manner, and the same or corresponding reference numerals represent the same or corresponding parts.

[0022] Figure 1 The present invention is a flow chart of a monitoring method for water conservancy projects according to an embodiment of the present invention. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention.

[0024] It should be understood that when the terms "first", "second", etc. are used in the claims, descriptions, and drawings of the present invention, they are only used to distinguish different objects, rather than to describe a specific order. The terms "include" and "comprise" used in the description and claims of the present invention indicate the presence of the described features, wholes, steps, operations, elements, and / or components, but do not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components, and / or their collections.

[0025] The embodiment of the present invention discloses a monitoring method for a water conservancy project, referring to Figure 1 , comprising steps S1 to S4: S1: Collect monitoring data.

[0026] It should be noted that monitoring data refers to various data related to the operation of water conservancy facilities collected through various sensors, equipment and technical means. By analyzing real-time monitoring data, abnormal changes can be discovered, providing data support for early warning, thereby reducing labor costs and mitigating disaster losses; In an embodiment of the present invention, a sampling time is set every two minutes, and a water level meter and a flow meter are arranged in the water conservancy facility. Water level data and flow data are collected in turn each time, and the collection is carried out for a total of five hours. The water level data and flow data at each collection time are used as a monitoring data.

[0027] S2: Perform the first iterative clustering on the monitoring data to obtain the outlier degree of each monitoring data in each clustering cluster of each round in the first iterative clustering result; obtain the isolation degree of each monitoring data according to the outlier degree of each monitoring data in each clustering cluster of each round in the first iterative clustering result.

[0028] It should be noted that the iterative self-organizing clustering algorithm is an algorithm for anomaly detection of multidimensional data. In the clustering process, the initial cluster center is randomly selected and iterated repeatedly to optimize the clustering result. In each iteration, the algorithm assigns the data point to the nearest cluster center and updates the position of the cluster center according to the assignment result until the cluster center no longer changes or reaches the preset number of iterations, thereby realizing the clustering of high-dimensional data and clustering multidimensional data points with similar characteristics in the same cluster cluster. However, when collecting monitoring data of water conservancy equipment, due to the reasons of the water level meter and the flow meter themselves, some noise data may be present in the collected monitoring data. The difference between the distance of these noise data and other monitoring data is large. In the process of iterative clustering, all samples participate in clustering. Therefore, the noise data in the monitoring data affects the accuracy of the iteration of the cluster center, thereby affecting the accuracy of the clustering result, thereby affecting the accuracy of the abnormal judgment of the subsequent data. Therefore, the present invention performs the first iterative clustering on all monitoring data. In the first iterative clustering process, the degree of isolation of each monitoring data is obtained according to the first iterative clustering result, so as to facilitate the subsequent distinction of the noise data.

[0029] Step S2 includes steps S20 and S21, which are specifically as follows: S20: Perform the first iterative clustering on the monitoring data, and obtain the outlier degree of each monitoring data of each clustering cluster in each round in the first iterative clustering result.

[0030] It should be noted that the present invention first performs the first clustering on the collected monitoring data to obtain the first iterative clustering result. If the Euclidean distance between any monitoring data of any clustering cluster of any round in the first iterative clustering result and the clustering center of its clustering cluster is farther, it means that the degree of outlier of the monitoring data of the clustering cluster of this round in the first iterative clustering result is relatively large.

[0031] In an embodiment of the present invention, a first clustering round T is preset. According to the first clustering round T, an iterative self-organizing clustering algorithm is used to cluster the monitoring data to obtain a first iterative clustering result. The first iterative clustering result includes each clustering cluster of each round. In an embodiment of the present invention, the implementer can preset the value of the first clustering round T according to the specific implementation method.

[0032] Get the outlier degree of each monitoring data of each cluster cluster in each round in the first iterative clustering results: ; In the formula, represents the outlier degree of the kth monitoring data of the jth cluster in the i-th round; Represents the Euclidean distance between the kth monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; Represents the number of monitoring data of the jth cluster in the i-th round; represents the mean of the Euclidean distances between all monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; norm() represents the normalization function; The larger the value of is, the greater the degree of outlier of the kth monitoring data of the jth cluster in the i-th round in the first iterative clustering result is; The larger the value of is, the closer the Euclidean distance between all monitoring data in the jth cluster in the i-th round and the cluster center of the cluster is, and the higher the confidence level of the outlier degree of the kth monitoring data in the jth cluster in the i-th round is.

[0033] S21: Obtain the isolation degree of each monitoring data according to the outlier degree of each monitoring data of each clustering cluster in each round in the first iterative clustering result.

[0034] It should be noted that in the process of iterative clustering of all monitoring data using the iterative self-organizing clustering algorithm, these monitoring data will be assigned to different clustering clusters in different clustering rounds. Therefore, the outlier degree of each monitoring data in each clustering cluster in each round of the first iterative clustering result can also be recorded as the outlier degree of each monitoring data in each round of the first iterative clustering result. For any monitoring data, if its outlier degree in each round of the iterative clustering process has always maintained a high level, it means that the difference between the monitoring data and other monitoring data is large, that is, the degree of isolation of the monitoring data is high.

[0035] In an embodiment of the present invention, the isolation degree of each monitoring data is obtained: ; In the formula, represents the degree of isolation of the mth monitoring data; T represents the first clustering round; Represents the degree of outlier of the mth monitoring data in the i-th round in the first iterative clustering result; represents the mean of the outlier degree of the mth monitoring data in all rounds in the first iteration clustering result; || represents the absolute value symbol; norm() represents the normalization function; Represents the average level of the outlier degree of the mth monitoring data in the first iterative clustering process. The larger the value, the greater the degree of isolation of the mth monitoring data. It represents the difference between the outlier degree of the mth monitoring data in each round in the first iterative clustering result and the average level of outlier degree. The smaller the value is, the smaller the fluctuation of the outlier degree of the mth monitoring data in the first iterative clustering process is, and the higher the isolation degree of the mth monitoring data is.

[0036] S3: After removing the monitoring data with a large degree of isolation, the remaining monitoring data are obtained, and the remaining monitoring data are then clustered to obtain the second iterative clustering result. According to the average level of the degree of outliers of each remaining monitoring data in the second iterative clustering result, the abnormality degree of each remaining monitoring data is obtained, and according to the abnormality degree, whether the water conservancy facility is abnormal is judged.

[0037] Step S3 includes steps S30 and S31, which are specifically as follows: S30: After removing the monitoring data with a large degree of isolation, the remaining monitoring data is obtained, and the remaining monitoring data is then clustered to obtain a second iterative clustering result.

[0038] It should be noted that the higher the degree of isolation of the monitoring data, the greater the possibility that the monitoring data is noise, and the greater its impact on the clustering results. It is necessary to promptly remove the monitoring data with a large degree of isolation and then perform clustering to improve the accuracy of the clustering results.

[0039] In an embodiment of the present invention, an isolation threshold T1 is preset. For any monitoring data, if the degree of isolation of the monitoring data is greater than the isolation threshold, the monitoring data is noise data. All noise data in the monitoring data is deleted to obtain the remaining monitoring data. The preset isolation threshold T1=0.7. In other embodiments, the implementer can adjust it according to the specific situation.

[0040] A second clustering round T2 is preset. According to the second clustering round T2, the remaining monitoring data are iteratively clustered using an iterative self-organizing clustering algorithm to obtain a second iterative clustering result, wherein the second iterative clustering result includes each clustering cluster of each round; wherein, the second clustering round T2=30, and in other embodiments, the implementer may adjust it according to the specific circumstances.

[0041] S31: Obtain the abnormality degree of each remaining monitoring data according to the average level of the outlier degree of each remaining monitoring data in the second iteration clustering result, and determine whether the water conservancy project equipment has an abnormality according to the abnormality degree.

[0042] It should be noted that in the iterative clustering process, the monitoring data that is more likely to be noise data is eliminated and then clustered, and secondary clustering is completed for all remaining monitoring data. Therefore, if the average level of outlier degree of any remaining monitoring data in the second iterative clustering result is greater, it means that the degree of abnormality of the remaining monitoring data is greater.

[0043] In the embodiment of the present invention, the outlier degree of each remaining monitoring data in each round in the second iterative clustering result is obtained according to the outlier degree of each monitoring data in each clustering cluster in each round in the first iterative clustering result.

[0044] Get the abnormality level of each remaining monitoring data: ; In the formula, Represents the abnormality degree of the pth remaining monitoring data; represents the second clustering round; represents the outlier degree of the pth remaining monitoring data in the bth round in the second iteration clustering result; norm() represents the normalization function; It represents the average level of outlier degree of the pth remaining monitoring data in the second iterative clustering process. The larger the average level of outlier degree is, the higher the abnormality degree of the pth remaining monitoring data is. Conversely, the lower the abnormality degree of the pth remaining monitoring data is.

[0045] In an embodiment of the present invention, an abnormality level threshold T3 is preset. If the average abnormality level of all remaining monitoring data is greater than or equal to the abnormality level threshold T3, the system issues an early warning to the staff, and the water conservancy equipment is abnormal at this time. In an embodiment of the present invention, the abnormality level threshold T3 is preset to 0.8. In other embodiments, the implementers can preset the value of the abnormality level threshold T3 according to the specific implementation situation.

[0046] An embodiment of the present invention further discloses a monitoring system for a water conservancy project, including a processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a monitoring method for a water conservancy project according to the present invention is implemented.

[0047] The above system also includes other components well known to those skilled in the art, such as a communication bus and a communication interface, and their configuration and functions are known in the art, so they will not be described in detail here.

[0048] In the present invention, the aforementioned memory may be any tangible medium containing or storing a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. For example, a computer-readable storage medium may be any suitable magnetic storage medium or magneto-optical storage medium, such as a resistive random access memory, a dynamic random access memory, a static random access memory, an enhanced dynamic random access memory, a high bandwidth memory, a hybrid storage cube, etc., or any other medium that can be used to store the required information and can be accessed by an application, a module, or both. Any such computer storage medium may be part of the device or accessible or connectable to the device.

[0049] Although this specification has shown and described a number of embodiments of the present invention, it will be apparent to those skilled in the art that such embodiments are provided by way of example only. Those skilled in the art will conceive of many modifications, changes and alternatives without departing from the ideas and spirit of the present invention. It should be understood that in the practice of the present invention, various alternatives to the embodiments of the present invention described herein may be employed.

[0050] The above are all preferred embodiments of the present invention, and are not intended to limit the protection scope of the present invention. Therefore, any equivalent changes made based on the structure, shape, and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A monitoring method for a water conservancy project, characterized in that: Includes steps: Collect monitoring data; perform the first iteration clustering on the monitoring data, obtain the outlier degree of each monitoring data in each clustering cluster of each round in the first iteration clustering result; obtain the isolation degree of each monitoring data: , Represents the degree of isolation of the mth monitoring data; T represents the first clustering round; Represents the degree of outlier of the mth monitoring data in the i-th round in the first iterative clustering result; represents the mean of the outlier degree of the mth monitoring data in all rounds in the first iteration clustering result; || represents the absolute value symbol; norm() represents the normalization function; The remaining monitoring data are obtained by eliminating the monitoring data with a greater degree of isolation; Perform iterative clustering on the remaining monitoring data to obtain the second iterative clustering result; Obtaining the abnormality degree of each remaining monitoring data, where the abnormality degree is the average of the outlier degree of each remaining monitoring data in each round in the second iterative clustering result; Based on the degree of abnormality, determine whether there is any abnormality in the water conservancy facility.

2. A monitoring method for water conservancy projects according to claim 1, characterized in that: The process of performing the first iterative clustering of the monitoring data includes: A first clustering round T is preset, and according to the first clustering round T, the monitoring data is clustered using an iterative self-organizing clustering algorithm to obtain a first iterative clustering result, wherein the first iterative clustering result includes each clustering cluster of each round.

3. A monitoring method for water conservancy projects according to claim 1, characterized in that: The step of obtaining the outlier degree of each monitoring data of each clustering cluster in each round in the first iterative clustering result includes: ； In the formula, represents the outlier degree of the kth monitoring data of the jth cluster in the i-th round; Represents the Euclidean distance between the kth monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; Represents the number of monitoring data of the jth cluster in the i-th round; Represents the mean of the Euclidean distances between all monitoring data of the jth cluster in the i-th round and the cluster center of its cluster; norm() represents the normalization function.

4. A monitoring method for water conservancy projects according to claim 1, characterized in that: The process of eliminating the monitoring data with a greater degree of isolation and obtaining the remaining monitoring data includes: An isolation threshold T1 is preset. For any monitoring data, if the isolation degree of the monitoring data is greater than the isolation threshold, the monitoring data is noise data. All noise data in the monitoring data is deleted to obtain the remaining monitoring data.

5. A monitoring method for water conservancy projects according to claim 1, characterized in that: The process of iteratively clustering the remaining monitoring data to obtain the second iterative clustering result includes: A second clustering round T2 is preset, and according to the second clustering round T2, an iterative self-organizing clustering algorithm is used to iteratively cluster the remaining monitoring data to obtain a second iterative clustering result, wherein the second iterative clustering result includes each clustering cluster of each round.

6. A monitoring method for water conservancy projects according to claim 1, characterized in that: The process of judging whether the water conservancy facility has an abnormality according to the abnormality degree includes: The abnormality level threshold T3 is preset. If the average abnormality level of all remaining monitoring data is greater than or equal to the abnormality level threshold T3, there is an abnormality in the water conservancy facility, and the system issues an early warning to the staff.

7. A monitoring method for water conservancy projects according to claim 1, characterized in that: The collecting and monitoring data includes: Set every two minutes as a sampling time, install water level meters and flow meters in the water conservancy facilities, collect water level data and flow data in turn each time, and collect data for a total of five hours. Use the water level data and flow data at each collection time as a monitoring data.

8. A monitoring system for water conservancy projects, characterized in that: include: A processor and a memory, wherein the memory stores computer program instructions, and when the computer program instructions are executed by the processor, a monitoring method for a water conservancy project according to any one of claims 1 to 7 is implemented.

Images