A water conservancy sluice station operation management method and system based on IOT data center

By decomposing the water pressure data sequence and estimating the noise level evaluation value, determining the appropriate decomposition number of layers for wavelet transformation, the problem of poor noise removal effect of water pressure data at the water conservancy gate station is solved, and the accuracy and ability of water conservancy gate station operation management is improved. Reliability.

CN118551158BActive Publication Date: 2024-11-19SUZHOU HIGH-TECH ZONE JIAOFA DIGITAL TECH CO LTD
View PDF 6 Cites 0 Cited by

Patent Information

Application Number
CN202410598788.4
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-05-15
Publication Date
2024-11-19
Estimated Expiration
2044-05-15

AI Technical Summary

Technical Problem

When the existing wavelet transform denoising the water pressure data of the water conservancy gate station, the decomposition layer setting is inappropriate, which affects the denoising effect and leads to poor credibility in the operation and management of the water conservancy gate station.

Method used

By obtaining the water pressure data sequence, decompose it into seasonal term curves and residual curves, estimating the noise degree evaluation value and correction coefficient, determining the appropriate number of decomposition layers for wavelet transformation processing, and removing noise.

Benefits of technology

It improves the noise removal effect of water pressure data of water conservancy gate stations and enhances the accuracy and credibility of operation and management of water conservancy gate stations.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118551158B_ABST
    Figure CN118551158B_ABST
Patent Text Reader

Abstract

The present invention relates to the technical field of water pressure data processing of water conservancy sluice stations, and specifically to a method and system for water conservancy sluice station operation management based on IOT data middle station. The method comprises: obtaining a water pressure data sequence of a water conservancy sluice station, decomposing it to obtain a seasonal term curve and a residual curve; obtaining a noise level evaluation value of the water pressure data sequence and a noise level evaluation value of the residual curve according to the fluctuation of the water pressure data; obtaining a correction coefficient according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve; determining the number of decomposition layers based on the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum value point and the minimum value point on the seasonal term curve, and then using wavelet transform to process the water pressure data sequence, and managing the operation of the water conservancy sluice station based on the denoised water pressure data. The present invention improves the credibility and accuracy of the operation management of the water conservancy sluice station.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of water pressure data processing of water conservancy sluice stations, and in particular to a water conservancy sluice station operation management method and system based on an IOT data center. Background Art

[0002] The data middle platform is a data management and application architecture that aims to centrally manage and integrate data resources inside and outside the organization, provide unified data services and application interfaces to support business applications and data analysis needs. The water conservancy sluice station operation management method based on the Internet of Things (IOT) data middle platform mainly collects and analyzes water pressure, flow, water level and other data by integrating Internet of Things technology, so as to optimize the operation of the sluice, improve the operation and maintenance efficiency, and realize remote monitoring and intelligent scheduling. When the water conservancy sluice station is in operation, the water level changes can be understood in real time by monitoring the water pressure data, so as to take control measures in time to ensure the safe operation of the water conservancy project. At the same time, it can also be used to predict the water flow, help decision makers make more scientific water resources scheduling plans, and improve the utilization efficiency of water resources. However, the monitored water pressure data may be affected by external factors, resulting in noise in the collected water pressure data, which affects the accuracy of subsequent analysis and decision-making of the water conservancy sluice station operation management. Therefore, it is necessary to denoise the collected water pressure data to improve the accuracy of subsequent analysis and management based on water pressure data.

[0003] When using wavelet transform to denoise the water pressure data during the operation of the sluice station, the water pressure data signals collected in different time periods may be affected by noise to different degrees. Therefore, the number of decomposition layers in the process of processing the collected water pressure data using wavelet transform may be different. The number of layers of control signal decomposition can affect the fineness of the decomposition. Deeper decomposition can extract more detailed signal features, but it may also mix in more noise. The choice of the number of decomposition layers has a great influence on the accuracy of the final result of denoising the collected water pressure data. Therefore, if the number of decomposition layers is not set appropriately, it will affect the denoising effect of the water pressure data, and thus lead to poor credibility in the operation and management of the water conservancy sluice station. Summary of the invention

[0004] In order to solve the problem that the decomposition layer number is not set properly when the existing wavelet transform is used to denoise the water pressure data of the water conservancy sluice station, which affects the denoising effect of the water pressure data and leads to poor credibility of the operation and management of the water conservancy sluice station, the purpose of the present invention is to provide a water conservancy sluice station operation management method and system based on IOT data middle station, and the technical scheme adopted is as follows:

[0005] In a first aspect, the present invention provides a method for operating and managing a water conservancy sluice station based on an IOT data center, the method comprising the following steps:

[0006] Obtain the water pressure data sequence of the water conservancy sluice station in the current time period collected by the IOT device;

[0007] Decomposing the water pressure data sequence to obtain the corresponding seasonal term curve and residual curve; obtaining the noise level evaluation value of the water pressure data sequence and the noise level evaluation value of the residual curve according to the fluctuation of the data on the water pressure data sequence or the residual curve; obtaining the correction coefficient of the noise level evaluation value according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve;

[0008] Based on the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum point and the minimum point on the seasonal term curve, the decomposition parameter of the water pressure data sequence is obtained; based on the decomposition parameter, the number of decomposition layers corresponding to the water pressure data sequence is determined;

[0009] Based on the decomposition layer number, the water pressure data sequence is processed by wavelet transform to obtain the denoised water pressure data, and the operation of the water conservancy sluice station is managed based on the denoised water pressure data.

[0010] Preferably, the step of decomposing the water pressure data sequence to obtain a corresponding seasonal term curve and a residual curve includes:

[0011] Performing curve fitting on the water pressure data in the water pressure data sequence to obtain a water pressure data curve, wherein the abscissa of the water pressure data curve is time;

[0012] The water pressure data curve is decomposed by using the STL decomposition algorithm to obtain the corresponding seasonal term curve and residual curve.

[0013] Preferably, obtaining the noise level evaluation value of the water pressure data sequence according to the fluctuation of the data in the water pressure data sequence includes:

[0014] Calculate the difference between each water pressure data and other water pressure data in the water pressure data sequence; take the ratio between the number of water pressure data identical to each water pressure data in the water pressure data sequence and the number of water pressure data in the water pressure data sequence as the number ratio of each water pressure data in the water pressure data sequence; calculate the standard deviation of all water pressure data in the water pressure data sequence;

[0015] According to the difference between each water pressure data and other water pressure data in the water pressure data sequence, the quantity proportion and the standard deviation of all water pressure data in the water pressure data sequence, the noise level evaluation value of the water pressure data sequence is obtained. The difference between each water pressure data and other water pressure data and the standard deviation of all water pressure data in the water pressure data sequence are positively correlated with the noise level evaluation value of the water pressure data sequence, and the quantity proportion is negatively correlated with the noise level evaluation value of the water pressure data sequence.

[0016] Preferably, the noise level evaluation value of the water pressure data sequence is calculated using the following formula:

[0017] ;

[0018] Among them, Q represents the noise level evaluation value of the water pressure data sequence, M represents the number of water pressure data in the water pressure data sequence, and F i represents the i-th water pressure data in the water pressure data sequence, F i,s represents the sth water pressure data in the water pressure data sequence except the ith water pressure data, N i represents the number of water pressure data in the water pressure data sequence that are the same as the i-th water pressure data, σ represents the standard deviation of all water pressure data in the water pressure data sequence, exp( ) represents an exponential function with a natural constant as the base, and || represents the absolute value sign.

[0019] Preferably, the correction coefficient of the noise level evaluation value is obtained according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve, including:

[0020] The amplitudes of all maximum points on the seasonal term curve constitute a maximum set, and the amplitudes of all minimum points on the seasonal term curve constitute a minimum set; calculate the standard deviation of all data values ​​in the maximum set and the standard deviation of all data values ​​in the minimum set respectively;

[0021] Every two adjacent extreme value points on the seasonal term curve constitute an extreme value point pair; obtain the time interval between the two extreme value points in each extreme value point pair, and record it as the time interval of each extreme value point pair;

[0022] The correction coefficient of the noise level evaluation value is obtained based on the difference between the time interval of each extreme point pair and the average time interval of all extreme point pairs, the difference in the noise level evaluation value between the water pressure data series and the residual curve, the standard deviation of all data values ​​in the maximum value set and the standard deviation of all data values ​​in the minimum value set.

[0023] Preferably, the correction coefficient of the noise level evaluation value is calculated using the following formula:

[0024] ;

[0025] Among them, Y represents the correction coefficient of the noise level evaluation value, Q represents the noise level evaluation value of the water pressure data sequence, and Q c represents the noise level evaluation value of the residual curve, U represents the number of extreme point pairs, d(u) represents the time interval of the uth extreme point pair, represents the average value of the time intervals between all pairs of extreme points, Represents the standard deviation of all data values ​​in the maximum value set, represents the standard deviation of all data values ​​in the minimum set, e represents a natural constant, || represents the absolute value sign, and norm() represents the normalization function.

[0026] Preferably, the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum point and the minimum point on the seasonal term curve are used to obtain the decomposition parameters of the water pressure data sequence, including:

[0027] The difference between the mean of the data values ​​in the maximum value set and the mean of the data values ​​in the minimum value set is recorded as the extreme value difference;

[0028] According to the extreme value difference, the correction coefficient and the noise level evaluation value of the water pressure data sequence, the decomposition parameters of the water pressure data sequence are obtained, the extreme value difference and the noise level evaluation value of the water pressure data sequence are both positively correlated with the decomposition parameters, and the correction coefficient is negatively correlated with the decomposition parameters.

[0029] Preferably, determining the number of decomposition layers corresponding to the water pressure data sequence based on the decomposition parameter includes:

[0030] The result of rounding up the product of the decomposition parameter and the hyperparameter of the preset number of decomposition levels is determined as the decomposition level corresponding to the water pressure data sequence; wherein the hyperparameter of the preset number of decomposition levels is a positive integer.

[0031] Preferably, the step of obtaining the water pressure data sequence of the water conservancy sluice station collected by the IOT device in the current time period includes:

[0032] The water pressure data of the water conservancy sluice station collected by the IOT device at each collection time in the current time period is obtained. The water pressure data of all collection times in the current time period constitute the water pressure data sequence in the current time period.

[0033] In the second aspect, the present invention provides a water conservancy gate station operation management system based on the IOT data center, including a memory and a processor, and the processor executes a computer program stored in the memory to implement the above-mentioned water conservancy gate station operation management method based on the IOT data center.

[0034] The present invention has at least the following beneficial effects:

[0035] The present invention takes into account that when the water pressure data sequence of the collected water conservancy sluice station is decomposed and denoised by wavelet transform, the degree to which the water pressure signal at different times is affected by noise may be different, and the number of decomposition layers is related to the noise level of the collected water pressure data. Therefore, it is necessary to estimate the noise level of the water pressure data sequence. The present invention first estimates the noise level of the water pressure data sequence as a whole to obtain a noise level evaluation value of the water pressure data sequence. The noise level evaluation value of the water pressure data sequence may be related to the change of the regularity of the collected signal. Therefore, the noise level evaluation value of the water pressure data sequence may not be accurate enough. The water pressure data sequence is further decomposed to obtain a seasonal term curve and a residual curve. By further analyzing the characteristics of the seasonal term curve and the residual curve, a correction coefficient of the noise level evaluation value is obtained. At the same time, the noise level evaluation value of the water pressure data sequence is corrected in combination with the amplitude difference between the maximum point and the minimum point on the seasonal term curve to obtain the decomposition layer corresponding to the water pressure data sequence, and then decomposed and denoised, thereby effectively removing the noise, ensuring the denoising effect of the water pressure data of the water conservancy sluice station, and improving the credibility and accuracy of the operation and management of the water conservancy sluice station. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the drawings required for use in the embodiments or the prior art descriptions are briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0037] Figure 1 A flowchart of a water conservancy sluice station operation management method based on an IOT data center provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0038] In order to further explain the technical means and effects adopted by the present invention to achieve the predetermined purpose of the invention, the following is a detailed description of a water conservancy sluice station operation management method based on IOT data center proposed by the present invention in combination with the accompanying drawings and preferred embodiments.

[0039] Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.

[0040] The following is a detailed description of a specific scheme of a water conservancy sluice station operation management method based on an IOT data center provided by the present invention in conjunction with the accompanying drawings.

[0041] An embodiment of a water conservancy sluice station operation management method based on IOT data center:

[0042] The specific scenario targeted by this embodiment is: when managing the operation of a water conservancy sluice station, first collect the water pressure data of the current time period of the water conservancy sluice station. Considering that there may be noise in the collected water pressure data, it is necessary to perform denoising processing on it to improve the accuracy of subsequent analysis results. This embodiment uses wavelet transform to process the collected water pressure data. Since the number of decomposition layers will directly affect the processing effect, this embodiment will analyze the degree of interference of the collected water pressure data by noise, determine the optimal number of sampling layers, and then perform wavelet transform on the water pressure data in the current time period, and manage the operation of the water conservancy sluice station based on the processing results.

[0043] This embodiment proposes a water conservancy sluice station operation management method based on IOT data center, such as Figure 1 As shown, a water conservancy sluice station operation management method based on IOT data center in this embodiment includes the following steps:

[0044] Step S1, obtaining the water pressure data sequence of the water conservancy sluice station in the current time period collected by the IOT device.

[0045] In this embodiment, IOT equipment is first deployed in the water conservancy sluice station to collect water pressure data of the water conservancy sluice station. In this embodiment, the water pressure data of each collection moment in the current time period of the water conservancy sluice station collected by the IOT equipment is obtained. The current time period is a collection of all historical moments whose time interval with the current moment is less than or equal to a preset time length. In this embodiment, the preset time length is 12 hours, and the collection frequency of water pressure data is once per second. In specific applications, the implementer can set the preset time length and the collection frequency of water pressure data according to the specific situation.

[0046] At this point, this embodiment has collected the water pressure data of the water conservancy sluice station at each collection moment in the current time period, and arranged the collected water pressure data of the water conservancy sluice station at each collection moment in the current time period in chronological order to obtain the water pressure data sequence in the current time period.

[0047] Step S2, decomposing the water pressure data sequence to obtain the corresponding seasonal term curve and residual curve; obtaining the noise level evaluation value of the water pressure data sequence and the noise level evaluation value of the residual curve according to the fluctuation of the data on the water pressure data sequence or the residual curve respectively; obtaining the correction coefficient of the noise level evaluation value according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve.

[0048] The water pressure data collected by the hydraulic sluice station during operation may be affected by external factors such as ambient temperature, water flow velocity, and water surface fluctuations, and noise may be generated. The degree of interference of external factors on the collected water pressure data in different time periods may be different, so the degree of noise influence may be different. When using wavelet transform to denoise the collected water pressure data, it is necessary to decompose the analyzed signal data. The number of decomposition layers when decomposing the signal will affect the denoising accuracy of the final data. One of the key factors for the number of decomposition layers when decomposing the signal is the degree of noise influence on the collected signal. If the collected signal is greatly affected by noise, more wavelet decomposition layers are usually required, which can better separate the noise components in the signal, so that the noise components are more concentrated in the high-frequency part, and the signal components are more concentrated in the low-frequency part. By increasing the number of wavelet decomposition layers, the noise can be separated more in frequency, so that the energy of the noise is more concentrated in the high-frequency details, thereby better suppressing or removing the noise in the collected water pressure data. Therefore, in order to more accurately remove the noise in the collected water pressure data, it is necessary to analyze the degree of noise influence on the collected water pressure data, so as to determine a more accurate number of decomposition layers.

[0049] In this embodiment, the water pressure data in the water pressure data sequence is firstly curve-fitted, and the curve obtained at this time is recorded as the water pressure data curve, wherein the horizontal coordinate of the water pressure data curve is time and the vertical coordinate is the water pressure data. Curve fitting is an existing method and will not be described in detail here. In order to obtain the characteristic information of the water pressure signal, the water pressure data curve is decomposed by the time series decomposition algorithm (Seasonal and Trend decomposition using Loess, STL) to obtain the corresponding seasonal term curve and residual curve. The STL decomposition algorithm is an existing technology and will not be described in detail here. Next, the degree of interference of the water pressure data sequence with noise and the degree of interference of the residual curve with noise will be evaluated according to the fluctuation of the data on the water pressure data sequence or the residual curve, and the noise degree evaluation value of the water pressure data sequence and the noise degree evaluation value of the residual curve will be obtained respectively.

[0050] Specifically, the difference between each water pressure data and other water pressure data in the water pressure data sequence is calculated; the ratio between the number of water pressure data identical to each water pressure data in the water pressure data sequence and the number of water pressure data in the water pressure data sequence is respectively taken as the number proportion of each water pressure data in the water pressure data sequence; the standard deviation of all water pressure data in the water pressure data sequence is calculated; according to the difference between each water pressure data and other water pressure data in the water pressure data sequence, the number proportion and the standard deviation of all water pressure data in the water pressure data sequence, the noise level evaluation value of the water pressure data sequence is obtained, the difference between each water pressure data and other water pressure data and the standard deviation of all water pressure data in the water pressure data sequence are both positively correlated with the noise level evaluation value of the water pressure data sequence, and the number proportion is negatively correlated with the noise level evaluation value of the water pressure data sequence. Among them, a positive correlation relationship indicates that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, or the power of an exponential function, which is determined by actual applications; a negative correlation relationship indicates that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual applications. As a specific implementation method, a specific calculation formula for the noise level evaluation value of the water pressure data sequence is given. The calculation formula for the noise level evaluation value of the water pressure data sequence is:

[0051] ;

[0052] Among them, Q represents the noise level evaluation value of the water pressure data sequence, M represents the number of water pressure data in the water pressure data sequence, and F i represents the i-th water pressure data in the water pressure data sequence, F i,s represents the sth water pressure data in the water pressure data sequence except the ith water pressure data, N i represents the number of water pressure data in the water pressure data sequence that are the same as the i-th water pressure data, σ represents the standard deviation of all water pressure data in the water pressure data sequence, exp( ) represents an exponential function with a natural constant as the base, and || represents the absolute value sign.

[0053] |F i -F i,s | represents the numerical difference between the i-th water pressure data and the s-th water pressure data except the i-th water pressure data in the water pressure data sequence, It represents the average difference between the ith water pressure data in the water pressure data sequence and all water pressure data except the ith water pressure data. If the ith water pressure data in the water pressure data sequence is noise data, the difference between the ith water pressure data and other water pressure data should be large. Therefore, the larger the average difference, the greater the degree to which the ith water pressure data is affected by noise. It represents the mean of the overall difference between all water pressure data and other water pressure data in the water pressure data sequence, and is used to reflect the degree to which all collected water pressure data are affected by noise. The larger the value, the greater the degree to which the collected water pressure data as a whole is affected by noise. It represents the proportion of the i-th water pressure data in the water pressure data sequence. The smaller the value, the more likely the i-th water pressure data is to be noise data. It represents the average value of the proportion of all water pressure data in the water pressure data sequence. The larger the value, the greater the degree of influence of noise on the collected water pressure data. The standard deviation of all water pressure data in the water pressure data sequence is used to reflect the degree of fluctuation of water pressure data in the current time period. The larger the standard deviation, the greater the fluctuation of water pressure data in the current time period, and the greater the possibility of noise interference on the collected water pressure data. When the mean of the overall difference between all water pressure data and other water pressure data in the water pressure data sequence is larger, the standard deviation of all water pressure data in the water pressure data sequence is larger, and the average value of the proportion of all water pressure data in the water pressure data sequence is smaller, it means that the water pressure data in the current time period is more affected by noise during collection, that is, the noise level evaluation value of the water pressure data sequence is larger.

[0054] The calculation method of the noise level evaluation value of the analog water pressure data series is used to calculate the noise level evaluation value of the residual curve according to the fluctuation of the data on the residual curve. The specific calculation formula of the noise level evaluation value of the residual curve is:

[0055] ;

[0056] Among them, Q c Represents the noise level evaluation value of the residual curve, R represents the number of residual data on the residual curve, represents the rth residual data on the residual curve, Represents the tth residual data on the residual curve except the rth residual data, Represents the number of residual data on the residual curve that is the same as the rth residual data, σ c It represents the standard deviation of the residual data corresponding to all the acquisition moments on the residual curve, exp( ) represents the exponential function with the natural constant as the base, and || represents the absolute value sign.

[0057] By using the above method, the noise level evaluation value of the water pressure data sequence and the noise level evaluation value of the residual curve are obtained. The collected water pressure data may have multiple frequencies and periodic changes, which may cause the estimated value of the noise level of the collected original data to be too large, that is, the noise level evaluation value of the water pressure data sequence is too large. Then, there may be a certain error in judging the number of decomposition layers of the collected water pressure signal according to the noise level. Therefore, it is necessary to further analyze the characteristics of the collected original water pressure signal and make certain corrections to the noise level evaluation value, so as to obtain a more accurate noise impact degree and then determine a more accurate number of decomposition layers.

[0058] Specifically, the amplitudes of all maximum points on the seasonal term curve constitute a maximum set, and the amplitudes of all minimum points on the seasonal term curve constitute a minimum set; the standard deviation of all data values ​​in the maximum set and the standard deviation of all data values ​​in the minimum set are calculated respectively; every two adjacent extreme points on the seasonal term curve constitute an extreme point pair, that is, multiple extreme point pairs are obtained, each of which contains a maximum point and a minimum point; the time interval between the two extreme points in each extreme point pair is obtained, recorded as the time interval of each extreme point pair; according to the difference between the time interval of each extreme point pair and the average value of the time intervals of all extreme point pairs, the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the standard deviation of all data values ​​in the maximum set and the standard deviation of all data values ​​in the minimum set, the correction coefficient of the noise level evaluation value is obtained. The specific calculation formula for the correction coefficient of the noise level evaluation value is:

[0059] ;

[0060] Among them, Y represents the correction coefficient of the noise level evaluation value, Q represents the noise level evaluation value of the water pressure data sequence, and Q c represents the noise level evaluation value of the residual curve, U represents the number of extreme point pairs, d(u) represents the time interval of the uth extreme point pair, represents the average value of the time intervals between all pairs of extreme points, Represents the standard deviation of all data values ​​in the maximum value set, represents the standard deviation of all data values ​​in the minimum set, e represents a natural constant, || represents the absolute value sign, and norm() represents the normalization function.

[0061] It represents the average difference between the time interval of two extreme points in all extreme point pairs in the seasonal term curve and the average time interval. The larger the value is, the higher the frequency richness of the signal in the water pressure data sequence is. Then the signal change of the collected water pressure data may be a normal periodic change, rather than caused by excessive noise. Therefore, the larger the value is, the larger the correction coefficient of the noise level evaluation value is, and the greater the correction degree is. It represents the mean of the standard deviation of all data values ​​in the maximum value set and the standard deviation of all data values ​​in the minimum value set, which is used to reflect the degree of dispersion of data in the maximum value set and the minimum value set. The larger the value, the more likely the water pressure data is to change with the periodic change, that is, the change in water pressure may be due to the normal periodic change of water level rise or fall. The smaller the degree of noise influence, the larger the correction coefficient of the noise level evaluation value. c | represents the difference between the noise level evaluation value of the water pressure data sequence and the noise level evaluation value of the residual curve. Since the residual curve may contain more large noise signals or other random signals, the greater the difference between the noise level evaluation value of the residual curve and the noise level evaluation value of the water pressure data sequence, the greater the correction coefficient of the noise level evaluation value.

[0062] So far, this embodiment has obtained the noise level evaluation value of the water pressure data sequence and the correction coefficient of the noise level evaluation value.

[0063] Step S3, obtaining the decomposition parameters of the water pressure data sequence based on the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum point and the minimum point on the seasonal term curve; and determining the number of decomposition layers corresponding to the water pressure data sequence based on the decomposition parameters.

[0064] Taking into account that the collected water pressure signal may have multiple frequencies and periodic changes, the estimated value of the noise level of the water pressure data may be too large, that is, the noise level evaluation value of the water pressure data series is too large. There may be certain errors when judging the number of decomposition layers of the collected water pressure data series based on the noise level evaluation value of the water pressure data series. Therefore, it is necessary to further analyze the characteristics of the collected original signal and make certain corrections to the noise level evaluation value of the water pressure data series, so as to obtain a more accurate degree of noise influence and then determine a more accurate number of decomposition layers.

[0065] Specifically, in step S2, this embodiment has constructed a maximum value set and a minimum value set. Next, this embodiment records the difference between the mean of the data values ​​in the maximum value set and the mean of the data values ​​in the minimum value set as the extreme value difference; according to the extreme value difference, the correction coefficient and the noise level evaluation value of the water pressure data sequence, the decomposition parameter of the water pressure data sequence is obtained. The extreme value difference and the noise level evaluation value of the water pressure data sequence are both positively correlated with the decomposition parameter, and the correction coefficient is negatively correlated with the decomposition parameter. Among them, the positive correlation relationship means that the dependent variable will increase as the independent variable increases, and the dependent variable will decrease as the independent variable decreases. The specific relationship can be a multiplication relationship, an addition relationship, and the power of an exponential function, which is determined by actual application; the negative correlation relationship means that the dependent variable will decrease as the independent variable increases, and the dependent variable will increase as the independent variable decreases. It can be a subtraction relationship, a division relationship, etc., which is determined by actual application. As a specific implementation method, a specific calculation formula for the decomposition parameter of the water pressure data sequence is given:

[0066] ;

[0067] Where W represents the decomposition parameter of the water pressure data series, norm( ) represents the normalization function, Q represents the noise level evaluation value of the water pressure data series, and Y represents the correction coefficient of the noise level evaluation value. represents the mean of the data values ​​in the maximum value set, Represents the mean of the data values ​​in a set of very small values.

[0068] Q×(1-Y) represents the noise level after the noise level evaluation value of the water pressure data sequence is corrected. The larger the value is, the larger the number of layers of decomposition of the collected water pressure data signal should be. It represents the extreme value difference, which is used to reflect the difference between the average amplitude of all maximum values ​​and the average amplitude of all minimum values, that is, it reflects the overall vibration amplitude of the collected water pressure signal. The vibration amplitude of the water pressure signal reflects the strength and energy of the signal. If the vibration amplitude of the water pressure signal is large, more levels of wavelet decomposition are required to fully represent the changes and details of the signal. Therefore, the larger the extreme value difference, the more decomposition levels of the water pressure data sequence should be.

[0069] In this embodiment, the product of the decomposition parameter and the hyperparameter of the preset number of decomposition levels is rounded up to determine the number of decomposition levels corresponding to the water pressure data sequence; wherein the hyperparameter of the preset number of decomposition levels is a positive integer, and in this embodiment, the hyperparameter of the preset number of decomposition levels is 10. In specific applications, the implementer can set it according to specific circumstances. The specific calculation formula for the number of decomposition levels corresponding to the water pressure data sequence is:

[0070] ;

[0071] Among them, Z represents the number of decomposition layers corresponding to the water pressure data sequence, W represents the decomposition parameter of the water pressure data sequence, and R represents the hyperparameter of the preset number of decomposition layers. Indicates the round-up symbol.

[0072] So far, the decomposition level number corresponding to the water pressure data sequence is obtained by using the method provided in this embodiment, and subsequently the data in the water pressure data sequence will be subjected to wavelet transform based on the decomposition level number.

[0073] Step S4, based on the number of decomposition layers, the water pressure data sequence is processed by wavelet transform to obtain denoised water pressure data, and the operation of the water conservancy sluice station is managed based on the denoised water pressure data.

[0074] In this embodiment, the number of decomposition levels of the water pressure data sequence is determined in step S3. Next, the water pressure data in the water pressure data sequence is subjected to wavelet transform processing based on the number of decomposition levels to remove noise interference and further manage the operation of the water conservancy sluice station.

[0075] Specifically, the number of decomposition layers of the water pressure data sequence is used as the number of decomposition layers during wavelet transform processing, and the water pressure data in the water pressure data sequence is decomposed by wavelet transform to obtain each component signal, and then each component signal is denoised and the component signal is reconstructed to obtain the denoised water pressure data. Since the process of denoising the data signal by wavelet transform is a well-known technology, it will not be described in detail here.

[0076] The denoised water pressure data is used as the input of the Autoregressive Integrated Moving Average Model (ARIMA) to obtain the water pressure prediction value at the next moment, that is, to predict the water pressure data at the future moment; the ARIMA prediction model is an existing prediction model and will not be described in detail here. If the difference between the water pressure prediction value at the next moment and the water pressure data at the current moment is greater than the preset first threshold, it means that the water pressure data at the next moment has increased, and there may be a rise in the water level. In order to prevent the water conservancy station from being overly stressed, it is necessary to increase the discharge volume in advance to reduce the pressure on the water conservancy station caused by the water pressure; it should be noted that the difference between the water pressure prediction value at the next moment and the water pressure data at the current moment is the difference obtained by subtracting the water pressure data at the current moment from the water pressure prediction value at the next moment; on the contrary, if the difference between the water pressure prediction value at the next moment and the water pressure data at the current moment is less than or equal to the preset first threshold, the discharge volume is reduced to ensure the reserve of water resources and avoid waste of resources, thereby realizing the reasonable management of water resources during the operation of the water conservancy station. In this embodiment, the preset first threshold is 0. In specific applications, the implementer can set it according to specific circumstances.

[0077] So far, the method provided in this embodiment has been used to achieve reasonable management of the operation of the water conservancy sluice station.

[0078] In this embodiment, it is considered that when the water pressure data sequence of the collected water conservancy sluice station is decomposed and denoised by wavelet transform, the degree to which the water pressure signal at different times is affected by noise may be different, and the number of decomposition layers is related to the noise level of the collected water pressure data. Therefore, it is necessary to estimate the noise level of the water pressure data sequence. In this embodiment, the noise level of the water pressure data sequence is first estimated as a whole to obtain a noise level evaluation value of the water pressure data sequence. The noise level evaluation value of the water pressure data sequence may be related to the change of the regularity of the collected signal. Therefore, the noise level evaluation value of the water pressure data sequence may not be accurate enough. The water pressure data sequence is further decomposed to obtain a seasonal term curve and a residual curve. By further analyzing the characteristics of the seasonal term curve and the residual curve, a correction coefficient of the noise level evaluation value is obtained. At the same time, the noise level evaluation value of the water pressure data sequence is corrected in combination with the amplitude difference between the maximum point and the minimum point on the seasonal term curve to obtain the number of decomposition layers corresponding to the water pressure data sequence, and then it is decomposed and denoised, thereby effectively removing the noise, ensuring the denoising effect of the water pressure data of the water conservancy sluice station, and improving the credibility and accuracy of the operation and management of the water conservancy sluice station.

[0079] An implementation example of a water conservancy sluice station operation management system based on an IOT data center:

[0080] In this embodiment, a water conservancy sluice station operation management system based on the IOT data center includes a memory and a processor, and the processor executes a computer program stored in the memory to implement the above-mentioned water conservancy sluice station operation management method based on the IOT data center.

[0081] Since a method for operating and managing a water conservancy gate station based on an IOT data middle station has been described in an embodiment of a method for operating and managing a water conservancy gate station based on an IOT data middle station, this embodiment will no longer repeat a method for operating and managing a water conservancy gate station based on an IOT data middle station.

[0082] It should be noted that the above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A water conservancy sluice station operation management method based on IOT data center, characterized in that: The method comprises the following steps: Obtain the water pressure data sequence of the water conservancy sluice station in the current time period collected by the IOT device; Decomposing the water pressure data sequence to obtain the corresponding seasonal term curve and residual curve; obtaining the noise level evaluation value of the water pressure data sequence and the noise level evaluation value of the residual curve according to the fluctuation of the data on the water pressure data sequence or the residual curve; obtaining the correction coefficient of the noise level evaluation value according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve; Based on the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum point and the minimum point on the seasonal term curve, the decomposition parameter of the water pressure data sequence is obtained; based on the decomposition parameter, the number of decomposition layers corresponding to the water pressure data sequence is determined; Processing the water pressure data sequence using wavelet transform based on the decomposition layer number to obtain denoised water pressure data, and managing the operation of the water conservancy sluice station based on the denoised water pressure data; According to the fluctuation of the data in the water pressure data sequence, the noise level evaluation value of the water pressure data sequence is obtained, including: Calculate the difference between each water pressure data and other water pressure data in the water pressure data sequence; take the ratio between the number of water pressure data identical to each water pressure data in the water pressure data sequence and the number of water pressure data in the water pressure data sequence as the number ratio of each water pressure data in the water pressure data sequence; calculate the standard deviation of all water pressure data in the water pressure data sequence; According to the difference between each water pressure data and other water pressure data in the water pressure data sequence, the quantity proportion and the standard deviation of all water pressure data in the water pressure data sequence, the noise level evaluation value of the water pressure data sequence is obtained, the difference between each water pressure data and other water pressure data and the standard deviation of all water pressure data in the water pressure data sequence are both positively correlated with the noise level evaluation value of the water pressure data sequence, and the quantity proportion is negatively correlated with the noise level evaluation value of the water pressure data sequence; The noise level evaluation value of the water pressure data sequence is calculated using the following formula: ; Among them, Q represents the noise level evaluation value of the water pressure data sequence, M represents the number of water pressure data in the water pressure data sequence, and F i represents the i-th water pressure data in the water pressure data sequence, F i,s represents the sth water pressure data in the water pressure data sequence except the ith water pressure data, N i represents the number of water pressure data in the water pressure data sequence that is the same as the i-th water pressure data, σ represents the standard deviation of all water pressure data in the water pressure data sequence, exp( ) represents an exponential function with a natural constant as the base, and | | represents the absolute value sign; Decomposing the water pressure data sequence to obtain corresponding seasonal term curves and residual curves includes: Performing curve fitting on the water pressure data in the water pressure data sequence to obtain a water pressure data curve, wherein the abscissa of the water pressure data curve is time; Decomposing the water pressure data curve by using the STL decomposition algorithm to obtain the corresponding seasonal term curve and residual curve; The correction coefficient of the noise level evaluation value is obtained according to the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the position distribution and the discrete degree of the extreme value points on the seasonal term curve, including: The amplitudes of all maximum points on the seasonal term curve constitute a maximum set, and the amplitudes of all minimum points on the seasonal term curve constitute a minimum set; calculate the standard deviation of all data values ​​in the maximum set and the standard deviation of all data values ​​in the minimum set respectively; Every two adjacent extreme value points on the seasonal term curve constitute an extreme value point pair; obtain the time interval between the two extreme value points in each extreme value point pair, and record it as the time interval of each extreme value point pair; According to the difference between the time interval of each extreme value point pair and the average value of the time interval of all extreme value point pairs, the difference in the noise level evaluation value between the water pressure data sequence and the residual curve, the standard deviation of all data values ​​in the maximum value set and the standard deviation of all data values ​​in the minimum value set, a correction coefficient of the noise level evaluation value is obtained; The correction coefficient of the noise level evaluation value is calculated using the following formula: ; Among them, Y represents the correction coefficient of the noise level evaluation value, Q represents the noise level evaluation value of the water pressure data sequence, and Q c represents the noise level evaluation value of the residual curve, U represents the number of extreme point pairs, d(u) represents the time interval of the uth extreme point pair, represents the average value of the time intervals between all pairs of extreme points, Represents the standard deviation of all data values ​​in the maximum value set, represents the standard deviation of all data values ​​in the minimum value set, e represents a natural constant, | | represents the absolute value symbol, and norm() represents the normalization function; The decomposition parameters of the water pressure data sequence are obtained based on the noise level evaluation value of the water pressure data sequence, the correction coefficient and the amplitude difference between the maximum point and the minimum point on the seasonal term curve, including: The difference between the mean of the data values ​​in the maximum value set and the mean of the data values ​​in the minimum value set is recorded as the extreme value difference; According to the extreme value difference, the correction coefficient and the noise level evaluation value of the water pressure data sequence, a decomposition parameter of the water pressure data sequence is obtained, wherein the extreme value difference and the noise level evaluation value of the water pressure data sequence are both positively correlated with the decomposition parameter, and the correction coefficient is negatively correlated with the decomposition parameter; The step of determining the number of decomposition layers corresponding to the water pressure data sequence based on the decomposition parameter comprises: The result of rounding up the product of the decomposition parameter and the hyperparameter of the preset number of decomposition layers is determined as the number of decomposition layers corresponding to the water pressure data sequence; wherein the hyperparameter of the preset number of decomposition layers is a positive integer; The noise level evaluation value of the residual curve is calculated using the following formula: ; Among them, Q c Represents the noise level evaluation value of the residual curve, R represents the number of residual data on the residual curve, represents the rth residual data on the residual curve, Represents the tth residual data on the residual curve except the rth residual data, Represents the number of residual data on the residual curve that is the same as the rth residual data, σ c It represents the standard deviation of the residual data corresponding to all the acquisition moments on the residual curve, exp( ) represents the exponential function with the natural constant as the base, and | | represents the absolute value sign.

2. According to claim 1, a water conservancy sluice station operation management method based on IOT data center is characterized in that: The step of obtaining the water pressure data sequence of the water conservancy sluice station collected by the IOT device within the current time period includes: The water pressure data of the water conservancy sluice station collected by the IOT device at each collection time in the current time period is obtained. The water pressure data of all collection times in the current time period constitute the water pressure data sequence in the current time period.

3. A water conservancy sluice station operation management system based on IOT data center, including a memory and a processor, characterized in that: The processor executes the computer program stored in the memory to implement a water conservancy sluice station operation management method based on the IOT data center as described in any one of claims 1-2.

Citation Information

Patent Citations

  • Biodegradable nonwoven fabric and use of same

    CA3228979A1

  • First-arrival travel time picking method and device for seismic signal comprising noise

    CN107272066A

  • Production process of high-density metal injection molding copper powder

    CN110216293A

  • Reliability identification and mining method for dam prototype observation data

    CN114595503A

  • IoT-based intelligent water quality monitoring method and system

    CN117990628A