CN117493778A - On-line monitoring method and system for associated data of water supply and drainage equipment - Google Patents
On-line monitoring method and system for associated data of water supply and drainage equipment Download PDFInfo
- Publication number
- CN117493778A CN117493778A CN202410004202.7A CN202410004202A CN117493778A CN 117493778 A CN117493778 A CN 117493778A CN 202410004202 A CN202410004202 A CN 202410004202A CN 117493778 A CN117493778 A CN 117493778A
- Authority
- CN
- China
- Prior art keywords
- data
- difference
- standard deviation
- temperature data
- water supply
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000012544 monitoring process Methods 0.000 title claims abstract description 48
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 title claims abstract description 46
- 238000012937 correction Methods 0.000 claims abstract description 46
- 230000008859 change Effects 0.000 claims abstract description 18
- 230000008569 process Effects 0.000 claims description 26
- 230000006870 function Effects 0.000 claims description 14
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000005259 measurement Methods 0.000 claims description 4
- 238000004590 computer program Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004422 calculation algorithm Methods 0.000 description 11
- 238000004364 calculation method Methods 0.000 description 7
- 239000006185 dispersion Substances 0.000 description 5
- 230000009466 transformation Effects 0.000 description 4
- 238000005070 sampling Methods 0.000 description 3
- 230000001419 dependent effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000005856 abnormality Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01D—MEASURING NOT SPECIALLY ADAPTED FOR A SPECIFIC VARIABLE; ARRANGEMENTS FOR MEASURING TWO OR MORE VARIABLES NOT COVERED IN A SINGLE OTHER SUBCLASS; TARIFF METERING APPARATUS; MEASURING OR TESTING NOT OTHERWISE PROVIDED FOR
- G01D21/00—Measuring or testing not otherwise provided for
- G01D21/02—Measuring two or more variables by means not covered by a single other subclass
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention relates to the technical field of data processing, in particular to an online monitoring method and an online monitoring system for associated data of water supply and drainage equipment, comprising the following steps: collecting monitoring data of water supply and drainage equipment; obtaining a local range of a first difference sequence of temperature data; obtaining a correction coefficient of a difference data point according to the change of the data in the local range; further obtaining the correction degree of the difference data points; correcting the correction degree and the amplitude of the difference data point to obtain a corrected first difference sequence, and obtaining the iteration range of the Gaussian white noise standard deviation according to the sequence; adding noise to the original data according to the iteration range to obtain a target signal; comparing the data change between the target signal and the temperature data to obtain the preference degree of the target signal; determining an optimal standard deviation according to the preference degree; and denoising the temperature data according to the optimal standard deviation, and monitoring the water supply and drainage equipment according to the denoised temperature data.
Description
Technical Field
The invention relates to the technical field of data processing, in particular to an online monitoring method and system for associated data of water supply and drainage equipment.
Background
When monitoring the related data of the water supply and drainage equipment, noise exists in the collected data, so that the collected temperature data needs to be subjected to denoising treatment. One commonly used method for denoising data is to denoise the IMF (eigenmode function) components after decomposition by EEMD (improved empirical mode decomposition).
In the prior art, the EEMD algorithm solves the problem of modal aliasing in the EMD (empirical mode decomposition) decomposition process by adding random white noise to the raw data (meaning that one IMF component consists of signals of different scales or one signal with a similar scale stays in different IMF components, the intention of EMD decomposition is that each IMF component corresponds to information of different frequencies in the raw signal, so that the true physical meaning of the IMF component is lost). However, when the algorithm is iterated, the standard deviation of the white noise is often not fixed, and different white noise also has great influence on the decomposition result, so that the accuracy of monitoring the water supply and drainage data is influenced.
Disclosure of Invention
In order to solve the problems, the invention provides an online monitoring method and an online monitoring system for associated data of water supply and drainage equipment.
The invention relates to an online monitoring method and an online monitoring system for associated data of water supply and drainage equipment, which adopts the following technical scheme:
the embodiment of the invention provides an online monitoring method for associated data of water supply and drainage equipment, which comprises the following steps:
collecting original data of water supply and drainage equipment; the original data comprise temperature data, rotating speed data and room temperature data;
obtaining a first difference sequence of temperature data, and selecting a local range of each difference data point in the first difference sequence; obtaining each difference data point according to the change of the data in the local rangeIs used for the correction coefficient of (a); obtaining each difference data point according to the data relation among the room temperature data, the rotating speed data and the temperature data and the correction coefficient>Is a correction degree of (a); according to difference data point->Is the correction degree and difference data point +.>Amplitude vs. difference data point->Correcting to obtain a corrected first difference sequence, and obtaining an iteration range of the Gaussian white noise standard deviation according to the corrected first difference sequence;
according to the iteration range of the Gaussian white noise standard deviation, the original data is subjected to noise adding to obtain a target signal; comparing the data change between the target signal and the temperature data to obtain the preference degree of the target signal; determining an optimal standard deviation according to the preference degree;
adding noise to the temperature data according to the optimal standard deviation to obtain noise-added temperature data; decomposing the noise temperature data to obtain a plurality of component signals; denoising each component signal to obtain a denoising signal of the component signal; reconstructing the denoising signal of the component signal to obtain denoising data of the temperature data; and monitoring the water supply and drainage equipment according to the denoised temperature data.
Further, the obtaining the first difference sequence of the temperature data, selecting a local range of each difference data point in the first difference sequence, includes:
taking the difference between two adjacent data points on the time sequence of the temperature data to obtain the difference value of the two data points, and forming a first difference sequence by all the difference value data; in the first difference sequence, for the firstDifference data points->Taking h difference data points which are adjacent in time sequence and take the difference data point as the center, and representing the difference data point +.>Is a preset number.
Further, each difference data point is obtained according to the change of the data in the local rangeComprises:
obtaining each difference data point by a first formulaIs used for the correction coefficient of (a); the first formula is:
，
in the method, in the process of the invention,representing the first difference sequenceDifference data point>Correction coefficient of->Representation->Variance of the difference data in the local range of (a); />Is indicated at->In the local range of->Amplitude of the difference data points in the fitted curve, +.>Is indicated at->Is>The size of the difference data points, +.>Representing the number of data points contained within the local range.
Further, each difference data point is obtained according to the data relationship among the room temperature data, the rotating speed data and the temperature data and the correction coefficientComprises:
obtaining each difference data point by a second formulaThe second formula is:
，
in the method, in the process of the invention,representing difference data points +.>Is (are) corrected by->Representing the difference data points in the first difference sequence +.>Is used for the correction of the coefficient of (c),is indicated at->Structural similarity of the fitted curve of temperature data and room temperature data in the local range of (2)>Is indicated at->Structural similarity of the fitted curve of temperature data and rotational speed data in a local range of (2)>Data representing room temperature>Representing temperature data, ++>Representing rotational speed data.
Further, the data points according to the difference valueIs the correction degree and difference data point +.>Amplitude vs. difference data point->Correcting to obtain a corrected first difference sequence, and obtaining an iteration range of the Gaussian white noise standard deviation according to the corrected first difference sequence, wherein the method comprises the following steps:
and correcting the difference data points in the first difference sequence by using correction coefficients based on a third formula, wherein the third formula is as follows:
，
in the method, in the process of the invention,indicate->Correction data for the individual difference data points, +.>Indicate->Difference data points>An exponential function that is based on a natural constant;
the correction data of all the difference data points form a corrected first difference sequence, and the maximum value and the minimum value of the difference data points in the corrected first difference sequence are obtained;
the time sequence of the abscissa corresponding to the maximum value and the minimum value of the difference data points is recorded asThe corresponding Gaussian white noise standard deviation is superimposedThe substitution range is->。
Further, the iteration range of the standard deviation of the Gaussian white noise is，/>For starting point of iteration, ++>For the end of the iteration, +.>Indicate->Multiple iterations(s)>The method comprises the steps of carrying out a first treatment on the surface of the First->Standard deviation after several iterations is +.>The method comprises the steps of carrying out a first treatment on the surface of the The step of adding noise to the original data according to the iteration range of the Gaussian white noise standard deviation to obtain a target signal comprises the following steps:
based on the original data of the temperature data, the standard deviation is added as followsThe Gaussian white noise of (2) is recorded as a target signal, and +.>Representing the minimum value of the difference data points in the modified first difference sequence.
Further, the comparing the data change between the target signal and the temperature data to obtain the preference degree of the target signal includes:
in the first placeAfter completion of the iteration, the target signal obtained +.>Performing EMD (empirical mode decomposition) on a target signal to obtain a plurality of IMF (inertial measurement unit) component signals, performing Fourier transform on the original data and each IMF component signal of the target signal based on Fourier transform to obtain a spectrogram of the original data and each IMF component signal, and comparing the difference between the original signal and each IMF component signal through a fourth formula to obtain the preference degree of the target signal, wherein the fourth formula is as follows:
，
in the method, in the process of the invention,indicate->Target signal after several iterations->Relative to the original data->Is used to determine the degree of preference of the (c),indicate->Maximum frequency in spectrogram of strip IMF component signal, < >>Indicate->Minimum frequency in spectrogram of strip IMF component signal, < >>Indicate->Curve function of continuous spectrogram corresponding to IMF component signal>Independent variables representing curve functions, similarly, < ->Curve function representing the continuous spectrogram of the original data, < >>Indicate->Target signal after several iterations->Is included in the IMF component signal.
Further, the determining the optimal standard deviation according to the preference degree includes:
obtaining target signals after each iterationAnd determining the iteration number when the preference degree is maximum, and determining the standard deviation of the iteration number as the optimal standard deviation.
Further, the temperature data is noisy according to the optimal standard deviation, and noisy temperature data is obtained; decomposing the noise temperature data to obtain a plurality of component signals; denoising each component signal to obtain a denoising signal of the component signal; reconstructing the denoising signal of the component signal to obtain denoising data of the temperature data; monitoring the water supply and drainage equipment according to the denoised temperature data, comprising:
according to the obtained optimal standard deviation, gaussian white noise corresponding to the optimal standard deviation is added into the original signalObtaining noise adding temperature data, performing EEMD (ensemble empirical mode decomposition) on the noise adding temperature data added with Gaussian white noise corresponding to the optimal standard deviation to obtain a plurality of IMF (inertial measurement unit) component signals, denoising each IMF component signal to obtain a denoising signal of the component signal, and reconstructing each denoised IMF component signal to obtain denoising data of the temperature data; temperature monitoring is carried out according to the denoised temperature data, and when the temperature data after any denoising is larger than a preset threshold valueAnd when the alarm is given.
The embodiment provides an online monitoring system for associated data of water supply and drainage equipment, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory so as to realize the online monitoring method for the associated data of the water supply and drainage equipment.
The technical scheme of the invention has the beneficial effects that: through adding Gaussian white noise with different standard deviations, the relation between the IMF component and the original data in the decomposition result under each standard deviation can be analyzed to obtain the optimal degree, so that the standard deviation selection of the self-adaptive Gaussian white noise is realized, and compared with the traditional mode of adding white noise by adopting a fixed experiment, the method can effectively process different temperature data, better solve the problem of modal aliasing and improve the efficiency of a monitoring system of water supply and drainage associated equipment. The iteration range of the Gaussian white noise can be determined by considering the change characteristics of the temperature data of the water supply and drainage equipment and the relation between the associated data, so that unnecessary iteration does not occur, the calculated amount is reduced, the algorithm efficiency is improved, the associated equipment for water supply and drainage can be better monitored, and the monitoring result is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a flow chart showing the steps of an online monitoring method for associated data of water supply and drainage equipment.
Detailed Description
In order to further describe the technical means and effects adopted by the invention to achieve the preset aim, the following is a detailed description of specific implementation, structure, characteristics and effects of the on-line monitoring method and system for related data of water supply and drainage equipment according to the invention in combination with the accompanying drawings and the preferred embodiment. In the following description, different "one embodiment" or "another embodiment" means that the embodiments are not necessarily the same. Furthermore, the particular features, structures, or characteristics of one or more embodiments may be combined in any suitable manner.
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.
The invention provides a specific scheme of an on-line monitoring method and system for associated data of water supply and drainage equipment, which are specifically described below with reference to the accompanying drawings.
Referring to fig. 1, a flowchart of a method for online monitoring related data of a water supply and drainage device according to an embodiment of the invention is shown, the method includes the following steps:
s001, arranging sensors and collecting multiple monitoring data;
the main purpose of the present invention is to denoise the monitoring data of the water supply and drainage equipment, so that the monitoring data of the water supply and drainage equipment needs to be obtained first. According to the invention, the temperature sensor is used for collecting the room temperature data and the temperature data of the equipment, the rotating speed sensor is used for collecting the rotating speed data of the fan blade of the water supply equipment, the sampling frequency is 10 seconds, the sampling time is 1 hour, and the data collecting time is 1 hour. And then, respectively performing curve fitting on the obtained room temperature data, temperature data and equipment rotating speed data through a polynomial fitting algorithm, and respectively marking the obtained fitting curves as:、/>、/>wherein->、/>Representing the dependent variable temperature, < >>Representing the argument time, ++>Representing the rotational speed of the dependent variable. The polynomial fitting algorithm is a prior art, and will not be described in detail herein, and the fitting curve used in this embodiment is a fifth order polynomial.
S002, determining an iteration range through the change characteristics of temperature data of the water supply and drainage equipment and the relation among all the associated data;
in denoising the temperature data of the device by the EEMD algorithm, the added gaussian white noise should be such that the amplitude of the white noise is small compared to the amplitude in the raw data of the device temperature to ensure that the noise does not mask the real components of the raw data. However, there may be individual noise data in the temperature data, resulting in an amplitude greater than that of the overall data change of the original data, which may result in an amplitude range of the original data being larger, thereby increasing the amount of calculation, and also in an overestimated standard deviation of the original data, thereby causing white noise estimated from the standard deviation of the original data to mask the real information of the original data. The amplitude range of the original data can be corrected by calculating the amplitude abnormality degree, so that the reliable iteration range of the Gaussian white noise standard deviation is obtained.
Specifically, for temperature data, i.e., raw data, two data points are obtained by differencing two data points that are adjacent in time seriesIs characterized by a local amplitude of the device temperature, and the difference is recorded as a first difference sequenceWherein->Representing the absolute value of the difference between the first temperature data and the second temperature data collected,/->Represents the number of differences (for 1 hour of data acquired, the sampling interval is 10 seconds, the number of data points is 600, the number of adjacent differences is 599, therefore +.>). Each data in the first sequence of differences is noted as a difference data point. The correction of the amplitude range can then be switched to the correction of the first difference sequence, since the final amplitude range is determined by the maximum and minimum values of the data corrected for the first difference sequence.
Further, in the first difference sequence, for the firstDifference data points->Taking the difference data point as the center and the adjacent parts in time sequence>Difference data points (including->If there are less than 11 then the corresponding truncations, e.g. the first difference data point then take 5 difference data points containing this point extending to the right), for example: in the first difference sequence, the adjacent 10 difference data points of the 20 th difference data point are +.>The data sequence composed of these difference data points is recorded as the current difference data point +.>Is a local range of (1) for difference data points->The correction process of (c) is performed in the local area. In the local range, the degree of dispersion of the difference data point size primarily represents the regularity of the data change in the range, because the temperature data fluctuation is relatively intense in the noise data range and the difference between the adjacent equipment temperatures is inconsistent, the corresponding degree of dispersion is represented as regularity in the local range, and the degree of dispersion can be represented by variance.
At the same time, the corresponding difference change can be regular when the temperature is increased normally, and the degree of dispersion can not well represent the regularity, so the difference data in the local range is utilized to carry out curve fitting and is recorded asThe method is characterized in that the loss in the fitting process is calculated, the change of the data in the noise range is irregular, and the occurrence of one noise point influences the fitting of other surrounding points in the fitting process, so that the fitting loss is larger, the regularity can be represented by using the fitting loss in the fitting process, the more the fitting loss in the local range is, the greater the probability that the difference belongs to noise is, and the larger the correction is needed for the difference data point. The calculation formula of the correction coefficient is as follows:
，
in the method, in the process of the invention,representing the difference data points in the first difference sequence +.>Correction coefficient of->Representation->Variance of the difference data in the local range of (a); />Is indicated at->In the local range of->Amplitude of the difference data points in the fitted curve, +.>Is indicated at->Is>The size of the difference data points, +.>Representing the number of data points contained within the local range. />Representing the loss during fitting in a local range, it can be seen that the higher the degree of dispersion, the higher the fitting loss, the higher the correction coefficient.
Further, the influence of the room temperature and the rotating speed on the temperature of the water supply and drainage equipment is closely related in the monitoring process of the water supply and drainage equipment. For example, the higher the rotational speed of the device, the more heat generated by friction, resulting in an increase in the temperature of the device. The change in the room temperature data and the rotational speed data can be used to make corrections to its correction coefficients, since the correction coefficients are calculated based on the temperature data, and the room temperature and rotational speed can reflect the reliability of the temperature data. The specific implementation process is as follows:
for difference data pointsThe local range of (2) contains difference data points in the corresponding time range of the original temperature data of +.>If the temperature data and the rotation speed data in the time range are changed to be consistent with the temperature data, the reliability of the temperature data in the time range is higher, and the correction coefficient is higher. The calculation formula of the correction process of the correction coefficient is as follows:
，
in the method, in the process of the invention,representing difference data points +.>Is (are) corrected by->Representing the difference data points in the first difference sequence +.>Is used for the correction of the coefficient of (c),is indicated at->Structural similarity of the fitted curve of temperature data and room temperature data in the local range of (2)>Is indicated at->The calculation of the structural similarity is known in the prior art, and is not described herein in detail. Because of->The value of the function ranges from-1 to 1, and the addition of 1 ensures that the correction process is not negative.
As can be seen from the above equation, the higher the structural similarity with the room temperature data and the rotational speed data, the higher the reliability of the temperature data, and thus the higher the reliability of the correction coefficient calculated based on the temperature data. And then correcting the difference data points in the first difference sequence by using correction coefficients, wherein the calculation formula is as follows:
，
in the method, in the process of the invention,indicate->Correction data for the individual difference data points, +.>Indicate->Difference data points>An exponential function based on a natural constant is represented.
Further, the correction data of all the difference data points are recorded as a corrected first difference sequence, the maximum value and the minimum value of the difference data points in the corrected first difference sequence are obtained, and the time sequence of the abscissa corresponding to the maximum value and the minimum value of the difference data points is recorded asI.e. the amplitude range of the temperature data is +.>The iteration range of the standard deviation of the corresponding Gaussian white noise is +.>（/>One decimal fraction is retained by rounding), the determination of this iteration range is a known technique, and will not be described in detail here.
So far, the iteration range of the Gaussian white noise standard deviation is calculated through the relation between the change characteristics of the temperature data and each associated data.
S003, iterating the standard deviation of Gaussian white noise according to the determined iteration range to obtain the optimal degree;
according to the iteration range of the obtained standard deviation of the Gaussian white noise, in the iteration process, the preference degree of the corresponding noise adding data when white noise with different standard deviation sizes is added needs to be determined, and if the corresponding relation between the noise adding data and the original signal is better in a certain iteration process, the preference degree is higher. After the iteration is finished, selecting the standard deviation with the highest degree of preference as the optimal standard deviation, and taking the optimal standard deviation as the finally added Gaussian white noise standard deviation. The specific implementation process is as follows:
from Gaussian white noise standard deviation ofStarting to iterate until the standard deviation of Gaussian white noise is equal to +.>After each iteration is completed, the preference degree of the data after each addition of gaussian white noise is calculated. The process comprises the following steps: first of all, the raw data of the temperature data +.>On the basis of (1) plus standard deviation +.>In the formula, < + >, is shown in the formula>Indicate->Standard deviation at multiple iterations ∈ ->. The data signal added with Gaussian white noise is marked as a target signal +.>. For example: the original data signal after the first iteration is marked as target signal +.>. And then EMD decomposition is carried out on the target signal to obtain a plurality of IMF component signals. And then carrying out Fourier transformation on each IMF component signal of the original data and the target signal by utilizing Fourier transformation to obtain spectrograms of the original signal and each IMF component signal. The above EMD algorithm and fourier transform algorithm are well known in the art, and will not be described herein. Then the target signal preference degree is obtained by comparing the difference between the original signal and each IMF component signal to +.>Target signal after several iterations->And target signal->The optimization degree is calculated by taking a plurality of IMF component signals and spectrograms of the IMF component signals as examples;
the calculation formula of the preference degree is as follows:
，
in the method, in the process of the invention,indicate->Target signal after several iterations->Relative to the original data->Is used to determine the degree of preference of the (c),indicate->Maximum frequency in spectrogram of strip IMF component signal, < >>Indicate->Minimum frequency in spectrogram of strip IMF component signal, < >>Indicate->The curve function of the continuous spectrogram corresponding to the IMF component signal can be obtained by using a polynomial fitting algorithm, and the technology is the prior art and will not be described in detail herein. Similarly, let go of>Curve function representing the continuous spectrogram of the original data, < >>Indicate->Target signal after several iterations->Is included in the IMF component signal.
In particular, the method comprises the steps of,indicate->The smaller the frequency range of the IMF component signal, the more concentrated the frequency of the IMF component in the original signal, the less the possibility of modal aliasing, and the higher the preference thereof, and the negative correlation is. />Indicate->Average amplitude of the strip IMF component signal, +.>Representing the corresponding original data in the frequency range +.>An average amplitude within; since the physical meaning of the definite integral is to take the area of the objective function of the closed interval, the value of +.>Summing the magnitudes corresponding to all of its frequencies, i.e. representing the area of the interval, thus dividing by the length of the data interval +.>The average amplitude of the data in the data interval is indicated. />Indicate->The IMF component signal is in the data intervalMean amplitude in and raw data>In the data interval +.>The difference in average amplitude in the first and second frequency ranges represents the first and second frequency ranges>The amplitude of the IMF component signal in the frequency range is consistent with the amplitude of the IMF component signal in the corresponding frequency range in the original data, and the larger the difference value is, the better the consistency is. Then, the difference values of all IMF component signals relative to the original signal are averaged to obtain the +.>Target signal after several iterations->Preference with respect to the original signal.
Target signal after each iteration obtained from the above calculationThe degree of preference with the original data, that is, the degree of preference of the target signal after adding different white gaussian noise, and then the iteration number when the degree of preference is maximum is obtained, and the standard deviation when the iteration number is recorded as the optimal standard deviation.
Thus, the best standard deviation is obtained.
S004, gaussian white noise with the optimal standard deviation is added to the original data, so that the monitoring data is denoised;
according to the obtained optimal standard deviation, adding Gauss corresponding to the optimal standard deviation into the original signalWhite noise, EEMD (ensemble empirical mode decomposition) is carried out on the signal added with the Gaussian white noise corresponding to the optimal standard deviation to obtain each IMF (inertial measurement unit) component signal, then each component is denoised, and further each IMF component signal after denoising is reconstructed. When each IMF component signal is denoised, a wavelet transformation algorithm is used, and when the denoised IMF component signal is reconstructed, a least square method is used, wherein the wavelet transformation algorithm and the least square method are both prior known techniques, and no description is repeated here. The reconstructed data is the data after denoising the temperature data, then the temperature monitoring is carried out according to the denoised temperature data, and when the temperature data is larger than a preset threshold valueWhen the temperature of the device is abnormal, an alarm is given, and in the implementation, the alarm is taken +.>The threshold value is an empirical threshold value at the temperature, and an implementer can set the threshold value according to different implementation environments.
Through the steps, the online monitoring method for the associated data of the water supply and drainage equipment is completed.
The invention also provides an online monitoring system for the related data of the water supply and drainage equipment, which comprises a memory and a processor, wherein the processor executes a computer program stored in the memory so as to realize the online monitoring method for the related data of the water supply and drainage equipment.
The above description is only of the preferred embodiments of the present invention and is not intended to limit the invention, but any modifications, equivalent substitutions, improvements, etc. within the principles of the present invention should be included in the scope of the present invention.
Claims (10)
1. The online monitoring method for the associated data of the water supply and drainage equipment is characterized by comprising the following steps of:
collecting original data of water supply and drainage equipment; the original data comprise temperature data, rotating speed data and room temperature data;
obtaining a first sequence of differences of temperature data, selecting a firstA local range for each difference data point in a difference sequence; obtaining each difference data point according to the change of the data in the local rangeIs used for the correction coefficient of (a); obtaining each difference data point according to the data relation among the room temperature data, the rotating speed data and the temperature data and the correction coefficient>Is a correction degree of (a); according to difference data point->Is the correction degree and difference data point +.>Amplitude vs. difference data point->Correcting to obtain a corrected first difference sequence, and obtaining an iteration range of the Gaussian white noise standard deviation according to the corrected first difference sequence;
according to the iteration range of the Gaussian white noise standard deviation, the original data is subjected to noise adding to obtain a target signal; comparing the data change between the target signal and the temperature data to obtain the preference degree of the target signal; determining an optimal standard deviation according to the preference degree;
adding noise to the temperature data according to the optimal standard deviation to obtain noise-added temperature data; decomposing the noise temperature data to obtain a plurality of component signals; denoising each component signal to obtain a denoising signal of the component signal; reconstructing the denoising signal of the component signal to obtain denoising data of the temperature data; and monitoring the water supply and drainage equipment according to the denoised temperature data.
2. The method for online monitoring of water supply and drainage equipment related data according to claim 1, wherein the obtaining the first difference sequence of temperature data, selecting the local range of each difference data point in the first difference sequence, comprises:
taking the difference between two adjacent data points on the time sequence of the temperature data to obtain the difference value of the two data points, and forming a first difference sequence by all the difference value data; in the first difference sequence, for the firstDifference data points->Taking h difference data points which are adjacent in time sequence and take the difference data point as the center, and representing the difference data point +.>Is a preset number.
3. The method for online monitoring of related data of water supply and drainage equipment according to claim 1, wherein each difference data point is obtained according to the change of the data in the local rangeComprises:
obtaining each difference data point by a first formulaIs used for the correction coefficient of (a); the first formula is:
，
in the method, in the process of the invention,representing the difference data points in the first difference sequence +.>Correction coefficient of->Representation->Variance of the difference data in the local range of (a); />Is indicated at->In the local range of->The magnitudes of the individual difference data points in the fitted curve,is indicated at->Is>The size of the difference data points, +.>Representing the number of data points contained within the local range.
4. The method for online monitoring of related data of water supply and drainage equipment according to claim 1, wherein each difference data point is obtained according to a data relationship among room temperature data, rotation speed data and temperature data and a correction coefficientComprises:
obtaining each difference data point by a second formulaThe second formula is:
，
in the method, in the process of the invention,representing difference data points in a first sequence of difference values obtained from data relationships of different types of monitored dataIs (are) corrected by->Representing the difference data points in the first difference sequence +.>Correction coefficient of->Is indicated at->Structural similarity of the fitted curve of temperature data and room temperature data in the local range of (2)>Is indicated at->Structural similarity of the fitted curve of temperature data and rotational speed data in a local range of (2)>The data representing room temperature is shown in the table,representing temperature data, ++>Representing rotational speed data.
5. The method for online monitoring of water supply and drainage equipment related data according to claim 1, wherein the data points are based on difference valuesIs the correction degree and difference data point +.>Amplitude vs. difference data point->Correcting to obtain a corrected first difference sequence, and obtaining an iteration range of the Gaussian white noise standard deviation according to the corrected first difference sequence, wherein the method comprises the following steps:
and correcting the difference data points in the first difference sequence by using correction coefficients based on a third formula, wherein the third formula is as follows:
，
in the method, in the process of the invention,indicate->Correction data for the individual difference data points, +.>Indicate->Difference data points>An exponential function that is based on a natural constant;
the correction data of all the difference data points form a corrected first difference sequence, and the maximum value and the minimum value of the difference data points in the corrected first difference sequence are obtained;
the time sequence of the abscissa corresponding to the maximum value and the minimum value of the difference data points is recorded asThe iteration range of the standard deviation of the corresponding Gaussian white noise is +.>。
6. The online monitoring method for associated data of water supply and drainage equipment according to claim 1, wherein the iteration range of the standard deviation of the white gaussian noise is，/>For starting point of iteration, ++>For the end of the iteration, +.>Indicate->A number of iterations of the process are performed,the method comprises the steps of carrying out a first treatment on the surface of the First->Standard deviation after several iterations is +.>The method comprises the steps of carrying out a first treatment on the surface of the The step of adding noise to the original data according to the iteration range of the Gaussian white noise standard deviation to obtain a target signal comprises the following steps:
based on the original data of the temperature data, the standard deviation is added as followsThe Gaussian white noise of (2) is recorded as a target signal, and +.>Representing the minimum value of the difference data points in the modified first difference sequence.
7. The method for online monitoring of water supply and drainage equipment related data according to claim 6, wherein the step of comparing the data change between the target signal and the temperature data to obtain the preference degree of the target signal comprises the steps of:
in the first placeAfter completion of the iteration, the target signal obtained +.>Performing EMD (empirical mode decomposition) on a target signal to obtain a plurality of IMF (inertial measurement unit) component signals, performing Fourier transform on the original data and each IMF component signal of the target signal based on Fourier transform to obtain a spectrogram of the original data and each IMF component signal, and comparing the difference between the original signal and each IMF component signal through a fourth formula to obtain the preference degree of the target signal, wherein the fourth formula is as follows:
，
in the method, in the process of the invention,indicate->Target signal after several iterations->Relative to the original data->Is (are) preferred degree of->Indicate->Maximum frequency in spectrogram of strip IMF component signal, < >>Indicate->Minimum frequency in spectrogram of strip IMF component signal, < >>Indicate->Curve function of continuous spectrogram corresponding to IMF component signal>Independent variables representing curve functions, similarly, < ->Curve function representing the continuous spectrogram of the original data, < >>Indicate->Target signal after several iterations->Is included in the IMF component signal.
8. The method for online monitoring of water supply and drainage equipment related data according to claim 6, wherein the determining the optimal standard deviation according to the preference degree comprises:
obtaining target signals after each iterationAnd determining the iteration number when the preference degree is maximum, and determining the standard deviation of the iteration number as the optimal standard deviation.
9. The online monitoring method of related data of water supply and drainage equipment according to claim 1, wherein the method is characterized in that the temperature data is noisy according to the optimal standard deviation to obtain noisy temperature data; decomposing the noise temperature data to obtain a plurality of component signals; denoising each component signal to obtain a denoising signal of the component signal; reconstructing the denoising signal of the component signal to obtain denoising data of the temperature data; monitoring the water supply and drainage equipment according to the denoised temperature data, comprising:
adding Gaussian white noise corresponding to the optimal standard deviation into an original signal according to the obtained optimal standard deviation to obtain noise adding temperature data, EEMD decomposing the Gaussian white noise adding temperature data corresponding to the optimal standard deviation to obtain a plurality of IMF component signals, denoising each IMF component signal to obtain a denoised signal of the component signal, reconstructing each denoised IMF component signal to obtain denoised data of the temperature data; temperature monitoring is carried out according to the denoised temperature data, and when the temperature data after any denoising is larger than a preset threshold valueAnd when the alarm is given.
10. An on-line monitoring system for water supply and drainage equipment associated data, the system comprising a memory and a processor, wherein the processor executes a computer program stored in the memory to implement an on-line monitoring method for water supply and drainage equipment associated data according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410004202.7A CN117493778B (en) | 2024-01-03 | 2024-01-03 | On-line monitoring method and system for associated data of water supply and drainage equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410004202.7A CN117493778B (en) | 2024-01-03 | 2024-01-03 | On-line monitoring method and system for associated data of water supply and drainage equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117493778A true CN117493778A (en) | 2024-02-02 |
| CN117493778B CN117493778B (en) | 2024-03-22 |
Family
ID=89676897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410004202.7A Active CN117493778B (en) | 2024-01-03 | 2024-01-03 | On-line monitoring method and system for associated data of water supply and drainage equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117493778B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117927459A (en) * | 2024-03-25 | 2024-04-26 | 陕西中环机械有限责任公司 | Grouting pump grouting flow optimization control method |
| CN118133053A (en) * | 2024-05-08 | 2024-06-04 | 山东瑞福锂业有限公司 | Industrial data collecting and processing system and method |
| CN118505436A (en) * | 2024-07-16 | 2024-08-16 | 西安五常电力技术有限公司 | Operation mode control method and system for wind power plant |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104375973A (en) * | 2014-11-24 | 2015-02-25 | 沈阳建筑大学 | Blind source signal denoising method based on ensemble empirical mode decomposition |
| WO2019179340A1 (en) * | 2018-03-19 | 2019-09-26 | 河北工业大学 | Eemd- and msb-based failure feature extraction method for rolling-element bearing |
| CN112506663A (en) * | 2020-12-17 | 2021-03-16 | 华南理工大学 | Cloud server CPU load prediction method, system and medium based on denoising and error correction |
| CN115860232A (en) * | 2022-12-08 | 2023-03-28 | 国电和风风电开发有限公司 | Steam load prediction method, system, electronic device and medium |
| CN116703183A (en) * | 2023-08-04 | 2023-09-05 | 国网吉林省电力有限公司经济技术研究院 | Novel power distribution network system power load assessment method |
| CN116842410A (en) * | 2023-09-01 | 2023-10-03 | 福建赛鲲鹏网络科技有限公司 | Intelligent helmet antitheft management method and system based on dynamic perception |
| CN117195007A (en) * | 2023-11-08 | 2023-12-08 | 张家港长寿工业设备制造有限公司 | Heat exchanger performance prediction method and system |
-
2024
- 2024-01-03 CN CN202410004202.7A patent/CN117493778B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104375973A (en) * | 2014-11-24 | 2015-02-25 | 沈阳建筑大学 | Blind source signal denoising method based on ensemble empirical mode decomposition |
| WO2019179340A1 (en) * | 2018-03-19 | 2019-09-26 | 河北工业大学 | Eemd- and msb-based failure feature extraction method for rolling-element bearing |
| CN112506663A (en) * | 2020-12-17 | 2021-03-16 | 华南理工大学 | Cloud server CPU load prediction method, system and medium based on denoising and error correction |
| CN115860232A (en) * | 2022-12-08 | 2023-03-28 | 国电和风风电开发有限公司 | Steam load prediction method, system, electronic device and medium |
| CN116703183A (en) * | 2023-08-04 | 2023-09-05 | 国网吉林省电力有限公司经济技术研究院 | Novel power distribution network system power load assessment method |
| CN116842410A (en) * | 2023-09-01 | 2023-10-03 | 福建赛鲲鹏网络科技有限公司 | Intelligent helmet antitheft management method and system based on dynamic perception |
| CN117195007A (en) * | 2023-11-08 | 2023-12-08 | 张家港长寿工业设备制造有限公司 | Heat exchanger performance prediction method and system |
Non-Patent Citations (1)
| Title |
|---|
| 蔡艳平;李艾华;徐斌;许平;何艳萍;: "集成经验模态分解中加入白噪声的自适应准则", 振动.测试与诊断, no. 06, 15 December 2011 (2011-12-15) * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117927459A (en) * | 2024-03-25 | 2024-04-26 | 陕西中环机械有限责任公司 | Grouting pump grouting flow optimization control method |
| CN117927459B (en) * | 2024-03-25 | 2024-06-11 | 陕西中环机械有限责任公司 | Grouting pump grouting flow optimization control method |
| CN118133053A (en) * | 2024-05-08 | 2024-06-04 | 山东瑞福锂业有限公司 | Industrial data collecting and processing system and method |
| CN118505436A (en) * | 2024-07-16 | 2024-08-16 | 西安五常电力技术有限公司 | Operation mode control method and system for wind power plant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117493778B (en) | 2024-03-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117493778B (en) | On-line monitoring method and system for associated data of water supply and drainage equipment | |
| Jayawardena et al. | Noise reduction and prediction of hydrometeorological time series: dynamical systems approach vs. stochastic approach | |
| KR101829560B1 (en) | Method, system and computer device for predicting a capacity based on kalman filter | |
| WO2016086329A1 (en) | Actually-measured marine environment data assimilation method based on sequence recursive filtering three-dimensional variation | |
| CN109657613B (en) | Large-scale power grid abnormal load identification method based on power method and parallel computing technology | |
| CN116955938B (en) | Dry-type waste gas treatment equipment monitoring method and system based on data analysis | |
| CN110717472B (en) | Fault diagnosis method and system based on improved wavelet threshold denoising | |
| CN117195007B (en) | Heat exchanger performance prediction method and system | |
| CN117786371B (en) | Temperature monitoring data optimization prediction analysis method and system | |
| CN117196353A (en) | Environmental pollution assessment and monitoring method and system based on big data | |
| CN114384565A (en) | Dynamic positioning coordinate sequence abnormal value identification method based on VMD iterative decomposition | |
| Vargas et al. | Electrocardiogram signal denoising by clustering and soft thresholding | |
| CN113901379A (en) | Dynamic online rapid processing method for real-time data of edge terminal | |
| CN117611031B (en) | Real-time monitoring method and system for logistics temperature of cold chain Internet of things | |
| KR102100386B1 (en) | Method for Kalman filtering using measurement noise recommendation, and recording medium thereof | |
| CN112013910B (en) | Drainage pipe network flow detection method and device, server and storage medium | |
| Na et al. | FASER: Fault-affected signal energy ratio for fault diagnosis of gearboxes under repetitive operating conditions | |
| CN116701840A (en) | Method and system for optimizing and calculating cepstrum of mechanical vibration signal | |
| CN114112819B (en) | Method and device for measuring ore grinding granularity | |
| CN103268403A (en) | Target tracking method based on cubature strong tracking information filter | |
| CN115563579A (en) | Data fusion method for measuring sand content by capacitive sensor | |
| CN110457863B (en) | Parameter estimation method for wind driven generator pitch subsystem based on ellipsoid contraction filtering | |
| CN116736278A (en) | Robust method for estimating velocity of moving sound source based on line spectrum Doppler frequency shift | |
| CN113052938A (en) | Method and device for constructing boiler energy efficiency curve | |
| CN118467935B (en) | Motor data denoising method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |