CN116738152A - Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method - Google Patents
Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method Download PDFInfo
- Publication number
- CN116738152A CN116738152A CN202311017175.9A CN202311017175A CN116738152A CN 116738152 A CN116738152 A CN 116738152A CN 202311017175 A CN202311017175 A CN 202311017175A CN 116738152 A CN116738152 A CN 116738152A
- Authority
- CN
- China
- Prior art keywords
- damage
- vibration
- parameters
- pipeline
- parameter
- 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
- 230000006378 damage Effects 0.000 title claims abstract description 114
- 238000012544 monitoring process Methods 0.000 title claims abstract description 58
- 238000000034 method Methods 0.000 title claims abstract description 40
- 239000012530 fluid Substances 0.000 title claims abstract description 15
- 239000011159 matrix material Substances 0.000 claims abstract description 50
- 239000013598 vector Substances 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 21
- 238000011156 evaluation Methods 0.000 claims abstract description 15
- 230000002159 abnormal effect Effects 0.000 claims description 24
- 208000027418 Wounds and injury Diseases 0.000 claims description 9
- 208000014674 injury Diseases 0.000 claims description 9
- 238000001228 spectrum Methods 0.000 claims description 9
- 238000004891 communication Methods 0.000 claims description 8
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 6
- 230000003902 lesion Effects 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000000354 decomposition reaction Methods 0.000 claims description 4
- 238000000605 extraction Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 230000008094 contradictory effect Effects 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 238000001914 filtration Methods 0.000 description 5
- 230000003321 amplification Effects 0.000 description 4
- 238000003199 nucleic acid amplification method Methods 0.000 description 4
- 230000035945 sensitivity Effects 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 230000006735 deficit Effects 0.000 description 3
- 239000003651 drinking water Substances 0.000 description 2
- 235000020188 drinking water Nutrition 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 230000003595 spectral effect Effects 0.000 description 2
- 239000004831 Hot glue Substances 0.000 description 1
- 241000287127 Passeridae Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000012790 confirmation Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 230000002401 inhibitory effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M3/00—Investigating fluid-tightness of structures
- G01M3/02—Investigating fluid-tightness of structures by using fluid or vacuum
- G01M3/04—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point
- G01M3/24—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations
- G01M3/243—Investigating fluid-tightness of structures by using fluid or vacuum by detecting the presence of fluid at the leakage point using infrasonic, sonic, or ultrasonic vibrations for pipes
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F17—STORING OR DISTRIBUTING GASES OR LIQUIDS
- F17D—PIPE-LINE SYSTEMS; PIPE-LINES
- F17D5/00—Protection or supervision of installations
- F17D5/02—Preventing, monitoring, or locating loss
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H17/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves, not provided for in the preceding groups
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/10—Pre-processing; Data cleansing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Pipeline Systems (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention belongs to the technical field of urban underground pipeline facility safety monitoring, and discloses an underground fluid pipeline leakage damage distributed vibration monitoring evaluation system and method, wherein vibration sensors are arranged at all nodes of an underground pipeline network, vibration signals are transmitted to a central control system in a wireless mode, SSA-CVMD processing is carried out on the vibration signals, multidimensional damage parameters of the signals are extracted to obtain six time-frequency domain parameters, index weights of the parameters are determined according to a CRITIC weight method, and a judgment matrix is constructed to obtain a parameter weight vector; then constructing a reference GMM model based on the damage parameter database, and constructing a membership matrix by using the similarity of the GMM probability distribution; and finally, carrying out real-time evaluation on the damage of the underground pipe network according to the fuzzy operation results of the parameter weight vector and the membership matrix. The method provided by the invention has the advantages of accurate identification result, good real-time performance and advance performance, and can evaluate the damage state of the pipeline in real time.
Description
Technical Field
The invention belongs to the technical field of urban underground pipeline facility safety monitoring, and particularly relates to an underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method.
Background
When the underground pipeline leaks, the leakage of the tiny flow caused by small leakage holes of the pipeline is difficult to find, so that the water resource waste and the environmental damage are easy to cause for a long time, and further, great economic loss is brought, and the drinking water safety is also influenced. The damage accident caused by the leakage of the underground pipeline is very serious, so that the development of the damage assessment and early warning work for the underground water supply pipeline has important scientific significance for guaranteeing the engineering progress and the safety of resident drinking water.
When the pipeline leaks, a pressure difference exists between the inside and the outside of the pipeline and the pipe wall is thinner, so that a larger pressure gradient exists at the leakage hole. Due to the conversion of kinetic energy and pressure energy at the leakage hole, vibration can be excited at the outlet, so that a vibration signal is generated, and the vibration signal can be changed according to the change of the damage condition of the pipeline. When the pipeline is in a complex external environment or a complex working condition, and the flow velocity of the fluid in the pipeline is changed, the information reflecting the damage condition of the pipeline is possibly changed, so that errors are generated, and the real damage state of the pipeline cannot be estimated. How to realize low cost and high reliability while guaranteeing the sensitivity and advance of the damage state identification of the underground pipeline is a difficult problem to be solved urgently.
In the prior art, researches on underground pipe network damage monitoring are carried out, for example, patent application CN115854271A discloses an urban underground pipe network damage monitoring and repairing system and a damage identification repairing method, an envelope signal and fractal dimension parameter are extracted through collected real-time monitoring data, the envelope signal and the fractal dimension parameter are calculated and input into a Softmax classifier to obtain normal and damage classification probability, a high probability value is selected as a recognition result, and real-time damage monitoring can be completed.
Disclosure of Invention
In order to solve the technical problems, the invention provides a distributed vibration monitoring and evaluating system and method for leakage damage of an underground fluid pipeline, which are used for collecting damage vibration signals of an underground water supply pipeline network and performing SSA-CVMD processing according to vibration signal differences of different states through pipe network node vibration sensor arrangement and data, extracting multidimensional damage parameters, and realizing real-time evaluation of damage states of the underground pipeline network through a GMM (Gaussian mixture model) fuzzy evaluation research method.
The invention relates to a distributed vibration monitoring and evaluating system for leakage damage of an underground fluid pipeline, which comprises a distributed abnormal vibration signal monitoring system, a local control system and a central control system;
the distributed abnormal vibration signal monitoring system collects vibration signals of the underground pipeline through vibration sensors arranged at a plurality of monitoring nodes of the underground pipeline network, performs pretreatment, and transmits the processed vibration signals to the local control system;
the local control system receives the vibration signals of the nodes of the pipe network of the distributed abnormal vibration monitoring system, and transmits the normal vibration signals and the abnormal vibration signals to the central control system through wireless communication;
the central control system preprocesses the received vibration signals to realize real-time damage monitoring and evaluation of the underground pipe network;
the central control system comprises an SSA-CVMD (sparrow search algorithm-variation modal decomposition correlation) vibration signal processing module, a damage parameter feature extraction module, a CRITIC (objective) weight vector module, a Gaussian membership matrix module and a GMM fuzzy evaluation module;
the SSA-CVMD vibration signal processing module is used for taking a pipeline damage vibration signal as a search space, adopting SSA to optimize CVMD parameters and finishing the pretreatment of the signal;
the damage parameter characteristic extraction module is used for extracting cross-correlation damage factors, root mean square, spectrum amplitude difference, normalized cross-correlation and signal energy under the normal state and the abnormal state of the pipeline;
the CRITIC weight vector module is used for calculating the information bearing capacity of each parameter in the damaged state of the pipeline, determining the importance of the parameters and constructing a CRITIC judgment matrix so as to obtain a parameter CRITIC weight vector;
the Gaussian membership matrix module is used for constructing a reference GMM and a dynamic GMM by utilizing the damage parameter database, and determining a Gaussian membership matrix by using the probability distribution similarity of the GMM;
the GMM fuzzy evaluation module is used for carrying out fuzzy operation of a parameter CRITIC weight vector and a Gaussian membership matrix, and judging the damage level state of the underground pipeline.
Based on the system, the invention discloses a distributed vibration monitoring and evaluating method for leakage damage of an underground fluid pipeline, which comprises the following steps:
step 1, collecting vibration signals of all nodes of an underground pipe network through a distributed abnormal vibration signal monitoring system, and transmitting the preprocessed vibration signals to a central control system through a local control system;
step 2, the central control system carries out SSA-CVMD pretreatment on the vibration signals aiming at the received vibration signals;
step 3, the central control system extracts six damage characteristic parameters of cross-correlation damage factors, root mean square, spectrum amplitude difference, normalized cross-correlation and signal energy from the pre-processed vibration signals;
step 4, the central control system calculates the information bearing capacity of each parameter in the damaged state of the pipeline, determines the importance of the parameters, and constructs a CRITIC judgment matrix so as to obtain a parameter CRITIC weight vector;
step 5, the central control system utilizes the damage characteristic parameter database to construct a reference GMM and a dynamic GMM, and determines an output row vector through the probability distribution similarity of the GMM to obtain a Gaussian membership matrix;
and 6, performing SSA-CVMD signal preprocessing on the real-time monitoring data, extracting signal multidimensional damage parameters, performing CRITIC weight calculation and Gaussian membership matrix calculation, multiplying the CRITIC weight calculation and the Gaussian membership matrix calculation to obtain the sequence of the largest element in the result vector, and taking the sequence as the damage level state of the underground pipeline.
Further, in step 2, an original vibration signal SSA-CVMD processing is performed, a penalty factor and a modal decomposition number in the VMD are determined by SSA for the original vibration time domain signal, the correlation is combined with the VMD, i.e. CVMD, and the number of IMFs (Intrinsic Mode Functions) is determined by the center frequency of the component; and determining a corresponding threshold according to the energy spectrum index of the IMFs, and reconstructing the residual components to obtain the noise-reduced vibration signal.
Further, in step 4, the CRITIC weight method is adopted to calculate the information bearing capacity of each parameter, and the specific steps are as follows:
(1) Index forward processing and setting data matrix， The method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofRepresents the elements after treatment, m is the number of damage grades of the pipeline, n is the number of vibration parameters,a set of impairment parameters is represented,representing the minimum value of the damage parameters of each column,representing the maximum value of each column of injury parameters;
(2) Calculating the information bearing capacity:
contrast: the standard deviation is used to represent the firstContrast of item indicators，Representing the mean value of each column of injury parameters;
contradiction: reflecting the degree of correlation between different indices；Is taken as an indexThe contradiction between the index and the other indexes is large,indicating indexAnd (3) withCorrelation coefficients between;
information bearing capacity:，is taken as an indexAnd information bearing capacity;
(3) Calculating the importance of parameters:constructing a judgment matrix according to the importance of the parameters, wherein the basic form is as follows:wherein b ij For parameter x i And x j The importance of the phase is thus the reciprocal of the diagonal elements in the matrix, i.eThe method comprises the steps of carrying out a first treatment on the surface of the This isExternal lawIn the time-course of which the first and second contact surfaces,representing importance as compared to itself for elements on the diagonal; the CRITIC method calculates the importance difference of every two parameters under each working condition to obtain the maximum valueDividing the importance into equal parts c for the boundary, and judging the value of the matrix element as，The importance of the maximum parameter is represented, which interval is located is determined according to the importance calculation result, and the value of u is determined according to the importance calculation result, wherein u= [1,3,5,7,9]。
Further, the step 5 specifically includes:
using a damage parameter database as input, adopting PCA data to reduce the dimension, taking every two parameters as a group, and using the two parameters as two parameters of GMM analysis to obtain a reference GMM model;
in the test stage, the damage parameters of unknown damage states of the pipeline are subjected to the same method to obtain a dynamic GMM model;
by calculating the GMM probability density function similarity SIM of the monitored data with the reference data,whereinAnd (3) withProbability density function of GMM representing reference data and monitoring data, respectively, where n is the number of vibration signal parameters, DI i Representing a damage parameter; and determining an output row vector according to the obtained result to obtain a Gaussian membership matrix.
Further, in the step 6, SSA-CVMD signal processing is performed on the real-time monitoring data, multidimensional damage characteristic parameters are extracted, parameter CRITIC weight calculation and gaussian membership matrix calculation are performed, a parameter CRITIC weight vector and a gaussian membership matrix are obtained and input into a GMM fuzzy calculation module, the two parameters are multiplied to obtain the sequence of the largest element in the result vector, and the sequence is used as the damage level state of the underground water supply pipeline.
The beneficial effects of the invention are as follows:
1) The invention can effectively eliminate a large amount of irrelevant noise, including low-frequency noise, periodic noise, irrelevant noise with correlation and the like, contained in the signals by carrying out SSA-CVMD processing on the original vibration signals in a central control system, thereby further ensuring the reliability of the vibration signals;
2) According to the invention, the multidimensional damage parameters are extracted, and can reflect the characteristics of vibration signals in various aspects such as time domain, frequency domain and the like, so that the accuracy of damage evaluation is further ensured;
3) The invention utilizes the GMM method to carry out vibration signal damage evaluation, the GMM method analyzes the statistical characteristics of multiple parameters, the historical data is fully utilized, the database is continuously rich along with the continuous expansion of the monitoring data, the probabilistic fuzzy evaluation method has good rationality and robustness, and the model also has scientific basis.
Drawings
FIG. 1 is a schematic diagram of a multi-node vibration sensing monitoring system of the present invention;
FIG. 2 is a schematic diagram of a vibration sensor;
FIG. 3 is a diagram of a signal processing circuit;
fig. 4 is a signal amplifying circuit diagram;
FIG. 5 is a signal filtering circuit diagram;
FIG. 6 is a circuit diagram of a communication module;
FIG. 7 is a diagram of a vibration signal acquisition system;
FIG. 8 is a graph of the original damage vibration signal;
FIG. 9 is a graph showing the vibration signal of lesions after SSA-CVMD treatment;
FIG. 10 is a schematic representation of the importance of six damage parameters of a pipeline under four different damage conditions;
FIG. 11 is a graph of GMM probability density function for reference injury level 2;
FIG. 12 is a graph of GMM probability density function for test injury class 2;
FIG. 13 is a graph of the result of four kinds of impairment level fuzzy operation;
FIG. 14 is a schematic diagram of the architecture of a local control system;
FIG. 15 is a schematic diagram of a method of damage monitoring assessment;
FIG. 16 is a schematic flow chart of the method of the present invention;
Detailed Description
In order that the invention may be more readily understood, a more particular description of the invention will be rendered by reference to specific embodiments that are illustrated in the appended drawings.
The invention relates to a leakage damage distributed vibration monitoring and evaluating system for an underground fluid pipeline, which comprises three parts, namely: the system comprises a distributed abnormal vibration signal monitoring system, a local control system and a central control system, and the whole structure of the system is shown in figure 1.
The distributed abnormal vibration signal monitoring system comprises a vibration sensor and a signal processing module; the vibration sensing probes are respectively arranged on each monitoring node of the underground pipe network and are used for collecting abnormal vibration signals generated by water flow impact on the pipe wall at the damaged part of the pipe and converting the abnormal vibration signals into electric signals; the signal processing module comprises a voltage amplifying circuit, a signal filtering circuit, a microprocessor, a signal receiving and transmitting module and a power supply module; the voltage amplifying circuit amplifies an original weaker vibration voltage signal to a voltage interval of the signal filtering circuit; the signal filter circuit removes noise from the amplified vibration voltage signal and transmits the noise to the microprocessor; the microprocessor is STM32, and the denoised vibration voltage signal is transmitted to a local control system; the power module is a storage battery which respectively supplies power for the voltage amplifying circuit, the signal filtering circuit and the microprocessor.
In order to realize global monitoring and evaluation of urban underground pipe network damage, vibration signals of pipeline nodes need to be acquired in real time, and when a pipeline leaks, a large pressure gradient exists at a leakage hole because pressure difference exists between the inside and the outside of the pipeline and the pipe wall is thin. Vibration is excited at the outlet due to the conversion of kinetic and pressure energy at the leakage orifice, thereby generating a vibration signal. The sound energy generated by abnormal vibration of the pipeline is captured by the vibration sensor after being transmitted by the pipeline wall, SSA-CVMD is adopted for processing, multidimensional damage parameters are extracted by analyzing the characteristics of the SSA-CVMD vibration signals in a normal state and the SSA-CVMD vibration signals in an abnormal state, and the real-time damage state assessment of the pipeline network can be realized by adopting GMM fuzzy assessment.
The vibration sensor adopts a flexible magnet material as a base, and is adhered to the surface of a pipeline by smearing hot melt adhesive at the bottom end of the base, so that the sensor can be ensured to be in stable contact with the remembered pipelines of different materials, and the structure of the sensor is shown in figure 2. The selection of the sensing chip is required to cover the frequency domain range of the vibration signal and has better sensitivity. The experimental environment noise is mostly larger than 5Khz, and the general damage characteristic signal frequency is mostly smaller than 2Khz, so that the effect of effectively inhibiting the environment noise is achieved, and therefore a chip with high sensitivity in a low frequency band can be selected. In addition, the sensor chip has certain requirements in terms of waterproofness, dynamic range and the like, and ADXL345BCCZ is selected as an acceleration chip in the embodiment, the frequency response range of the chip is 0.1-2.5Khz, and the sensitivity is 6.33V/g.
The vibration sensors are deployed at all monitoring nodes of the underground pipe network, all the monitoring nodes collect according to a certain frequency, continuous collection is carried out on certain specific vibration sensors in the intensive monitoring stage, and the starting and stopping of the vibration sensors are controlled by the central control system.
Because the collected original pipeline vibration signal is very weak, and the collected signal contains more noise due to the turbulence in the pipeline, a signal processing module is required to amplify and filter the original signal, and the function is shown in fig. 3. The amplification chip is selected to consider the influence of the self electric noise on the whole circuit, and also consider the influence factors such as impedance matching, amplification factor and the like, in this embodiment, max44280 of the meixin semiconductor company is selected as the core amplification chip, so that the index requirements of noise, linearity and the like can be met, and a signal amplification circuit diagram is shown in fig. 4. The Max7408 filter chip is adopted to realize band-pass filtering, the cut-off frequency is controlled through PWM wave regulation, and the signal filter circuit is shown in fig. 5. The amplified and filtered preprocessed vibration signal is transmitted to a microprocessor, and the microprocessor needs to consider digital-to-analog conversion performance, power consumption and the like when selecting, and in the embodiment, STM32 is selected as a processor of the distributed abnormal signal monitoring system.
The distributed abnormal vibration signal monitoring system working mode comprises the following specific steps:
1) The central control system sends an acquisition starting instruction to the local control system;
2) The local control system sends an instruction to the distributed abnormal vibration signal monitoring system for signal acquisition;
3) The distributed abnormal vibration signal monitoring system performs signal preprocessing and transmits the preprocessed signals to the local controller;
4) The local control system transmits the received conditioning signal to the central control system.
The local control system is configured as shown in fig. 14, and is used for processing data output by the regional abnormal vibration signal monitoring system, wirelessly transmitting the data to the central control system, and bidirectionally transmitting control instructions. The local control system adopts STM32 as a processor, vibration signals acquired by all vibration sensors are connected to different I/O ports of the processor, and sequential acquisition is realized.
A single acquisition of the pipe section vibration signal typically lasts for a period of time, thus expanding the storage capacity of the local control system. The signal storage module sets a number for each vibration sensing channel, and associates the number with the extended external storage unit to realize the sequence storage of signals. The storage expansion method generally comprises an SD card, an EEPROM and the like, and in the embodiment, an SD card mode is adopted, and communication is carried out between the SD card mode and an STM32 processor through an SDIO protocol, so that sequence storage of monitoring signals is realized.
In order to realize wireless communication between the local control system and the central control system, a wire harness pipe is adopted to transfer a wireless communication module of the local control system to an open place. And adopting a GPRS protocol to wirelessly transmit monitoring signals temporarily stored in a local control system. In this embodiment, the SIM800A is used as a communication chip to communicate with the microprocessor STM32, and the circuit connection of the wireless communication module is shown in fig. 6.
And a central control system: the node vibration signals and the node numbers transmitted by the local control system are collected, and the start and stop of the local control system are controlled by receiving the confirmation signals, sending the start and stop signals and the like, and the control flow is shown in figure 7.
Based on the system, the invention also discloses a distributed vibration monitoring and evaluating method for leakage damage of the underground fluid pipeline, which is shown in fig. 16 and comprises the following steps:
step 1, collecting vibration signals of all nodes of an underground pipe network through a distributed abnormal vibration signal monitoring system, and transmitting the preprocessed vibration signals to a central control system through a local control system;
step 2, the central control system carries out SSA-CVMD pretreatment on the vibration signals aiming at the received vibration signals;
step 3, the central control system extracts six damage characteristic parameters of cross-correlation damage factors, root mean square, spectrum amplitude difference, normalized cross-correlation and signal energy from the pre-processed vibration signals;
step 4, the central control system calculates the information bearing capacity of each parameter in the damaged state of the pipeline, determines the importance of the parameters, and constructs a CRITIC judgment matrix so as to obtain a parameter CRITIC weight vector;
step 5, the central control system utilizes the damage characteristic parameter database to construct a reference GMM and a dynamic GMM, and determines an output row vector through the probability distribution similarity of the GMM to obtain a Gaussian membership matrix;
and 6, performing SSA-CVMD signal preprocessing on the real-time monitoring data, extracting signal multidimensional damage parameters, performing CRITIC weight calculation and Gaussian membership matrix calculation, multiplying the CRITIC weight calculation and the Gaussian membership matrix calculation to obtain the sequence of the largest element in the result vector, and taking the sequence as the damage level state of the underground pipeline.
As shown in fig. 15, the original vibration signal SSA-CVMD processing is performed, penalty factors and modal decomposition numbers in the VMD are determined with SSA for the time domain signal S (t), correlation is combined with the VMD, i.e. CVMD,
judging by calculating the correlation coefficient between the IMF and the original vibration sequence S (t), wherein the calculation formula of the correlation coefficient is as follows: ， IMFi represents a decomposed modality; determining a corresponding threshold according to the energy spectrum index of the IMFs, and reconstructing the residual component to obtain a denoised sequence S (t) signal:
；
extracting multidimensional damage parameters from S (t) signal, and settingThe time domain vibration signal of the pipeline in a healthy state is a reference CVMD signal after noise reduction treatment;and the vibration CVMD signal is monitored in real time after noise reduction.
The 6 parameters for extracting the pipeline vibration signals are respectively as follows:
，
DI1 characterizes the correlation of the reference signal and the monitoring signal, wherein、The start and stop times of the valid signal, respectively;
，
DI2 is the root mean square of the time domain signal;
，
DI3 is the difference in frequency response between the reference signal and the monitor signal, whereThe start and stop frequencies at which the spectral amplitude of the effective signal is located,、respectively isAndis a frequency response of (2);
，
DI4 is the amplitude difference of the frequency response, which is an energy dependent measure of the signal variation;
，
DI5 is a normalized correlation moment for evaluating the phase and amplitude variations, whereIs the cross-correlation coefficient of the reference signal and the monitor signal,is the cross-correlation coefficient of the reference signal and the self, and n is the order of the statistical moment;
，
DI6 is the relative area of the envelope of the time domain signal and represents the relative energy of the reference signal and the monitor signal.
The CRITIC weight method is adopted to calculate the information bearing capacity of each parameter, and the specific method is as follows:
(1) Index forward processing and setting data matrix， The method comprises the steps of carrying out a first treatment on the surface of the Wherein the method comprises the steps ofThe elements after the treatment are represented as such,represents the elements after treatment, m is the number of damage grades of the pipeline, n is the number of vibration parameters,a set of impairment parameters is represented,representing the minimum value of the damage parameters of each column,representing the maximum value of each column of injury parameters;
(2) Calculating the information bearing capacity and comparing: the standard deviation is used to represent the firstContrast of item indicators，Representing the mean value of each column of injury parameters; contradiction: reflecting the degree of correlation between different indices；Is taken as an indexThe contradiction between the index and the other indexes is large,indicating indexAnd (3) withCorrelation coefficients between; information bearing capacity:，is taken as an indexAnd information bearing capacity.
Determining the information bearing capacity of each parameter by using a CRITIC weighting method, and calculating the importance of the parameter:and constructing a judgment matrix according to the importance to obtain a parameter CRITIC weight vector.
The Gaussian membership matrix row vector obtaining method comprises the following steps: taking a damage parameter database as input, adopting PCA data to reduce the dimension, taking every two parameters as a group to obtain a reference GMM model, adopting the same method to obtain a dynamic GMM model by using damage parameters of unknown damage states of the pipeline in a test stage, and determining an output row vector through the similarity of the GMM probability distribution; the combination sequence of the two parameters is as follows: cross-correlation damage factor-PCA, root mean square-PCA, spectrum amplitude difference-PCA, normalized cross-correlation-PCA and signal energy-PCA, wherein PCA represents that data dimension reduction is carried out on other five damage parameters; the Gaussian membership matrix is formed by combining a plurality of output row vectors, and each output matrix row vector is obtained by training GMM probability distribution similarity by using two specific parameters.
Multiplying the parameter CRITIC weight vector by the Gaussian membership matrix, taking the sequence of the largest element in the result vector, and taking the sequence as the damage level state of the underground pipeline.
Fig. 8 and 9 show the original vibration signal and the vibration signal processed by SSA-CVMD, respectively, where the amplitude of the processed vibration signal is reduced, and by separating the noise from the original signal and distributing it to the high-frequency IMF, the high-frequency noise interference of the original vibration signal is eliminated, so that the signal analysis is more accurate and reliable.
The four plots (a), (b), (c) and (d) in fig. 10 show the importance of the damage parameters for four different damage conditions (2 mm,4mm,6mm,8 mm) for the pipeline, DI1, DI2, DI3, DI4, DI5 and DI6 respectively representing the cross-correlation damage factor, root mean square, spectral amplitude difference, normalized cross-correlation and signal energy.
Fig. 11 and 12 show GMM probability density functions for benchmark and test lesion level 2, each ellipse representing a gaussian component, with the deepest color being the mean, where the probability density is the greatest. It can be seen that the GMM distribution of the parameters is greatly different although at the same lesion level; the difference of the Gaussian component distribution of DI4, DI5 and DI6 is obviously compared with DI1, DI2 and DI3; the probability function difference between DI1 and DI6 is the largest; this is because both parameters characterize the energy of the signal, which can have a significant impact on the vibration signal in the event of leakage damage. Compared with the reference level 2, the probability density function distribution of the parameter GMM has higher similarity, and the weight coefficient, the mean value and the covariance matrix change slightly.
The judgment matrix is constructed according to the importance of the parameters, as shown in table 1, and the result of calculating the CRITIC weight vector of the leakage parameter of the pipeline 2mm by adopting a square root method is (0.245,0.068,0.173,0.137,0.280,0.097). Taking the 2mm leakage state of the pipeline as an example, parameters are input into the GMM function in a pairwise combination way, and the output result is shown in table 2 according to the similarity of the GMM probability distribution.
TABLE 12 mm lesion CRITIC judgment matrix
，
TABLE 2mm injury GMM function outputs results for different parameter combinations
；
Combining the row vectors can obtain a Gaussian membership matrix:multiplying the parameter CRITIC weight vector by the Gaussian membership matrix to obtain a result vector as follows: (0.582,0.193,0.129,0.096) the resulting vector maximum of 0.582 was found at the first location, indicating that this sample was 58% most likely, which corresponds to the actual pipe damage condition.
FIG. 13 shows the fuzzy recognition results of four leakage conditions, according to which the fuzzy evaluation vector is changed with the change of the damage level. The maximum value element number is consistent with the actual leakage state number all the time, and the damage level can be accurately evaluated.
The foregoing is merely a preferred embodiment of the present invention, and is not intended to limit the present invention, and all equivalent variations using the description and drawings of the present invention are within the scope of the present invention.
Claims (6)
1. The underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system is characterized by comprising a distributed abnormal vibration signal monitoring system, a local control system and a central control system,
the distributed abnormal vibration signal monitoring system collects vibration signals of the underground pipeline through vibration sensors arranged at a plurality of monitoring nodes of the underground pipeline network, performs pretreatment, and transmits the processed vibration signals to the local control system;
the local control system receives the vibration signals of the nodes of the pipe network of the distributed abnormal vibration monitoring system, and transmits the normal vibration signals and the abnormal vibration signals to the central control system through wireless communication;
the central control system preprocesses the received vibration signals to realize real-time damage monitoring and evaluation of the underground pipe network;
the central control system comprises an SSA-CVMD vibration signal processing module, a damage parameter feature extraction module, a CRITIC weight vector module, a Gaussian membership matrix module and a GMM fuzzy evaluation module;
the SSA-CVMD vibration signal processing module is used for taking a pipeline damage vibration signal as a search space, adopting SSA to optimize CVMD parameters and finishing the pretreatment of the signal;
the damage parameter characteristic extraction module is used for extracting cross-correlation damage factors, root mean square, spectrum amplitude difference, normalized cross-correlation and signal energy under the normal state and the abnormal state of the pipeline;
the CRITIC weight vector module is used for calculating the information bearing capacity of each parameter in the damaged state of the pipeline, determining the importance of the parameters and constructing a CRITIC judgment matrix so as to obtain a parameter CRITIC weight vector;
the Gaussian membership matrix module is used for constructing a reference GMM and a dynamic GMM by utilizing the damage parameter database, and determining a Gaussian membership matrix by using the probability distribution similarity of the GMM;
the GMM fuzzy evaluation module is used for carrying out fuzzy operation of a parameter CRITIC weight vector and a Gaussian membership matrix, and judging the damage level state of the underground pipeline.
2. A method for monitoring and evaluating leakage damage of a subsurface fluid pipeline in a distributed vibration manner, which is realized based on the system as claimed in claim 1, and comprises the following steps:
step 1, collecting vibration signals of all nodes of an underground pipe network through a distributed abnormal vibration signal monitoring system, and transmitting the preprocessed vibration signals to a central control system through a local control system;
step 2, the central control system carries out SSA-CVMD pretreatment on the vibration signals aiming at the received vibration signals;
step 3, the central control system extracts six damage characteristic parameters of cross-correlation damage factors, root mean square, spectrum amplitude difference, normalized cross-correlation and signal energy from the pre-processed vibration signals;
step 4, the central control system calculates the information bearing capacity of each parameter in the damaged state of the pipeline, determines the importance of the parameters, and constructs a CRITIC judgment matrix so as to obtain a parameter CRITIC weight vector;
step 5, the central control system utilizes the damage characteristic parameter database to construct a reference GMM and a dynamic GMM, and determines an output row vector through the probability distribution similarity of the GMM to obtain a Gaussian membership matrix;
and 6, performing SSA-CVMD signal preprocessing on the real-time monitoring data, extracting signal multidimensional damage parameters, performing CRITIC weight calculation and Gaussian membership matrix calculation, multiplying the CRITIC weight calculation and the Gaussian membership matrix calculation to obtain the sequence of the largest element in the result vector, and taking the sequence as the damage level state of the underground pipeline.
3. The method for monitoring and evaluating the leakage damage distributed vibration of the underground fluid pipeline according to claim 2, wherein in the step 2, the processing of an original vibration signal SSA-CVMD is carried out, a punishment factor and a modal decomposition number in the VMD are determined by adopting SSA for an original vibration time domain signal, the correlation is combined with the VMD, namely CVMD, and the number of IMFs is determined by the central frequency of components; and determining a corresponding threshold according to the energy spectrum index of the IMFs, and reconstructing the residual components to obtain the noise-reduced vibration signal.
4. The method for monitoring and evaluating the leakage damage distributed vibration of the underground fluid pipeline according to claim 2, wherein in the step 4, the CRITIC weight method is adopted to calculate the information bearing capacity of each parameter, and the specific steps are as follows:
(1) Index forward processing and setting data matrix， />The method comprises the steps of carrying out a first treatment on the surface of the Wherein->Representing the treated elements, m is the number of damage grades of the pipeline, n is the number of vibration parameters,/->Representing the set of lesion parameters->Representing the minimum value of the damage parameter of each column, < >>Representing the maximum value of each column of injury parameters;
(2) Calculating the information bearing capacity:
contrast: the standard deviation is used to represent the firstContrast of item indicators->，/>Representing the mean value of each column of injury parameters;
contradiction: reflecting the degree of correlation between different indices；/>Is index->Contradictory magnitude with other index ++>Indication index->And->Correlation coefficients between;
information bearing capacity:，/>is index->And information bearing capacity;
(3) Calculating the importance of parameters:constructing a judgment matrix according to the importance of the parameters, wherein the basic form is as follows:wherein b ij For parameter x i And x j The importance of the phase is thus that the diagonal elements in the matrix are reciprocal, i.e. +.>The method comprises the steps of carrying out a first treatment on the surface of the Furthermore, when->When (I)>Representing importance as compared to itself for elements on the diagonal; the CRITIC method calculates the importance difference of every two parameters under every working condition, and the maximum value +.>Dividing the importance into equal parts c for the boundary, and judging the value of the matrix element as +.>，/>The importance of the maximum parameter is represented, which interval is located is determined according to the importance calculation result, and the value of u is determined according to the importance calculation result, wherein u= [1,3,5,7,9]。
5. The method for monitoring and evaluating leakage damage distributed vibration of an underground fluid pipeline according to claim 2, wherein the step 5 is specifically:
using a damage parameter database as input, adopting PCA data to reduce the dimension, taking every two parameters as a group, and using the two parameters as two parameters of GMM analysis to obtain a reference GMM model;
in the test stage, the damage parameters of unknown damage states of the pipeline are subjected to the same method to obtain a dynamic GMM model;
by calculating the GMM probability density function similarity SIM of the monitored data with the reference data,wherein->And->Probability density function of GMM representing reference data and monitoring data, respectively, where n is the number of vibration signal parameters, DI i Representing a damage parameter; and determining an output row vector according to the obtained result to obtain a Gaussian membership matrix.
6. The method according to claim 2, wherein in the step 6, SSA-CVMD signal processing is performed on the real-time monitoring data, multidimensional damage characteristic parameters are extracted, parameter CRITIC weight calculation and gaussian membership matrix calculation are performed, parameter CRITIC weight vectors and gaussian membership matrix are obtained and input into a GMM fuzzy calculation module, the two are multiplied to obtain the sequence of the largest element in the result vectors, and the sequence is used as the damage level state of the underground water supply pipeline.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311017175.9A CN116738152B (en) | 2023-08-14 | 2023-08-14 | Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311017175.9A CN116738152B (en) | 2023-08-14 | 2023-08-14 | Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116738152A true CN116738152A (en) | 2023-09-12 |
| CN116738152B CN116738152B (en) | 2023-10-27 |
Family
ID=87910076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311017175.9A Active CN116738152B (en) | 2023-08-14 | 2023-08-14 | Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116738152B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190294649A1 (en) * | 2016-11-11 | 2019-09-26 | Oxford University Innovation Limited | Method and system for tracking sinusoidal wave parameters from a received signal that includes noise |
| CN112858473A (en) * | 2020-12-25 | 2021-05-28 | 杭州浙达精益机电技术股份有限公司 | Turnout switch blade damage state monitoring method based on feature fusion |
| CN113935231A (en) * | 2021-09-14 | 2022-01-14 | 南京邮电大学 | Large-scale structural damage monitoring and evaluating method based on sparse array |
| CN114722856A (en) * | 2022-03-02 | 2022-07-08 | 中国计量大学 | Pipeline damage monitoring method and device |
| CN115509877A (en) * | 2022-09-30 | 2022-12-23 | 广东产品质量监督检验研究院（国家质量技术监督局广州电气安全检验所、广东省试验认证研究院、华安实验室） | Method for evaluating performance efficiency of information system |
| CN115854271A (en) * | 2023-02-22 | 2023-03-28 | 南京邮电大学 | Urban underground pipe network damage monitoring and repairing system and damage identification repairing method |
| CN115937504A (en) * | 2022-12-01 | 2023-04-07 | 西南林业大学 | Bridge structure damage identification method and system |
| CN116438754A (en) * | 2020-11-02 | 2023-07-14 | 伟视达电子工贸有限公司 | Multiple radio frequency impairment estimation |
-
2023
- 2023-08-14 CN CN202311017175.9A patent/CN116738152B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190294649A1 (en) * | 2016-11-11 | 2019-09-26 | Oxford University Innovation Limited | Method and system for tracking sinusoidal wave parameters from a received signal that includes noise |
| CN116438754A (en) * | 2020-11-02 | 2023-07-14 | 伟视达电子工贸有限公司 | Multiple radio frequency impairment estimation |
| CN112858473A (en) * | 2020-12-25 | 2021-05-28 | 杭州浙达精益机电技术股份有限公司 | Turnout switch blade damage state monitoring method based on feature fusion |
| CN113935231A (en) * | 2021-09-14 | 2022-01-14 | 南京邮电大学 | Large-scale structural damage monitoring and evaluating method based on sparse array |
| CN114722856A (en) * | 2022-03-02 | 2022-07-08 | 中国计量大学 | Pipeline damage monitoring method and device |
| CN115509877A (en) * | 2022-09-30 | 2022-12-23 | 广东产品质量监督检验研究院（国家质量技术监督局广州电气安全检验所、广东省试验认证研究院、华安实验室） | Method for evaluating performance efficiency of information system |
| CN115937504A (en) * | 2022-12-01 | 2023-04-07 | 西南林业大学 | Bridge structure damage identification method and system |
| CN115854271A (en) * | 2023-02-22 | 2023-03-28 | 南京邮电大学 | Urban underground pipe network damage monitoring and repairing system and damage identification repairing method |
Non-Patent Citations (4)
| Title |
|---|
| DONGMEI WANG等: "Application of improved variational mode decomposition method based on two-dimensional sparrow search algorithm in natural gas pipeline leakage signal denoising", 《TRANSACTIONS OF THE INSTITUTE OF MEASUREMENT AND CONTROL》, vol. 44, no. 13, pages 2588 - 2602 * |
| KAI TAO等: "An automatic fuzzy monitoring method of underground rock moisture permeation damage based on MAE fractal", 《MEASUREMENT》, vol. 205, pages 1 - 12 * |
| 侯宇祥等: "自适应麻雀搜索算法的太阳轮故障诊断研究", 《机械设计与制造》, pages 1 - 6 * |
| 陶锴: "基于声发射的含水岩土安全监测技术研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》, no. 02, pages 038 - 163 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116738152B (en) | 2023-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109357822B (en) | Bridge rapid testing and evaluating method based on time-varying power characteristic change of axle coupling system | |
| Kumar et al. | Tacho-less sparse CNN to detect defects in rotor-bearing systems at varying speed | |
| EP3828512A1 (en) | Fluid consumption meter with noise sensor | |
| CN105263731B (en) | Pulse width measuring method and device | |
| CN104239736A (en) | Structure damage diagnosis method based on power spectrum and intelligent algorithms | |
| CN104236911A (en) | Train bogie bearing service process monitoring and fault diagnosis system and method | |
| CN111520615B (en) | Pipe network leakage identification and positioning method based on line spectrum pair and cubic interpolation search | |
| CN103308011A (en) | Ultrasonic film thickness measuring instrument and measuring method thereof | |
| CN110160765A (en) | A kind of shock characteristic recognition methods and system based on sound or vibration signal | |
| CN117078490B (en) | Urban small micro water body risk assessment method based on synchronous analysis of multiple factors | |
| CN107907206A (en) | A kind of intrinsic frequency on-line detecting system | |
| CN115854271B (en) | Urban underground pipe network damage monitoring and repairing system and damage identification and repairing method | |
| CN116738152B (en) | Underground fluid pipeline leakage damage distributed vibration monitoring and evaluating system and method | |
| CN202661269U (en) | Compound fault diagnosis test platform of diesel engine | |
| CN114263621B (en) | Test method and system for centrifugal pump cavitation fault diagnosis simulation | |
| CN115618205A (en) | Portable voiceprint fault detection system and method | |
| CN110186521A (en) | Vortex street moisture based on Wavelet Ridge feature extraction crosses reading compensation and flow-measuring method | |
| CN117169346A (en) | High-altitude building damage identification method based on wavelet packet energy spectrum analysis | |
| CN211478951U (en) | Fault diagnosis device and fault diagnosis system | |
| CN115839763A (en) | Transformer vibration noise monitoring system | |
| CN105890738A (en) | Conflux vortex impact vibration identification method | |
| CN211477587U (en) | Online safety early warning device and fault diagnosis system | |
| CN108646248A (en) | A kind of passive acoustics for low-speed motion sound source tests the speed distance measuring method | |
| KR101724151B1 (en) | Estimating method for impact position and mass of metal piece using ambiguity pattern recognition | |
| WO2022150999A1 (en) | Tire abnormality detection method and apparatus |
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 |