CN111695465A - Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification - Google Patents
Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification Download PDFInfo
- Publication number
- CN111695465A CN111695465A CN202010485209.7A CN202010485209A CN111695465A CN 111695465 A CN111695465 A CN 111695465A CN 202010485209 A CN202010485209 A CN 202010485209A CN 111695465 A CN111695465 A CN 111695465A
- Authority
- CN
- China
- Prior art keywords
- fault
- pressure wave
- pipe network
- information
- positioning
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 98
- 238000000034 method Methods 0.000 title claims abstract description 78
- 238000003909 pattern recognition Methods 0.000 claims abstract description 25
- 238000012544 monitoring process Methods 0.000 claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 14
- 230000001052 transient effect Effects 0.000 claims description 47
- 239000011159 matrix material Substances 0.000 claims description 24
- 238000013528 artificial neural network Methods 0.000 claims description 23
- 238000012549 training Methods 0.000 claims description 23
- 239000013598 vector Substances 0.000 claims description 22
- 230000006870 function Effects 0.000 claims description 20
- 238000004422 calculation algorithm Methods 0.000 claims description 13
- 238000005457 optimization Methods 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 7
- 210000002569 neuron Anatomy 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 7
- 238000011144 upstream manufacturing Methods 0.000 claims description 7
- 230000004927 fusion Effects 0.000 claims description 6
- 230000009466 transformation Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 5
- 230000009467 reduction Effects 0.000 claims description 5
- 230000004807 localization Effects 0.000 claims description 4
- 238000002864 sequence alignment Methods 0.000 claims description 4
- 239000000126 substance Substances 0.000 claims description 4
- 238000013519 translation Methods 0.000 claims description 4
- 238000012935 Averaging Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000010801 machine learning Methods 0.000 claims description 3
- 206010063385 Intellectualisation Diseases 0.000 abstract description 8
- 230000008439 repair process Effects 0.000 abstract description 5
- 238000010586 diagram Methods 0.000 description 14
- 230000005540 biological transmission Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 4
- 239000012530 fluid Substances 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 239000002245 particle Substances 0.000 description 3
- 238000005070 sampling Methods 0.000 description 3
- 230000008030 elimination Effects 0.000 description 2
- 238000003379 elimination reaction Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 238000004088 simulation Methods 0.000 description 2
- 238000011426 transformation method Methods 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 230000002238 attenuated effect Effects 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007500 overflow downdraw method Methods 0.000 description 1
- 230000001902 propagating effect Effects 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
- G06F2218/06—Denoising by applying a scale-space analysis, e.g. using wavelet analysis
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01L—MEASURING FORCE, STRESS, TORQUE, WORK, MECHANICAL POWER, MECHANICAL EFFICIENCY, OR FLUID PRESSURE
- G01L19/00—Details of, or accessories for, apparatus for measuring steady or quasi-steady pressure of a fluent medium insofar as such details or accessories are not special to particular types of pressure gauges
- G01L19/06—Means for preventing overload or deleterious influence of the measured medium on the measuring device or vice versa
- G01L19/0672—Leakage or rupture protection or detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
Abstract
The invention belongs to the technical field of fault monitoring, diagnosis and positioning of industrial internet, and particularly relates to a pipe network fault diagnosis and positioning method and system based on pressure wave pattern recognition, wherein the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition comprises the following steps: collecting information; information preprocessing is carried out; extracting fault characteristic parameters according to the preprocessed information; carrying out fault diagnosis according to the fault characteristic parameters; positioning the fault; and fault information is sent according to fault diagnosis and positioning, so that more real assessment and practical feasibility are provided for realizing intellectualization and intellectualization of the heat supply system and safe operation, more accurate fault types and corresponding repair suggestions are provided for pipe network operators, and a set of complete intelligent fault diagnosis and positioning method and system for the heat supply pipe network are provided.
Description
Technical Field
The invention belongs to the technical field of fault monitoring, diagnosis and positioning of industrial internet, and particularly relates to a pipe network fault diagnosis and positioning method and system based on pressure wave mode identification.
Background
The regional central heating system consists of three parts, namely a heat source, a heat supply network and a heat user. The heat supply network is used as an important component of a heat supply system, takes on the task of timely conveying and distributing heat of a heat source to each heat user, and plays a role of a bridge connecting the heat source and the heat source. The aging, corrosion, sudden natural disasters, artificial damages and the like of the pipe network can cause the pipe network to break and even leak, if the pipe network is not discovered and remedied in time, the economic loss and the environmental pollution are caused, the personal safety is endangered, and even disaster accidents are caused. Therefore, the research on the monitoring and diagnosis technology of the pipe network faults is of practical significance. At present, a manual inspection method is generally adopted in China, and emergency treatment is carried out after a fault is found, but the method not only brings inconvenience to the operation and maintenance of the heat supply pipe network, but also costs a large amount of unnecessary manpower and material resources and causes a lot of unnecessary loss, and can not meet the requirement of the development of the current heat supply pipe network. Therefore, an intelligent diagnosis system for transient pressure events of a pipe network is urgently needed to ensure the economical and safe operation of a heat supply network and improve the automatic control and management level of the heat supply network.
When a transient pressure accident occurs to a pipe network, substances are immediately lost at the accident position, and local density is reduced, so that pressure is reduced, and the generated pressure reduction wave is called negative pressure wave. Because the negative pressure wave has a high propagation speed which is equal to the sound velocity in the fluid and can reach 1200m/s at most, pressure acquisition equipment with the characteristics of ultrahigh transmission speed, mass connection of millions of equipment, millisecond time delay, high positioning precision, high reliability and the like is needed for accurately acquiring a complete transient pressure waveform, for example, a pressure sensing acquisition device with a 5G communication technology can be adopted, the problem that a sensor is difficult to acquire corresponding transient pressure change in the prior art can be solved, and a pipe network pressure signal can be acquired more quickly, more reliably and in a lower time delay manner in real time. The sensors arranged at two ends of the leakage point can determine the fault position according to the change of the pressure signal and the time difference of the negative pressure wave generated by the fault propagating to the upstream and the downstream. The method is sensitive and accurate, does not need to establish a mathematical model of the pipeline, has simple principle and strong applicability, and can deal with the rapid and sudden situation.
The heat supply network comprehensive state detection and operation sensing system is characterized in that the problems existing in the existing heat supply network are effectively solved by ultrahigh transmission speed, massive equipment connection support and millisecond-level low time delay, a high-speed low-delay communication network technology is adopted in the operation of a pipe network, and the operation pressure parameters of the heat supply network are acquired through pressure sensing installed in the pipe network, so that the comprehensive state detection and operation sensing system of the whole network is constructed, the problems that the operation safety faults such as leakage, pipe explosion, abnormal change of valves and the like possibly occur in the operation of the heat supply network are further solved, the occurring time and place are not required to be searched by any rule, and the economical efficiency and the safety of the operation of the heat supply network are seriously influenced are.
Therefore, a new method and a system for diagnosing and positioning the fault of the pipe network based on the pressure wave pattern recognition are needed to be designed based on the above technical problems.
Disclosure of Invention
The invention aims to provide a pipe network fault diagnosis and positioning method and system based on pressure wave mode identification.
In order to solve the technical problem, the invention provides a pipe network fault diagnosis and positioning method based on pressure wave mode identification, which comprises the following steps:
collecting information;
information preprocessing is carried out;
extracting fault characteristic parameters according to the preprocessed information;
carrying out fault diagnosis according to the fault characteristic parameters;
positioning the fault; and
and sending fault information according to fault diagnosis and positioning.
Further, the information acquisition method comprises the following steps:
transient pressure wave signals in the pipe are collected through a pressure wave collector arranged on a pipe network of the diagnosed pipe network system.
Further, the information preprocessing method comprises the following steps:
and performing signal denoising processing, signal filtering processing and time sequence alignment on the acquired transient pressure wave signals, and storing the acquired transient pressure wave signals to form a global database of a historical database and real-time data.
Further, the method for extracting the fault characteristic parameters according to the preprocessed information comprises the following steps:
through wavelet transformation, multilayer wavelet decomposition is carried out on transient pressure wave change signals, interference noise in the signals is eliminated by adopting a heuristic wavelet threshold method, and fault characteristic parameters sensitive to leakage in a time-frequency domain, namely the fault characteristic parameters are extracted from noise reduction signals
The wavelet mother function psi (t) is stretched and translated to obtain the function psia,τ(t)：
Wherein a is a scaling factor; τ is a translation factor; psia,τ(t) is the wavelet basis function dependent on parameters a and τ;
function f (t) continuous wavelet transform CWT, whose expression is:
carrying out discrete binary wavelet transform on the noisy signal, denoising the noisy signal on n-layer scales by adopting different threshold methods respectively, and reconstructing a waveform, wherein the signal reconstruction method comprises the following steps:
wherein l, k is 1,2, … N, l, k are time sequence numbers, and N is a maximum time sequence number; j represents the number of layers; h and g are respectively wavelet low-pass filter and band-pass filter coefficients;
and if the statistical indexes are suitable for reflecting the leakage characteristics of the pipe network, the calculation method of each fault characteristic parameter comprises the following steps:
peak value: xamax＝max{|xi|}；
Average amplitude value:
variance:
square root amplitude:
kurtosis:
energy ratio:
wherein x isi(i ═ 1, 2.., N) denotes the values of discrete points of the reconstructed signal.
Further, the method for fault diagnosis according to the fault characteristic parameters comprises the following steps:
according to a heuristic optimization algorithm and a BP neural network, constructing an optimization and neural network fusion structure of pipe network fault characteristic parameters, and completing the initial identification of the sensor node on the fault, namely
Constructing a corresponding relation between the waveform characteristics of the fault and the fault type, namely a diagnosis matrix; describing the influence factor of each characteristic on the corresponding fault type through a weight matrix table; training by adopting a machine learning algorithm to obtain a fault characteristic vector, performing pattern recognition and matching with a diagnosis matrix, and determining the transient pressure fault type;
before diagnosis, initializing a weight value by using data in a global database;
taking the extracted fault characteristic parameters as an input layer, training the network through training sample data, and reversely adjusting the connection weight and the threshold value among the neurons according to an error result until the training progress is reached;
the number of neurons in the output layer of the neural network is m, and the ideal output vector is Tout，Tout＝(0,0…1)，ρi∈[0,1]；
After the neural network training is output, all data information collected by the pipe network is converted into a characteristic vector suitable for fault diagnosis:
Tout＝[ρ1,ρ2,ρ3,...ρi,...ρm]；
wherein the content of the first and second substances,
ρiindicating a feature vector, 0 indicating that the feature vector is not present in the data information, and 1 indicating that the feature vector is present.
Further, the method for locating the fault comprises the following steps:
after the fault type is determined, traversing all node data in the pipe network by a traversal binary method, calculating the time difference of the pressure wave collectors at the upstream end and the downstream end receiving the pressure signal, and further determining the fault position; and
through the repeated positioning algorithm of the nodes of the multi-pressure wave collector, the fault position is accurately positioned, namely
Grouping and pairing all signals according to the average amplitude of the single-mode acoustic emission signals obtained by wavelet decomposition, obtaining the position of a leakage point positioned by each pair of signals through waveform cross-correlation analysis, and finally performing weighted averaging to accurately position the fault position.
Further, the method for sending fault information according to fault diagnosis and positioning comprises the following steps:
generating corresponding fault suggestions according to fault diagnosis and positioning;
the fault information includes: fault diagnosis, localization and recommendation.
In a second aspect, the present invention also provides an operation monitoring terminal,
the operation monitoring terminal is suitable for extracting fault characteristic parameters according to the preprocessed information, diagnosing faults according to the fault characteristics, positioning the faults and sending fault information according to the fault diagnosis and the positioning.
In a third aspect, the present invention also provides a pressure wave collection node,
the pressure wave acquisition node is provided with a pressure wave collector to acquire information and send the information, namely acquiring transient pressure wave signals in a network pipe of the system of the diagnosed pipe network and sending the transient pressure wave signals.
In a fourth aspect, the present invention further provides a pipe network fault diagnosis and location system based on pressure wave pattern recognition, including:
the system comprises a plurality of pressure wave acquisition nodes, an operation monitoring terminal and an upper computer;
the pressure wave acquisition nodes are provided with pressure wave collectors for acquiring information and sending the information to the upper computer, namely acquiring transient pressure wave signals in the pipe network of the system of the diagnosed pipe network and sending the transient pressure wave signals to the upper computer;
the upper computer is suitable for preprocessing information and sending the preprocessed information to the operation monitoring terminal;
the operation monitoring terminal is suitable for extracting fault characteristic parameters according to the preprocessed information, diagnosing faults according to the fault characteristic parameters, positioning the faults and sending fault information to the upper computer according to the fault diagnosis and the positioning.
The invention has the advantages that the invention collects information; information preprocessing is carried out; extracting fault characteristic parameters according to the preprocessed information; carrying out fault diagnosis according to the fault characteristic parameters; positioning the fault; and fault information is sent according to fault diagnosis and positioning, so that more real assessment and practical feasibility are provided for realizing intellectualization and intellectualization of the heat supply system and safe operation, more accurate fault types and corresponding repair suggestions are provided for pipe network operators, and a set of complete intelligent fault diagnosis and positioning method and system for the heat supply pipe network are provided.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
In order to make the aforementioned and other objects, features and advantages of the present invention comprehensible, preferred embodiments accompanied with figures are described in detail below.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and other drawings can be obtained by those skilled in the art without creative efforts.
FIG. 1 is a flow chart of a method for diagnosing and positioning a fault of a pipe network based on pressure wave pattern recognition according to the present invention;
FIG. 2 is a detailed flow chart of the method for diagnosing and positioning the fault of the pipe network based on the pressure wave pattern recognition according to the present invention;
FIG. 3 is a pressure wave waveform diagram of a time sequence process of obtaining pressure waves by measuring at multiple nodes of the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition, according to the invention;
FIG. 4 is a schematic structural diagram of a neural network of the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the present invention;
FIG. 5 is a schematic diagram of a fault diagnosis weight matrix training of a pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the present invention;
FIG. 6 is a schematic block diagram of a pipe network fault diagnosis and location system based on pressure wave pattern recognition according to the present invention;
fig. 7 is a conceptual diagram of the overall data transmission process of the pipe network fault diagnosis and positioning system based on pressure wave pattern recognition according to the present invention.
Detailed Description
To make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings, and it is apparent that the described embodiments are some, but not all embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Fig. 1 is a flow chart of a pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the invention.
As shown in fig. 1, embodiment 1 provides a method for diagnosing and locating a pipe network fault based on pressure wave pattern recognition, including: collecting information; information preprocessing is carried out; extracting fault characteristic parameters according to the preprocessed information; carrying out fault diagnosis according to the fault characteristic parameters; positioning the fault; the fault information is sent according to fault diagnosis and positioning, so that more real assessment and practical feasibility are provided for realizing intellectualization and intellectualization of the heat supply system and safe operation, more accurate fault types and corresponding repair suggestions are provided for pipe network operators, and a set of complete intelligent fault diagnosis and positioning method and system for the heat supply pipe network are provided; the safety fault of the heat supply pipe network can be found in time, and the occurrence position, time and type can be accurately confirmed.
Fig. 2 is a specific flowchart of a pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the present invention.
As shown in fig. 2, in this embodiment, the information collecting method includes: the pressure wave data sampling device is used for rapidly and high-frequency collecting transient pressure wave signals in the pipe; high-frequency, quick and low-delay sampling of pipe network pressure parameters (transient pressure wave signals) is realized; because the negative pressure wave has a high propagation speed which is equal to the sound velocity in the fluid and can reach up to 1200m/s, pressure acquisition equipment with the characteristics of ultrahigh transmission speed, mass connection of millions of equipment, millisecond time delay, high positioning precision, high reliability and the like is needed for accurately acquiring a complete transient pressure waveform, for example, a pressure sensing acquisition device (pressure wave collector) with a 5G communication technology can be adopted, the problem that a sensor is difficult to acquire corresponding transient pressure change in the prior art can be solved, and a pipe network pressure signal can be acquired in real time more quickly, more reliably and with lower time delay.
Fig. 3 is a pressure wave waveform diagram of a time sequence process of obtaining pressure waves by measuring at multiple nodes of the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition.
As shown in fig. 3, in this embodiment, the information preprocessing method includes: the transient pressure wave signals collected by the pressure wave collector are subjected to signal conversion through the pressure transmitter, the transient pressure wave signals subjected to signal conversion are subjected to signal de-noising processing, signal filtering processing and time sequence alignment, and the collected transient pressure wave signals are stored (the real-time data are changed into historical data through data rolling), so that a global database of a historical database and the real-time data is formed.
In this embodiment, the method for extracting the fault characteristic parameter according to the preprocessed information includes: selecting a proper wavelet basis and wavelet transformation method for decomposing the layer number, performing multilayer wavelet decomposition on the transient pressure wave change signal, eliminating interference noise in the signal by adopting a heuristic wavelet threshold method, and extracting fault characteristic parameters sensitive to leakage in a time-frequency domain from a noise reduction signal; analyzing the wavelet change characteristics of the global data;
the influence of various transient pressure faults including pipe network leakage, abnormal valve change, pipe explosion and the like on heat supply parameters is researched, signals can be analyzed in a time-frequency domain at the same time by utilizing wavelet transformation, and the method has the characteristic of multi-resolution analysis, namely the method has the capacity of representing local characteristics of the signals in the time-frequency domain; extracting characteristics of a pipe network pressure signal (transient pressure wave signal), and extracting multi-scale characteristic signals (fault characteristic parameters) which can most effectively represent the state of a system from a historical database and historical transient pressure fault events, wherein the multi-scale characteristic signals comprise peak values, average amplitude values, variances, square root amplitude values, kurtosis, energy ratios and the like;
multi-layer wavelet decomposition is carried out on transient pressure wave change signals by wavelet transformation (a wavelet transformation method for selecting proper wavelet basis and decomposing layer number), interference noise in the signals is eliminated by adopting a heuristic wavelet threshold method, and fault characteristic parameters sensitive to leakage in a time-frequency domain, namely the fault characteristic parameters are extracted from noise reduction signals
The wavelet analysis is to decompose the signal into the superposition of a series of wavelet functions, and the wavelet functions are obtained by translation and scale expansion of a wavelet mother function, and the irregular wavelet functions are used for approaching the sharply changed signal, so that the local characteristics of the signal are highlighted; the wavelet analysis method can simultaneously analyze signals in a time-frequency domain, has the characteristic of multi-resolution analysis, and has the capability of representing the local characteristics of the signals in the time-frequency domain; the method has higher frequency resolution and lower time resolution in a low-frequency part and higher time resolution and lower frequency resolution in a high-frequency part, and is suitable for detecting transient abnormal phenomena carried in normal signals and displaying components of the transient abnormal phenomena, so that noise elimination and fault characteristic parameter extraction are performed by utilizing wavelet transformation;
the wavelet mother function psi (t) is stretched and translated to obtain the function psia,τ(t)：
Wherein a is a scaling factor; τ is a translation factor; psia,τ(t) is the wavelet basis function dependent on parameters a and τ;
function f (t) continuous wavelet transform CWT, whose expression is:
carrying out discrete binary wavelet transform on the noisy signal, denoising the noisy signal on n-layer scales by adopting different threshold methods respectively, and reconstructing a waveform, wherein the signal reconstruction method is
Wherein l, k is 1,2, … N, l, k are time sequence numbers, and N is a maximum time sequence number; j represents the number of layers;
h and g are respectively wavelet low-pass filter and band-pass filter coefficients;
the statistical indexes such as peak value, average amplitude, variance, square root amplitude, kurtosis and energy ratio can sensitively reflect the leakage characteristics of the pipe network, and the calculation method of each characteristic index (fault characteristic parameter) comprises the following steps:
peak value: xamax＝max{|xi|}；
Average amplitude value:
variance:
square root amplitude:
kurtosis:
energy ratio:
wherein x isi(i ═ 1, 2.., N) denotes the values of discrete points of the reconstructed signal.
FIG. 4 is a schematic structural diagram of a neural network of the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the present invention;
fig. 5 is a schematic diagram of a fault diagnosis weight matrix training of the pipe network fault diagnosis and positioning method based on pressure wave pattern recognition according to the present invention.
In this embodiment, the method for performing fault diagnosis according to the fault characteristic parameter includes: according to a heuristic optimization algorithm and a BP neural network, an optimization and neural network fusion structure of pipe network fault characteristic parameters is constructed, initial identification of the sensor nodes on the faults is completed, the training speed of the network can be greatly improved, convergence on a local minimum value is avoided, and meanwhile the accuracy of fault identification is improved, namely
Constructing a corresponding relation between waveform characteristics (fault characteristic parameters including geometric characteristics) of the fault and the fault type, namely a weight matrix (which can be also called as a diagnosis matrix because of being used for diagnosis); describing influence factors of each characteristic (waveform characteristic) on forming corresponding fault types through a weight matrix table; training by adopting a machine learning algorithm to obtain a fault characteristic vector, performing pattern recognition and matching with a diagnosis matrix, and determining the transient pressure fault type;
before diagnosis, initializing a weight value by using data in a global database; in order to adapt to various new conditions, the self-learning is realized by retraining the data after the diagnosis, so that the fault diagnosis is continuously perfected and is more accurate in the diagnosis process;
aiming at the defects of low convergence speed, low recognition rate and easy convergence to a local optimal solution of the BP neural network, the weight of a heuristic optimization algorithm global optimization network is introduced; in order to ensure that the network has higher training speed and recognition accuracy, the number of hidden layer neurons required by the network is determined by adopting a trial optimization method, and on the basis, a heuristic optimization and BP neural network fusion structure of the pipe network fault characteristic parameters is established to complete the initial recognition of the sensor node on the leakage; compared with a BP neural network, the heuristic optimization + BP neural network fusion structure can greatly improve the training speed of the network, avoid convergence on a local minimum value and improve the accuracy of leakage identification;
the heuristic optimization and BP neural network fusion structure algorithm is explained by taking a neural network based on particle swarm as an example, the neural network learning algorithm based on particle swarm optimization is easy to realize, can better converge on an optimal solution, and meanwhile, the network has good learning performance and strong adaptability; the multi-scale feature vector after wavelet change is used as the input feature vector of the neural network, so that the organic combination of two data fusion methods of wavelet transformation and the neural network is realized; by utilizing the advantages of the neural network model in the aspects of system identification, pattern recognition and the like and combining the advantages of the particle swarm algorithm, namely, the high convergence speed and the good global solution are realized on the complex nonlinear multimodal problem, the network is converged as soon as possible, the situation that the local optimal solution is trapped is avoided, and the self-learning capability and the robustness of the network are greatly improved;
as shown in fig. 4, the extracted fault characteristic parameters (assumed to be P) are used as input layers, the network is trained through training sample data, and the connection weight and the threshold between neurons are adjusted reversely according to the error result until the training progress is reached;
the number of neurons in the output layer of the neural network is m, and the ideal output vector is ToutE.g. Tout＝(0,0…1)，ρi∈[0,1]；
After the neural network training is output, all data information collected by the pipe network is converted into a characteristic vector suitable for fault diagnosis:
Tout＝[ρ1,ρ2,ρ3,...ρi,...ρm]；
wherein the content of the first and second substances,
ρiindicating a feature vector, 0 indicating the absence of the feature vector in the data information, 1 indicating the presence of the featureAnd (5) sign vectors.
Constructing a corresponding relation between the characteristic vector of the fault and the fault type, namely a weight matrix (which can be called as a diagnosis matrix because of being used for diagnosis), and describing an influence factor of each characteristic on forming a certain fault type by using a weight matrix table; before diagnosis, establishing a basic framework of an initialization weight matrix by utilizing engineering practice experience and pipe network fault common knowledge obtained in fault simulation; in order to adapt to various new conditions, the self-learning is realized by feeding back the data after diagnosis and performing retraining, so that the system is continuously improved and is more accurate in the diagnosis process; a plurality of measuring nodes are arranged on the system management network of the diagnosed management network, the complementarity of the detection information of various sensors on a single node is processed, and the diagnosis results of a plurality of sensor nodes at different monitoring positions are jointly decided, so that the identification and diagnosis of the fault are greatly improved;
table one: initializing a weight matrix table
Wherein X0 is a normal working condition; x represents fault, subscript 1,2 … n indicates fault type;
as shown in fig. 5, the initialized weight matrix table has correct knowledge, but is not accurate enough, and a large amount of data is needed to train the weight matrix; the training data are obtained, on one hand, the training data are extracted and summarized from dynamic heat supply pipe network fault simulation research, on the other hand, a large amount of data are extracted from a historical database and combined with historical fault events to train the system; after training, extracting a weight matrix from the weight matrix table for fault diagnosis;
table two: weight matrix table after training
Wherein, βi,j∈[0,1]The value of which is proportional to the importance of the semantic feature; x0 is normal operating condition; x represents fault, subscript 1,2 … n indicates fault type;
then, combining the characteristic vectors and the weight matrix, calculating the probability of each type of fault in the pipe network by matrix multiplication:
probility＝[PX1,PX2,PX3,...,PXi,...,PXn]；
wherein, PXiRepresenting the probability of the occurrence of Xi type faults of the pipe network;
through the two formulas, the probability of all types of faults of the pipe network can be calculated, and most of the obtained results are 0; if the probability of a certain value is not 0 and is greater than a certain rated threshold value, the pipe network is considered to have the fault, and a corresponding reasonable fault diagnosis report suggestion is given; otherwise, the pipe network is considered to be safely operated.
In this embodiment, the method for locating a fault includes: after the fault type is determined, traversing all node data in the pipe network by a traversal binary method, calculating the time difference of the pressure wave collectors at the upstream end and the downstream end receiving the pressure signal, and further determining the fault position (further determining the approximate spatial position triggered by the event); and
in order to further improve the positioning precision of the accident source, the fault position is accurately positioned through the repeated positioning algorithm of the nodes of the multi-pressure wave collector, namely
Grouping and pairing all signals according to the average amplitude of the single-mode acoustic emission signals obtained by wavelet decomposition, obtaining the position of a leakage point positioned by each pair of signals through waveform cross-correlation analysis, and finally performing weighted averaging to accurately position a fault position; the multi-node time difference repeated positioning of the fault position is realized;
when a certain part of a pipe network suddenly breaks down, transient pressure suddenly drops at the fault part, namely, a pipe network transient pressure event is caused, a negative pressure wave is formed, the negative pressure wave is transmitted to two ends of the pipe network at a certain speed, the pipe wall is like a waveguide pipe, attenuation is small when the pressure wave is transmitted, and the pressure wave can be transmitted far; after a plurality of times, the signals are respectively transmitted to upstream and downstream, and the upstream and downstream pressure sensors (pressure wave collectors) capture specific transient pressure waveforms to diagnose and judge faults; if the time difference of the pressure signals received by the upstream and downstream pressure sensors can be accurately determined, the leakage point can be determined according to the propagation speed of the negative pressure wave;
abstracting the physical structure of the heat supply pipe network into a tree structure of a graph theory, converting the tree structure into a binary tree structure, and describing the characteristics of the pipe network by using the basic principle of the binary tree; when the pressure in the pipe network is transient, pressure difference is generated between the transient position and the adjacent region, and fluid in other regions flows to the leakage position, so that the density of the fluid in the adjacent region is reduced, and the pressure is also reduced, namely negative pressure waves; when a transient pressure event occurs at a certain position of a pipeline, negative pressure waves which are transmitted at a certain speed are generated at an accident point, and when the negative pressure waves are transmitted to two ends of a tree node, the sampling value of a pressure sensor is reduced;
placing a plurality of pressure wave sensors (pressure wave collectors) on fixed points according to a certain geometric relationship to form a sensor array, measuring and calculating the relative time difference of pressure wave change transmitted to each sensor caused by the same fault source, and substituting the relative time difference into an equation set meeting the geometric relationship of the sensor array for solving to obtain the position coordinate of an acoustic emission source; the negative pressure wave has energy loss in the process of transmission, namely the intensity of a negative pressure wave signal is attenuated along with the increase of the distance between the measuring point and the sound emission source; according to the characteristic, the area where the sound emission source is located can be roughly determined by analyzing the signal intensity of the negative pressure wave received by the sensor; by analyzing the attenuation characteristic of the negative pressure wave signal, the acoustic emission source can be accurately positioned.
In this embodiment, the method for sending fault information according to fault diagnosis and location includes: generating corresponding fault suggestions according to fault diagnosis and positioning; the fault information includes: fault diagnosis, localization and recommendation (corresponding repair resolution recommendation generated from fault).
Example 2
On the basis of embodiment 1, this embodiment 2 further provides an operation monitoring terminal, where the operation monitoring terminal is adapted to perform fault feature parameter extraction according to the preprocessed information, perform fault diagnosis according to the fault features, perform fault location, and send fault information according to the fault diagnosis and the fault location.
In this embodiment, the operation monitoring terminal is adapted to perform, by using the pressure wave pattern recognition-based pipe network fault diagnosis and location method according to embodiment 1, fault feature parameter extraction according to the preprocessed information, fault diagnosis according to the fault features, location of the fault, and sending of fault information according to the fault diagnosis and location.
Example 3
On the basis of the embodiments 1 and 2, the present embodiment 3 further provides a pressure wave collecting node, which is provided with a pressure wave collector to collect information and transmit the information, that is, to collect a transient pressure wave signal in the pipe network of the diagnosed pipe network system and transmit the transient pressure wave signal.
In this embodiment, the pressure wave collecting node is adapted to collect transient pressure wave signals by using the information collecting method described in embodiment 1.
Example 4
FIG. 6 is a schematic block diagram of a pipe network fault diagnosis and location system based on pressure wave pattern recognition according to the present invention;
fig. 7 is a conceptual diagram of the overall data transmission process of the pipe network fault diagnosis and positioning system based on pressure wave pattern recognition according to the present invention.
As shown in fig. 6 and 7, on the basis of embodiments 1,2 and 3, this embodiment 4 further provides a system for diagnosing and locating a fault of a pipe network based on pressure wave pattern recognition, including: the system comprises a plurality of pressure wave acquisition nodes (namely local nodes in the graph), an operation monitoring terminal (or an external network server) and an upper computer; the upper computer can adopt a computer, a browser and the like without limitation; the pressure wave acquisition nodes are provided with pressure wave collectors (the pressure wave collectors can be arranged on the wireless terminal) to acquire information and send the information to the upper computer, namely, transient pressure wave signals in the network pipe of the system of the diagnosed pipe network are acquired and sent to the upper computer; the upper computer is suitable for preprocessing information and sending the preprocessed information to the operation monitoring terminal; the operation monitoring terminal is suitable for extracting fault characteristic parameters according to the preprocessed information, diagnosing faults according to the fault characteristic parameters, positioning the faults and sending fault information to the upper computer according to the fault diagnosis and the positioning.
The sensor signals collected in the pressure wave collecting nodes are subjected to signal conversion through the pressure transmitter, and as very much noise exists, the collected signals are subjected to signal noise elimination and filtration treatment; then, signal preprocessing (such as signal filtering processing, time sequence alignment and the like) can be performed on the upper computer, and then pressure information is transmitted to an operation monitoring terminal by using a wireless communication technology to perform pipe network fault diagnosis and positioning; other preprocessing steps of signals can also be carried out on the lower computer.
In summary, the invention collects information; information preprocessing is carried out; extracting fault characteristic parameters according to the preprocessed information; carrying out fault diagnosis according to the fault characteristic parameters; positioning the fault; and fault information is sent according to fault diagnosis and positioning, so that more real assessment and practical feasibility are provided for realizing intellectualization, intellectualization and safe operation of the heat supply system, more accurate fault types and corresponding repair suggestions are provided for pipe network operators, and a set of complete intelligent fault diagnosis and positioning method and system for the heat supply pipe network are provided.
In the embodiments provided in the present application, it should be understood that the disclosed apparatus and method can be implemented in other ways. The apparatus embodiments described above are merely illustrative, and for example, the flowchart and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods and computer program products according to various embodiments of the present invention. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). It should also be noted that, in some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. It will also be noted that each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
In addition, the functional modules in the embodiments of the present invention may be integrated together to form an independent part, or each module may exist separately, or two or more modules may be integrated to form an independent part.
The functions, if implemented in the form of software functional modules and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In light of the foregoing description of the preferred embodiment of the present invention, many modifications and variations will be apparent to those skilled in the art without departing from the spirit and scope of the invention. The technical scope of the present invention is not limited to the content of the specification, and must be determined according to the scope of the claims.
Claims (10)
1. A pipe network fault diagnosis and positioning method based on pressure wave mode identification is characterized by comprising the following steps:
collecting information;
information preprocessing is carried out;
extracting fault characteristic parameters according to the preprocessed information;
carrying out fault diagnosis according to the fault characteristic parameters;
positioning the fault; and
and sending fault information according to fault diagnosis and positioning.
2. The pipe network fault diagnosis and location method of claim 1,
the information acquisition method comprises the following steps:
transient pressure wave signals in the pipe are collected through a pressure wave collector arranged on a pipe network of the diagnosed pipe network system.
3. The pipe network fault diagnosis and location method of claim 2,
the information preprocessing method comprises the following steps:
and performing signal denoising processing, signal filtering processing and time sequence alignment on the acquired transient pressure wave signals, and storing the acquired transient pressure wave signals to form a global database of a historical database and real-time data.
4. The pipe network fault diagnosis and localization method of claim 3,
the method for extracting the fault characteristic parameters according to the preprocessed information comprises the following steps:
through wavelet transformation, multilayer wavelet decomposition is carried out on transient pressure wave change signals, interference noise in the signals is eliminated by adopting a heuristic wavelet threshold method, and fault characteristic parameters sensitive to leakage in a time-frequency domain, namely the fault characteristic parameters are extracted from noise reduction signals
The wavelet mother function psi (t) is stretched and translated to obtain the function psia,τ(t)：
Wherein a is a scaling factor; τ is a translation factor; psia,τ(t) is the wavelet basis function dependent on parameters a and τ;
function f (t) continuous wavelet transform CWT, whose expression is:
carrying out discrete binary wavelet transform on the noisy signal, denoising the noisy signal on n-layer scales by adopting different threshold methods respectively, and reconstructing a waveform, wherein the signal reconstruction method comprises the following steps:
wherein l, k is 1,2, … N, l, k are time sequence numbers, and N is a maximum time sequence number; j represents the number of layers;
h and g are respectively wavelet low-pass filter and band-pass filter coefficients;
and if the statistical indexes are suitable for reflecting the leakage characteristics of the pipe network, the calculation method of each fault characteristic parameter comprises the following steps:
peak value: xamax＝max{|xi|}；
Average amplitude value:
variance:
square root amplitude:
kurtosis:
energy ratio:
wherein x isi(i ═ 1, 2.., N) denotes the values of discrete points of the reconstructed signal.
5. The pipe network fault diagnosis and location method of claim 4,
the method for fault diagnosis according to the fault characteristic parameters comprises the following steps:
according to a heuristic optimization algorithm and a BP neural network, constructing an optimization and neural network fusion structure of pipe network fault characteristic parameters, and completing the initial identification of the sensor node on the fault, namely
Constructing a corresponding relation between the waveform characteristics of the fault and the fault type, namely a diagnosis matrix; describing the influence factor of each characteristic on the corresponding fault type through a weight matrix table; training by adopting a machine learning algorithm to obtain a fault characteristic vector, performing pattern recognition and matching with a diagnosis matrix, and determining the transient pressure fault type;
before diagnosis, initializing a weight value by using data in a global database;
taking the extracted fault characteristic parameters as an input layer, training the network through training sample data, and reversely adjusting the connection weight and the threshold value among the neurons according to an error result until the training progress is reached;
the number of neurons in the output layer of the neural network is m, and the ideal output vector is Tout，Tout＝(0,0…1)，ρi∈[0,1]；
After the neural network training is output, all data information collected by the pipe network is converted into a characteristic vector suitable for fault diagnosis:
Tout＝[ρ1,ρ2,ρ3,...ρi,...ρm]；
wherein the content of the first and second substances,
ρiindicating a feature vector, 0 indicating that the feature vector is not present in the data information, and 1 indicating that the feature vector is present.
6. The pipe network fault diagnosis and location method of claim 5,
the method for positioning the fault comprises the following steps:
after the fault type is determined, traversing all node data in the pipe network by a traversal binary method, calculating the time difference of the pressure wave collectors at the upstream end and the downstream end receiving the pressure signal, and further determining the fault position; and
through the repeated positioning algorithm of the nodes of the multi-pressure wave collector, the fault position is accurately positioned, namely
Grouping and pairing all signals according to the average amplitude of the single-mode acoustic emission signals obtained by wavelet decomposition, obtaining the position of a leakage point positioned by each pair of signals through waveform cross-correlation analysis, and finally performing weighted averaging to accurately position the fault position.
7. The pipe network fault diagnosis and location method of claim 6,
the method for sending the fault information according to the fault diagnosis and the positioning comprises the following steps:
generating corresponding fault suggestions according to fault diagnosis and positioning;
the fault information includes: fault diagnosis, localization and recommendation.
8. An operation monitoring terminal is characterized in that,
the operation monitoring terminal is suitable for extracting fault characteristic parameters according to the preprocessed information, diagnosing faults according to the fault characteristics, positioning the faults and sending fault information according to the fault diagnosis and the positioning.
9. A pressure wave collection node comprising a plurality of pressure wave collection nodes,
the pressure wave acquisition node is provided with a pressure wave collector to acquire information and send the information, namely acquiring transient pressure wave signals in a network pipe of the system of the diagnosed pipe network and sending the transient pressure wave signals.
10. A pipe network fault diagnosis and positioning system based on pressure wave mode identification is characterized by comprising:
the system comprises a plurality of pressure wave acquisition nodes, an operation monitoring terminal and an upper computer;
the pressure wave acquisition nodes are provided with pressure wave collectors for acquiring information and sending the information to the upper computer, namely acquiring transient pressure wave signals in the pipe network of the system of the diagnosed pipe network and sending the transient pressure wave signals to the upper computer;
the upper computer is suitable for preprocessing information and sending the preprocessed information to the operation monitoring terminal;
the operation monitoring terminal is suitable for extracting fault characteristic parameters according to the preprocessed information, diagnosing faults according to the fault characteristic parameters, positioning the faults and sending fault information to the upper computer according to the fault diagnosis and the positioning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010485209.7A CN111695465B (en) | 2020-06-01 | 2020-06-01 | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010485209.7A CN111695465B (en) | 2020-06-01 | 2020-06-01 | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111695465A true CN111695465A (en) | 2020-09-22 |
| CN111695465B CN111695465B (en) | 2024-03-05 |
Family
ID=72479117
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010485209.7A Active CN111695465B (en) | 2020-06-01 | 2020-06-01 | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111695465B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112985790A (en) * | 2021-02-07 | 2021-06-18 | 中国石油大学(北京) | Heat exchanger operation monitoring and fault diagnosis method and system |
| CN116906313A (en) * | 2023-09-12 | 2023-10-20 | 山东亿昌装配式建筑科技有限公司 | Intelligent control system for building energy-saving water supply and drainage |
| CN116793574B (en) * | 2023-08-25 | 2023-11-07 | 新誉集团有限公司 | Fault detection method and system for train pressure wave sensor |
Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1184931A (en) * | 1996-12-11 | 1998-06-17 | 唐秀家 | Method and apparatus for detecting and positioning leakage of fluid transferring pipeline |
| CN1435678A (en) * | 2002-07-04 | 2003-08-13 | 东北大学 | Method and device for intelligent diagnosis and location of leakage fault of fluid delivery pipeline |
| KR100883446B1 (en) * | 2008-02-25 | 2009-02-13 | 주식회사 렉터슨 | Defect diagnostics system and method using acoustic emission |
| US20100106458A1 (en) * | 2008-10-28 | 2010-04-29 | Leu Ming C | Computer program and method for detecting and predicting valve failure in a reciprocating compressor |
| CN101718396A (en) * | 2009-11-30 | 2010-06-02 | 东北大学 | Method and device for detecting leakage of fluid conveying pipeline based on wavelet and mode identification |
| KR20110060632A (en) * | 2009-11-30 | 2011-06-08 | 주식회사 렉터슨 | Acoustics and vibration complex sensing unit for defect of plant and defect diagnostics system for high pressure pipe |
| CN102095588A (en) * | 2010-12-28 | 2011-06-15 | 中国人民解放军军事交通学院 | Intelligent fault diagnosis method for diesel engine |
| CN103245454A (en) * | 2013-05-14 | 2013-08-14 | 西南石油大学 | Non-intrusive pipeline real-time monitoring, prewarning and fault locating system |
| CN103491651A (en) * | 2013-09-25 | 2014-01-01 | 河海大学 | Abnormal/fault positioning detection method based on binomial tree model |
| US20140201571A1 (en) * | 2005-07-11 | 2014-07-17 | Brooks Automation, Inc. | Intelligent condition monitoring and fault diagnostic system for preventative maintenance |
| US20150061659A1 (en) * | 2012-03-02 | 2015-03-05 | Speir Hunter Ltd. | Fault detection for pipelines |
| CN105844051A (en) * | 2016-04-12 | 2016-08-10 | 中国科学院上海高等研究院 | Detection method of oil and gas pipeline slow leakage on basis of negative pressure wave signal sparse representation |
| US20170055356A1 (en) * | 2014-03-28 | 2017-02-23 | Siemens Aktiengesellschaft | Pressure compensator failure detection |
| CN107368799A (en) * | 2017-07-12 | 2017-11-21 | 内蒙古大学 | Leakage detection and localization method based on multiple features and adaptive time delay stimation |
| CN108870091A (en) * | 2018-07-19 | 2018-11-23 | 东北大学 | Line leakage system and method based on low-and high-frequency hybrid detection |
| CN109838696A (en) * | 2019-01-09 | 2019-06-04 | 常州大学 | Pipeline fault diagnostic method based on convolutional neural networks |
| CN111191727A (en) * | 2019-12-31 | 2020-05-22 | 北京建筑大学 | Gas pressure regulator fault diagnosis method, system, terminal and computer storage medium based on PSO-KPCA-LVQ |
-
2020
- 2020-06-01 CN CN202010485209.7A patent/CN111695465B/en active Active
Patent Citations (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1184931A (en) * | 1996-12-11 | 1998-06-17 | 唐秀家 | Method and apparatus for detecting and positioning leakage of fluid transferring pipeline |
| CN1435678A (en) * | 2002-07-04 | 2003-08-13 | 东北大学 | Method and device for intelligent diagnosis and location of leakage fault of fluid delivery pipeline |
| US20140201571A1 (en) * | 2005-07-11 | 2014-07-17 | Brooks Automation, Inc. | Intelligent condition monitoring and fault diagnostic system for preventative maintenance |
| KR100883446B1 (en) * | 2008-02-25 | 2009-02-13 | 주식회사 렉터슨 | Defect diagnostics system and method using acoustic emission |
| US20100106458A1 (en) * | 2008-10-28 | 2010-04-29 | Leu Ming C | Computer program and method for detecting and predicting valve failure in a reciprocating compressor |
| CN101718396A (en) * | 2009-11-30 | 2010-06-02 | 东北大学 | Method and device for detecting leakage of fluid conveying pipeline based on wavelet and mode identification |
| KR20110060632A (en) * | 2009-11-30 | 2011-06-08 | 주식회사 렉터슨 | Acoustics and vibration complex sensing unit for defect of plant and defect diagnostics system for high pressure pipe |
| CN102095588A (en) * | 2010-12-28 | 2011-06-15 | 中国人民解放军军事交通学院 | Intelligent fault diagnosis method for diesel engine |
| US20150061659A1 (en) * | 2012-03-02 | 2015-03-05 | Speir Hunter Ltd. | Fault detection for pipelines |
| CN103245454A (en) * | 2013-05-14 | 2013-08-14 | 西南石油大学 | Non-intrusive pipeline real-time monitoring, prewarning and fault locating system |
| CN103491651A (en) * | 2013-09-25 | 2014-01-01 | 河海大学 | Abnormal/fault positioning detection method based on binomial tree model |
| US20170055356A1 (en) * | 2014-03-28 | 2017-02-23 | Siemens Aktiengesellschaft | Pressure compensator failure detection |
| CN105844051A (en) * | 2016-04-12 | 2016-08-10 | 中国科学院上海高等研究院 | Detection method of oil and gas pipeline slow leakage on basis of negative pressure wave signal sparse representation |
| CN107368799A (en) * | 2017-07-12 | 2017-11-21 | 内蒙古大学 | Leakage detection and localization method based on multiple features and adaptive time delay stimation |
| CN108870091A (en) * | 2018-07-19 | 2018-11-23 | 东北大学 | Line leakage system and method based on low-and high-frequency hybrid detection |
| CN109838696A (en) * | 2019-01-09 | 2019-06-04 | 常州大学 | Pipeline fault diagnostic method based on convolutional neural networks |
| CN111191727A (en) * | 2019-12-31 | 2020-05-22 | 北京建筑大学 | Gas pressure regulator fault diagnosis method, system, terminal and computer storage medium based on PSO-KPCA-LVQ |
Non-Patent Citations (2)
| Title |
|---|
| 燕宗伟: "基于神经网络的管道泄漏检测研究", 中国优秀硕士论文电子期刊, 31 January 2020 (2020-01-31), pages 019 - 895 * |
| 王立坤;赵晋云;付松广;谭东杰;李健;靳世久;: "基于神经网络的管道泄漏声波信号特征识别", no. 3, pages 483 - 485 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112985790A (en) * | 2021-02-07 | 2021-06-18 | 中国石油大学(北京) | Heat exchanger operation monitoring and fault diagnosis method and system |
| CN116793574B (en) * | 2023-08-25 | 2023-11-07 | 新誉集团有限公司 | Fault detection method and system for train pressure wave sensor |
| CN116906313A (en) * | 2023-09-12 | 2023-10-20 | 山东亿昌装配式建筑科技有限公司 | Intelligent control system for building energy-saving water supply and drainage |
| CN116906313B (en) * | 2023-09-12 | 2023-11-28 | 山东亿昌装配式建筑科技有限公司 | Intelligent control system for building energy-saving water supply and drainage |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111695465B (en) | 2024-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
| CN111695465B (en) | Pipe network fault diagnosis and positioning method and system based on pressure wave mode identification | |
| CN108488638B (en) | Line leakage system and method based on sound wave suction wave hybrid monitoring | |
| Romano et al. | Automated detection of pipe bursts and other events in water distribution systems | |
| CN108931387B (en) | Fault diagnosis method based on multi-sensor signal analysis and capable of providing accurate diagnosis decision | |
| CN100456010C (en) | Method for detecting leakage of oil gas pipe based on pressure signal knee | |
| CN104061445A (en) | Pipeline leakage detection method based on neural network | |
| CN113935439B (en) | Fault detection method, equipment, server and storage medium for drainage pipe network | |
| CN108804740B (en) | Long-distance pipeline pressure monitoring method based on integrated improved ICA-KRR algorithm | |
| CN103953490A (en) | Implementation method for monitoring status of hydraulic turbine set based on HLSNE | |
| Zheng et al. | An online real-time estimation tool of leakage parameters for hazardous liquid pipelines | |
| CN112016251A (en) | Nuclear power device fault diagnosis method and system | |
| CN101012913A (en) | Chaos analysis and micro-processor based conduit pipe micro-leakage diagnosing method and device | |
| CN113987908A (en) | Natural gas pipe network leakage early warning method based on machine learning method | |
| Wang et al. | Pipeline leak detection method based on acoustic-pressure information fusion | |
| CN109613109A (en) | A kind of Pipeline Magnetic Flux Leakage Inspection automatic data analysis system | |
| Chen et al. | Fault diagnosis of full-hydraulic drilling rig based on RS–SVM data fusion method | |
| CN113344275A (en) | Floating platform wave climbing online forecasting method based on LSTM model | |
| Nasimi et al. | Signal de-noising methods for fault diagnosis and troubleshooting at CANDU® stations | |
| Gao et al. | Leakage detection of pipeline based on weighted-permutation entropy | |
| CN112413413B (en) | Pipeline leakage monitoring and positioning method combining deep learning and multiple measurement technology | |
| Lei et al. | Burst detection for district metering areas based on soft-voting ensemble model in water distribution system | |
| CN112182959A (en) | Leakage detection method for water distribution pipe network | |
| He et al. | An adaptive interval forecast CNN model for fault detection method | |
| CN114139648B (en) | Intelligent detection method and system for abnormity of tailing filling pipeline |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 310000 rooms 208, 209-1, 209-2, building 2, 88 Longyuan Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province Applicant after: Zhejiang Yingji Power Technology Co.,Ltd. Address before: 310000 rooms 208, 209-1, 209-2, building 2, 88 Longyuan Road, Cangqian street, Yuhang District, Hangzhou City, Zhejiang Province Applicant before: Hangzhou Yingji Power Technology Co.,Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |