CN108875841A - A kind of pumped storage unit vibration trend forecasting method - Google Patents
A kind of pumped storage unit vibration trend forecasting method Download PDFInfo
- Publication number
- CN108875841A CN108875841A CN201810692295.1A CN201810692295A CN108875841A CN 108875841 A CN108875841 A CN 108875841A CN 201810692295 A CN201810692295 A CN 201810692295A CN 108875841 A CN108875841 A CN 108875841A
- Authority
- CN
- China
- Prior art keywords
- unit
- signal
- trend
- vibration
- prediction
- 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.)
- Withdrawn
Links
- 238000013277 forecasting method Methods 0.000 title abstract 2
- 238000000034 method Methods 0.000 claims abstract description 57
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 34
- 238000011156 evaluation Methods 0.000 claims abstract description 16
- 238000004458 analytical method Methods 0.000 claims abstract description 15
- 238000012098 association analyses Methods 0.000 claims abstract description 11
- 238000011161 development Methods 0.000 claims abstract description 4
- 239000011159 matrix material Substances 0.000 claims description 32
- 238000005086 pumping Methods 0.000 claims description 16
- 238000012843 least square support vector machine Methods 0.000 claims description 12
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000002955 isolation Methods 0.000 claims description 9
- 230000005540 biological transmission Effects 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 7
- 238000001228 spectrum Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 5
- 238000005065 mining Methods 0.000 claims description 5
- 238000012417 linear regression Methods 0.000 claims description 4
- 238000004445 quantitative analysis Methods 0.000 claims description 4
- 230000009466 transformation Effects 0.000 claims description 4
- 241001123248 Arma Species 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 239000000470 constituent Substances 0.000 claims description 3
- 230000007423 decrease Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000010977 unit operation Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 3
- 230000002123 temporal effect Effects 0.000 abstract 1
- 230000008569 process Effects 0.000 description 4
- 238000012097 association analysis method Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000004092 self-diagnosis Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of pumped storage unit vibration trend forecasting methods,It first obtains the history and real time data of unit nonstationary vibration online,User terminal is passed data to again,Time-Frequency Analysis is carried out to vibration signal followed by experience wavelet decomposition,Then Energy-Entropy and singular value comprehensive characteristics are extracted,Then analysis is associated with unit operating condition according to after certain rule progress sliding-model control to signal characteristic data acquisition system,Frequent-item is carried out using Apriori algorithm,Parse the temporal correlation of data characteristics and unit failure,Unit safety operation region is marked off by association analysis result,Finally construct time series models,Using time series trend prediction technique,Predict the development trend in its following finite time,And then operating states of the units trend is predicted and assessed,Technical support is provided to implement set state maintenance.The present invention can not only Accurate Prediction trend, also have the advantages that evaluation index relatively comprehensively and assessment more conveniently.
Description
Technical Field
The invention relates to a method for predicting vibration trend of a pumping storage unit.
Background
The water pump turbine set of the pumped storage power station has the advantages of complex working condition, frequent start and stop, more vibration parts, wide distribution and more influence factors (including hydraulic factors, mechanical factors and electromagnetic factors). The trend prediction method widely used at present is to obtain a historical data trend graph of the vibration state of the unit through an online monitoring system, to subjectively analyze the possible later operation state of the unit, or to use a least square method to realize regression fitting on characteristic parameters, but vibration signals are generally nonlinear and non-stable, so that the traditional mathematical statistics method is difficult to realize accurate trend prediction on the state of the vibration signals. Due to improper selection of the weights of the analytic hierarchy process, the requirement for judging the consistency of the matrix cannot be met, and an evaluation index reflecting the overall state of the pumping and storage unit cannot be obtained. Therefore, the existing pumping unit vibration trend prediction method has the problems of inaccurate trend prediction and incomplete evaluation index.
Disclosure of Invention
The invention aims to provide a vibration trend prediction method for a pumping unit. The method not only can accurately predict the trend, but also has the advantage of relatively comprehensive evaluation indexes.
The technical scheme of the invention is as follows: a vibration trend prediction method for a pumping unit comprises the following steps:
a1, acquiring online data, namely acquiring historical and real-time data of non-stationary vibration of the unit online from a pumped storage power station vibration monitoring and monitoring system by adopting a 485 communication protocol;
b1, data transmission, converting the history and real-time data of the non-stationary vibration of the unit acquired on line into a non-stationary vibration signal of the unit, and transmitting the non-stationary vibration signal to a user terminal through a network isolation device, a WEB server, a hardware firewall and a power plant local area network in sequence;
c1, analyzing signals, namely, performing time-frequency domain analysis on the non-stationary vibration signals of the unit by the user terminal through empirical wavelet decomposition on the non-stationary vibration signals of the unit;
d1, extracting features, namely extracting comprehensive features describing the vibration state of the unit from the non-stationary vibration signals of the unit on the basis of performing time-frequency domain analysis on the non-stationary vibration signals of the unit by using empirical wavelet decomposition to obtain an energy entropy and singular values;
e1, association and quantitative analysis of vibration, decomposing a vibration signal for a data set of energy entropy and singular value by using Ensemble Empirical Mode Decomposition (EEMD) or an improved empirical wavelet decomposition (EWT) to obtain a series of single frequency components, carrying out discretization treatment and then carrying out association analysis on the vibration signal and the operation condition of the unit, carrying out frequent item mining by using an Apriori algorithm, analyzing the time-space correlation between the vibration data characteristics of the unit and the fault of the unit, and dividing a safe operation area of the unit according to the association analysis result;
f1, constructing a time series decomposition model, a multiple linear regression model and an ARMA model, predicting the development trend within limited time in the future by adopting a time series trend prediction method, further predicting and evaluating the unit operation state trend, and providing technical support for implementing unit state overhaul.
In the foregoing method for predicting a vibration trend of a storage unit, the method for predicting a time series trend in step f1 includes the following steps:
a2, extracting a time sequence of the state parameters of the unit;
b2, decomposing the time sequence of the unit state parameters into subsequences of different decomposition domains by using empirical wavelet decomposition to obtain a fluctuation term of stationarity and a nonlinear trend term;
c2, obtaining a signal A by adopting an AR prediction model for a fluctuation item of stationarity, and obtaining a signal B by adopting a prediction model of a least square support vector machine for a nonlinear trend item;
d2, reconstructing the signal A and the signal B to realize the prediction of the unit state trend.
In the aforementioned prediction method for the vibration trend of the pumped storage unit, in step b1, data transmission may also be performed to convert online acquired history of non-stationary vibration of the unit and real-time data into a non-stationary vibration signal of the unit, and the non-stationary vibration signal is transmitted to the APP on the mobile terminal through the network isolation device, the WEB server, the hardware firewall and the ali cloud in sequence.
In the aforementioned prediction method for the vibration trend of the pumping and storage unit, the prediction model of the least square support vector machine is expressed as
Where X is the input vector, n is a constant, k is one of values 1-n, m is the spatial dimension, and τ is the delay time constant.
In the aforementioned method for predicting vibration trend of pumped storage unit, the AR model is expressed as
In the formula:is an autoregressive parameter, i is 1 … p, and p is an order; a istIs white noise, representing the residual.
In the prediction method for the vibration trend of the storage unit, the order of the model is determined according to the AIC criterion during modeling of the AR model, and the parameter of the model is estimated.
In the foregoing method for predicting a vibration trend of a storage unit, the method for reconstructing a signal in step d2 includes the following steps:
a3, performing multilayer wavelet decomposition on the time sequence of the unit state parameters to obtain each layer of subsequence describing a trend term and a fluctuation term:
X＝ak+d１+d2+…+dk
in the formula, akAs a trend term, diFor the fluctuation term, i is 1, 2, …, k is the wavelet decomposition layer number;
b3 for trend item akEstablishing an LSSVM prediction model, carrying out model training and new value prediction, and accurately evaluating the result;
c3, for each fluctuation term diThe results are evaluated in terms of accuracy by performing AR modeling on the i-1, 2, … and k respectively;
d3, obtaining the prediction results of the trend item and each fluctuation item, and then carrying out superposition calculation to obtain the prediction sequence of the original vibration sequenceCalculating error indexes of the measured value and the predicted value, and performing precision evaluation;
e3, evaluating the precision of the prediction result of the original vibration sequence, analyzing the deviation degree of the prediction result and the actual value, and adopting the following common error indexes for evaluating the prediction effect.
In the aforementioned method for predicting vibration trend of pumping and storage unit, the common error index includes
Average relative error:and
root mean square error:
where k is a value from 1 to N,are averages.
In the aforementioned method for predicting vibration trend of pumping and storage unit, the signal analysis shows that, for a signal f (t), EWT decomposes the signal f into mode functions f of N +1 single frequency componentsk(t)。
Wherein f iskThe AM-FM signal (AM-FM) of (t) may be defined as:
fk(t)＝Fk(t)cos(φk(t))
wherein k is a value of 0 to N, FkAs a function of the frequency domain, phikIs an angular vector.
Decomposition of non-stationary signals is desirable to be able to decompose f of the AM-FM component from the original signalk(t) of (d). EWT extracts the AM-FM component of a signal by an adaptive split fourier spectrum construction wavelet filter. Suppose that Fourier is supported by [0, π [ ]]Divided into N successive portions. Each section is made of ^nRepresents:
Λn＝[ωn-1，ωn]，n＝1，2，…，N
wherein, ω isnFor the boundary of each segment, ωnThe selection mode is many, and the terminal point between two adjacent maximum value points in the Fourier spectrum is generally taken, and omega0＝0，ωnPi. At omeganDefine one for the centerWidth of Tn＝2τnThe transition section of (1). For each lambda according to the construction mode of Meyer waveletnConstructing a bandpass filter with empirical wavelet functionsAnd empirical scale functionIs defined as:
wherein,
suppose the Fourier transform is denoted as F [ ·]Inverse Fourier transform is denoted F-1[·](ii) a Then defining empirical wavelet transform according to solving mode of traditional wavelet transform, and making detail coefficient of empirical wavelet transform be defined by empirical wavelet function psin(t) inner product of signal f (t):
empirical wavelet approximation coefficient is formed by signal f (t) and scale function Ψ1(t) obtaining an inner product of:
wherein,andfourier transform of an empirical wavelet function and a scale function, respectively;andrespectively, the complex conjugate of the empirical wavelet function and the scale function.
The original signal can be reconstructed from an empirical wavelet function and a scale function:
wherein denotes a convolution; Λ represents the fourier transform.
From this, the mode f decomposed by the empirical wavelet can be obtainedk(t)：
In the aforementioned method for predicting vibration trend of pumped storage unit, the feature extraction is represented by assuming that a series of modes are obtained after an original signal is subjected to empirical wavelet transform, and cs(t), s 1, 2, K being the number of layers after decomposition, E1,E2,…，EKIs the energy value corresponding to each layer mode. The energy characteristics are calculated as follows:
firstly, calculating the energy characteristics of each layer of mode:
the total energy value for all modes is then calculated:
finally, calculating energy entropy characteristics;
after signal experience wavelet transformation, singular value characteristics of all modes forming a matrix are extracted. The singular value feature is a series of eigenvectors obtained by performing singular value decomposition on the matrix. According to the matrix theory principle, a singular value is a value that reflects an intrinsic property of a matrix and has stability. Meanwhile, singular values have scale invariance and rotation invariance. Therefore, the singular value characteristic is a very reliable evaluation index for distinguishing different faults
After the original signal is subjected to empirical wavelet transform, the energy of each layer decreases from the first layer to the last layer, and when the current Q layer mode almost can contain most energy information of the original signal, the front Q layer mode is taken to construct an initial characteristic matrix A:
A＝[c１,c2，…，cQ]T
the size of the real number matrix A is assumed to be PQ, and the following conditions are satisfied:
A＝U∧VT
wherein U and V are orthogonal matrix of QQ and PP, respectively, Λ is a fault feature matrix of QP, and all constituent elements σi(i＝1，2，...，Q) (Q is less than or equal to P) is arranged from low to high according to the number of modal layers. These failure matrix elements are some of the singular values of matrix a. Thus will vector [ sigma ]1，σ2，...，σQ]As another fault feature.
Compared with the prior art, the method improves the existing pumping unit vibration trend prediction method, optimizes a prediction algorithm from multiple angles by establishing a trend prediction model reflecting key characteristic parameters of the unit vibration state, and constructs a prediction model based on time series combination; the method comprises the steps of extracting detailed characteristics of signals by adopting a wavelet transformation theory, decomposing unit vibration state parameters into a nonlinear trend term and a stable fluctuation term, respectively performing trend prediction by utilizing a Least Square Support Vector Machine (LSSVM) theory and an Autoregressive (AR) model, and finally reconstructing the signals by utilizing an addition principle to realize the trend prediction of the unit vibration state parameters, wherein the prediction of the vibration trend of the pumped storage unit is more accurate and the evaluation index is more comprehensive. In addition, the model is applied to the unit state online monitoring system, data are transmitted to the mobile terminal provided with TN8000APP through adding partial equipment and software interfaces (mainly comprising a WEB server, a transverse isolation device, a hardware firewall and a network switch) under the original framework of the unit state monitoring system of the pumped storage power station, the functions of monitoring and analyzing the unit state through the mobile terminal, pushing early warning and fault information in real time and the like are realized, the unit state is monitored through the TN8000APP through the mobile terminal, the vibration trend of the unit can be automatically analyzed, and the evaluation of the unit state by operation and maintenance personnel of the pumped storage power station is facilitated. Therefore, the method and the device can accurately predict the trend, and have the advantages of more comprehensive evaluation indexes and more convenient evaluation.
Drawings
FIG. 1 is a model for predicting the vibration trend of a storage unit of the present invention;
FIG. 2 is a flow chart of the Apriori algorithm;
FIG. 3 is a schematic diagram of a combined prediction model.
Detailed Description
The invention is further illustrated by the following figures and examples, which are not to be construed as limiting the invention.
Examples are given. A method for predicting a vibration trend of a storage unit, as shown in fig. 1, the prediction method mainly includes six steps, that is: the method comprises the steps of online data acquisition, data transmission, signal analysis, feature extraction, vibration association and quantitative analysis and trend prediction.
Firstly, acquiring online data, and acquiring history and real-time data of non-stationary vibration of a unit online from a system for monitoring and controlling vibration of a certain pumping and storage power station through related interface design and configuration, so as to provide information resources for signal analysis, feature extraction, state evaluation and fault diagnosis.
The second step of data transmission, namely converting the history of the non-stationary vibration of the unit and real-time data acquired on line into a non-stationary vibration signal of the unit, and transmitting the non-stationary vibration signal to a user terminal through a network isolation device, a WEB server, a hardware firewall and a power plant local area network in sequence; or converting the history and real-time data of the non-stationary vibration of the unit acquired on line into a non-stationary vibration signal of the unit, and transmitting the non-stationary vibration signal to the APP on the mobile terminal through the network isolation device, the WEB server, the hardware firewall and the Aliskiu cloud in sequence.
And thirdly, signal analysis, namely performing time-frequency domain analysis on the vibration signals by using empirical wavelet decomposition (EWT) for the non-stationary vibration signals of a certain pumping and storage unit.
For a signal f (t), EWT decomposes it into a modal function f of N +1 single frequency componentsk(t)。
Wherein f iskThe AM-FM signal (AM-FM) of (t) may be defined as:
fk(t)＝Fk(t)cos(φk(t))
wherein k is a value of 0 to N, FkAs a function of the frequency domain, phikIs an angular vector.
Decomposition of non-stationary signals is desirable to be able to decompose f of the AM-FM component from the original signalk(t) of (d). EWT extracts the AM-FM component of a signal by an adaptive split fourier spectrum construction wavelet filter. Suppose that Fourier is supported by [0, π [ ]]Divided into N successive portions. Each section is made of ^nRepresents:
∧n＝[ωn-1，ωn]，n＝1，2，…，N
wherein, ω isnFor the boundary of each segment, ωnThe selection mode is many, and the terminal point between two adjacent maximum value points in the Fourier spectrum is generally taken, and omega0＝0，ωnPi. At omeganDefining a width T for the centern＝2τnThe transition section of (1). For each lambda according to the construction mode of Meyer waveletnConstructing a bandpass filter with empirical wavelet functionsAnd empirical scale functionIs defined as:
wherein,
suppose the Fourier transform is denoted as F [ ·]Inverse Fourier transform is denoted F-1[·](ii) a Then defining empirical wavelet transform according to solving mode of traditional wavelet transform, and making detail coefficient of empirical wavelet transform be defined by empirical wavelet function psin(t) inner product of signal f (t):
empirical wavelet approximation coefficient is formed by signal f (t) and scale function Ψ1(t) obtaining an inner product of:
wherein,andfourier transform of an empirical wavelet function and a scale function, respectively;andrespectively, the complex conjugate of the empirical wavelet function and the scale function.
The original signal can be reconstructed from an empirical wavelet function and a scale function:
wherein denotes a convolution; Λ represents the fourier transform.
From this, the mode f decomposed by the empirical wavelet can be obtainedk(t)：
And fourthly, feature extraction, namely extracting comprehensive features such as energy entropy, singular values and the like describing the vibration state of the unit on the basis of signal analysis.
The entropy characteristics are indexes for measuring uncertainty and uncertainty, when a fault occurs, the fault position generates impact, so that the frequency response of a vibration signal relative to the fault position is changed, and the distribution and the size of energy are changed. Firstly, a series of modes are obtained after signals are subjected to empirical wavelet transform, and then energy characteristics and energy entropy characteristics are obtained for the modes. Compared with a fault signal, a normal working signal has stronger certainty and stationarity, so the signality metaphor of the normal working condition is larger in entropy value of the fault signal.
Assuming that the original signal is subjected to empirical wavelet transform to obtain a series of modes, cs(t), s ═ 1, 2, …, K, K being the number of layers after decomposition, E1，E2，…，EKIs the energy value corresponding to each layer mode. The energy characteristics are calculated as follows:
firstly, calculating the energy characteristics of each layer of mode:
the total energy value for all modes is then calculated:
finally, calculating energy entropy characteristics;
after signal experience wavelet transformation, singular value characteristics of all modes forming a matrix are extracted. The singular value feature is a series of eigenvectors obtained by performing singular value decomposition on the matrix. According to the matrix theory principle, a singular value is a value that reflects an intrinsic property of a matrix and has stability. Meanwhile, singular values have scale invariance and rotation invariance. Therefore, the singular value characteristic is a very reliable evaluation index for distinguishing different faults
After the original signal is subjected to empirical wavelet transform, the energy of each layer decreases from the first layer to the last layer, and when the current Q layer mode almost can contain most energy information of the original signal, the front Q layer mode is taken to construct an initial characteristic matrix A:
A＝[c１,c2，…，cQ]T
the size of the real number matrix A is assumed to be PQ, and the following conditions are satisfied:
A＝U∧VT
wherein U and V are orthogonal matrix of QQ and PP, respectively, Λ is a fault feature matrix of QP, and all constituent elements σi(i-1, 2, …, Q) (Q. ltoreq.P) according to the mode layerThe numbers are arranged from low to high. These failure matrix elements are some of the singular values of matrix a. Thus will vector [ sigma ]1，σ2，…，σQ]As another fault feature.
And fifthly, association and quantitative analysis of vibration, namely performing discretization treatment on a characteristic data set of the unit runout signal of a certain pumping and storage power station according to a certain rule, then performing association analysis on the characteristic data set and the operation condition of the unit, performing frequent item mining by using an Apriori algorithm, analyzing the time-space correlation between the vibration data characteristic of the unit and the unit fault, and dividing a safe operation area of the unit according to the association analysis result.
The Apriori algorithm is an effective data association analysis method for mining implicit data information and discovering frequent item sets, the frequent item sets are discovered by limiting candidates, and a flow chart is shown in fig. 2. The method for mining the discretized runout data of the pumped storage unit by using the Apriori algorithm comprises the following steps: firstly, through scanning the established pumping energy storage unit vibration signal characteristics and the operation state analysis database, the occurrence times of the unit operation state quantity are accumulated, state items meeting the set minimum support degree are collected, and a set of frequent 1 item sets is found and recorded as L1. Then, according to Apriori property, L1 is used to find the set of frequent 2-term sets, L2, L2 is used to find L3, and so on until no more frequent k-term sets can be found. And obtaining a safe operation area of the unit through correlation analysis between the runout signal and the state of the unit, and providing support for judging the operation safety domain of the unit.
And sixthly, predicting the trend, namely constructing a time series decomposition model, a multiple linear regression model and an ARMA model, predicting the development trend of the unit in the limited time in the future by adopting a time series trend prediction method, predicting and estimating the running state trend of the unit, and providing technical support for implementing the state overhaul of the unit.
The sixth step of predicting the trend of the vibration state of the unit is as follows: 1) extracting a unit state parameter time sequence; 2) the wavelet decomposition decomposes the time sequence of the state parameters of the unit into subsequences of different decomposition domains (nonlinear trend terms and stable fluctuation terms); 3) adopting an AR prediction model for a fluctuation item of stationarity, and adopting a prediction model of a least square support vector machine for a nonlinear trend item; 4) and reconstructing the signal to realize the prediction of the state trend of the unit. The specific implementation is as follows:
1) constructing an input vector based on time series modeling of a least square support vector machine:
the original time sequence is a group of one-dimensional measured values, and before the LSSVM model is established, phase space reconstruction needs to be carried out on the time sequence to obtain a corresponding phase space matrix which is used as an input vector of the LSSVM model.
Where X is the input vector, n is a constant, k is one of values 1-n, m is the spatial dimension, and τ is the delay time constant.
2) AR modeling
The random difference equation (AR model) of the linear regression model is expressed as:
in the formula:is an autoregressive parameter, i is 1 … p, and p is an order; a istIs white noise, representing the residual.
When the AR model is established, the order of the model needs to be determined and the parameter estimation of the model needs to be carried out. Common criteria for determining the order of the model are the AIC criterion:
in the formula: p is a modulusThe order of type; n is the number of data;prediction errors in different orders.
In the modeling process, the model order is given first, model parameters are estimated to obtain models of all orders, and finally the order corresponding to the first minimum value of AIC (p) is taken to determine the optimal order of the models, and finally the AR model can be determined.
Combinatorial predictive modeling
Setting the state quantity sequence of the hydroelectric generating set as Xt＝{X1…XnThe predictive modeling steps are as follows:
I. and performing multi-layer decomposition on the obtained product by using wavelet transform to obtain sub-sequences of each layer for describing a trend item and a fluctuation item:
X＝ak+d１+d2+…+dk
II. In the formula, akAs a trend term, diFor the fluctuation term, i is 1, 2, …, and k is the wavelet decomposition level number.
III for trend term akAnd establishing an LSSVM prediction model, carrying out model training and new value prediction, and accurately evaluating the result.
IV for each fluctuation term diAnd i is 1, 2, …, k is subjected to AR modeling respectively, and the result is subjected to precision evaluation.
V, after the prediction results of all the sequences are obtained, superposition calculation is carried out to obtain the prediction sequence of the original vibration sequenceAnd calculating error indexes of the measured value and the predicted value, and performing precision evaluation. The implementation process of the high-combination prediction model is shown in fig. 3.
VI, evaluating the prediction performance of the result, namely evaluating the precision of the prediction result, analyzing the deviation degree of the prediction result and an actual value, and evaluating the prediction effect by adopting the following common error indexes:
VII, average relative error:
VIII, root mean square error:
where k is a value from 1 to N,are averages.
The mobile terminal APP provided by the embodiment of the invention can monitor the state of the unit and analyze the trend through the mobile equipment, and simultaneously, can push the alarm, early warning and equipment fault information to the mobile equipment in real time.
In order to realize mobile application, related equipment is additionally arranged on the basis of the original pumping and storage power station unit state monitoring system, and mainly comprises a WEB server, a transverse isolation device, a hardware firewall and a network switch in a region III. The WEB server is deployed in the safety area III, is isolated from the area II through the unidirectional network isolation device, and data are transmitted to the WEB server from the area II in a unidirectional mode for management and storage. The WEB server is connected with the local area network through a firewall to release data to the local area network, and users on the local area network can monitor and analyze the data through special software. The WEB server is accessed to the Internet (using a private line or accessed through a local area network) through a firewall, is connected to a mobile application special server deployed on the Alice cloud, and issues state data, alarm and early warning information to the mobile terminal through the server, so that a mobile terminal user can browse and analyze data through a special APP. The data is stored on a WEB server and is released through a special server on the Ali cloud, and no data is stored on the Ali cloud. In order to ensure the safety of data, the transmission process of the data is encrypted, and the data is decrypted and displayed at the mobile terminal. To ensure security of the WEB server, the WEB server is only connected to the mobile application specific server over the Internet (via firewall security policies), and connections from other computers will be considered illegitimate and rejected.
The APP function of the mobile terminal mainly comprises the following aspects:
1) the system provides various visual charts such as a curve chart, a numerical table, a bar graph, a wave form chart, a frequency spectrogram and the like for a user to select, can monitor the state of the unit from different angles and different levels, and can master the running state of the unit at any time and any place.
2) And data analysis and trend prediction are carried out, and the system carries out prediction analysis on the unit state through a vibration trend prediction model, so that operation and maintenance personnel of the pumped storage power station can conveniently evaluate the unit state.
3) And event pushing, wherein the system can push early warning and warning information to the mobile terminal in real time, so that a user is reminded to pay attention to the state change of the unit in time, and accidents are prevented. The system also provides a function of inquiring historical event information.
4) The system self-diagnosis can monitor the state of the unit state monitoring system in real time through the mobile APP, including the state of the sensor, the state of the acquisition device, the state of a system network, the running state of software and the like, so that defects in the running process of the system can be found in time, and the long-term and stable running of the system is ensured.
Claims (10)
1. A vibration trend prediction method for a pumping unit is characterized by comprising the following steps:
a1, acquiring online data, namely acquiring historical and real-time data of non-stationary vibration of the unit online from a pumped storage power station vibration monitoring and monitoring system by adopting a 485 communication protocol;
b1, data transmission, converting the history and real-time data of the non-stationary vibration of the unit acquired on line into a non-stationary vibration signal of the unit, and transmitting the non-stationary vibration signal to a user terminal through a network isolation device, a WEB server, a hardware firewall and a power plant local area network in sequence;
c1, analyzing signals, namely, performing time-frequency domain analysis on the non-stationary vibration signals of the unit by the user terminal through empirical wavelet decomposition on the non-stationary vibration signals of the unit;
d1, extracting features, namely extracting comprehensive features describing the vibration state of the unit from the non-stationary vibration signals of the unit on the basis of performing time-frequency domain analysis on the non-stationary vibration signals of the unit by using empirical wavelet decomposition to obtain an energy entropy and singular values;
e1, association and quantitative analysis of vibration, decomposing a vibration signal for a data set of energy entropy and singular value by using Ensemble Empirical Mode Decomposition (EEMD) or empirical wavelet decomposition (EWT) to obtain a series of single-frequency components, performing discretization treatment and then performing association analysis on the vibration signal and the operation condition of the unit, performing frequent item mining by using an Apriori algorithm, analyzing the time-space correlation between the vibration data characteristics of the unit and the fault of the unit, and dividing a safe operation area of the unit according to the association analysis result;
f1, constructing a time series decomposition model, a multiple linear regression model and an ARMA model, predicting the development trend within limited time in the future by adopting a time series trend prediction method, further predicting and evaluating the unit operation state trend, and providing technical support for implementing unit state overhaul.
2. The method of claim 1, wherein the method comprises the steps of: the time series trend prediction method in the step f1 comprises the following steps:
a2, extracting a time sequence of the state parameters of the unit;
b2, decomposing the time sequence of the unit state parameters into subsequences of different decomposition domains by using empirical wavelet decomposition to obtain a fluctuation term of stationarity and a nonlinear trend term;
c2, obtaining a signal A by adopting an AR prediction model for a fluctuation item of stationarity, and obtaining a signal B by adopting a prediction model of a least square support vector machine for a nonlinear trend item;
d2, reconstructing the signal A and the signal B to realize the prediction of the unit state trend.
3. The method of claim 1, wherein the method comprises the steps of: in the step b1, data transmission may further convert the history of the non-stationary vibration of the unit and real-time data acquired online into a non-stationary vibration signal of the unit, and the non-stationary vibration signal is transmitted to the APP on the mobile terminal through the network isolation device, the WEB server, the hardware firewall and the ali cloud in sequence.
4. The method of claim 2, wherein the method comprises the steps of: the prediction model of the least square support vector machine is expressed as
Where X is the input vector, n is a constant, k is one of values 1-n, m is the spatial dimension, and τ is the delay time constant.
5. The method of claim 2, wherein the method comprises the steps of: the AR model is represented as
In the formula:is an autoregressive parameter, i is 1 … p, and p is an order; a istIs white noise, representing the residual.
6. The method of claim 5, wherein the method comprises the steps of: and determining the order of the model through an AIC (automatic aided objective) criterion and performing parameter estimation on the model when the AR model is modeled.
7. The method of claim 2, wherein the method comprises the steps of: method for reconstructing a signal in step d2, comprising the steps of:
a3, performing multilayer wavelet decomposition on the time sequence of the unit state parameters to obtain each layer of subsequence describing a trend term and a fluctuation term:
X＝ak+d1+d2+…+dk
in the formula, akAs a trend term, diFor the fluctuation term, i is 1, 2, …, k is the wavelet decomposition layer number;
b3 for trend item akEstablishing an LSSVM prediction model, carrying out model training and new value prediction, and accurately evaluating the result;
c3, for each fluctuation term diThe results are evaluated in terms of accuracy by performing AR modeling on the i-1, 2, … and k respectively;
d3, obtaining the prediction results of the trend item and each fluctuation item, and then carrying out superposition calculation to obtain the prediction sequence of the original vibration sequenceCalculating error indexes of the measured value and the predicted value, and performing precision evaluation;
e3, evaluating the precision of the prediction result of the original vibration sequence, analyzing the deviation degree of the prediction result and the actual value, and adopting the following common error indexes for evaluating the prediction effect.
8. The method of claim 7, wherein the method comprises the steps of: the common error index comprises
Average relative error:and
root mean square error:
where k is a value from 1 to N,are averages.
9. The method of claim 1, wherein the method comprises the steps of: the signal analysis is expressed as, for a signal f (t), EWT decomposes it into N +1 modal functions f of single frequency componentsk(t)。
Wherein f iskThe AM-FM signal (AM-FM) of (t) may be defined as:
fk(t)＝Fk(t)cos(φk(t))
wherein k is a value of 0 to N, FkAs a function of the frequency domain, phikIs an angular vector.
Decomposition of non-stationary signals is desirable to be able to decompose f of the AM-FM component from the original signalk(t) of (d). EWT extracts the AM-FM component of a signal by an adaptive split fourier spectrum construction wavelet filter. Suppose that Fourier is supported by [0, π [ ]]Divided into N successive portions. Each section is made of ^nRepresents:
∧n＝[ωn-1，ωn]，n＝1，2，...，N
wherein, ω isnFor the boundary of each segment, ωnThe selection mode is many, and the terminal point between two adjacent maximum value points in the Fourier spectrum is generally taken, and omega0＝0，ωnPi. At omeganDefining a width T for the centern＝2τnThe transition section of (1). For each lambda according to the construction mode of Meyer waveletnConstruction ofBandpass filter of empirical wavelet functionAnd empirical scale functionIs defined as:
wherein,
β(x)＝x4(35-84x+70x2-20x3)。
suppose the Fourier transform is denoted as F [ ·]Inverse Fourier transform is denoted F-1[·](ii) a Then defining empirical wavelet transform according to solving mode of traditional wavelet transform, and making detail coefficient of empirical wavelet transform be defined by empirical wavelet function psin(t) inner product of signal f (t):
empirical wavelet approximation coefficient is formed by signal f (t) and scale function Ψ1(t) obtaining an inner product of:
wherein,andfourier transform of an empirical wavelet function and a scale function, respectively;andrespectively, the complex conjugate of the empirical wavelet function and the scale function.
The original signal can be reconstructed from an empirical wavelet function and a scale function:
wherein denotes a convolution; Λ represents the fourier transform.
From this, the mode f decomposed by the empirical wavelet can be obtainedk(t)：
。
10. The method of claim 1, wherein the method comprises the steps of: the feature extraction is represented by assuming that the original signal is subjected to empirical wavelet transform to obtain a series of modes, cs(t), s ═ 1, 2, …, K, K being the number of layers after decomposition, E1,E2,…，EKIs the energy value corresponding to each layer mode. The energy characteristics are calculated as follows:
firstly, calculating the energy characteristics of each layer of mode:
the total energy value for all modes is then calculated:
finally, calculating energy entropy characteristics;
after signal experience wavelet transformation, singular value characteristics of all modes forming a matrix are extracted. The singular value feature is a series of eigenvectors obtained by performing singular value decomposition on the matrix. According to the matrix theory principle, a singular value is a value that reflects an intrinsic property of a matrix and has stability. Meanwhile, singular values have scale invariance and rotation invariance. Therefore, the singular value characteristic is a very reliable evaluation index for distinguishing different faults
After the original signal is subjected to empirical wavelet transform, the energy of each layer decreases from the first layer to the last layer, and when the current Q layer mode almost can contain most energy information of the original signal, the front Q layer mode is taken to construct an initial characteristic matrix A:
A＝[c1，c2，...，cQ]T
the size of the real number matrix A is assumed to be PQ, and the following conditions are satisfied:
A＝U∧VT
wherein U and V are orthogonal matrix of QQ and PP, respectively, Λ is a fault feature matrix of QP, and all constituent elements σi(i ═ 1, 2., Q) (Q ≦ P) is arranged in low to high order number of modal layers. These failure matrix elements are some of the singular values of matrix a. Thus will vector [ sigma ]1，σ2，...，σQ]As another fault feature.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810692295.1A CN108875841A (en) | 2018-06-29 | 2018-06-29 | A kind of pumped storage unit vibration trend forecasting method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810692295.1A CN108875841A (en) | 2018-06-29 | 2018-06-29 | A kind of pumped storage unit vibration trend forecasting method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108875841A true CN108875841A (en) | 2018-11-23 |
Family
ID=64296816
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810692295.1A Withdrawn CN108875841A (en) | 2018-06-29 | 2018-06-29 | A kind of pumped storage unit vibration trend forecasting method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108875841A (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946075A (en) * | 2018-12-25 | 2019-06-28 | 东北大学 | A kind of bearing condition monitoring and method for diagnosing faults |
| CN110175541A (en) * | 2019-05-13 | 2019-08-27 | 武汉大学 | A kind of method that sea level variability nonlinear trend is extracted |
| CN110298132A (en) * | 2019-07-05 | 2019-10-01 | 国家电网有限公司 | A kind of turbine-generator units bearing throw trend forecasting method |
| CN110673997A (en) * | 2019-09-06 | 2020-01-10 | 苏州浪潮智能科技有限公司 | Disk failure prediction method and device |
| CN110943481A (en) * | 2019-12-04 | 2020-03-31 | 重庆大学 | Unit combination method considering wind turbine generator safety domain with frequency response control |
| CN110991055A (en) * | 2019-12-08 | 2020-04-10 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN111489027A (en) * | 2020-04-08 | 2020-08-04 | 五凌电力有限公司近尾洲水电厂 | Hydroelectric generating set waveform data trend prediction method and system |
| CN111695248A (en) * | 2020-05-27 | 2020-09-22 | 淮阴工学院 | Rapid early warning method for degradation state trend of pumped storage unit |
| CN112668419A (en) * | 2020-12-17 | 2021-04-16 | 太原理工大学 | Engine emission prediction method based on vibration signal |
| CN112949986A (en) * | 2021-02-01 | 2021-06-11 | 中国人民解放军海军工程大学 | Steam power system operation stability evaluation method and system, electronic equipment and storage medium |
| CN113052370A (en) * | 2021-03-15 | 2021-06-29 | 哈尔滨工程大学 | Marine environment element statistical prediction method based on space-time experience orthogonal function |
| CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
| CN114298413A (en) * | 2021-12-28 | 2022-04-08 | 浙江大学 | Hydroelectric generating set runout trend prediction method |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
| CN114863651A (en) * | 2021-01-15 | 2022-08-05 | 湖南五凌电力科技有限公司 | Intelligent early warning method for monitoring state of auxiliary machine |
| CN115511880A (en) * | 2022-11-07 | 2022-12-23 | 长江勘测规划设计研究有限责任公司 | Method for identifying and measuring vibration amplitude and frequency of two shafts by using machine vision |
| CN115685949A (en) * | 2022-12-29 | 2023-02-03 | 深圳市信润富联数字科技有限公司 | Method and device for adjusting data sampling frequency in discrete machining production process |
| CN115795999A (en) * | 2022-10-26 | 2023-03-14 | 国网新源控股有限公司 | Performance abnormity early warning method for long-term service pumped storage unit |
| CN118287244A (en) * | 2024-03-22 | 2024-07-05 | 常熟市龙腾特种钢有限公司 | Intelligent adjustment control system and method for coal mill |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268658A (en) * | 2014-09-29 | 2015-01-07 | 招商局重庆交通科研设计院有限公司 | Bridge structure safety monitoring data prediction method |
| CN104899432A (en) * | 2015-05-19 | 2015-09-09 | 上海大学 | Kernel function combination-based PSO-LSSVM fluctuating wind speed prediction method |
| CN106529145A (en) * | 2016-10-27 | 2017-03-22 | 浙江工业大学 | Bridge monitoring data prediction method based on ARIMA-BP neural network |
-
2018
- 2018-06-29 CN CN201810692295.1A patent/CN108875841A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268658A (en) * | 2014-09-29 | 2015-01-07 | 招商局重庆交通科研设计院有限公司 | Bridge structure safety monitoring data prediction method |
| CN104899432A (en) * | 2015-05-19 | 2015-09-09 | 上海大学 | Kernel function combination-based PSO-LSSVM fluctuating wind speed prediction method |
| CN106529145A (en) * | 2016-10-27 | 2017-03-22 | 浙江工业大学 | Bridge monitoring data prediction method based on ARIMA-BP neural network |
Non-Patent Citations (5)
| Title |
|---|
| YUNXIAO FU等: ""Product function correntropy and its application in rolling bearing fault identification"", 《MEASUREMENT》 * |
| 姜鑫 等: ""数据挖掘技术在水电厂主设备状态检修中的应用研究"", 《水电自动化与大坝监测》 * |
| 孙慧芳 等: ""基于时间序列组合模型的水电机组状态趋势预测"", 《水力发电学报》 * |
| 罗萌: ""水电机组振动故障诊断与趋势预测研究"", 《万方数据库》 * |
| 陆冠鹏: ""深圳抽蓄机组在线监测系统设计"", 《吉林水利》 * |
Cited By (26)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109946075A (en) * | 2018-12-25 | 2019-06-28 | 东北大学 | A kind of bearing condition monitoring and method for diagnosing faults |
| CN110175541B (en) * | 2019-05-13 | 2022-06-14 | 武汉大学 | Method for extracting sea level change nonlinear trend |
| CN110175541A (en) * | 2019-05-13 | 2019-08-27 | 武汉大学 | A kind of method that sea level variability nonlinear trend is extracted |
| CN110298132A (en) * | 2019-07-05 | 2019-10-01 | 国家电网有限公司 | A kind of turbine-generator units bearing throw trend forecasting method |
| CN110673997A (en) * | 2019-09-06 | 2020-01-10 | 苏州浪潮智能科技有限公司 | Disk failure prediction method and device |
| CN110673997B (en) * | 2019-09-06 | 2023-01-10 | 苏州浪潮智能科技有限公司 | Disk failure prediction method and device |
| CN110943481A (en) * | 2019-12-04 | 2020-03-31 | 重庆大学 | Unit combination method considering wind turbine generator safety domain with frequency response control |
| CN110991055A (en) * | 2019-12-08 | 2020-04-10 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN110991055B (en) * | 2019-12-08 | 2022-09-16 | 中国航空综合技术研究所 | Residual life prediction system for rotary mechanical products |
| CN111489027A (en) * | 2020-04-08 | 2020-08-04 | 五凌电力有限公司近尾洲水电厂 | Hydroelectric generating set waveform data trend prediction method and system |
| CN111695248A (en) * | 2020-05-27 | 2020-09-22 | 淮阴工学院 | Rapid early warning method for degradation state trend of pumped storage unit |
| CN111695248B (en) * | 2020-05-27 | 2024-01-05 | 淮阴工学院 | Quick early warning method for degradation state trend of pumped storage unit |
| CN112668419A (en) * | 2020-12-17 | 2021-04-16 | 太原理工大学 | Engine emission prediction method based on vibration signal |
| CN112668419B (en) * | 2020-12-17 | 2022-05-24 | 太原理工大学 | Engine emission prediction method based on vibration signal |
| CN114863651A (en) * | 2021-01-15 | 2022-08-05 | 湖南五凌电力科技有限公司 | Intelligent early warning method for monitoring state of auxiliary machine |
| CN112949986A (en) * | 2021-02-01 | 2021-06-11 | 中国人民解放军海军工程大学 | Steam power system operation stability evaluation method and system, electronic equipment and storage medium |
| CN112949986B (en) * | 2021-02-01 | 2022-06-28 | 中国人民解放军海军工程大学 | Steam power system operation stability evaluation method and system, electronic equipment and storage medium |
| CN113052370A (en) * | 2021-03-15 | 2021-06-29 | 哈尔滨工程大学 | Marine environment element statistical prediction method based on space-time experience orthogonal function |
| CN113077172A (en) * | 2021-04-19 | 2021-07-06 | 瑞湖智科数据(苏州)有限公司 | Equipment state trend analysis and fault diagnosis method |
| CN114442543A (en) * | 2021-10-29 | 2022-05-06 | 南京河海南自水电自动化有限公司 | Computer monitoring method suitable for early warning of hydropower station fault |
| CN114298413B (en) * | 2021-12-28 | 2024-07-23 | 浙江大学 | Hydroelectric generating set runout trend prediction method |
| CN114298413A (en) * | 2021-12-28 | 2022-04-08 | 浙江大学 | Hydroelectric generating set runout trend prediction method |
| CN115795999A (en) * | 2022-10-26 | 2023-03-14 | 国网新源控股有限公司 | Performance abnormity early warning method for long-term service pumped storage unit |
| CN115511880A (en) * | 2022-11-07 | 2022-12-23 | 长江勘测规划设计研究有限责任公司 | Method for identifying and measuring vibration amplitude and frequency of two shafts by using machine vision |
| CN115685949A (en) * | 2022-12-29 | 2023-02-03 | 深圳市信润富联数字科技有限公司 | Method and device for adjusting data sampling frequency in discrete machining production process |
| CN118287244A (en) * | 2024-03-22 | 2024-07-05 | 常熟市龙腾特种钢有限公司 | Intelligent adjustment control system and method for coal mill |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875841A (en) | A kind of pumped storage unit vibration trend forecasting method | |
| CN108008332B (en) | New energy remote testing equipment fault diagnosis method based on data mining | |
| CN104504296B (en) | Gaussian of Mixture Hidden Markov Model and the method for predicting residual useful life of regression analysis | |
| CN102867132B (en) | The online fault combination forecasting method of aviation DC converter based on fractional wavelet transform | |
| Wang et al. | Bayesian dynamic forecasting of structural strain response using structural health monitoring data | |
| Wadduwage et al. | Identification of dominant low‐frequency modes in ring‐down oscillations using multiple Prony models | |
| CN106529145A (en) | Bridge monitoring data prediction method based on ARIMA-BP neural network | |
| EP2880578A2 (en) | Estimating remaining useful life from prognostic features discovered using genetic programming | |
| CN106874676B (en) | State evaluation method for electric energy metering device | |
| CN113947017A (en) | Method for predicting residual service life of rolling bearing | |
| Li et al. | A Hybrid Short‐Term Power Load Forecasting Model Based on the Singular Spectrum Analysis and Autoregressive Model | |
| CN114201825B (en) | Evaluation method and system for equipment performance degradation state based on combined characteristics | |
| CN109916634A (en) | A kind of aviation turbofan engine remaining life prediction technique and system | |
| Kumar et al. | Exhaust gas temperature data prediction by autoregressive models | |
| Anis | Towards remaining useful life prediction in rotating machine fault prognosis: an exponential degradation model | |
| CN117290685A (en) | Power plant power equipment expert diagnosis system and method based on historical data | |
| Rathinasamy et al. | Multiscale nonlinear model for monthly streamflow forecasting: a wavelet-based approach | |
| CN113740671A (en) | Fault arc identification method based on VMD and ELM | |
| CN116128690B (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| Kumar et al. | Measuring software reliability: a fuzzy model | |
| CN115600695B (en) | Fault diagnosis method for metering equipment | |
| JP7062505B2 (en) | Equipment management support system | |
| Luo et al. | A novel method for remaining useful life prediction of roller bearings involving the discrepancy and similarity of degradation trajectories | |
| Li | Remaining useful life prediction of bearings using fuzzy multimodal extreme learning regression | |
| Liu et al. | ESN-based Combination Method for Turbine Condition Prediction |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20181123 |
|
| WW01 | Invention patent application withdrawn after publication |