CN115828139A - Gate structure safety assessment and prediction method and system based on vibration signals - Google Patents
Gate structure safety assessment and prediction method and system based on vibration signals Download PDFInfo
- Publication number
- CN115828139A CN115828139A CN202211559652.XA CN202211559652A CN115828139A CN 115828139 A CN115828139 A CN 115828139A CN 202211559652 A CN202211559652 A CN 202211559652A CN 115828139 A CN115828139 A CN 115828139A
- Authority
- CN
- China
- Prior art keywords
- gate
- vibration
- vibration signal
- mathematical model
- bayesian theory
- 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
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
Abstract
The invention provides a method for evaluating and predicting the safety of a gate structure based on a vibration signal, which comprises the following steps: obtaining a vibration signal of the gate, and putting the vibration signal into a modal characteristic extraction model to obtain modal information characteristics; putting the modal information features into a mathematical model based on a Bayesian theory, wherein the mathematical model based on the Bayesian theory comprises a convolutional neural network and a support vector machine; the convolutional neural network extracts the features of the modal information, and the support vector machine classifies and regresses the extracted features to obtain feature signals; comparing the characteristic signal with a vibration standard to obtain a safety evaluation result of the gate; and placing the plurality of characteristic signals into a mathematical model based on the Bayesian theory for prediction to obtain a posterior distribution result, and obtaining a structure prediction result of the gate according to the posterior distribution result. The method shortens the test evaluation period of the gate, improves the monitoring precision of the gate, and can predict the future trend of the gate structure.
Description
Technical Field
The invention belongs to the technical field of gate vibration, and particularly relates to a gate structure safety assessment and prediction method and system based on a vibration signal.
Background
The reservoir gate is connected with the upstream and the downstream of the reservoir, the gate not only has the functions of retaining water and draining water, but also can adjust and control the water level of the reservoir and the discharge flow, so the stability of the reservoir gate structure is very important in hydraulic engineering. When the reservoir gate works, various water flow impacts can be applied to the reservoir gate, for example, when the reservoir gate is closed in a flood control stage, the water flow is increased rapidly, and the gate is vibrated due to the fluctuation of the water flow; when the gate is opened, the gate is vibrated by vortex, backflow and the like generated when water flows pass through the opening of the gate, and the gate is also vibrated by other external force; these vibrations may cause accelerated wear of some parts of the gate, reduce the life span, and may cause excessive stress on some components of the gate, resulting in fatigue damage, even damage to the gate and stop working, thus causing a great safety hazard in flood control of the reservoir.
Common gate vibration monitoring methods in the prior art comprise a prototype monitoring method, a model experiment method and a data analysis method, and the methods have high operation cost, long test evaluation period and inaccurate monitoring results. Therefore, a new method and system for monitoring a gate structure are needed to shorten the test evaluation period and improve the monitoring accuracy of the gate structure.
Disclosure of Invention
The invention aims to at least solve the technical problems in the prior art, and provides a method and a system for evaluating and predicting the safety of a gate structure based on a vibration signal, so that the test evaluation period of the gate is shortened, the monitoring precision of the gate is improved, and the future trend of the gate structure can be predicted.
In order to achieve the above object of the present invention, according to a first aspect of the present invention, there is provided a gate structure safety evaluation and prediction method based on a vibration signal, comprising the steps of: obtaining a vibration signal of the gate, and putting the vibration signal into a modal characteristic extraction model to obtain modal information characteristics; the modal information features are put into a mathematical model based on the Bayesian theory, and the mathematical model based on the Bayesian theory comprises a convolutional neural network and a support vector machine; the convolutional neural network extracts the features of the modal information, and the support vector machine classifies and regresses the extracted features to obtain feature signals; comparing the characteristic signal with a vibration standard, and outputting a safety evaluation result of the gate; and predicting the characteristic signals to obtain a posterior distribution result, and outputting a structure prediction result of the gate according to the posterior distribution result.
Further, the step of obtaining the vibration signal of the gate and putting the vibration signal into the modal characteristic extraction model to obtain the modal information characteristic specifically comprises the following steps: establishing a discrete time random state space model according to the vibration signal of the gate, generating a covariance matrix, forming a T-shaped matrix according to the covariance matrix, and solving the T-shaped matrix to obtain modal information characteristics; the modal information characteristics include frequency, damping ratio, mode shape, damping, and modal engagement factors, as followsThe formula shows that:
wherein, ω is i Denotes the frequency, λ, of the i-th stage i Representing the signal complex eigenvalue of the vibration signal state matrix of the ith stage, and superscripts Re and I respectively represent a real part and an imaginary part; epsilon i Indicating the damping ratio, phi i Indicating mode of vibration, C d Representing a discrete output matrix, Ψ i A T-type matrix representing the i-th stage covariance matrix; xi shape i Indicating damping, u i Denotes the ith characteristic value, lnu i Denotes u i The natural logarithm of (a), at represents the time period after dispersion,
represents a plurality of numbers
The real part of (a); MP (moving Picture experts group) i A representation of the modal engagement factor is provided,
indicating mode phi i R represents a random vector.
Further, the steps of putting a plurality of characteristic signals into a mathematical model based on the Bayesian theory to predict, and obtaining the posterior distribution result specifically comprise: calculating density distribution functions of a plurality of characteristic signals, integrating sample information and prior information of unknown parameters in the characteristic signals based on Bayesian theory to obtain estimation of posterior distribution, and further deducing the unknown parameters to obtain a posterior distribution result; the density distribution function is specifically:
wherein F (x) represents a density distribution function, x represents prior data, i represents the ith stage, M represents the total number of prior results x,
represents the weight of the first convolutional layer, b l Represents the bias value, x, of the first layer convolution layer i Denotes the ith a priori data, f (x) i ) Denotes x i The activation function value of (a).
Further, the mathematical model based on bayesian theory is as follows:
wherein, L (theta, x) represents a mathematical model based on Bayesian theory, rho (theta) is a prior data probability distribution function, P (F (x), theta) represents a likelihood function, and theta represents modal information characteristics.
Further, the mathematical model based on the Bayesian theory comprises a first input layer, a second convolution layer, a third sub-sampling layer, a fourth convolution layer, a fifth sub-sampling layer, a support vector machine and a seventh output layer.
Further, the fifth sub-sampling layer and the support vector machine use a relu function as an activation function.
Further, the mathematical model based on Bayesian theory is generated by training through the following steps: collecting vibration signals of a gate to form a data sample; dividing the data sample into a training data set and a testing data set; establishing a convolutional neural network; replacing a full connection layer in the convolutional neural network with a support vector machine to generate an initial model; and putting the training data set and the test data set into an initial model for training, and generating a mathematical model based on the Bayesian theory after the model is converged.
Further, the step of collecting the vibration signal of the gate to form a data sample specifically comprises: and collecting vibration signals of the gate according to a sampling frequency of 2000Hz to form data samples.
Further, the step of placing the modal information features into a mathematical model based on the bayesian theory specifically comprises: preprocessing the modal information features, and putting the preprocessed modal information features into a mathematical model based on a Bayesian theory; the preprocessing process comprises filtering processing and normalization processing.
In order to achieve the above object of the present invention, according to a second aspect of the present invention, a system for evaluating and predicting safety of a structure of a damper based on a vibration signal uses any one of the above methods for evaluating and predicting safety of a structure of a damper based on a vibration signal during operation; the system comprises an acquisition module, an extraction module, a training module and an evaluation prediction module; the acquisition module is used for acquiring a vibration signal of the gate; the extraction module is used for acquiring modal information characteristics according to the vibration signals of the gate; the training module is used for generating and training a mathematical model based on Bayesian theory; and the evaluation prediction module is used for obtaining the safety evaluation result of the gate and the prediction result of the gate according to the modal information characteristics and the mathematical model based on the Bayesian theory.
The basic principle and the beneficial effects of the invention are as follows: according to the scheme, modal information features are extracted through a vibration signal, the modal information features comprise parameters with characteristics in the vibration signal, the modal information features are input into a mathematical model based on a Bayesian theory, the mathematical model based on the Bayesian theory is trained by using a deep learning convolutional neural network algorithm and a support vector machine, and the mathematical model based on the Bayesian theory monitors and evaluates the vibration signal of a gate according to the modal information features to obtain feature signals; comparing the characteristic signal with standard data, and judging whether the vibration signal of the gate is a safe vibration signal; the mathematical model based on the Bayesian theory in the scheme adopts a convolutional neural network and a support vector machine, the convergence rate is high, the calculation precision is high, the detection monitoring period of the gate vibration signal is shortened, and the monitoring accuracy is improved. The scheme also calculates posterior distribution estimation of a plurality of characteristic signals based on Bayesian theory, and carries out short-term prediction on the operation state of the gate structure according to the posterior distribution estimation result.
Drawings
FIG. 1 is a schematic flow chart illustrating the steps of a method for evaluating and predicting the safety of a gate structure based on a vibration signal according to the present invention;
FIG. 2 is a schematic diagram illustrating the steps for obtaining modal information features of the present invention;
FIG. 3 is a flow chart illustrating the training procedure of the mathematical model based on Bayesian theory according to the present invention;
FIG. 4 is a partial structural diagram of a mathematical model based on Bayesian theory according to the present invention;
FIG. 5 is a schematic structural diagram of a system for evaluating and predicting the safety of a gate structure based on a vibration signal.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
In the description of the present invention, it is to be understood that the terms "longitudinal", "lateral", "upper", "lower", "front", "rear", "left", "right", "vertical", "horizontal", "top", "bottom", "inner", "outer", and the like, indicate orientations or positional relationships based on those shown in the drawings, and are used merely for convenience of description and for simplicity of description, and do not indicate or imply that the referenced devices or elements must have a particular orientation, be constructed in a particular orientation, and be operated, and thus, are not to be construed as limiting the present invention.
In the description of the present invention, unless otherwise specified and limited, it should be noted that the terms "mounted," "connected," and "connected" are to be interpreted broadly, and may be, for example, a mechanical connection or an electrical connection, a communication between two elements, a direct connection, or an indirect connection through an intermediate medium, and those skilled in the art will understand the specific meaning of the terms as they are used in the specific case.
As shown in the attached figure 1, the invention provides a method for evaluating and predicting the safety of a gate structure based on a vibration signal, which comprises the following steps:
obtaining a vibration signal of the gate, and putting the vibration signal into a modal characteristic extraction model to obtain modal information characteristics;
the modal information features are put into a mathematical model based on the Bayesian theory, and the mathematical model based on the Bayesian theory comprises a convolutional neural network and a support vector machine; the convolutional neural network extracts the features of the modal information, and the support vector machine classifies and regresses the extracted features to obtain feature signals; comparing the characteristic signal with a vibration standard to obtain a safety evaluation result of the gate;
and placing the plurality of characteristic signals into a mathematical model based on the Bayesian theory to predict, obtaining a posterior distribution result, and obtaining a structure prediction result of the gate according to the posterior distribution result.
Specifically, the vibration signal of the gate is obtained by online real-time detection of a vibration sensor mounted on the gate, in order to ensure the accuracy of vibration detection, the vibration sensor is preferably arranged at the central position of the gate, and the vibration sensor is preferably a capacitive vibration sensor which has the characteristics of simple structure, good environmental adaptability, good dynamic measurement performance and the like.
As shown in fig. 2, the step of obtaining the vibration signal of the gate and putting the vibration signal into the modal characteristic extraction model to obtain the modal information characteristic specifically includes:
establishing a discrete time random state space model according to the vibration signal of the gate, generating a covariance matrix, forming a T-shaped matrix according to the covariance matrix, and solving the T-shaped matrix to obtain modal information characteristics; specifically, a system discrete time random state space model of the degree of freedom n under environmental excitation is established according to the vibration signals:
X k+1 ＝A d X k +W k
Y k ＝C d X k +V k
wherein, X k And X k+1 Representing discrete-time state vectors at time k and at time k +1, respectively, Y k The vibration signal of the vibration sensor at the kth moment; a. The d As a signal state matrix, A d ∈R 2n×2n ，C d As a discrete output matrix, C d ∈R m×2n Where R represents a real number space, m represents the number of output channels, W k Display moduleZero mean gaussian white noise vector, V, due to pattern building k Representing a zero mean white noise vector caused by the vibration sensor measurement response;
the discrete vibration signal of the gate measured by the vibration sensor is Y k ＝{y 1 ，y 2 ，...，y n Forming a Hankel matrix by using discrete vibration signals, and dividing the Hankel matrix H into a past output matrix Y p And a future output matrix Y f Two parts are as follows:
wherein i and j represent the number of rows and columns, respectively, of the Hankel matrix.
The discrete-time state vector and the discrete vibration signal can be described by a zero-mean stationary random process, and the generated covariance matrix R is assumed to have ergodicity in the vibration signal of the response of the monitoring point of the vibration sensor i Comprises the following steps:
wherein the content of the first and second substances,
e is the mathematical expectation.
Further, the covariance matrix is formed into a T-shaped matrix
Based on the singular value decomposition, Ψ can be approximated as
Wherein P and Q both represent orthogonal matrices, S represents a diagonal matrix, and the elements of the matrix are arranged in order from large to small. Obtaining a state matrix of the gate vibration signal according to the T-shaped matrix:
wherein, the first and the second end of the pipe are connected with each other,
for state matrix A of vibration signal d Decomposing the eigenvalue to obtain complex eigenvalue lambda of signal i ：
Wherein λ is i Representing complex eigenvalues, ω i And xi i Respectively, the frequency and damping ratio of the ith order mode. Taking into account the conversion of discrete-time eigenvalues into continuous-time models, the complex eigenvalues λ are calculated from the signal as described above i Extracting and calculating modal information characteristics, wherein the modal information characteristics comprise frequency, damping ratio, vibration mode, damping and modal participation factors, and are expressed by the following formula:
φ i ＝C d Ψ i
wherein, ω is i Denotes the frequency, λ, of the i-th stage i Representing the complex eigenvalue of the vibration signal state matrix of the ith stage, and superscripts Re and I respectively represent a real part and an imaginary part; epsilon i Indicating the damping ratio, phi i Indicating mode of vibration, C d Representing a discrete output matrix, Ψ i A T-type matrix representing the i-th stage covariance matrix; xi i Indicating damping, u i Denotes the ith characteristic value, lnu i Represents u i Of the time interval, at represents the time interval after dispersion,
represents a plurality of numbers
The real part of (a); MP (moving Picture experts group) i A representation of the modal engagement factor is provided,
indicating mode phi i R represents a random vector. The modal information characteristics also include amplitude and phase. The modal information features obtained by the modal feature extraction model have good reliability and high precision.
Further, the step of placing the modal information features into a mathematical model based on the bayesian theory specifically comprises: preprocessing the modal information features, and putting the preprocessed modal information features into a mathematical model based on a Bayesian theory; the preprocessing process comprises a filtering process and a normalization process. W k Specifically, zero mean gaussian white noise vector caused by the preprocessing process and model establishment is shown. Specifically, a fourth-order band-pass filter of 1MHz-10Hz is used for filtering and denoising the modal information features, and then normalization processing is carried out to enable the modal information features to be in a certain range, so that the phenomenon that the modal information features have overlarge differences is avoided, and dimensional influence among data is eliminated. Specifically, the normalization formula is:
in particular, mu i And σ i Respectively mean and standard deviation, x nij Is x ij Normalized values.
Further, the extracted modal information features are preprocessed and then used as input of a mathematical model based on the bayesian theory, the mathematical model based on the bayesian theory comprises two convolution and pooling, as shown in fig. 4, the mathematical model based on the bayesian theory comprises a first input layer, a second convolution layer, a third sub-sampling layer, a fourth convolution layer, a fifth sub-sampling layer, a support vector machine and a seventh output layer.
As shown in fig. 3, the mathematical model based on the bayesian theory is generated by training through the following steps: collecting vibration signals of a gate to form a data sample; dividing the data sample into a training data set and a testing data set; establishing a convolutional neural network; replacing a full connection layer in the convolutional neural network with a support vector machine to generate an initial model; and putting the training data set and the test data set into an initial model for training, and generating a mathematical model based on the Bayesian theory after the model is converged. Preferably, the step of collecting the vibration signal of the gate to form the data sample specifically comprises: and collecting vibration signals of the gate according to the sampling frequency of 2000HZ to form data samples. The deep learning network model in fig. 3 is a mathematical model based on the bayesian theory.
Specifically, the acquisition frequency of the vibration signal is 2000Hz, each vibration signal is 2560 points, the characteristic dimension of the mode information extracted by the vibration signal through a mode specific diagnosis extraction model is 6 × 2560, the characteristic dimension of the second convolution layer after 4 × 561 convolution through a primary convolution kernel is 3 × 2000, the characteristic dimension of the third sub-sampling layer after 1 × 20 pooling through a primary pooling kernel is 3 × 100, the characteristic dimension of the fourth convolution layer after 3 × 51 convolution through a secondary convolution kernel is 1 × 50, the characteristic dimension of the fifth sub-sampling layer after 1 × 2 pooling through a secondary pooling kernel is 1 × 25, the one-dimensional data obtained after two convolutions and pooling is 150, the structural parameters of the convolutional neural network of 6 × 25 are finally obtained, the characteristic dimensions of 6 × 25 are input into a support vector machine model for classification, 6 characteristic vectors can be obtained, the 6 characteristic vectors are output as characteristic signals through a seventh output layer, the characteristic signals are compared with the standard vectors of the vibration standard, whether the vibration signal is acquired by the sensor or not is evaluated, and the historical data is designed and recorded according to the historical data.
Furthermore, the fifth sub-sampling layer and the support vector machine use the relu function as the activation function, compared with other activation functions, the calculation of the relu function is simpler, meanwhile, the relu function can reduce the dependency of parameters, has good sparsity and high convergence speed, and shortens the gate vibration detection period. The formula for the relu function to process the data Z is:
f(Z)＝max(0，Z)
furthermore, the Bayesian theory analyzes the occurrence probability of various conditions according to all existing evidence conditions, and further obtains the occurrence probability of the interested unknown parameters, so as to predict the occurrence probability of future objects.
Specifically, the step of placing a plurality of characteristic signals into a mathematical model based on the bayesian theory for prediction to obtain a posterior distribution result specifically comprises: calculating density distribution functions of a plurality of characteristic signals, integrating sample information and prior information of unknown parameters in the characteristic signals based on Bayesian theory to obtain estimation of posterior distribution, and further deducing the unknown parameters to obtain a posterior distribution result; the density distribution function is specifically:
wherein F (x) represents a density distribution function, x represents prior data, i represents the ith stage M represents the total number of prior results x,
represents the weight of the first convolutional layer, b l Represents the bias value, x, of the first layer convolution layer i Denotes the ith a priori data, f (x) i ) Denotes x i The activation function value of (1).
Specifically, the mathematical model based on bayesian theory is as follows:
wherein, L (theta, x) represents a mathematical model based on Bayesian theory, rho (theta) is a prior data probability distribution function, P (F (x), theta) represents a likelihood function, and theta represents modal information characteristics.
In order to achieve the above object of the present invention, according to a second aspect of the present invention, as shown in fig. 5, the system for evaluating and predicting the safety of a structure of a lock gate based on a vibration signal uses any one of the above-mentioned methods for evaluating and predicting the safety of a structure of a lock gate based on a vibration signal during operation; the system comprises an acquisition module, an extraction module, a training module and an evaluation prediction module; the acquisition module is used for acquiring a vibration signal of the gate; the extraction module is used for acquiring modal information characteristics according to the vibration signals of the gate; the training module is used for generating and training a mathematical model based on Bayesian theory; and the evaluation prediction module is used for obtaining the safety evaluation result of the gate and the prediction result of the gate according to the modal information characteristics and the mathematical model based on the Bayesian theory.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
Claims (10)
1. The method for evaluating and predicting the safety of the gate structure based on the vibration signal is characterized by comprising the following steps of:
obtaining a vibration signal of the gate, and putting the vibration signal into a modal characteristic extraction model to obtain modal information characteristics;
the modal information features are put into a mathematical model based on the Bayesian theory, and the mathematical model based on the Bayesian theory comprises a convolutional neural network and a support vector machine; the convolutional neural network extracts the features of the modal information, and the support vector machine classifies and regresses the extracted features to obtain feature signals; comparing the characteristic signal with a vibration standard, and outputting a safety evaluation result of the gate;
and predicting the characteristic signals to obtain a posterior distribution result, and outputting a structure prediction result of the gate according to the posterior distribution result.
2. The method for security assessment and prediction of a gate structure based on a vibration signal according to claim 1, wherein the step of obtaining the vibration signal of the gate and putting the vibration signal into a modal feature extraction model to obtain the modal information features comprises:
establishing a discrete time random state space model according to the vibration signal of the gate, generating a covariance matrix, forming a T-shaped matrix according to the covariance matrix, and solving the T-shaped matrix to obtain modal information characteristics; the modal information characteristics include frequency, damping ratio, mode shape, damping and modal participation factors, and are expressed by the following formula:
φ i ＝C d Ψ i
wherein, ω is i Denotes the frequency, λ, of the i-th stage i Representing the signal complex eigenvalue of the vibration signal state matrix of the ith stage, and superscripts Re and I respectively represent a real part and an imaginary part; epsilon i Indicating the damping ratio, phi i Indicating mode of vibration, C d Representing a discrete output matrix, Ψ i A T-type matrix representing the i-th stage covariance matrix; xi i Indicating damping, u i Indicates the ith characteristic value, lnu i Represents u i The natural logarithm of (a), at represents the time period after dispersion,
represents a plurality of numbers
The real part of (a); MP (moving Picture experts group) i A representation of the modal engagement factor is provided,
indicating mode phi i R represents a random vector.
3. The method for security assessment and prediction of a structure of a lock gate based on a vibration signal as claimed in claim 1 or 2, wherein the step of predicting a plurality of characteristic signals to obtain a posterior distribution result comprises: calculating density distribution functions of a plurality of characteristic signals, integrating sample information and prior information of unknown parameters in the characteristic signals based on Bayesian theory to obtain estimation of posterior distribution, and further deducing the unknown parameters to obtain a posterior distribution result;
the density distribution function is specifically:
wherein F (x) represents a density distribution function, and x representsA priori data, i denotes the ith stage, M denotes the total number of a priori results x,
represents the weight of the first convolutional layer, b l Represents the offset, x, of the first convolution layer i Denotes the ith a priori data, f (x) i ) Denotes x i The activation function value of (a).
4. The security assessment and prediction method of a gate structure based on vibration signals as claimed in claim 3, wherein the mathematical model based on Bayesian theory is as follows:
wherein, L (theta, x) represents a mathematical model based on Bayesian theory, rho (theta) is a prior data probability distribution function, P (F (x), theta) represents a likelihood function, and theta represents modal information characteristics.
5. The security assessment and prediction method for a gate structure based on vibration signals according to claim 1, 2 or 4, characterized in that the mathematical model based on Bayesian theory comprises a first input layer, a second convolution layer, a third sub-sampling layer, a fourth convolution layer, a fifth sub-sampling layer, a support vector machine and a seventh output layer.
6. The security assessment and prediction method of a gate structure based on vibration signals according to claim 5, characterized in that the fifth sub-sampling layer and the support vector machine use relu function as activation function.
7. The method for security assessment and prediction of a door structure based on vibration signals according to claim 5, characterized in that the mathematical model based on Bayesian theory is generated by training through the following steps:
collecting vibration signals of a gate to form a data sample; dividing the data sample into a training data set and a testing data set;
establishing a convolutional neural network; replacing a full connection layer in the convolutional neural network with a support vector machine to generate an initial model;
and putting the training data set and the test data set into an initial model for training, and generating a mathematical model based on the Bayesian theory after the model is converged.
8. The security assessment and prediction method for a gate structure based on vibration signals as claimed in claim 7, wherein the step of collecting the vibration signals of the gate to form data samples comprises the steps of: and collecting vibration signals of the gate according to the sampling frequency of 2000Hz to form data samples.
9. A method for security assessment and prediction of a structure of a door based on a vibration signal as claimed in claim 1, 2, 4, 6, 7 or 8, characterized in that: the method for putting modal information characteristics into a mathematical model based on a Bayesian theory specifically comprises the following steps: preprocessing the modal information features, and putting the preprocessed modal information features into a mathematical model based on a Bayesian theory; the preprocessing process comprises a filtering process and a normalization process.
10. Gate structure safety assessment and prediction system based on vibration signal, its characterized in that: a method for evaluating and predicting the safety of a gate structure based on a vibration signal according to any one of claims 1 to 9 is used in the operation process; the system comprises an acquisition module, an extraction module, a training module and an evaluation prediction module;
the acquisition module is used for acquiring a vibration signal of the gate;
the extraction module is used for acquiring modal information characteristics according to the vibration signals of the gate;
the training module is used for generating and training a mathematical model based on Bayesian theory;
and the evaluation prediction module is used for obtaining the safety evaluation result of the gate and the prediction result of the gate according to the modal information characteristics and the mathematical model based on the Bayesian theory.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211559652.XA CN115828139B (en) | 2022-12-06 | 2022-12-06 | Gate structure safety assessment and prediction method and system based on vibration signals |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211559652.XA CN115828139B (en) | 2022-12-06 | 2022-12-06 | Gate structure safety assessment and prediction method and system based on vibration signals |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115828139A true CN115828139A (en) | 2023-03-21 |
| CN115828139B CN115828139B (en) | 2023-07-21 |
Family
ID=85544309
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211559652.XA Active CN115828139B (en) | 2022-12-06 | 2022-12-06 | Gate structure safety assessment and prediction method and system based on vibration signals |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115828139B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8600917B1 (en) * | 2011-04-18 | 2013-12-03 | The Boeing Company | Coupling time evolution model with empirical regression model to estimate mechanical wear |
| EP2720024A2 (en) * | 2012-10-09 | 2014-04-16 | The Boeing Company | Methods and systems for structural health monitoring |
| CN104850736A (en) * | 2015-04-27 | 2015-08-19 | 大连理工大学 | Service life prediction method of high-speed numerical control milling machine cutter on basis of state space model |
| CN106897717A (en) * | 2017-02-09 | 2017-06-27 | 同济大学 | Bayesian model modification method under multiple test based on environmental excitation data |
| CN113221282A (en) * | 2021-05-19 | 2021-08-06 | 西安交通大学 | Aero-engine service life prediction method based on Bayesian residual convolutional network |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
| CN114896712A (en) * | 2021-12-07 | 2022-08-12 | 中铁五局集团建筑工程有限责任公司 | Structural damage identification method based on reference Bayesian principle and sparse regularization |
-
2022
- 2022-12-06 CN CN202211559652.XA patent/CN115828139B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8600917B1 (en) * | 2011-04-18 | 2013-12-03 | The Boeing Company | Coupling time evolution model with empirical regression model to estimate mechanical wear |
| EP2720024A2 (en) * | 2012-10-09 | 2014-04-16 | The Boeing Company | Methods and systems for structural health monitoring |
| CN104850736A (en) * | 2015-04-27 | 2015-08-19 | 大连理工大学 | Service life prediction method of high-speed numerical control milling machine cutter on basis of state space model |
| CN106897717A (en) * | 2017-02-09 | 2017-06-27 | 同济大学 | Bayesian model modification method under multiple test based on environmental excitation data |
| CN113221282A (en) * | 2021-05-19 | 2021-08-06 | 西安交通大学 | Aero-engine service life prediction method based on Bayesian residual convolutional network |
| CN114896712A (en) * | 2021-12-07 | 2022-08-12 | 中铁五局集团建筑工程有限责任公司 | Structural damage identification method based on reference Bayesian principle and sparse regularization |
| CN114707227A (en) * | 2022-04-28 | 2022-07-05 | 水利部南京水利水文自动化研究所 | Dam safety early warning and warning method and system based on digital twins |
Non-Patent Citations (1)
| Title |
|---|
| 呼文亮;王惠文;: "基于贝叶斯准则的支持向量机预测模型", 北京航空航天大学学报, no. 04 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115828139B (en) | 2023-07-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11630034B2 (en) | Method for diagnosing and predicting operation conditions of large-scale equipment based on feature fusion and conversion | |
| Kwan et al. | A novel approach to fault diagnostics and prognostics | |
| CN110781592B (en) | Method and system for predicting residual life of equipment | |
| CN111120348A (en) | Centrifugal pump fault early warning method based on support vector machine probability density estimation | |
| CN111562108A (en) | Rolling bearing intelligent fault diagnosis method based on CNN and FCMC | |
| CN110702418A (en) | Aircraft engine fault prediction method | |
| CN108897975A (en) | Coalbed gas logging air content prediction technique based on deepness belief network | |
| CN108444696A (en) | A kind of gearbox fault analysis method | |
| CN114623050A (en) | Method, system and medium for detecting abnormal operation data of wind turbine generator | |
| Chen et al. | Intelligent model-based integrity assessment of nonstationary mechanical system | |
| CN114626413A (en) | Structural modal parameter identification method and device based on random subspace algorithm | |
| CN115130495A (en) | Rolling bearing fault prediction method and system | |
| CN111753776A (en) | Structural damage identification method based on echo state and multi-scale convolution combined model | |
| CN115221973A (en) | Aviation bearing fault diagnosis method based on enhanced weighted heterogeneous ensemble learning | |
| CN116597350A (en) | Flotation process fault early warning method based on BiLSTM predictive deviation | |
| CN116741148A (en) | Voice recognition system based on digital twinning | |
| Karimian et al. | Neural network and particle filtering: a hybrid framework for crack propagation prediction | |
| Zhang et al. | Complementary ensemble adaptive local iterative filtering and its application to rolling bearing fault diagnosis | |
| CN114861349A (en) | Rolling bearing RUL prediction method based on model migration and wiener process | |
| CN117556670A (en) | Assembled structure damage identification method based on Bayesian theory | |
| CN115828139A (en) | Gate structure safety assessment and prediction method and system based on vibration signals | |
| Kannadaguli et al. | Microwave imaging based automatic crack detection system using machine learning for columns | |
| CN103400021A (en) | KDSNE hydroelectric generating set noise source detection method based on heavy tailed distribution | |
| CN108009514B (en) | Material level prediction method for ball mill | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |