CN113280908A - Building structure real-time diagnosis method and device based on fusion index - Google Patents
Building structure real-time diagnosis method and device based on fusion index Download PDFInfo
- Publication number
- CN113280908A CN113280908A CN202110667817.4A CN202110667817A CN113280908A CN 113280908 A CN113280908 A CN 113280908A CN 202110667817 A CN202110667817 A CN 202110667817A CN 113280908 A CN113280908 A CN 113280908A
- Authority
- CN
- China
- Prior art keywords
- real
- index
- health
- time
- fusion
- 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.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01H—MEASUREMENT OF MECHANICAL VIBRATIONS OR ULTRASONIC, SONIC OR INFRASONIC WAVES
- G01H11/00—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties
- G01H11/06—Measuring mechanical vibrations or ultrasonic, sonic or infrasonic waves by detecting changes in electric or magnetic properties by electric means
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a building structure real-time diagnosis method and a device based on fusion indexes, wherein the method comprises the following steps: intercepting the acquired real-time vibration data and the acquired health vibration data according to a preset diagnosis step length to obtain real-time sample data and health sample data; then, calculating various structural health assessment indexes to obtain real-time performance parameter indexes and health parameter indexes of the building structure; after the real-time performance parameter index and the health parameter index are respectively subjected to regularization and probabilistic processing, fusion processing is carried out by adopting a weighted average theory, or a Bayesian theory, or a D-S evidence theory to obtain a real-time fusion index and a health fusion index; and comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring and early warning information of the building structure. According to the technical scheme provided by the invention, a new fusion index is constructed, so that the problem that the health state of a building structure cannot be comprehensively reflected by a single index in the prior art is solved.
Description
Technical Field
The invention relates to the technical field of large building structure safety monitoring, in particular to a building structure real-time diagnosis method and device based on fusion indexes.
Background
At present, large building structures in cities become more and more complex, and develop towards diversification and multi-functionalization. The service life of a building structure is usually dozens of years or even hundreds of years, and in the using process of the building structure, the structure is gradually damaged and accumulated due to the effects of factors such as supernormal load, material aging, component defects, fatigue effect and the like, so that the bearing capacity of the structure is reduced, and the capacity of resisting natural disasters is reduced. When the earthquake, typhoon and other disastrous loads act, the earthquake and typhoon can be seriously damaged, and great loss is brought to the life and property of the country and people. Therefore, the method has very important practical significance for monitoring and diagnosing the health condition of the building structure, finding out the structural damage in time, predicting possible disasters and evaluating the safety, reliability, durability and applicability of the service structure.
The evaluation indexes which are developed more mature and have higher calculation efficiency comprise self-vibration frequency, main components, wavelet packet energy and the like, but the different indexes have different response sensitivity degrees to different working conditions, namely different building structure damage conditions, the performance difference among the indexes brings about great troubles for building structure health diagnosis, and the seeking and constructing of an index which can comprehensively and accurately reflect the building structure health state becomes an important appeal for building structure health diagnosis.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention provides a building structure real-time diagnosis method and a building structure real-time diagnosis device based on fusion indexes, wherein a new fusion index is constructed for evaluating the health state of a building structure so as to solve the problem of performance difference among different indexes mentioned in the background technology.
A building structure real-time diagnosis method based on fusion indexes is characterized by comprising the following steps:
intercepting the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; intercepting the acquired healthy vibration data according to the preset diagnosis step length to obtain healthy sample data;
calculating various structural health assessment indexes of the real-time sample data and the health sample data respectively to obtain a real-time performance parameter index and a health parameter index of the building structure;
after the real-time performance parameter index and the health parameter index are respectively subjected to regularization and probabilistic processing, fusion processing is carried out by adopting a weighted average theory, or a Bayesian theory, or a D-S evidence theory, so as to obtain a real-time fusion index and a health fusion index;
and comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring and early warning information of the building structure.
A building structure real-time diagnosis device based on fusion index is applied to computer equipment or a computer readable storage medium, and is characterized by comprising:
the data acquisition module is used for intercepting the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; intercepting the acquired healthy vibration data according to the preset diagnosis step length to obtain healthy sample data;
the multiple structure health assessment index calculation module is used for respectively calculating multiple structure health assessment indexes of the real-time sample data and the health sample data to obtain a real-time performance parameter index and a health parameter index of the building structure;
the index fusion preprocessing and multi-index fusion computing module is used for performing regularization and probability processing on the real-time performance parameter index and the health parameter index respectively, and then performing fusion processing on the real-time performance parameter index and the health parameter index by adopting a weighted average theory, a Bayesian theory or a D-S evidence theory to obtain a real-time fusion index and a health fusion index;
and the diagnosis output module is used for comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring and early warning information of the building structure.
The invention provides a building structure real-time diagnosis method based on fusion indexes, which comprises the following steps of firstly, intercepting real-time vibration data and healthy vibration data acquired from a monitoring terminal according to a preset diagnosis step length to obtain input data for constructing the fusion indexes: real-time sample data and health sample data; secondly, calculating various structural health assessment indexes of the sample data to obtain a plurality of parameter indexes including natural vibration frequency, principal components, wavelet packet energy and secondary covariance, and performing fusion processing on the parameter indexes by using a weighted average theory, a Bayesian theory or a D-S evidence theory to obtain a real-time fusion index and a health fusion index; and then, comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring early warning information of the building structure so as to judge whether the building structure has potential safety hazards and conveniently achieve the purpose of real-time monitoring through the early warning information.
Compared with the existing scheme of judging the safety of the building structure through a single index (natural frequency, principal component, wavelet packet energy and the like), the fusion index constructed by the building structure real-time diagnosis method based on the fusion index can adapt to different working conditions, is sensitive to response to different building structure damage conditions, overcomes the problem of inaccurate diagnosis result caused by performance difference among the single indexes, and forms a measuring index capable of comprehensively and accurately reflecting the health state of the building structure.
The building structure real-time diagnosis device based on the fusion index is used for realizing the method, can be applied to computer equipment or computer readable storage media, and is convenient to deploy on a server and a cloud server.
Drawings
FIG. 1 is a schematic view of an application scenario of a building structure real-time diagnosis method based on fusion indexes in an embodiment of the present invention;
FIG. 2 is a flow chart of a method for real-time diagnosis of a building structure based on fusion indicators according to an embodiment of the present invention;
FIG. 3 is a flow chart of a method for real-time building structure diagnosis based on fusion indicators according to another embodiment of the present invention;
FIG. 4 is a block diagram of a real-time building structure diagnosis apparatus based on fusion indexes according to an embodiment of the present invention;
Detailed Description
In order to make the technical problems, technical solutions and advantageous effects to be solved by the present invention more clearly apparent, the present invention is further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
A building structure real-time diagnosis method based on fusion indexes is applied to an application scene shown in figure 1, wherein a hardware equipment three-way MEMS (Micro-Electro Mechanical Systems) acceleration sensor is deployed in a floor of a building structure and used for acquiring implementation vibration data and health vibration data of the building structure; the three-direction MEMS acceleration sensor is communicated with a remote cloud server through a 5G/4G network, the building structure real-time diagnosis method based on the fusion index is applied to the cloud server, and health information of a building structure can be provided for managers through management software of a B/S framework.
In one embodiment, a method for real-time diagnosis of a building structure based on a fusion index is provided, which is a process shown in fig. 2 and includes the following steps:
s1: intercepting the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; and intercepting the acquired healthy vibration data according to a preset diagnosis step length to obtain healthy sample data.
The real-time vibration data and the healthy vibration data are acquired from the MEMS acceleration sensor; the real-time vibration data refers to real-time acceleration data, and the healthy vibration data refers to vibration data under the condition that the structure is not damaged. The preset diagnosis step size can be determined according to experience and actual vibration conditions of the building structure, and is 1 minute and the like.
S2: and respectively calculating various structural health evaluation indexes of the real-time sample data and the health sample data to obtain a real-time performance parameter index and a health parameter index of the building structure.
The calculation of the multiple structural health assessment indexes refers to the calculation of indexes such as self-vibration frequency, principal component, wavelet packet energy, quadratic covariance and the like according to the intercepted vibration data (namely real-time sample data and health sample data).
S3: after the real-time performance parameter index and the health parameter index are respectively subjected to regularization and probability processing, fusion processing is carried out by adopting a weighted average theory, or a Bayesian theory, or a D-S evidence theory, so as to obtain a real-time fusion index and a health fusion index.
The regularization and the probability are used for preprocessing the real-time performance parameter index and the health parameter index; after preprocessing, three different index fusion technologies, namely a weighted average theory, a Bayesian theory and a D-S evidence theory, can be selected and used for fusing the indexes of the natural frequency, the principal component, the wavelet packet energy, the secondary covariance and the like which are subjected to regularization and probability to obtain fusion indexes (real-time fusion indexes and health fusion indexes).
S4: and comparing the real-time fusion index with the health fusion index to obtain the health diagnosis information of the building structure.
And comparing the real-time fusion index obtained by the real-time vibration data with the health fusion index obtained by the health vibration data to obtain the health diagnosis information and the monitoring and early warning information of the building structure.
Specifically, a process flow of acquiring health diagnosis information of a building structure is shown in fig. 3; the real-time performance parameter index and the health parameter index respectively comprise natural vibration frequency, principal component, wavelet packet energy and secondary covariance.
For the natural vibration frequency, in the process of respectively calculating various structural health assessment indexes of real-time sample data and health sample data, the following modes are adopted for calculation:
and (2) calculating by a random subspace method, and if the number of output channels is l, wherein the number of reference channels is r, constructing a (2i) Hankel matrix H with rows multiplied by j columns by using output data, and decomposing into two parts of 'past' and 'future':
wherein the structural response data matrices for past (corresponding past) and future (corresponding future) measurements are respectively
And Yf，
yk∈YfAnd i and j are important control parameters in the stochastic subspace approach. If all s output data are used for analysis, s is 2i + j-1; then, according to the following formula, a Toeplitz matrix T is constructed by using a Hankel matrix as follows:
after the Toeplitz matrix is obtained, the identification frequency, namely the natural frequency, can be obtained through the processes of singular value decomposition and system order determination.
For the principal component, in the process of respectively calculating various structural health assessment indexes of the real-time sample data and the health sample data, the principal component is obtained by calculation through the following steps:
assuming that n observations are made on m parameters, an original data matrix X can be obtained:
(1) raw data were normalized using the following formula for standard deviation normalization:
wherein the content of the first and second substances,
is XjMean value of (1), sjIs XjThe normalized original matrix is taken as X';
(2) the correlation matrix R is calculated according to the following formula:
wherein, the normalized matrix correlation matrix R is the covariance matrix thereof;
(3) performing characteristic decomposition on the sample data correlation matrix R to obtain a characteristic value lambda of the first m orders1≥λ2≥…≥λmNot less than 0; and defining the j-th principal component contribution rate
Cumulative contribution rate of the first p principal components
(4) The feature vector corresponding to each feature value is obtained as a correlation coefficient aijThe following calculation formula is substituted:
the principal component of each order can be obtained, wherein Y1、Y2And YmRespectively, the 1 st, 2 nd and m th order principal components.
For wavelet packet energy, in the process of respectively calculating various structural health assessment indexes of real-time sample data and health sample data, the wavelet packet energy is obtained by calculation in the following mode:
the wavelet packet decomposition technique is used to decompose the signal into independent sub-bands by using wavelet functions such as Db6, and the energy components of each sub-band are calculated. The wavelet packet decomposition decomposes the time series S into two parts, low frequency information a1 and high frequency information d 1. In the decomposition, the information lost in the low frequency a1 is captured by the high frequency d 1. In the next layer of decomposition, a1 is decomposed into two parts, a2 and d2, and so on, as shown below,
each decomposed segment contains information of structures in different frequency bands, and wavelet packet energy E of each order is calculated according to the following formula:
i.e. obtaining the wavelet packet energy of each order, wherein
Represents the ith node energy value at decomposition level j, and
representing the normalized energy value of the ith node at decomposition level j.
For the secondary covariance, in the process of respectively calculating various structural health assessment indexes of the real-time sample data and the health sample data, the secondary covariance is obtained by calculating according to the following formula:
Tpl＝Rpl·Rpl T
wherein R isplIs a covariance matrix, and TplIs the quadratic covariance matrix, and p and l are the station positions.
Further, for the fusion processing using the weighted average theory, the following formula is used:
wherein D isiIs the (i) th index of the (i) th index,
is a fusion index obtained based on the weighted average theory, WiThe weight coefficient of the ith index is taken, and the value of the weight coefficient is the minimum variance among the indexes; and solving the above formula by a least square method to obtain a real-time fusion index and a health fusion index.
Further, when the fusion processing is performed by using the bayesian theory, the method includes:
set the multiple damage conditions as { A1 A2…An}, multiple index set { B1 B2…Bm}; and is carried out by the following formula:
wherein, P (A)j) Is a priori probability, and P (B)k|Aj) Is the index BkTo AjDiagnosis of lesions, P (A)iAnd | B) is a fusion index obtained based on Bayesian theory.
Further, when the fusion processing is performed by adopting the D-S evidence theory, the method comprises the following steps:
set the multiple damage conditions as { A1 A2…AnThe multi-index set is { m }1 m2…mmAnd by the following formula:
wherein m isj(Ai) And K is a real-time fusion index or a health fusion index obtained based on a D-S evidence theory for judging the ith damage condition by the jth index.
It can be understood that the real-time performance parameter index and the health parameter index (i.e. the natural frequency, the principal component, the wavelet packet energy, and the secondary covariance index) calculated in step S2, and the real-time fusion index and the health fusion index calculated in steps S3 and S4 can be used to evaluate the health status of the building structure, and the fusion index can make up for the defect of a single index.
In one embodiment, a real-time building structure diagnosis apparatus based on fusion index is provided, as shown in fig. 4, applied on a computer device or a computer readable storage medium, and includes:
the data acquisition module 101 is configured to intercept the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; intercepting the acquired healthy vibration data according to a preset diagnosis step length to obtain healthy sample data;
the multiple structure health assessment index calculation module 102 is used for respectively calculating multiple structure health assessment indexes of the real-time sample data and the health sample data to obtain a real-time performance parameter index and a health parameter index of the building structure;
the index fusion preprocessing and multi-index fusion calculating module 103 is used for performing regularization and probability processing on the real-time performance parameter index and the health parameter index respectively, and then performing fusion processing by adopting a weighted average theory, a Bayesian theory or a D-S evidence theory to obtain a real-time fusion index and a health fusion index;
and the diagnosis output module 104 is used for comparing the real-time fusion index with the health fusion index to obtain the health diagnosis information of the building structure.
The device is used for realizing the building structure real-time diagnosis method based on the fusion index, and is not described herein again.
Further, in an embodiment, a building structure real-time diagnosis system based on fusion indexes is provided, and the system comprises a cloud server and a monitoring terminal, wherein the cloud server and the monitoring terminal are communicated through a 5G/4G wireless network, so that the monitoring terminal can be flexibly deployed, and the system is not limited by complex environments of different building structures. The monitoring terminal is used for acquiring real-time data of different floors of the building structure, namely acquiring real-time vibration data and healthy vibration data; the cloud server is used for processing the data collected by the monitoring terminal and calculating the health information of the building structure, namely the building structure real-time diagnosis device based on the fusion index is included, and a corresponding diagnosis method is realized; the monitoring terminal comprises an MEMS acceleration sensor, a power supply module and a wireless transmission module, and is used for monitoring real-time vibration data and healthy vibration data of the building structure, supplying power to a power supply and transmitting data to the cloud server.
Compared with the prior art for monitoring the health condition of the building structure, the building structure real-time diagnosis system based on the fusion index has the characteristics of high automation degree, strong real-time performance and more reliable building structure health diagnosis information, can be flexibly deployed in a complex building structure, greatly reduces the labor and financial cost for detection, and is convenient to popularize and expand.
The method and the device for diagnosing the building structure in real time based on the fusion index are explained to help the understanding of the invention; the present invention is not limited to the above embodiments, and any changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit of the present invention are intended to be equivalent replacements within the scope of the present invention.
Claims (10)
1. A building structure real-time diagnosis method based on fusion indexes is characterized by comprising the following steps:
intercepting the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; intercepting the acquired healthy vibration data according to the preset diagnosis step length to obtain healthy sample data;
calculating various structural health assessment indexes of the real-time sample data and the health sample data respectively to obtain a real-time performance parameter index and a health parameter index of the building structure;
after the real-time performance parameter index and the health parameter index are respectively subjected to regularization and probabilistic processing, fusion processing is carried out by adopting a weighted average theory, or a Bayesian theory, or a D-S evidence theory, so as to obtain a real-time fusion index and a health fusion index;
and comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring and early warning information of the building structure.
2. The method according to claim 1, wherein the real-time performance parameter index and the health parameter index respectively comprise natural frequency, principal component, wavelet packet energy, and quadratic covariance.
3. The method for real-time diagnosis of building structure based on fusion index according to claim 2, wherein in the calculation of the plurality of structural health assessment indexes for the real-time sample data and the health sample data, the natural frequency is calculated as follows:
and (2) calculating by a random subspace method, and if the number of output channels is l, wherein the number of reference channels is r, constructing a (2i) Hankel matrix H with rows multiplied by j columns by using output data, and decomposing into two parts of 'past' and 'future':
wherein the structural response data matrices for past (corresponding past) and future (corresponding future) measurements are respectively
And Yf，
yk∈YfAnd i and j are important control parameters in the stochastic subspace approach. If all s output data are used for analysis, s is 2i + j-1; then, according to the following formula, a Toeplitz matrix T is constructed by using a Hankel matrix as follows: :
after the Toeplitz matrix is obtained, the identification frequency, namely the natural frequency, can be obtained through the processes of singular value decomposition and system order determination.
4. The method for real-time diagnosis of building structure based on fusion index according to claim 2, wherein in said calculation of a plurality of structural health assessment indexes for said real-time sample data and said health sample data, said principal component is obtained by the following steps:
assuming that n observations are made on m parameters, an original data matrix X can be obtained:
(1) raw data were normalized using the following formula for standard deviation normalization:
wherein the content of the first and second substances,
is XjMean value of (1), sjIs XjThe normalized original matrix is taken as X';
(2) the correlation matrix is calculated according to the following formula:
wherein, the normalized matrix correlation matrix R is the covariance matrix thereof;
(3) performing characteristic decomposition on the sample data correlation matrix R to obtain a characteristic value lambda of the first m orders1≥λ2≥…≥λmNot less than 0; and defining the j-th principal component contribution rate
Cumulative contribution rate of the first p principal components
(4) The feature vector corresponding to each feature value is obtained as a correlation coefficient aijSubstituting into the following calculation formula:
the principal component of each order can be obtained, wherein Y1、Y2And YmRespectively, the 1 st, 2 nd and m th order principal components.
5. The method according to claim 2, wherein in the calculation of the plurality of structural health assessment indicators for the real-time sample data and the health sample data, the wavelet packet energy is calculated as follows:
decomposing the signals into independent sub-frequency bands by adopting a wavelet function, and calculating the energy components of the sub-frequency bands; each decomposed segment contains information of structures in different frequency bands, and the wavelet packet energy E of each order is calculated according to the following formula:
obtaining the wavelet packet energy of each order, wherein
Represents the ith node energy value at decomposition level j, and
representing the normalized energy value of the ith node at decomposition level j.
6. The method according to claim 2, wherein in the step of performing a plurality of structural health assessment index calculations on the real-time sample data and the health sample data, the secondary covariance is calculated by the following formula:
Tpl＝Rpl·Rpl T
wherein R isplIs a covariance matrix, and TplIs the quadratic covariance matrix, and p and l are the station positions.
7. The method for real-time diagnosis of building structure based on fusion index according to claim 1, wherein the fusion process using weighted average theory is performed according to the following formula:
wherein D isiIs the (i) th index of the (i) th index,
is a fusion index obtained based on the weighted average theory, WiAs the i-th indexThe weight coefficient is taken to minimize the variance among the indexes; and solving the formula (10) by a least square method to obtain the real-time fusion index and the health fusion index.
8. The method according to claim 1, wherein the Bayesian theory is used for fusion processing, and the multi-damage condition set is set as { A }1 A2…An}, multiple index set { B1 B2…Bm}; and is carried out by the following formula:
wherein, P (A)j) Is a priori probability, and P (B)k|Aj) Is the index BkTo AjDiagnosis of lesions, P (A)iAnd | B) is a fusion index obtained based on Bayesian theory.
9. The method for real-time diagnosis of building structure based on fusion index according to claim 1, wherein the D-S evidence theory is adopted for fusion treatment, and the set of multiple damage conditions is set as { A }1 A2…AnThe multi-index set is { m }1 m2…mmAnd by the following formula:
wherein m isj(Ai) And K is a real-time fusion index or a health fusion index obtained based on a D-S evidence theory for judging the ith damage condition by the jth index.
10. A building structure real-time diagnosis device based on fusion index is applied to computer equipment or a computer readable storage medium, and is characterized by comprising:
the data acquisition module is used for intercepting the acquired real-time vibration data according to a preset diagnosis step length to obtain real-time sample data; intercepting the acquired healthy vibration data according to the preset diagnosis step length to obtain healthy sample data;
the multiple structure health assessment index calculation module is used for respectively calculating multiple structure health assessment indexes of the real-time sample data and the health sample data to obtain a real-time performance parameter index and a health parameter index of the building structure;
the index fusion preprocessing and multi-index fusion computing module is used for performing regularization and probability processing on the real-time performance parameter index and the health parameter index respectively, and then performing fusion processing on the real-time performance parameter index and the health parameter index by adopting a weighted average theory, a Bayesian theory or a D-S evidence theory to obtain a real-time fusion index and a health fusion index;
and the diagnosis output module is used for comparing the real-time fusion index with the health fusion index to obtain health diagnosis information and monitoring and early warning information of the building structure.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667817.4A CN113280908A (en) | 2021-06-16 | 2021-06-16 | Building structure real-time diagnosis method and device based on fusion index |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110667817.4A CN113280908A (en) | 2021-06-16 | 2021-06-16 | Building structure real-time diagnosis method and device based on fusion index |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113280908A true CN113280908A (en) | 2021-08-20 |
Family
ID=77284702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110667817.4A Pending CN113280908A (en) | 2021-06-16 | 2021-06-16 | Building structure real-time diagnosis method and device based on fusion index |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113280908A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050114090A1 (en) * | 2003-11-20 | 2005-05-26 | Black Scott E. | Component health assessment for reconfigurable control |
| CN106525129A (en) * | 2016-11-21 | 2017-03-22 | 深圳市道桥维修中心桥梁检测站 | Intelligent bridge monitoring system based on multi-source detection fusion means |
| CN111222290A (en) * | 2020-01-13 | 2020-06-02 | 浙江工业大学 | Large-scale equipment residual service life prediction method based on multi-parameter feature fusion |
| CN111523573A (en) * | 2020-04-10 | 2020-08-11 | 重庆大学 | Bridge structure state evaluation method and system based on multi-parameter fusion |
-
2021
- 2021-06-16 CN CN202110667817.4A patent/CN113280908A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050114090A1 (en) * | 2003-11-20 | 2005-05-26 | Black Scott E. | Component health assessment for reconfigurable control |
| CN106525129A (en) * | 2016-11-21 | 2017-03-22 | 深圳市道桥维修中心桥梁检测站 | Intelligent bridge monitoring system based on multi-source detection fusion means |
| CN111222290A (en) * | 2020-01-13 | 2020-06-02 | 浙江工业大学 | Large-scale equipment residual service life prediction method based on multi-parameter feature fusion |
| CN111523573A (en) * | 2020-04-10 | 2020-08-11 | 重庆大学 | Bridge structure state evaluation method and system based on multi-parameter fusion |
Non-Patent Citations (2)
| Title |
|---|
| 张永祥 等: "基于随机子空间法的模态参数自动提取", 《机械工程学报》 * |
| 王立新 等: "基于强震动台阵实时数据的悬索桥结构诊断融合指标研究", 《城市与减灾》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109923595B (en) | Urban road traffic abnormity detection method based on floating car data | |
| KR101903879B1 (en) | Device and method for seismic safety estimation for infrastructures | |
| CN110750875B (en) | Structure dynamic and static parameter uncertainty quantitative analysis system only using output response | |
| CN110360461B (en) | Pressure pipeline monitoring system, method, device and computer readable storage medium | |
| Yao et al. | Compressive sensing based structural damage detection and localization using theoretical and metaheuristic statistics | |
| KR20210085168A (en) | System and method for safety inspection by trainiing nature freqeuncy of structure based on machine learning | |
| CN110912737A (en) | Dynamic perception performance early warning method based on hybrid model | |
| CN109684774A (en) | A kind of beam bridge safety monitoring and assessment device | |
| Meeker et al. | Statistical methods for probability of detection in structural health monitoring | |
| CN115759729A (en) | Disaster risk early warning management system based on algorithm and prediction method | |
| CN116680658B (en) | Heat wave monitoring station site selection method and system based on risk evaluation | |
| CN108809706B (en) | Network risk monitoring system of transformer substation | |
| CN112668526A (en) | Bolt group loosening positioning monitoring method based on deep learning and piezoelectric active sensing | |
| CN105205565A (en) | Controller workload prediction method and system based on multiple regression model | |
| CN114338351B (en) | Network anomaly root cause determination method and device, computer equipment and storage medium | |
| CN117074839B (en) | Electromagnetic valve fault diagnosis method and system | |
| CN116452154B (en) | Project management system suitable for communication operators | |
| CN113280908A (en) | Building structure real-time diagnosis method and device based on fusion index | |
| US10032321B2 (en) | Method and system for predicting the operation of an aircraft by similarity analysis using distributed storage and calculation capacities | |
| CN109625025B (en) | BTM equipment early warning system | |
| CN112816122B (en) | Bolt tightness degree monitoring method based on deep learning and piezoelectric active sensing | |
| CN116128690A (en) | Carbon emission cost value calculation method, device, equipment and medium | |
| CN115913891A (en) | Big data analysis-based advanced operation and maintenance system and operation and maintenance method | |
| CN114880954A (en) | Landslide sensitivity evaluation method based on machine learning | |
| CN114925517A (en) | Urban multi-disaster coupling analysis method |
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 |