CN114511017A - Multi-step identification method and system for structural damage of railway station house - Google Patents
Multi-step identification method and system for structural damage of railway station house Download PDFInfo
- Publication number
- CN114511017A CN114511017A CN202210081678.1A CN202210081678A CN114511017A CN 114511017 A CN114511017 A CN 114511017A CN 202210081678 A CN202210081678 A CN 202210081678A CN 114511017 A CN114511017 A CN 114511017A
- Authority
- CN
- China
- Prior art keywords
- damage
- damaged
- substructure
- determining
- railway station
- 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
- 230000006378 damage Effects 0.000 title claims abstract description 163
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000010206 sensitivity analysis Methods 0.000 claims abstract description 6
- 230000008859 change Effects 0.000 claims description 33
- 238000013528 artificial neural network Methods 0.000 claims description 30
- 238000012549 training Methods 0.000 claims description 25
- 230000003902 lesion Effects 0.000 description 9
- 230000006870 function Effects 0.000 description 7
- 208000027418 Wounds and injury Diseases 0.000 description 6
- 208000014674 injury Diseases 0.000 description 6
- 238000000342 Monte Carlo simulation Methods 0.000 description 5
- 230000036541 health Effects 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 230000035945 sensitivity Effects 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 238000005260 corrosion Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 230000005779 cell damage Effects 0.000 description 1
- 208000037887 cell injury Diseases 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010200 validation analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Computational Linguistics (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
A multi-step identification method and a system for structural damage of a railway station house are disclosed, wherein the method comprises the following steps: step 1, dividing a railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure; and 2, determining a damaged substructure in the railway station house structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component. The method comprises the steps of dividing a station house into a plurality of substructures according to different characteristics of each part of the structure, further dividing members in each substructure into important members and common members according to sensitivity analysis, determining the damaged substructures in the station house, then determining the damaged members in the known damaged substructures, and finally determining the damage degree of the damaged members. The method can reduce the complexity of the network, greatly reduce the learning samples and save the learning time.
Description
Technical Field
The invention relates to the field of building health monitoring, in particular to a method and a system for identifying structural damage of a railway station house in multiple steps.
Background
The structural health monitoring adopts a sensor to acquire information (such as stress, strain, temperature, natural frequency, mode and the like) related to the structural health condition on line in real time, and combines an advanced communication system, an information processing technology and a finite element modeling method to diagnose the damage position and degree of the structure and evaluate the service condition, reliability, durability and bearing capacity of the structure, so that the structural health monitoring can be controlled in the early stage of structural damage to eliminate potential safety hazards or send out early warning signals when the structural use condition is seriously deteriorated, thereby avoiding the occurrence of major safety accidents and ensuring the safety of people life and property.
In recent decades, many typical engineering accidents occur in large-span space structures at home and abroad, and the frequent engineering accidents not only cause the loss of personnel and property, but also generate severe social influence. Therefore, how to diagnose the structure and predict the failure behavior of the structure in advance becomes a problem which needs to be solved urgently in the current large-scale engineering.
Disclosure of Invention
In view of the technical defects and technical drawbacks in the prior art, embodiments of the present invention provide a method and a system for identifying structural damage of a railway station building in multiple steps, which overcome the above problems or at least partially solve the above problems, and the specific scheme is as follows:
as a first aspect of the present invention, there is provided a method for multiple step-by-step identification of structural damage to a railway station house, the method comprising:
step 1, dividing a railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
and 2, determining a damaged substructure in the railway station house structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
Further, the method further comprises: the components in each substructure are classified into important components for which only damage identification is performed and general components based on sensitivity analysis.
Further, the sensitivity-based analysis is divided into important and general components, specifically: the Spearman grade correlation coefficient equal to or greater than 0.025 is an important component, and is otherwise a general component, based on the Spearman grade correlation coefficient as a criterion for distinguishing the important component from the general component.
Further, in step 2, determining a damaged substructure in the railway station house structure comprises: determining a first damage index affecting the structure of a railway station house, and training a first neural network by using the first damage index as a training sample; and acquiring a first damage index of each substructure as an input parameter of the trained first neural network, and determining the substructure with damage in the railway station house structure based on an output result of the first neural network, wherein the first damage index is a damage index related to a damage position.
Further, in step 2, identifying a damaged member within a known damaged substructure comprises: determining a second damage index affecting the inner component of the substructure, and training a second neural network by using the second damage index as a training sample; and acquiring a second damage index of the substructure, wherein the second damage index is used as an input parameter of the trained second neural network, and determining a damaged component in the substructure based on an output result of the second neural network, and the second damage index is a damage index related to a damage position.
Further, in step 2, determining the damage degree of the damaged member includes: determining a third damage index which influences the damage degree of a component in the substructure, and training a third neural network by taking the third damage index as a training sample; and acquiring a third damage index of the damaged component in the substructure, wherein the third damage index is used as an input parameter of the trained third neural network, and determining the damage degree of the component based on an output result of the third neural network.
Further, the damage index related to the damage position is a regularized frequency change rate or a change ratio of a two-order frequency
Further, the third damage indicator for determining the degree of damage affecting the component within the substructure is a square ratio of two-order frequency changes.
As a second aspect of the present invention, there is provided a multiple step-by-step identification system for structural damage of a railway station house, the system comprising a classification module and a step-by-step identification module;
the classification module is used for dividing the railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
the step identification module is used for determining a damaged substructure in the railway station building structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
The invention has the following beneficial effects:
the method comprises the steps of dividing a station house into a plurality of substructures according to different characteristics of each part of the structure, further dividing members in each substructure into important members and common members according to sensitivity analysis, determining the damaged substructures in the station house, then determining the damaged members in the known damaged substructures, and finally determining the damage degree of the damaged members. The method can reduce the complexity of the network, greatly reduce the learning samples and save the learning time.
Drawings
Fig. 1 is a flowchart of a multiple step-by-step identification method for structural damage of a railway station building according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in fig. 1, as a first embodiment of the present invention, a method for identifying structural damage of a railway station house in multiple steps is provided, which mainly includes the following steps:
step 1, dividing a railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
and 2, determining a damaged substructure in the railway station house structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
The idea of the method will be described in detail below:
wherein: the classification of the railway station building structure is specifically shown in the following table, because the adoption of the substructure still can cause dimension disaster, the components in the substructure are further divided into important components and general components according to sensitivity analysis, and damage identification is only carried out on the important components, wherein the Spearman grade correlation coefficient is used as a standard for distinguishing the important components from the general components, the important components with the correlation coefficient of 0.025 or more are, and the general components are not.
Preferably, determining a damaged substructure in a railway station house structure comprises: determining a first damage index affecting the structure of a railway station house, and training a first neural network by using the first damage index as a training sample; acquiring a first damage index of each substructure, wherein the first damage index is used as an input parameter of a trained first neural network, and determining a damaged substructure in a railway station house structure based on an output result of the first neural network, and the first damage index is a damage index related to a damage position;
in the above embodiment, only the positions of the damaged substructures need to be determined, so that all important components in the substructures generate required data, i.e. the first damage index, by randomly changing the rigidity of the components by using the monte carlo method, and then generate corresponding training samples using the data, where only the positions of the damaged substructures need to be determined, so that the parameters which are independent of the damage degree and only related to the damage positions need to be used as much as possible when selecting the input parameters, and the number of output units is the number of the substructures.
Preferably, the means for determining the presence of a lesion within a known-lesion substructure comprises: determining a second damage index affecting the inner component of the substructure, and training a second neural network by using the second damage index as a training sample; and acquiring a second damage index of the substructure, wherein the second damage index is used as an input parameter of the trained second neural network, and determining a damaged component in the substructure based on an output result of the second neural network, and the second damage index is a damage index related to a damage position.
In the embodiment, because the damaged components are selected from the substructure rather than the whole railway station house structure, the training samples can be greatly reduced, and the network training is simplified. At the moment, all important components in the substructure need to generate required data, namely a second damage index, by independently utilizing a Monte Carlo method, and then corresponding training samples are generated by using the data. Similarly, here, it is also necessary to select as many parameters as possible only regarding the damage location as input, and the number of output units is the number of important components in the substructure.
Preferably, determining the extent of damage of the damaged member comprises: determining a third damage index which influences the damage degree of a component in the substructure, and training a third neural network by taking the third damage index as a training sample; and acquiring a third damage index of the damaged component in the substructure, wherein the third damage index is used as an input parameter of the trained third neural network, and determining the damage degree of the component based on an output result of the third neural network.
In the above embodiment, after the position of the damaged member is determined, the problem is not a classification problem but a regression problem, so that the label does not use a discrete value of one-hot code (vector composed of 0 and 1) but uses a continuous value of the damage degree, and in this case, input parameters related to the damage degree, such as a change in frequency before and after damage, a square of a frequency change, a change in mode before and after damage, and the like, need to be used as much as possible.
The input parameters of the neural network are various, different damage identification targets can be achieved by selecting different input parameters, and the cost and the use performance for selecting different input parameters are different. Therefore, in order to better identify the damage of the structure, the advantages and disadvantages of various damage indexes must be analyzed, and only then can a proper damage index be selected. The present invention uses two types of damage indicators: frequency-based and mode-vibration-type-based damage indicators;
frequency-based dynamic impairment indicators include:
(1) regularized frequency rate of change NFRN
Kaminski notes that the rate of frequency change is related to both lesion location and extent of lesion, whereas the rate of regularized frequency change is related only to lesion location.
The frequency rate of change (NFR) is expressed as:
the normalized frequency change rate (NFRN) is expressed as:
wherein q represents all the vibration mode numbers involved in the calculation.
Regularized frequency rate of change NFRNiThe principle for lesion localization is derived as follows: by local damageThe change in the ith order natural frequency of the structure is caused as a function of the amount of stiffness change and the location of the damage:
δωi＝f(δK，r) (3)
where r is the damage location vector, the series expansion and neglecting higher order terms can be:
since there is no frequency change without damage, f (0, r) ═ 0, then:
NFRi＝δKgi(0，r) (5)
thus, when a structure is singly damaged, the frequency change rate of regularization can be expressed as:
obviously, the frequency rate of change of the regularization is a function of the lesion location only:
(2) ratio of change of two-order frequency
From formula (5), it can be obtained:
NFRj＝δKgj(0，r) (7)
assuming that the stiffness varies independently of frequency, there are:
obviously, the ratio of change of the two order frequencies is a function of lesion location only.
(3) Square ratio of frequency change
The solution for the natural frequency is attributed to the following generalized eigenvalue problem:
wherein M and K are each a total of the structureMass array and total stiffness array, omegaiIs the ith order circle frequency, phiiAssuming that the damage causes the change in the stiffness matrix to be Δ K and the mass is unchanged for the corresponding mode shape vector, then:
in the formula (I), the compound is shown in the specification,
and delta phiiRespectively, the change in frequency and mode vector due to damage; left-multiplying equation (10) by phii TApplying equation (9) and ignoring higher order terms, we get:
the damage delta K of the overall rigidity matrix is composed of rigidity matrixes of all damage units, namely:
in the formula, neΔ K is the total number of damaged unitseAnd (4) an expanded e-th damage unit stiffness matrix. Substituting formula (12) for formula (11) to obtain:
considering the unit damage degree index alphanCan be considered as follows:
ΔKe＝αeKe (14)
thus, it is obtained:
for a single lesion element e, equation (15) can be simplified as:
the equation shows the rate of change of the square of the frequency and the degree of cell damage αeIn relation to the location (cell e), when using i, j two-order frequency information, we can obtain:
therefore, when only one damage unit or the damage degrees of all the damage units are similar, the change ratio of the square of the frequency is only a function of the damage position; commonly used parameters related to the extent of damage include the frequency rate of change and the rate of change of the frequency squared, among others. The station house belongs to a high-order hyperstatic structure, and generally can withstand the sudden fracture of a certain component, but if the damage is caused by corrosion (weak links are generated on other components), the redistribution of force can cause or accelerate the damage of other more components, and the integrity of the structure can be seriously damaged, so that the gradual breakdown of the structure can be caused. The prior research on the injury by using the neural network mainly aims at the single injury condition, because the regularization frequency of the single injury is only related to the injury position and is not related to the injury degree, so that the injury position is easier to identify. Generally, for a structural system composed of multiple components, the damage condition is not single damage, such as damage caused by corrosion, and multiple components can be involved at the same time, which is a typical multiple damage condition. For a multiple damage case, the regularization frequency is not only related to the damage location, but also to the damage level, so identifying the damage location by a common method is more difficult than for a single damage case. However, since the monte carlo method is used herein to generate enough samples, it is not important whether the samples are related to the lesion location only. By adopting a deep learning method, sample parameters can be selected at will as long as a large number of samples exist. The latter analysis we mainly use the regularized frequency rate of change, the ratio of change of the two orders of frequency and the ratio of the square of the two orders of frequency change. Based on the Monte Carlo method, the damage identification of multiple damages can be directly researched, and the damage identification of single damage can also be researched. The basic idea of the method is to classify the problems into two problems of classification and regression
Among these, with regard to the classification problem:
(1) damage data is generated within each sub-structure using the Monte Carlo method, where the damage data refers to the natural frequencies obtained when the modulus of elasticity of the structurally important member is changed. The regularization frequency change rate, the change ratio of the two-order frequency and the square ratio of the two-order frequency change can be calculated by using the damage data, and can be used as input samples of the network, and the label adopts one-hot coding.
(2) The damage sample is divided into a training sample and a test sample (also called a validation sample). Usually 80% of the total number of samples are used as training samples and 20% as test samples.
(3) The number of layers of the neural network, the number of cells per layer, and the activation function are selected. The loss function uses class cross entropy (categorical cross entropy). Training the network with the samples and labels in (1). The last layer adopts a softmax layer with n units, and an array consisting of n probability values (the sum is 1) is returned. The largest element in the array indicates that the corresponding substructure (or structure) is damaged.
Among these, with respect to the regression problem:
the damage degree of the member is a regression problem, and the same input as the classification problem can be used for the input at this time, but the label does not use the discrete value of one-hot encoding, but uses a continuous value of the damage degree. The loss function takes the MSE, the Mean Squared Error (MSE), the square of the difference between the predicted value and the target value. The number of output units of the network is the number of important components of the substructure, and the output of the units is the degree of damage to the components.
The invention provides a multiple step-by-step identification method of structure damage based on sensitivity, which comprises the steps of firstly dividing the whole structure into a plurality of substructures, then dividing the component into an important component and a common component in the substructures through self sensitivity, carrying out damage identification only aiming at the important component, and respectively solving the damage problem as a substructure classification identification problem and a component damage degree regression problem.
As a second embodiment of the present invention, there is provided a multiple step-by-step identification system for structural damage of a railway station house, the system including a classification module and a step-by-step identification module;
the classification module is used for dividing the railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
the step identification module is used for determining a damaged substructure in the railway station building structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.
Claims (9)
1. A multiple step-by-step identification method for structural damage of a railway station house is characterized by comprising the following steps:
step 1, dividing a railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
and 2, determining a damaged substructure in the railway station house structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
2. The method of multiple step-by-step identification of structural damage to a railway station house of claim 1, further comprising: the components in each substructure are classified into important components for which only damage identification is performed and general components based on sensitivity analysis.
3. The multiple step-by-step identification method of railway station building structural damage according to claim 1, characterized in that the classification into important components and general components based on sensitivity analysis is specifically: the Spearman grade correlation coefficient equal to or greater than 0.025 is an important component, and is otherwise a general component, based on the Spearman grade correlation coefficient as a criterion for distinguishing the important component from the general component.
4. The method for multiple step-by-step identification of structural damage of a railway station house according to claim 1, wherein the step 2 of determining the damaged substructure of the railway station house structure comprises: determining a first damage index affecting the structure of a railway station house, and training a first neural network by using the first damage index as a training sample; and acquiring a first damage index of each substructure, wherein the first damage index is used as an input parameter of the trained first neural network, and determining the damaged substructure in the railway station house structure based on an output result of the first neural network, and the first damage index is a damage index related to the damage position.
5. The method of multiple step identification of structural damage to a railway station house of claim 1 wherein the step 2 of identifying damaged components within a known damaged substructure comprises: determining a second damage index affecting the inner component of the substructure, and training a second neural network by using the second damage index as a training sample; and acquiring a second damage index of the substructure, wherein the second damage index is used as an input parameter of the trained second neural network, and determining a damaged component in the substructure based on an output result of the second neural network, and the second damage index is a damage index related to a damage position.
6. The method of claim 1, wherein the step 2 of determining the damage level of the damaged member comprises: determining a third damage index which influences the damage degree of a component in the substructure, and training a third neural network by taking the third damage index as a training sample; and acquiring a third damage index of the damaged component in the substructure, wherein the third damage index is used as an input parameter of the trained third neural network, and determining the damage degree of the component based on an output result of the third neural network.
7. The method for multiple step-by-step identification of structural damage of a railway station building according to claim 4 or 5, wherein the damage index related to the damage position is a regularized frequency change rate or a change ratio of a two-step frequency.
8. The method of claim 1, wherein the third damage indicator that determines the degree of damage to a component within the substructure is a square ratio of two-order frequency changes.
9. A multi-step identification system for structural damage of a railway station house is characterized by comprising a classification module and a step identification module;
the classification module is used for dividing the railway station house structure into a plurality of substructures according to different characteristics of each part of the railway station house structure;
the step identification module is used for determining a damaged substructure in the railway station building structure, then determining a damaged component in the known damaged substructure, and finally determining the damage degree of the damaged component.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081678.1A CN114511017A (en) | 2022-01-24 | 2022-01-24 | Multi-step identification method and system for structural damage of railway station house |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210081678.1A CN114511017A (en) | 2022-01-24 | 2022-01-24 | Multi-step identification method and system for structural damage of railway station house |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114511017A true CN114511017A (en) | 2022-05-17 |
Family
ID=81550164
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210081678.1A Pending CN114511017A (en) | 2022-01-24 | 2022-01-24 | Multi-step identification method and system for structural damage of railway station house |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114511017A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109325308A (en) * | 2018-10-17 | 2019-02-12 | 江苏开放大学（江苏城市职业学院） | Reinforced concrete hollow shear wall seismic Damage evaluation method based on energy transfer rate |
| US20190095781A1 (en) * | 2017-09-23 | 2019-03-28 | Nanoprecise Sci Corp. | System and method for automated fault diagnosis and prognosis for rotating equipment |
| KR102097120B1 (en) * | 2018-12-31 | 2020-04-09 | 주식회사 애자일소다 | System and method for automatically determining the degree of breakdown by vehicle section based on deep running |
| DE102019125949A1 (en) * | 2019-09-26 | 2021-04-01 | Schaeffler Technologies AG & Co. KG | Model-based method for determining the wear condition of a component |
| CN112861223A (en) * | 2021-01-26 | 2021-05-28 | 石家庄铁道大学 | Method for discriminating damage of structural part of power transmission tower |
| CN113420964A (en) * | 2021-06-07 | 2021-09-21 | 煤炭科学研究总院 | Bridge safety detection method and device and electronic equipment |
-
2022
- 2022-01-24 CN CN202210081678.1A patent/CN114511017A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20190095781A1 (en) * | 2017-09-23 | 2019-03-28 | Nanoprecise Sci Corp. | System and method for automated fault diagnosis and prognosis for rotating equipment |
| CN109325308A (en) * | 2018-10-17 | 2019-02-12 | 江苏开放大学（江苏城市职业学院） | Reinforced concrete hollow shear wall seismic Damage evaluation method based on energy transfer rate |
| KR102097120B1 (en) * | 2018-12-31 | 2020-04-09 | 주식회사 애자일소다 | System and method for automatically determining the degree of breakdown by vehicle section based on deep running |
| DE102019125949A1 (en) * | 2019-09-26 | 2021-04-01 | Schaeffler Technologies AG & Co. KG | Model-based method for determining the wear condition of a component |
| CN112861223A (en) * | 2021-01-26 | 2021-05-28 | 石家庄铁道大学 | Method for discriminating damage of structural part of power transmission tower |
| CN113420964A (en) * | 2021-06-07 | 2021-09-21 | 煤炭科学研究总院 | Bridge safety detection method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102252843B (en) | Assessment method for rolling bearing performance variation | |
| US20100191503A1 (en) | Prognostics and health management implementation for self cognizant electronic products | |
| Shahidi et al. | Structural damage detection and localisation using multivariate regression models and two-sample control statistics | |
| CN104221475A (en) | Fault detection, localization and performance monitoring of photosensors for lighting controls | |
| KR102065435B1 (en) | Infrastructure health monitoring system and method | |
| Tang et al. | Rolling bearing remaining useful life prediction via weight tracking relevance vector machine | |
| Thöns et al. | On damage detection system information for structural systems | |
| CN116677570A (en) | Fault early warning method and system based on cabin temperature monitoring of offshore wind turbine | |
| CN117113166A (en) | Industrial boiler fault detection method based on improved integrated learning | |
| Agusta et al. | Value of information-based risk and fatigue management for offshore structures | |
| Lan et al. | Performance degradation prediction model of rolling bearing based on self-checking long short-term memory network | |
| CN101526433B (en) | Method for automatically diagnosing faults of monitoring system | |
| CN108536980B (en) | Gas detector discrete site selection optimization method considering reliability factor | |
| CN114511017A (en) | Multi-step identification method and system for structural damage of railway station house | |
| CN117434450A (en) | Battery health state prediction method and system | |
| CN117269340A (en) | GIS equipment intelligent fault diagnosis method and system based on gas components | |
| Law et al. | Damage Models and Algorithms for Assessment of Structures under Operating Conditions: Structures and Infrastructures Book Series, Vol. 5 | |
| Sridevi et al. | Predictive Maintenance of Lead-Acid Batteries Using Machine Learning Algorithms | |
| CN113139584B (en) | Sensor optimal arrangement method for water supply pipe network pollutant invasion point identification | |
| CN114154305A (en) | Sensor optimal arrangement multi-criterion decision analysis method for detecting and identifying leakage of water supply pipe network | |
| CN115169650A (en) | Equipment health prediction method for big data analysis | |
| KR20230102431A (en) | Oil gas plant equipment failure prediction and diagnosis system based on artificial intelligence | |
| CN113591982A (en) | Performance evaluation method and system of fault detection and diagnosis algorithm | |
| Lesobre et al. | A Usage-Informed Preventive Maintenance Policy to Optimize the Maintenance Free Operating Period for Multi-Component Systems | |
| Sun et al. | Multidamage Detection of Bridges Using Rough Set Theory and Naive‐Bayes Classifier |
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 |