CN111027168A - In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision - Google Patents
In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision Download PDFInfo
- Publication number
- CN111027168A CN111027168A CN201910977030.0A CN201910977030A CN111027168A CN 111027168 A CN111027168 A CN 111027168A CN 201910977030 A CN201910977030 A CN 201910977030A CN 111027168 A CN111027168 A CN 111027168A
- Authority
- CN
- China
- Prior art keywords
- equipment
- bearing capacity
- destructive
- model
- characteristic parameters
- 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
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M7/00—Vibration-testing of structures; Shock-testing of structures
- G01M7/08—Shock-testing
Abstract
Aiming at the situation that nondestructive detection and destructive collision belong to two deformation levels with completely different magnitude levels and properties, and a mathematical/mechanical theory for revealing the mapping relation of the two deformation levels is not proposed so far, the invention provides an in-situ nondestructive detection method for detecting the bearing capacity of equipment during destructive collision based on artificial intelligence. Based on machine learning theory, an artificial intelligent bridge (AI model) is erected between the characteristic parameters of the equipment and the bearing capacity of the equipment in destructive collision, the characteristic parameters of the equipment are obtained based on nondestructive testing methods such as a structural dynamic recognition method and the like, then the bearing capacity of the equipment in destructive collision is obtained by means of the AI model, and in-situ nondestructive testing of the bearing capacity of the equipment in destructive collision is realized. Compared with the prior art, the technical scheme of the invention has the beneficial effects that: and the in-situ nondestructive testing of the loading capacity of the equipment under the destructive collision condition is realized by using a nondestructive testing method.
Description
Technical Field
The invention relates to the field of nondestructive testing, in particular to an in-situ nondestructive testing method for testing the bearing capacity of equipment in destructive collision.
Background
The bearing capacity of the equipment in destructive collision determines the safety protection capacity of the equipment in resisting the striking of an external invading object, such as the collision safety protection capacity of automobiles, trains, airplanes, road traffic safety facilities and the like, and the capacity of satellites, aircraft carriers, naval vessels, tanks, armored vehicles, large dams, nuclear power facilities and the like in resisting the striking of external objects such as missiles and the like, which are examples of the bearing capacity of the equipment in destructive collision.
The nondestructive testing is suitable for in-situ testing, but the nondestructive testing is nondestructive, so that the nondestructive testing can only detect the characteristic parameters when the deformation is small, but the bearing capacity of the equipment during destructive collision is the characteristic parameters when the deformation is large, including large displacement and large rotation, and the conventional nondestructive testing method cannot detect the characteristic parameters when the deformation is large.
Nondestructive detection and destructive collision belong to two deformation levels with different magnitude levels and properties, and a mathematical/mechanical theory for revealing the mapping relation of the two levels is not proposed up to now. Obviously, only by establishing a mapping relation or a special connection mechanism between the two layers, the characteristic parameters obtained by nondestructive testing can be used for obtaining the characteristic parameters in destructive collision. The briskly-developed artificial intelligence has the potential of establishing such special connection mechanisms, thereby indicating a new direction for the nondestructive testing of the loading capacity during destructive collision. It is against this background that the present invention has come to mind.
Disclosure of Invention
Aiming at the current situation that the existing nondestructive detection method can not detect the characteristic parameters when the elastoplasticity is greatly deformed, the invention provides an in-situ nondestructive detection method for detecting the bearing capacity of equipment in destructive collision, which comprises the following implementation steps:
s1: formulating a sample equipment test plan for constructing the AI model;
s2: obtaining dynamic characteristic parameters of the equipment based on a structural power identification method, obtaining physical parameters of the equipment, such as structural size and the like, based on measuring of a measuring tool, wherein the dynamic characteristic parameters of the equipment and the physical parameters of the structural size and the like jointly form characteristic parameters of the sample equipment;
s3: acquiring the bearing capacity of the sample equipment in destructive collision by using a collision test platform based on destructive collision tests;
s4: based on a machine learning theory, taking results of S2 and S3 as training samples, and establishing an AI model taking the result of S2 as input and the result of S3 as output;
s5: constructing an error set based on a prediction result and a physical test result of the AI model, and determining a confidence interval of the AI model under a given confidence coefficient by using a pivot method aiming at the error set;
s6: for equipment to be tested, dynamic characteristic parameters of the equipment are obtained based on a structural power identification method, physical parameters such as the structural size of the equipment are obtained based on measurement of a measuring tool, the dynamic characteristic parameters of the equipment and the physical parameters such as the structural size form characteristic parameters of sample equipment, and then the bearing capacity and the confidence interval of the equipment to be tested in destructive collision are obtained by means of an AI model.
Preferably, the sample equipment test planning in step S1 is formulated by using an orthogonal test table for the sensitive factors and their effective value intervals on the basis of single factor analysis, and each factor and level in the orthogonal table includes physical parameters and mechanical parameters corresponding to various typical use environment conditions and key geometric parameters corresponding to the representative model of the equipment.
Preferably, the characteristic parameters acquired in step S2, the physical parameters such as the structural dimensions of the equipment, and the like are measured by a gauge, and the gauge is calibrated. The dynamic characteristic parameters are obtained by using a force hammer excitation method to excite the equipment, then using a sensor to pick up the dynamic response of a measuring point of the equipment, and then using a structural dynamic identification method to identify the dynamic characteristic parameters of the structural dynamic model. The dynamic response of the measuring point of the pickup equipment adopts a digital filtering mode to filter out interference signals through low-pass filtering software, and the force hammer and the sensor are calibrated.
Preferably, the loading capacity obtained in step S3 is obtained by selecting a test system with a high-speed data acquisition card for data acquisition, and the sampling frequency is preferably not less than 1 MHz. The acquired bearing capacity is the result of eliminating the influence of the inertia effect of the test device, interference signals are filtered out by adopting a digital filtering mode through low-pass filtering software, and test equipment for acquiring the bearing capacity and a test system with a high-speed data acquisition card are calibrated.
Preferably, the AI model in step S4 is constructed using a least squares support vector machine.
Preferably, in the step S5, the determination of the confidence interval of the AI model is to construct an error set by using the prediction result and the physical test result of the AI model, and then determine the confidence interval of the AI model at a given confidence by using the pivot method for the error set.
The test of the device to be tested in step S5 is a nondestructive test, and the collision test is not required to be performed.
Compared with the prior art, the technical scheme of the invention has the beneficial effects that: and the in-situ nondestructive testing of the loading capacity of the equipment under the destructive collision condition is realized by using a nondestructive testing method.
Drawings
FIG. 1 is a flow chart of the method of the present invention.
Detailed Description
The drawings are only for illustrative purposes and are not to be construed as limiting the patent, and the technical scheme of the invention is further described in the following with reference to the drawings and the embodiment.
Example 1:
for a certain equipment, the in-situ nondestructive detection of the bearing capacity of the equipment in destructive collision is realized through the following steps.
S1: a sample rig test plan is formulated for constructing the AI model. Firstly, main physical parameters and mechanical parameters of the equipment are determined according to various typical use environment conditions of the equipment (for example, the physical parameters and the mechanical parameters of pile foundation soil are required to be determined for the equipment related to a pile foundation), and meanwhile, key geometric parameters of the equipment are determined according to a representative model of the equipment. Then, carrying out single factor analysis (specific single factor analysis, which can be a collision test or a simulation analysis, is adopted in the present example) on the bearing capacity of the equipment in destructive collision, carrying out single factor analysis on each factor influencing the bearing capacity of the equipment in destructive collision, and determining the influence rule of the value of each factor on the bearing capacity of the equipment, thereby finding out the sensitive factor which is the factor obviously influencing the bearing capacity of the equipment from the factors, and simultaneously determining the effective value interval of each sensitive factor according to the feasible design area and the manufacturing process level. Then, the total number of training samples that can be provided to the AI model is determined based on the relationship between the prediction accuracy of the AI model and the capacity of the training samples, and how much development expenditure is. And finally, selecting an orthogonal test table meeting the requirements from the orthogonal test tables according to the total number of the training samples and the number of the sensitive factors, and determining the horizontal number of each sensitive factor so as to complete the sample equipment test planning for constructing the AI model.
S2: for all sample equipment planned in S1, dynamic characteristic parameters of the equipment are obtained based on a structural power identification method, physical parameters of the equipment, such as structural size, are obtained based on measuring tool measurement, and the dynamic characteristic parameters of the equipment and the physical parameters, such as the structural size, of the equipment jointly form characteristic parameters of the sample equipment. Firstly, measuring key geometric parameters of sample equipment by using a measuring tool to obtain physical parameters of the equipment, such as structure size and the like, and recording the physical parameters on a record. Then, utilizing vibration excitation facilities such as a force hammer to excite the equipment and recording a vibration excitation force function applied to the equipment by the vibration excitation facilities such as the force hammer, and filtering out interference signals by adopting a digital filtering mode through low-pass filtering software for the recorded vibration excitation force function; and picking up dynamic response of the equipment measuring point by using a sensor arranged on the equipment measuring point, and filtering out interference signals by adopting a digital filtering mode and low-pass filtering software for the picked dynamic response. And then, carrying out dynamic response analog simulation analysis of the equipment under the excitation of the force hammer, namely, establishing a dynamic response analysis model of the equipment by arbitrarily giving a group of dynamic characteristic parameters, applying an excitation force function to the position of the analysis model corresponding to the real object, and obtaining the dynamic response of the upper measuring point of the analysis model corresponding to the real object measuring point through simulation analysis of the dynamic response analysis model. Finally, utilizing a structural power identification method to carry out inversion identification research on the dynamic characteristic parameters of the equipment, namely constantly optimizing and adjusting the dynamic characteristic parameters of the equipment by taking the minimization of the error between the corresponding dynamic responses of the object measuring points and the model measuring points as a target, and circulating the steps until the error between the corresponding dynamic responses of the object measuring points and the model measuring points reaches an expected target, wherein the corresponding dynamic characteristic parameters are the dynamic characteristic parameters of the sample equipment.
S3: and (4) developing destructive collision tests on all sample equipment planned by the S1 by using a collision test platform, and acquiring the bearing capacity of all the sample equipment. The test data is acquired by a high-speed data acquisition card, and the sampling frequency is not less than 1 MHz. The influence of the inertia effect of the testing device is eliminated from the acquired bearing capacity of the equipment, and meanwhile, the interference signals are filtered out through low-pass filtering software in a digital filtering mode.
S4: and establishing an AI model taking the result of S2 as input and the result of S3 as output by adopting a least squares support vector machine or a neural network in a machine learning theory and taking the results of S2 and S3 as training samples.
S5: and constructing an error set by utilizing the prediction result of the AI model and the physical test result, wherein the physical test result can be a training sample set, the prediction result of the AI model is a prediction sample set which is in the same specification as the training sample set, and then determining the confidence interval of the AI model under the given confidence coefficient by utilizing a principal component method aiming at the error set.
S6: an in-situ test was developed, comprising the following steps:
s61: determining characteristic parameters of equipment to be tested;
s611: measuring key geometric parameters of the equipment to be measured by using the measuring tool to obtain physical parameters of the equipment to be measured, such as structure size and the like, and recording the physical parameters on a record;
s612: exciting the equipment to be tested by using an excitation facility such as a force hammer, recording an excitation force function applied to the equipment to be tested by the excitation facility such as the force hammer, and filtering out an interference signal by adopting a digital filtering mode through low-pass filtering software for the recorded excitation force function; picking up the dynamic response of the measuring point of the equipment to be measured by using a sensor arranged on the measuring point of the equipment to be measured, and filtering out an interference signal by adopting a digital filtering mode and low-pass filtering software for the picked dynamic response;
s613: carrying out dynamic response analog simulation analysis of the equipment to be tested under the excitation of the force hammer, namely establishing a dynamic response analysis model of the equipment to be tested by arbitrarily giving a group of dynamic characteristic parameters, applying an excitation force function to the position of the analysis model corresponding to a real object, and obtaining the dynamic response of a measuring point on the analysis model corresponding to the real object measuring point through simulation analysis of the dynamic response analysis model;
s614: carrying out inversion recognition research on the dynamic characteristic parameters of the equipment to be tested by using a structural power recognition method, namely continuously optimizing and adjusting the dynamic characteristic parameters of the equipment to be tested by taking the minimization of the error between the physical measuring point and the dynamic response corresponding to the model measuring point as a target, and circulating the steps until the error between the physical measuring point and the dynamic response corresponding to the model measuring point reaches an expected target, wherein the corresponding dynamic characteristic parameters are the solved dynamic characteristic parameters of the equipment to be tested;
s615: combining the physical parameters such as the structural size of the equipment to be tested obtained in the step S611 and the dynamic characteristic parameters of the equipment to be tested obtained in the step S614 into characteristic parameters of the equipment to be tested;
s62: taking the characteristic parameters of the equipment to be tested of S615 as input parameters of the AI model, and obtaining the bearing capacity of the equipment to be tested during destructive collision by means of the AI model;
s63: determining a confidence interval of the bearing capacity of the equipment to be tested in the destructive collision in the S62 by using the confidence interval of the AI model given in the S5 under the given confidence coefficient;
the invention provides an in-situ nondestructive testing method for testing the bearing capacity of equipment in destructive collision, which establishes a special connection mechanism between deformation levels with two completely different magnitude levels and properties of nondestructive testing and destructive collision by means of artificial intelligence. Based on machine learning theory, an artificial intelligent bridge (AI model) is erected between the characteristic parameters of the equipment and the bearing capacity of the equipment in destructive collision, the characteristic parameters of the equipment are obtained based on nondestructive testing methods such as a structural dynamic recognition method and the like, then the bearing capacity of the equipment in destructive collision is obtained by means of the AI model, and in-situ nondestructive testing of the bearing capacity of the equipment in destructive collision is realized. Compared with the prior art, the technical scheme of the invention has the beneficial effects that: and the in-situ nondestructive testing of the loading capacity of the equipment under the destructive collision condition is realized by using a nondestructive testing method. .
It should be understood that the above-described embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. Other variations and modifications will be apparent to persons skilled in the art in light of the above description. And are neither required nor exhaustive of all embodiments. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the claims of the present invention.
Claims (7)
1. An in-situ nondestructive testing method for testing the bearing capacity of equipment in destructive collision is characterized in that: by means of artificial intelligence, an artificial intelligence bridge (AI model) is erected between the characteristic parameters of equipment and the bearing capacity of the equipment in destructive collision, the characteristic parameters of the equipment are obtained based on nondestructive testing methods such as a structural dynamic identification method and the like, then the bearing capacity of the equipment in destructive collision is obtained by means of the AI model, and in-situ nondestructive testing of the bearing capacity of the equipment in destructive collision is realized, and the specific implementation steps are as follows:
s1: formulating a sample equipment test plan for constructing the AI model;
s2: obtaining dynamic characteristic parameters of the equipment based on a structural power identification method, obtaining physical parameters of the equipment, such as structural size and the like, based on measuring of a measuring tool, wherein the dynamic characteristic parameters of the equipment and the physical parameters of the structural size and the like jointly form characteristic parameters of the sample equipment;
s3: acquiring the bearing capacity of the sample equipment in destructive collision by using a collision test platform based on destructive collision tests;
s4: based on a machine learning theory, taking results of S2 and S3 as training samples, and establishing an AI model taking the result of S2 as input and the result of S3 as output;
s5: constructing an error set based on an AI model prediction result and a physical test result, and determining a confidence interval of the AI model under a given confidence coefficient by using a pivot method aiming at the error set;
s6: for equipment to be tested, dynamic characteristic parameters of the equipment are obtained based on a structural power identification method, physical parameters such as the structural size of the equipment are obtained based on measurement of a measuring tool, the dynamic characteristic parameters of the equipment and the physical parameters such as the structural size form characteristic parameters of sample equipment, and then the bearing capacity and the confidence interval of the equipment to be tested in destructive collision are obtained by means of an AI model.
2. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: the sample equipment test planning in step S1 is made by using an orthogonal test table for sensitive factors and effective value intervals thereof based on single factor analysis, and each factor and level in the orthogonal table includes physical parameters and mechanical parameters corresponding to various typical use environment conditions and key geometric parameters corresponding to representative model numbers of equipment.
3. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: the characteristic parameters obtained in the step S2, the physical parameters of the equipment such as the structure size and the like are obtained by measuring a measuring tool, the dynamic characteristic parameters are obtained by picking up the dynamic response of the measuring points of the equipment after the equipment is excited by a force hammer excitation method, and then identifying the dynamic characteristic parameters of the structure dynamic model by using a structure dynamic identification method, wherein the dynamic response of the measuring points of the picked-up equipment is filtered by low-pass filtering software in a digital filtering mode to remove interference signals.
4. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: the bearing capacity obtained in step S3 is obtained by using a high-speed data acquisition card to acquire data, the sampling frequency is not less than 1MHz, the acquired bearing capacity is a result of eliminating the influence of the inertia effect of the test device, and the interference signal is filtered out by using low-pass filtering software in a digital filtering manner.
5. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: the AI model in step S4 is constructed using a least squares support vector machine.
6. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: in the step S5, the determination of the confidence interval of the AI model is to construct an error set according to the prediction result and the physical test result of the AI model, and then determine the confidence interval of the AI model under the given confidence by using the pivot method for the error set.
7. The in-situ non-destructive testing method for testing the load-bearing capacity of an apparatus in a destructive collision according to claim 1, wherein: the test of the device to be tested in step S6 is a nondestructive test, and the collision test is not required to be performed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977030.0A CN111027168B (en) | 2019-10-15 | 2019-10-15 | In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910977030.0A CN111027168B (en) | 2019-10-15 | 2019-10-15 | In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111027168A true CN111027168A (en) | 2020-04-17 |
| CN111027168B CN111027168B (en) | 2022-10-04 |
Family
ID=70204823
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910977030.0A Active CN111027168B (en) | 2019-10-15 | 2019-10-15 | In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111027168B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101865758A (en) * | 2010-06-12 | 2010-10-20 | 南京航空航天大学 | Impact load location method based on multiple signal classification algorithm |
| US20130216089A1 (en) * | 2010-04-22 | 2013-08-22 | The University Of North Carolina At Charlotte | Method and System for Remotely Inspecting Bridges and Other Structures |
| CN103279795A (en) * | 2013-06-13 | 2013-09-04 | 中南大学 | Method for predicating collision damage of passengers |
| JP6401358B1 (en) * | 2017-09-13 | 2018-10-10 | 中日本高速技術マーケティング株式会社 | Grout filling status discrimination system and program |
-
2019
- 2019-10-15 CN CN201910977030.0A patent/CN111027168B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130216089A1 (en) * | 2010-04-22 | 2013-08-22 | The University Of North Carolina At Charlotte | Method and System for Remotely Inspecting Bridges and Other Structures |
| CN101865758A (en) * | 2010-06-12 | 2010-10-20 | 南京航空航天大学 | Impact load location method based on multiple signal classification algorithm |
| CN103279795A (en) * | 2013-06-13 | 2013-09-04 | 中南大学 | Method for predicating collision damage of passengers |
| JP6401358B1 (en) * | 2017-09-13 | 2018-10-10 | 中日本高速技術マーケティング株式会社 | Grout filling status discrimination system and program |
Non-Patent Citations (6)
| Title |
|---|
| 刘春燕: "基于智能方法的桩基承载力检测", 《舰船电子工程》, no. 06, 20 June 2010 (2010-06-20) * |
| 梅亚敏等: "基于碰撞声信号的农产品品级检测技术综述", 《西北农林科技大学学报(自然科学版)》, no. 04, 27 March 2013 (2013-03-27) * |
| 王山山等: "基于振动理论的水工结构无损检测技术研究综述", 《河海大学学报(自然科学版)》, no. 05, 30 October 2004 (2004-10-30) * |
| 陈世杰: "混凝土结构的无损检测技术", 《居舍》, no. 04, 5 February 2018 (2018-02-05) * |
| 雷正保等: "基于混合元胞自动机的护栏防撞端头设计", 《西华大学学报》, 30 November 2018 (2018-11-30) * |
| 黄卫平等: "基于神经网络的压力容器焊缝磁性无损检测的研究", 《制造业自动化》, no. 08, 15 August 2007 (2007-08-15) * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111027168B (en) | 2022-10-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105865735B (en) | A kind of bridge vibration test and dynamic characteristics recognition methods based on video monitoring | |
| CN110704801B (en) | Bridge cluster structure operation safety intelligent monitoring and rapid detection complete method | |
| Mevel et al. | Application of a subspace-based fault detection method to industrial structures | |
| CN103076394B (en) | Safety evaluation method for ocean platform based on integration of vibration identification frequencies and vibration mode | |
| CN110108551B (en) | Rock mechanical property testing device and method based on acoustic emission detection technology | |
| CN101836100A (en) | A method for detection and automatic identification of damage to rolling bearings | |
| CN106017833B (en) | A kind of performance test methods of high-damping micro-vibration isolation device | |
| WO2019020825A1 (en) | Apparatus and method for performing an impact excitation technique | |
| CN205843918U (en) | Slab and girder load identification and the multi-function test stand of non-destructive tests | |
| US10533970B2 (en) | System and method for detecting irregularities in rebar in reinforced concrete | |
| CN110470738A (en) | Structural Damage Identification based on vibratory response difference than function | |
| Sun et al. | Damage detection based on structural responses induced by traffic load: Methodology and application | |
| Entezami et al. | Improving feature extraction via time series modeling for structural health monitoring based on unsupervised learning methods | |
| CN110057918B (en) | Method and system for quantitatively identifying damage of composite material under strong noise background | |
| CN111027168B (en) | In-situ nondestructive testing method for bearing capacity of detection equipment in destructive collision | |
| CN109781863A (en) | Structure erosion two-stage detection method and its system based on fast vibration test | |
| CN112131781A (en) | Steel structure damage detection method based on full-connection neural network and transfer rate function | |
| CN114627121B (en) | Structural member stress detection method, device, equipment and medium | |
| CN116522085A (en) | Full-automatic inhaul cable frequency extraction, fixed-order and cable force identification method and application | |
| Dudzik et al. | Optimal dynamic error formula for charge output accelerometer obtained by the neural network | |
| Zhen et al. | Damage detection of offshore platform structures using time domain response data | |
| CN112161785A (en) | Ocean engineering structure micro-damage judgment method | |
| Janapati et al. | Fatigue crack quantification approach based on multi-path unit-cell concept in sensor network | |
| Cheng et al. | Detecting damage to offshore platform structures using the time-domain data | |
| Long et al. | Research on displacement monitoring method of heavy load bridge structure based on stereo vision |
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 |