CN111639450A - Tower crane damage identification method based on support vector machine - Google Patents
Tower crane damage identification method based on support vector machine Download PDFInfo
- Publication number
- CN111639450A CN111639450A CN202010494400.8A CN202010494400A CN111639450A CN 111639450 A CN111639450 A CN 111639450A CN 202010494400 A CN202010494400 A CN 202010494400A CN 111639450 A CN111639450 A CN 111639450A
- Authority
- CN
- China
- Prior art keywords
- damage
- tower crane
- support vector
- vector machine
- damage identification
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/23—Design optimisation, verification or simulation using finite element methods [FEM] or finite difference methods [FDM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- General Engineering & Computer Science (AREA)
- Operations Research (AREA)
- Educational Administration (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Geometry (AREA)
- Game Theory and Decision Science (AREA)
- Computer Hardware Design (AREA)
- Artificial Intelligence (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Data Mining & Analysis (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Biology (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Control And Safety Of Cranes (AREA)
Abstract
The invention relates to a tower crane damage identification method based on a support vector machine, and aims to solve the technical problems that the existing method for identifying tower crane damage mostly adopts manual regular maintenance, and is time-consuming and labor-consuming. The invention comprises the following steps: establishing an ANSYS finite element model according to the size data of the tower crane; setting multiple damage working conditions for modal analysis, and dividing modal analysis results into training group samples and testing group samples; establishing a support vector machine damage identification model; inputting the sample data of the training group into a support vector machine damage identification model for training, and storing the trained support vector machine damage identification model after the training is finished; and carrying out damage identification on the tower crane by using the trained support vector machine damage identification model. The method can obviously improve the sensitivity of damage identification of the tower crane structure, accurately position the damage position and the damage degree, save manpower and material resources, greatly improve the working efficiency and have high intellectualization.
Description
Technical Field
The invention belongs to the technical field of damage identification of tower cranes, and particularly relates to a tower crane damage identification method based on a support vector machine.
Background
The tower crane is the most common hoisting equipment on the construction site, is also called as a tower crane, and is indispensable equipment on the construction site. The material is used for hoisting construction raw materials such as reinforcing steel bars, wood ridges, concrete, steel pipes and the like for construction. The tower crane is used in industrial factory building construction, national symbol building (Olympic Games stadiums), city symbol building (television buildings), resident living building floors, large-scale ship (aircraft carrier) berthing ports and world-level large bridge construction, national nuclear power generation area construction, wind generating set hoisting, thermal power plant cooling tower construction, large dam (three gorges dam) construction and hydroelectric generating set equipment hoisting, and plays an irreplaceable role.
The tower crane is an indispensable hoisting equipment in the construction, has promoted construction's work efficiency greatly, has practiced thrift the labour, nevertheless because of the reason such as the inspection to equipment, maintenance not in place or misoperation simultaneously, some incident often can appear. In recent years, accidents of casualties caused by collapse of the tower crane occur.
In order to ensure the safety of life and property, the regular maintenance of the tower crane is an essential link. Due to the complexity of the structure of the tower crane, the conventional tower crane damage identification method mostly adopts manual regular maintenance, and the method is time-consuming and labor-consuming, so that an effective means is urgently needed for carrying out safety monitoring and safety evaluation on the tower crane.
Disclosure of Invention
The invention aims to solve the technical problems that the existing method for identifying the damage of the tower crane mostly adopts manual regular maintenance, the method is time-consuming and labor-consuming, and the damage condition of the tower crane cannot be monitored safely in real time.
In order to solve the technical problems, the technical scheme adopted by the invention is as follows:
a tower crane damage identification method based on a support vector machine comprises the following steps:
(1) establishing an ANSYS finite element model according to the size data of the tower crane of which the damage position and the damage degree are to be predicted;
(2) setting multiple damage working conditions for modal analysis, and dividing the obtained damage working condition modal analysis result into a training group sample and a test group sample; respectively extracting acceleration time-course responses under each damage working condition, and carrying out wavelet packet decomposition to further construct and obtain a wavelet packet energy change rate damage index;
(3) establishing a support vector machine damage identification model, taking the wavelet packet energy change rate damage index obtained in the step (2) as an input parameter of the support vector machine damage identification model, and taking the damage position and the damage degree of the tower crane as output parameters of the support vector machine damage identification model;
(4) inputting the sample data of the training group into the support vector machine damage identification model established in the step (3) for training, testing and correcting the support vector machine damage identification model by using the test group sample divided in the step (2) after the training is finished, and storing the trained support vector machine damage identification model after the training is finished;
(5) and (5) carrying out damage identification on the tower crane by using the damage identification model of the support vector machine trained and tested in the step (4).
Further, the multiple damage conditions set in the step (2) comprise single-position damage, multi-position damage and damage of different degrees; here, the damage is expressed by the reduction of the elastic modulus E, and the degree of damage is expressed by the reduction of the elastic modulus E.
Further, the damage degrees of different degrees are set as four damage degrees of 10%, 20%, 30% and 50%, and the damage degrees are changed by changing the elastic modulus E.
Further, the wavelet packet energy change rate damage index Δ (E)fj)kThe construction process of (1) is as follows: when the K-th position of the tower crane is damaged, the acceleration time-course response signal is decomposed by a wavelet packet of the j level, and the calculated ith component energy is
When the tower crane is not damaged, the acceleration time course response signal is decomposed by a wavelet packet of a j level, and the calculated ith component energy is
The energy change rate of the ith component is
Wavelet packet energy change rate damage index for defining j horizontal acceleration time-course response
The invention has the beneficial effects that:
according to the method, the support vector machine model is established, the wavelet packet energy change rate is used as the damage index, the sensitivity of damage identification of the tower crane structure can be obviously improved, the single damage state and the multiple damage states can be identified, the damage position and the damage degree can be accurately positioned, manpower and material resources are saved, the working efficiency is greatly improved, and the method has high intelligentization. The method has extremely important value for safe operation and maintenance of the tower crane, and has extremely important significance for preventing accidents and protecting life and property safety. The damage can be found as early as possible, and qualitative and quantitative analysis can be carried out on the structure position.
Drawings
FIG. 1 is a flow chart of a method for identifying damage to a tower crane according to the present invention;
fig. 2 is an ANSYS finite element model established in an embodiment of the present invention.
Detailed Description
The invention is further described below with reference to examples and figures.
As shown in fig. 1, the method for identifying damage to a tower crane based on a support vector machine in this embodiment includes the following steps:
(1) and establishing an ANSYS finite element model according to the dimension data of the tower crane of which the damage position and the damage degree are to be predicted, as shown in figure 2. And dividing the tower crane into different groups according to the size rule.
(2) Setting multiple damage working conditions for modal analysis, wherein the multiple damage working conditions comprise unit damage, multi-position damage and damage of different degrees; the unit position damage, the multi-position damage and the like are realized by simulating different damage degrees to tower cranes grouped differently. The damage is expressed by the reduction of the elastic modulus E, and the degree of damage is expressed by the amount of reduction of the elastic modulus E. Wherein, the damage degrees of different degrees are set as four damage degrees of 10%, 20%, 30% and 50%, and the damage degrees are realized by changing the elastic modulus E.
For example, if the unit damage is simulated, one of the areas is selected to simulate the damage, and the damage simulation of different degrees at the single position is realized by setting the damage degree. If multi-position damage is required, if the damage degree of the area A is set to be 10% and the damage degree of the area B is set to be 30%, different damage degrees are set for different areas to be combined, and finally damage degree simulation under various working conditions is achieved.
Dividing the obtained damage working condition modal analysis result into a training group sample and a testing group sample; acceleration time-course responses under various damage working conditions are respectively extracted, wavelet packet decomposition is carried out, and then a wavelet packet energy change rate damage index is obtained through construction, wherein the specific process is as follows:
for the j th order and the j +1 th order horizontal wavelet packet decomposition recurrence relation of the signal, the method comprises the following steps:
after the wavelet packet decomposition of j level, the original signal f (t) can be represented as:
defining the energy of the response signal at the j level
Is composed of
Is the component energy of the wavelet packet, which is stored in the component signal
Of medium energy, i.e.
By using the condition of orthogonality, the method can obtain the target,
the reduction rate α of stiffness before and after injury is defined as the injury factor, i.e., α ═ (EI)d/(EI)uWherein (EI)dFor stiffness after damage, (EI)uFor Pre-injury stiffness (α)1α2……αn) Is a damage factor of n units of the tower crane, when the k position is damaged, the acceleration time course response f (t) changes, and the damaged acceleration time course response is f (t)kThe method is a function of n unit damage factors of the tower crane and is represented by a letter a, namely: f (t)k＝a(α1α2……αn) Energy of component of wavelet packet
Is also a function of n unit damage factors of the tower crane, and is represented by a letter e,
using Taylor series expansion and omitting higher-order terms in the expansion, assuming initial value of damage factor as
Then
Can be approximately expressed as
When the K-th position of the tower crane is damaged, the acceleration time-course response signal is decomposed by a wavelet packet of the j level, and the calculated ith component energy is
When the tower crane is not damaged, the acceleration time course response signal is decomposed by a wavelet packet of a j level, and the calculated ith component energy is
The energy change rate of the ith component is
Wavelet packet energy change rate damage index for defining j horizontal acceleration time-course response
(3) Establishing a support vector machine damage identification model, wherein the specific establishing process comprises the following steps: set the sample set of lesions as (x)i,yi),i＝1,2,……n,xi∈Rn,yi∈(-1,1)，xiIs the wavelet packet energy change rate vector y at the i-th position injuryiIs xiThe corresponding desired output. And (4) identifying the damage state, namely, solving the classification problem of the support vector machine, and finding out the optimal classification hyperplane. By solving the optimization problem, the optimal classification function can be obtained
The damage degree is identified by regression using a support vector machine, a regression function is defined as f (x) ═ ω x + b, and a regression estimation function can be obtained by solving an optimization problem under constraint conditions. If data which cannot be estimated under the precision exists, introducingAnd (3) relaxing variables, Lagrange functions and dual variables, solving parameters according to an optimal solution condition (KKT condition), and finally obtaining a regression estimation function:
after a support vector machine damage identification model is established, taking the wavelet packet energy change rate damage index obtained in the step (2) as an input parameter of the support vector machine damage identification model, and taking the damage position and the damage degree of the tower crane as output parameters of the support vector machine damage identification model;
(4) and (4) inputting the sample data of the training group into the support vector machine damage identification model established in the step (3) for training, wherein in the training process, the damage working condition is expressed by a matrix representing the damage position and the damage degree. After the training is finished, testing and correcting the support vector machine damage identification model by using the test group sample divided in the step (2), and after the training is finished, storing the trained support vector machine damage identification model;
(5) and (4) carrying out damage identification on the tower crane by using the support vector machine damage identification model trained in the step (4).
From the above description, the damage identification method of the tower crane based on the support vector machine can obviously improve the sensitivity of the damage identification of the tower crane structure, can identify the single damage state and the multiple damage states, accurately positions the damage position and the damage degree, saves manpower and material resources, and greatly improves the working efficiency.
The above-described embodiments are only for illustrating the technical ideas and features of the present invention, and the purpose thereof is to enable those skilled in the art to understand the contents of the present invention and to carry out the same, and the scope of the present invention is not limited only by the embodiments, i.e., all equivalent changes or modifications made in the spirit of the present invention are still within the scope of the present invention.
Claims (4)
1. A tower crane damage identification method based on a support vector machine is characterized in that: the method comprises the following steps:
(1) establishing an ANSYS finite element model according to the size data of the tower crane of which the damage position and the damage degree are to be predicted;
(2) setting multiple damage working conditions for modal analysis, and dividing the obtained damage working condition modal analysis result into a training group sample and a test group sample; respectively extracting acceleration time-course responses under each damage working condition, and carrying out wavelet packet decomposition to further construct and obtain a wavelet packet energy change rate damage index;
(3) establishing a support vector machine damage identification model, taking the wavelet packet energy change rate damage index obtained in the step (2) as an input parameter of the support vector machine damage identification model, and taking the damage position and the damage degree of the tower crane as output parameters of the support vector machine damage identification model;
(4) inputting the sample data of the training group into the support vector machine damage identification model established in the step (3) for training, testing and correcting the model by using the test group sample divided in the step (2), and storing the trained support vector machine damage identification model after training is finished;
(5) and carrying out damage identification on the tower crane by using the trained support vector machine damage identification model.
2. The tower crane damage identification method based on the support vector machine according to claim 1, characterized in that: the multiple damage working conditions set in the step (2) comprise unit position damage, multi-position damage and damage of different degrees; here, the damage is expressed by the reduction of the elastic modulus E, and the degree of damage is expressed by the reduction of the elastic modulus E.
3. The tower crane damage identification method based on the support vector machine according to claim 2, characterized in that: the damage degrees of different degrees are set as four damage degrees of 10%, 20%, 30% and 50%, and the damage degrees are realized by changing the elastic modulus E.
4. The tower crane damage recognition based on the support vector machine according to claim 1The method is characterized in that: the wavelet packet energy change rate damage index delta (E)fj)kThe construction process of (1) is as follows: when the K-th position of the tower crane is damaged, the acceleration time-course response signal is decomposed by a wavelet packet of the j level, and the calculated ith component energy is
When the tower crane is not damaged, the acceleration time course response signal is decomposed by a wavelet packet of a j level, and the calculated ith component energy is
The energy change rate of the ith component is
Wavelet packet energy change rate damage index for defining j horizontal acceleration time-course response
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010494400.8A CN111639450A (en) | 2020-06-03 | 2020-06-03 | Tower crane damage identification method based on support vector machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010494400.8A CN111639450A (en) | 2020-06-03 | 2020-06-03 | Tower crane damage identification method based on support vector machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111639450A true CN111639450A (en) | 2020-09-08 |
Family
ID=72329527
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010494400.8A Withdrawn CN111639450A (en) | 2020-06-03 | 2020-06-03 | Tower crane damage identification method based on support vector machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639450A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239492A (en) * | 2021-04-09 | 2021-08-10 | 山东建筑大学 | Tower crane body steel structure damage positioning and monitoring method |
| CN115374575A (en) * | 2022-10-25 | 2022-11-22 | 山东建筑大学 | Tower crane body structure damage positioning method based on adjacent space point distance model |
| CN117909853A (en) * | 2024-03-19 | 2024-04-19 | 合肥通用机械研究院有限公司 | Intelligent monitoring method and system for equipment damage based on mechanism and working condition big data |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090295A (en) * | 2017-12-27 | 2018-05-29 | 武汉光谷北斗控股集团有限公司 | A kind of long-span cablestayed bridges Damages in Stay Cables recognition methods |
| CN110532657A (en) * | 2019-08-21 | 2019-12-03 | 哈尔滨工业大学 | Bridge pier structure state evaluating method based on transmission vehicle excitation and wavelet packet analysis |
-
2020
- 2020-06-03 CN CN202010494400.8A patent/CN111639450A/en not_active Withdrawn
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108090295A (en) * | 2017-12-27 | 2018-05-29 | 武汉光谷北斗控股集团有限公司 | A kind of long-span cablestayed bridges Damages in Stay Cables recognition methods |
| CN110532657A (en) * | 2019-08-21 | 2019-12-03 | 哈尔滨工业大学 | Bridge pier structure state evaluating method based on transmission vehicle excitation and wavelet packet analysis |
Non-Patent Citations (5)
| Title |
|---|
| 何浩祥等: "基于支持向量机的钢筋混凝土桥梁损伤识别", 《公路交通科技》 * |
| 李延强等: "基于小波包分析与支持向量机的斜拉索损伤识别", 《石家庄铁道大学学报(自然科学版)》 * |
| 沈荣胜: "塔式起重机动力特性分析及在结构预警中的应用研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 王胜春等: "基于小波包和支持向量机的塔机结构损伤诊断研究", 《机械科学与技术》 * |
| 罗丹等: "应用小波包神经网络的塔机起重臂损伤识别", 《机械设计与制造》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113239492A (en) * | 2021-04-09 | 2021-08-10 | 山东建筑大学 | Tower crane body steel structure damage positioning and monitoring method |
| CN113239492B (en) * | 2021-04-09 | 2022-08-05 | 山东建筑大学 | Tower crane body steel structure damage positioning and monitoring method |
| CN115374575A (en) * | 2022-10-25 | 2022-11-22 | 山东建筑大学 | Tower crane body structure damage positioning method based on adjacent space point distance model |
| CN115374575B (en) * | 2022-10-25 | 2023-03-24 | 山东建筑大学 | Tower crane body structure damage positioning method based on adjacent space point distance model |
| CN117909853A (en) * | 2024-03-19 | 2024-04-19 | 合肥通用机械研究院有限公司 | Intelligent monitoring method and system for equipment damage based on mechanism and working condition big data |
| CN117909853B (en) * | 2024-03-19 | 2024-05-31 | 合肥通用机械研究院有限公司 | Intelligent monitoring method and system for equipment damage based on mechanism and working condition big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111639450A (en) | Tower crane damage identification method based on support vector machine | |
| CN100470416C (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
| CN111585349B (en) | Power grid model management and monitoring system | |
| CN112069698A (en) | Hoisting simulation construction method and system based on BIM | |
| CN108536128A (en) | A kind of machine learning fault diagnosis system of parameter optimization | |
| CN108614191A (en) | A kind of power distribution network and buried cable fault detection method based on BIM models | |
| CN112507414B (en) | Method, system and storage medium for evaluating safety of power transmission tower under downburst | |
| CN108536130A (en) | A kind of Fault Diagnosis in Chemical Process system of colony intelligence optimizing | |
| CN115659756A (en) | Method for analyzing windproof performance of transmission tower | |
| CN106408016A (en) | Distribution network power outage time automatic identification model construction method | |
| CN115293424A (en) | New energy maximum power generation capacity calculation method, terminal and storage medium | |
| CN113159503B (en) | Remote control intelligent safety evaluation system and method | |
| CN116704729A (en) | Industrial kiln early warning system and method based on big data analysis | |
| CN116317937A (en) | Distributed photovoltaic power station operation fault diagnosis method | |
| CN116146421A (en) | Intelligent control method and system based on fan state sensing | |
| Zhao et al. | Research on the application of computer intelligent detection in civil engineering technology | |
| CN112507290B (en) | Power distribution equipment fault probability pre-judging method, device and storage medium | |
| CN104697585A (en) | Cooling tower tower-barrel strength predicating control system and method thereof | |
| CN106934729A (en) | Building Testing and appraisal method and device | |
| Feng et al. | Application of BIM in the Design and Construction of Fabricated Buildings | |
| CN117670313B (en) | Power plant inspection method, power plant inspection system and storable medium | |
| CN116258481B (en) | Control method and system for intelligent construction of building engineering | |
| CN109472006B (en) | Calculation result screening method based on PSD-BPA | |
| CN117152355B (en) | Visual supervision system based on factory data | |
| CN111293701B (en) | Method and device for estimating sunken area of power distribution network containing distributed photovoltaic |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200908 |
|
| WW01 | Invention patent application withdrawn after publication |