CN110210629A - The crane safety assessment system excavated based on big data - Google Patents
The crane safety assessment system excavated based on big data Download PDFInfo
- Publication number
- CN110210629A CN110210629A CN201910393440.0A CN201910393440A CN110210629A CN 110210629 A CN110210629 A CN 110210629A CN 201910393440 A CN201910393440 A CN 201910393440A CN 110210629 A CN110210629 A CN 110210629A
- Authority
- CN
- China
- Prior art keywords
- crane
- data
- big data
- big
- mis
- 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
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 28
- 238000005065 mining Methods 0.000 claims abstract description 24
- 238000011156 evaluation Methods 0.000 claims abstract description 19
- 238000012544 monitoring process Methods 0.000 claims abstract description 18
- 230000036541 health Effects 0.000 claims abstract description 10
- 238000003860 storage Methods 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012800 visualization Methods 0.000 claims abstract description 5
- 238000000034 method Methods 0.000 claims description 18
- 238000013528 artificial neural network Methods 0.000 claims description 9
- 238000007689 inspection Methods 0.000 claims description 9
- 238000012423 maintenance Methods 0.000 claims description 5
- 230000006641 stabilisation Effects 0.000 claims description 5
- 238000011105 stabilization Methods 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 4
- 230000003993 interaction Effects 0.000 claims description 4
- 230000005284 excitation Effects 0.000 claims description 3
- 238000013138 pruning Methods 0.000 claims description 3
- 238000009877 rendering Methods 0.000 claims description 2
- 238000009966 trimming Methods 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 2
- 230000007246 mechanism Effects 0.000 abstract description 3
- 238000012502 risk assessment Methods 0.000 abstract 1
- 238000012545 processing Methods 0.000 description 6
- 230000002159 abnormal effect Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000013461 design Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004519 manufacturing process Methods 0.000 description 4
- 239000002184 metal Substances 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 238000007792 addition Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 230000000737 periodic effect Effects 0.000 description 2
- 238000004321 preservation Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 206010011906 Death Diseases 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010130 dispersion processing Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003862 health status Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000630 rising effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2455—Query execution
- G06F16/24564—Applying rules; Deductive queries
-
- 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
- G06Q10/20—Administration of product repair or maintenance
-
- 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
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
- G06Q50/265—Personal security, identity or safety
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Strategic Management (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Computational Linguistics (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Databases & Information Systems (AREA)
- Computer Security & Cryptography (AREA)
- Game Theory and Decision Science (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Health & Medical Sciences (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of crane safety assessment systems excavated based on big data, including crane safety assessment big data acquisition module, crane database storage module, crane big data preprocessing module, crane big data association rule mining module and crane big data security evaluation visualization model.Relevance between crane measuring point data is introduced into crane safety prediction and assessment by the system, utilize correlation rule strong between improved CFP-Growth++ algorithm mining data, rule digging is carried out to health monitoring numerical value between the measuring points such as vibration between the stress of certain vibrative mechanism, crossbeam and track, so as to find and predict the potential failure of crane, to realize the risk assessment of early stage.
Description
Technical field
The present invention relates to the fault identification of crane and security evaluation field, it is specifically a kind of based on big data excavate
Crane safety assessment system.
Background technique
Crane, since all kinds of failures or damage often occur for itself or external factor, causes huge during long service
Big casualties and property loss.The effectively health status of analysis assessment crane, for identification crane facility operation in time
It is abnormal, it ensures crane safety, reliably with economical operation provide important support.
For a long time, lifting equipment is mostly by using mandatory manufacturing supervision and inspection, control and examination of installation and artificial periodically inspection
The modes such as test detect its whether safety, focus primarily upon the abnormity early warning of individual event Monitoring data flow, the degree of automation is low, examines
Excessive cycle, inspection data is limited, has significant limitation, its in use safe and reliable can not be completely secured
Property.And since the measuring point for needing to monitor on crane is more, the sample frequency of each measuring point is high, from beginning one's duty end-of-life
Data collection last length, this process can generate a large amount of monitoring data, higher and higher to the performance requirement of data processing.It removes
Outside above-mentioned periodic detection and online monitoring data, crane also creates a large amount of during design, manufacture, use, maintenance etc.
Basic data, virtual emulation data, mantenance data etc., data information amount is huge, data format diversification and structure is complicated, often
The data processing of rule and safety evaluation method are awkward, do not adapt to the requirement of hoisting machinery development.
Big data is the important content of generation information technology industry, is answered in the fault identification of equipment and security evaluation field
With having a high potential, hoisting machinery security evaluation has had been provided with the data basis for carrying out big data analysis and data excacation.
Therefore, it needs to carry out crane multi-source information statistical analysis and data mining technology based on big data theory, effectively identifies
The abnormal conditions of crane facility realize the security state evaluation and prediction of crane, transport for crane safety, reliably with economy
Row provides safeguard.
Summary of the invention
In order to overcome the above-mentioned deficiencies of the prior art, the present invention provides a kind of crane safeties excavated based on big data
Assessment system.
The technical scheme adopted by the invention is that:
There is provided a kind of crane safety assessment system excavated based on big data, which is characterized in that the system includes: lifting
Machine security evaluation big data acquisition module, for acquiring and transmitting crane running state data and health monitoring data；
Crane database storage module, for storing the data of big data acquisition module acquisition, and the big number arranged
According to including crane regular inspection record, maintenance record；
Crane big data preprocessing module, for being pre-processed to the data stored in database storage module；
Crane big data association rule mining module, crane big data association rule mining module are advised using association
CFP-Growth++ algorithm is then excavated, pretreated data are analyzed and concluded, it is specific to choose crane steady operation
When running state data as data source, including each measuring point big data that can most reflect crane structure feature, then carry out
Sliding-model control is associated rule digging by CFP-Growth++ algorithm, closes according between stress data and vibration data
Connection regular grid DEM and confidence level determine correlation, and then by the stress data of obtained stabilization Strong association rule, vibration
Data carry out the security evaluation prediction of crane state parameter by compact type wavelet neural network；
Crane big data security evaluation visualization model, heavy-duty machine big data association rule mining module is pre- for rendering
It surveys as a result, and realizing human-computer interaction.
The crane safety assessment system excavated based on big data, wherein crane safety assessment big data acquisition
Module by the design and manufacture data and regular inspection mantenance data etc. of combing crane, while using novel sensing, telecommunication and
The technologies such as Digital Signal Analysis and Processing acquire the operating status and health monitoring data of heavy-duty machine in real time, are transmitted.
The crane safety assessment system excavated based on big data, wherein crane database storage module is used for
Store crane regular inspection record, the dimension of the crane operating status big data, health monitoring big data and the arrangement that locally acquire
The big datas such as record are repaired, in order to query history record, the additions and deletions that can also carry out data, which change, the operation such as looks into, prints preservation, convenient
Management and operation of the user to system, realize the mass management of data.
The described crane safety assessment system excavated based on big data, wherein crane big data preprocessing module be
Premise and the basis for analyzing data and mining data, for being processed to crane big data and improving the quality of data.
The crane safety assessment system excavated based on big data, wherein crane big data security evaluation is visual
Change the situation that crane is presented with intuitive text, figure, warning note etc. for module, realizes human-computer interaction.
The crane safety assessment system excavated based on big data, it is preferred that emphasis is realize the association of crane big data
Rule digging module: the method that the present invention introduces association rule mining to the security evaluation of crane, from the health prison of crane
It surveys and searches out relatively useful rule in numerous data, and these rules can show the correlation between each group of data, from
And crane structure vibration is studied with the correlation between stress data, the interested rule in part is obtained, and rule has been used for
The prediction of heavy-duty machine monitor value.
The described crane safety assessment system excavated based on big data, wherein crane big data association rule mining
Module:, can in order to increase result when carrying out crane data correlation rule digging the characteristics of according to crane mass data
Reliability, present invention introduces more minimum support models, to original big data association rules mining algorithm Apriori algorithm and
FP-Growth (Frequent Pattern Growth) algorithm improves, and proposes a kind of based on the improved of MIS-Tree
Association rule mining method: different item supports is arranged for different item for CFP-Growth++ algorithm, multinomial to construct with this
Mesh supports tree construction (Minimum Item Support Tree, MIS-Tree), while introducing minimum minimum support value
The cut operator of (Least Minimum Support, LMS) optimization item collection.
In the crane big data association rule mining module of above scheme, wherein CFP-Growth++ algorithm passes through following
Process is realized:
1, one group of transaction itemset I={ v is given1,v2,v3,...,vm, for Arbitrary TermMIS (v) indicates v most
Event support, allocation rule are as follows:
M(av)=Δ f (av) (2)
MIN indicates the smallest MIS value in all items, f (a in formulav) it is the frequency that project v occurs, Δ (0≤Δ≤1)
It is the parameter of the MIS value and project Frequency relationship for item controlled.When Δ=0, only single most ramuscule is indicated
Degree of holding.
2, present invention introduces entries to support tree MIS-Tree, and optimizes its cut operator, to find all frequent episodes
Collection and those supports are greater than the nonmatching grids of MIN.
3, it after generating initial MIS-Tree, needs to delete some non-frequent nodes and cut operator is carried out to tree construction, cut
When branch, in order to reduce search space, the present invention is using following trimming strategy: (1) since last of MIS list, if
The support of item collection is less than its MIS value and is then trimmed to about；(2) if finding frequent item, select its MIS value as minimum minimum
Support angle value, be defined as LMS value, and the support of residual term in MIS list is compared with LMS value, if less than if LMS from
It is trimmed in MIS-Tree.
4, in order to more succinct, merging has the node of identical items name, and the beta pruning of non-frequent leaf node can reduce
Merge the scale of MIS-Tree.
5, it is similar to FP-Growth algorithm, CFP-Growth++ algorithm recursively constructs item according to MIS-Tree tree construction
Part MIS-Tree obtains all frequent episode destination aggregation (mda)s.
The crane big data association rule mining module is wherein following beneficial produced by CFP-Growth++ algorithm
Effect:
1, data class in the database is various, substantial amounts when, only focusing on a unified minimum support can draw
Rise some problems, miss some useful rules, CFP-Growth++ algorithm when carrying out crane data correlation rule digging,
Increase the confidence level of result.
2, the speed of service of CFP-Growth++ algorithm ratio FP-Growth algorithm is faster.When α is smaller, when algorithm is run
Between gap become apparent from, this is because CFP-Growth++ algorithm optimization beta pruning process, reduces the search space of algorithm.
3, CFP-Growth++ is with good stability as FP-Growth algorithm, and works as and apply extensive
When on data set, the scalability of CFP-Growth++ is stronger, and operational efficiency is more excellent.
The described crane safety assessment system excavated based on big data, wherein crane big data association rule mining
Module is when the on-line monitoring parameter to crane is predicted, using compact type wavelet neural network as the base of prediction modeling
Plinth chooses Morlet small echo as input layer to the excitation function of intermediate hidden layer, and Morlet small echo calculation formula is as follows:
Crane big data association rule mining module on above scheme basis, is realized by following procedure:
1, data when choosing crane steady operation are as data source, including each can most reflect crane structure feature
Measuring point big data, such as ladder frame top vertical vibration, crossbeam front end vertical vibration, left side in the middle part of big beam orbit
Vibration data etc. in vertical direction.
2, record, missing data, noise jamming data and abnormal data etc. repeat just to the measuring point data of acquisition
After step pretreatment, reselection carries out sliding-model control based on the method for distance.
3, to data rule that may be present between the measuring points such as vibration between the stress of vibrative mechanism, crossbeam and track
Then, be associated rule digging with CFP-Growth++ algorithm proposed by the present invention, using crossbeam, interorbital vibrational term as
The left side of item collection, right side of the stress of metal structure as item collection, it is 10% that MIS value in set algorithm is selected after being run multiple times,
Min confidence min_conf=50%.
4, rules results are analyzed, by after excavation support, confidence value compared with setting value, if support
Value and confidence value are all higher, and the probability for illustrating that above-mentioned rule occurs in gantry crane operation is larger, and is stable, Ke Yixin
The Strong association rule appointed, has reacted the correlation between vibration and pressure detection point data, then using the correlation between data to rising
The quantity that heavy-duty machine monitors measuring point carries out reasonably optimizing, simultaneously for more dangerous measuring point, predicts monitor value, is advanced by
The case where solving measuring point.
5, it is implicit to centre as input layer to be chosen to crane state parameter prediction based on correlation rule for Morlet small echo
The excitation function of layer, by the vibration number in the stabilization Strong association rule crossbeam front end vertical direction obtained under sample data set
Input according to the stress data of, land side crossbeam horizontal direction vibration data and rear crossbeam as wavelet neural network, rear crossbeam
Output of the stress data as neural network, carry out security evaluation to predict after crane big stress beam with this.
The crane safety assessment system excavated the present invention is based on big data the utility model has the advantages that the present invention by crane measuring point
Relevance between data introduces crane safety prediction with the research of assessment, not only can use the correlation pair between data
The quantity for monitoring measuring point carries out reasonably optimizing, simultaneously for more dangerous measuring point, can more accurately carry out to monitor value
The case where predicting, measuring point can be understood in advance, and it is effectively combined the security evaluation that other theories carry out early stages.
Detailed description of the invention
Fig. 1 is structure chart of the invention；
Fig. 2 is the rear crossbeam stress data predicted value and measured value comparison diagram of example；
Fig. 3 is the rear crossbeam stress data prediction error comparison diagram of example.
Specific embodiment
In order to which the contents of the present invention are more clearly understood with technical solution, this is further elaborated below in conjunction with attached drawing
The principle and specific embodiment of invention.
The present invention provides a kind of crane safety assessment system excavated based on big data, as shown in Figure 1, the system includes
Crane safety assesses big data acquisition module, crane database storage module, crane big data preprocessing module, lifting
Machine big data association rule mining module and crane big data security evaluation visualization model.
Wherein design and manufacture data and regular inspection dimension that crane safety assessment big data acquisition module passes through combing crane
Motor, gear-box, bearing repaired data etc., while choosing operating mechanism therein and other structures etc. is as main research pair
As operating status and health monitoring data using technologies such as novel sensing, telecommunication and Digital Signal Analysis and Processings, to heavy-duty machine
The vibration at such as each position, stress, temperature data are acquired in real time, are transmitted.
Wherein crane database storage module is for storing the crane operating status big data locally acquired, health prison
The big datas such as crane regular inspection record, the maintenance record of big data and arrangement are surveyed, in order to query history record, can also be carried out
The additions and deletions of data, which change, the operation such as looks into, prints preservation, and user is facilitated to realize the mass pipe of data to the management and operation of system
Reason.
Wherein crane big data preprocessing module is to analyze premise and the basis of data and mining data, for acquisition
Crane big data carry out repeating the pretreatment such as record, missing data, noise jamming data and abnormal data, wherein using
SNM (Sorted-Neighborhood Method) neighbour's ranking method handles Data duplication record；It is analyzed according to data
Parameter type, purposes etc. select different methods to be filled the missing data of crane, as there is periodic law
Data such as strain is filled temperature monitoring data using most reliable value using the method for mean value filling, and for nonumeric type
Vacancy value, be filled according to artificial experience or the most value of statistics frequency of occurrence；Using wavelet threshold denoising method to making an uproar
Acoustic jamming data are pre-processed；Using local outlier factor LOF (Local Outlier Factor) detection method as different
The method of regular data processing.
Wherein crane big data association rule mining module use association rule mining CFP-Growth++ algorithm, to rise
Heavy-duty machine monitoring data are analyzed and are concluded.The present invention specifically chooses metal knot when certain shore container crane steady operation
Health monitoring data between the measuring points such as the vibration between the stress of structure, crossbeam and track as data source, carry out data from
After dispersion processing, rule digging is associated by CFP-Growth++ algorithm, is closed according between stress data and vibration data
Connection regular grid DEM and confidence level determine correlation, and then by the stress data of obtained stabilization Strong association rule, vibration
Data carry out the prediction of crane state parameter by compact type wavelet neural network.
Wherein crane big data security evaluation visualization model is risen with presentations such as intuitive text, figure, warning notes
The situation of heavy-duty machine realizes human-computer interaction.
On the basis of above scheme, crane safety assessment big data acquisition module is contained to rubber tyre gantry crane design, system
Make, install, detecting, the information data that use, multiple stages such as maintenance are related to is acquired, be mainly included in line monitoring number
According to, such as stress signal, vibration signal.
On the basis of above scheme, crane big data association rule mining module is using more based on MIS-Tree
Degree of holding association rule mining CFP-Growth++ method forms strong correlation rule between crane data, the strong association to discovery
Rule is analyzed, and is applied to the prediction of health monitoring parameter, provides more effective numbers for the security evaluation of early stage
According to support.
Illustrate detailed process of the invention now in conjunction with example:
1, by taking certain shore container crane as an example, the measuring point progress that wherein can most react crane structure feature is had selected
Analysis, the monitoring measuring point and its meaning selected are as shown in table 1, and data when choosing crane steady operation are used as data source, sharp
Rule digging is associated with CFP-Growth++ algorithm.
Table 1 monitors measuring point and its meaning
2, this example carries out after tentatively pre-processing the measuring point data of acquisition, and reselection is carried out discrete based on the method for distance
Change processing.
3, rule that may be present between the measuring points such as vibration between the stress of metal structure, crossbeam and track is visited
It begs for.In order to keep the result excavated more targeted, using crossbeam, interorbital vibrational term as the left side of item collection, metal structure
Right side of the stress as item collection, it is 10% that MIS value in set algorithm is selected after being run multiple times, min confidence min_conf=
50%, the partial association rules results obtained after excavating are as shown in table 2.
Table 2 partial association rule
4, interpretation of result: by taking rule 1 and rule 3 as an example, the simultaneous reactions stress data (Y2) of rear crossbeam, crossbeam front end
The correlation between vibration data (Z2) and land side crossbeam horizontal direction vibration data (Z8) in portion's vertical direction.Due to this
Two regular grid DEM values and confidence value are all higher, and the probability for illustrating that above-mentioned rule occurs in gantry crane operation is larger, and
It and is rule that is stable, can trusting.
5, the crane state parameter prediction based on correlation rule: using compact type wavelet neural network as prediction modeling
The on-line monitoring parameter of crane is predicted on basis.The curve comparison figure of prediction result as indicated with 2, relative error such as Fig. 3
It is shown.As seen from the figure, rule is used for the prediction of crane monitor value, prediction error falls to 0.11%-8.81%, demonstrates base
In the validity and accuracy of Association Rules Model prediction, the crane safety assessment excavated based on big data is realized.
It should be understood that for those of ordinary skills, it can be modified or changed according to the above description,
And all these modifications and variations should all belong to the protection domain of appended claims of the present invention.
Claims (5)
1. a kind of crane safety assessment system excavated based on big data, which is characterized in that the system includes:
Crane safety assesses big data acquisition module, for acquiring and transmitting crane running state data and health monitoring number
According to；
Crane database storage module, for storing the data of big data acquisition module acquisition, and the big data packet arranged
Include crane regular inspection record, maintenance record；
Crane big data preprocessing module, for being pre-processed to the data stored in database storage module；
Crane big data association rule mining module, using association rule mining CFP-Growth++ algorithm, after pretreatment
Data analyzed and concluded, specific running state data when choosing crane steady operation is including each as data source
A measuring point big data that can most reflect crane structure feature, then carry out sliding-model control, by CFP-Growth++ algorithm into
Row association rule mining determines related according to the support of correlation rule between stress data and vibration data and confidence level
Property, and then by stress data, the vibration data of obtained stabilization Strong association rule, it is carried out by compact type wavelet neural network
The security evaluation of crane state parameter is predicted；
Crane big data security evaluation visualization model, for rendering the prediction knot of heavy-duty machine big data association rule mining module
Fruit, and realize human-computer interaction.
2. the crane safety assessment system according to claim 1 excavated based on big data, which is characterized in that described anti-
The measuring point big data for reflecting crane structure feature includes ladder frame top vertical vibration data, crossbeam front end vertical direction
Vibration data, land side crossbeam horizontal direction vibration data, vibration data on left vertical direction in the middle part of big beam orbit, rear crossbeam
Stress data.
3. the crane safety assessment system according to claim 2 excavated based on big data, which is characterized in that choose
Morlet small echo is strong by the stabilization obtained by CFP-Growth++ algorithm as input layer to the excitation function of intermediate hidden layer
Correlation rule data, including crossbeam front end vertical vibration data, land side crossbeam horizontal direction vibration data and rear big
Input of the stress data of beam as wavelet neural network, output of the stress data of rear crossbeam as neural network, with prediction
Big stress beam and security evaluation is carried out to it after crane.
4. the crane safety assessment system according to claim 1 excavated based on big data, which is characterized in that CFP-
Growth++ algorithm is realized by following procedure:
Give one group of transaction itemset I={ v1,v2,v3,...,vm, for Arbitrary TermThe minterm branch of MIS (v) expression v
Degree of holding, allocation rule are as follows:
M(av)=Δ f (av)
MIN indicates the smallest MIS value in all items, f (a in formulav) it is the frequency that project v occurs, Δ is for item controlled
The parameter of MIS value and project Frequency relationship, 0≤Δ≤1 indicate only single minimum support when Δ=0；
It introduces entry and supports tree MIS-Tree, and optimize its cut operator, it is big with the frequent item set and support that find all
In the nonmatching grids of MIN；
After generating initial MIS-Tree, non-frequent node is deleted, cut operator carried out to tree construction, when beta pruning, use is following
Trimming strategy: (1) it since last of MIS list, is trimmed to about if the support of item collection is less than its MIS value；(2) such as
Fruit finds frequent item, selects its MIS value as minimum minimum support value, is defined as LMS value, and will remain in MIS list
The support of remainder is compared with LMS value, is trimmed from MIS-Tree if being less than LMS.
5. the crane safety assessment system according to claim 4 excavated based on big data, which is characterized in that merge tool
There is the node of identical items name.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393440.0A CN110210629A (en) | 2019-05-13 | 2019-05-13 | The crane safety assessment system excavated based on big data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910393440.0A CN110210629A (en) | 2019-05-13 | 2019-05-13 | The crane safety assessment system excavated based on big data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110210629A true CN110210629A (en) | 2019-09-06 |
Family
ID=67787010
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910393440.0A Pending CN110210629A (en) | 2019-05-13 | 2019-05-13 | The crane safety assessment system excavated based on big data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110210629A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111076886A (en) * | 2020-01-02 | 2020-04-28 | 南京中船绿洲机器有限公司 | Vibration testing method of high-performance electric deck crane |
| CN111160759A (en) * | 2019-12-27 | 2020-05-15 | 上海建工集团股份有限公司 | Preprocessing method and system for construction safety monitoring big data of building engineering |
| CN111178674A (en) * | 2019-12-04 | 2020-05-19 | 中国特种设备检测研究院 | Industrial big data driven hoisting machinery health management and control service system |
| CN112398906A (en) * | 2020-10-14 | 2021-02-23 | 上海海典软件股份有限公司 | Internet platform data interaction method and device |
| CN113651245A (en) * | 2021-08-16 | 2021-11-16 | 合肥市春华起重机械有限公司 | Crane bearing capacity monitoring system |
| CN116976014A (en) * | 2023-06-13 | 2023-10-31 | 江苏省特种设备安全监督检验研究院 | Crane design optimization method and system based on performance check |
-
2019
- 2019-05-13 CN CN201910393440.0A patent/CN110210629A/en active Pending
Non-Patent Citations (3)
| Title |
|---|
| R. UDAY KIRAN ETAL.: "Novel Techniques to Reduce Search Space in Multiple Minimum Supports-Based Frequent Pattern Mining Algorithms", 《INTERNATIONAL CONFERENCE ON EXTENDING DATABASE TECHNOLOGY》 * |
| 佘俊胜等: "基于FP树的多最小支持度广义关联规则挖掘算法", 《小型微型计算机系统》 * |
| 蒋明华: "工程机械液压缸拉缸和密封圈损坏故障诊断研究", 《中国优秀博硕士学位论文全文数据库(硕士)工程科技Ⅱ辑》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111178674A (en) * | 2019-12-04 | 2020-05-19 | 中国特种设备检测研究院 | Industrial big data driven hoisting machinery health management and control service system |
| CN111160759A (en) * | 2019-12-27 | 2020-05-15 | 上海建工集团股份有限公司 | Preprocessing method and system for construction safety monitoring big data of building engineering |
| CN111076886A (en) * | 2020-01-02 | 2020-04-28 | 南京中船绿洲机器有限公司 | Vibration testing method of high-performance electric deck crane |
| CN112398906A (en) * | 2020-10-14 | 2021-02-23 | 上海海典软件股份有限公司 | Internet platform data interaction method and device |
| CN113651245A (en) * | 2021-08-16 | 2021-11-16 | 合肥市春华起重机械有限公司 | Crane bearing capacity monitoring system |
| CN113651245B (en) * | 2021-08-16 | 2023-07-21 | 合肥市春华起重机械有限公司 | Crane bearing capacity monitoring system |
| CN116976014A (en) * | 2023-06-13 | 2023-10-31 | 江苏省特种设备安全监督检验研究院 | Crane design optimization method and system based on performance check |
| CN116976014B (en) * | 2023-06-13 | 2024-03-22 | 江苏省特种设备安全监督检验研究院 | Crane design optimization method and system based on performance check |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110210629A (en) | The crane safety assessment system excavated based on big data | |
| Christer | Developments in delay time analysis for modelling plant maintenance | |
| CN112152830B (en) | Intelligent fault root cause analysis method and system | |
| CN110955575A (en) | Business system fault positioning method based on correlation analysis model | |
| Zaher et al. | A multi-agent fault detection system for wind turbine defect recognition and diagnosis | |
| CN112596495A (en) | Industrial equipment fault diagnosis method and system based on knowledge graph | |
| CN110674842A (en) | Wind turbine generator main shaft bearing fault prediction method | |
| CN106779200A (en) | Based on the Wind turbines trend prediction method for carrying out similarity in the historical data | |
| CN101770219A (en) | Knowledge acquisition method of fault diagnosis knowledge base of turn-milling combined machine tool | |
| CN106446181A (en) | Big data processing and remote monitoring system | |
| CN109263271A (en) | A kind of printing equipment determination method based on big data | |
| CN110263229B (en) | Data lake-based data management method and device | |
| CN112417700B (en) | Fault diagnosis system of EH oil station based on state evaluation | |
| Kozielski et al. | DISESOR-decision support system for mining industry | |
| CN115145252B (en) | Fault tree-based fault diagnosis method, system and medium for water turbine speed regulator | |
| CN117194919A (en) | Production data analysis system | |
| CN110879151B (en) | Gas turbine remote monitoring and diagnosis system and method based on operation big data | |
| CN115544519A (en) | Method for carrying out security association analysis on threat information of metering automation system | |
| CN116361059A (en) | Diagnosis method and diagnosis system for abnormal root cause of banking business | |
| CN117235524A (en) | Learning training platform of automatic valuation model | |
| CN113420162B (en) | Equipment operation chain state monitoring method based on knowledge graph | |
| CN114565328A (en) | AGC frequency modulation performance assessment method and device | |
| KR102108975B1 (en) | Apparatus and method for condition based maintenance support of naval ship equipment | |
| CN117591679A (en) | Intelligent analysis system and method for carbon footprint of building block type product based on knowledge graph | |
| CN117520960A (en) | Bearing fault diagnosis method based on XGBoost and feature combination |
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 |