CN109144986A - A kind of importance appraisal procedure of industrial equipment data - Google Patents
A kind of importance appraisal procedure of industrial equipment data Download PDFInfo
- Publication number
- CN109144986A CN109144986A CN201810853576.0A CN201810853576A CN109144986A CN 109144986 A CN109144986 A CN 109144986A CN 201810853576 A CN201810853576 A CN 201810853576A CN 109144986 A CN109144986 A CN 109144986A
- Authority
- CN
- China
- Prior art keywords
- data
- data set
- industrial equipment
- importance
- sample
- 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
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000013441 quality evaluation Methods 0.000 claims abstract description 12
- 238000011157 data evaluation Methods 0.000 claims abstract description 5
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000007405 data analysis Methods 0.000 claims description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 5
- 238000001303 quality assessment method Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000005611 electricity Effects 0.000 claims description 2
- 238000012804 iterative process Methods 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 2
- 238000007418 data mining Methods 0.000 description 3
- 238000003062 neural network model Methods 0.000 description 3
- 241000209094 Oryza Species 0.000 description 2
- 235000007164 Oryza sativa Nutrition 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 235000009566 rice Nutrition 0.000 description 2
- 230000032683 aging Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004422 calculation algorithm Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- G06Q50/06—Energy or water supply
Landscapes
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
Technical solution of the present invention discloses a kind of importance appraisal procedure of industrial equipment data, its step are as follows: S1: collecting industrial equipment sample data set, record the basic condition of sample data set, and give a mark to the importance of the quality evaluation index of the data set, form sample marking data grade form；S2: the virtual scoring model based on sample data is established；S3: it is given a mark according to virtual scoring model to data set to be assessed；S4: based on marking result and combined data Evaluation Model on Quality, the data quality accessment score of data set to be assessed is obtained.Technical solution of the present invention realizes the real-time assessment of industrial equipment data importance, avoids the need for the case where inviting entity expert, reduces human cost, assessment result is accurate and reliable.
Description
Technical field
The present invention relates to industrial equipment technical field of data processing more particularly to a kind of importance of industrial equipment data to comment
Estimate method.
Background technique
In modern society, data are that industrial enterprise moves towards information-based necessary basis, however as the continuous of business equipment
Aging, sensor failure, transmission network unstability, data quality problem becomes to become increasingly conspicuous.Right
When quality of data situation is assessed, a variety of data quality accessment indexs can be related to, for example, integrality, accuracy, consistency,
Reliability etc., every kind of index all have a certain impact to data quality condition, influence to vary, it is desirable to obtain quality of data feelings
The accurate evaluation of condition is as a result, firstly the need of shadow of the importance to final data quality assessment result for accurately measuring different indexs
Situation is rung, and this influence situation is indicated in the form of quantification.
At present to the evaluation of index importance, relies primarily on and invite industry experience expert abundant, the Heuristics of expert
It gives a mark to the importance of different indexs, the importance quantized result of each index is obtained with this.It is based on by entity expert special
Although the mode that family's experience is given a mark is a kind of effective marking mode, but during data quality accessment, only by real
Body expert is based on experience and carries out index importance marking with greater risk.The major defect of this mode has: human cost is thrown
Enter that huge, experience dependence is strong, processing lag.
Summary of the invention
The technical problem to be solved is that provide a kind of importance assessment side of industrial equipment data for technical solution of the present invention
Method, this method in real time can assess the importance of data to be assessed in the case where not inviting entity expert.
In order to solve the above technical problems, technical solution of the present invention provides a kind of importance assessment side of industrial equipment data
Method includes the following steps:
S1: collecting industrial equipment sample data set, give a mark to the importance of the quality evaluation index of the data set, shape
At sample marking data grade form；
S2: the virtual scoring model based on sample data is established；
S3: it is given a mark according to virtual scoring model to data set to be assessed；
S4: based on marking result and combined data Evaluation Model on Quality, the data quality accessment of data set to be assessed is obtained
Score.
Optionally, step S1 specifically: collect the different sample data set of several groups, record sample data set type,
Size, data variable number, data analyze purpose, and the quality evaluation for choosing several experts for several groups sample data set refers to
Target importance is given a mark respectively, forms sample marking data grade form.
It is further alternative, the quality evaluation index include in accuracy, integrality, reliability and redundancy at least
It is a kind of.
It is further alternative, step S2 specifically: establish several between sample data set and respective sample marking data
Nonlinear Mapping model, as several virtual scoring models based on sample data.
It is further alternative, it is built using at least one of neural network, support vector machine, random forest model
Mould.
Optionally, step S3 specifically: by several virtual scoring models based on sample data to data set to be assessed
It gives a mark, obtains several marking results.
Optionally, in step s 4, the Data quality assessment model is as follows:
Wherein, wherein the data quality accessment score of S expression data set；N indicates the number of virtual scoring model；RijTable
Show marking of i-th of expert to j-th of evaluation index；wiFor the weight coefficient of i-th of expert；SiFor i-th of virtual scoring model
The obtained data quality accessment score of marking result；B2And B1For setup parameter.
Optionally, further include step S5: repeating step S3 and step S4 several times, obtain several groups data quality accessment and obtain
Point, and adjustment is iterated to the weight of each score.
It is further alternative, iterative process specifically: calculate SiWith SjBetween related coefficient, if related coefficient reaches pre-
If value, the marking result of i-th of virtual scoring model will be carried out to increase power Δ ω, the calculation formula of related coefficient is as follows:
Wherein, SjFor true score；Var(Si) it is SiVariance；Var(Sj) it is SjVariance；Cov(Si, Sj) it is SiWith Sj
Covariance.
It is further alternative, Δ ω ∈ [1 ‰, 1%].
Optionally, above-mentioned data set to be assessed is the acquisition of wind-power electricity generation field data and the data in supervisor control data
Variable.
Further alternative, the variable includes blower number, blower active power, reactive power, voltage, electric current, power
At least one of factor, instantaneous wind speed, wind speed round, temperature, generated energy, generator speed, propeller pitch angle.
Compared with prior art, the present invention realizes the real-time assessment of industrial equipment data importance, by virtually giving a mark
The foundation of model avoids the need for the case where inviting entity expert, reduces human cost；It is commented based on expert's sample marking data
The virtual scoring model for dividing table training effectively can calculate expert estimation in real time as a result, and there is self iteration adjustment to beat
The function of fraction weight keeps marking result more accurate and reliable；Whole day is awaited orders, annual nothing is stopped, completes marking task in real time.
Detailed description of the invention
Fig. 1 is the flow diagram of the importance appraisal procedure of the industrial equipment data of the embodiment of the present invention 1.
Specific embodiment
Embodiment 1
As shown in Figure 1, the importance appraisal procedure of the industrial equipment data of the embodiment of the present invention, its step are as follows:
S1: collecting industrial equipment sample data set, give a mark to the importance of the quality evaluation index of the data set, shape
At sample marking data grade form；
S2: the virtual scoring model based on sample data is established；
S3: it is given a mark according to virtual scoring model to data set to be assessed；
S4: based on marking result and combined data Evaluation Model on Quality, the data quality accessment of data set to be assessed is obtained
Score；
S5: repeating step S3 and step S4 several times, several groups data quality accessment score is obtained, to the power of each score
It is iterated adjustment again.
In the present embodiment, step S1 is specifically operated as follows: being carried out the preliminary screening of sample data first, is collected
The different sample data set of several groups records type, size, data variable number, the data analysis purpose of sample data set, choosing
Veteran expert in 100 the field of data mining is taken, to the weight of the data quality accessment index of the sample data set of collection
The property wanted is given a mark respectively, forms sample marking data grade form.The number suggestion of expert is greater than ten, to guarantee following model
Accuracy with no restriction to number at this be determined according to the actual situation.Wherein quality evaluation index includes but is not limited to
Regression, classification, poly- is also optionally added in accuracy rate, percentage of head rice, reliability and not redundancy rate in other embodiments
The indexs such as class.
Step S2 specifically: input sample data set gives a mark data grade form to sample based on the sample that step S1 is formed
Data set given a mark and export sample data set marking as a result, its it is practical include 100 groups of marking as a result, passing through nerve again
Network model establishes 100 Nonlinear Mapping models between input data and output data, i.e.,
The process of the neural network model of the present embodiment is as follows: it is initial to carry out parameter to neural network model first
Change, the weight and bias of initialization model, then by sample data set input model, calculates preliminary output as a result, will
This output result is compared with 100 groups of marking results respectively respectively, root-mean-square error between the two is calculated, based on this error
Size carries out tuning to model initial parameter, and error is finally made to reach setting value, carries out later to the model parameter regulated
It is fixed, material is thus formed the 100 virtual scoring model based on sample data.
Certainly in other embodiments, neural network model can not had to, pass through the moulds such as support vector machines, random forest
Type establishes 100 Nonlinear Mapping models between sample data set and respective sample marking data.
It is collected into new data quality accessment task, carries out step S3, by above-mentioned established based on sample data
Virtual scoring model carries out hind computation, and each virtual scoring model can give a mark to data, so calculating terminates simultaneously
Obtain 100 marking results.
After system obtains the marking result of virtual scoring model, progress step S4, combined data Evaluation Model on Quality, finally
The data quality accessment score of the data set is obtained, Data quality assessment model is as follows:
Wherein, wherein the data quality accessment score of S expression data set；N indicates the number of virtual scoring model；RijTable
Show marking of i-th of expert to j-th of evaluation index；wiFor the weight coefficient of i-th of expert；SiFor i-th of virtual scoring model
The obtained data quality accessment score of marking result；B2And B1For setup parameter.
In the present embodiment, data quality accessment index includes accuracy, integrality, reliability and redundancy, is set first
The matrix that fixed data set to be assessed is m × n, wherein m is number of data, and n is variable number, and the total number of data is r.
Accuracy rate R1It is as follows comprising abnormal rate and irregularity rate, calculation formula corresponding to accuracy index:
Wherein, a1Indicate data exception rate, a2Indicate defect of data rate, hoIndicate the abnormal data number in data set,
hcIndicate that the irregularity data amount check in data set, r indicate the data total number in data set, p indicates used index
Number.
Percentage of head rice R2Corresponding to integrity metrics, include missing values rate, missing variable rate and missing time stamp rate, meter
Calculation method is as follows:
Wherein, b1Indicate missing values rate, b2Indicate missing variable rate, b3Indicate missing time stamp rate, hmIt indicates in data set
Missing data number, hvIndicate the missing variable number in data set, htIndicate that the missing time in data set stabs number.
Reliability R3, correspond to reliability index, exceed codomain rate comprising data, calculation method is as follows:
R3=1-c1；
Wherein, c1Indicate that data are more than codomain rate, hrIndicate that data intensive data exceeds the number of codomain.
Not redundancy rate R4, correspond to redundancy index, include Data duplication rate, variable correlation ratio and variable inefficiency,
Calculation method is as follows:
Wherein, ccuvIndicate the correlation in data set between variable u and variable v, uiIndicate the value of the i-th row in variable u,
Indicate the average value of variable u, σuIndicate the standard deviation of variable u, viIndicate the value of the i-th row in variable v,Indicate being averaged for variable v
Value, σvIndicate the standard deviation of variable v, d1Indicate Data duplication rate, d2Indicate variable correlation ratio, d3Indicate variable inefficiency, hqTable
Repeated data item number of the registration according to concentration, hsIndicate the Invalided variable number in data set.
More accurate quality of data appraisal result in order to obtain needs to carry out step S5: being iterated tune to marking result
It is whole.Specifically, step S3 and step S4 is repeated, system carries out several times operations, and 100 virtual scoring models can obtain largely
Marking as a result, calculate SiWith SjBetween related coefficient will be to i-th of virtual scoring model if related coefficient reaches preset value
Marking result SiIt carries out increasing power Δ ω, Δ ω ∈ [1 ‰, 1%], the calculation formula of related coefficient is as follows:
Wherein, SjFor true score；Var(Si) it is SiVariance；Var(Sj) it is SjVariance；Cov(Si, Sj) it is SiWith Sj
Covariance.
The every operation a period of time (time is set according to specific requirements) of system, the marking of 100 virtual scoring models
Weight will do it primary dynamic and adjust, and make every effort to obtain more accurate quality of data appraisal result.
Embodiment 2
The present embodiment assesses the importance of the quality evaluation index of fan operation data, and specific implementation process is such as
Under:
(1) data variable (blower number, blower active power, the idle function in 100 groups of wind field SCADA control systems are collected
Rate, voltage, electric current, power factor, instantaneous wind speed, wind speed round, temperature, generated energy, generator speed, propeller pitch angle) it is used as 100
Group sample data set, and type, size, data variable number, the data analysis purpose of sample data set are recorded, invite 10 numbers
It according to expert veteran in excavation applications, gives a mark to the importance of quality evaluation index, forms expert's sample and grade
According to grade form.
(2) based on expert's sample marking data grade form, input data and output data are established by neural network algorithm
Between 10 Nonlinear Mapping models, so as to form 10 virtual scoring models based on sample data.
(3) data set of fan operation is inputted into virtual scoring model, by 10 virtual scoring model needles are calculated
To the fan operation data to the importance marking result of each data quality accessment index.
(4) based on the marking as a result, calculating the quality evaluation score of the data, data matter using Data quality assessment model
It measures assessment models and embodiment 1 is consistent.
(5) data quality accessment scores are fed back into user, user is subsequent to carry out data mining and divide to the data
Analysis, obtains the true scores of data mining and analysis, this error information is fed back to virtual scoring model.
(6) this scores is taken in virtual marking, calculates between true score and the marking result of virtual scoring model
The related coefficient of related coefficient, the true score and two of them expert have been more than preset value, therefore have obtained corresponding two specially
The two increasing weights are recorded, are calculated to call in next subtask by the increasing weight of family.
Specific embodiments of the present invention are described in detail above, it should be understood that those skilled in the art are without wound
The property made labour, which according to the present invention can conceive, makes many modifications and variations.Therefore, all technician in the art
Pass through the available technology of logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Scheme, all should be within the scope of protection determined by the claims.
Claims (10)
1. a kind of importance appraisal procedure of industrial equipment data, which comprises the steps of:
S1: industrial equipment sample data set is collected, the basic condition of sample data set, and the quality evaluation to the data set are recorded
The importance of index is given a mark, and sample marking data grade form is formed；
S2: the virtual scoring model based on sample data is established；
S3: it is given a mark according to virtual scoring model to data set to be assessed；
S4: based on marking result and combined data Evaluation Model on Quality, the data quality accessment score of data set to be assessed is obtained.
2. the importance appraisal procedure of industrial equipment data as described in claim 1, which is characterized in that step S1 specifically:
The different sample data set of several groups is collected, the type, size, data variable number, data analysis mesh of sample data set are recorded
, the importance for choosing several experts for the quality evaluation index of several groups sample data set is given a mark.
3. the importance appraisal procedure of industrial equipment data as claimed in claim 2, which is characterized in that the quality evaluation refers to
Mark includes at least one of accuracy, integrality, reliability and redundancy.
4. the importance appraisal procedure of industrial equipment data as claimed in claim 2, which is characterized in that step S2 specifically:
Several Nonlinear Mapping models between sample data set and respective sample marking data are established, it is as several to be based on sample data
Virtual scoring model.
5. the importance appraisal procedure of industrial equipment data as claimed in claim 4, which is characterized in that using neural network,
At least one of support vector machines, random forest model is modeled.
6. the importance appraisal procedure of industrial equipment data as claimed in claim 4, which is characterized in that step S3 specifically:
It is given a mark by several virtual scoring models based on sample data to data set to be assessed, obtains several marking results.
7. the importance appraisal procedure of industrial equipment data as claimed in claim 6, which is characterized in that in step s 4, institute
It is as follows to state Data quality assessment model:
Wherein, S indicates the data quality accessment score of data set；N indicates the number of virtual scoring model；RijI-th of expression special
Marking of the family to j-th of evaluation index；wiFor the weight coefficient of i-th of expert；SiFor the marking knot of i-th of virtual scoring model
The data quality accessment score that fruit obtains；B2And B1For setup parameter.
8. the importance appraisal procedure of industrial equipment data as claimed in claim 7, which is characterized in that further include step S5:
It repeats step S3 and step S4 several times, obtains several groups data quality accessment score, the weight of each score is iterated
Adjustment.
9. the importance appraisal procedure of industrial equipment data as claimed in claim 8, which is characterized in that iterative process is specific
Are as follows: calculate SiWith SjBetween related coefficient, if related coefficient reaches preset value, by the marking knot to i-th of virtual scoring model
Fruit carries out increasing power Δ ω, and the calculation formula of related coefficient is as follows:
Wherein, SjFor true score；Var(Si) it is SiVariance；Var(Sj) it is SjVariance；Cov(Si, Sj) it is SiWith SjAssociation
Variance.
10. the importance appraisal procedure of industrial equipment data as described in any one of claim 1 to 9, which is characterized in that it is described to
Assessing data set is the acquisition of wind-power electricity generation field data and the data variable in supervisor control data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810853576.0A CN109144986A (en) | 2018-07-30 | 2018-07-30 | A kind of importance appraisal procedure of industrial equipment data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810853576.0A CN109144986A (en) | 2018-07-30 | 2018-07-30 | A kind of importance appraisal procedure of industrial equipment data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109144986A true CN109144986A (en) | 2019-01-04 |
Family
ID=64798862
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810853576.0A Pending CN109144986A (en) | 2018-07-30 | 2018-07-30 | A kind of importance appraisal procedure of industrial equipment data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109144986A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288789A (en) * | 2019-06-27 | 2019-09-27 | 吉林建筑大学 | A kind of building electric fire fighting alarm device and its control method |
| CN113569374A (en) * | 2020-04-29 | 2021-10-29 | 上海宝信软件股份有限公司 | Method and system for evaluating manufacturability of steel product |
| CN113902963A (en) * | 2021-12-10 | 2022-01-07 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN114282745A (en) * | 2021-11-04 | 2022-04-05 | 山东大学 | Risk early warning method for wading product production enterprise and related equipment |
| CN114595781A (en) * | 2022-03-17 | 2022-06-07 | 南京星环智能科技有限公司 | Octane value loss prediction method, device, equipment and storage medium |
| CN117667640A (en) * | 2024-02-02 | 2024-03-08 | 华测检测认证集团股份有限公司 | System data value evaluation method, device, equipment and storage medium |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102708149A (en) * | 2012-04-01 | 2012-10-03 | 河海大学 | Data quality management method and system |
| US20130259378A1 (en) * | 2009-02-05 | 2013-10-03 | Google Inc. | Methods and systems for assessing the quality of automatically generated text |
| CN106384197A (en) * | 2016-09-13 | 2017-02-08 | 北京协力筑成金融信息服务股份有限公司 | Service quality evaluation method and device based on big data |
| CN106558308A (en) * | 2016-12-02 | 2017-04-05 | 深圳撒哈拉数据科技有限公司 | A kind of internet audio quality of data auto-scoring system and method |
| US20170132217A1 (en) * | 2015-11-06 | 2017-05-11 | Samsung Electronics Co., Ltd. | Apparatus and method for evaluating quality of automatic translation and for constructing distributed representation model |
| US20180113898A1 (en) * | 2016-10-25 | 2018-04-26 | Mastercard International Incorporated | Systems and methods for assessing data quality |
| CN108197280A (en) * | 2018-01-10 | 2018-06-22 | 上海电气集团股份有限公司 | Mining ability evaluation method based on industrial equipment data |
| CN108257132A (en) * | 2018-03-05 | 2018-07-06 | 南方医科大学 | A kind of method of the CT image quality measures based on machine learning |
-
2018
- 2018-07-30 CN CN201810853576.0A patent/CN109144986A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130259378A1 (en) * | 2009-02-05 | 2013-10-03 | Google Inc. | Methods and systems for assessing the quality of automatically generated text |
| CN102708149A (en) * | 2012-04-01 | 2012-10-03 | 河海大学 | Data quality management method and system |
| US20170132217A1 (en) * | 2015-11-06 | 2017-05-11 | Samsung Electronics Co., Ltd. | Apparatus and method for evaluating quality of automatic translation and for constructing distributed representation model |
| CN106384197A (en) * | 2016-09-13 | 2017-02-08 | 北京协力筑成金融信息服务股份有限公司 | Service quality evaluation method and device based on big data |
| US20180113898A1 (en) * | 2016-10-25 | 2018-04-26 | Mastercard International Incorporated | Systems and methods for assessing data quality |
| CN106558308A (en) * | 2016-12-02 | 2017-04-05 | 深圳撒哈拉数据科技有限公司 | A kind of internet audio quality of data auto-scoring system and method |
| CN108197280A (en) * | 2018-01-10 | 2018-06-22 | 上海电气集团股份有限公司 | Mining ability evaluation method based on industrial equipment data |
| CN108257132A (en) * | 2018-03-05 | 2018-07-06 | 南方医科大学 | A kind of method of the CT image quality measures based on machine learning |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110288789A (en) * | 2019-06-27 | 2019-09-27 | 吉林建筑大学 | A kind of building electric fire fighting alarm device and its control method |
| CN113569374A (en) * | 2020-04-29 | 2021-10-29 | 上海宝信软件股份有限公司 | Method and system for evaluating manufacturability of steel product |
| CN114282745A (en) * | 2021-11-04 | 2022-04-05 | 山东大学 | Risk early warning method for wading product production enterprise and related equipment |
| CN113902963A (en) * | 2021-12-10 | 2022-01-07 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN113902963B (en) * | 2021-12-10 | 2022-06-17 | 交通运输部公路科学研究所 | Method and device for evaluating fire detection capability of tunnel |
| CN114595781A (en) * | 2022-03-17 | 2022-06-07 | 南京星环智能科技有限公司 | Octane value loss prediction method, device, equipment and storage medium |
| CN117667640A (en) * | 2024-02-02 | 2024-03-08 | 华测检测认证集团股份有限公司 | System data value evaluation method, device, equipment and storage medium |
| CN117667640B (en) * | 2024-02-02 | 2024-05-31 | 华测检测认证集团股份有限公司 | System data value evaluation method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109144986A (en) | A kind of importance appraisal procedure of industrial equipment data | |
| CN108375476B (en) | Hydroelectric generating set health assessment method | |
| CN105973594B (en) | A kind of rolling bearing fault Forecasting Methodology based on continuous depth confidence network | |
| CN108897954A (en) | Wind turbines temperature pre-warning method and its system based on BootStrap confidence calculations | |
| CN108108877A (en) | A kind of transmission line of electricity damage to crops caused by thunder methods of risk assessment based on BP neural network | |
| CN105527112B (en) | A kind of rotating machinery health status comprehensive estimation method influenceed based on use with maintenance | |
| DE112016005511T5 (en) | Method for evaluating performance characteristics of wind turbines, apparatus and storage medium | |
| CN105117602A (en) | Metering apparatus operation state early warning method | |
| CN103106535B (en) | Method for solving collaborative filtering recommendation data sparsity based on neural network | |
| CN111178616B (en) | Wind speed prediction method based on negative correlation learning and regularization extreme learning machine integration | |
| CN104700321A (en) | Analytical method of state running tendency of transmission and distribution equipment | |
| CN102074955A (en) | Method based on knowledge discovery technology for stability assessment and control of electric system | |
| CN105956779A (en) | Power transformer running state evaluation method and power transformer running state evaluation device | |
| CN111523778A (en) | Power grid operation safety assessment method based on particle swarm algorithm and gradient lifting tree | |
| CN105303331A (en) | Transformer repair risk decision-making method | |
| CN105893757A (en) | Voltage sag severity comprehensive evaluation method | |
| CN106875037A (en) | Wind-force Forecasting Methodology and device | |
| CN104182816A (en) | Method for evaluating power quality comprehensively based on the Vague sets and the improved technique for order preference by similarity to ideal solution and application thereof | |
| CN108667069A (en) | A kind of short-term wind power forecast method returned based on Partial Least Squares | |
| CN110378549A (en) | A kind of transmission tower bird pest grade appraisal procedure based on FAHP- entropy assessment | |
| CN105956798A (en) | Sparse random forest-based method for assessing running state of distribution network device | |
| CN105095989A (en) | Fourier-series-based fitting method of wind power probability distribution at same time | |
| CN108196444A (en) | Based on the control of the variable pitch wind energy conversion system of feedback linearization sliding formwork and SCG and discrimination method | |
| CN112990627B (en) | Power quality evaluation method | |
| CN107368940A (en) | Count and respond uncertain temperature control Load aggregation response potential evaluation method and system |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |
|
| RJ01 | Rejection of invention patent application after publication |