CN103018383B - Oil chromatogram on-line monitoring noise data correction method - Google Patents
Oil chromatogram on-line monitoring noise data correction method Download PDFInfo
- Publication number
- CN103018383B CN103018383B CN201210523683.XA CN201210523683A CN103018383B CN 103018383 B CN103018383 B CN 103018383B CN 201210523683 A CN201210523683 A CN 201210523683A CN 103018383 B CN103018383 B CN 103018383B
- Authority
- CN
- China
- Prior art keywords
- data
- line
- support vector
- online
- parameter
- 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.)
- Active
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 47
- 238000000034 method Methods 0.000 title claims abstract description 18
- 238000012937 correction Methods 0.000 title claims abstract description 15
- 238000012706 support-vector machine Methods 0.000 claims abstract description 26
- 241000254158 Lampyridae Species 0.000 claims abstract description 24
- 238000012360 testing method Methods 0.000 claims abstract description 23
- 238000004587 chromatography analysis Methods 0.000 claims description 42
- 230000002159 abnormal effect Effects 0.000 claims description 18
- GNBHRKFJIUUOQI-UHFFFAOYSA-N fluorescein Chemical compound O1C(=O)C2=CC=CC=C2C21C1=CC=C(O)C=C1OC1=CC(O)=CC=C21 GNBHRKFJIUUOQI-UHFFFAOYSA-N 0.000 claims description 17
- 241000131894 Lampyris noctiluca Species 0.000 claims description 13
- 241001269238 Data Species 0.000 claims description 3
- 230000008859 change Effects 0.000 claims description 3
- 239000003623 enhancer Substances 0.000 claims description 3
- 238000012549 training Methods 0.000 abstract description 6
- 230000000694 effects Effects 0.000 abstract description 4
- 230000008569 process Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 5
- 238000003745 diagnosis Methods 0.000 description 4
- 230000008901 benefit Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000011156 evaluation Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000008439 repair process Effects 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013524 data verification Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000001131 transforming effect Effects 0.000 description 1
- 238000009966 trimming Methods 0.000 description 1
Landscapes
- Feedback Control In General (AREA)
Abstract
The invention relates to a correction method for oil chromatogram on-line device noise data. The method comprises the steps of: 1) collecting oil chromatogram off-line test and on-line monitoring data; 2) acquiring an optimal combination of important parameters in a support vector machine regression model by a firefly algorithm; 3) training the support vector machine by the minority accurate oil chromatogram off-line test data obtained in step1) so as to the support vector machine regression model; 4) initializing the allowable deviation radius h of the on-line monitoring data, calculating a piecewise function between off-line tests, and judging whether the data of oil chromatogram on-line monitoring are in an error range allowed by the model; 5) correcting the on-line data; and 6) adjusting the parameters in the model according to a feedback result of on-site data correction. The method for oil chromatogram on-line data correction provided in the invention has the characteristics of stable and accurate effect, short time, and good timeliness, thus being very suitable for correction of on-site oil chromatogram on-line data.
Description
Technical field
The invention belongs to converting equipment on-line monitoring technique field, be applied in the noise data trimming process of transformer online monitoring equipment, specifically a kind of oil chromatography on-line monitoring noise data bearing calibration.
Background technology
Transformer oil chromatographic on-line monitoring can grasp the operation conditions of transformer in time, finds and follows the tracks of Hidden fault, for the reliability service of transformer provides safeguard.But be subject to the impact of the factors such as self error of environment temperature, humidity and monitoring equipment due to oil chromatography on-line monitoring, may there is distortion in online data, need to carry out data school before state evaluation and fault diagnosis.At present, Chinese scholars has been done a large amount of research work to data Correction Problems and has been proposed some algorithms.Principle component regression can remove noise data effectively, but the error of matching is large, and calibration accuracy is low; Neural network algorithm fitting effect is good, but when data volume is large, the training time is long, there is the problem of " crossing study ".
For the situation of current oil chromatography online data calibration result difference, the present invention proposes the method based on the Data correction of firefly support vector machine.First by glowworm swarm algorithm, the important parameter affecting support vector machine performance is optimized.Then calculate the piecewise function between oil chromatography off-line data, when online data exceeds the scope of piecewise function error permission, think that online data is abnormal.Utilize minority accurately oil chromatography off-line data to the training of Support vector regression model, when online data occurs abnormal, corrected by the online data of Support vector regression model to exception.The algorithm that the present invention proposes can be applied among oil chromatography on-Line Monitor Device, on-line calibration is carried out to the Condition Monitoring Data of transformer oil chromatographic, the data true and accurate more that oil chromatography on-Line Monitor Device is exported, effective rejecting bad point data, under the prerequisite ensureing data validity, improve the availability of data; Also can be applied in the master system of power transmission and transformation equipment state monitoring, the data of oil chromatography on-line monitoring be verified, reasonably tells effective data, propose bad point data, oil chromatography data are played to the effect of filtration.The data that this algorithm process of process is crossed can directly apply to fault diagnosis and the state evaluation of the power transmission and transforming equipments such as transformer, thus directly Instructing manufacture operation, repair based on condition of component and fault diagnosis work, great raising production cost and management level, the industry developments such as advanced state monitoring, repair based on condition of component and intelligent O&M, produce huge economic benefit and social benefit.
Summary of the invention
In order to solve the above-mentioned problems in the prior art, the invention provides a kind of oil chromatography on-line monitoring noise data bearing calibration being suitable for transformer.
The present invention has done brand-new design on the algorithm of Data correction, and concrete technical scheme is as follows:
The bearing calibration of a kind of oil chromatography on-line monitoring noise data, its method comprises the following steps:
Step 1), collection oil chromatography off-line testing and online monitoring data;
Step 2), obtained the optimum combination of important parameter in Support vector regression model by glowworm swarm algorithm;
Step 3), utilize step 1) to obtain minority accurately oil chromatography off-line testing data support vector machine is trained, obtain Support vector regression model;
The allowing of step 4), initialization online monitoring data departs from radius h, calculates the piecewise function between off-line testing, judges that the data of oil chromatography on-line monitoring are whether within the error range of model permission; If, then think that online data is normal; Otherwise, think that online data is abnormal;
Step 5), online data to be corrected: judge that whether online data is normal one by one, if data exception, then by the data in this moment of Support vector regression models fitting, replace abnormal data with match value; Otherwise, think that oil chromatography online monitoring data is normal, do not need to correct;
Step 6), result according to field data correction feedback, adjust the parameter in model.
In above scheme, described step 2) in concrete steps as follows:
Step 2.1), initialization fluorescein volatility coefficient ρ, fluorescein enhancer γ, sensing range r
s, neighborhood rate of change β, neighbours threshold value n
t, the position of moving step length s and every firefly;
Step 2.2), determine in support vector machine, to need the span of Optimal Parameters: determine wrong penalty factor, the span of insensitive parameter ε and nuclear parameter σ optimal value;
Step 2.3), often organizing within the scope of parameter value, random selecting one class value is as the position of firefly individuality; Using the error of support vector machine match value and actual value as fitness, error is less, then the performance of this group parameter is better, and fitness is larger;
Step 2.4), calculate the fluorescein concentration of the fluorescein concentration of each firefly, decision domain scope and neighbours, determine the moving direction of firefly by the fluorescein concentration of neighbours and move forward;
Step 2.5), judge whether glowworm swarm algorithm reaches end condition; If reach, then choose the parameter that optimum solution is support vector machine; Otherwise, go to step 2.4).
In above scheme, described step 2.1) in, owing to needing the important parameter optimized to be wrong penalty factor in support vector machine, insensitive parameter ε and nuclear parameter σ optimal value, in firefly, colony is expressed as X=((C
1, ε
1, σ
1), (C
2, ε
2, σ
2) ..., (C
n, ε
n, σ
n))
In above scheme, in described step 4), suppose moment t
iand t
j(t
i≠ t
j) off-line data be respectively y
iand y
j, then the piecewise function between these two moment off-line datas is
If between twice off-line testing, piecewise function allows the radius departed to be h, then moment t
iand t
jbetween twice off-line testing, the upper limit function of online monitoring data is
the lower limit function of online monitoring data is
if the upper limit that online data allows beyond off-line data piecewise function or lower limit, then think that online monitoring data is abnormal, need to correct.
In above scheme, in described step 6), the error sum of squares of models fitting off-line data is less, then model is more accurate.
In above scheme, in described step 6), the quadratic sum of two data difference that abnormal data corrected value is adjacent with on-line monitoring is less, then the data after correcting get over stable and continuous, and calibration result is better.
In above scheme, in described step 6), the training time of model is shorter, then model is more applicable carries out real time correction to online data.
Proved by engineer applied, the present invention carries out oil chromatography online data calibration result exactly, and the time, short real-time was good, is applicable to very much correcting the oil chromatography online data at scene.
Accompanying drawing explanation
Fig. 1 is the schematic diagram of embodiment of the present invention oil chromatography online data means for correcting;
Fig. 2 is the structural drawing that embodiment of the present invention oil chromatography online data corrects;
Fig. 3 is the process flow diagram of embodiment of the present invention glowworm swarm algorithm Support Vector Machines Optimized important parameter;
Fig. 4 is the process flow diagram of the online noise data of embodiment of the present invention Support vector regression model tuning.
Embodiment
Below in conjunction with the drawings and specific embodiments, the invention will be further described.
Fig. 3 is the process flow diagram of embodiment of the present invention glowworm swarm algorithm Support Vector Machines Optimized important parameter; Fig. 4 is the process flow diagram of the online noise data of embodiment of the present invention Support vector regression model tuning.As Fig. 3, Fig. 4, the bearing calibration of a kind of oil chromatography on-line monitoring noise data, its method comprises the following steps:
Step 1), collection oil chromatography off-line testing and online monitoring data;
Step 2), obtained the optimum combination of important parameter in Support vector regression model by glowworm swarm algorithm;
Step 3), utilize step 1) to obtain minority accurately oil chromatography off-line testing data support vector machine is trained, obtain Support vector regression model;
The allowing of step 4), initialization online monitoring data departs from radius h, calculates the piecewise function between off-line testing, judges that the data of oil chromatography on-line monitoring are whether within the error range of model permission; If, then think that online data is normal; Otherwise, think that online data is abnormal;
Step 5), online data to be corrected: judge that whether online data is normal one by one, if data exception, then by the data in this moment of Support vector regression models fitting, replace abnormal data with match value; Otherwise, think that oil chromatography online monitoring data is normal, do not need to correct;
Step 6), result according to field data correction feedback, adjust the parameter in model.
The one-piece construction of oil chromatography online data correcting algorithm as shown in Figure 2, this algorithm adopts off-line data verification, corrects the thinking of online monitoring data, build off-line oil chromatography Sample Storehouse by the data message under the various situations of collection oil chromatography off-line testing, optimized the parameter of on-line testing algorithm by offline database.The data that on-Line Monitor Device is collected by online data checking algorithm to data analysis, algorithm does not do special processing to normal data, the irrational noise data of algorithm to on-line equipment corrects, and then the result of correction is sent into the relevant data analysis of follow-up senior application and diagnosis.
As shown in Figure 1, be the module that online data corrects in frame, it obtains data by data acquisition module to the principle of oil chromatography online data means for correcting, and data results is turned back to display interface, thus guide field personnel carry out work.The important parameter of performance is affected comparatively accurately in off-line data Support Vector Machines Optimized, then to the model training after Optimal Parameters, when judging that online data is abnormal by piecewise function, by the data in this moment of Support vector regression models fitting, replace abnormal data with match value, if judge, online data is normal, does not correct.
Be described in detail the algorithm that oil chromatography online data corrects, algorithm is mainly divided into two parts.Part I obtains the optimum combination of important parameter in Support vector regression model by glowworm swarm algorithm, and as shown in Figure 3, the concrete steps of this some algorithm are as follows:
Step 1: the parameter of initialization glowworm swarm algorithm: initialization fluorescein volatility coefficient ρ, fluorescein enhancer γ, sensing range r
s, neighborhood rate of change β, neighbours threshold value n
t, the position of moving step length s and every firefly;
Step 2: determine the span needing Optimal Parameters in support vector machine; Determine wrong penalty factor, the span of insensitive parameter ε and nuclear parameter σ optimal value;
Step 3: often organizing within the scope of parameter value, random selecting one class value is as the position of firefly individuality.Using the error of support vector machine match value and actual value as fitness, error is less, then the performance of this group parameter is better, and fitness is larger;
Step 4: the fluorescein concentration calculating the fluorescein concentration of each firefly, decision domain scope and neighbours, determines the moving direction of firefly by the fluorescein concentration of neighbours and moves forward;
Step 5: judge whether glowworm swarm algorithm reaches end condition; If reach, then choose the parameter that optimum solution is support vector machine; Otherwise, go to step 4).
Owing to needing the important parameter optimized to be wrong penalty factor in support vector machine, insensitive parameter ε and nuclear parameter σ optimal value, so colony is expressed as follows in firefly:
X=((C
1,ε
1,σ
1),(C
2,ε
2,σ
2),...,(C
N,ε
N,σ
N))……(1)。
The fluorescein concentration of i-th firefly is as follows:
l
i(t)=(1-ρ)l
i(t-1)+γJ(x
i(t))……(2),
Decision domain scope more new formula is as follows:
The neighborhood of t i-th firefly is as follows:
Firefly is in motion process, and the fluorescein concentration according to firefly each in its neighborhood decides its moving direction, and t i-th firefly is as follows to the probability of the firefly movement of jth in its neighborhood:
I-th firefly is as follows in the position in t+1 moment:
Part II is corrected irrational noise data by the Support vector regression model trained, and as shown in Figure 4, the concrete steps of this some algorithm are as follows:
Step 1: collect oil chromatography off-line testing and online monitoring data;
Step 2: the parameter of Support Vector Machines Optimized regression model.The optimum combination of important parameter in regression model is obtained by glowworm swarm algorithm;
Step 3: utilize minority accurately oil chromatography off-line testing data support vector machine is trained, obtain Support vector regression model;
Step 4: the allowing of initialization online monitoring data departs from radius h, calculates the piecewise function between off-line testing, judges that the data of oil chromatography on-line monitoring are whether within the error range of model permission.If, then think that online data is normal; Otherwise, think that online data is abnormal;
Step 5: online data is corrected.Judge that whether online data is normal one by one, if data exception, then by the data in this moment of Support vector regression models fitting, replace abnormal data with match value; Otherwise, think that oil chromatography online monitoring data is normal, do not need to correct;
Step 6: according to the result of field data correction feedback, adjusts the parameter in model, makes the method in the present invention to the better effects if of the online noise compensation of oil chromatography.
The function that Support vector regression is estimated is as follows:
F (x)=ω φ (x)+b ... (7), support vector machine adopts and minimizes structure to determine ω and b, namely
Wherein
And L
ε(x, y-f (x))=max{0, | y-f (x)-ε | ... (10), solving formula (8), finally can to obtain the function of Support vector regression model as follows:
The radial basis RBF kernel function selecting usable range the most general in regression model is as follows:
Judge that whether online data is abnormal by the piecewise function of off-line data, suppose moment t
iand t
j(t
i≠ t
j) off-line data be respectively y
iand y
j, then the piecewise function between these two moment off-line datas is
Suppose that between twice off-line testing, piecewise function allows the radius departed to be h, then moment t
iand t
jbetween twice off-line testing, the upper limit function of online monitoring data is
the lower limit function of online monitoring data is
if the upper limit that online data allows beyond off-line data piecewise function or lower limit, then think that online monitoring data is abnormal, need to correct.
The error sum of squares of models fitting off-line data is less, then model is more accurate.The quadratic sum of two data difference that abnormal data corrected value is adjacent with on-line monitoring is less, then the data after correcting get over stable and continuous, and calibration result is better.The training time of model is shorter, then model is more applicable carries out real time correction to online data.Demonstrated by engineer applied, the present invention carries out oil chromatography online data calibration result exactly, and the time, short real-time was good, is applicable to very much correcting the oil chromatography online data at scene.
Claims (1)
1. an oil chromatography on-line monitoring noise data bearing calibration, is characterized in that: its method comprises the following steps:
Step 1), collection oil chromatography off-line testing and online monitoring data;
Step 2), obtained the optimum combination of important parameter in Support vector regression model by glowworm swarm algorithm;
Step 3), utilize step 1) to obtain minority accurately oil chromatography off-line testing data support vector machine is trained, obtain Support vector regression model;
The allowing of step 4), initialization online monitoring data departs from radius h, calculates the piecewise function between off-line testing, judges that the data of oil chromatography on-line monitoring are whether within the error range of model permission; If, then think that online data is normal; Otherwise, think that online data is abnormal; In described step 4), suppose moment ti and tj(ti ≠ tj) off-line data be respectively yi and yj, then the piecewise function between these two moment off-line datas is
If piecewise function allows the radius departed to be h between twice off-line testing, then between moment ti and tj twice off-line testing, the upper limit function of online monitoring data is
the lower limit function of online monitoring data is
if the upper limit that online data allows beyond off-line data piecewise function or lower limit, then think that online monitoring data is abnormal, need to correct;
Step 5), online data to be corrected: judge that whether online data is normal one by one, if data exception, then by the data in this moment of Support vector regression models fitting, replace abnormal data with match value; Otherwise, think that oil chromatography online monitoring data is normal, do not need to correct;
Step 6), result according to field data correction feedback, adjust the parameter in model.
Described step 2) in concrete steps as follows:
Step 2.1), initialization fluorescein volatility coefficient ρ, fluorescein enhancer γ, sensing range rs, neighborhood rate of change β, neighbours threshold value nt, the position of moving step length s and every firefly; Need the important parameter optimized to be wrong penalty factor in support vector machine, insensitive parameter ε and nuclear parameter σ optimal value, in firefly, colony is expressed as X=((C
1, ε
1, σ
1), (C
2, ε
2, σ
2) ..., (C
n, ε
n, σ
n));
Step 2.2), determine in support vector machine, to need the span of Optimal Parameters: determine wrong penalty factor, the span of insensitive parameter ε and nuclear parameter σ optimal value;
Step 2.3), often organizing within the scope of parameter value, random selecting one class value is as the position of firefly individuality; Using the error of support vector machine match value and actual value as fitness;
Step 2.4), calculate the fluorescein concentration of the fluorescein concentration of each firefly, decision domain scope and neighbours, determine the moving direction of firefly by the fluorescein concentration of neighbours and move forward;
Step 2.5), judge whether glowworm swarm algorithm reaches end condition; If reach, then choose the parameter that optimum solution is support vector machine; Otherwise, go to step 2.4).
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210523683.XA CN103018383B (en) | 2012-12-07 | 2012-12-07 | Oil chromatogram on-line monitoring noise data correction method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201210523683.XA CN103018383B (en) | 2012-12-07 | 2012-12-07 | Oil chromatogram on-line monitoring noise data correction method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN103018383A CN103018383A (en) | 2013-04-03 |
CN103018383B true CN103018383B (en) | 2015-07-15 |
Family
ID=47967222
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201210523683.XA Active CN103018383B (en) | 2012-12-07 | 2012-12-07 | Oil chromatogram on-line monitoring noise data correction method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN103018383B (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105590011B (en) * | 2014-10-20 | 2019-04-30 | 深圳市迈迪加科技发展有限公司 | A kind of ecg signal data modification method and system based on pulse regression model |
CN105203876B (en) * | 2015-09-15 | 2018-04-24 | 云南电网有限责任公司电力科学研究院 | It is a kind of to utilize support vector machines and the transformer online monitoring state evaluating method of correlation analysis |
CN108022231A (en) * | 2016-10-31 | 2018-05-11 | 兰州交通大学 | A kind of inside workpiece defect identification method based on firefly neutral net |
CN114491383B (en) * | 2022-04-15 | 2022-09-16 | 江西飞尚科技有限公司 | Abnormal data processing method and system for bridge monitoring |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101271063A (en) * | 2008-05-07 | 2008-09-24 | 陕西恒智科技发展有限公司 | Process of vector machine emendation model method supported by gas infrared spectrum analysis |
CN101493440A (en) * | 2008-08-06 | 2009-07-29 | 通标标准技术服务(天津)有限公司 | Method for measuring migration volume of phthalic ester and di(2-ethylhexyl) adipate in fatty foodstuff contact material |
CN101701940B (en) * | 2009-10-26 | 2012-05-30 | 南京航空航天大学 | On-line transformer fault diagnosis method based on SVM and DGA |
CN102735761A (en) * | 2012-06-26 | 2012-10-17 | 河海大学 | Method for predicting transformer oil chromatographic data based on relevance vector machine |
CN103149278A (en) * | 2012-12-07 | 2013-06-12 | 四川电力科学研究院 | Correction method for on-line monitoring noisy data of oil chromatography |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2492690A1 (en) * | 2011-02-22 | 2012-08-29 | BIOCRATES Life Sciences AG | Method and use of metabolites for the diagnosis of inflammatory brain injury in preterm born infants |
-
2012
- 2012-12-07 CN CN201210523683.XA patent/CN103018383B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101271063A (en) * | 2008-05-07 | 2008-09-24 | 陕西恒智科技发展有限公司 | Process of vector machine emendation model method supported by gas infrared spectrum analysis |
CN101493440A (en) * | 2008-08-06 | 2009-07-29 | 通标标准技术服务(天津)有限公司 | Method for measuring migration volume of phthalic ester and di(2-ethylhexyl) adipate in fatty foodstuff contact material |
CN101701940B (en) * | 2009-10-26 | 2012-05-30 | 南京航空航天大学 | On-line transformer fault diagnosis method based on SVM and DGA |
CN102735761A (en) * | 2012-06-26 | 2012-10-17 | 河海大学 | Method for predicting transformer oil chromatographic data based on relevance vector machine |
CN103149278A (en) * | 2012-12-07 | 2013-06-12 | 四川电力科学研究院 | Correction method for on-line monitoring noisy data of oil chromatography |
Non-Patent Citations (1)
Title |
---|
The improvement of glowworm swarm optimization for continuous optimization problems;Bin Wu et al;《Expert Systems with Applications》;20120630;第39卷(第7期);6335-6342 * |
Also Published As
Publication number | Publication date |
---|---|
CN103018383A (en) | 2013-04-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN102622473B (en) | Optimization design method for step stress accelerated degradation test based on Bayesian theory | |
CN103473480B (en) | Based on the online monitoring data bearing calibration improving universal gravitation support vector machine | |
CN102663412B (en) | Power equipment current-carrying fault trend prediction method based on least squares support vector machine | |
CN103793853B (en) | Condition of Overhead Transmission Lines Based appraisal procedure based on two-way Bayesian network | |
CN103018383B (en) | Oil chromatogram on-line monitoring noise data correction method | |
CN104239694A (en) | Fault prediction and condition-based repair method of urban rail train bogie | |
CN105956216A (en) | Finite element model correction method for large-span steel bridge based on uniform temperature response monitoring value | |
CN103971171A (en) | State evaluation method for power transmission equipment | |
CN104390657A (en) | Generator set operating parameter measuring sensor fault diagnosis method and system | |
CN110838075A (en) | Training and predicting method and device for prediction model of transient stability of power grid system | |
CN110045317B (en) | Mutual inductor metering error online detection method and system | |
CN110865924B (en) | Health degree diagnosis method and health diagnosis framework for internal server of power information system | |
CN105320987A (en) | Satellite telemetry data intelligent interpretation method based on BP neural network | |
CN105930571A (en) | Unit temperature response monitoring value based correction method for finite element model of large-span steel bridge | |
CN103258103A (en) | Thevenin equivalent parameter identification method based on partial least squares regression | |
CN106503861B (en) | Wind power prediction method based on probability statistics and particle swarm optimization and integrating wind speeds of multiple meteorological sources | |
CN104035431A (en) | Obtaining method and system for kernel function parameters applied to nonlinear process monitoring | |
CN102147982A (en) | Method for predicating dynamic volume of sector area | |
CN103149278A (en) | Correction method for on-line monitoring noisy data of oil chromatography | |
CN103324858A (en) | Three-phase load flow state estimation method of power distribution network | |
CN104008433A (en) | Method for predicting medium-and-long-term power loads on basis of Bayes dynamic model | |
CN104713730B (en) | Method for determining degeneration rate of aircraft engine according to vibration signal | |
CN102087311B (en) | Method for improving measurement accuracy of power mutual inductor | |
CN104156453A (en) | Real-time on-line ultra-short-term busbar load prediction, assessment and analysis method | |
CN105741184A (en) | Transformer state evaluation method and apparatus |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |