CN107016235A - The equipment running status health degree appraisal procedure adaptively merged based on multiple features - Google Patents
The equipment running status health degree appraisal procedure adaptively merged based on multiple features Download PDFInfo
- Publication number
- CN107016235A CN107016235A CN201710171131.XA CN201710171131A CN107016235A CN 107016235 A CN107016235 A CN 107016235A CN 201710171131 A CN201710171131 A CN 201710171131A CN 107016235 A CN107016235 A CN 107016235A
- Authority
- CN
- China
- Prior art keywords
- index
- equipment
- health degree
- running status
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16Z—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS, NOT OTHERWISE PROVIDED FOR
- G16Z99/00—Subject matter not provided for in other main groups of this subclass
Abstract
The invention discloses a kind of equipment running status health degree appraisal procedure adaptively merged based on multiple features, including:1) according to the time domain charactreristic parameter and frequency domain character parameter of the vibration signal computing device rotor part of each measuring surface of equipment rotor part;While the technique measure feature parameter of collecting device current working;2) equipment state health degree evaluation model is obtained, the equipment state health degree evaluation model can reflect the recursive hierarchy structure of health degree membership, recycle the recursive hierarchy structure of health degree membership to determine object set and index set;3) agriculture products concentrate the corresponding membership function of each index;4) the healthy angle value of each index is calculated according to the corresponding membership function of each index in index set;5) final equipment running status health degree is obtained by data fusion according to the weight after the healthy angle value of each index and its corresponding adjustment, this method can accurately realize the self-adaptive estimation of equipment running status health degree.
Description
Technical field
The invention belongs to mechanical fault diagnosis field, it is related to a kind of equipment operation adaptively merged based on multiple features
State health degree appraisal procedure.
Background technology
Power-equipment using rotating machinery as representative is the core tool and main resource of enterprise implement production, from manufacture
Industry, power industry are to military aerospace, and each industry has the key equipment of its core, and aircraft carrier, large-scale power transformer flies
Machine engine, the operation health status of such equipment such as generator is particularly important, once there is equipment fault, consequence is often
It is hardly imaginable.Thus, find, catch, track, monitor and assessment equipment state in time, it is ensured that equipment is in normal, stable work
Condition is the problem of current every profession and trade is paid close attention to and paid attention to the most.
The research of state estimation has historical origin for a long time, is mostly used for the forecast assessment of Changes in weather and medically
Assessment to natural person's physical condition, the two is largely dependent upon the judgement of experience, not deep to the problem
Enter research method and theoretical model that research forms science, other research fields are difficult therefrom to use for reference its research method.20th century
The continuous ripe strong of end, the correlative study such as artificial intelligence, data fusion, fuzzy theory, neutral net and theoretical method is pushed away
Moved continuing to develop for health state evaluation and Predicting Technique, the field of research also from the industries such as space flight and aviation, weaponry to
Other industries are constantly expanded, and health state evaluation technology is applied to engine, bridge, plant equipment etc. by many experts and scholar
Field.
The vibration data of unit is the reflection directly perceived of unit operation situation, and tradition machinery state evaluating method is to be directed to unit
Single measuring point or section measuring point are monitored and assessed, and the parameter index that can be analyzed is more single, generally require stronger special
Industry technical ability could be assessed accurately, and the simplicity used is not good, and adaptive degree is not high.On the other hand, Traditional measurements side
Method is simply to be compared detected value with threshold value in the case of given tolerance threshold, and the setting of tolerance threshold exist it is larger
Subjectivity, state evaluating method reliability is relatively low, does not possess the reply diversified ability of failure now.
The content of the invention
It is an object of the invention to overcome the shortcoming of above-mentioned prior art adaptively to be merged based on multiple features there is provided one kind
Equipment running status health degree appraisal procedure, this method can accurately realize that the adaptive of equipment running status health degree is commented
Estimate, reliability is high.
It is of the present invention to be commented based on the equipment running status health degree that multiple features are adaptively merged to reach above-mentioned purpose
The method of estimating comprises the following steps:
1) vibration signal of each measuring surface of synchronous acquisition equipment rotor part, and respectively measured according to the equipment rotor part
The time domain charactreristic parameter and frequency domain character parameter of the vibration signal computing device rotor part in face;While collecting device current working
Technique measure feature parameter;
2) time domain charactreristic parameter of equipment rotor part, the frequency domain character of equipment rotor part are joined using analytic hierarchy process (AHP)
The technique measure feature parameter of number and equipment current working is classified, and obtains equipment state health degree evaluation model, the equipment shape
State health degree evaluation model can reflect the recursive hierarchy structure of equipment health degree membership, recycle equipment health degree to be subordinate to
The recursive hierarchy structure of relation determines object set and index set;
3) agriculture products concentrate the corresponding membership function of each index;
4) according to step 3) the corresponding membership function of each index calculates the healthy angle value of each index in the index set that determines;
5) by step 4) the healthy angle value of obtained each index, each index is to the contribution rate of its last layer and each index
Variable weight function adjusts the weight of each index, then passes through number according to the weight after the healthy angle value of each index and its corresponding adjustment
According to equipment running status health degree is merged to obtain, the equipment running status health degree for completing adaptively to be merged based on multiple features is assessed.
The expression formula of the variable weight function of each index is:
Wherein,For the weight after index optimization, wiFor the original weight of index, hiFor the health degree of i-th of indicator layer
Value, n is the index number of present analysis level.
The invention has the advantages that:
It is of the present invention specifically to be grasped based on the equipment running status health degree appraisal procedure that multiple features are adaptively merged
When making, with the time domain charactreristic parameter of equipment rotor part, the frequency domain character parameter of equipment rotor part and equipment current working
Equipment state health degree evaluation model is built based on technique measure feature parameter, the Recurison order hierarchy of health degree membership is recycled
Structure determination object set and index set, the then contribution rate and change according to the healthy angle value, each index of each index to its last layer
Weight function adjusts the weight of each index, and the weight after healthy angle value and its corresponding adjustment further according to each index is melted by data
Final equipment running status health degree is closed to obtain, realizes that the adaptive quantizing of equipment running status monitoring degree is assessed, reliability and standard
True property is significantly lifted.It should be noted that the present invention adjusts the weight of each index using the variable weight function of each index, with
Reach the effect of adaptive variable weight.The present invention breaks through traditional single measuring point Monitoring Data or single index to assess the limitation of object
Property, the level of substantial equipment state estimation and status monitoring is improved, is provided effectively for the healthy reliability service of slewing
Support.
Brief description of the drawings
Fig. 1 is the schematic diagram of the recursive hierarchy structure of reflection health degree membership in the present invention;
Fig. 2 is the schematic diagram of the healthy angle value of equipment and the mapping relations of equipment running status in the present invention;
Fig. 3 is the distribution schematic diagram of smaller more excellent type index health degree membership function in the present invention;
Fig. 4 is the distribution schematic diagram of more excellent type index health degree membership function more placed in the middle in the present invention;
Fig. 5 is the distribution schematic diagram of each state clustering model of slewing and its sample in the present invention;
Fig. 6 is Clustering Model schematic diagram enlarged drawing in the present invention.
Embodiment
The present invention is described in further detail below in conjunction with the accompanying drawings:
The present invention's is comprised the following steps based on the equipment running status health degree appraisal procedure that multiple features are adaptively merged:
1) vibration signal of each measuring surface of synchronous acquisition equipment rotor part, and respectively measured according to the equipment rotor part
The time domain charactreristic parameter and frequency domain character parameter of the vibration signal computing device rotor part in face;While collecting device current working
Technique measure feature parameter;
2) time domain charactreristic parameter of equipment rotor part, the frequency domain character of equipment rotor part are joined using analytic hierarchy process (AHP)
The technique measure feature parameter of number and equipment current working is classified, and obtains equipment state health degree evaluation model, the equipment shape
State health degree evaluation model can reflect the recursive hierarchy structure of equipment health degree membership, recycle equipment health degree to be subordinate to
The recursive hierarchy structure of relation determines object set and index set;
3) agriculture products concentrate the corresponding membership function of each index;
4) according to step 3) the corresponding membership function of each index calculates the healthy angle value of each index in the index set that determines;
5) by step 4) the healthy angle value of obtained each index, each index is to the contribution rate of its last layer and each index
Variable weight function adjusts the weight of each index, then passes through number according to the weight after the healthy angle value of each index and its corresponding adjustment
According to equipment running status health degree is merged to obtain, the equipment running status health degree for completing adaptively to be merged based on multiple features is assessed.
Initial weight of the weight of each index as the layer fusion of evaluation item next time after can this be adjusted.
It is used as using certain factory reality in operation nitrogen compressor group and assesses object (abnormality), it is contemplated that the control system of equipment
And the online monitoring data of monitoring system can reflect the operation health status of equipment in real time, therefore the present invention considers equipment and existed
The characteristic value data as shown in table 1 of line monitoring system collection, the characteristic value data specifically includes the temperature of nitrogen turbine steam
Degree, pressure and flow, the time and frequency domain characteristics value of bearing temperature and each vibration measuring point, nitrogen compressor gas pressure, bearing temperature with
And the temporal signatures value and frequency domain character value, deceleration device rotating shaft temperature, gear-box of each vibration measuring point respectively vibrate the time-frequency of measuring point
Characteristic of field value and equipment rotating speed.
As shown in figure 1, using analytic hierarchy process (AHP), based on above-mentioned each characteristic value, setting up Grand Equipments running status and being good for
Kang Du evaluation models, as shown in Figure 1, the Grand Equipments running status health degree evaluation model are divided into tri-layer index system, mesh
Mark layer is equipment running status health degree, and item layer is the running status for each machine that current device is included, and sub-project layer includes
The sets of factors for influenceing destination layer to judge, wherein, sub-project layer includes equipment operational shock amount quantitatively evaluating index set, equipment and transported
Row technique amount evaluation indice and equipment operation dimensionless group evaluation indice, then continue to decompose to indicator layer, index
Layer specifically include table 1) in all collections characteristic information;The health degree appraisement system is in from bottom to top recursive hierarchy structure, is referred to
The sets of factors of mark layer can reflect destination layer equipment running status health degree comprehensively, and destination layer equipment running status health degree
The mapping relations of value and equipment actual motion state are as shown in Fig. 2 be healthy, good, inferior health by actual motion state demarcation
And 4 grades of failure, the corresponding healthy angle value interval range difference of different brackets.
Each index in analysis indexes layer, determines the expression formula of corresponding health degree membership function.Fig. 3 and Fig. 4
Expression gives two kinds of typical health degree membership function distributions in evaluation model, includes the degree of membership of smaller more excellent type index
And the degree of membership distribution of middle optimal type index.
Fig. 3 is the distribution map of smaller more excellent type index membership function, and the index for meeting the distribution map is surveyed including vibration equipment
Point vibration passband value, a frequency multiplication value and steam flow;And the membership function of the membership function distribution map is as follows:
Wherein, h (x) is the health degree of judging quota, and x is judging quota measured value, and e is the index permissible value, and E refers to for this
Target limit value.
Fig. 4 be middle optimal type index Membership Function Distribution figure, meet the distribution map characteristic parameter include steam pressure,
Temperature and bearing temperature.
Wherein, E1And e1For the higher limit and lower limit of index;E2And e2For index permissible value.
It is main in the embodiment above to have studied equipment operation process amount evaluation indice and the quantization of equipment operational shock amount
Each index that evaluation index is concentrated, runs metrics evaluation in dimensionless group evaluation indice, it is contemplated that equipment for equipment
Vibrate dimensionless group insensitive to operating mode, be difficult to quantify, but to signal characteristic it is sensitive the characteristics of, the present invention choose have dimension,
Dimensionless group is characterized parameter, calculates and amounts to 15 characteristic ginseng values, and table 2 show in particular the title of this 15 kinds of characteristic parameters
And its defined formula;Then, by the obvious running status of experimental simulation rotor apparatus feature (crackle, touch and rub and normally) simultaneously
Gathered data is analyzed, using principal component method to eigenmatrix carry out dimensionality reduction obtain fuzzy clustering result, obtain as
Each state clustering distribution of results figure shown in Fig. 5;As shown in Figure 4, in the visual analyzing of three characteristic parameters used,
Each state, which has itself, obvious boundary between good Clustering Effect, different conditions, therefore in the class by defining each state
Away from and each state between class spacing as assessment equipment current operating conditions another standard.
More intuitively to express above-mentioned thought, Fig. 5 progress partial enlargements are obtained into local refinement figure as shown in Figure 6, and
In the Fig. 6 to each state be distributed class in away from and maximum kind spacing carried out mark explanation;In view of actual state estimation
In often using normal condition as standard, so during the present invention also assesses the class spacing of normal condition as dimensionless index
A threshold value, and rubbed in Fig. 6 with the farthest state of normal condition cluster centre to touch, the maximum kind spacing between two states
(the distance between two cluster centres add in two classes away from sum) is used as another threshold value.And in the present invention by setting up model most
Away from for 0.6125 in the class of the normal condition determined eventually, the maximum kind spacing with normal condition is 3.2991.Actual capabilities are because building
The difference of formwork erection type, is determined away from being had differences with maximum kind spacing in obtained class, as long as model is once set up, what is built
It is rational to carry out health degree on the basis of model to assess.
On the basis of being analyzed more than, it is considered to which the evaluation index membership function in time domain parameter index set meets smaller get over
The degree of membership distribution form of excellent type index, and away from will be as higher limit e in the class of normal condition mentioned above, i.e. measured data
Class spacing it is high (the healthy angle value that assessment is obtained is accordingly high) as normal condition degree of membership within e=0.6125, and most
Major class spacing as lower limit E, i.e. measured data class spacing be more than E=3.2991 as normal condition to be subordinate to angle value low
(the healthy angle value that assessment is obtained is accordingly low).
Therefore the membership function in the indicator layer shown in Fig. 1 corresponding to each characteristic parameter is all determined, is direct table
Up to the health degree of the running status of equipment, result above need to be merged.In indicator layer data fusion aspect, the present invention is carried out
Fusion Features twice, assessment result is as shown in table 3;Data Layer Fusion Features are as follows:Items for belonging to same project layer
Health degree determined by index carries out first time Fusion Features using moving average, for different subitems after a Fusion Features
Secondary weighted fusion is carried out using weight between mesh layer.Theoretical foundation is that the characteristic parameter under same project layer runs shape to equipment
State influence coefficient can be regarded as identical, and different item layers are different to the influence degree of equipment running status, vibration
Quantitative evaluation accounts for leading factor, and this is also consistent with actual conditions.
As shown in table 3, the result for the abnormal item data of projects layer health degree that moving average fusion is obtained is not equal to 1,
Major parameter monitoring is should be used as in actual state estimation, so in the present invention using variable weight function to right-value optimization, weights
Assessment result before and after optimization is as shown in Table.
Existing slewing state estimation priori is combined when being merged between disparity items layer, and to this method institute
The device history state of research and the analysis of historical data, to weighted average there is provided initial often weights
Universality and assessment in view of the present invention it is comprehensive, now normal weights are set and makees following situation and assumes to analyze:
Situation is 1.:When three category feature data are collected in items of equipment layer, then W is madeH=[0.6,0.2,0.2];
Situation is 2.:When without technique figureofmerit data, then W is madeH=[0.7,0,0.3];
Situation is 3.:When only technique figureofmerit data, then W is madeH=[0,1,0];
Situation is 4.:When only vibratory output evaluation index data, then W is madeH=[1,0,0];
Situation is 5.:When amount evaluation index data without friction, then W is madeH=[0,0.6,0.4];
Situation is 6.:When only dimensionless evaluation index data, then W is madeH=[0,0,1];
Situation is 7.:When no dimensionless evaluation index data, then W is madeH=[0.9,0.1,0].
Wherein, WHFor equipment health degree evaluation weight matrix,WithThe power of first layer item layer is represented respectively
The weighted value of weight values, the weighted value of second layer item layer and third layer item layer.And do hypothesis and mainly consider item layer
Certain characteristic concentrates corresponding data type not configure measuring point gathered data, and vibrating measuring point when configuration collects vibration signal, then
Dimensionless evaluation index data and vibratory output evaluation index data can be accordingly obtained, therefore situation is 1., 2. and 3. to be actual normal
See situation, the present invention by mainly by situation 1. based on complete whole evaluation process, that is, it is W to select initial often weightsH=[0.6,
0.2,0.2].
Different working conditions are often run in view of equipment, to improve evaluation result to healthy angle value muting sensitive sense degree, are disappeared
Except index it is excessive in the case of flood the phenomenons of abnormal index data, the present invention introduces variable weight algorithm on the basis of given normal weights
To improve weights distribution, variable weight function formula is:
Wherein,For the weight after optimization, wiFor original weight, hiFor the healthy angle value of i-th of indicator layer, n is current point
Analyse the index number of level.Above-mentioned variable weight function formula can effectively remove the average effect in fusion process and extract sensitive features,
Ignoring influences little index on health status, and influences larger index weights to carry out increasing strong on health degree for those
Change, this is also corresponding with often paying close attention to abnormal information in actual production.So every layer of index is in the when weight that data Layer is merged
Adaptive optimization, i.e., the contribution rate of current last layer index health degree assessment result is repaiied using variable weight function according to each index
Positive weights.
For example, above-mentioned initial often weights WHAfter=[0.6,0.2,0.2] optimizes through variable weight function, weights are respectively WH=
Assessment result before and after [0.803,0.066,0.131], right-value optimization is as shown in table 3.Meanwhile, the weights after optimization, which will be used as, works as
Initial Chang Quan when being merged during the running status health degree assessment next time of preceding equipment between disparity items layer;The final present invention is to this
Equipment is 0.712 in the assessment result of running status health degree, understands that the equipment currently belongs to sub- be good for reference to Fig. 2 corresponding relation
Health state, part machinery equipment there may be to be needed to pay close attention in failure or operation risk, status monitoring.
It can be seen that, the present invention can be realized using substantial equipment as research object, considered special including technique amount data, vibration
Value indicative data, vibrational waveform data and Parameters of Time-frequency Field etc. have an impact or reflected the multicharacteristic information of equipment running status, lead to
The improvement to regulatory thresholds monitoring means is crossed, the equipment running status health degree using introduction is target, and utilization state is adaptively drawn
The intelligent evaluation method divided improves equipment health operation evaluation capacity, realizes that equipping running status health degree adaptive quantizing comments
Estimate.The present invention breaches the assessment object and the single limitation of evaluation index of Legacy Status appraisal procedure, has expanded Legacy Status
The application of appraisal procedure.Meanwhile, the weight that each index of methods described fusion is used has been reached adaptive using variable weight function
The effect of variable weight is answered, it is achieved thereby that the adaptive quantizing of health degree is assessed.This method is applied to macroscopic view understanding, assessment equipment fortune
Row state health degree, provides for the healthy reliably operation of rotating machinery and provides powerful support for.
Table 1
Table 2
Table 3
Claims (2)
1. a kind of equipment running status health degree appraisal procedure adaptively merged based on multiple features, it is characterised in that including with
Lower step:
1) vibration signal of each measuring surface of synchronous acquisition equipment rotor part, and according to each measuring surface of equipment rotor part
The time domain charactreristic parameter and frequency domain character parameter of vibration signal computing device rotor part;While the work of collecting device current working
Skill measure feature parameter;
2) using analytic hierarchy process (AHP) to the time domain charactreristic parameter of equipment rotor part, the frequency domain character parameter of equipment rotor part and
The technique measure feature parameter of equipment current working is classified, and obtains equipment state health degree evaluation model, and the equipment state is good for
Kang Du evaluation models can reflect the recursive hierarchy structure of equipment health degree membership, recycle equipment health degree membership
Recursive hierarchy structure determine object set and index set;
3) agriculture products concentrate the corresponding membership function of each index;
4) according to step 3) the corresponding membership function of each index calculates the healthy angle value of each index in the index set that determines;
5) according to the variable weight function of each index, each index to the contribution rate and step 4 of its last layer) the obtained health of each index
Angle value adjusts the weight of each index, is then melted according to the weight after the healthy angle value of each index and its corresponding adjustment by data
Equipment running status health degree is closed to obtain, the equipment running status health degree for completing adaptively to be merged based on multiple features is assessed.
2. the equipment running status health degree appraisal procedure according to claim 1 adaptively merged based on multiple features, its
It is characterised by, the expression formula of the variable weight function of each index is:
Wherein,For the weight after index optimization, wiFor the original weight of index, hiFor the healthy angle value of i-th of indicator layer, n is
The index number of present analysis level.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710171131.XA CN107016235B (en) | 2017-03-21 | 2017-03-21 | Equipment running state health degree evaluation method based on multi-feature adaptive fusion |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710171131.XA CN107016235B (en) | 2017-03-21 | 2017-03-21 | Equipment running state health degree evaluation method based on multi-feature adaptive fusion |
Publications (2)
Publication Number | Publication Date |
---|---|
CN107016235A true CN107016235A (en) | 2017-08-04 |
CN107016235B CN107016235B (en) | 2020-06-19 |
Family
ID=59439593
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710171131.XA Active CN107016235B (en) | 2017-03-21 | 2017-03-21 | Equipment running state health degree evaluation method based on multi-feature adaptive fusion |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107016235B (en) |
Cited By (15)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107941537A (en) * | 2017-10-25 | 2018-04-20 | 南京航空航天大学 | A kind of mechanical equipment health state evaluation method |
CN108062603A (en) * | 2017-12-29 | 2018-05-22 | 国网福建省电力有限公司 | Based on distribution power automation terminal life period of an equipment life-span prediction method and system |
CN108363836A (en) * | 2018-01-17 | 2018-08-03 | 杭州安脉盛智能技术有限公司 | Multi-state adaptive industrial robot health degree appraisal procedure and system |
CN109194534A (en) * | 2018-07-24 | 2019-01-11 | 西安电子科技大学 | The scheduling and management method of internet of things oriented device populations |
CN109472369A (en) * | 2017-09-06 | 2019-03-15 | 云南电网有限责任公司保山供电局 | The monitoring method and device of power equipment |
CN109615275A (en) * | 2019-01-21 | 2019-04-12 | 国网福建省电力有限公司 | A kind of power telecom network equipment health degree integrated evaluating method |
CN110082623A (en) * | 2019-05-21 | 2019-08-02 | 国网安徽省电力有限公司合肥供电公司 | A kind of switchgear health status evaluation method and system |
WO2020134641A1 (en) * | 2018-12-28 | 2020-07-02 | 上海奥普生物医药股份有限公司 | Data processing method and apparatus |
CN111581811A (en) * | 2020-04-30 | 2020-08-25 | 浙江三一装备有限公司 | Health assessment method for engineering machinery |
CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
CN112488432A (en) * | 2019-09-10 | 2021-03-12 | 上海杰之能软件科技有限公司 | Equipment health assessment method, storage device and terminal |
CN113489605A (en) * | 2021-06-29 | 2021-10-08 | 南京航空航天大学 | Network node importance evaluation method based on health degree |
CN114204651A (en) * | 2022-01-26 | 2022-03-18 | 深圳市德航智能技术有限公司 | Three proofings panel computer with safe reserve power |
CN115619107A (en) * | 2022-12-20 | 2023-01-17 | 浙江浙能数字科技有限公司 | Coal-fired power plant equipment health degree evaluation method based on multi-dimensional information |
CN115758277A (en) * | 2022-11-30 | 2023-03-07 | 重庆忽米网络科技有限公司 | Online health state evaluation method for rotary equipment |
Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN103218515A (en) * | 2013-03-21 | 2013-07-24 | 西北工业大学 | Satellite health status evaluation method based on variable-weight hierarchical scores |
CN104091066A (en) * | 2014-07-04 | 2014-10-08 | 山东大学 | Condition evaluation method for high-voltage circuit breaker |
CN104952000A (en) * | 2015-07-01 | 2015-09-30 | 华侨大学 | Wind turbine operating state fuzzy synthetic evaluation method based on Markov chain |
CN105631771A (en) * | 2016-03-01 | 2016-06-01 | 国家电网公司 | Variable weight function-based multi-parameter cable state evaluation method |
CN105975735A (en) * | 2016-07-19 | 2016-09-28 | 广西电网有限责任公司电力科学研究院 | Modeling method for assessing health state of power equipment |
CN106203875A (en) * | 2016-07-19 | 2016-12-07 | 广西电网有限责任公司电力科学研究院 | A kind of model for power equipment health state evaluation |
CN106227185A (en) * | 2016-07-05 | 2016-12-14 | 杨林 | A kind of elevator risk evaluating system |
-
2017
- 2017-03-21 CN CN201710171131.XA patent/CN107016235B/en active Active
Patent Citations (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102621421A (en) * | 2012-03-29 | 2012-08-01 | 贵阳供电局 | Transformer state evaluation method based on correlation analysis and variable weight coefficients |
CN102768115A (en) * | 2012-06-27 | 2012-11-07 | 华北电力大学 | Method for dynamically monitoring health status of wind turbine gearbox in real time |
CN103218515A (en) * | 2013-03-21 | 2013-07-24 | 西北工业大学 | Satellite health status evaluation method based on variable-weight hierarchical scores |
CN104091066A (en) * | 2014-07-04 | 2014-10-08 | 山东大学 | Condition evaluation method for high-voltage circuit breaker |
CN104952000A (en) * | 2015-07-01 | 2015-09-30 | 华侨大学 | Wind turbine operating state fuzzy synthetic evaluation method based on Markov chain |
CN105631771A (en) * | 2016-03-01 | 2016-06-01 | 国家电网公司 | Variable weight function-based multi-parameter cable state evaluation method |
CN106227185A (en) * | 2016-07-05 | 2016-12-14 | 杨林 | A kind of elevator risk evaluating system |
CN105975735A (en) * | 2016-07-19 | 2016-09-28 | 广西电网有限责任公司电力科学研究院 | Modeling method for assessing health state of power equipment |
CN106203875A (en) * | 2016-07-19 | 2016-12-07 | 广西电网有限责任公司电力科学研究院 | A kind of model for power equipment health state evaluation |
Non-Patent Citations (1)
Title |
---|
郇嘉嘉: "电网设备状态检修策略的研究", 《中国博士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109472369A (en) * | 2017-09-06 | 2019-03-15 | 云南电网有限责任公司保山供电局 | The monitoring method and device of power equipment |
CN107941537A (en) * | 2017-10-25 | 2018-04-20 | 南京航空航天大学 | A kind of mechanical equipment health state evaluation method |
CN108062603A (en) * | 2017-12-29 | 2018-05-22 | 国网福建省电力有限公司 | Based on distribution power automation terminal life period of an equipment life-span prediction method and system |
CN108363836A (en) * | 2018-01-17 | 2018-08-03 | 杭州安脉盛智能技术有限公司 | Multi-state adaptive industrial robot health degree appraisal procedure and system |
CN109194534A (en) * | 2018-07-24 | 2019-01-11 | 西安电子科技大学 | The scheduling and management method of internet of things oriented device populations |
CN109194534B (en) * | 2018-07-24 | 2022-03-22 | 西安电子科技大学 | Scheduling and management method for Internet of things equipment group |
WO2020134641A1 (en) * | 2018-12-28 | 2020-07-02 | 上海奥普生物医药股份有限公司 | Data processing method and apparatus |
CN109615275A (en) * | 2019-01-21 | 2019-04-12 | 国网福建省电力有限公司 | A kind of power telecom network equipment health degree integrated evaluating method |
CN110082623A (en) * | 2019-05-21 | 2019-08-02 | 国网安徽省电力有限公司合肥供电公司 | A kind of switchgear health status evaluation method and system |
CN112488432A (en) * | 2019-09-10 | 2021-03-12 | 上海杰之能软件科技有限公司 | Equipment health assessment method, storage device and terminal |
CN111581811A (en) * | 2020-04-30 | 2020-08-25 | 浙江三一装备有限公司 | Health assessment method for engineering machinery |
CN111581811B (en) * | 2020-04-30 | 2023-11-03 | 浙江三一装备有限公司 | Engineering machinery health assessment method |
CN112034789A (en) * | 2020-08-25 | 2020-12-04 | 国家机床质量监督检验中心 | Health assessment method, system and assessment terminal for key parts and complete machine of numerical control machine tool |
CN113489605A (en) * | 2021-06-29 | 2021-10-08 | 南京航空航天大学 | Network node importance evaluation method based on health degree |
CN113489605B (en) * | 2021-06-29 | 2023-02-03 | 南京航空航天大学 | Network node importance evaluation method based on health degree |
CN114204651A (en) * | 2022-01-26 | 2022-03-18 | 深圳市德航智能技术有限公司 | Three proofings panel computer with safe reserve power |
CN115758277A (en) * | 2022-11-30 | 2023-03-07 | 重庆忽米网络科技有限公司 | Online health state evaluation method for rotary equipment |
CN115619107A (en) * | 2022-12-20 | 2023-01-17 | 浙江浙能数字科技有限公司 | Coal-fired power plant equipment health degree evaluation method based on multi-dimensional information |
CN115619107B (en) * | 2022-12-20 | 2023-03-28 | 浙江浙能数字科技有限公司 | Coal-fired power plant equipment health degree evaluation method based on multi-dimensional information |
Also Published As
Publication number | Publication date |
---|---|
CN107016235B (en) | 2020-06-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107016235A (en) | The equipment running status health degree appraisal procedure adaptively merged based on multiple features | |
CN106444703B (en) | Dynamic equipment running status fuzzy evaluation and prediction technique based on fault mode probability of happening | |
CN107941537B (en) | A kind of mechanical equipment health state evaluation method | |
CN108375476B (en) | Hydroelectric generating set health assessment method | |
CN105300692B (en) | A kind of bearing failure diagnosis and Forecasting Methodology based on expanded Kalman filtration algorithm | |
CN104573850B (en) | A kind of Power Plant Equipment state evaluating method | |
CN104061445B (en) | A kind of pipeline leakage detection method based on neutral net | |
CN103344914B (en) | Based on normalized Wind turbines fault early warning method | |
CN101408951B (en) | Method for obtaining equivalent load spectrum and estimating weariness residual longevity of bridge crane based on neural network | |
CN101718634B (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
CN102486833B (en) | Method for predicting efficiency and detecting fault of device | |
CN109613428A (en) | It is a kind of can be as system and its application in motor device fault detection method | |
CN103020438A (en) | Aero-engine reliability monitoring method based on mixed weibull distribution | |
CN103810328A (en) | Transformer maintenance decision method based on hybrid model | |
CN107679768A (en) | A kind of Situation Awareness System and its construction method based on real-time data of power grid | |
CN102788696A (en) | Evaluation method for health degree of bearing on basis of improved BP (Back Propagation) neural network and fuzzy set theory | |
CN110137947B (en) | Grid voltage sag severity assessment method based on ITIC curve | |
CN103793859A (en) | Wind power plant running monitoring and event comprehensive evaluation method | |
CN104795819B (en) | Power system state estimation system based on strong tracking set membership estimation | |
CN103996147A (en) | Comprehensive evaluation method for power distribution network | |
CN108204895A (en) | A kind of Wind turbines change gear box fault diagnosis method and system | |
CN102879728A (en) | Health evaluation index and failure predication method for DC (Direct Current)-DC convertor | |
CN105005822A (en) | Optimal step length and dynamic model selection based ultrahigh arch dam response prediction method | |
CN103810532A (en) | Method for optimizing running state of urban drainage system | |
CN105653851A (en) | Residual life prediction method of antifriction bearing on the basis of staged physical model and particle filter |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |