CN107016235B - Equipment running state health degree evaluation method based on multi-feature adaptive fusion - Google Patents
Equipment running state health degree evaluation method based on multi-feature adaptive fusion Download PDFInfo
- Publication number
- CN107016235B CN107016235B CN201710171131.XA CN201710171131A CN107016235B CN 107016235 B CN107016235 B CN 107016235B CN 201710171131 A CN201710171131 A CN 201710171131A CN 107016235 B CN107016235 B CN 107016235B
- Authority
- CN
- China
- Prior art keywords
- index
- equipment
- health degree
- characteristic parameters
- health
- 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
Images
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
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method for evaluating the health degree of equipment running state based on multi-feature self-adaptive fusion, which comprises the following steps: 1) calculating time domain characteristic parameters and frequency domain characteristic parameters of the equipment rotor component according to the vibration signals of all the measuring surfaces of the equipment rotor component; simultaneously collecting technological parameter characteristic parameters of the current working condition of the equipment; 2) obtaining an equipment state health degree evaluation model, wherein the equipment state health degree evaluation model can reflect the hierarchical structure of the health degree membership, and then the hierarchical structure of the health degree membership is utilized to determine a target set and an index set; 3) determining membership functions corresponding to indexes in the index set; 4) calculating the health degree value of each index according to the membership function corresponding to each index in the index set; 5) and obtaining the final equipment running state health degree through data fusion according to the health degree value of each index and the corresponding adjusted weight of each index.
Description
Technical Field
The invention belongs to the field of fault diagnosis of mechanical equipment, and relates to an equipment running state health degree evaluation method based on multi-feature adaptive fusion.
Background
The power equipment represented by rotary machinery is a core tool and a main resource for enterprises to implement production, each industry has key equipment at the core from manufacturing industry, power industry to military aerospace industry, the operation health state of the equipment such as aircraft carriers, large-scale power transformers, aircraft engines, generators and the like is extremely important, and once equipment failure occurs, the result is often beyond the assumption. Therefore, finding, capturing, tracking, monitoring and evaluating the state of the equipment in time and ensuring that the equipment is in a normal and stable working condition are the most concerned and valued problems in various industries at present.
The state evaluation research has long history sources, and is mostly used for the prediction evaluation of weather change and the medical evaluation of physical health conditions of natural people, the two methods depend on the judgment of experience to a great extent, scientific research methods and theoretical models are not deeply researched to form the problem, and the research methods are difficult to be used as reference in other research fields. At the end of the 20 th century, the continuous maturity of relevant research and theoretical methods such as artificial intelligence, data fusion, fuzzy theory, neural network and the like powerfully promotes the continuous development of health state assessment and prediction technology, the research field is continuously expanded from the industries such as aerospace, weaponry and the like to other industries, and a plurality of experts and scholars apply the health state assessment technology to the fields such as engines, bridges, mechanical equipment and the like.
The vibration data of the unit is visual reflection of the operation condition of the unit, the traditional mechanical state evaluation method is used for monitoring and evaluating a single measuring point or a cross-section measuring point of the unit, the parameter index which can be analyzed is single, the accurate evaluation can be carried out only by needing stronger professional skills, the use simplicity is poor, and the self-adaption degree is low. On the other hand, the traditional evaluation method is to simply compare the detection value with the threshold value under the condition of giving the tolerance threshold value, but the setting of the tolerance threshold value has larger subjectivity, and the state evaluation method has lower reliability and does not have the capability of coping with the current fault diversification.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a method for evaluating the health degree of the running state of the equipment based on multi-feature adaptive fusion, which can accurately realize the adaptive evaluation of the health degree of the running state of the equipment and has high reliability.
In order to achieve the above purpose, the method for evaluating the health degree of the running state of the equipment based on the multi-feature adaptive fusion comprises the following steps:
1) synchronously acquiring vibration signals of each measuring surface of the equipment rotor component, and calculating time domain characteristic parameters and frequency domain characteristic parameters of the equipment rotor component according to the vibration signals of each measuring surface of the equipment rotor component; simultaneously collecting technological parameter characteristic parameters of the current working condition of the equipment;
2) classifying time domain characteristic parameters of the equipment rotor component, frequency domain characteristic parameters of the equipment rotor component and process quantity characteristic parameters of the current working condition of the equipment by adopting an analytic hierarchy process to obtain an equipment state health degree evaluation model, wherein the equipment state health degree evaluation model can reflect a hierarchical structure of equipment health degree membership, and then determining a target set and an index set by utilizing the hierarchical structure of the equipment health degree membership;
3) determining membership functions corresponding to indexes in the index set;
4) calculating the health degree value of each index according to the membership function corresponding to each index in the index set determined in the step 3);
5) and 4) adjusting the weight of each index through the health value of each index, the contribution rate of each index to the upper layer of the index and the variable weight function of each index obtained in the step 4), and then obtaining the health degree of the running state of the equipment through data fusion according to the health value of each index and the corresponding adjusted weight of each index, thereby completing the evaluation of the health degree of the running state of the equipment based on the multi-feature self-adaptive fusion.
The expression of the variable weight function of each index is as follows:
wherein the content of the first and second substances,
for the weight after index optimization, wiIs the original weight of the index, hiThe index value is the health value of the ith index layer, and n is the index number of the current analysis layer.
The invention has the following beneficial effects:
the equipment running state health degree evaluation method based on the multi-feature adaptive fusion is characterized in that during specific operation, an equipment state health degree evaluation model is constructed on the basis of time domain characteristic parameters of an equipment rotor component, frequency domain characteristic parameters of the equipment rotor component and process quantity characteristic parameters of the current working condition of equipment, a target set and an index set are determined by utilizing a hierarchical structure of a health degree membership relationship, the weight of each index is adjusted according to the health degree value of each index, the contribution rate of each index to the upper layer of the index and a variable weight function, the health degree value of each index and the corresponding adjusted weight are subjected to data fusion to obtain the final equipment running state health degree, the adaptive quantitative evaluation of the equipment running state monitoring degree is achieved, and the reliability and the accuracy are greatly improved. It should be noted that, the present invention adjusts the weight of each index by using the variable weight function of each index, so as to achieve the effect of adaptive weight change. The invention breaks through the limitation that the traditional single measuring point monitoring data or single index is an evaluation object, improves the level of major equipment state evaluation and state monitoring, and provides powerful support for the healthy and reliable operation of the rotating equipment.
Drawings
FIG. 1 is a schematic diagram of a hierarchical structure reflecting health degree membership in the present invention;
FIG. 2 is a diagram illustrating a mapping relationship between a health value of a device and an operating status of the device according to the present invention;
FIG. 3 is a diagram illustrating distribution of membership functions of health indexes of more optimal indicators according to the present invention;
FIG. 4 is a schematic diagram showing the distribution of the health degree membership function of the more central and more optimal index in the present invention;
FIG. 5 is a schematic diagram of a cluster model of states of a rotating device and a distribution of samples thereof according to the present invention;
FIG. 6 is an enlarged view of a clustering model according to the present invention.
Detailed Description
The invention is described in further detail below with reference to the accompanying drawings:
the equipment running state health degree evaluation method based on multi-feature adaptive fusion comprises the following steps:
1) synchronously acquiring vibration signals of each measuring surface of the equipment rotor component, and calculating time domain characteristic parameters and frequency domain characteristic parameters of the equipment rotor component according to the vibration signals of each measuring surface of the equipment rotor component; simultaneously collecting technological parameter characteristic parameters of the current working condition of the equipment;
2) classifying time domain characteristic parameters of the equipment rotor component, frequency domain characteristic parameters of the equipment rotor component and process quantity characteristic parameters of the current working condition of the equipment by adopting an analytic hierarchy process to obtain an equipment state health degree evaluation model, wherein the equipment state health degree evaluation model can reflect a hierarchical structure of equipment health degree membership, and then determining a target set and an index set by utilizing the hierarchical structure of the equipment health degree membership;
3) determining membership functions corresponding to indexes in the index set;
4) calculating the health degree value of each index according to the membership function corresponding to each index in the index set determined in the step 3);
5) and 4) adjusting the weight of each index through the health value of each index, the contribution rate of each index to the upper layer of the index and the variable weight function of each index obtained in the step 4), and then obtaining the health degree of the running state of the equipment through data fusion according to the health value of each index and the corresponding adjusted weight of each index, thereby completing the evaluation of the health degree of the running state of the equipment based on the multi-feature self-adaptive fusion.
The weight of each index after the adjustment can be used as the initial weight for evaluating the project layer fusion next time.
The method takes a nitrogen compressor unit which is actually operated in a certain factory as an evaluation object (abnormal state), and considers that the online monitoring data of a control system and a monitoring system of the equipment can reflect the operation health state of the equipment in real time, so the method comprehensively considers the characteristic data which is collected by the online monitoring system of the equipment and is shown in the table 1, wherein the characteristic data specifically comprises the temperature, the pressure and the flow of the steam of the nitrogen turbine, the bearing temperature, the time-frequency domain characteristic value of each vibration measuring point, the nitrogen compressor gas pressure, the bearing temperature, the time-frequency domain characteristic value and the frequency-domain characteristic value of each vibration measuring point, the speed reducer rotating shaft temperature, the time-frequency domain characteristic value of each vibration measuring point of the gear box.
As shown in fig. 1, an analytic hierarchy process is utilized, based on the above characteristic values, a major equipment operation state health degree evaluation model is established, as can be seen from fig. 1, the major equipment operation state health degree evaluation model is divided into a three-level index system, a target layer is an equipment operation state health degree, a project layer is an operation state of each machine included in the current equipment, and a sub-project layer includes a factor set influencing the evaluation of the target layer, wherein the sub-project layer includes an equipment operation vibration quantity quantitative evaluation index set, an equipment operation process quantity evaluation index set and an equipment operation dimensionless parameter evaluation index set, and then continues to be decomposed to the index layer, and the index layer specifically includes all the collected characteristic information in table 1); the health degree evaluation system presents a hierarchical structure from bottom to top, the factor set of the index layer can comprehensively reflect the health degree of the running state of the target layer equipment, the mapping relation between the running state health degree value of the target layer equipment and the actual running state of the equipment is shown in figure 2, the actual running state is divided into 4 grades of health, good, sub-health and fault, and the ranges of the health degree values corresponding to different grades are different.
And analyzing each index in the index layer, and determining an expression of the health degree membership function corresponding to each index. FIGS. 3 and 4 show two typical distributions of health degree membership functions in the evaluation model, including the distribution of membership degrees of the smaller and the better indicators and the distribution of membership degrees of the intermediate and the best indicators.
FIG. 3 is a distribution diagram of a membership function of a more optimal index as the size decreases, wherein the indexes conforming to the distribution diagram include a vibration pass frequency value of a vibration measuring point of the equipment, a frequency doubling value and a steam flow; and the distribution diagram of the membership function has the following membership functions:
wherein h (x) is the health degree of the evaluation index, x is the measured value of the evaluation index, E is the allowable value of the index, and E is the limit value of the index.
FIG. 4 is a graph of the distribution of membership functions for the intermediate optimum index, with the parameters including steam pressure, temperature and bearing temperature.
Wherein E is1And e1The upper limit value and the lower limit value of the index; e2And e2Is an index allowable value.
In the embodiment, each index in the equipment operation process quantity evaluation index set and the equipment operation vibration quantity quantitative evaluation index set is mainly researched, for the index centralized evaluation of the equipment operation dimensionless parameter evaluation index, the characteristics that the vibration dimensionless parameter of the equipment is not sensitive to the working condition, is not easy to quantify and is sensitive to the signal characteristic are considered, the dimensionless parameter and the dimensionless parameter are selected as the characteristic parameters, the total 15 characteristic parameter values are calculated, and the names and the definition formulas of the 15 characteristic parameters are specifically given in a table 2; then, simulating the running states (cracks, rubbing and normality) with obvious characteristics of the rotor equipment through experiments, collecting data for analysis, and reducing the dimension of the characteristic matrix by using a principal component analysis method to obtain fuzzy clustering results to obtain a clustering result distribution diagram of each state as shown in fig. 5; as can be seen from fig. 4, in the visual analysis of the three characteristic parameters, each state has a good clustering effect and distinct boundaries exist between different states, so that the class inner distance of each state and the class interval between states are defined as another criterion for evaluating the current operating state of the equipment.
In order to express the above idea more intuitively, fig. 5 is partially enlarged to obtain a partially refined diagram as shown in fig. 6, and the class inner distance and the maximum class distance of each state distribution are labeled and explained in fig. 6; considering that the normal state is often used as the standard in the actual state evaluation, the invention also uses the class spacing of the normal state as one threshold in the dimensionless index evaluation, while the state farthest from the normal state cluster center in fig. 6 is rub-in, and the maximum class spacing between two states (the distance between two cluster centers plus the sum of two intra-class distances) is used as another threshold. The class inner distance of the normal state finally determined by establishing the model in the invention is 0.6125, and the maximum class distance from the normal state is 3.2991. In practice, the determined inter-class distance and the maximum inter-class distance may differ due to differences in the established models, and it is reasonable to perform the health assessment based on the established models as long as the models are established once.
On the basis of the above analysis, the evaluation index membership function in the time domain parameter index set is considered to conform to the smaller membership degree distribution form of the optimal index, and the above-mentioned intra-class distance in the normal state is used as an upper limit value E, that is, the intra-class distance of the measured data within E0.6125 is used as the membership degree in the normal state (the health degree value obtained by the evaluation is correspondingly high), and the maximum intra-class distance is used as a lower limit value E, that is, the membership degree value in the normal state is low (the health degree value obtained by the evaluation is correspondingly low) when the inter-class distance of the measured data is greater than E3.2991.
Therefore, all membership functions corresponding to the characteristic parameters in the index layer shown in fig. 1 are determined, and the results need to be fused to directly express the health degree of the operating state of the equipment. In the index layer data fusion layer, the invention carries out two times of feature fusion, and the evaluation result is shown in table 3; the data layer features are fused as follows: and performing first feature fusion on the health degree determined by each index belonging to the same project layer by adopting a moving average, and performing second weighted fusion on different sub-project layers after the first feature fusion by adopting weights. The theoretical basis is that the influence coefficients of the characteristic parameters under the same project layer on the running state of the equipment can be regarded as the same, the influence degrees of different project layers on the running state of the equipment are different, and quantitative evaluation of vibration is the dominant factor, which is consistent with the actual situation.
As shown in table 3, the result of the abnormal health item data of each project layer obtained by the moving average fusion is not equal to 1, and should be monitored as a main parameter in the actual state evaluation, so that the weight is optimized by adopting the variable weight function in the invention, and the evaluation results before and after the weight optimization are shown in the table.
The prior knowledge of the existing state evaluation of the rotating equipment is combined during fusion between different project layers, the historical state and the historical data of the equipment researched by the method are analyzed, and the initial weighted average is setInitial weight value
Considering the universality and the comprehensiveness of the evaluation, the following hypothesis analysis is performed on the common weight setting:
Case ④ where only the vibration quantity evaluation index data is present, let WH＝[1，0，0]；
Case ⑥, when there is only dimensionless evaluation index data, let WH＝[0，0，1]；
Case ⑦ where there is no dimensionless evaluation index data, let WH＝[0.9，0.1，0]。
Wherein, WHA weight matrix is evaluated for the health of the device,
and
the method mainly considers that measuring point acquisition data is not configured in a certain characteristic data set of the project layer corresponding to the data type, and dimensionless evaluation index data and vibration quantity evaluation index data can be correspondingly obtained when a vibration measuring point is configured to acquire a vibration signal, so that the situations ①, ② and ③ are actual common situations, the method mainly completes the whole evaluation process on the basis of the situation ①, namely the initial constant weight value is selected as WH＝[0.6，0.2，0.2]。
Considering that the equipment is frequently operated under different working conditions, in order to improve the low sensitivity degree of the judgment result to the health degree value and eliminate the phenomenon of submerging abnormal index data under the condition of excessive indexes, the invention introduces a variable weight algorithm on the basis of the given normal weight value to improve weight distribution, and the variable weight function formula is as follows:
wherein the content of the first and second substances,
for optimized weight, wiAs an original weight, hiThe index value is the health value of the ith index layer, and n is the index number of the current analysis layer. The variable weight function formula can effectively remove the average effect in the fusion process and extract sensitive features, neglect indexes which have little influence on the health state, and increase and strengthen the weight of the indexes which have great influence on the health degree, which also corresponds to the fact that abnormal information is usually concerned in the actual production. Therefore, the weight of each layer of indexes is self-adaptively optimized when the indexes are fused in the data layer, namely, the weight is corrected by adopting a variable weight function according to the contribution rate of each index to the health degree evaluation result of the index in the previous layer.
For example, the initial constant weight WH＝[0.6，0.2，0.2]After the optimization of the variable weight function, the weights are respectively WH＝[0.803，0.066，0.131]The evaluation results before and after the weight optimization are shown in table 3. Meanwhile, the optimized weight value is used as an initial constant weight when different project layers are fused when the health degree of the next running state of the current equipment is evaluated; finally, the evaluation result of the health degree of the equipment in the running state is 0.712, and the corresponding relation in fig. 2 shows that the equipment currently belongs to the sub-health state, part of machine equipment possibly has faults or running risks, and close attention is needed in state monitoring.
Therefore, the method can realize that major equipment is taken as a research object, all influences including process quantity data, vibration characteristic value data, vibration waveform data, time-frequency domain parameters and the like or multi-characteristic information reflecting the running state of the equipment are comprehensively considered, the health degree of the running state of the equipment is taken as a target by improving a conventional threshold monitoring means, and the self-adaptive quantitative evaluation capability of the health degree of the equipment is improved by utilizing an intelligent evaluation method of state self-adaptive division, so that the self-adaptive quantitative evaluation of the health degree of the running state of the equipment is realized. The invention breaks through the limitation of single evaluation object and evaluation index of the traditional state evaluation method and expands the application range of the traditional state evaluation method. Meanwhile, the method integrates the weight adopted by each index and uses the variable weight function to achieve the effect of self-adaption variable weight, so that the self-adaption quantitative evaluation of the health degree is realized. The method is suitable for macroscopically understanding and evaluating the health degree of the running state of the equipment, and provides powerful support for the healthy and reliable running of the rotary machine.
TABLE 1
TABLE 2
TABLE 3
Claims (2)
1. A health degree assessment method for equipment running state based on multi-feature adaptive fusion is characterized by comprising the following steps:
1) synchronously acquiring vibration signals of each measuring surface of the equipment rotor component, and calculating time domain characteristic parameters and frequency domain characteristic parameters of the equipment rotor component according to the vibration signals of each measuring surface of the equipment rotor component; simultaneously collecting technological parameter characteristic parameters of the current working condition of the equipment;
2) classifying time domain characteristic parameters of the equipment rotor component, frequency domain characteristic parameters of the equipment rotor component and process quantity characteristic parameters of the current working condition of the equipment by adopting an analytic hierarchy process to obtain an equipment state health degree evaluation model, wherein the equipment state health degree evaluation model can reflect a hierarchical structure of equipment health degree membership, and then determining a target set and an index set by utilizing the hierarchical structure of the equipment health degree membership;
3) determining membership functions corresponding to indexes in the index set;
4) calculating the health degree value of each index according to the membership function corresponding to each index in the index set determined in the step 3);
5) and (4) adjusting the weight of each index according to the variable weight function of each index, the contribution rate of each index to the upper layer of each index and the health value of each index obtained in the step 4), and then obtaining the health degree of the running state of the equipment through data fusion according to the health value of each index and the corresponding adjusted weight of each index, so as to complete the evaluation of the health degree of the running state of the equipment based on the multi-feature self-adaptive fusion.
2. The method for evaluating the health degree of the running state of the equipment based on the multi-feature adaptive fusion as claimed in claim 1, wherein the expression of the variable weight function of each index is as follows:
wherein the content of the first and second substances,
for the weight after index optimization, wiIs the original weight of the index, hiIs the health value of the ith index, and n is the index number of the current 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 CN107016235A (en) | 2017-08-04 |
| CN107016235B true 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) |
Families Citing this family (17)
| 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 |
| CN107941537B (en) * | 2017-10-25 | 2019-08-27 | 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 |
| CN108363836B (en) * | 2018-01-17 | 2021-07-20 | 杭州安脉盛智能技术有限公司 | Multi-working-condition self-adaptive industrial robot health degree assessment method and system |
| 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 |
| CN109637636A (en) * | 2018-12-28 | 2019-04-16 | 上海奥普生物医药有限公司 | Data processing method and device |
| 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 |
| CN112488432B (en) * | 2019-09-10 | 2024-05-07 | 上海杰之能软件科技有限公司 | Equipment health assessment method, storage device and terminal |
| CN111581811B (en) * | 2020-04-30 | 2023-11-03 | 浙江三一装备有限公司 | Engineering machinery health assessment method |
| CN112034789B (en) * | 2020-08-25 | 2021-10-15 | 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 |
| CN112116262A (en) * | 2020-09-24 | 2020-12-22 | 华能盐城大丰新能源发电有限责任公司 | Evaluation method for health degree of wind generating set equipment |
| CN113052555A (en) * | 2021-03-26 | 2021-06-29 | 浙江三一装备有限公司 | Method and system for managing loss parts |
| 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 |
| CN114204651B (en) * | 2022-01-26 | 2022-08-05 | 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 |
| 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 |
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 |
|---|
| 电网设备状态检修策略的研究;郇嘉嘉;《中国博士学位论文全文数据库 工程科技Ⅱ辑》;20121115(第11期);第12-25页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107016235A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107016235B (en) | Equipment running state health degree evaluation method based on multi-feature adaptive fusion | |
| CN108375476B (en) | Hydroelectric generating set health assessment method | |
| CN109460618B (en) | Rolling bearing residual life online prediction method and system | |
| CN106682814B (en) | Wind turbine generator fault intelligent diagnosis method based on fault knowledge base | |
| CN110907066B (en) | Wind turbine generator gearbox bearing temperature state monitoring method based on deep learning model | |
| WO2022156330A1 (en) | Fault diagnosis method for rotating device | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN111695521B (en) | Attention-LSTM-based rolling bearing performance degradation prediction method | |
| CN110926809B (en) | Big data analysis-based wind turbine generator transmission chain fault early warning method | |
| CN109492777A (en) | A kind of Wind turbines health control method based on machine learning algorithm platform | |
| CN109556863B (en) | MSPAO-VMD-based large turntable bearing weak vibration signal acquisition and processing method | |
| CN111366123A (en) | Part surface roughness and cutter wear prediction method based on multi-task learning | |
| CN111539553A (en) | Wind turbine generator fault early warning method based on SVR algorithm and skewness | |
| CN106127192A (en) | A kind of bearing remaining life Forecasting Methodology based on similarity | |
| CN111581597A (en) | Wind turbine generator gearbox bearing temperature state monitoring method based on self-organizing kernel regression model | |
| CN104794492A (en) | Online machine tool equipment machining and running state recognizing method based on power feature models | |
| CN115614292B (en) | Vibration monitoring device and method for vertical water pump unit | |
| CN111814848B (en) | Self-adaptive early warning strategy design method for temperature faults of wind turbine generator | |
| CN107103425B (en) | Intelligent energy evaluation system for power generation equipment running state computer | |
| CN106596110B (en) | The automatic analyzing and diagnosing method of turbine-generator units waterpower imbalance fault based on online data | |
| CN114169718A (en) | Method for improving reliability of wind turbine generator based on state evaluation of wind turbine generator | |
| CN108709426B (en) | Sintering machine air leakage fault online diagnosis method based on frequency spectrum characteristic bilateral detection method | |
| Lu et al. | Gear fault diagnosis and life prediction of petroleum drilling equipment based on SOM neural network | |
| CN116204825A (en) | Production line equipment fault detection method based on data driving | |
| Peng et al. | Wind turbine blades icing failure prognosis based on balanced data and improved entropy |
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 |