CN109270445A - Breaker spring operating mechanism abnormal state detection method based on LMD - Google Patents
Breaker spring operating mechanism abnormal state detection method based on LMD Download PDFInfo
- Publication number
- CN109270445A CN109270445A CN201811044333.9A CN201811044333A CN109270445A CN 109270445 A CN109270445 A CN 109270445A CN 201811044333 A CN201811044333 A CN 201811044333A CN 109270445 A CN109270445 A CN 109270445A
- Authority
- CN
- China
- Prior art keywords
- operating mechanism
- spring operating
- vibration signal
- component
- abnormal state
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/327—Testing of circuit interrupters, switches or circuit-breakers
- G01R31/3271—Testing of circuit interrupters, switches or circuit-breakers of high voltage or medium voltage devices
- G01R31/3275—Fault detection or status indication
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Arc-Extinguishing Devices That Are Switches (AREA)
Abstract
The breaker spring operating mechanism abnormal state detection method based on LMD that the invention discloses a kind of, is related to Fault Diagnosis for HV Circuit Breakers technical field.The spring operating mechanism of circuit breaker abnormal state detection method based on LMD, the vibration signal in breaker operator is obtained using IEPE piezoelectric vibration pickup, LMD and characteristic vector pickup are decomposed by local mean value, obtain the characteristic parameter of spring operating mechanism, trained supporting vector machine model is finally imported to detect breaker operation mechanism spring abnormality, the detection method can fast and accurately obtain the failure modes result of spring operating mechanism, and fault detection accuracy rate is high, it is a kind of new method for being changed using vibration signal characteristics and carrying out breaker spring running state recognition.
Description
Technical field
The invention belongs to Fault Diagnosis for HV Circuit Breakers technical fields more particularly to a kind of height based on LMD and SVM to break
Road device spring operating mechanism abnormal state detection method.
Background technique
High-voltage circuitbreaker is responsible for control action and protective effect as electric system infrastructure device, to its operation and maintenance
It is one of the major tasks for ensureing safe and stable operation of power system.Spring operating mechanism is widely used in respectively because of its unique advantage
Class breaker, energy-stored spring are the key that breaker operation commands as operating mechanism core energy storage component.Utilize installation
The vibration signal of acceleration vibrating sensor acquisition on case for circuit breaker pedestal, reflects in breaker closing action process and closes
The instantaneous variation of lock spring energy.It spring state and is abnormal with spring associated part, can cause energy stores and release
Put the variation of rule.Using switching-in spring energy storage in making process and the exergonic vibration signal of switching-in spring, it can be achieved that
High-voltage breaker spring operating mechanism abnormal state is detected.
Based on this, the present invention proposes a kind of spring operating mechanism of circuit breaker state based on the analysis of vibration signal energy feature
Detection method obtains the vibration signal in breaker operator using IEPE piezoelectric vibration pickup, decomposes by local mean value
(Local mean decomposition, LMD) and characteristic vector pickup, obtain the characteristic parameter of spring operating mechanism, finally
It is different to breaker operation mechanism spring to import trained supporting vector machine model (support vector machine, SVM)
Normal state is detected.
Summary of the invention
In view of the deficiencies of the prior art, the present invention provides a kind of breaker spring operating mechanism abnormal state based on LMD
Detection method.
The present invention is to solve above-mentioned technical problem by the following technical solutions: a kind of breaker bullet based on LMD
Spring operating mechanism abnormal state detection method, including the following steps:
Step 1: obtaining vibration signal;
Obtain high-voltage breaker spring operating mechanism vibration signal X (t) in operation;
Step 2: LMD decomposition being carried out to vibration signal, extracts feature vector;
Using LMD algorithm to vibration signal X (t) carry out Time-frequency Decomposition, by vibration signal X (t) resolve into n PF component and
The sum of one residual component;The gross energy for calculating each PF component, is normalized the gross energy of PF component, and construct
Feature vector T;
Step 3: the abnormal state detection of spring operating mechanism is carried out according to the feature vector under different conditions;
Faulty tag is carried out to the feature vector under different conditions, the feature vector in same faulty tag is divided into training
Sample and test sample, the input vector using training sample as support vector machines obtain the optimal punishment of support vector machines
Parameter c and optimal kernel functional parameter g;Input vector of the test sample as support vector machines is used again, and it is different can to obtain spring
Normal Status Type.
Further, it in the step 1, is acquired using piezoelectric vibration pickup and obtains high-voltage breaker spring operation machine
Structure vibration signal X (t) in operation.
Further, in the step 2, the mathematic(al) representation of vibration signal LMD decomposition are as follows:
Wherein, X (t) indicates vibration signal, PFi(t) indicate that a series of instantaneous frequencys have the product signal letter of physical significance
Number, uk(t) indicate that monotonic function, n indicate the number of the PF component comprising major failure information.
It is a kind of new adaptive Time-Frequency Analysis Method proposed in 2005 by Smith, phase that local mean value, which decomposes LMD,
Than the EMD algorithm proposed in 1998, end effect that LMD is generated when improving EMD decomposed signal well on its basis,
It crosses envelope, owe the problems such as envelope, the number of iterations, negative frequency.The essence of LMD algorithm is that pure frequency modulation letter is isolated from original signal
Number and envelope signal, pure FM signal, which is multiplied with envelope signal, can obtain the PF that an instantaneous frequency has physical significance
Component, envelope signal are the instantaneous amplitudes of PF component, and the instantaneous frequency of PF component is acquired using pure FM signal.
Further, in the step 2, the calculation formula of each PF component gross energy are as follows:
Ej=∫ | cj(t)|2Dt j=1,2,3 ... n
Wherein, EjIndicate the gross energy of j-th of PF component, cj(t) various discrete signal component is indicated.
It include work state information abundant and failure in the energy of each frequency content of high-voltage circuitbreaker vibration signal
Characteristic information.When breaker operation mechanism breaks down, the energy difference of same frequency inband signaling in the vibration signal of acquisition
It is larger, therefore local mean value can be selected to decompose energy as feature vector, circuit breaker failure is diagnosed.
Further, the normalized process of PF component gross energy are as follows:
Wherein, EiFor the gross energy of the PF component after normalized;E is the gross energy of vibration signal.
Further, in the step 2, the expression formula of the feature vector T of construction are as follows:
T=[E1E2…En]
Wherein, EnThe gross energy of n-th of PF component after indicating normalized.
Further, in the step 3, the kernel function of support vector machines selects radial basis function.
Further, penalty parameter c and kernel functional parameter g are optimized using mesh parameter optimizing method.
Support vector machines is built upon the learning algorithm in Statistical Learning Theory, be suitable for solve small sample, it is non-linear, when
Between sequence analysis and the problem of regression analysis etc., basic thought is the Nonlinear Mapping that is had determined by one sample
Originally be mapped in high-dimensional space, establish an optimal separating hyper plane in this space, realize classification to input sample and
Identification.
Compared with prior art, a kind of spring operating mechanism of circuit breaker state based on LMD and SVM provided by the present invention
Method for detecting abnormality obtains the vibration signal in breaker operator using IEPE piezoelectric vibration pickup, by local mean value
LMD and characteristic vector pickup are decomposed, the characteristic parameter of spring operating mechanism is obtained, finally imports trained support vector machines mould
Type detects breaker operation mechanism spring abnormality, which can fast and accurately obtain operating machine of the spring
The failure modes of structure as a result, and fault detection accuracy rate it is high, be a kind of to utilize vibration signal characteristics variation progress breaker spring
The new method of running state recognition.
Detailed description of the invention
It, below will be to attached drawing needed in embodiment description in order to illustrate more clearly of technical solution of the present invention
It is briefly described, it should be apparent that, the accompanying drawings in the following description is only one embodiment of the present of invention, general for this field
For logical technical staff, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 is normal condition and malfunction vibration signal figure in the embodiment of the present invention;
Fig. 2 is PF component map under normal condition in the embodiment of the present invention;
Fig. 3 is svm classifier result figure in the embodiment of the present invention.
Specific embodiment
With reference to the attached drawing in the embodiment of the present invention, the technical solution in the present invention is clearly and completely described,
Obviously, described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.Based in the present invention
Embodiment, those of ordinary skill in the art's every other embodiment obtained without creative labor,
It shall fall within the protection scope of the present invention.
A kind of breaker spring operating mechanism abnormal state detection method based on LMD provided by the present invention, including with
Under several steps:
Step 1: obtaining vibration signal;
It is acquired using piezoelectric vibration pickup and obtains high-voltage breaker spring operating mechanism vibration signal X in operation
(t)。
The vibration signal of breaker actuating process has with spring energy release and storing process directly to be contacted, and division can be characterized
The specific defect of lock process spring and failure, when breaker operation mechanism breaks down, same frequency in the vibration signal of acquisition
The energy difference of inband signaling is larger, therefore, can judge spring operating mechanism by carrying out feature extraction to vibration signal
Abnormal state situation.
Step 2: LMD decomposition being carried out to vibration signal, extracts feature vector;
Using LMD algorithm to vibration signal X (t) carry out Time-frequency Decomposition, by vibration signal X (t) resolve into n PF component and
One residual component ukThe sum of (t);The gross energy for calculating each PF component, is normalized the gross energy of PF component,
And construction feature vector T.
It include work state information abundant and failure in the energy of each frequency content of high-voltage circuitbreaker vibration signal
Characteristic information.When breaker operation mechanism breaks down, the energy difference of same frequency inband signaling in the vibration signal of acquisition
It is larger, therefore local mean value can be selected to decompose energy as feature vector, circuit breaker failure is diagnosed.It will be collected
Vibration signal extracts respective feature vector T using LMD algorithm respectively, then puts it into eigenvectors matrix.
The mathematic(al) representation that vibration signal LMD is decomposed are as follows:
Wherein, X (t) indicates vibration signal, PFi(t) indicate that a series of instantaneous frequencys have the product signal letter of physical significance
Number, uk(t) indicate that monotonic function, n indicate the number of the PF component comprising major failure information.
The calculation formula of each PF component gross energy are as follows:
Ej=∫ | cj(t)|2Dt j=1,2,3 ... n (2)
Wherein, EjIndicate the gross energy of j-th of PF component, cj(t) indicate various discrete signal component, to vibration signal into
After row LMD is decomposed, extracted envelope signal is discrete signal component cj(t)。
The normalized process of PF component gross energy are as follows:
Wherein, EiFor the gross energy of the PF component after normalized;E is the gross energy of vibration signal.
Using PF component normalized energy as element construction feature vector T, the expression formula of feature vector T are as follows:
T=[E1E2…En] (4)
Wherein, EnThe gross energy of n-th of PF component after indicating normalized.
Step 3: the abnormal state detection of spring operating mechanism is carried out according to the feature vector under different conditions;
Faulty tag is carried out to the feature vector under different conditions, the feature vector in same label is divided into training sample
And test sample, the input vector using training sample as support vector machines obtain optimized parameter c, g of support vector machines;
Input vector of the test sample as support vector machines is used again, obtains spring abnormality type.
Specific embodiment:
Using the ZN65-12 vacuum circuit breaker of spring-type operating mechanism as test object, simulation energy storage bullet is blocked using iron plate
Spring movement generates jam faults, and the pin generation for taking down drive rod and main shaft is refused to close failure, imitating shell that breaker spring is threaded off
Spring looseness fault.Obtain the vibration signal under 120 groups of breaker normal conditions and three kinds of failures, each 30 groups of every class signal,
Partial vibration signal (every class has chosen 2 groups of data) as shown in Figure 1, be respectively normal condition, energy-stored spring bite from top to bottom
Failure (referred to as fault-signal I), energy-stored spring are refused to close failure (fault-signal II) and energy-stored spring looseness fault (referred to as failure
Signal III).4 kinds of signals are subjected to LMD decomposition, obtain PF component and residual component.For choosing a normal signal, decompose
As a result as shown in Figure 2, it can be seen that decomposite 6 PF components and 1 residual component.PF component is calculated using formula (4) to normalize
Gross energy, it is known that signal energy concentrates on preceding 3 PF components, and it comprises the most informations of original vibration signal, while by
It will increase calculation amount in choosing multi -components, thus choose preceding 3 PF component normalized energy as feature vector.Each fault type
Partial Feature vector data as shown in table 1 (only having chosen 2 in every class signal to be included in table), vibrate by three kinds of states of extraction
Signal characteristic vector distinguishes spring abnormality type, reacts spring energy variation under different abnormalities.
The normalized energy of 1 partial vibration signal first three PF component of table
Only list in every class signal 2 in table 1 and represent the energy feature parameter of data, from table it can be seen that, every class
It there is no significantly going to distinguish between the parameter of signal, can not directly differentiate, therefore these data are imported into SVM model training pair
A few class signals are classified, to realize the condition diagnosing to spring operating mechanism of circuit breaker.
Selecting libsvm-3.22 is support vector machines analysis tool case used in this embodiment.By collected three
After 120 groups of data (being used as training set data for each 30 groups under every kind of operating status) under kind state extract characteristic value, to different shapes
Feature vector assigns faulty tag under state.Working normally is 1, and failure I is 0, and failure II is -1, and failure III is 2.By same mark
Feature vector in label is divided into two groups, respectively as training sample (20 groups) and test sample (10 groups), to state class to be measured
Type number is as shown in table 2.
The number of the Status Type to be measured of table 2
SVM model selection C-SVC in the present embodiment, kernel function select radial basis function.With training sample and corresponding failure
Label is trained SVM and seeks obtaining optimized parameter c, g.Using mesh parameter optimizing method, optimizing obtains c=0.25, g=
0.17678.Then model is substituted into 40 groups of test samples, svm classifier result figure is as shown in figure 3, contrast model calculated result
With known actual result it is found that there is 39 groups of identifications correct in 40 groups of signals, classification accuracy is up to 97.5%, generally meets disconnected
Road device spring mechanism state-detection precise requirements.From test result as can be seen that normal condition (label 1) can be distinguished completely
With abnormal condition (label 0, -1), the 12nd group of data (energy-stored spring jam faults) misjudgement is that energy-stored spring is refused to close failure, is said
Bright spring energy variation degree differentiates there is sensibility to fault type, and needs are accurately recognized for malfunction type and increase survey
Sample sheet or the PF component that higher order number is chosen when LMD is decomposed, can further improve discrimination.
The present invention proposes the spring condition discrimination new method that a kind of local mean value is decomposed and support vector machines combines, first benefit
It is decomposed with vibration signal of the local mean value algorithm to breaker, seeks the conduct of PF component normalized energy and judge breaker bullet
Spring state feature vector, then in this, as the input vector of SVM, support vector machines parameter is carried out using mesh parameter optimizing method
Optimization, more rapidly can accurately obtain spring-like failure modes result.The experimental results showed that the method energy that LMD and SVM are combined
Breaker spring abnormal state type is enough accurately identified, to realize a kind of disconnected using vibration signal characteristics variation effectively differentiation
The new method of road device spring operating status.
Above disclosed is only a specific embodiment of the invention, but scope of protection of the present invention is not limited thereto,
Anyone skilled in the art in the technical scope disclosed by the present invention, can readily occur in variation or modification,
It is covered by the protection scope of the present invention.
Claims (8)
1. a kind of high-voltage breaker spring operating mechanism abnormal state detection method based on LMD and SVM, which is characterized in that packet
Include following steps:
Step 1: obtaining vibration signal;
Obtain high-voltage breaker spring operating mechanism vibration signal X (t) in operation;
Step 2: LMD decomposition being carried out to vibration signal, extracts feature vector;
Time-frequency Decomposition is carried out to vibration signal X (t) using LMD algorithm, vibration signal X (t) is resolved into n PF component and one
The sum of residual component;The gross energy for calculating each PF component, is normalized the gross energy of PF component, and construction feature
Vector T;
Step 3: the abnormal state detection of spring operating mechanism is carried out according to the feature vector under different conditions;
Faulty tag is carried out to the feature vector under different conditions, the feature vector in same faulty tag is divided into training sample
And test sample, the input vector using training sample as support vector machines obtain the optimal penalty parameter c of support vector machines
With optimal kernel functional parameter g;Input vector of the test sample as support vector machines is used again, can obtain spring abnormality
Type.
2. high-voltage breaker spring operating mechanism abnormal state detection method as described in claim 1, which is characterized in that described
In step 1, is acquired using piezoelectric vibration pickup and obtain high-voltage breaker spring operating mechanism vibration signal X in operation
(t)。
3. high-voltage breaker spring operating mechanism abnormal state detection method as described in claim 1, which is characterized in that described
In step 2, the mathematic(al) representation of vibration signal LMD decomposition are as follows:
Wherein, X (t) indicates vibration signal, PFi(t) indicate that a series of instantaneous frequencys have the product signal function of physical significance, uk
(t) indicate that monotonic function, n indicate the number of the PF component comprising major failure information.
4. high-voltage breaker spring operating mechanism abnormal state detection method as claimed in claim 1 or 3, which is characterized in that
In the step 2, the calculation formula of each PF component gross energy are as follows:
Ej=∫ | cj(t)|2Dt j=1,2,3 ... n
Wherein, EjIndicate the gross energy of j-th of PF component, cj(t) various discrete signal component is indicated.
5. high-voltage breaker spring operating mechanism abnormal state detection method as claimed in claim 4, which is characterized in that PF points
Measure the normalized process of gross energy are as follows:
Wherein, EiFor the gross energy of the PF component after normalized;E is the gross energy of vibration signal.
6. high-voltage breaker spring operating mechanism abnormal state detection method as claimed in claim 5, which is characterized in that described
In step 2, the expression formula of the feature vector T of construction are as follows:
T=[E1E2…En]
Wherein, EnThe gross energy of n-th of PF component after indicating normalized.
7. high-voltage breaker spring operating mechanism abnormal state detection method as described in claim 1, which is characterized in that described
In step 3, the kernel function of support vector machines selects radial basis function.
8. high-voltage breaker spring operating mechanism abnormal state detection method as described in claim 1, which is characterized in that use
Mesh parameter optimizing method optimizes parameter c, g.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811044333.9A CN109270445A (en) | 2018-09-07 | 2018-09-07 | Breaker spring operating mechanism abnormal state detection method based on LMD |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811044333.9A CN109270445A (en) | 2018-09-07 | 2018-09-07 | Breaker spring operating mechanism abnormal state detection method based on LMD |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109270445A true CN109270445A (en) | 2019-01-25 |
Family
ID=65188855
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811044333.9A Pending CN109270445A (en) | 2018-09-07 | 2018-09-07 | Breaker spring operating mechanism abnormal state detection method based on LMD |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109270445A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112557966A (en) * | 2020-12-02 | 2021-03-26 | 国网江苏省电力有限公司南京供电分公司 | Transformer winding looseness identification method based on local mean decomposition and support vector machine |
CN113532893A (en) * | 2020-04-15 | 2021-10-22 | 激发认知有限公司 | Anomaly detection based on device vibration |
CN113654771A (en) * | 2021-06-30 | 2021-11-16 | 中国电力科学研究院有限公司 | Formatting method and system for vibration waveform of spring type operating mechanism |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102829974A (en) * | 2012-08-07 | 2012-12-19 | 北京交通大学 | LMD (local mean decomposition) and PCA (principal component analysis) based rolling bearing state identification method |
CN104832418A (en) * | 2015-05-07 | 2015-08-12 | 北京航空航天大学 | Hydraulic pump fault diagnosis method based on local mean conversion and Softmax |
CN105241643A (en) * | 2015-09-19 | 2016-01-13 | 东北电力大学 | High-voltage circuit breaker mechanical state monitoring method employing HS transformation and single-type support vector machine |
CN105424057A (en) * | 2015-10-30 | 2016-03-23 | 东南大学 | Fiber-optic gyroscope vibration signal analysis method based on improved LMD |
CN105973593A (en) * | 2016-04-22 | 2016-09-28 | 北京航空航天大学 | Rolling bearing health evaluation method based on local characteristic scale decomposition-approximate entropy and manifold distance |
CN107101813A (en) * | 2017-04-26 | 2017-08-29 | 河北工业大学 | A kind of frame-type circuit breaker mechanical breakdown degree assessment method based on vibration signal |
KR101773433B1 (en) * | 2016-11-29 | 2017-08-31 | (주)에너시스 | The dual-type automatic test equipment for air circuit breakers |
CN107202950A (en) * | 2017-05-12 | 2017-09-26 | 南京邮电大学 | Analog-circuit fault diagnosis method based on LMD approximate entropies and SVM |
CN107395540A (en) * | 2017-06-16 | 2017-11-24 | 南京邮电大学 | Modulation Signals Recognition method based on LMD approximate entropies, high accumulation accumulated amount and SVM |
CN107607303A (en) * | 2017-09-13 | 2018-01-19 | 河海大学 | Mechanical Failure of HV Circuit Breaker recognition methods based on wavelet packet Yu SOM networks |
-
2018
- 2018-09-07 CN CN201811044333.9A patent/CN109270445A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102829974A (en) * | 2012-08-07 | 2012-12-19 | 北京交通大学 | LMD (local mean decomposition) and PCA (principal component analysis) based rolling bearing state identification method |
CN104832418A (en) * | 2015-05-07 | 2015-08-12 | 北京航空航天大学 | Hydraulic pump fault diagnosis method based on local mean conversion and Softmax |
CN105241643A (en) * | 2015-09-19 | 2016-01-13 | 东北电力大学 | High-voltage circuit breaker mechanical state monitoring method employing HS transformation and single-type support vector machine |
CN105424057A (en) * | 2015-10-30 | 2016-03-23 | 东南大学 | Fiber-optic gyroscope vibration signal analysis method based on improved LMD |
CN105973593A (en) * | 2016-04-22 | 2016-09-28 | 北京航空航天大学 | Rolling bearing health evaluation method based on local characteristic scale decomposition-approximate entropy and manifold distance |
KR101773433B1 (en) * | 2016-11-29 | 2017-08-31 | (주)에너시스 | The dual-type automatic test equipment for air circuit breakers |
CN107101813A (en) * | 2017-04-26 | 2017-08-29 | 河北工业大学 | A kind of frame-type circuit breaker mechanical breakdown degree assessment method based on vibration signal |
CN107202950A (en) * | 2017-05-12 | 2017-09-26 | 南京邮电大学 | Analog-circuit fault diagnosis method based on LMD approximate entropies and SVM |
CN107395540A (en) * | 2017-06-16 | 2017-11-24 | 南京邮电大学 | Modulation Signals Recognition method based on LMD approximate entropies, high accumulation accumulated amount and SVM |
CN107607303A (en) * | 2017-09-13 | 2018-01-19 | 河海大学 | Mechanical Failure of HV Circuit Breaker recognition methods based on wavelet packet Yu SOM networks |
Non-Patent Citations (4)
Title |
---|
孙一航: "结合经验模态分解能量总量法的断路器振动信号特征向量提取", 《电工技术学报》 * |
孙曙光: "基于振动信号的低压万能式断路器分合闸故障程度评估方法的研究", 《中国电机工程学报》 * |
孙曙光: "基于灰色关联度的框架式断路器故障诊断方法", 《仪器仪表学报》 * |
黄辉敏: "基于LMD和SVM的高压断路器弹簧操动机构状态异常检测", 《高压电器》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113532893A (en) * | 2020-04-15 | 2021-10-22 | 激发认知有限公司 | Anomaly detection based on device vibration |
CN112557966A (en) * | 2020-12-02 | 2021-03-26 | 国网江苏省电力有限公司南京供电分公司 | Transformer winding looseness identification method based on local mean decomposition and support vector machine |
CN113654771A (en) * | 2021-06-30 | 2021-11-16 | 中国电力科学研究院有限公司 | Formatting method and system for vibration waveform of spring type operating mechanism |
CN113654771B (en) * | 2021-06-30 | 2024-05-17 | 中国电力科学研究院有限公司 | Formatting method and system for vibration waveform of spring type operating mechanism |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109270445A (en) | Breaker spring operating mechanism abnormal state detection method based on LMD | |
CN107817098A (en) | A kind of Mechanical Failure of HV Circuit Breaker diagnostic method | |
CN102944416B (en) | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades | |
CN105759201B (en) | High-voltage circuitbreaker self-diagnosing method based on exceptional sample identification | |
CN109614997A (en) | A kind of stealing Risk Forecast Method and device based on deep learning | |
CN103336243A (en) | Breaker fault diagnosis method based on separating/closing coil current signals | |
CN104081301B (en) | Monitoring of primary devices in a power system | |
CN110503004A (en) | A kind of online method of discrimination of Switching Power Supply operating status | |
CN101688892A (en) | Method and device to predict a state of a power system in the time domain | |
CN109375010A (en) | Winding in Power Transformer method for diagnosing faults based on vibration distribution characteristic model | |
CN106019138A (en) | Online diagnosis method for mechanical fault of high-voltage circuit breaker | |
CN109389325B (en) | Method for evaluating state of electronic transformer of transformer substation based on wavelet neural network | |
CN107202027A (en) | A kind of large fan operation trend analysis and failure prediction method | |
CN105137354A (en) | Motor fault detection method based on nerve network | |
CN112149569B (en) | Voiceprint fault diagnosis method of transformer based on fuzzy C-means clustering algorithm | |
CN105703258A (en) | Action state monitoring system of gas insulated switchgear (GIS) and application method of action state monitoring system | |
CN110596490A (en) | Intelligent detection method for railway turnout fault | |
CN112557966A (en) | Transformer winding looseness identification method based on local mean decomposition and support vector machine | |
CN108489717A (en) | On-load tap changers of transformers machine performance monitoring method and system | |
CN110646685A (en) | Comprehensive evaluation method for state of switch cabinet | |
CN108267687B (en) | Based on probability density and the Mechanical Failure of HV Circuit Breaker diagnostic method being locally linear embedding into | |
CN115496108A (en) | Fault monitoring method and system based on manifold learning and big data analysis | |
Zhang et al. | Vibration signal-based defect detection method for railway signal relay using parameter-optimized VMD and ensemble feature selection | |
CN108152733B (en) | Method for detecting opening and closing time in electrified mode for mechanical characteristics of high-voltage circuit breaker | |
CN107092247A (en) | A kind of packaging production line method for diagnosing faults based on status data |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190125 |