CN105652120A - Power transformer fault detection method and detection system - Google Patents
Power transformer fault detection method and detection system Download PDFInfo
- Publication number
- CN105652120A CN105652120A CN201511031000.9A CN201511031000A CN105652120A CN 105652120 A CN105652120 A CN 105652120A CN 201511031000 A CN201511031000 A CN 201511031000A CN 105652120 A CN105652120 A CN 105652120A
- Authority
- CN
- China
- Prior art keywords
- power transformer
- expert
- transformer
- storage device
- decision
- 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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Protection Of Transformers (AREA)
Abstract
The invention discloses a power transformer fault detection method and detection system. The power transformer fault detection method comprises the following steps: collecting information about operation statuses of multiple aspects of the power transformer using a plurality of sensors; establishing a transformer status database according to the collected information and in combination with transformer related parameter; establishing an expert database of a fault detection related field of the power transformer; retrieving the data in the transformer status database, obtaining abnormal parameter data through computation, and computing a decision vector R; feeding back the decision vector R obtained in above step to an upper machine. The power transformer fault detection method disclosed by the invention can fast and accurately give out the performance evaluation of the operation status of the transformer, thereby guaranteeing long-term, safe and reliable operation of the equipment system. The power transformer detection system disclosed by the invention is capable of continuously monitoring the operation status of the transformer in off-line or online manner, thereby guaranteeing the long-term, safe and reliable operation of the equipment system.
Description
Technical field
The present invention is about a kind of Power Transformer Faults detection method and power transformer detection system.
Background technology
The direction that the power system of China is interconnecting to super (spy) high pressure, Large Copacity, the whole nation strides forward, and scale is still in continuous expansion, and quantity and the capacity of transformator promote further. Under overall background so, the requirement for generating, power supply and safe distribution of electric power is also more and more higher. Transformator is one of electrical equipment most important and valuable in power system, the whether safe safety and stability being directly connected to whole power system of its running status.
For a long time, China's power system maintenance of electrical equipment strategy mainly adopt with the time be standard periodic maintenance, scheduled overhaul system undoubtedly fault diagnosis, prevent equipment breakdown occur, ensure power supply safely and reliably in play good effect. But its tool bears the character of much blindness and mandatory, often result in the excessive maintenance of equipment, waste substantial amounts of manpower and materials.
Comparing with repair method traditional, off-line, on-line monitoring equipment is not also highly developed and perfect, and its running environment is poor. Result is affected again by the reliability of equipment self and the accuracy rate of fault diagnosis. Owing to the failure cause complexity of power transformer is various, only it is difficult to meet fault diagnosis requirement by single method for diagnosing faults. The conventional fault diagnosis method of various maturations is combined by shortage, or takes into account the comprehensive diagnos method of each diagnostic method advantage as far as possible.
Owing to power transformer is present in the factor of " artificially " in the process run, so inevitably there is the delay issue of malfunction, previous failure predication technology can not synchronize with practical situation.
Owing to the relation between phenomenon of the failure, position and reason may often be such that complexity, and each equipment has it specific and information instruction ability of limitation, thus how numerous imperfect informations are carried out comprehensive, integrated come failure judgement, reaching information fusion in some cases, be failure predication technical research difficult point and emphasis.
For the problems referred to above, the present inventor devises a kind of Power Transformer Faults detection method and detection system, its above-mentioned detection method and detection system adjustable high fault diagnosis speed and diagnosis accurateness, reduces the waste of manpower and materials.
Summary of the invention
In view of this, an object of the present invention is to provide a kind of Power Transformer Faults detection method, the method can provide the performance evaluation of the running status of transformator rapidly and accurately, provides foundation for equipment control, diagnosis and maintenance, thus support equipment system long-term safety is reliably run.
The present invention reaches above-mentioned technical purpose by techniques below means:
The Power Transformer Faults detection method of the present invention, comprises the following steps:
Multiple sensors is adopted to gather the information of power transformer many aspects running status;
Transformer state data base is set up according to the information gathered and in conjunction with transformator relevant parameter;
Setting up the expert database of Power Transformer Faults detection association area, in described expert database, storage has each fault type judged result that each domain expert provides according to oneself experience and preference;
Transferring the data in transformer state data base, obtain anomaly parameter data by calculating, the anomaly parameter data that the fault type judged result analysis provided in conjunction with domain expert each in expert database obtains are thus calculating decision vector R;
The decision vector R that above-mentioned steps obtains is fed back to host computer, and the failture evacuation of power transformer is carried out the distribution of manpower and materials by host computer according to decision vector R.
Further, described decision vector R, meet below equation:
Above-mentioned middle PiFor the coarse ordering vector of likelihood of failure that each domain expert provides, described PiDraw according to following methods: arranging fault type number is m, then each domain expert is to each likelihood of failure assignment respectivelyThere is the relative value of probability in its value representing fault. If the probability of certain 2 fault is the same, thereby increases and it is possible to property assignment should beThen to this fault assignmentBy that analogy. The coarse ordering vector of likelihood of failure that each domain expert provides can be obtained: P according to whichi={ Pi1,Pi2,...,Pim}��
Further, each fault type judged result that in described expert database, each domain expert of storage provides according to oneself experience and preference has different weight coefficientsFor the weight coefficient of each fault type judged result that the i-th expert experience according to oneself and preference provide, described weight coefficientMeet below equation:
In above formula, �� is expert's significance level coefficient in decision ranking module, ��iI-th expert is to the significance level coefficient in decision ranking module, and n is the history testing time of likelihood of failure sequence.
Further, described expert significance level coefficient �� in decision ranking module meets below equation:
��=(��1,��2,...,��n)
Wherein the expert is to the significance level coefficient �� in decision ranking moduleiMeet below equation:
Wherein, n is the history testing time of likelihood of failure sequence.
The two of the purpose of the present invention are to provide a kind of power transformer detection system, and the running status of transformator can be carried out the monitoring of off-line or on-line uninterruption by this power transformer detection system, thus support equipment system long-term safety is reliably run.
The present invention reaches above-mentioned technical purpose by techniques below means:
The power transformer detection system of the present invention, including:
Multiple sensing devices, for gathering the information of power transformer many aspects running status;
Transformer state data storage device, for storing information and the transformator relevant parameter that sensing device gathers, sets up transformer state data base;
Expert data storage device, for storing each fault type judged result data that each domain expert provides according to oneself experience and preference;
Symptoms abstraction device, it is connected with the plurality of sensing device, transformer state data storage device and expert data storage device respectively, for reading and the data of storage in calculating transformer status data storage device and expert data storage device, and obtain anomaly parameter data by calculating;
Power Transformer Faults analytical equipment, is connected with described symptoms abstraction device, and the anomaly parameter data that the fault type judged result analysis for providing in conjunction with domain expert each in expert database obtains are thus calculating decision vector R;
Host computer, it is connected with described Power Transformer Faults analytical equipment, the data that reception is transmitted, and gets rid of the fault of power transformer according to acquired results, and it includes display unit and processor.
Further, also including pattern recognition device, described pattern recognition device is connected with described symptoms abstraction device, transformer state data storage device, expert data storage device, Power Transformer Faults analytical equipment and host computer respectively.
Further, the plurality of sensing device includes high-voltage operation voltage sensor, high voltage load current sensor, high pressure end shield current sensor, high pressure neutral point current sensor, middle pressure working voltage sensor, middle pressure load current sensor, middle pressure end shield current sensor, middle pressure neutral point current sensor, vibrating sensor, temperature sensor.
Beneficial effects of the present invention:
1, the Power Transformer Faults detection method of the present invention, has the advantages that
1) Monitoring Data of power transformer can be transferred to decision center with monitoring network, when breaking down, each domain expert provides the probability ranking results of each fault type according to oneself experience and preference, the method can draw final ranking results according to said method, and then facilitates decision-maker to carry out the distribution of manpower and materials.
2) result drawn according to the method, the combination property of system is drawn evaluation, if performance and physical presence difference, revise the relevant parameter in the method, otherwise show that parameter is suitable for, it is possible to continue Monitoring Power Transformer relevant parameter and provide foundation for decision-making, with Comparison between detecting methods traditional, off-line, the method is applicable to on-line monitoring system, improves the reliability of equipment and the accuracy rate of fault diagnosis.
3) method of the present invention is knowledge and the experience of comprehensive multi-field expert, solves, because the fault type complexity of power transformer is various, only to be difficult to meet the shortcoming that fault diagnosis requires by single method for diagnosing faults.
4) can adopt appropriate measures according to the result of decision and avoid or reduce economy owing to incipient fault is likely to result in and social loss, change preventive maintenance is condition maintenarnce, it is to avoid unnecessary maintenance, reaches the purpose shot the arrow at the target.
5) each monitoring equipment has it specific and the information knowledge ability of limitation, this method numerous imperfect informations can be carried out comprehensive, integrated come failure judgement, reach the effect of information fusion.
6) decrease scheduled overhaul, overcome its blindness and enforceable shortcoming, saved substantial amounts of manpower and materials, it is to avoid the damage of the other side in maintenance process, transformator caused.
2, the running status of transformator can be carried out the monitoring of off-line or on-line uninterruption by the power transformer detection system of the present invention, thus support equipment system long-term safety is reliably run.
Accompanying drawing explanation
Below in conjunction with drawings and Examples, the invention will be further described.
Fig. 1 is the network model figure of Power Transformer Faults detection method of the present invention in embodiment 1;
Fig. 2 is the connection diagram of Power Transformer Faults of the present invention detection system in embodiment 2.
Detailed description of the invention
Below with reference to accompanying drawing, the present invention is described in detail:
1 one kinds of Power Transformer Faults detection methods of embodiment
As it is shown in figure 1, the Power Transformer Faults detection method of the present invention, comprise the following steps:
Multiple sensors is adopted to gather the information of power transformer many aspects running status;
Transformer state data base is set up according to the information gathered and in conjunction with transformator relevant parameter;
Setting up the expert database of Power Transformer Faults detection association area, in described expert database, storage has each fault type judged result that each domain expert provides according to oneself experience and preference;
Transferring the data in transformer state data base, obtain anomaly parameter data by calculating, the anomaly parameter data that the fault type judged result analysis provided in conjunction with domain expert each in expert database obtains are thus calculating decision vector R;
The decision vector R that above-mentioned steps obtains is fed back to host computer, and the failture evacuation of power transformer is carried out the distribution of manpower and materials by host computer according to decision vector R.
When power transformer operation exception, different domain experts may provide different fault type probability sizes according to same anomaly parameter. The judged result of each field expert knowledge base has different weight coefficientsThe result that specialist system is passed judgment on directly influences the manpower and materials distribution in Power Transformer Faults exclusion process, and for meeting decision requirements, its Comprehensive Evaluation result is only final decision reference frame, is referred to as decision vector R, andThis is expertise attribute knowledge importance degree method for diagnosing faults core concept in actual applications.
Model parameter structure algorithm is analyzed: in order to ensure the method concordance in actual use, the probability assignment of fault type is set as follows rule: if fault type number is m, then each domain expert is to each likelihood of failure assignment respectivelyThere is the relative value of probability in its value representing fault. If the probability of certain 2 fault is the same, thereby increases and it is possible to property assignment should beThen to this fault assignmentBy that analogy. The coarse ordering vector P of likelihood of failure that each domain expert provides can be obtained according to this rulei={ Pi1,Pi2,...,Pim}��
Field expert knowledge base Attribute Significance defining method: owing to each domain expert is different to familiarity and the preferred way in respective field, the result of the coarse sequence therefore provided can be inconsistent, complete final decision ranking module, it is necessary for first establishing the weight coefficient of each domain expert, defines i-th expert for this significance level coefficient of decision ranking module is as follows:
In formula: niThe number of times of actual ranking results is met in an experiment for i-th domain expert; N is the history testing time of likelihood of failure sequence, and this can be obtained by test data and historical data. By above formula it can be seen that multi-field expert importance degree coefficient in decision system
��=(��1,��2,...,��n)
From test data analysis, i-th domain expert is at the accurately number n of history experimental resultiExist such as lower inequality:
There is coupling phenomenon, therefore adopt such as drag to carry out decoupling computing in the process determine weight factor:
So far, field expert knowledge base Attribute Significance is determined.
The Monitoring Data of power transformer can be transferred to decision center with monitoring network, when breaking down, each domain expert provides the probability ranking results of each fault type according to oneself experience and preference, the method can draw final ranking results according to said method, and then facilitates decision-maker to carry out the distribution of manpower and materials.
Embodiment 2 power transformer detection system
As in figure 2 it is shown, the power transformer detection system of the present invention, including:
Multiple sensing devices 10, for gathering the information of power transformer many aspects running status, the plurality of sensing device includes high-voltage operation voltage sensor, high voltage load current sensor, high pressure end shield current sensor, high pressure neutral point current sensor, middle pressure working voltage sensor, middle pressure load current sensor, middle pressure end shield current sensor, middle pressure neutral point current sensor, vibrating sensor, temperature sensor, high pressure and the operating on low voltage signal of power transformer is gathered by high-voltage signal collecting unit and middle pressure signal gathering unit, power transformer vibration and tank temperature data are gathered respectively by vibrating sensor and temperature sensor, thus providing Power Transformer in Field run signal for Power Transformer Faults analytical equipment, transformer state data storage device 20, for storing information and the transformator relevant parameter that sensing device gathers, sets up transformer state data base,Expert data storage device 30, for storing each fault type judged result data that each domain expert provides according to oneself experience and preference, symptoms abstraction device 40, it is connected with the plurality of sensing device, transformer state data storage device and expert data storage device respectively, symptoms abstraction device 40 is internally provided with microprocessor, can be used for reading and the data of storage in calculating transformer status data storage device and expert data storage device, and obtain anomaly parameter data by calculating, Power Transformer Faults analytical equipment 50, it is connected with described symptoms abstraction device, the anomaly parameter data obtained for the fault type judged result analysis that provides in conjunction with domain expert each in expert database are thus calculating decision vector R, and Power Transformer Faults analytical equipment specifically can be made up of microprocessor or MCU, host computer 60, it is connected with described Power Transformer Faults analytical equipment, the data that reception is transmitted, and the fault of power transformer is got rid of according to acquired results, it includes display unit and processor, and host computer is used for forming control centre, for receiving and dispatching control instruction and instructing the eliminating of fault, also include pattern recognition device 70, described pattern recognition device 70 respectively with described symptoms abstraction device 40, transformer state data storage device 20, expert data storage device 30, Power Transformer Faults analytical equipment 50 and host computer 60 connect, pattern recognition device 70 can accept from transformer state data storage device 20 respectively, expert data storage device 30, the information of Power Transformer Faults analytical equipment 50 and host computer 30 or control instruction, reach comprehensive analysis, process requirement and the purpose of data, specific address, pattern recognition device internal circuit can integrated microprocessor, memorizer and multiple data-interface.
Further improvement as technique scheme, rule generator 80 also can be set, described rule generator 80 is connected with Power Transformer Faults analytical equipment and pattern recognition device respectively, described rule generator includes Signal-regulated kinase, A/D convertor circuit, DSP signal processing module, Chip Microprocessor Temperature signal processing unit etc., and rule generator can perform following control: 1) by Signal-regulated kinase, the power transformer working signal of high-voltage signal collecting unit, the output of middle pressure signal gathering unit is carried out shaping, filtering and signal condition; 2) signal vibrating sensor and temperature sensor exported by A/D convertor circuit, Chip Microprocessor Temperature signal processing unit carries out patten transformation; 3) parameters such as operational factor virtual value, power factor calculating, harmonic wave, voltage transient value are calculated by DSP signal processing module. The testing result of electricity transformer monitoring device can be drawn by said method efficiently, solution can be provided the very first time simultaneously, and then facilitate decision-maker to carry out the distribution of manpower and materials.
What finally illustrate is, above example is only in order to illustrate technical scheme and unrestricted, although the present invention being described in detail with reference to preferred embodiment, it will be understood by those within the art that, technical scheme can be modified or equivalent replacement, without deviating from objective and the scope of technical solution of the present invention, it all should be encompassed in the middle of scope of the presently claimed invention.
Claims (7)
1. a Power Transformer Faults detection method, comprises the following steps:
Multiple sensors is adopted to gather the information of power transformer many aspects running status;
Transformer state data base is set up according to the information gathered and in conjunction with transformator relevant parameter;
Setting up the expert database of Power Transformer Faults detection association area, in described expert database, storage has each fault type judged result that each domain expert provides according to oneself experience and preference;
Transferring the data in transformer state data base, obtain anomaly parameter data by calculating, the anomaly parameter data that the fault type judged result analysis provided in conjunction with domain expert each in expert database obtains are thus calculating decision vector R;
The decision vector R that above-mentioned steps obtains is fed back to host computer, and the failture evacuation of power transformer is carried out the distribution of manpower and materials by host computer according to decision vector R.
2. Power Transformer Faults detection method according to claim 1, it is characterised in that: described decision vector R, meet below equation:
Above-mentioned middle PiFor the coarse ordering vector of likelihood of failure that each domain expert provides, described PiDraw according to following methods: arranging fault type number is m, then each domain expert is to each likelihood of failure assignment respectivelyThere is the relative value of probability in its value representing fault. If the probability of certain 2 fault is the same, thereby increases and it is possible to property assignment should beThen to this fault assignmentBy that analogy. The coarse ordering vector of likelihood of failure that each domain expert provides can be obtained: P according to whichi={ Pi1,Pi2,...,Pim}��
3. Power Transformer Faults detection method according to claim 2, it is characterised in that: each fault type judged result that in described expert database, each domain expert of storage provides according to oneself experience and preference has different weight coefficients For the weight coefficient of each fault type judged result that the i-th expert experience according to oneself and preference provide, described weight coefficientMeet below equation:
In above formula, �� is expert's significance level coefficient in decision ranking module, ��iI-th expert is to the significance level coefficient in decision ranking module, and n is the history testing time of likelihood of failure sequence.
4. Power Transformer Faults detection method according to claim 3, it is characterised in that: described expert significance level coefficient �� in decision ranking module meets below equation:
��=(��1,��2,...,��n)
Wherein the expert is to the significance level coefficient �� in decision ranking moduleiMeet below equation:
Wherein, n is the history testing time of likelihood of failure sequence.
5. a power transformer detection system, it is characterised in that: include,
Multiple sensing devices, for gathering the information of power transformer many aspects running status;
Transformer state data storage device, for storing information and the transformator relevant parameter that sensing device gathers, sets up transformer state data base;
Expert data storage device, for storing each fault type judged result data that each domain expert provides according to oneself experience and preference;
Symptoms abstraction device, it is connected with the plurality of sensing device, transformer state data storage device and expert data storage device respectively, for reading and the data of storage in calculating transformer status data storage device and expert data storage device, and obtain anomaly parameter data by calculating;
Power Transformer Faults analytical equipment, is connected with described symptoms abstraction device, and the anomaly parameter data that the fault type judged result analysis for providing in conjunction with domain expert each in expert database obtains are thus calculating decision vector;
Host computer, it is connected with described Power Transformer Faults analytical equipment, the data that reception is transmitted, and gets rid of the fault of power transformer according to acquired results, and it includes display unit and processor.
6. power transformer according to claim 5 detection system, it is characterized in that: also include pattern recognition device, described pattern recognition device is connected with described symptoms abstraction device, transformer state data storage device, expert data storage device, Power Transformer Faults analytical equipment and host computer respectively.
7. power transformer according to claim 6 detection system, it is characterised in that: the plurality of sensing device includes high-voltage operation voltage sensor, high voltage load current sensor, high pressure end shield current sensor, high pressure neutral point current sensor, middle pressure working voltage sensor, middle pressure load current sensor, middle pressure end shield current sensor, middle pressure neutral point current sensor, vibrating sensor, temperature sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511031000.9A CN105652120A (en) | 2015-12-31 | 2015-12-31 | Power transformer fault detection method and detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201511031000.9A CN105652120A (en) | 2015-12-31 | 2015-12-31 | Power transformer fault detection method and detection system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105652120A true CN105652120A (en) | 2016-06-08 |
Family
ID=56491444
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201511031000.9A Pending CN105652120A (en) | 2015-12-31 | 2015-12-31 | Power transformer fault detection method and detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105652120A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106646096A (en) * | 2016-11-15 | 2017-05-10 | 国网四川省电力公司广安供电公司 | Transformer fault classification and identification method based on vibration analysis method |
| CN107392324A (en) * | 2017-07-03 | 2017-11-24 | 山东电力设备有限公司 | The specialized maintenance total management system of transformer |
| CN111693794A (en) * | 2019-03-12 | 2020-09-22 | 株式会社日立制作所 | Abnormality detection device and abnormality detection method |
| CN112017793A (en) * | 2020-08-28 | 2020-12-01 | 中国科学院合肥物质科学研究院 | Molecular pump maintenance decision management system and method for fusion device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050096874A1 (en) * | 2003-10-31 | 2005-05-05 | Smiley Karen J. | Transformer testing |
| CN102221651A (en) * | 2011-03-11 | 2011-10-19 | 太原理工大学 | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine |
| CN104267270A (en) * | 2014-08-06 | 2015-01-07 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Transformer key parameter extraction method based on vector similarity |
| CN104316803A (en) * | 2014-11-04 | 2015-01-28 | 国家电网公司 | Power transformer state evaluation method and system based on electriferous detection |
-
2015
- 2015-12-31 CN CN201511031000.9A patent/CN105652120A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20050096874A1 (en) * | 2003-10-31 | 2005-05-05 | Smiley Karen J. | Transformer testing |
| CN102221651A (en) * | 2011-03-11 | 2011-10-19 | 太原理工大学 | Fault on-line diagnosis and early warning method of flameproof dry-type transformer for mine |
| CN104267270A (en) * | 2014-08-06 | 2015-01-07 | 中国南方电网有限责任公司超高压输电公司检修试验中心 | Transformer key parameter extraction method based on vector similarity |
| CN104316803A (en) * | 2014-11-04 | 2015-01-28 | 国家电网公司 | Power transformer state evaluation method and system based on electriferous detection |
Non-Patent Citations (2)
| Title |
|---|
| 刘守明 等: "基于知识库的电力变压器故障诊断专家系统", 《计算机测量与控制》 * |
| 黄大荣 等: "基于专家知识属性重要度的集群目标威胁评估方法", 《兵工学报》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106646096A (en) * | 2016-11-15 | 2017-05-10 | 国网四川省电力公司广安供电公司 | Transformer fault classification and identification method based on vibration analysis method |
| CN106646096B (en) * | 2016-11-15 | 2019-07-02 | 国网四川省电力公司广安供电公司 | Transformer fault classification and recognition methods based on vibration analysis method |
| CN107392324A (en) * | 2017-07-03 | 2017-11-24 | 山东电力设备有限公司 | The specialized maintenance total management system of transformer |
| CN111693794A (en) * | 2019-03-12 | 2020-09-22 | 株式会社日立制作所 | Abnormality detection device and abnormality detection method |
| CN111693794B (en) * | 2019-03-12 | 2022-08-30 | 株式会社日立制作所 | Abnormality detection device and abnormality detection method |
| CN112017793A (en) * | 2020-08-28 | 2020-12-01 | 中国科学院合肥物质科学研究院 | Molecular pump maintenance decision management system and method for fusion device |
| CN112017793B (en) * | 2020-08-28 | 2021-09-03 | 中国科学院合肥物质科学研究院 | Molecular pump maintenance decision management system and method for fusion device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | A hybrid forecasting method for wind power ramp based on orthogonal test and support vector machine (OT-SVM) | |
| CN106199305B (en) | Underground coal mine power supply system dry-type transformer insulation health state evaluation method | |
| CN104503399B (en) | The regimental Wind turbines status monitoring of one kind collection and fault diagnosis platform | |
| CN108320043B (en) | Power distribution network equipment state diagnosis and prediction method based on electric power big data | |
| CN105787584B (en) | Wind turbine group fault early warning method based on cloud platform | |
| CN108336725A (en) | The management of dispatching of power netwoks monitoring of tools and intelligent analysis system | |
| Khalili et al. | Optimal instantaneous prediction of voltage instability due to transient faults in power networks taking into account the dynamic effect of generators | |
| CN101799674B (en) | Method for analyzing service state of numerical control equipment | |
| CN105652120A (en) | Power transformer fault detection method and detection system | |
| CN110135064B (en) | Method, system and controller for predicting temperature faults of rear bearing of generator | |
| CN112700032A (en) | Fault prediction system and method for low-voltage direct-current power distribution and utilization system | |
| CN107807860B (en) | Power failure analysis method and system based on matrix decomposition | |
| Hu et al. | Hierarchical fault diagnosis for power systems based on equivalent-input-disturbance approach | |
| CN115614292A (en) | Vibration monitoring device and method for vertical water pump unit | |
| Yao et al. | Fault identification of lithium-ion battery pack for electric vehicle based on ga optimized ELM neural network | |
| CN117057785A (en) | Power equipment operation and maintenance scheduling method, system, electronic equipment and storage medium | |
| CN111062569A (en) | Low-current fault discrimination method based on BP neural network | |
| CN104484828A (en) | High-voltage electrical appliance operation quality evaluation method and system based on logistic regression | |
| CN115878992A (en) | Monitoring method and monitoring system for comprehensive pipe rack power supply system | |
| CN117556238A (en) | Power equipment inspection method and system based on fault prediction | |
| CN104598969A (en) | High-voltage electrical appliance operation quality evaluation method and system based on neural network | |
| CN205263234U (en) | Power transformer monitoring devices | |
| Moreira et al. | Evaluation of pattern recognition algorithms for applications on power factor compensation | |
| CN105976127A (en) | Risk evaluation method and apparatus for integrated electric propulsion system | |
| Zhang et al. | Distributed Architecture of Power Grid Asset Management and Future Research Directions |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into 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: 20160608 |