CN100470416C - Power plant thermal equipment intelligent state diagnosing and analyzing system - Google Patents
Power plant thermal equipment intelligent state diagnosing and analyzing system Download PDFInfo
- Publication number
- CN100470416C CN100470416C CNB2006101481502A CN200610148150A CN100470416C CN 100470416 C CN100470416 C CN 100470416C CN B2006101481502 A CNB2006101481502 A CN B2006101481502A CN 200610148150 A CN200610148150 A CN 200610148150A CN 100470416 C CN100470416 C CN 100470416C
- Authority
- CN
- China
- Prior art keywords
- neural network
- diagnosing
- thermal equipment
- equipment
- output
- 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.)
- Expired - Fee Related
Links
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Testing And Monitoring For Control Systems (AREA)
Abstract
The invention discloses an intelligent state diagnosing and analysis system for electric power plant heat engineering device. The feature is that it includes the state diagnosing of state monitoring, state analysis, error diagnosis, defect trend, useful life prediction, including the testing reports of immediately repairing report, mid-term checking report, long time checking report and testing determining link. It uses nerve network as tool, adopts state diagnosing based on nerve network identification module and based on nerve network fuzzy judgment. It could gain the state of device and realize state diagnosing and testing for device.
Description
Technical field
The present invention relates to a kind of Power Plant Thermal Process equipment state diagnostic system, especially a kind of intellectual status diagnostic analysis system that is used on the Power Plant Thermal Process equipment.
Background technology
The equipment state diagnostic techniques is a new subject that grows up over nearly 40 years, and it is to adapt to the industrial process actual needs and the interdisciplinary study of each subject crossing of forming.The equipment state diagnosis should be able to be in " health ", " inferior health " or " morbid state " state by discriminating device, and it is a kind of diagnostic method of full operating mode.Along with the raising of management of equipment maintenance level and the development of fault diagnosis technology, the condition diagnosing technology progresses into practicability, has worldwide also caused widely to pay attention to, and theoretical research and production practices are all deepening continuously, and what have has obtained great achievement.
Thermal power generation unit apparatus expensive, and its method of operation requires to carry out continuously with Best Economy.Along with the continuous increase of power station single-machine capacity, it is huger and complicated that its thermal process becomes, and any one Thermal Equipment fault all may directly cause enormous economic loss.At present, domestic most of electric power enterprise all proposes to implement repair based on condition of component, but what at first consider is the repair based on condition of component of main large equipment, as boiler, steam turbine and generator etc., and more considers as yet for Thermal Equipment.The author thinks, Thermal Equipment is the important component part of electric power factory equipment, in electrical production, bringing into play crucial effect, especially sensor and actuator are indispensable Thermal Equipments in the power plant, the whether normal economical operation process that is directly connected to total system of its running status is so also should realize repair based on condition of component.According to statistics, 80% control system lost efficacy and to result from the fault of sensor and actuator.Therefore, in the condition diagnosing technology of power industry promote heat construction equipment, its economic benefit and social benefit all will be huge.
Neural network has large-scale parallel, self-adaptation, self study, and non-linear mapping capability, and its plurality of advantages makes it in the control Application for Field more and more widely, and the application potential in fault diagnosis field also is very big.Neural network, equipment state diagnostic techniques are combined with Power Plant Thermal Process equipment, can scientifically obtain the state of equipment, realize equipment state diagnosis and maintenance.
Summary of the invention
The present invention will provide a kind of power plant thermal equipment intelligent state diagnosing and analyzing system, and this system combines neural network, equipment state diagnostic techniques with Power Plant Thermal Process equipment, can scientifically obtain the state of equipment, realizes equipment state diagnosis and maintenance.
For achieving the above object, the technical solution used in the present invention is:
A kind of power plant thermal equipment intelligent state diagnosing and analyzing system, with Power Plant Thermal Process equipment is object, it is characterized in that, this system is made up of status monitoring, state analysis, condition diagnosing, service bulletin, maintenance decision link, described condition diagnosing comprises fault diagnosis, defective trend, life prediction, and described service bulletin comprises immediately service bulletin, interims overhaul report, long-term service bulletin; This system is instrument with the neural network, adopts based on the condition diagnosing of neural network identification model or based on the condition diagnosing of neural network fuzzy evaluation.
Condition diagnosing system based on the neural network model identification is made up of two parts, and a part is that system model approaches device, and promptly the neural network identification model is used to provide modular system, the output when providing system's operate as normal; Another part is a diagnostic logic, is used for judging whether the difference of being approached between the device output by diagnostic system output and model surpasses preset threshold, makes the running status of system and adjudicates.The knowledge model is debated according to the off-line neural network of Thermal Equipment by this system, utilize neural network off-line modeling inline diagnosis mode that Thermal Equipment is carried out condition diagnosing, be used for diagnosing out the diagnostic result that sensor, electric actuator etc. are impacted, setovered and drift about in the Thermal Equipment.
Based on the Thermal Equipment condition diagnosing of neural network fuzzy evaluation be with the characterisitic parameter of Thermal Equipment by after the fuzzy membershipization as the input information of neural network, difference with the hamming approach degree of the output of neural network and fuzzy membership characterisitic parameter is come neural network training, when diagnosis, the characterisitic parameter of input Thermal Equipment, obtain output according to the neural network that has trained, obtain the running status of Thermal Equipment under these characterisitic parameters again according to output according to the fuzzy evaluation rule.
This system data collecting part is on the Keithley2000 digital multimeter basis of U.S. Keithley company, gather the individual features parameter of Thermal Equipment to notebook computer or industrial computer by the RS-232C serial line interface, and adopt OO program language Visual C++6.0, be used to realize data acquisition, processing and the diagnostic analysis of device parameter signal.
The present invention combines neural network, equipment state diagnostic techniques with Power Plant Thermal Process equipment, can scientifically obtain the state of equipment, realizes equipment state diagnosis and maintenance.
The present invention is an object with Power Plant Thermal Process equipment, adopts neural network method to realize its condition diagnosing, and this method has important significance for theories and practical value.
Description of drawings
Fig. 1 is a Power Plant Thermal Process equipment state diagnostic system schematic diagram of the present invention;
Fig. 2 is the condition diagnosing schematic diagram that the present invention is based on the neural network identification model;
Fig. 3 is used for the structural drawing of fuzzy evaluation neural network for the present invention.
Embodiment
The present invention is further illustrated below in conjunction with accompanying drawing and embodiment.
As shown in Figure 1, the present invention relates to two kinds of method for diagnosing status based on neural network of Power Plant Thermal Process equipment: (1) is based on the condition diagnosing of neural network identification model; (2) based on the condition diagnosing of neural network fuzzy evaluation.Condition diagnosing based on the neural network identification model is a non-linear mapping capability of utilizing neural network, make network to come nonlinear dynamic system of identification by study, make condition diagnosing by the difference of system's output and neural network prediction output is compared with a setting threshold, off-line diagnosis and inline diagnosis dual mode are arranged.Based on the condition diagnosing of neural network fuzzy evaluation be with the characterisitic parameter of Thermal Equipment by after the fuzzy membershipization as the input information of neural network, difference with the hamming approach degree of the output of neural network and fuzzy membership characterisitic parameter comes neural network training up to satisfying given error requirements, weights are preserved for doing diagnosis then and used, when diagnosis, the characterisitic parameter of input Thermal Equipment, obtain output according to the neural network that has trained, obtain the running status of Thermal Equipment under these characterisitic parameters again according to output according to the fuzzy evaluation rule.
Now respectively the embodiment of two kinds of diagnostic methods is described as follows:
(1) based on the Thermal Equipment condition diagnosing of neural network identification model
Condition diagnosing system based on the neural network model identification is made up of two parts.As shown in Figure 2, a part is that system model approaches device, and promptly the neural network identification model is used to provide modular system, the output when providing system's operate as normal; Another part is a diagnostic logic, is used for judging whether the difference of being approached between the device output by diagnostic system output and model surpasses preset threshold, makes the running status of system and adjudicates.When system was in health status, its residual error was less than the threshold value of health limit, and this residual error is only by modeling error noise and disturbance do not cause that its amplitude approaches zero; When system was in morbid state, the output residual error had departed from the threshold value of ill limit according to certain rules; If residual error is between the threshold value of two limits, then system is in sub-health state.The qualitative change of system's residual error depends on the Status Type of equipment operation, can carry out state classification and location according to its variation characteristic and corresponding decision rule.
The neural network model that system is correct can reflect the data relation between input and output in system's course of normal operation.Therefore, the output of output y of the system of operate as normal and neural network model
Between deviation e
In Ying Zaiyi the less error range, this scope can be defined as the threshold value of fault detect, is designated as d, if e〉d, it is unusual to think that then system occurs.In this method,, can only judge according to the size of e is rough to the identification of fault degree.In order to improve the robustness of detection, can adopt some as measures such as continuation check, voting logics.
The course of work: under the situation that system hardware structure is put up, operate to supporting data acquisition of the present invention and intellectual status diagnostic analysis system software, and at first carry out the data acquisition of equipment running status, gathered the back and preserved data; And select weighting coefficient filtering, arithmetic mean filtering and any one or more data filtering mode of first-order lag filtering to carry out data filtering.
When the Thermal Equipment condition diagnosing that carries out based on the neural network model identification, at first to carry out the parameter identification of neural network, at the parameter identification of system software the structure that neural network is set in the dialog box is set and (comprises the input layer number, hidden layer number and output layer number) and the neural metwork training index (comprise learning rate, factor of momentum, error target limit and maximum frequency of training etc.) etc. parameter, can carry out neural metwork training to selected training data after setting up parameter, and obtain the graph of errors that the equipment off-line neural network model is debated knowledge result and neural metwork training.Off-line neural network according to Thermal Equipment is debated the knowledge model, utilize neural network off-line modeling inline diagnosis mode that Thermal Equipment is carried out condition diagnosing, can diagnose out the diagnostic result that impacts, setovers and drift about for Thermal Equipment such as sensor, electric actuator etc.
Can several typical ill states of effective diagnosis Thermal Equipment based on the method for diagnosing status of neural network identification model, and the prediction of neural network output can recover ill signal, in real process, can temporarily drive field apparatus like this with this restoring signal.But when detecting the Thermal Equipment drifting state, the detection and the recovery of morbid state signal have certain hysteresis quality, therefore we can say that also there is certain hysteresis quality in this method for gradual situation, promptly after residual error accumulates the degree that reaches certain, pathologic condition just can be detected, at this moment, choosing of detection threshold just seems especially important.
(2) based on the Thermal Equipment condition diagnosing of neural network fuzzy evaluation
Another Thermal Equipment method for diagnosing status of the present invention is the method for diagnosing status based on the neural network fuzzy evaluation.Is that example is introduced at this with typical heat construction equipment electric actuator, specific practice is: with several characterisitic parameters (pure hysteresis, escalating rate, dead band and return difference) of electric actuator, by after the fuzzy membershipization as the input information of neural network, difference with the hamming approach degree of the output of neural network and fuzzy membership characterisitic parameter comes neural network training up to satisfying given error requirements, weights is preserved for doing diagnosis later on then and is used.When diagnosing, as long as these characterisitic parameters of input electric actuator, just can obtain an output, can obtain the running status of electric actuator under these characterisitic parameters again according to this output according to the fuzzy evaluation rule according to the neural network that has trained.
The course of work: with the electric actuator is example, with several characterisitic parameters (pure hysteresis, escalating rate, dead band and return difference) of electric actuator, by after the fuzzy membershipization as the input information of neural network.But the directly input neural network training of these input informations need be done further processing.By means of fuzzy mathematics knowledge, these sample datas are transformed into closed interval [0 with subordinate function, 1] fuzzy message variable is used as the input information of neural network, suppose the quantification input of corresponding two neural networks of each input variable here, can certainly be corresponding three, four or only corresponding one, this can determine according to the needs of actual conditions.Two fuzzy membership functions that quantize input (less than normal, bigger than normal) that define each variable are:
μ
L=exp (kx
2) and μ H=1-exp (kx
2)
X is a real variable in the above subordinate function, i.e. the characterisitic parameter of electric actuator, k are the parameter of suitably selecting.Data x after simultaneously each characterisitic parameter sample being quantized through fuzzy membership functions
1～x
8Be the neural network input information, and the hamming approach degree y after four characteristic index fuzzy membership functions quantifications be used as the teacher signal of neural network output.Like this, just can determine that neural network has 8 inputs and an output, select that for the number of hidden layer certain randomness is arranged, but generally all be to determine optimal number according to experiment repeatedly, to choose hidden layer be 5 through repeatedly testing in the present invention.Thus, can be identified for the structure of fuzzy evaluation neural network, as shown in Figure 3.This neural network structure is similar to the fuzzy BP neural network network structure, and wherein the algorithm at dotted portion adopts improved BP network algorithm, and network is input as through the data x after the fuzzy membership functions quantification
1～x
8, y is according to certain reverse gelatinization principle (being the fuzzy evaluation rule) in network output, obtains the output of three kinds of states, shows with following rule list:
It is pointed out that above fuzzy evaluation rule is that concrete judgment criteria need be determined at concrete Thermal Equipment through the resulting judgment criteria of experimental summary and expertise repeatedly.
Claims (2)
1. power plant thermal equipment intelligent state diagnosing and analyzing system, with Power Plant Thermal Process equipment is object, it is characterized in that, this system is made up of status monitoring, state analysis, condition diagnosing, service bulletin, maintenance decision link, described condition diagnosing comprises fault diagnosis, defective trend, life prediction, and described service bulletin comprises immediately service bulletin, interims overhaul report, long-term service bulletin; This system is instrument with the neural network, adopts based on the condition diagnosing of neural network identification model or based on the condition diagnosing of neural network fuzzy evaluation;
Described condition diagnosing system based on the neural network model identification is made up of two parts, and a part is that system model approaches device, and promptly the neural network identification model is used to provide modular system, the output when providing system's operate as normal; Another part is a diagnostic logic, be used for judging by diagnostic system output and model and whether approach difference between the device output above preset threshold, make the running status judgement of system, condition diagnosing based on the neural network model identification is to debate the knowledge model according to the off-line neural network of Thermal Equipment, utilize neural network off-line modeling inline diagnosis mode Thermal Equipment to be carried out condition diagnosing, the diagnostic result that is used for diagnosing sensor in the Thermal Equipment, electric actuator to impact, setover and drift about;
Described Thermal Equipment condition diagnosing based on the neural network fuzzy evaluation be with the characterisitic parameter of Thermal Equipment by after the fuzzy membershipization as the input information of neural network, difference with the hamming approach degree of the output of neural network and fuzzy membership characterisitic parameter is come neural network training, when diagnosis, the characterisitic parameter of input Thermal Equipment, obtain output according to the neural network that has trained, obtain the running status of Thermal Equipment under these characterisitic parameters again according to output according to the fuzzy evaluation rule.
2. power plant thermal equipment intelligent state diagnosing and analyzing system according to claim 1, its feature also is, this system data collecting part is on the Keithley2000 digital multimeter basis of U.S. Keithley company, gather the individual features parameter of Thermal Equipment to notebook computer or industrial computer by the RS-232C serial line interface, and adopt OO program language Visual C++6.0, be used to realize data acquisition, processing and the diagnostic analysis of device parameter signal.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101481502A CN100470416C (en) | 2006-12-28 | 2006-12-28 | Power plant thermal equipment intelligent state diagnosing and analyzing system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2006101481502A CN100470416C (en) | 2006-12-28 | 2006-12-28 | Power plant thermal equipment intelligent state diagnosing and analyzing system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101025618A CN101025618A (en) | 2007-08-29 |
| CN100470416C true CN100470416C (en) | 2009-03-18 |
Family
ID=38743972
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2006101481502A Expired - Fee Related CN100470416C (en) | 2006-12-28 | 2006-12-28 | Power plant thermal equipment intelligent state diagnosing and analyzing system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100470416C (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI639907B (en) * | 2017-06-06 | 2018-11-01 | 國立彰化師範大學 | Tool machine residual service life prediction system and method thereof |
| TWI671607B (en) * | 2018-08-07 | 2019-09-11 | 英業達股份有限公司 | Light signal controlling and managing system for tower-shaped indicator light of manufacturing equipment and method thereof |
Families Citing this family (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101540009B (en) * | 2008-03-17 | 2011-11-16 | 大叶大学 | Method for predicting facility and equipment failure |
| CN101556168B (en) * | 2008-04-11 | 2012-05-09 | 株式会社东芝 | Equipment operating data monitoring device |
| CN101436264B (en) * | 2008-11-28 | 2012-05-09 | 北京交通大学 | Mine downhole debris flow prediction method based on subsection fuzzy BP neural network |
| CN101763580A (en) * | 2009-09-17 | 2010-06-30 | 宁波北电源兴电力工程有限公司 | Equipment state overhaul management module for EAM system of power plant |
| CN102495549B (en) * | 2011-11-22 | 2013-08-07 | 中联重科股份有限公司 | Remote maintenance decision system and method for engineering machinery |
| CN102799176A (en) * | 2012-08-20 | 2012-11-28 | 上海理工大学 | Fault diagnosis method for nonlinear time-delay discrete system based on fuzzy theory |
| CN104154531B (en) * | 2014-07-28 | 2016-06-22 | 广州市恒力安全检测技术有限公司 | A kind of Properties of CFB efficiency optimization method and system |
| CN104731083B (en) * | 2015-02-03 | 2017-06-20 | 浙江大学 | A kind of industrial method for diagnosing faults and application based on self-adaptive feature extraction |
| CN104732276B (en) * | 2015-03-18 | 2017-09-15 | 国家电网公司 | One kind metering production facility on-line fault diagnosis method |
| CN105911976B (en) * | 2016-04-18 | 2018-09-07 | 中国神华能源股份有限公司 | A kind of thermal power plant's automatic fault analysis device, method and system |
| JP6834446B2 (en) * | 2016-12-14 | 2021-02-24 | オムロン株式会社 | Control system, control program and control method |
| CN107505922B (en) * | 2017-08-23 | 2019-11-29 | 北京赛普泰克技术有限公司 | Factory's early warning implementation method, apparatus and system |
| CN109087013A (en) * | 2018-08-13 | 2018-12-25 | 北京必可测科技股份有限公司 | A kind of facility diagnosis method and system based on technical supervision data |
| EP3877857A4 (en) | 2018-11-07 | 2022-06-22 | Hewlett-Packard Development Company, L.P. | Receiving thermal data and producing system thermal grades |
| CN109540057B (en) * | 2018-11-16 | 2021-03-16 | 上海发电设备成套设计研究院有限责任公司 | System and method for online evaluation of defects of high-temperature pressure-bearing component of steam turbine |
| CN111487950B (en) * | 2020-04-24 | 2021-11-16 | 西安交通大学 | 'prediction-verification-feedback-optimization' closed-loop system for online early warning and offline diagnosis |
| CN115828699B (en) * | 2022-12-19 | 2023-07-21 | 华中科技大学 | Method, system and terminal for predicting full life cycle junction temperature of power semiconductor module |
| CN116027673B (en) * | 2023-03-29 | 2023-06-06 | 中国电子科技集团公司第二十九研究所 | Equipment control autonomous decision-making method based on fuzzy neural network |
| CN117851951B (en) * | 2024-01-16 | 2024-08-02 | 广州美保科技有限公司 | Safety data safety wind control platform and control method thereof |
-
2006
- 2006-12-28 CN CNB2006101481502A patent/CN100470416C/en not_active Expired - Fee Related
Non-Patent Citations (2)
| Title |
|---|
| 模糊与神经网络相结合的控制方法. 彭道刚，韩璞，于希宁，杨平.华北电力大学学报，第30卷第1期. 2003 * |
| 用VC++6.0实现工控机与数字万用表的串行通信. 杨平，彭道刚，张世玺，李志斌.计算机应用，第23卷. 2003 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI639907B (en) * | 2017-06-06 | 2018-11-01 | 國立彰化師範大學 | Tool machine residual service life prediction system and method thereof |
| TWI671607B (en) * | 2018-08-07 | 2019-09-11 | 英業達股份有限公司 | Light signal controlling and managing system for tower-shaped indicator light of manufacturing equipment and method thereof |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101025618A (en) | 2007-08-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100470416C (en) | Power plant thermal equipment intelligent state diagnosing and analyzing system | |
| CN104992270B (en) | Power transmission and transformation equipment state overhauling aid decision-making system and method | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN102411106B (en) | Fault monitoring method and device for power transformer | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| CN103711645B (en) | Based on the wind power generating set state evaluating method of modeling parameters signature analysis | |
| CN110320892A (en) | The sewage disposal device fault diagnosis system and method returned based on Lasso | |
| CN105160489A (en) | Variable-weight hydropower unit deterioration evaluation system and evaluation method | |
| CN114519923B (en) | Intelligent diagnosis and early warning method and system for power plant | |
| CN110636066B (en) | Network security threat situation assessment method based on unsupervised generative reasoning | |
| CN107291830A (en) | A kind of creation method of equipment knowledge base | |
| CN106199174A (en) | Extruder energy consumption predicting abnormality method based on transfer learning | |
| CN109492790A (en) | Wind turbines health control method based on neural network and data mining | |
| CN109740727A (en) | A kind of hydraulic turbine shaft state monitoring method neural network based and system | |
| CN111122811A (en) | Sewage treatment process fault monitoring method of OICA and RNN fusion model | |
| CN113339204A (en) | Wind driven generator fault identification method based on hybrid neural network | |
| Dong et al. | Review of research on intelligent diagnosis of oil transfer pump malfunction | |
| CN117993562A (en) | Wind turbine generator system fault prediction method and system based on artificial intelligent big data analysis | |
| KR20220089853A (en) | Method for Failure prediction and prognostics and health management of renewable energy generation facilities using machine learning technology | |
| CN105741184A (en) | Transformer state evaluation method and apparatus | |
| CN112287586A (en) | Rapid reliability assessment method based on medium and small bridge damage identification result | |
| CN106844861A (en) | Orthotropic Steel Bridge Deck welding node measured stress width dynamic probability modeling method | |
| CN114320773B (en) | Wind turbine generator system fault early warning method based on power curve analysis and neural network | |
| CN114219206B (en) | Gray-level-analysis-based comprehensive evaluation method for oil system state of pumped storage unit | |
| CN108071562B (en) | Wind turbine generator energy efficiency state diagnosis method based on energy flow |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20070829 Assignee: CPI POWER ENGINEERING CO., LTD. Assignor: Shanghai University of Electric Power Contract record no.: 2013330000240 Denomination of invention: Power plant thermal equipment intelligent state diagnosing and analyzing system Granted publication date: 20090318 License type: Exclusive License Record date: 20130716 |
|
| LICC | Enforcement, change and cancellation of record of contracts on the licence for exploitation of a patent or utility model | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090318 Termination date: 20151228 |
|
| EXPY | Termination of patent right or utility model |