CN110245391A - A method of based on artificial neural network with the Hardness Prediction service life - Google Patents
A method of based on artificial neural network with the Hardness Prediction service life Download PDFInfo
- Publication number
- CN110245391A CN110245391A CN201910450543.6A CN201910450543A CN110245391A CN 110245391 A CN110245391 A CN 110245391A CN 201910450543 A CN201910450543 A CN 201910450543A CN 110245391 A CN110245391 A CN 110245391A
- Authority
- CN
- China
- Prior art keywords
- neural network
- artificial neural
- hardness
- life
- mathematical model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/04—Ageing analysis or optimisation against ageing
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Hardware Design (AREA)
- Evolutionary Computation (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Testing Resistance To Weather, Investigating Materials By Mechanical Methods (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The present invention provides a kind of based on the artificial neural network method in Hardness Prediction service life, it is characterized in that, artificial neural network is trained with the persistant data in existing hardness section, the artificial neural network after enabling training exports the creep rupture life prediction result in broader hardness section.The present invention establishes the model between hardness and remaining life using artificial neural network technology.Compared with prior art; the present invention can fast and accurately predict remaining creep rupture life of the material under specific steam parameter by simple and convenient, lossless hardness test; can directly it remove from because of brings economic losses such as shutdown or pipe cuttings, because its convenient and efficient feature timely can effectively can prevent accident generation caused by failing because of material aging by assessment material remaining life.
Description
Technical field
The present invention relates to a kind of quick, lossless methods for carrying out life appraisal, more particularly to one kind to be based on artificial neural network
Network, the method for carrying out quick life prediction using hardness.
Background technique
The some critical components of thermal power plant are run at high temperature under high pressure for a long time, therefore material during the evaluation of quick nondestructive military service
Creep impairment state, accurately estimate its remaining life, and propose in advance reasonable maintenance strategy to avoid the generation of accident,
The project extremely paid close attention to as academia and engineering circles.Industry mainly uses real the life appraisal of high-temperature material at present
The field sampling of border equipment, then in its damage of laboratory measurement and remaining life method.This method not only can be to practical fortune
Row equipment generates larger damage, and the test period is long, costly, and industrial production is caused to be interrupted for a long time, and economic loss is big.
It there is now the method for carrying out quick nondestructive prediction creep rupture life using hardness, this method is sampled without pipe cutting, directly
It connects and live hardness result is substituted into the life appraisal model that data with existing is established, the enduring quality of present material state can be obtained
Data realize quickly losslessization assessment.When scene, the hardness number that measures falls into the hardness for having grasped corresponding enduring quality data
When section, these data can play a role well and carry out residual life evaluation, incompetent without just seeming at these sections
For power.However, it is generally the case that since material wall unevenness, manufacture installation operation are lack of standardization, random larger, tissue
Hardness often shows extremely non-uniform situation, and various low durometers have, and section is very big.If will be until this be completely covered
It goes processing such problems when enough data in a little hardness sections again, the time and spatially has little time, need to use other sides
Method fast implements this process.
Summary of the invention
The technical problem to be solved by the present invention is when the live hardness measured is not in the hardness range of data with existing,
The existing method for carrying out quick nondestructive prediction creep rupture life using hardness can not work.
In order to solve the above-mentioned technical problem, the technical solution of the present invention is to provide a kind of based on artificial neural network with firmly
Spend the method for bimetry, which is characterized in that be trained, made to artificial neural network with the persistant data in existing hardness section
Artificial neural network after training can export the creep rupture life prediction result in broader hardness section, comprising the following steps:
Step 1 establishes artificial neural network mathematical model: selecting to influence the parameter of material remaining life as nerve
One group of input signal of member establishes the people between material hardness and remaining life using the remaining life data of material as output
Artificial neural networks mathematical model；
Step 2, using existing hardness number and the remaining life of the hardness number material under certain temperature, stress as one group
Training sample carries out learning training to the artificial neural network mathematical model that step 1 obtains using multiple groups training sample, to artificial
The model parameter of neutral net mathematical model is constantly debugged and is corrected, to reach the existing consistency output and input；
Step 3, the hardness number obtained in real time using the artificial neural network mathematical model after learning training, input, and
The running temperature and stress for needing assessment material, by the corresponding predicting residual useful life of artificial neural network mathematical model output
Value；
Step 4 carries out corresponding test, verifies to prediction result, and using test result as sample data, repeats
Step 2 carries out re -training to artificial neural network mathematical model, is continuously increased the study energy of artificial neural network mathematical model
Power and prediction reliability.
Preferably, the parameter that can influence material remaining life includes temperature, stress, hardness.
Preferably, the artificial neural network mathematical model is BP neural network.
The present invention establishes the model between hardness and remaining life using artificial neural network.Compared to general mathematics
It is extremely complex it is assumed that but as far as possible that the advantages of model, artificial nerve network model, is that it does not need to do input variable
Mostly using each factor information for influencing things result, comprehensive quantification anticipation is realized.The present invention is exactly to consider hardness pair
The influence of material remaining life then realizes that the service life is pre- by nerual network technique to the learning training of existing sample data
The function of survey.In addition, artificial nerve network model also has powerful self-organizing, self study, adaptive ability, and to data
There are original excavation and processing capacity, is highly suitable for current big data era and carries out multidimensional data modeling and analysis work
Make.
The present invention establishes the model between hardness and remaining life using artificial neural network technology.With prior art phase
Than the present invention can fast and accurately predict material under specific steam parameter by simple and convenient, lossless hardness test
Remaining creep rupture life can directly remove from because of brings economic losses such as shutdown or pipe cuttings, because its convenient and efficient feature can
Accident caused by failing because of material aging can effectively be prevented with timely assessment material remaining life to occur.
Detailed description of the invention
Fig. 1 be embodiment in the method based on the artificial neural network Hardness Prediction service life used in artificial neuron
The method that network Model is trained；
Fig. 2 is that the L-M parametric method of main pipeline stress rupture data is handled.
Specific embodiment
Present invention will be further explained below with reference to specific examples.It should be understood that these embodiments are merely to illustrate the present invention
Rather than it limits the scope of the invention.In addition, it should also be understood that, after reading the content taught by the present invention, those skilled in the art
Member can make various changes or modifications the present invention, and such equivalent forms equally fall within the application the appended claims and limited
Range.
The parametric data for characterizing materials behavior is many, and characterizes the parameter of material remaining life: temperature, stress, when
Between, hardness etc., have huge data, and it is almost irregular between them follow, so the present invention uses artificial neural network
Technology studies the relevance between them, utilizes non-linear global effect, good fault-tolerance and the associative memory of ANN height
Function, powerful adaptive and self-learning function, to which proper neural network model can be established, with existing hardness section
Persistant data be trained, the creep rupture life prediction result in broader hardness section can be exported.
Specifically, a kind of method based on the artificial neural network Hardness Prediction service life provided by the invention includes following
Step:
Step 1 establishes artificial neural network mathematical model: selecting to influence the parameter of material remaining life as nerve
One group of input signal of member establishes the people between material hardness and remaining life using the remaining life data of material as output
Artificial neural networks mathematical model；
Step 2, using existing hardness number and the remaining life of the hardness number material under certain temperature, stress as one group
Training sample carries out learning training to the artificial neural network mathematical model that step 1 obtains using multiple groups training sample, to artificial
The model parameter of neutral net mathematical model is constantly debugged and is corrected, to reach the existing consistency output and input；
Step 3, the hardness number obtained in real time using the artificial neural network mathematical model after learning training, input, and
The running temperature and stress for needing assessment material, by the corresponding predicting residual useful life of artificial neural network mathematical model output
Value；
Step 4 carries out corresponding test, verifies to prediction result, and using test result as sample data, repeats
Step 2 carries out re -training to artificial neural network mathematical model, is continuously increased the study energy of artificial neural network mathematical model
Power and prediction reliability.
Residual life evaluation is carried out to the P91 steel pipe that certain power plant was on active service using the method for the present invention, specific implementation is such as
Under:
Step 1 needs the P91 pipeline of life appraisal to carry out hardness determination power plant using portable hardometer, and will just
The hardness number that the formula hardometer of taking measures is converted to the Brinell hardness that standard Brookfield hardometer measures, and the average value for measuring result is
160.7HB。
Step 2, the military service stress and tube wall temperature for calculating P91 steel pipe.By being calculated: the maximum clothes of this P91 steel pipe
Use as a servant stress σmax=53.8MPa takes 1.5 times of safety coefficient, obtains calculating stress σ=80.7MPa, highest tube wall temperature is 605
℃。
After step 3, artificial neural network life appraisal model carry out learning training to sample data, more mature mould is formed
Then type inputs three neurons, respectively hardness: 160.7HB, stress: 80.7MPa, temperature: 605 DEG C, being exported by model
The remaining life t of this P91 steel piper=4204.7h.
In order to verify the reliability of the method bimetry, to existing, hardness range between 155HB~165HB P91
Steel pipe creep rupture strength data carry out the processing of L-M parametric method, and carry out fitting of a polynomial, as a result as shown in Figure 2.
Principal curve formula in figure in Fig. 2 are as follows:
PL-M=10-3·T(K)(16.9607+logtr)
=-25.5616+69.8643log σ -34.2284log2σ+5.0253·log3σ
Stress will be calculated and tube wall temperature substitutes into principal curve formula, the remaining life t of this power plant P91 steel pipe can be obtainedr
=3899h.In formula, T (K) indicates highest tube wall temperature (unit K), PL-MIndicate the strong parameter of heat.
The predicting residual useful life value of the method for the present invention is compared with the predicted value of maturation method life appraisal, error is
7.84%.Illustrate that the method is relatively reliable.
Claims (3)
1. a kind of based on the artificial neural network method in Hardness Prediction service life, which is characterized in that with holding for existing hardness section
Long data are trained artificial neural network, and the artificial neural network after enabling training exports holding for broader hardness section
Long life prediction result, comprising the following steps:
Step 1 establishes artificial neural network mathematical model: selecting the parameter that can influence material remaining life as neuron
One group of input signal establishes the artificial mind between material hardness and remaining life using the remaining life data of material as output
Through network Model；
Step 2 is trained using existing hardness number and the remaining life of the hardness number material under certain temperature, stress as one group
Sample carries out learning training to the artificial neural network mathematical model that step 1 obtains using multiple groups training sample, to artificial neuron
The model parameter of network Model is constantly debugged and is corrected, to reach the existing consistency output and input；
Step 3, the hardness number obtained in real time using the artificial neural network mathematical model after learning training, input, and need
The running temperature and stress of assessment material, by the corresponding predicting residual useful life value of artificial neural network mathematical model output；
Step 4 carries out corresponding test, verifies to prediction result, and using test result as sample data, repeats step
2 pairs of artificial neural network mathematical models carry out re -trainings, be continuously increased artificial neural network mathematical model learning ability and
Predict reliability.
2. as described in claim 1 a kind of based on the artificial neural network method in Hardness Prediction service life, which is characterized in that institute
It includes temperature, stress, hardness that the parameter of material remaining life can be influenced by, which stating,.
3. as described in claim 1 a kind of based on the artificial neural network method in Hardness Prediction service life, which is characterized in that institute
Stating artificial neural network mathematical model is BP neural network.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910450543.6A CN110245391B (en) | 2019-05-28 | 2019-05-28 | Method for predicting service life based on hardness of artificial neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910450543.6A CN110245391B (en) | 2019-05-28 | 2019-05-28 | Method for predicting service life based on hardness of artificial neural network |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110245391A true CN110245391A (en) | 2019-09-17 |
| CN110245391B CN110245391B (en) | 2023-07-18 |
Family
ID=67885136
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910450543.6A Active CN110245391B (en) | 2019-05-28 | 2019-05-28 | Method for predicting service life based on hardness of artificial neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110245391B (en) |
Citations (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3210693A1 (en) * | 1982-03-24 | 1983-10-06 | Schweiger Hubert | Reinforcing and armouring material, process and device for the preparation thereof, and the use thereof |
| JPS6295461A (en) * | 1985-10-23 | 1987-05-01 | Hitachi Ltd | Reliability guarantee testing method for high-temperature long-life strength of ceramic parts |
| JPH04256825A (en) * | 1991-02-08 | 1992-09-11 | Toshiba Corp | Pipe life diagnosis method |
| JPH05340857A (en) * | 1992-06-05 | 1993-12-24 | Ishikawajima Harima Heavy Ind Co Ltd | Method for diagnosing deterioration of inservice metal material |
| JPH0694589A (en) * | 1992-09-09 | 1994-04-05 | Toshiba Corp | Life diagnosis method for high temperature part |
| JPH10170503A (en) * | 1996-12-13 | 1998-06-26 | Mitsubishi Heavy Ind Ltd | Evaluation method for creep life of tempered martensite heat-resisting steel |
| RU2193772C1 (en) * | 2001-03-05 | 2002-11-27 | Общество с ограниченной ответственностью "Фирма "Геотехпрогресс" | Procedure predicting residual service life of steel structures |
| US20050091004A1 (en) * | 1998-04-15 | 2005-04-28 | Alexander G. Parlos | System and method for condition assessment and end-of-life prediction |
| CN101042059A (en) * | 2007-04-25 | 2007-09-26 | 上海发电设备成套设计研究院 | Method and system for on-line monitoring steam turbine roter low-cycle fatigue life consumption |
| US20100106458A1 (en) * | 2008-10-28 | 2010-04-29 | Leu Ming C | Computer program and method for detecting and predicting valve failure in a reciprocating compressor |
| US20100299085A1 (en) * | 2006-06-28 | 2010-11-25 | Jan Ture Slycke | Method for indicating fatigue damage of a metal object |
| CN101930223A (en) * | 2010-09-07 | 2010-12-29 | 曾谊晖 | Intelligent screening system based on numerical control processing technology for difficult-to-machine metal |
| EP2581594A2 (en) * | 2011-10-13 | 2013-04-17 | Bayern-Chemie Gesellschaft für flugchemische Antriebe mbH | System for lifespan monitoring of missiles |
| CN104089835A (en) * | 2014-07-01 | 2014-10-08 | 宁德职业技术学院 | Method for predicting life Nf and analyzing reliability R of TC4 welding component |
| CN104834808A (en) * | 2015-04-07 | 2015-08-12 | 青岛科技大学 | Back propagation (BP) neural network based method for predicting service life of rubber absorber |
| CN105158080A (en) * | 2015-05-12 | 2015-12-16 | 上海发电设备成套设计研究院 | Accelerated testing method for prediction of high temperature material creep life |
| CN105241749A (en) * | 2015-11-10 | 2016-01-13 | 昆山市交通工程试验检测中心 | Improved asphalt mixture wheel tracking test device |
| CN105352816A (en) * | 2015-11-26 | 2016-02-24 | 中国航空工业集团公司沈阳飞机设计研究所 | Composite structure failure prediction analytical method |
| US20160133070A1 (en) * | 2014-03-07 | 2016-05-12 | Hitachi Systems, Ltd. | Vehicle preventive maintenance system |
| CN106126776A (en) * | 2016-06-14 | 2016-11-16 | 国家电网公司 | Cable life Forecasting Methodology based on neutral net |
| CN106441383A (en) * | 2016-10-10 | 2017-02-22 | 山东大学 | Active excitation pressure filter filtering board health detection system based on fiber grating sensing |
| CN106771765A (en) * | 2017-01-05 | 2017-05-31 | 华北电力大学（保定） | A kind of multidimensional parameter appraisal procedure of operating composite insulator degree of aging |
| CN106897484A (en) * | 2017-01-09 | 2017-06-27 | 西北工业大学 | A kind of preparation method of the efficient low-stress grinding technological parameter of high temperature alloy |
| CN107598675A (en) * | 2017-06-21 | 2018-01-19 | 沈阳航空航天大学 | A kind of drilling parameter optimization method based on hard alloy cutter tipping failure prediction |
| CN107843510A (en) * | 2016-09-20 | 2018-03-27 | 中国科学院金属研究所 | Based on room temperature Brookfield Hardness Prediction supercritical unit T/P91 heat resisting steel residue creep rupture life appraisal procedures |
| CN108051364A (en) * | 2017-12-13 | 2018-05-18 | 中国科学院长春应用化学研究所 | A kind of EPR nuclear energy cable residue lifetime estimation method and prediction EPR nuclear energy cable remaining life methods |
| EP3353511A1 (en) * | 2015-09-25 | 2018-08-01 | Sikorsky Aircraft Corporation | System and method for load-based structural health monitoring of a dynamical system |
| CN108645615A (en) * | 2018-04-08 | 2018-10-12 | 太原科技大学 | A kind of Adaptive Fuzzy Neural-network gear method for predicting residual useful life |
| CN108846239A (en) * | 2018-07-03 | 2018-11-20 | 北京强度环境研究所 | A kind of elastic epoxy resin accelerated storage test and appraisal procedure based on temperature and humidity |
| CN108920893A (en) * | 2018-09-06 | 2018-11-30 | 南京医科大学 | A kind of cranio-maxillofacial bone and soft tissue form prediction method based on artificial intelligence |
| CN109142362A (en) * | 2018-09-10 | 2019-01-04 | 中国大唐集团科学技术研究院有限公司华中分公司 | It is a kind of based on the power plant of BP neural network service life of metal material appraisal procedure |
| CN109188082A (en) * | 2018-08-14 | 2019-01-11 | 国网陕西省电力公司电力科学研究院 | A kind of Transformer condition evaluation based on BP neural network |
| CN109540057A (en) * | 2018-11-16 | 2019-03-29 | 上海发电设备成套设计研究院有限责任公司 | A kind of system and method that steam turbine high-temperature pressure-containing member defect is evaluated online |
| CN109766583A (en) * | 2018-12-14 | 2019-05-17 | 南京航空航天大学 | Based on no label, unbalanced, initial value uncertain data aero-engine service life prediction technique |
-
2019
- 2019-05-28 CN CN201910450543.6A patent/CN110245391B/en active Active
Patent Citations (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE3210693A1 (en) * | 1982-03-24 | 1983-10-06 | Schweiger Hubert | Reinforcing and armouring material, process and device for the preparation thereof, and the use thereof |
| JPS6295461A (en) * | 1985-10-23 | 1987-05-01 | Hitachi Ltd | Reliability guarantee testing method for high-temperature long-life strength of ceramic parts |
| JPH04256825A (en) * | 1991-02-08 | 1992-09-11 | Toshiba Corp | Pipe life diagnosis method |
| JPH05340857A (en) * | 1992-06-05 | 1993-12-24 | Ishikawajima Harima Heavy Ind Co Ltd | Method for diagnosing deterioration of inservice metal material |
| JPH0694589A (en) * | 1992-09-09 | 1994-04-05 | Toshiba Corp | Life diagnosis method for high temperature part |
| JPH10170503A (en) * | 1996-12-13 | 1998-06-26 | Mitsubishi Heavy Ind Ltd | Evaluation method for creep life of tempered martensite heat-resisting steel |
| US20050091004A1 (en) * | 1998-04-15 | 2005-04-28 | Alexander G. Parlos | System and method for condition assessment and end-of-life prediction |
| RU2193772C1 (en) * | 2001-03-05 | 2002-11-27 | Общество с ограниченной ответственностью "Фирма "Геотехпрогресс" | Procedure predicting residual service life of steel structures |
| US20100299085A1 (en) * | 2006-06-28 | 2010-11-25 | Jan Ture Slycke | Method for indicating fatigue damage of a metal object |
| CN101042059A (en) * | 2007-04-25 | 2007-09-26 | 上海发电设备成套设计研究院 | Method and system for on-line monitoring steam turbine roter low-cycle fatigue life consumption |
| US20100106458A1 (en) * | 2008-10-28 | 2010-04-29 | Leu Ming C | Computer program and method for detecting and predicting valve failure in a reciprocating compressor |
| CN101930223A (en) * | 2010-09-07 | 2010-12-29 | 曾谊晖 | Intelligent screening system based on numerical control processing technology for difficult-to-machine metal |
| EP2581594A2 (en) * | 2011-10-13 | 2013-04-17 | Bayern-Chemie Gesellschaft für flugchemische Antriebe mbH | System for lifespan monitoring of missiles |
| US20160133070A1 (en) * | 2014-03-07 | 2016-05-12 | Hitachi Systems, Ltd. | Vehicle preventive maintenance system |
| CN104089835A (en) * | 2014-07-01 | 2014-10-08 | 宁德职业技术学院 | Method for predicting life Nf and analyzing reliability R of TC4 welding component |
| CN104834808A (en) * | 2015-04-07 | 2015-08-12 | 青岛科技大学 | Back propagation (BP) neural network based method for predicting service life of rubber absorber |
| CN105158080A (en) * | 2015-05-12 | 2015-12-16 | 上海发电设备成套设计研究院 | Accelerated testing method for prediction of high temperature material creep life |
| EP3353511A1 (en) * | 2015-09-25 | 2018-08-01 | Sikorsky Aircraft Corporation | System and method for load-based structural health monitoring of a dynamical system |
| CN105241749A (en) * | 2015-11-10 | 2016-01-13 | 昆山市交通工程试验检测中心 | Improved asphalt mixture wheel tracking test device |
| CN105352816A (en) * | 2015-11-26 | 2016-02-24 | 中国航空工业集团公司沈阳飞机设计研究所 | Composite structure failure prediction analytical method |
| CN106126776A (en) * | 2016-06-14 | 2016-11-16 | 国家电网公司 | Cable life Forecasting Methodology based on neutral net |
| CN107843510A (en) * | 2016-09-20 | 2018-03-27 | 中国科学院金属研究所 | Based on room temperature Brookfield Hardness Prediction supercritical unit T/P91 heat resisting steel residue creep rupture life appraisal procedures |
| CN106441383A (en) * | 2016-10-10 | 2017-02-22 | 山东大学 | Active excitation pressure filter filtering board health detection system based on fiber grating sensing |
| CN106771765A (en) * | 2017-01-05 | 2017-05-31 | 华北电力大学（保定） | A kind of multidimensional parameter appraisal procedure of operating composite insulator degree of aging |
| CN106897484A (en) * | 2017-01-09 | 2017-06-27 | 西北工业大学 | A kind of preparation method of the efficient low-stress grinding technological parameter of high temperature alloy |
| CN107598675A (en) * | 2017-06-21 | 2018-01-19 | 沈阳航空航天大学 | A kind of drilling parameter optimization method based on hard alloy cutter tipping failure prediction |
| CN108051364A (en) * | 2017-12-13 | 2018-05-18 | 中国科学院长春应用化学研究所 | A kind of EPR nuclear energy cable residue lifetime estimation method and prediction EPR nuclear energy cable remaining life methods |
| CN108645615A (en) * | 2018-04-08 | 2018-10-12 | 太原科技大学 | A kind of Adaptive Fuzzy Neural-network gear method for predicting residual useful life |
| CN108846239A (en) * | 2018-07-03 | 2018-11-20 | 北京强度环境研究所 | A kind of elastic epoxy resin accelerated storage test and appraisal procedure based on temperature and humidity |
| CN109188082A (en) * | 2018-08-14 | 2019-01-11 | 国网陕西省电力公司电力科学研究院 | A kind of Transformer condition evaluation based on BP neural network |
| CN108920893A (en) * | 2018-09-06 | 2018-11-30 | 南京医科大学 | A kind of cranio-maxillofacial bone and soft tissue form prediction method based on artificial intelligence |
| CN109142362A (en) * | 2018-09-10 | 2019-01-04 | 中国大唐集团科学技术研究院有限公司华中分公司 | It is a kind of based on the power plant of BP neural network service life of metal material appraisal procedure |
| CN109540057A (en) * | 2018-11-16 | 2019-03-29 | 上海发电设备成套设计研究院有限责任公司 | A kind of system and method that steam turbine high-temperature pressure-containing member defect is evaluated online |
| CN109766583A (en) * | 2018-12-14 | 2019-05-17 | 南京航空航天大学 | Based on no label, unbalanced, initial value uncertain data aero-engine service life prediction technique |
Non-Patent Citations (13)
| Title |
|---|
| GLOROT X: "Understanding the difficulty of training deep fecdforward neural networks", JOURNAL OF MACHINE LEARNING RESEARCH, pages 249 - 256 * |
| LI, YZ: "Improvement of predicting mechanical properties from spherical indentation test", INTERNATIONAL JOURNAL OF MECHANICAL SCIENCES, pages 182 - 196 * |
| STEVENS: "A comparative study on mechanical properties of single- and twin-wire welded joints through multi-objective meta-heuristic optimisation", INTERNATIONAL JOURNAL OF MANUFACTURING RESEARCH, pages 374 - 393 * |
| 周志刚: "随机风作用下风力发电机齿轮传动***动力学及动态可靠性研究", 《中国博士学位论文全文数据库》 * |
| 周志刚: "随机风作用下风力发电机齿轮传动***动力学及动态可靠性研究", 《中国博士学位论文全文数据库》, no. 02, 15 February 2013 (2013-02-15), pages 042 - 9 * |
| 张慰;李晓阳;姜同敏;黄领才;: "基于BP神经网络的多应力加速寿命试验预测方法", 航空学报, no. 09, pages 1691 - 1696 * |
| 文常保，茹锋: "《人工神经网络理论及应用》", 31 March 2019, pages: 20 - 24 * |
| 梁志强: "齿轮钢18Cr2Ni4WA磨削烧伤实验及仿真预测研究", 兵工学报, pages 1995 - 2001 * |
| 潘金平: "电站锅炉防焦箱鼓包寿命预测新方法", 压力容器, pages 39 - 45 * |
| 王义强: ""高速铣削SKD61模具钢表面完整性与疲劳寿命"", pages 2995 - 3000 * |
| 谭思超，张文超，庄乃亮: "《海洋条件下反应堆热工水力特性研究》", 31 August 2018, pages: 226 * |
| 陈凭: ""硅橡胶表面硬度的激光诱导击穿光谱分析"", pages 1315 - 1321 * |
| 韦家虎;张麦仓;: "烟气轮机涡轮盘高温合金剩余寿命预测", 失效分析与预防, no. 03, pages 68 - 71 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110245391B (en) | 2023-07-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109086804B (en) | Hydraulic equipment early failure prediction method based on fusion of multi-source state monitoring information and reliability characteristics | |
| CN109583585B (en) | Construction method of power station boiler wall temperature prediction neural network model | |
| CN110530650B (en) | Method for monitoring performance state of heavy-duty gas turbine based on generalized regression neural network and box diagram analysis | |
| CN110363334B (en) | Grid line loss prediction method of photovoltaic grid connection based on gray neural network model | |
| CN113204922B (en) | Transformer running state monitoring and predicting method | |
| CN103246279A (en) | CPA method in chemical process with viscosity of actuated valve | |
| CN114897331A (en) | Power transformer risk assessment method based on three-parameter interval gray number decision | |
| CN117113166A (en) | Industrial boiler fault detection method based on improved integrated learning | |
| CN114595883A (en) | Oil-immersed transformer residual life personalized dynamic prediction method based on meta-learning | |
| CN108710946B (en) | Human factor reliability balancing method for deepwater riser system risk maintenance decision optimization | |
| CN105741184B (en) | Transformer state evaluation method and device | |
| CN114091320A (en) | Natural gas pipeline corrosion failure time prediction method and device | |
| CN110245391A (en) | A method of based on artificial neural network with the Hardness Prediction service life | |
| CN117195647A (en) | Method, apparatus, device, medium and program product for post-earthquake evaluation of transformer bushings | |
| Zhang et al. | Gas pipeline corrosion prediction based on modified support vector machine and unequal interval model | |
| CN113836794B (en) | Soft and hard combined fly ash carbon content online monitoring method | |
| CN115470846A (en) | Transformer fault online diagnosis method based on graph neural network | |
| CN113484678A (en) | Power grid fault impact strength quantitative index analysis method based on EWM | |
| Kumar et al. | Gas turbine engine operational data analysis for anomaly detection: Statistical vs. neural network approach | |
| Triviño et al. | Damage detection and localization at the jacket support of an offshore wind turbine using transformer models | |
| Ma et al. | Forecasting of dissolved gas in transformer oil by optimized nonlinear Grey bernoulli Markov model | |
| CN112347695B (en) | Method and system for predicting top layer oil temperature of transformer | |
| CN117272844B (en) | Method and system for predicting service life of distribution board | |
| CN112270060B (en) | Method, system and equipment for predicting residual life of furnace tube of heating furnace on line in real time | |
| Sun | Simulation of Mechanical Component Fault Prediction Model Based on Artificial Neural Network Algorithm |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |