CN104515591A - Vibration detection process method for high-precision coal mill - Google Patents
Vibration detection process method for high-precision coal mill Download PDFInfo
- Publication number
- CN104515591A CN104515591A CN201410851654.5A CN201410851654A CN104515591A CN 104515591 A CN104515591 A CN 104515591A CN 201410851654 A CN201410851654 A CN 201410851654A CN 104515591 A CN104515591 A CN 104515591A
- Authority
- CN
- China
- Prior art keywords
- data
- coal pulverizer
- vibration
- parameter
- vibration detection
- 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
Landscapes
- Disintegrating Or Milling (AREA)
- Crushing And Grinding (AREA)
Abstract
The invention discloses a vibration detection process method for a high-precision coal mill. The vibration detection process method comprises the following steps: (a) acquiring n groups of historical running data for reflecting the running conditions of the coal mill in sequence according to a time sequence and obtaining actual vibration intensity data respectively corresponding to the n groups of historical running data through actual test; (b) building a coal mill vibration detection model by adopting a phase space algorithm and an extreme learning machine algorithm based on the above data and then performing optimized solution on the detection model; (c) performing online measurement on current working data of the coal mill and then obtaining corresponding output results according to the best detection model, wherein the output results are required current vibration state results of the coal mill. Through the vibration detection process method, the real-time detection on the vibration intensity of the coal mill can be realized in ways of high convenience in operation and control, high efficiency and high precision. The vibration detection process method is particularly suitable for application occasions such as large-scale thermal power plants and the like.
Description
Technical field
The invention belongs to thermoelectricity electrification technique as well as association area, more specifically, relate to a kind of high-precision coal pulverizer vibration detection process.
Background technology
Coal pulverizer is by coal crusher and wears into the machinery of coal dust, and it, as the important utility appliance of coal-powder boiler, is applied widely in coal fired thermal power plant.In actual motion, coal pulverizer generally easily vibrates, and this will inevitably cause problems such as grinding power reduction, wearing and tearing, shortening sealing life, joint breaking and weld seam drawing crack, tackles power plant's production guarantee mutually and plays adverse effect.Oscillation intensity according to coal pulverizer can effectively judge its running status.Therefore, the coal pulverizer of current power plant needs to be equipped with vibration measurement device, so that the vibration state of Real-Time Monitoring coal pulverizer.
Coal pulverizer vibration detection mode majority of the prior art is artificial spot check, waste time and energy and real-time monitoring cannot be realized, for this reason, proposed based on seasonal effect in time series ARIMA method, based on the support vector machine returned, and the method such as artificial neural network and gray theory is for giving modeling to the vibration of coal pulverizer.But, further research shows, above-mentioned existing method exists more deficiency or defect in measuring accuracy, model training and on-line prediction etc., such as, ARIMA model is linear autoregression smoothing prediction, and the simulate effect for non-linear values such as coal pulverizer vibratory outputs is not good enough; Adopt artificial neural network or support vector machine to carry out prediction can perform vibratory output and return, but need iteration optimizing due to the parameter of model, the training of model can time of at substantial, is difficult to be applied to on-line prediction, etc.Therefore, association area needs the more perfect solution of searching badly, so that the high-acruracy survey realized power plant coal vibrational state and on-line prediction.
Summary of the invention
For above defect or the Improvement requirement of prior art, the invention provides a kind of high-precision coal pulverizer vibration detection process, wherein by selecting coal pulverizer critical operational parameters and historical vibration intensity data thereof, and build specific vibration survey model and algorithm based on this to perform on-line measurement, mutually should be able to high-level efficiency, perform the real-time oscillation intensity of coal pulverizer accurately and measure, be thus particularly useful for the application scenarios such as thermal power plant's coal pulverizer oscillation intensity high-acruracy survey.
For achieving the above object, according to the present invention, provide a kind of high-precision coal pulverizer vibration detection process, it is characterized in that, the method comprises the following steps:
A () gathers the history data of n group reflection coal pulverizer ruuning situation successively according to sequential, and obtain this n group history data actual vibration intensity data corresponding separately by actual test; Wherein said each group of history data includes sampling moment numbering, the wind powder mixture temperature of discharge knockout drum, carbon monoxide content, frequency converter rotating speed and lubricating oil temperature, the working current of coal pulverizer and import primary air flow, the bearing temperature of the aperture of cooling water valve, the lubricating oil temperature of grinding roller bearing and motor driving side, the fuel tank temperature of Hydraulic Station, loading fuel pump outlet pressure, the aperture of maximum ventilation resistance, First air controllable register, and the operational data of 17 aspects such as coal pulverizer coal calorific value, moisture and interior water of adopting;
B () performs normalized to all data that step (a) obtains, coal pulverizer vibration detection model is built based on these data acquisition phase space algorithms and extreme learning machine algorithm, and optimization is performed to detection model, its detailed process is as follows:
(b1) first preset corresponding parameter respectively to phase space algorithm and extreme learning machine algorithm, namely Embedded dimensions m, delay operator τ, penalty factor, nuclear parameter γ, then perform initialization all in a random basis to these parameters;
(b2) according to the Embedded dimensions m after initialization and delay operator τ, the actual vibration intensity data of coal pulverizer is write as the form of phase space matrix X as follows:
Wherein, x
1, x
2..., x
nrepresent respectively gather in step (a) n group actual vibration intensity data, which together form the phase point of phase space, and total line number of this phase space matrix is n-(m-1) τ, total columns is m;
(b3) described history data is write as the form of matrix Y as follows:
Wherein, i=1,2 ..., 17, j=1,2 ..., n; y
i,jthen represent i-th parameter in above-mentioned 17 parameters be numbered j the sampling moment corresponding to data;
(b4) the sampling moment corresponding to last row actual vibration intensity data in described phase space matrix X, the a series of history datas inscribed when taking out this sampling from described matrix Y obtain matrix Z as follows before being placed in last row of described trajectory of phase space X as auxiliary parameter thus:
Wherein, the total line number of described matrix Z is n-(m-1) τ, and total columns is m+17;
(b5) each line number in described matrix Z step (b4) obtained according to this and front m+16 arrange data jointly as the input data of extreme learning machine, simultaneously using in described matrix Z last row as output correlation data;
(b6) according to the penalty factor after initialization and nuclear parameter γ, the input data in integrating step (b5) and output correlation data, calculate the modeling error of extreme learning machine;
(b7) whether the modeling error that determining step (b6) calculates drops within default threshold value: if, then using the Embedded dimensions m, delay operator τ, penalty factor and the nuclear parameter γ that adopt in step (b6) as final detection model parameter optimization result, and by the current detection model set up using this optimized results as coal pulverizer vibration detection, otherwise, then step (b8) is proceeded to;
(b8) genetic algorithm is utilized to perform crossover and mutation to above-mentioned Embedded dimensions m, delay operator τ, penalty factor and nuclear parameter γ, then circulation is performed according to the mode of step (b2) ~ (b7), till drawn modeling error drops within default threshold value, export the model parameter optimized results of optimized detection model and correspondence thereof simultaneously;
C () carries out on-line measurement to the work at present data that coal pulverizer relates to above-mentioned 17 aspects, then the optimal detection model obtained according to step (b) is to obtain corresponding Output rusults, and this Output rusults is required coal pulverizer current vibration state-detection result.
As further preferably, in step (b6), the method for 5 retransposing checkings is preferably adopted to calculate the modeling error of described extreme learning machine.
As further preferably, after obtaining optimization model by step (b), preferably can also regularly upgrade its model parameter, in the process, up-to-date sample data is joined in sample set, retains the classical sample data in original sample set simultaneously.
As further preferably, described coal pulverizer is preferably the coal pulverizer of large thermal power plant.
In general, the above technical scheme conceived by the present invention compared with prior art, owing to having taken into full account that current coal pulverizer operational factor and historical vibration situation are to the multifactor impact of its current vibration intensity, and select to adopt phase space algorithm and extreme learning machine algorithm to perform on-line checkingi to build suitable detection model, mutually should be able to so that manipulation, high-level efficiency and accurately mode realize the real-time detection to coal pulverizer oscillation intensity, and be particularly useful for the application scenario of large thermal power plant and so on.
Accompanying drawing explanation
Fig. 1 is the concrete technology process flow diagram according to the coal pulverizer vibration detection process constructed by the present invention;
Fig. 2 is the operate figure according to coal pulverizer method for detecting vibration of the present invention.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearly understand, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein only in order to explain the present invention, be not intended to limit the present invention.In addition, if below in described each embodiment of the present invention involved technical characteristic do not form conflict each other and just can mutually combine.
Fig. 1 is the concrete technology process flow diagram according to the coal pulverizer vibration detection process constructed by the present invention, and Fig. 2 is the operate figure according to coal pulverizer method for detecting vibration of the present invention.As shown in Figures 1 and 2, this process mainly comprises following technological operation step:
First, be screening and the acquisition step of coal pulverizer running parameter.
Real-time parameter in coal pulverizer work system reaches 207 (as primary air flow, a wind-warm syndrome etc.), the ature of coal information that in mill, coal is corresponding has 6 (as net calorific value, moisture as received coal etc.), if all parameters all participate in modeling, will make model complex, generalization ability weakens, and likely causes dimension disaster.Therefore, first by the related coefficient screening between dimension in the present invention, Pearson correlation coefficient is greater than in two dimensions of 0.99 and removes one of them, again based on the feature selecting of genetic algorithm, use wrapper structure, have chosen 17 parameters wherein, wherein obtain 14 by SIS real-time data base, comprise: sampling moment value, discharge knockout drum wind powder mixture temperature, outlet carbon monoxide content, discharge knockout drum frequency converter rotating speed, motor inboard bearing temperature, coal pulverizer electric current, separation vessel lubricating oil temperature, import primary air flow, cooling water valve aperture, shaft of grinding roller bearing lubrication oil temperature, heat primary air controllable register aperture, Hydraulic Station fuel tank temperature, maximum ventilation resistance, hydraulic oil unit loads fuel pump outlet pressure, ature of coal information 3, comprising: coal calorific value, moisture, Nei Shui.
Specifically, in this step, gather the history data of n group reflection coal pulverizer ruuning situation according to sequential successively, and obtain this n group history data actual vibration intensity data corresponding separately by actual test; Wherein said each group of history data includes sampling moment numbering, the wind powder mixture temperature of discharge knockout drum, carbon monoxide content, frequency converter rotating speed and lubricating oil temperature, the working current of coal pulverizer and import primary air flow, the bearing temperature of the aperture of cooling water valve, the lubricating oil temperature of grinding roller bearing and motor driving side, the fuel tank temperature of Hydraulic Station, loading fuel pump outlet pressure, the aperture of maximum ventilation resistance, First air controllable register, and the operational data of 17 aspects such as coal pulverizer coal calorific value, moisture and interior water of adopting.
Then, after getting out training set and test set, in the present invention, normalized is performed, then based on these data to above-mentioned obtained all data, select to adopt phase space algorithm and extreme learning machine algorithm to build coal pulverizer vibration detection model, and optimization is performed to detection model.With regard to its principle, its roughly step comprise first Parameters for Phase Space Reconstruction (Embedded dimensions m be set, delay operator τ), extreme learning machine parameter (penalty factor, nuclear parameter γ) optimizing space, in optimizing space, at random initialization is carried out to these four parameters, then training set and the parameter that obtains at random is utilized to set up measurement model, the precision of recycling test set detection model, if model accuracy can not reach requirement, rebuild model parameter by crossover and mutation, until obtain the satisfied model of precision, finally the structure of this model is stored for actual measurement, the further specific explanations of above-mentioned principle of work see the related introduction of phase space algorithm and extreme learning machine, therefore can not repeat them here.
More specifically, this structure coal pulverizer vibration detection model and to perform the process of optimization to detection model as follows:
(1) first preset corresponding parameter respectively to phase space algorithm and extreme learning machine algorithm, namely Embedded dimensions m, delay operator τ, penalty factor, nuclear parameter γ, then perform initialization all in a random basis to these parameters;
(2) according to the Embedded dimensions m after initialization and delay operator τ, the actual vibration intensity data of coal pulverizer is write as the form of phase space matrix X as follows:
Wherein, x
1, x
2..., x
nrepresent respectively gather in step (a) n group actual vibration intensity data, which together form the phase point of phase space, and total line number of this phase space matrix is n-(m-1) τ, total columns is m;
(3) described history data is write as the form of matrix Y as follows:
Wherein, i=1,2 ..., 17, j=1,2 ..., n; y
i,jthen represent i-th parameter in above-mentioned 17 parameters be numbered j the sampling moment corresponding to data;
(4) the sampling moment corresponding to last row actual vibration intensity data in described phase space matrix X, the a series of history datas inscribed when taking out this sampling from described matrix Y obtain matrix Z as follows before being placed in last row of described trajectory of phase space X as auxiliary parameter thus:
Wherein, the total line number of described matrix Z is n-(m-1) τ, and total columns is m+17;
(5) each line number in described matrix Z previous step obtained according to this and front m+16 arrange data jointly as the input data of extreme learning machine, simultaneously using in described matrix Z last row as output correlation data;
(6) according to the penalty factor after initialization and nuclear parameter γ, the input data obtained in conjunction with previous step and output correlation data, calculate the modeling error of extreme learning machine;
(7) whether the modeling error that determining step calculates drops within default threshold value: if, the Embedded dimensions m then it adopted, delay operator τ, penalty factor and nuclear parameter γ are as final detection model parameter optimization result, and by the current detection model set up using this optimized results as coal pulverizer vibration detection, otherwise, then next step is proceeded to;
(b8) genetic algorithm is utilized to perform crossover and mutation to above-mentioned Embedded dimensions m, delay operator τ, penalty factor and nuclear parameter γ, then circulation is performed according to the mode of above step, till drawn modeling error drops within default threshold value, export the model parameter optimized results of optimized detection model and correspondence thereof simultaneously.
Finally, be actual coal pulverizer vibration on-line checkingi operation.
For example by interface degree, again on-line measurement is carried out to the work at present data that coal pulverizer relates to above-mentioned 17 aspects, transfer the history coal pulverizer oscillation intensity data needed for calculating simultaneously, these Organization of Datas are become the form of mode input requirement, and normalization, then utilize and obtain corresponding Output rusults according to obtained optimal detection model above, this Output rusults is required coal pulverizer current vibration state-detection result.
In addition, As time goes on, equipment also can be deteriorated gradually, is therefore necessary regularly to revise model; The sample data that simultaneously spot check personnel measurements obtains constantly increases, also can correction model parameter further, raising model accuracy.In Modifying model process, as much as possible up-to-date sample data is joined in sample set, retain the classical sample data in original sample set, that remove repetition, very similar sample data simultaneously.Utilize the sample set re-training model newly obtained, replace original model.Training detailed process and the preceding step flow process of model are similar.
To sum up, the present invention is based on phase space reconfiguration and extreme learning machine measurement model can according in real time, perform the data estimation of coal pulverizer oscillation intensity exactly, and a large amount of actual test results shows, its relative error can ensure within 10%, thus there is very high use value, and be particularly useful for the application scenarios such as thermal power plant's coal pulverizer oscillation intensity high-acruracy survey.
Those skilled in the art will readily understand; the foregoing is only preferred embodiment of the present invention; not in order to limit the present invention, all any amendments done within the spirit and principles in the present invention, equivalent replacement and improvement etc., all should be included within protection scope of the present invention.
Claims (4)
1. a high-precision coal pulverizer vibration detection process, it is characterized in that, the method comprises the following steps:
A () gathers the history data of n group reflection coal pulverizer ruuning situation successively according to sequential, and obtain this n group history data actual vibration intensity data corresponding separately by actual test; Wherein said each group of history data includes sampling moment numbering, the wind powder mixture temperature of discharge knockout drum, carbon monoxide content, frequency converter rotating speed and lubricating oil temperature, the working current of coal pulverizer and import primary air flow, the bearing temperature of the aperture of cooling water valve, the lubricating oil temperature of grinding roller bearing and motor driving side, the fuel tank temperature of Hydraulic Station, loading fuel pump outlet pressure, the aperture of maximum ventilation resistance, First air controllable register, and the operational data of 17 aspects such as coal pulverizer coal calorific value, moisture and interior water of adopting;
B () performs normalized to all data that step (a) obtains, coal pulverizer vibration detection model is built based on these data acquisition phase space algorithms and extreme learning machine algorithm, and optimization is performed to detection model, its detailed process is as follows:
(b1) first preset corresponding parameter respectively to phase space algorithm and extreme learning machine algorithm, namely Embedded dimensions m, delay operator τ, penalty factor, nuclear parameter γ, then perform initialization all in a random basis to these parameters;
(b2) according to the Embedded dimensions m after initialization and delay operator τ, the actual vibration intensity data of coal pulverizer is write as the form of phase space matrix X as follows:
Wherein, x
1, x
2..., x
nrepresent respectively gather in step (a) n group actual vibration intensity data, which together form the phase point of phase space, and total line number of this phase space matrix is n-(m-1) τ, total columns is m;
(b3) described history data is write as the form of matrix Y as follows:
Wherein, i=1,2 ..., 17, j=1,2 ..., n; y
i,jthen represent i-th parameter in above-mentioned 17 parameters be numbered j the sampling moment corresponding to data;
(b4) the sampling moment corresponding to last row actual vibration intensity data in described phase space matrix X, the a series of history datas inscribed when taking out this sampling from described matrix Y obtain matrix Z as follows before being placed in last row of described trajectory of phase space X as auxiliary parameter thus:
Wherein, the total line number of described matrix Z is n-(m-1) τ, and total columns is m+17;
(b5) each line number in described matrix Z step (b4) obtained according to this and front m+16 arrange data jointly as the input data of extreme learning machine, simultaneously using in described matrix Z last row as output correlation data;
(b6) according to the penalty factor after initialization and nuclear parameter γ, the input data in integrating step (b5) and output correlation data, calculate the modeling error of extreme learning machine;
(b7) whether the modeling error that determining step (b6) calculates drops within default threshold value: if, then using the Embedded dimensions m, delay operator τ, penalty factor and the nuclear parameter γ that adopt in step (b6) as final detection model parameter optimization result, and by the current detection model set up using this optimized results as coal pulverizer vibration detection, otherwise, then step (b8) is proceeded to;
(b8) genetic algorithm is utilized to perform crossover and mutation to above-mentioned Embedded dimensions m, delay operator τ, penalty factor and nuclear parameter γ, then circulation is performed according to the mode of step (b2) ~ (b7), till drawn modeling error drops within default threshold value, export the model parameter optimized results of optimized detection model and correspondence thereof simultaneously;
C () carries out on-line measurement to the work at present data that coal pulverizer relates to above-mentioned 17 aspects, then the optimal detection model obtained according to step (b) is to obtain corresponding Output rusults, and this Output rusults is required coal pulverizer current vibration state-detection result.
2. coal pulverizer vibration detection process as claimed in claim 1, is characterized in that, in step (b6), preferably adopts the method for 5 retransposing checkings to calculate the modeling error of described extreme learning machine.
3. coal pulverizer vibration detection process as claimed in claim 1 or 2, it is characterized in that, after obtaining optimization model by step (b), preferably can also regularly upgrade its model parameter, in the process, up-to-date sample data is joined in sample set, retains the classical sample data in original sample set simultaneously.
4. the coal pulverizer vibration detection process as described in claim 1-3 any one, it is characterized in that ground, described coal pulverizer is preferably the coal pulverizer of large thermal power plant.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410851654.5A CN104515591B (en) | 2014-12-31 | 2014-12-31 | A kind of high-precision coal pulverizer vibration detection process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410851654.5A CN104515591B (en) | 2014-12-31 | 2014-12-31 | A kind of high-precision coal pulverizer vibration detection process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104515591A true CN104515591A (en) | 2015-04-15 |
| CN104515591B CN104515591B (en) | 2018-01-05 |
Family
ID=52791240
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410851654.5A Active CN104515591B (en) | 2014-12-31 | 2014-12-31 | A kind of high-precision coal pulverizer vibration detection process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104515591B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106597149A (en) * | 2016-11-22 | 2017-04-26 | 电子科技大学 | Oscillator residual life estimation method based on acceleration sensitivity |
| CN112270419A (en) * | 2020-11-02 | 2021-01-26 | 北京京能能源技术研究有限责任公司 | Grinding roller wear prediction method and device, computer equipment and readable storage medium |
| CN117610890A (en) * | 2024-01-19 | 2024-02-27 | 天津美腾科技股份有限公司 | Dynamic calculation method, device, equipment and medium for parameters of coal preparation plant |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103048041A (en) * | 2012-12-20 | 2013-04-17 | 北京信息科技大学 | Fault diagnosis method of electromechanical system based on local tangent space and support vector machine |
| CN103400210A (en) * | 2013-08-13 | 2013-11-20 | 广西电网公司电力科学研究院 | Short-term wind-speed combination forecasting method |
| US8725676B1 (en) * | 2011-03-31 | 2014-05-13 | Rockwell Collins, Inc. | State change detection |
| CN103902776A (en) * | 2014-04-02 | 2014-07-02 | 沈阳化工大学 | Wet type ball grinder load parameter integrated modeling method based on EEMD (ensemble empirical mode decomposition) |
-
2014
- 2014-12-31 CN CN201410851654.5A patent/CN104515591B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8725676B1 (en) * | 2011-03-31 | 2014-05-13 | Rockwell Collins, Inc. | State change detection |
| CN103048041A (en) * | 2012-12-20 | 2013-04-17 | 北京信息科技大学 | Fault diagnosis method of electromechanical system based on local tangent space and support vector machine |
| CN103400210A (en) * | 2013-08-13 | 2013-11-20 | 广西电网公司电力科学研究院 | Short-term wind-speed combination forecasting method |
| CN103902776A (en) * | 2014-04-02 | 2014-07-02 | 沈阳化工大学 | Wet type ball grinder load parameter integrated modeling method based on EEMD (ensemble empirical mode decomposition) |
Non-Patent Citations (2)
| Title |
|---|
| GUANG-BIN HUANG等: "Extreme learning machine: Theory and applications", 《NEUROCOMPUTING》 * |
| 张翌晖等: "基于集合经验模态分解和改进极限学习机的短期风速组合预测研究", 《电力系统保护与控制》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106597149A (en) * | 2016-11-22 | 2017-04-26 | 电子科技大学 | Oscillator residual life estimation method based on acceleration sensitivity |
| CN112270419A (en) * | 2020-11-02 | 2021-01-26 | 北京京能能源技术研究有限责任公司 | Grinding roller wear prediction method and device, computer equipment and readable storage medium |
| CN112270419B (en) * | 2020-11-02 | 2024-02-23 | 北京京能能源技术研究有限责任公司 | Grinding roller wear prediction method, grinding roller wear prediction device, computer equipment and readable storage medium |
| CN117610890A (en) * | 2024-01-19 | 2024-02-27 | 天津美腾科技股份有限公司 | Dynamic calculation method, device, equipment and medium for parameters of coal preparation plant |
| CN117610890B (en) * | 2024-01-19 | 2024-04-30 | 天津美腾科技股份有限公司 | Dynamic calculation method, device, equipment and medium for parameters of coal preparation plant |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104515591B (en) | 2018-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Tao et al. | Digital twin driven prognostics and health management for complex equipment | |
| Thelen et al. | A comprehensive review of digital twin—part 2: roles of uncertainty quantification and optimization, a battery digital twin, and perspectives | |
| Wang et al. | Reliability of offshore wind turbine support structures: A state-of-the-art review | |
| Rodríguez et al. | The use of artificial neural network (ANN) for modeling the useful life of the failure assessment in blades of steam turbines | |
| RU2310226C2 (en) | Method and device for evaluating productivity of steam-gas electric plants | |
| CN1105950C (en) | Method for blade temp. estimation in a steam turbine | |
| CN104808634A (en) | Thermal power plant visual management system based on virtual reality | |
| CN101681155A (en) | Virtual sensor system and method | |
| Nowak et al. | Using the artificial neural network to control the steam turbine heating process | |
| Maré | Novel simulations for energy management of mine cooling systems | |
| CN103217282B (en) | Fatigue test method of blade scaling model of horizontal axis wind turbine based on equal-service-life principle | |
| CN104515591A (en) | Vibration detection process method for high-precision coal mill | |
| CN108869174A (en) | A kind of blade of wind-driven generator intrinsic frequency operating condition compensation method of Nonlinear Modeling | |
| CN110672154A (en) | Civil engineering building monitoring system | |
| Okenyi et al. | A review of challenges and framework development for corrosion fatigue life assessment of monopile-supported horizontal-axis offshore wind turbines | |
| CN105715318B (en) | Comprehensive waste heat utilization evaluation method on basis of industrial steam turbine and comprehensive waste heat utilization device | |
| Zhang et al. | Condition based maintenance and operation of wind turbines | |
| Indrawan et al. | Readiness index for Indonesian power plant toward industry 4.0 | |
| Ziegler | Assessment of monopiles for lifetime extension of offshore wind turbines | |
| CN107956731A (en) | The Forecasting Methodology that the change of Air Cooling Fan for Power Station frequency influences unit back pressuce parameter | |
| CN103793746A (en) | Method for identifying parameters of coal-fired power plant boiler superheater model | |
| CN103714262B (en) | A kind of thermal technology's soft-sensing model update method based on buffer stopper timing Design | |
| JP4885008B2 (en) | Maintenance planning method | |
| Wagner | An integrated simulation-based method for deep-level mine dewatering planning | |
| Branner et al. | Towards more smart, efficient and reliable wind-turbine structures |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |