CN111222247A - Early fault early warning method for rotary machine - Google Patents
Early fault early warning method for rotary machine Download PDFInfo
- Publication number
- CN111222247A CN111222247A CN202010031040.8A CN202010031040A CN111222247A CN 111222247 A CN111222247 A CN 111222247A CN 202010031040 A CN202010031040 A CN 202010031040A CN 111222247 A CN111222247 A CN 111222247A
- Authority
- CN
- China
- Prior art keywords
- equipment
- early
- trend
- early warning
- point
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001914 filtration Methods 0.000 claims abstract description 34
- 238000012544 monitoring process Methods 0.000 claims abstract description 17
- 230000003595 spectral effect Effects 0.000 claims abstract description 17
- 238000005516 engineering process Methods 0.000 claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000001228 spectrum Methods 0.000 claims abstract description 6
- 238000013459 approach Methods 0.000 claims description 2
- 230000015556 catabolic process Effects 0.000 claims description 2
- 238000006731 degradation reaction Methods 0.000 claims description 2
- 238000009795 derivation Methods 0.000 claims description 2
- 230000035945 sensitivity Effects 0.000 claims description 2
- 238000012549 training Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 abstract description 4
- 238000012423 maintenance Methods 0.000 abstract description 4
- 230000002159 abnormal effect Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/005—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles during manufacturing process
-
- G—PHYSICS
- G08—SIGNALLING
- G08B—SIGNALLING OR CALLING SYSTEMS; ORDER TELEGRAPHS; ALARM SYSTEMS
- G08B21/00—Alarms responsive to a single specified undesired or abnormal condition and not otherwise provided for
- G08B21/18—Status alarms
- G08B21/187—Machine fault alarms
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Manufacturing & Machinery (AREA)
- Business, Economics & Management (AREA)
- Emergency Management (AREA)
- Measurement Of Mechanical Vibrations Or Ultrasonic Waves (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses an early-stage fault early-warning method for a rotary machine, which fully utilizes monitoring parameter data of an online monitoring system of equipment to realize early-stage alarm of abnormal operation of the equipment and improve the accuracy of the alarm of the equipment. The early-stage fault early-warning method utilizes the spectral distance index function to extract the equipment vibration characteristic signal and utilizes l1The trend filtering technology carries out filtering processing on the vibration characteristic signals, and an early fault early warning model based on the spectrum distance index function trend filtering technology is constructed according to the slope change of the curve of the filtered vibration characteristic signals, so that the occurrence and the development of early faults of equipment can be predicted, and the technical support can be provided for predictive maintenance of the equipment.
Description
Technical Field
The invention relates to the technical field of equipment state monitoring and early warning, in particular to an early fault early warning method for a rotary machine.
Background
The rotary machine is widely used in the process industry, and the safe operation of the equipment can bring good economic benefit and social benefit, so that the early fault early warning of the rotary machine is very important. Because the conventional alarm threshold line is set as a fixed threshold line according to the national standard of related equipment, the fixed threshold alarm method has the problems of insufficient alarm or repeated alarm of the same event; there is a problem that it is difficult to track occurrence and development of a failure at the initial stage of occurrence of the failure; there is a problem in that it is difficult to implement predictive maintenance of the equipment to ensure the safety of the operation of the equipment. If the alarm threshold is lowered to enable the monitoring system to achieve early warning, the monitoring data may pass through the alarm line repeatedly due to the influence of noise and acquisition errors, and thus an alarm may be generated erroneously. The early failure early warning technology capable of solving the problems is researched by fully utilizing the monitoring parameter data of the online monitoring system of the equipment, so that the hidden danger is prevented from developing into an accident, the influence consequences of safety, environment, production loss and the like possibly brought to enterprises by untimely failure warning or false warning of the equipment are reduced, and the early failure early warning technology has important engineering research significance.
Disclosure of Invention
The invention aims to provide an early fault early warning method for rotary equipment, which is characterized in that a vibration characteristic signal of the equipment is extracted based on a mechanical equipment operation reliability function (a spectral distance index function), and l is utilized1The trend filtering technology carries out filtering processing on the vibration characteristic signals, an early fault early warning model based on the reliability function trend filtering technology is constructed according to slope changes of a curve of the filtered vibration characteristic signals, whether early faults occur or not is judged according to the principle that whether the early faults occur or not is not based on a fixed threshold alarm line, and when the slope changes of the curve after the trend filtering of the vibration characteristic signals exceed a certain set multiple, the early faults are considered to occur, so that early warning of abnormal operation of equipment is achieved, the alarm accuracy of the equipment is improved, and technical support is provided for predictive maintenance of the equipment.
In order to achieve the above object, the present invention provides an early warning method for early failure of a rotating device, comprising:
step1, selecting the normal state monitoring data of the rotating equipment as reference data, and extracting equipment vibration characteristic signals according to a spectrum distance index function;
step2 use l1Trend filtering technique on vibration characteristicsPerforming trend filtering processing on the signals to obtain a smooth real vibration trend curve of the unit after an acquisition error is eliminated;
step3, calculating the derivative value of each point of the smooth vibration trend curve, selecting a certain point in the normal running state as a reference point, and taking the derivative value of the point as a reference value;
and Step4, presetting a threshold multiple, and when the derivative value at the real-time data point exceeds the threshold multiple of the reference value, determining that the equipment has early failure and generating early warning.
The method for extracting the equipment vibration characteristic signal according to the spectral distance index function specifically comprises the following steps:
(1) selecting normal state monitoring data x (t) of the rotating equipment and real-time monitoring data y (t), J in the vibration characteristic signalx,yIs the J divergence between the operating "excellent" state signal x (t) and the state signal to be evaluated y (t), which can be expressed as:
in the formula, Sx(k) And Sy(k) The self-power spectrums of the signals x (t) and y (t) respectively, wherein N is the number of power spectral lines;
(2) calculating a spectral distance index function R:
in the formula, α is a sensitivity coefficient determined by the tendency of device performance degradation.
Said adopt1The trend filtering technology carries out trend filtering processing on the vibration characteristic signal to obtain a smooth real vibration trend curve of the unit after an acquisition error is eliminated, and the method specifically comprises the following steps:
(1) setting the smoothness coefficient lambda of the trend filtering, and taking the value of lambda according to the actual requirement on signal processing;
(2) by means of1The trend filtering technology carries out filtering processing on the vibration characteristic signal extracted by the spectral distance index function to obtainEliminating the collection error and smoothing the real vibration trend curve of the unit;
(3)l1the trend filtering technique is implemented by a minimum weighted objective function, even if the following equation is minimal, the equation being:
(1/2)
in the formula, yi(i-1, …, n) is a standard time sequence, i.e. a vibration signature, xiFor basic trend, n is the number of vibration characteristic signal groups, and λ is a non-negative parameter to control the smoothness of the trend line and the size of balance remainder, and to control the balance between estimated trend and signal redundancy.
The method for solving the derivative value of each point of the smooth vibration trend curve specifically comprises the following steps:
and calculating the slope magnitude of each point of the vibration trend curve according to a derivation formula, namely calculating the magnitude of a derivative value.
The method comprises the following steps that a threshold multiple is preset, when the derivative value of a real-time data point exceeds the threshold multiple of a reference value, early failure of equipment is considered to occur, and early warning is generated, and the method specifically comprises the following steps:
(1) setting a threshold multiple m, wherein the value of m needs to be obtained by training according to the monitoring data of the previous fault cases. The more the derivative value of the reference point approaches to 0, the larger the value of the adjustment parameter m needs to be; the farther the derivative value of the reference point is from 0, the smaller the value of the adjustment parameter m needs to be;
(2) derivative value k at real-time data point ii(i ═ 1,2, …, n), where n is the number of data samples. Taking a point i in the normal operation state0Derivative value of
As a point of reference, the position of the reference,
is generally close to 0, provided that
When the equipment is in normal operation state, when the equipment is in normal operation state
And judging that the equipment is operated to deviate from a normal state or early faults occur.
The invention has the following beneficial effects:
the invention provides a early-starting fault early-warning method for rotary equipment1And filtering the vibration characteristic signal by using a trend filtering technology, and judging that the equipment has early failure and generates early warning when the derivative value at the real-time data point exceeds the threshold multiple of the reference value according to the slope change of the vibration characteristic signal curve after filtering. The method reduces the problems of insufficient alarm or repeated alarm of the same event, can predict the occurrence and development of the early failure of the equipment, can master the occurrence and development situations of the early failure of the normally-operated equipment in real time, and can provide technical support for predictive maintenance of the equipment.
Drawings
FIG. 1 is a schematic diagram of the algorithm flow of the present invention;
FIG. 2 is a graph of spectral distance index coefficient trend filtering;
FIG. 3 is a graph showing the variation of the derivative of the index coefficient of spectral distance;
fig. 4 shows a data spectrum diagram at an early fault point.
Detailed Description
The following further description is made in conjunction with the accompanying drawings and the specific embodiments.
Referring to fig. 1, the early fault warning method for a rotating machine of the present invention includes:
selecting the normal state monitoring data of the rotating equipment as reference data, and extracting equipment vibration characteristic signals according to a spectral distance index function;
by means of1The trend filtering technology carries out trend filtering processing on the vibration characteristic signal to obtain a smooth real vibration trend curve of the unit after the acquisition error is eliminated;
calculating derivative values of all points of the smooth vibration trend curve, selecting a certain point in a normal running state as a reference point, and taking the derivative value of the point as a reference value;
presetting a threshold multiple, and when the derivative value at the real-time data point exceeds the threshold multiple of the reference value, determining that the equipment has early failure and generating early warning.
Specifically, the 200 th group of data of the bearing normal operation of the NSFI/UCR center bearing experiment table No.2 of the university of Xinxinati in the United states is taken as a reference, all data of the bearing from the operation to the bad operation are selected as monitoring data, and the spectral distance index in the whole life cycle of the bearing is calculated.
By means of1Performing trend filtering processing on the spectral distance index by a trend filtering technology, setting a smoothness coefficient lambda of the trend filtering to be 75, and obtaining a smooth real vibration trend curve of the unit after eliminating the acquisition error, wherein comparison graphs before and after the trend filtering of the spectral distance index are shown in fig. 2;
obtaining the derivative value of each point of the curve after the spectral distance index trend filtering, wherein the derivative value curve is shown in fig. 3, the derivative value at the 200 th group of data is selected as a reference value, and the derivative value of the reference point is close to 0;
according to the value size of the abrupt change of the derivative curve, a threshold multiple m is preset to be 5, and k is provided at the 533 th group of data533＞5×k200It is thus determined that the bearing data may have an early failure at 533.
In order to identify the early failure point of the experimental data, the No.2 bearing outer ring failure data is subjected to spectrum analysis, and the result is shown in fig. 4. No fault characteristic frequency appears in the spectrogram (4(a)) of the 532 th group of data, and a fault characteristic frequency appears in the bearing outer ring in the spectrogram (4(b)) of the 533 th group of data. Thus, early failure of the bearing occurred at group 533.
Claims (5)
1. A early fault early warning method for rotating equipment is characterized by comprising the following steps: the method comprises the following steps of,
step1, selecting the normal state monitoring data of the rotating equipment as reference data, and extracting equipment vibration characteristic signals according to a spectrum distance index function;
step2 use l1The trend filtering technology carries out trend filtering processing on the vibration characteristic signal to obtain a smooth real vibration trend curve of the unit after the acquisition error is eliminated;
step3, calculating the derivative value of each point of the smooth vibration trend curve, selecting a certain point in the normal running state as a reference point, and taking the derivative value of the point as a reference value;
and Step4, presetting a threshold multiple, and when the derivative value at the real-time data point exceeds the threshold multiple of the reference value, determining that the equipment has early failure and generating early warning.
2. The early warning method for the fault of the rotating equipment according to claim 1, wherein the early warning method comprises the following steps: the method for extracting the equipment vibration characteristic signal according to the spectral distance index function specifically comprises the following steps,
(1) selecting normal state monitoring data x (t) of the rotating equipment and real-time monitoring data y (t), J in the vibration characteristic signalx,yIs the J divergence between the running "excellent" state signal x (t) and the state signal to be evaluated y (t), expressed as:
in the formula, Sx(k) And Sy(k) The self-power spectrums of the signals x (t) and y (t) respectively, wherein N is the number of power spectral lines;
(2) calculating a spectral distance index function R:
in the formula, α is a sensitivity coefficient determined by the tendency of device performance degradation.
3. The early warning method for the fault of the rotating equipment according to claim 1, wherein the early warning method comprises the following steps: said adopt1Trend filtering technology for trend filtering vibration characteristic signalsWave processing is carried out to obtain a smooth real vibration trend curve of the unit after the acquisition error is eliminated, and the method specifically comprises the following steps:
(1) setting the smoothness coefficient lambda of the trend filtering, and taking the value of lambda according to the actual requirement on signal processing;
(2) by means of1The trend filtering technology carries out filtering processing on the vibration characteristic signals extracted by the spectral distance index function to obtain a smooth real vibration trend curve of the unit after the acquisition error is eliminated;
(3)l1the trend filtering technique is implemented by a minimum weighted objective function, even if the following equation is minimal, the equation being:
in the formula, yi(i-1, …, n) is a standard time sequence, i.e. a vibration signature, xiFor basic trend, n is the number of vibration characteristic signal groups, and λ is a non-negative parameter to control the smoothness of the trend line and the size of balance remainder, and to control the balance between estimated trend and signal redundancy.
4. The early warning method for the fault of the rotating equipment according to claim 1, wherein the early warning method comprises the following steps: the method for solving the derivative value of each point of the smooth vibration trend curve specifically comprises the following steps:
and calculating the slope magnitude of each point of the vibration trend curve according to a derivation formula, namely calculating the magnitude of a derivative value.
5. The early warning method for the fault of the rotating equipment according to claim 1, wherein the early warning method comprises the following steps: the method comprises the following steps that a threshold multiple is preset, when the derivative value of a real-time data point exceeds the threshold multiple of a reference value, early failure of equipment is considered to occur, and early warning is generated, and the method specifically comprises the following steps:
(1) setting a threshold multiple m, wherein the value of m needs to be obtained according to the training of the monitoring data of the previous fault case; the more the derivative value of the reference point approaches to 0, the larger the value of the adjustment parameter m needs to be; the farther the derivative value of the reference point is from 0, the smaller the value of the adjustment parameter m needs to be;
(2) derivative value k at real-time data point ii(i ═ 1,2, …, n), where n is the number of data samples; taking a point i in the normal operation state0Derivative value of
As a point of reference, the position of the reference,
is generally close to 0, provided that
When the equipment is in normal operation state, when the equipment is in normal operation state
And judging that the equipment is operated to deviate from a normal state or early faults occur.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010031040.8A CN111222247A (en) | 2020-01-13 | 2020-01-13 | Early fault early warning method for rotary machine |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010031040.8A CN111222247A (en) | 2020-01-13 | 2020-01-13 | Early fault early warning method for rotary machine |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111222247A true CN111222247A (en) | 2020-06-02 |
Family
ID=70826739
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010031040.8A Pending CN111222247A (en) | 2020-01-13 | 2020-01-13 | Early fault early warning method for rotary machine |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111222247A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723998A (en) * | 2020-06-28 | 2020-09-29 | 国网湖南省电力有限公司 | Early warning method for fault of oil pressure system of generator oil pressure tank |
| CN112267979A (en) * | 2020-10-26 | 2021-01-26 | 积成电子股份有限公司 | Early warning method and system for judging failure of yaw bearing |
| CN112395550A (en) * | 2020-11-19 | 2021-02-23 | 中国船舶重工集团公司第七0四研究所 | Rotary machine fault early warning method based on visual characteristic parameter matrix |
| CN112525336A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Automatic detection method for continuous increase of vibration of mechanical equipment |
| CN114135477A (en) * | 2021-10-11 | 2022-03-04 | 昆明嘉和科技股份有限公司 | Pump equipment state monitoring dynamic threshold early warning method |
| CN114460024A (en) * | 2020-11-10 | 2022-05-10 | 蓝星智云(山东)智能科技有限公司 | Method and system for online real-time monitoring of hydrogen and chlorine in hydrogen chloride synthesis furnace |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5561610A (en) * | 1994-06-30 | 1996-10-01 | Caterpillar Inc. | Method and apparatus for indicating a fault condition |
| JP2009115481A (en) * | 2007-11-02 | 2009-05-28 | Jfe Advantech Co Ltd | Diagnosis system of rotary machine facility |
| CN105510023A (en) * | 2015-11-24 | 2016-04-20 | 国网内蒙古东部电力有限公司电力科学研究院 | Divergence-index-based fault diagnosis method of variable-working-condition wind-power planetary gearbox |
| CN105588717A (en) * | 2015-12-10 | 2016-05-18 | 潍坊学院 | Gearbox fault diagnosis method |
| CN110208019A (en) * | 2019-05-14 | 2019-09-06 | 北京博华信智科技股份有限公司 | A kind of dynamic equipment condition monitoring dynamic threshold method for early warning |
-
2020
- 2020-01-13 CN CN202010031040.8A patent/CN111222247A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5561610A (en) * | 1994-06-30 | 1996-10-01 | Caterpillar Inc. | Method and apparatus for indicating a fault condition |
| JP2009115481A (en) * | 2007-11-02 | 2009-05-28 | Jfe Advantech Co Ltd | Diagnosis system of rotary machine facility |
| CN105510023A (en) * | 2015-11-24 | 2016-04-20 | 国网内蒙古东部电力有限公司电力科学研究院 | Divergence-index-based fault diagnosis method of variable-working-condition wind-power planetary gearbox |
| CN105588717A (en) * | 2015-12-10 | 2016-05-18 | 潍坊学院 | Gearbox fault diagnosis method |
| CN110208019A (en) * | 2019-05-14 | 2019-09-06 | 北京博华信智科技股份有限公司 | A kind of dynamic equipment condition monitoring dynamic threshold method for early warning |
Non-Patent Citations (1)
| Title |
|---|
| JIAHE LIU 等: "A fault early warning and health status rating method for ensuring safe operation of rotating equipement", 《2019 6TH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND CONTROL ENGINEERING (ICISCE)》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111723998A (en) * | 2020-06-28 | 2020-09-29 | 国网湖南省电力有限公司 | Early warning method for fault of oil pressure system of generator oil pressure tank |
| CN112267979A (en) * | 2020-10-26 | 2021-01-26 | 积成电子股份有限公司 | Early warning method and system for judging failure of yaw bearing |
| CN114460024A (en) * | 2020-11-10 | 2022-05-10 | 蓝星智云(山东)智能科技有限公司 | Method and system for online real-time monitoring of hydrogen and chlorine in hydrogen chloride synthesis furnace |
| CN114460024B (en) * | 2020-11-10 | 2024-04-26 | 蓝星智云(山东)智能科技有限公司 | Hydrogen and chlorine online real-time monitoring method and system in hydrogen chloride synthesis furnace |
| CN112525336A (en) * | 2020-11-18 | 2021-03-19 | 西安因联信息科技有限公司 | Automatic detection method for continuous increase of vibration of mechanical equipment |
| CN112395550A (en) * | 2020-11-19 | 2021-02-23 | 中国船舶重工集团公司第七0四研究所 | Rotary machine fault early warning method based on visual characteristic parameter matrix |
| CN114135477A (en) * | 2021-10-11 | 2022-03-04 | 昆明嘉和科技股份有限公司 | Pump equipment state monitoring dynamic threshold early warning method |
| CN114135477B (en) * | 2021-10-11 | 2024-04-02 | 昆明嘉和科技股份有限公司 | Dynamic threshold early warning method for monitoring state of machine pump equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111222247A (en) | Early fault early warning method for rotary machine | |
| CN110298455B (en) | Mechanical equipment fault intelligent early warning method based on multivariate estimation prediction | |
| Duman et al. | Acoustic anomaly detection using convolutional autoencoders in industrial processes | |
| CN109211548A (en) | A kind of mechanical failure diagnostic method | |
| CN112487910A (en) | Fault early warning method and system for nuclear turbine system | |
| Han et al. | Fault detection of pneumatic control valves based on canonical variate analysis | |
| CN107202027A (en) | A kind of large fan operation trend analysis and failure prediction method | |
| KR100997009B1 (en) | The method for dynamic detection and on-time warning of industrial process | |
| CN110209144B (en) | Two-layer real-time monitoring and alarm tracing method based on dynamic and static cooperative difference analysis | |
| Khan et al. | System design for early fault diagnosis of machines using vibration features | |
| CN114061743A (en) | Vibration monitoring method, device, equipment and medium for wind generating set | |
| CN109238455A (en) | A kind of characteristic of rotating machines vibration signal monitoring method and system based on graph theory | |
| CN115578084A (en) | Wind turbine generator set frequency converter fault early warning method based on deep convolution self-encoder | |
| CN106441843B (en) | A kind of rotating machinery fault method for waveform identification | |
| Ginart et al. | Automated feature selection for embeddable prognostic and health monitoring (PHM) architectures | |
| CN109779938B (en) | Intelligent interlocking protection method for centrifugal compressor unit | |
| CN111913463B (en) | State monitoring method for chemical volume control system of nuclear power plant | |
| CN109872511B (en) | Self-adaptive two-stage alarm method for monitoring axial displacement sudden change | |
| CN116796261A (en) | Closed switch equipment mechanical characteristic prediction method based on artificial intelligence | |
| CN114818779A (en) | Fan rotor fault diagnosis method based on hierarchical classification algorithm | |
| Zheng et al. | Wavelet packet decomposition and neural network based fault diagnosis for elevator excessive vibration | |
| Rosli et al. | Application of Principle Component Analysis in Resolving Influential Factor Subject to Industrial Motor Failure | |
| CN104048287A (en) | Boiler drum water level alarming method based on RBF (Radial Basis Function) network | |
| CN111915052B (en) | Self-adaptive test method for intelligent prediction algorithm of analog measurement value | |
| CN102900534B (en) | Gas turbine vibration prevention monitoring and protecting method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200602 |