CN102837711B - Infrared waveform based intelligent identification method for railway bearing - Google Patents
Infrared waveform based intelligent identification method for railway bearing Download PDFInfo
- Publication number
- CN102837711B CN102837711B CN201110166933.4A CN201110166933A CN102837711B CN 102837711 B CN102837711 B CN 102837711B CN 201110166933 A CN201110166933 A CN 201110166933A CN 102837711 B CN102837711 B CN 102837711B
- Authority
- CN
- China
- Prior art keywords
- infrared
- squiggle
- normalized temperature
- waveform
- 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.)
- Active
Links
Landscapes
- Train Traffic Observation, Control, And Security (AREA)
- Radiation Pyrometers (AREA)
Abstract
The invention relates to a method of identifying bearing failures, in particular to an infrared waveform based intelligent identification method for a railway bearing. The method is based on a dynamic standard waveform of a specific detecting spot, a vertical scan in the original method is substituted with a once horizontal scan for processing the infrared waveform, and therefore, the nature of distinguishing a normal infrared waveform from an abnormal infrared waveform is reflected. With the adoption of the technical scheme, the intelligent identification method based on waveform characteristics is standard, concise and good in effect, and the workload can be effectively reduced on the premise that the effect of the method is better or not worse than that of artificial identification.
Description
Technical field
The present invention relates to a kind of detection recognition methods judging bearing fault, more particularly, refer to the method for the infrared waveform Intelligent Recognition of a kind of railway bearing.
Background technology
Bearing is the critical component of vehicle, and bearing fault is one of major failure source in train operation.Because bearing life has certain discreteness, in order to prevent from firing the generation of cutting axle accident, China railways establishes infrared vehicle axle temperature intelligent detecting system, online bearing temperature monitoring is carried out to operating rolling stock, system employing decentralized detection, the operating mode that networking is concentrated, road bureau manually reports to the police, effectively reduce the generation that axle accident is cut in combustion after spread.
Infrared vehicle axle temperature intelligent detecting system is about along the railway sets up 1 unattended acquisition station to carry out axle temperature detection every 30 km, site environment is complicated, severe, various factors such as vibration, impact, unexpected thermal source, sleet mist etc. all may affect axle temperature detection quality, cause unusual waveforms, other factors detect abnormal as system or defective mounting, power supply voltage instability etc. also can produce.Common Wave anomaly have all kinds of burr, sunlight interference, full pressure, not full, be shifted, narrow, broaden.
For solving interference problem, each railway axle temperature intelligent detecting system manufacturer have employed many measures at acquisition station, achieve certain effect, but in the infrared networking concentrated alarm of road bureau, still have the abnormal data of larger amt, increase the work capacity of infrared watch keeper, once there be strong sharp thermal warning, infrared watch keeper must within very short time, check infrared ray waveform, make correct judgement.Along with infrared watch keeper is responsible for the increase of equipment, abnormal data disturbs normal work, and infrared waveform Weigh sensor is extremely important.
Along with the progress of technology, China has carried out the research of hot box integrated alarm and has used, now infrared shaft temperature information is still important judging basis, its correctness, significant to the enforcement of integrated alarm, be necessary the intelligent identification Method realizing it, and then effectively realize the warning of hot box comprehensive automation.
Original infrared shaft temperature method for waveform identification mainly contains following several:
A, difference and many (being generally less than 4) step method of finite difference, calculate the difference of the adjacent multi-point of axle temperature curve, Wave anomaly is judged whether by the size of multistep difference and distribution (peak value number), the method is generally used for process burr type unusual waveforms, and in order to calculate, waveform rises multistep difference, falling edge provides mark simultaneously;
B, area-method, the area that calculated characteristics position (as whole, front portion, middle part, rear portion) temperature curve comprises and relative size relation thereof are to judge whether Wave anomaly, and the method is generally used for process sunlight interference waveform;
C, Furthest Neighbor, calculate the distance of squiggle and reference waveform, judges bearing type and whether normal;
D, correlation method, calculate the coefficient of correlation of squiggle and reference waveform, judges bearing type and whether normal;
E, other, as neural network etc.
But method mainly has disclosed in above-mentioned prior art: 1. arrange for the feature of difference exception; 2. the order of original algorithm Main Basis axle temperature data, the Measures compare of reflection data characteristics is complicated, as the difference mainly for all kinds of burr is just divided into a variety of; 3. calibrated curve obtains from all waveforms, and specific aim is not strong, passes judgment on threshold and determine difficulty; 4. original algorithm does not effectively embed the feature of normal waveform.
Summary of the invention
Based on the weak point of method disclosed in above-mentioned prior art, goal of the invention of the present invention there are provided a kind of intelligent identification Method based on wave character, and method specification is succinct, respond well.
Another goal of the invention of the present invention is the waveform intelligent identification Method adopting the present invention's proposition in addition, can be better than in effect or no less than under the prerequisite of artificial congnition, effectively reduce work capacity.
In order to realize above-mentioned goal of the invention, the present invention adopts following technical scheme:
A method for the infrared waveform Intelligent Recognition of railway bearing, comprises following step:
(1) preset reference normalized temperature Y
0;
(2) by certain bearing by time the current infrared normalized temperature curve of axle temperature transfinite and described benchmark normalized temperature Y
0relatively, obtain allly being not less than described benchmark normalized temperature Y
0the position of point for measuring temperature;
(3) if all of acquisition are not less than described benchmark normalized temperature Y
0point for measuring temperature position continuous, and do not comprise the beginning or end of infrared normalized temperature curve, then carry out the operation of (4), otherwise be directly judged to unusual waveforms;
(4) described current infrared normalized temperature curve is fixed to the interpolation of pattern, obtains standardization squiggle and the characteristic parameter thereof of this current infrared normalized temperature curve;
(5) Current specifications squiggle and characteristic parameter and measuring point dynamic standard squiggle and measuring point characteristic parameter are compared judge.
The invention described above adopt improve one's methods in generate the standardize method of squiggle of the step of described measuring point dynamic standard squiggle and measuring point characteristic parameter and above-mentioned formation basically identical, specifically comprise:
(1) preset reference normalized temperature Y
0;
(2) by certain infrared normalized temperature curve of certain measuring point and described benchmark normalized temperature Y
0relatively, obtain allly being not less than described benchmark normalized temperature Y
0the position of point for measuring temperature;
(3) if all of acquisition are not less than described benchmark normalized temperature Y
0point for measuring temperature position continuous, and do not comprise the beginning or end of infrared normalized temperature curve, then carry out the operation of (4);
(4) certain infrared normalized temperature curve described is fixed to the interpolation of pattern, obtains standardization squiggle and the characteristic parameter thereof of this current infrared normalized temperature curve;
(5) pointwise statistics is carried out to the described standardization squiggle of this measuring point specified requirements, obtain measuring point dynamic standard squiggle;
(6) statistics is carried out to the described standardization squiggle characteristic parameter of this measuring point specified requirements and obtain measuring point characteristic parameter.
In the present invention, if identify, point for measuring temperature position is abscissa X, the corresponding normalized temperature of point for measuring temperature is ordinate Y, and above-described fixed mode interpolation method can specifically be expressed as:
(1) infrared normalized temperature curve relatively described benchmark normalized temperature Y is obtained
0just pass through point (X
0+, Y
0) and negative pass through point (X
0-, Y
0);
(2) positive and negative, an abscissa [X is passed through to infrared normalized temperature curve
0+, X
0-] between carry out the equidistant interpolation of n point, generating standard squiggle, wherein the span of n is between 18-24.
The waveform feature parameter extracted has standardization squiggle center (X
0++ X
0-)/2 and standardization squiggle width (X
0--X
0+)/2.
When carrying out Current specifications squiggle and characteristic parameter compares judge with measuring point dynamic standard squiggle and measuring point characteristic parameter, center of curve and these two characteristic parameters of curve width to be assessed on the one hand, also will assess Current specifications waveform and the maxim difference of the corresponding interpolation point of measuring point dynamic standard waveform and the coefficient of correlation between Current specifications waveform and measuring point dynamic standard waveform on the other hand.
It should be noted that, described measuring point dynamic standard squiggle and characteristic parameter carry out upgrading when reaching default time threshold values or quantity threshold values and to carry out with the same category of device reference waveform of infrared central store and characteristic parameter comparison confirms, the measuring point dynamic standard squiggle that described Current specifications squiggle and characteristic parameter all confirm with corresponding measuring point latest update and characteristic parameter compare judge.Such one side can the comformability of basic guarantee measuring point dynamic standard waveform and real-time, can also monitor, be beneficial to the maintenance of equipment on the other hand and state ensures to the state of the art of measuring point.
In the present invention, the measuring point standardization waveform of more refinement can be generated for special vehicle and bearing type, to realize the identification of more refinement.
In the process realizing the above-mentioned method of the present invention, preferably, described benchmark normalized temperature Y
0value is between 50-70.More preferably, described benchmark normalized temperature Y
0value is 60.
By adopting above-mentioned technical scheme, the invention provides a kind of intelligent identification Method based on wave character, method is succinct, respond well.Waveform intelligent identification Method of the present invention in addition, can be better than in effect or no less than under the prerequisite of artificial congnition, effectively reduce work capacity.
Accompanying drawing explanation
What show in Fig. 1 is the existing method flow diagram of the measurement railway bearing adopted in prior art;
What show in Fig. 2 is the diagram of circuit of the method for the measurement railway bearing adopted in the present invention;
What show in Fig. 3 is the normal infrared normalized temperature curve sample of certain measuring point in the embodiment of the present invention;
That show in Fig. 4 is infrared normalized temperature curve sample relative datum normalized temperature Y in the embodiment of the present invention
0positive and negatively pass through a situation;
What show in Fig. 5 is the process of carrying out equidistant interpolation generating standard waveform in the embodiment of the present invention between positive and negative passing through a little;
What show in Fig. 6 is measuring point specification waveform parameter statistical graph in the embodiment of the present invention;
What show in Fig. 7 is that the pointwise statistics of measuring point dynamic standard waveform in the embodiment of the present invention generates;
What show in Fig. 8-Figure 12 is the sample graph being judged as obvious exception or unusual waveforms in the embodiment of the present invention; its chain lines (---*---) is 32 current infrared normalized temperature curves; basin type smooth curve is corresponding measuring point dynamic standard squiggle, and irising wipe line (---o---) if any Article 3 is then the standardization squiggle of current infrared normalized temperature curve.
Detailed description of the invention
The invention reside in and provide a kind of intelligent identification Method based on wave character, method specification is succinct, respond well.Waveform intelligent identification Method of the present invention, can be better than in effect or no less than under the prerequisite of artificial congnition, effectively reduce work capacity.
Below in conjunction with Figure of description, the specific embodiment of the present invention is described in detail.
Fig. 1 display be the infrared shaft temperature method for waveform identification flow process (draw from " train axle temperature detection system data processing algorithm and realization ") adopted in prior art, algorithm flow comprises: spike differentiations, surge detection, tub curve differentiates, waveform becomes fat differentiation, waveform moves and differentiates and characteristic distance calculating etc.Algorithm emphasis is the pretreatment to various unusual waveforms, and the Structure and Process of main program is clear, is the process of an order execution subroutine from top to bottom.
To analyze and determination system of train wheel axles data processing algorithm block diagram can be seen from above: disclosed in prior art, method mainly has: 1. arrange for the feature of difference exception; 2. the order of original algorithm Main Basis axle temperature data, the Measures compare of reflection data characteristics is complicated, as the difference mainly for all kinds of burr is just divided into a variety of; 3. calibrated curve is added up and is obtained and apply to all measuring points from the waveform of typical IR measuring point, and specific aim is not strong, and threshold range is wide; 4. original algorithm does not effectively embed the feature of normal waveform.
Fig. 2 is the flow process of the infrared waveform intelligent identification Method of railway bearing of the present invention, contrast prior art diagram of circuit (Fig. 1), can see: existing infrared method for waveform identification is based on unusual waveforms feature, so the Measures compare needed is many; Have employed unified calibrated curve in existing method, and actual waveform and measuring point relation are comparatively large, make the setting difficulty of threshold value in prior art, a very wide scope can only be provided; The present invention proposes the intelligent identification Method based on the normal wave character of measuring point, specification is succinct, respond well.
New mode is based on following normal waveform essential characteristic: the point for measuring temperature being greater than certain suitable temperature value (or normalized temperature value) is continuous print and is positioned at middle part; For same measuring point, the number of these points for measuring temperature changes in a less scope; For same measuring point, the position of these points for measuring temperature changes in a less scope; For same measuring point, the curve of these points for measuring temperature composition is similar and numerical value is close.
New mode is different from has 2 points the most at all in original method: 1 be normal waveform for concrete measuring point, solve threshold offering question; 2 is have employed once laterally " scanning " to infrared waveform to instead of in original method vertical " scanning " repeatedly, reflects the essence that normal infrared waveform distinguishes unusual waveforms, method specification, succinctly, strong adaptability.
New mode mainly contains two large links: the dynamic standard waveform based on measuring point generates; The infrared waveform of axle temperature transfinite according to normal waveform model is passed judgment on.
And concrete grammar of the present invention comprises following step:
(1) preset reference normalized temperature Y
0;
(2) by certain bearing by time the current infrared normalized temperature curve of axle temperature transfinite and described benchmark normalized temperature Y
0relatively, obtain allly being not less than described benchmark normalized temperature Y
0the position of point for measuring temperature;
(3) if all of acquisition are not less than described benchmark normalized temperature Y
0point for measuring temperature position continuous, and do not comprise the beginning or end of infrared normalized temperature curve, then carry out the operation of (4), otherwise be directly judged to unusual waveforms;
(4) described current infrared normalized temperature curve is fixed to the interpolation of pattern, obtains standardization squiggle and the characteristic parameter thereof of this current infrared normalized temperature curve;
(5) Current specifications squiggle and characteristic parameter and measuring point dynamic standard squiggle and measuring point characteristic parameter are compared judge.
Because the forming step of measuring point dynamic standard squiggle is substantially identical by the forming step than squiggle with current, therefore this only casehistory form the step of measuring point dynamic standard squiggle.Fig. 3-Fig. 7 illustrates and generates each step of measuring point dynamic standard squiggle, below in conjunction with the squiggle in Fig. 3-Fig. 7, concrete grammar of the present invention is described.
1.1 carry out preliminary differentiation to certain measuring point axle temperature data, obtain the set of the normal waveform of this measuring point;
1.1.1 benchmark normalized temperature Y is set
0, benchmark normalized temperature can be set between 50-70;
1.1.2 by 32 axle temperature normalized temperature curves recording and benchmark normalized temperature Y
0compare, obtain allly being not less than benchmark normalized temperature Y
0the position of point for measuring temperature;
Benchmark normalized temperature Y is not less than if 1.1.3 all
0the position of point for measuring temperature continuously (spacing is 1) and do not comprise starting point and terminal, then thinks that these 32 axle temperature normalized temperature curves are normal waveform.
1.2 statistics extract these measuring point ordinary wave shape parameters, ripple is wide, center, reference waveform etc.;
1.2.1 bar 32 axle temperature curves every in 1.1 are processed, obtain the positive and negative of curve relative datum normalized temperature and pass through point (X
0+, Y
0) and (X
0-, Y
0);
1.2.2 width and center that this curve is not less than benchmark normalized temperature is obtained, center equals (X
0++ X
0-)/2, width equals (X
0--X
0+)/2;
1.2.3 positive and negative, an abscissa [X is passed through to infrared normalized temperature curve
0+, X
0-] between carry out n point (as 20 points, passing through a little containing positive and negative) equidistantly interpolation, obtain the standardization waveform of this curve;
1.2.4 curve width is obtained to 1.2.2 under this measuring point specified requirements and center is added up, obtain corresponding dynamic benchmark;
1.2.5 pointwise statistics is carried out to the standardization waveform of the regular length that 1.2.3 under this measuring point specified requirements obtains, obtain the dynamic standard standardization waveform of certain measuring point.
The 1.3 measuring point standardization waveforms that can generate more refinement for special vehicle and bearing type, now only need by the data in 1.1 by vehicle and bearing type grouping;
The measuring point standardization waveform of extraction and characteristic parameter compare with infrared center same category of device standardization waveform and characteristic parameter by 1.4, confirm correctness.
1.5 measuring point standardization waveforms can carry out timing as required, quantitatively or in real time dynamically generate.
The reason generated based on the dynamic standard standardization waveform of measuring point is that reference waveform and measuring point equipment have certain correlativity, differing greatly between normal waveform and reference waveform will be made according to unified reference waveform, be unfavorable for the setting of threshold value, be unfavorable for the judge based on normal waveform model; A potential utilization is, by the contrast of certain measuring point dynamic standard waveform and other same category of device reference waveforms of infrared center, can judge measuring point equipment state, instruct adjustment, the maintenance of measuring point equipment.
The infrared waveform intelligent identification Method of railway bearing of the normal waveform model of further foundation, center wide according to waveform continuity, ripple and carry out the infrared waveform of axle temperature transfinite to relevant, the corresponding interpolation point maximum amplitude difference of measuring point dynamic standard waveform and pass judgment on.
2.1 pairs of infrared waveforms of axle temperature transfinite, the method by 1.1 confirms whether it is normal waveform;
If 2.2 normal waveforms are the similar 1.2 measuring point reference waveforms step of producing then, extract wide, the center of ripple and generate the standardization waveform of current form;
2.3 calculate Current specifications waveforms and measuring point dynamic standard standardizes the coefficient of correlation of waveform, the maxim of corresponding interpolation point difference in magnitude;
2.4 according to 2.1,2.2,2.3 result---whether normal, ripple is wide, center, coefficient of correlation and corresponding interpolation point difference in magnitude maxim pass judgment on waveform correctness.
In addition, in order to more specifically describe technique effect of the present invention, and the technical scheme of clear and definite this method, have collected expanding on Dalian-Qinhuangdao Railway on November 6,30 days to 2010 July in 2007 micro-, strong, swash thermal warning and process information carries out comparative evaluation.
Total sample number 16228, wherein 223 strong, swash thermal warning samples, through manual intervention (waveform artificial judgment, traffic control etc.) in practice, have 121 warnings to carry out blocking and stop and feed back.Below from strong swashing thermal warning sample, block that the waveform intelligent appraisement result of stopping sample is formed, evaluation result feedback is added up two aspects and assessed waveform intelligent appraisement effect in this paper.
Consider practice, critical parameter (center, ripple wide, coefficient of correlation, pointwise difference maxim etc.) have employed interval setting, and namely add and pass judgment on uncertain class, such waveform needs manually to confirm again.According to adding up each parameter distribution of obtaining, the interval of passing judgment on can be determined, as parameter to 223 swash by force thermal warning samples, 121 block and stop sample and carried out intelligent distinguishing, result is as table 1:
Table 1 swashs heat by force and infrared manually blocking stops sample Intelligent Recognition Comparative result
Note: obviously extremely refer to that waveform do not satisfy condition-the be greater than point of benchmark normalized temperature is discontinuous or comprise waveform beginning or end
Can see:
1, the infrared strong unusual waveforms ratio swashed in thermal warning of Datong-Qinhuangdao Railway is higher, and in 223 samples, 50 obviously abnormal, accounts for 22.42%; Abnormal 29, account for 13.00%; Toatl proportion is about 35%.
2, current manual confirmation screening is significant, swashs thermal warning to strong, and after manually passing judgment on, the obvious abnormal ratio of waveform is down to 8.26% from 22.42%, relatively declines 63.14%; Unusual waveforms ratio is down to 8.26% from 13.00%, relatively declines 36.45%; Meanwhile, normal waveform ratio rises to 71.07% from 51.12%, relatively rises 39.03%; Unascertainable ratio drops to 12.40% from 12.56%, relatively declines 1.27%.
If the evaluation result of the infrared waveform intelligent identification Method of a kind of railway bearing that this patent proposes is reliable, so will effectively reduce the work capacity of staff, staff only need confirm unascertainable portion waveshape, and the ratio of minimizing is not less than 85%.
Judge that whether the result of intelligent appraisement is reliable, need to stop feedback information analysis to corresponding blocking.Block at present and stop feedback and have 6 kinds: 1-to block to stop rear clearance, let pass after 2-uncouples, 3-bearing has fault after moving back and unloading, and 4-changes wheel and do not move back and unload, 5-bearing trouble free, 6-other 1 other 2; Because other situation information of 6-is indefinite, mainly can assess front 5 total situations (note: change wheel and do not move back to unload and do not mean that bearing has fault, according to the Ministry of Railways's ad hoc survey implemented by four directions, judge in problematic axle at the scene, bearing have obvious hurt less than 20%).
Table 1 Intelligent Recognition result stops feedback relationship table with blocking
Table 1 blocks 121 and stops sample and carried out waveform recognition, does not consider other situation of 6-, and in obviously abnormal and abnormal 18 (20-2) individual sample, the result of 13 blocks to park row; 4 bearings that normal sample contains all confirmations move back and have unloaded fault feedback, its centre bearer has fault and changes wheel and do not move back and unload 52, ratio is (4+48)/(86-5-2)=52/79=65.82%, is better than artificial congnition result (4+3+48+2+9)/(121-5-2-1-1-1-1)=66/110=60.00%.
It is that obviously abnormal or abnormal being recorded as is changed wheel and do not moved back the waveform sample unloaded that Fig. 8-Figure 12 lists all 5 Intelligent Recognition, can see that these waveforms are obviously problematic.
So the waveform intelligent identification Method adopting this method to propose, can be better than in effect or no less than under the prerequisite of artificial congnition, effectively reduce work capacity.
Protection scope of the present invention to be not limited in above-mentioned detailed description of the invention disclosed specific embodiment, as long as but the combination meeting technical characteristic in the claims in the present invention just fall within protection scope of the present invention.
Claims (9)
1. a method for the infrared waveform Intelligent Recognition of railway bearing, it is characterized in that, described method comprises following step:
(1) preset reference normalized temperature Y
0;
(2) by bearing by time the current infrared normalized temperature curve of axle temperature transfinite and described benchmark normalized temperature Y
0relatively, obtain allly being not less than described benchmark normalized temperature Y
0the position of point for measuring temperature;
(3) if all of acquisition are not less than described benchmark normalized temperature Y
0point for measuring temperature position continuous, and do not comprise the beginning or end of infrared normalized temperature curve, then carry out the operation of (4), otherwise be directly judged to unusual waveforms;
(4) described current infrared normalized temperature curve is fixed to the interpolation of pattern, obtains standardization squiggle and the characteristic parameter thereof of this current infrared normalized temperature curve;
(5) the standardization squiggle of current normalized temperature curve and characteristic parameter and measuring point dynamic standard squiggle and measuring point characteristic parameter are compared judge.
2. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1, is characterized in that, the step forming described measuring point dynamic standard squiggle comprises:
(1) preset reference normalized temperature Y
0;
(2) by the current infrared normalized temperature curve of measuring point and described benchmark normalized temperature Y
0relatively, obtain allly being not less than described benchmark normalized temperature Y
0the position of point for measuring temperature;
(3) if all of acquisition are not less than described benchmark normalized temperature Y
0point for measuring temperature position continuous, and do not comprise the beginning or end of infrared normalized temperature curve, then carry out the operation of (4);
(4) described current infrared normalized temperature curve is fixed to the interpolation of pattern, obtains standardization squiggle and the characteristic parameter thereof of this current infrared normalized temperature curve;
(5) pointwise statistics is carried out to the described standardization squiggle of this measuring point specified requirements, obtain measuring point dynamic standard squiggle;
(6) statistics is carried out to the described standardization squiggle characteristic parameter of this measuring point specified requirements and obtain measuring point characteristic parameter.
3. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1 and 2, is characterized in that, if identify, point for measuring temperature position is abscissa X, the corresponding normalized temperature of point for measuring temperature is ordinate Y, and the step of described fixed mode interpolation comprises:
(1) infrared normalized temperature curve relatively described benchmark normalized temperature Y is obtained
0just pass through point (X
0+, Y
0) and negative pass through point (X
0-, Y
0);
(2) positive and negative, an abscissa [X is passed through to infrared normalized temperature curve
0+, X
0-] between carry out the equidistant interpolation of n point, generating standard squiggle.
4. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 3, is characterized in that, described passes through an abscissa [X to infrared normalized temperature curve positive and negative
0+, X
0-] between carry out the equidistant interpolation of n point, n value is between 18-24.
5. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1 and 2, is characterized in that, described standardization squiggle characteristic parameter comprises:
(1) standardize squiggle center (X
0++ X
0-)/2;
(2) standardize squiggle width (X
0--X
0+)/2.
6. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1, it is characterized in that, described Current specifications squiggle and measuring point dynamic standard squiggle compare the comparison of the coefficient of correlation between maximum amplitude difference and curve passed judgment on and comprise corresponding interpolation point.
7. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1 and 2, it is characterized in that, described measuring point dynamic standard squiggle carries out upgrading when reaching default time threshold values or quantity threshold values and carries out characteristic parameter comparison confirmation with the same category of device reference waveform of infrared central store, and the measuring point dynamic standard squiggle that described Current specifications squiggle and characteristic parameter all confirm with corresponding measuring point latest update and characteristic parameter compare judge.
8. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 1 and 2, it is characterized in that, measuring point standardization waveform in order to realize more refinement can be generated, to realize the identification of more refinement for different automobile types and bearing type.
9. the method for the infrared waveform Intelligent Recognition of a kind of railway bearing according to claim 8, is characterized in that, described benchmark normalized temperature Y
0value is between 50-70.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110166933.4A CN102837711B (en) | 2011-06-21 | 2011-06-21 | Infrared waveform based intelligent identification method for railway bearing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201110166933.4A CN102837711B (en) | 2011-06-21 | 2011-06-21 | Infrared waveform based intelligent identification method for railway bearing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN102837711A CN102837711A (en) | 2012-12-26 |
| CN102837711B true CN102837711B (en) | 2015-04-08 |
Family
ID=47365508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201110166933.4A Active CN102837711B (en) | 2011-06-21 | 2011-06-21 | Infrared waveform based intelligent identification method for railway bearing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN102837711B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105466927B (en) * | 2014-07-02 | 2020-04-10 | 深圳迈瑞生物医疗电子股份有限公司 | Method for identifying, correcting and alarming abnormal reaction curve of turbidimetry |
| CN104679982B (en) * | 2014-12-29 | 2017-08-08 | 北京康拓红外技术股份有限公司 | A kind of recognition methods of the THDS system result of detection validity of feature based value detection |
| CN109812334B (en) * | 2019-03-27 | 2020-10-30 | 潍柴动力股份有限公司 | Engine main bearing fault monitoring method and device |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US2856540A (en) * | 1954-12-30 | 1958-10-14 | Gen Electric | Infrared detection apparatus |
| US4313583A (en) * | 1980-03-31 | 1982-02-02 | Servo Corporation Of America | Railroad car wheel bearing heat signal processing circuit |
| US4659043A (en) * | 1981-10-05 | 1987-04-21 | Servo Corporation Of America | Railroad hot box detector |
| CN101181901A (en) * | 2007-12-03 | 2008-05-21 | 北京康拓红外技术有限公司 | Hotbox distinguishing method for train infrared shaft-temperature detecting system |
| WO2008091444A1 (en) * | 2007-01-26 | 2008-07-31 | General Electric Company | Method and apparatus for monitoring bearings |
| CN101716945A (en) * | 2010-01-14 | 2010-06-02 | 广州科易光电技术有限公司 | Railway locomotive axle infrared thermal image monitoring method and system |
-
2011
- 2011-06-21 CN CN201110166933.4A patent/CN102837711B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US2856540A (en) * | 1954-12-30 | 1958-10-14 | Gen Electric | Infrared detection apparatus |
| US4313583A (en) * | 1980-03-31 | 1982-02-02 | Servo Corporation Of America | Railroad car wheel bearing heat signal processing circuit |
| US4659043A (en) * | 1981-10-05 | 1987-04-21 | Servo Corporation Of America | Railroad hot box detector |
| WO2008091444A1 (en) * | 2007-01-26 | 2008-07-31 | General Electric Company | Method and apparatus for monitoring bearings |
| CN101181901A (en) * | 2007-12-03 | 2008-05-21 | 北京康拓红外技术有限公司 | Hotbox distinguishing method for train infrared shaft-temperature detecting system |
| CN101716945A (en) * | 2010-01-14 | 2010-06-02 | 广州科易光电技术有限公司 | Railway locomotive axle infrared thermal image monitoring method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN102837711A (en) | 2012-12-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116660669B (en) | Power equipment fault on-line monitoring system and method | |
| CN111401583A (en) | Escalator full life cycle health management system based on predictive maintenance | |
| CN110533229B (en) | Track maintenance time prediction method and device | |
| CN109917213B (en) | Contact network detection fault early warning method based on dimensionality reduction fusion and factor analysis | |
| CN106056821A (en) | Power-transmission-line foreign-matter-invasion intelligent-video on-line monitoring evaluation system | |
| CN102633173A (en) | System and method for monitoring operation state of elevator car | |
| CN104925613A (en) | Online safety detection prewarning device of elevator and detection prewarning method thereof | |
| CN116227752B (en) | Park facility management system based on Internet of things | |
| CN101718634A (en) | Equipment state comprehensive dynamic alarming method based on multivariate probability model | |
| CN114386451B (en) | Contact net hanger fault diagnosis alarm method based on sensor information perception | |
| CN102837711B (en) | Infrared waveform based intelligent identification method for railway bearing | |
| CN115528810B (en) | Temperature measurement data operation analysis management system based on power equipment | |
| CN104677997A (en) | Transformer oil chromatography online monitoring differential early warning method | |
| CN113177646A (en) | Power distribution equipment online monitoring method and system based on self-adaptive edge proxy | |
| CN114135477A (en) | Pump equipment state monitoring dynamic threshold early warning method | |
| CN109298700B (en) | Method and system for judging abnormal change of operation parameters of thermal power generating unit in real time | |
| CN106325258B (en) | Relay protection device state evaluation method based on online monitoring information | |
| CN113007040B (en) | Online monitoring and fault early warning system and method for main shaft assembly movement of wind turbine generator | |
| CN117196590B (en) | Intelligent maintenance efficiency evaluation system for operation and maintenance of communication equipment | |
| CN117423225A (en) | Disaster remote sensing early warning system based on high-speed railway operation | |
| CN117708637A (en) | Wind turbine generator blade fault diagnosis method based on improved k-means clustering analysis | |
| CN112240267B (en) | Fan monitoring method based on wind speed correlation and wind power curve | |
| CN110319924A (en) | The online fault detection method of concrete production equipment and system based on noise decibel | |
| CN116188860A (en) | Method and device for identifying structural monitoring abnormal data with parameters adjusted in self-adaptive mode | |
| CN112014593B (en) | Device and method for monitoring and evaluating quality condition of railway track basic equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |