CN100472574C - Diesel oil power installation failure diagnosis system based on information amalgamation - Google Patents
Diesel oil power installation failure diagnosis system based on information amalgamation Download PDFInfo
- Publication number
- CN100472574C CN100472574C CNB2007101924806A CN200710192480A CN100472574C CN 100472574 C CN100472574 C CN 100472574C CN B2007101924806 A CNB2007101924806 A CN B2007101924806A CN 200710192480 A CN200710192480 A CN 200710192480A CN 100472574 C CN100472574 C CN 100472574C
- Authority
- CN
- China
- Prior art keywords
- module
- acquisition module
- electrically connected
- output terminal
- fusion
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a fault diagnosis system for a diesel power device based on information fusion, which includes: a fusion diagnosis subsystem (a monitor computer, a fusion diagnosis computer, a portable apparatuses, and a printer or an alarm), a signal conditioning subsystem (a serial port communications module, a USB collection module, a data collection card, a first collection module, a second collection module, a third collection module, a first signal conditioning module, and a second signal conditioning module), and a sensor subsystem (a pressure transmitter, a temperature transmitter, a rotating speed transmitter, a torque sensor, an explosion pressure sensor, and a vibration sensor).With the application of the method of information fusion, the invention successfully overcomes the current difficulty in locating the faults in the diesel power device, thus providing necessary means and technical support for the precise fault diagnosis of the diesel power device.
Description
Technical field
The invention belongs to the checkout equipment of mechanical driver unit, be specifically related to a kind of diesel powerplant fault diagnosis system.
Background technology
Diesel engine is as naval vessel a kind of power machine commonly used, in all kinds of naval vessels of naval, have extremely widely and use, and along with the development of military affairs, as the diesel engine of main power plant also just constantly to large-scale, at a high speed, carry by force, operation and high level of architectural complexity direction develop continuously.Diesel engine is the relatively poor relatively a kind of power machine of structure more complicated, reliability, and the general difficulty of its fault analysis is bigger, will cause the paralysis of weaponry in case break down, and tends to cause catastrophic consequence.Therefore, the diesel engine fault analysis has representative widely, and it is furtherd investigate, and the fault analysis of equipping for the naval vessel has general directive significance.
Whether the analysis of diesel engine fault is correct with diagnosis, and can appearance, the expansion of failure effect and the utilization of failure message resource etc. repeatedly for avoiding fault have decisive influence.In recent years and since diesel engine fault multiple, the diagnosis with improvement versatility and necessity, diesel engine failure diagnosis more and more is subject to people's attention.In the diesel engine failure diagnosis field, the single testing and diagnosing means and methods of main at present employing.Such as: based on the time domain of vibration signal, frequency domain character extraction and analysis method, based on the method for the diagnostic method of the fluctuation of speed, base engine torsional oscillation, based on method of engine thermal technology parameter etc.
Vibration analysis method, main measurement parameter are acceleration, speed and displacement.Vibration signal is the extremely responsive parameter that concerns between each parts in the reflection diesel engine, diesel vibration is that gas in the jar fires pressure, inlet and exhaust valve and takes a seat and impact and inlet and exhaust valve is opened the result of multiple exciting force combined actions such as gas shock, also be subjected to the influence of other factorses such as fuselage body vibration simultaneously, the existing periodic characteristic relevant on its form of expression with working cycle, become and some impact characteristics when again non-stationary being arranged, this extracts for signal analysis and sign and has brought very big difficulty.
Based on the diagnostic method of the fluctuation of speed, aspect diesel engine failure diagnosis, also obtained very big development in recent years.Diesel engine is when normal operating condition, and the power performance of each cylinder is answered basically identical, and machine run is more steady; Though the transient speed of each cylinder fluctuation is variant, always in a little scope, and present certain regularity.When a certain cylinder working of diesel engine undesired, faults such as oil-break, scuffing of cylinder bore or piston ring scuffing for example appear, and all the other cylinders just often, compare to some extent under the acting pressure of the cylinder that breaks down and the normal condition and descend, this certainly will will change the rotation speed change trend of this cylinder bent axle and flywheel when the acting, thereby causes the fluctuation of speed rule of bent axle and flywheel to change; Therefore, by analyzing the fluctuation pattern of speed of crankshaft, can diagnose the failure condition of each cylinder to a certain extent.But this method also has its weak point, though it can judge the abnormal cylinder of work position, can not determine to cause the reason of fault; The defective of this respect has then limited its range of application to a great extent.
Because the status signal travel path complexity of diesel engine, mapping relations between fault and the characteristic parameter are fuzzy, add the uncertainty of boundary condition, the factors such as polytrope of operating condition, between failure symptom and failure cause, often be difficult to set up corresponding relation accurately, therefore, adopt single testing and diagnosing means often to be difficult to obtain desirable localization of fault effect.
Summary of the invention
The object of the invention is to solve the problem that above prior art exists, and a kind of diesel powerplant fault diagnosis system based on information fusion that can integrated multiple testing and diagnosing means is provided.
Purpose of the present invention is achieved by adopting following technical scheme:
Based on the diesel powerplant fault diagnosis system of information fusion, mainly form by fusion diagnosis subsystem, signal condition subsystem, sensor subsystem.Wherein:
The fusion diagnosis subsystem comprises: monitoring computer, diagnosis computer, portable instrument, printer/alarm;
The signal condition subsystem comprises: serial communication module, USB acquisition module, data collecting card, first acquisition module, second acquisition module, the 3rd acquisition module, the first signal condition module, secondary signal conditioning module;
Sensor subsystem comprises: pressure unit, temperature transmitter, rotating speed transmitter, torque sensor, fire pressure transducer, vibration transducer;
Pressure unit, temperature transmitter, their output terminal of rotating speed transmitter is electrically connected on first acquisition module respectively, second acquisition module, the 3rd acquisition module, the torque sensor output terminal is electrically connected on the first signal condition module, fire their output terminal of pressure transducer and vibration transducer and be electrically connected on the secondary signal conditioning module, first acquisition module, second acquisition module, their output terminal of the 3rd acquisition module is electrically connected on the serial communication module respectively, the output terminal of the first signal condition module is electrically connected on the USB acquisition module, the output terminal of USB acquisition module is electrically connected on the fusion diagnosis computing machine, the output terminal of secondary signal conditioning module is electrically connected on data collecting card, the output terminal of data collecting card is electrically connected on portable instrument, monitoring computer is electrically connected with the serial communication module by serial ports, its output terminal is electrically connected on fusion diagnosis computing machine and alarm/printer respectively, portable instrument, it can be the thermal parameter instrument, the laser vibration gauge, infrared thermoviewers etc., its output terminal is electrically connected with the fusion diagnosis computing machine.
Pressure unit is mainly used in non-in-cylinder pressure measurement in the diesel engine, changes pressure signal into electric signal;
Temperature transmitter is mainly used in non-cylinder temperature measurement in the diesel engine, changes the temperature amount into electric signal;
The rotating speed transmitter is mainly used in the measurement of the speed of mainshaft, tailing axle rotating speed and diesel pressure booster rotating speed, directly changes rotating speed into electric signal;
Torque sensor is used for the sensitivity and the measurement of main-shaft torque;
Fire pressure transducer and vibration transducer, be mainly used in physical quantity that responsive portable instrument is surveyed, commonly used as cylinder internal combustion detonation pressure force signal, cylinder temperature signal and vibration signal etc.;
First acquisition module is used to gather the signal of pressure unit;
Second acquisition module is used for the signal of collecting temperature transmitter;
The 3rd acquisition module is used to gather the signal of rotating speed transmitter;
The serial communication module is used for the communication of first acquisition module, second acquisition module, the 3rd acquisition module and monitoring computer;
The first signal condition module is used to nurse one's health the output signal of torque sensor;
The USB acquisition module is used for the communication of the first signal condition module and fusion diagnosis computing machine;
The secondary signal conditioning module is used to nurse one's health the required signal of sensor of portable instrument;
Data collecting card is used for the collection of secondary signal conditioning module output data and realizes communication with portable instrument;
Monitoring computer is used for finishing warning, printing function, and providing monitoring result to the fusion diagnosis computing machine to on-line monitorings such as temperature, pressure, rotating speed, moments of torsion;
Alarm/printer is finished overload alarm function and Monitoring Data printing function;
Portable instrument can be thermal parameter instrument, laser vibration gauge, infrared thermoviewer etc., prepares according to the parameter that will monitor, finishes the test assignment of specific physical quantity;
The fusion diagnosis computing machine, obtain the Monitoring Data of diesel engine from monitoring computer, portable instrument, field test data is handled, extract the validity feature that characterizes fault, the using rough diversity method carries out preferably fault signature then, use the evidence theory method at last and carry out the fusion decision-making of fault, thus the location quick and precisely of realizing fault.
Characteristics of the present invention are: the fusion diagnosis computing machine obtains on-line monitoring parameters such as temperature, pressure, rotating speed, moment of torsion from on-Line Monitor Device, when finding that propulsion system are unusual, at first uses the on-line monitoring parameter of being obtained and carries out preliminary isolation; If can not accurately isolate, then start further diagnostic procedure, from portable instruments such as thermal technology detector, laser vibration measurer, obtain required supplementary data, and use and carry out fusion diagnosis, fault is accurately located based on the method for rough set and evidence theory.The method of this system applies information fusion has solved the problem of present diesel powerplant localization of fault difficulty preferably, and accurately diagnosing for the fault that realizes diesel powerplant provides necessary means and technical guarantee.
Description of drawings
Fig. 1 is a structural representation of the present invention
Fig. 2 is the process flow diagram that the present invention diagnoses the diesel powerplant fault
Embodiment
System architecture of the present invention mainly is made up of fusion diagnosis subsystem 1, signal condition subsystem 2, sensor subsystem 3 as shown in Figure 1, wherein:
Fusion diagnosis subsystem 1 comprises: monitoring computer 12, diagnosis computer 13, portable instrument 14, printer/alarm 11;
Signal condition subsystem 2 comprises: serial communication module 21, USB acquisition module 22, data collecting card 23, first acquisition module 24, second acquisition module 25, the 3rd acquisition module 26, the first signal condition module 27, secondary signal conditioning module 28;
Sensor subsystem 3 comprises: pressure unit 31, temperature transmitter 32, rotating speed transmitter 33, torque sensor 34, fire pressure transducer 35, vibration transducer 36;
Wherein the fusion diagnosis computing machine is the core of system of the present invention, it obtains on-line monitoring parameters such as temperature, pressure, rotating speed, moment of torsion from monitoring computer, when finding that propulsion system are unusual, at first use the on-line monitoring parameter of being obtained and carry out preliminary isolation.
If can not accurately isolate, then start further diagnostic procedure, from portable sets such as thermal technology detector, infrared thermoviewer, obtain required supplementary data, use and carry out fusion diagnosis, fault is accurately located based on the method for rough set and evidence theory.
Rough set (Rough Sets) theory is proposed in nineteen eighty-two by Pawlak, is a kind of new mathematical tool of handling uncertain and out of true problem; Rough set theory need not can be used for rejecting redundant composition about any initial or additional information of data, extracts incoherent mutually essential feature.Evidence theory claims the D-S theory again, is proposed in 1967 by Dempster, after Shafer is expanded and develops; Evidence theory is extremely effective a kind of uncertain inference method in the information fusion technology, is used widely in fault diagnosis field.The structure of diesel powerplant is very complicated, and it is bigger that it is carried out the fault analysis difficulty, and main difficulty is: show extremely complicated mapping relations between failure cause, failure symptom and the characteristic parameter.But, evidence theory depends on expertise and produces evidence, and the Dempster compositional rule to require each evidence body be separate, this often is difficult to satisfy in actual applications; Consider that rough set theory and evidence theory all pay close attention to " classification " of object, have very strong complementary relationship between the two, can overcome the defective that evidence obtains subjectivity and evidence body correlativity by rough set theory.The present invention is devoted to evidence theory and rough set theory are organically combined, a kind of new research thinking of troubleshooting issue has been proposed: utilize rough set theory, can reject the redundancy feature of not diagnosing value, extract the key characterization parameter collection of fault sensitivity and the relevant evidence of diagnosing as reasoning; After decision table realization basic reliability distribution, utilize the D-S evidence theory, can effectively merge each evidence, draw corresponding diagnostic result; Thus, solved the subjectivity and the relativity problem of evidence, improved accuracy of fault diagnosis, and effectively reduced the quantity of information that needs processing, helped to be implemented in radiodiagnosis x and use.
The fusion diagnosis flow process as shown in Figure 2.Wherein diesel powerplant is carried out fusion diagnosis research, comprised learning training process, two stages of failure diagnostic process.
In the learning training process, at first need to analyze the common failure pattern storehouse of setting up diesel powerplant, comprised the feature of extracting from line monitor signals such as temperature, pressure, moments of torsion in the library, and from firing the feature that portable detection signals such as pressure, vibration obtain.On the basis of analyzing diesel powerplant technical characterstic and fault mode characteristic, can determine Test to Failure and the test analysis that can implement, gather and extract the feature of diesel powerplant status signal; For the fault that is difficult to test simulation, the expertise experience that can be directly maintenance personal and other related datas be provided writes in the expert system rule storehouse in some way.For relevant fault signature, through after the Rule Extraction and feature reduction of rough set, can find out the key signal feature fully responsive to fault, at last the Expert Rules that draws is write expert system knowledge base, the fault status signal after the yojan can be used as mode standard and puts into fault pattern base.
In failure diagnostic process, at first signals such as temperature, pressure, moment of torsion are carried out on-line monitoring, when signal characteristic surpasses the threshold value limit and after status alert occurring, calls expert knowledge library, the current fault mode of diesel powerplant is carried out a preliminary analysis.When needing high speed acquisition to fire signal such as pressure in the process of fault mode initial analysis because of information is not enough, can append means of testing by portable set, the image data line correlation Feature Extraction of going forward side by side.On this basis, can further analyze and judge fault mode, utilize the D-S evidence theory that the evidence of reflection malfunction is merged, this have comprised the fault signature that obtains after evidence that line monitor signal is formed and the portable high-speed data acquisition.At last, can obtain corresponding fault diagnosis conclusion, and improve relevant maintenance operation suggestion thus, and expert knowledge library is fed back, realize the renewal of knowledge.
With an instantiation beneficial effect of the present invention is described below:
Test signal comprises: multi-measuring point vibration signal, in-cylinder pressure signal, tailing axle torque signal, and by merging the isolation that realizes faults such as the 2nd cylinder oil-break, the 3rd cylinder oil-break, the 4th cylinder oil-break, inlet flap close, inlet flap is opened.
Monitoring computer comprises according to the feature that monitor signal extracted:
● the feature that vibration signal extracts has: peak value, peak-to-peak value, root-mean-square value, all square amplitude, skewness factor, kurtosis factor, shape factor, the pulse factor, frequency band energy 1～8.
● the feature of in-cylinder pressure signal extraction has: peak value, peak-to-peak value, root-mean-square value, all square amplitude, skewness factor, kurtosis factor, shape factor, the pulse factor.
● the feature that the tailing axle torque signal extracts has: peak value, peak-to-peak value, root-mean-square value, all square amplitude, skewness factor, kurtosis factor, shape factor, the pulse factor, frequency band energy 1～8.
Under every kind of operating mode picked at random 16 groups of samples, wherein 15 groups are used for information fusion diagnosis decision-making research, stay 1 group and are used to check final effect.Be:, its 40 category feature (containing redundancy feature) is analyzed at 90 groups of samples.
The result of application characteristic yojan is: in 40 category features, it is essential features that 5 kinds of features are only arranged, and remaining feature is disallowable as their redundancy feature, and is as shown in table 1.
Table 1 feature reduction result
| 3. (1) kurtosis factor (e1) | 5. (1) root-mean-square value (e2) | 7. (3) peak-to-peak value (e3) | 9. peak-to-peak value (e4) | 9. frequency band 3 energy (e5) | Operating mode D |
| 1 | 1 | 1 | 1 | 1 | ① |
| 1 | 1 | 1 | 1 | 2 | ① |
| 2 | 1 | 1 | 1 | 2 | ① |
| 3 | 1 | 1 | 1 | 2 | ① |
| 4 | 1 | 2 | 1 | 2 | ① |
| 5 | 2 | 3 | 1 | 1 | ② |
| 5 | 2 | 3 | 1 | 2 | ② |
| 6 | 2 | 3 | 1 | 1 | ② |
| 6 | 2 | 3 | 1 | 2 | ② |
| 1 | 1 | 4 | 1 | 1 | ③ |
| 1 | 1 | 4 | 1 | 2 | ③ |
| 2 | 1 | 4 | 1 | 2 | ③ |
| 4 | 1 | 4 | 1 | 1 | ③ |
| 4 | 1 | 4 | 1 | 2 | ③ |
| 7 | 1 | 4 | 1 | 2 | ③ |
| 1 | 1 | 5 | 1 | 2 | ④ |
| 1 | 3 | 4 | 1 | 1 | ④ |
| 1 | 4 | 4 | 1 | 2 | ④ |
| 1 | 5 | 4 | 1 | 2 | ④ |
| 1 | 6 | 4 | 1 | 1 | ④ |
| 2 | 4 | 4 | 1 | 2 | ④ |
| 4 | 4 | 4 | 1 | 1 | ④ |
| 4 | 5 | 4 | 1 | 1 | ④ |
| 7 | 1 | 4 | 1 | 1 | ④ |
| 7 | 4 | 4 | 1 | 1 | ④ |
| 1 | 1 | 1 | 2 | 1 | ⑤ |
| 1 | 1 | 1 | 2 | 3 | ⑤ |
| 1 | 1 | 1 | 2 | 4 | ⑤ |
| 2 | 1 | 1 | 2 | 4 | ⑤ |
| 3 | 1 | 1 | 2 | 4 | ⑤ |
| 4 | 1 | 2 | 2 | 4 | ⑤ |
| 1 | 1 | 1 | 3 | 2 | ⑥ |
| 1 | 1 | 1 | 3 | 5 | ⑥ |
| 1 | 1 | 1 | 4 | 1 | ⑥ |
| 2 | 1 | 1 | 3 | 1 | ⑥ |
| 2 | 1 | 1 | 3 | 2 | ⑥ |
| 2 | 1 | 1 | 3 | 6? | ⑥? |
| 3 | 1 | 1 | 3 | 2 | ⑥ |
| 4 | 1 | 2 | 3 | 2 | ⑥ |
Characteristic series after the yojan can be used as the reasoning evidence of diagnosis decision-making, is: (e1) peak-to-peak value of the vibration signal root-mean-square value of cylinder 1 signal kurtosis factor, (e2) measuring point 5, (e3) cylinder 2 signal peak peak values, (e4) torque signal, certain sub-band energy of (e5) torque signal.Decision-making is listd and is followed successively by: (normally) is normal, (F1) the 2nd cylinder oil-break, (F2) the 3rd cylinder oil-break, (F3) the 4th cylinder oil-break, (F4) inlet flap close, (F5) inlet flap is opened etc. 6 kinds normally and fault conditions.
Based on the relevant calculation method of D-S evidence theory, sample to be verified is put in order the final degree of confidence allocation table that is used to diagnose decision-making that generates.Enumerated the wherein part situation of several operating modes below, respectively shown in table 2, table 3, table 4.
The sample checking of table 2 nominal situation
| Normally | Normally | F1 | F2 | F3 | F4 | F5 |
| e1 | 0.4493 | 0.1544 | 0.0939 | 0.0749 | 0.1137 | 0.1137 |
| e2 | 0.2711 | 0.1164 | 0.1243 | 0.0472 | 0.2205 | 0.2205 |
| e3 | 0.299 | 0.0544 | 0.1032 | 0.0847 | 0.2293 | 0.2293 |
| e4 | 0.1986 | 0.2448 | 0.1995 | 0.1995 | 0.1122 | 0.0453 |
| e5 | 0.2514 | 0.1727 | 0.1727 | 0.1727 | 0.0511 | 0.1795 |
| e1+e2 | 0.5938 | 0.0876 | 0.0569 | 0.0172 | 0.1222 | 0.1222 |
| e1+e2+e3 | 0.7225 | 0.0194 | 0.0239 | 0.006 | 0.1141 | 0.1141 |
| e1+e2+e3+e4 | 0.8334 | 0.0276 | 0.0277 | 0.007 | 0.0744 | 0.03 |
| e1+e2+e3+e4+e5 | 0.9134 | 0.0207 | 0.0208 | 0.0052 | 0.0166 | 0.0234 |
The sample checking of table 3 the 2nd cylinder oil-break operating mode
| 2. the 2nd cylinder oil-break | Normally | F1 | F2 | F3 | F4 | F5 |
| e1 | 0.361 | 0.1601 | 0.116 | 0.0997 | 0.1316 | 0.1316 |
| e2 | 0.168 | 0.327 | 0.1107 | 0.0555 | 0.1694 | 0.1694 |
| e3 | 0.1326 | 0.4394 | 0.0823 | 0.0737 | 0.136 | 0.136 |
| e4 | 0.1986 | 0.2448 | 0.1995 | 0.1995 | 0.1122 | 0.0453 |
| e5 | 0.2514 | 0.1727 | 0.1727 | 0.1727 | 0.0511 | 0.1795 |
| e1+e2 | 0.2976 | 0.3446 | 0.0729 | 0.0314 | 0.1267 | 0.1267 |
| e1+e2+e3 | 0.2084 | 0.5964 | 0.0274 | 0.0106 | 0.0786 | 0.0786 |
| e1+e2+e3+e4 | 0.1996 | 0.7041 | 0.0264 | 0.0102 | 0.0425 | 0.0172 |
| e1+e2+e3+e4+e5 | 0.2738 | 0.6631 | 0.0249 | 0.0096 | 0.0118 | 0.0168 |
The go into operation sample checking of condition of table 4 inlet flap
| 6. inlet flap is opened | Normally | F1 | F2 | F3 | F4 | F5 |
| e1 | 0.3252 | 0.1929 | 0.1055 | 0.1327 | 0.1327 | 0.1108 |
| e2 | 0.1114 | 0.0781 | 0.1637 | 0.1107 | 0.1107 | 0.4255 |
| e3 | 0.1286 | 0.0561 | 0.2481 | 0.125 | 0.125 | 0.3171 |
| e4 | 0.1986 | 0.2448 | 0.1995 | 0.0453 | 0.1122 | 0.1995 |
| e5 | 0.2514 | 0.1727 | 0.1727 | 0.1795 | 0.0511 | 0.1727 |
| e1+e2 | 0.2536 | 0.111 | 0.1274 | 0.1082 | 0.1082 | 0.2916 |
| e1+e2+e3 | 0.2052 | 0.0341 | 0.1729 | 0.074 | 0.074 | 0.4399 |
| e1+e2+e3+e4 | 0.2227 | 0.0455 | 0.1885 | 0.0183 | 0.0453 | 0.4797 |
| e1+e2+e3+e4+e5 | 0.303 | 0.0425 | 0.1761 | 0.0178 | 0.0125 | 0.4481 |
From table 2, table 3, table 4 as can be seen, utilize the unavoidable appearance of single evidence can't diagnose or the situation of diagnostic error, judged corresponding fault or operating mode mistakenly.In table 2, single evidence e1 is 0.4493 about the degree of belief of " normally ", much larger than the degree of belief numerical value about other operating mode, can correctly diagnose; Though and single evidence e2, e3, e5 be for the degree of belief maximum of " normally ", do not show the obvious gap with other operating mode, the credibility of diagnosis is not high; As for single evidence e4, then be judged as " F1 " operating mode, belong to the situation of diagnostic error.In table 3, e2, e3 can correctly diagnose, and error diagnosis has then appearred in e1, e5 similarly, and e4 then belongs to the not high situation of trusting degree.The basic condition of table 4 similarly no longer describes in detail.
From table 2, table 3, table 4, can also see, under the complex reasoning of multiple evidence, obtain very big improvement, can judge corresponding fault or operating mode exactly; Situation for single evidence can accurately be judged still keeps correct under the complex reasoning of multiple evidence.In table 2, for the combined evidence of e1+e2, e1+e2+e3, e1+e2+e3+e4 and e1+e2+e3+e4+e5, all provided correct " normally " diagnostic result, and degree of belief increases constantly, uncertainty constantly reduces; Need to prove, also be that similarly the reasoning diagnostic result constantly improves for other evidence combined situation, and degree of belief and credibility are all in enhancing constantly.In table 3, though the credibility that e1+e2 correctly diagnoses is not high, e1+e2+e3, e1+e2+e3+e4 and e1+e2+e3+e4+e5 can both make right judgement; For table 4, analysis result also is similar.Need to prove especially,, in complex reasoning, can provide the effective diagnosis result for whole key feature e1+e2+e3+e4+e5.
Generally speaking, evidential reasoning is an important method of handling uncertain sexual type decision problem, but the elementary probability of its hypothesis space assign often by the expert by rule of thumb, knowledge and in advance given to the understanding of Problem Areas, thereby have very big subjectivity.Rough set theory and evidential reasoning have confidential relation, start with from the fundamental relation of rough set theory and evidence theory, and both combine and have strengthened the ability of handling the decision under uncertainty problem well.
Claims (1)
1, a kind of diesel powerplant fault diagnosis system based on information fusion is characterized in that mainly being made up of fusion diagnosis subsystem, signal condition subsystem, sensor subsystem, wherein:
The fusion diagnosis subsystem comprises: monitoring computer, fusion diagnosis computing machine, portable instrument, printer/alarm;
The signal condition subsystem comprises: serial communication module, USB acquisition module, data collecting card, first acquisition module, second acquisition module, the 3rd acquisition module, the first signal condition module, secondary signal conditioning module;
Sensor subsystem comprises: pressure unit, temperature transmitter, rotating speed transmitter, torque sensor, fire pressure transducer, vibration transducer;
Pressure unit, temperature transmitter, their output terminal of rotating speed transmitter is electrically connected on first acquisition module respectively, second acquisition module, the 3rd acquisition module, the torque sensor output terminal is electrically connected on the first signal condition module, fire their output terminal of pressure transducer and vibration transducer and be electrically connected on the secondary signal conditioning module, first acquisition module, second acquisition module, their output terminal of the 3rd acquisition module is electrically connected on the serial communication module respectively, the output terminal of the first signal condition module is electrically connected on the USB acquisition module, the output terminal of USB acquisition module is electrically connected on the fusion diagnosis computing machine, the output terminal of secondary signal conditioning module is electrically connected on data collecting card, the output terminal of data collecting card is electrically connected on portable instrument, monitoring computer is electrically connected with the serial communication module by serial ports, its output terminal is electrically connected on fusion diagnosis computing machine and alarm/printer respectively, and the portable instrument output terminal is electrically connected with the fusion diagnosis computing machine.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101924806A CN100472574C (en) | 2007-12-03 | 2007-12-03 | Diesel oil power installation failure diagnosis system based on information amalgamation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CNB2007101924806A CN100472574C (en) | 2007-12-03 | 2007-12-03 | Diesel oil power installation failure diagnosis system based on information amalgamation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101178844A CN101178844A (en) | 2008-05-14 |
| CN100472574C true CN100472574C (en) | 2009-03-25 |
Family
ID=39405083
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CNB2007101924806A Expired - Fee Related CN100472574C (en) | 2007-12-03 | 2007-12-03 | Diesel oil power installation failure diagnosis system based on information amalgamation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100472574C (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101798957B (en) * | 2010-01-27 | 2011-10-05 | 北京信息科技大学 | Failure diagnosis method of power equipment |
| CN101799359B (en) * | 2010-01-27 | 2011-05-25 | 北京信息科技大学 | Failure monitoring and predicting method and system of power equipment |
| CN103616187B (en) * | 2013-10-15 | 2016-06-01 | 北京化工大学 | A kind of method for diagnosing faults based on multi-dimension information fusion |
| CN104865075B (en) * | 2014-02-26 | 2020-11-17 | 南京理工大学 | Analysis system and method for marine diesel engine vibration signal |
| CN103900824B (en) * | 2014-03-27 | 2016-09-14 | 哈尔滨工程大学 | Diagnosis Method of Diesel Fault based on transient speed cluster analysis |
| CN104361408B (en) * | 2014-11-04 | 2017-11-10 | 沈阳黎明航空发动机(集团)有限责任公司 | A kind of aeroplane engine main bearing assembles clearance matching method |
| CN105487530B (en) * | 2016-02-01 | 2018-07-31 | 中国人民解放军镇江船艇学院 | The low failure prediction system of diesel engine row's temperature and method |
| CN109521752B (en) * | 2018-11-13 | 2022-04-22 | 中国人民解放军陆军工程大学 | Control box detection system |
| CN110530647B (en) * | 2019-08-30 | 2021-05-14 | 大连海事大学 | Internal combustion engine health monitoring method based on acoustic emission technology and crankshaft instantaneous rotating speed |
| CN110715806A (en) * | 2019-10-25 | 2020-01-21 | 中船动力有限公司 | Diesel engine intake and exhaust system health assessment method |
| CN111076808B (en) * | 2019-12-20 | 2022-03-22 | 中国北方发动机研究所(天津) | Real-time vibration monitoring and early warning system for diesel engine bench test |
| CN115112360B (en) * | 2022-06-22 | 2024-04-16 | 南京智慧水运科技有限公司 | Rudder fault diagnosis method based on reliability updating and fusion |
-
2007
- 2007-12-03 CN CNB2007101924806A patent/CN100472574C/en not_active Expired - Fee Related
Also Published As
| Publication number | Publication date |
|---|---|
| CN101178844A (en) | 2008-05-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100472574C (en) | Diesel oil power installation failure diagnosis system based on information amalgamation | |
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN106644484A (en) | Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set | |
| CN102494899A (en) | Composite fault diagnosis method for diesel engine and diagnosis system | |
| CN203083829U (en) | Automobile fault diagnosis system based on tail gas discharge detection adopting simple driving mode | |
| Czech et al. | Application of cepstrum and spectrum histograms of vibration engine body for setting up the clearance model of the piston-cylinder assembly for RBF neural classifier | |
| CN108920426A (en) | A kind of method for diagnosing faults based on power equal operator and DS evidence theory | |
| CN103969052A (en) | Diesel engine fault diagnosis method based on outlier analysis | |
| CN105447250A (en) | Method for determining health characterizing parameters of electromechanical device | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| CN202661269U (en) | Compound fault diagnosis test platform of diesel engine | |
| CN110554682B (en) | Fault detection reasoning method based on fault correlation analysis | |
| CN107977679A (en) | Method based on frequency response function and operation response characteristic diagnosis of complex device initial failure | |
| CN106339720A (en) | Automobile engine failure detection method | |
| CN106909136A (en) | A kind of method for diagnosing faults based on index regularization kernel linear discriminant analysis | |
| CN109990891A (en) | A kind of diesel vibration impact source title method based on the fusion of multi-measuring point information | |
| CN110334844A (en) | Utilize the ship optimized use method of the main promotion diesel engine operating status of ship | |
| Du et al. | Research on the application of artificial intelligence method in automobile engine fault diagnosis | |
| CN112487709A (en) | Marine diesel engine fault tracing method based on sensitivity analysis | |
| Yan et al. | Misfire detection on internal combustion engine based on fluctuation of exhaust gas temperature | |
| Shi et al. | Fault diagnosis of me marine diesel engine fuel injector with novel IRCMDE method | |
| CN113050595B (en) | Potential fault analysis method based on PFMEA and HRA method | |
| CN111709453B (en) | Online fault diagnosis method for electrical system of aircraft engine | |
| Wei et al. | Fault Status Information Monitoring Technology for Large Complex Electromechanical System. | |
| Tang et al. | Fault Diagnosis of Rolling Bearing Based on BP Nural Network Technology |
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 | ||
| C17 | Cessation of patent right | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20090325 Termination date: 20101203 |