CN107194429A - A kind of mechanical fault diagnosis system - Google Patents
A kind of mechanical fault diagnosis system Download PDFInfo
- Publication number
- CN107194429A CN107194429A CN201710392430.6A CN201710392430A CN107194429A CN 107194429 A CN107194429 A CN 107194429A CN 201710392430 A CN201710392430 A CN 201710392430A CN 107194429 A CN107194429 A CN 107194429A
- Authority
- CN
- China
- Prior art keywords
- hardware
- software system
- fault diagnosis
- induction element
- mechanical fault
- 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.)
- Withdrawn
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Geometry (AREA)
- Computer Hardware Design (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention discloses a kind of mechanical fault diagnosis system, it is made up of induction element, hardware/software system, Man Machine Interface, induction element is connected with hardware/software system, induction element transmits a signal to hardware/software system, hardware/software system is connected with Man Machine Interface, and people passes through Man Machine Interface and hardware/software system interactive information.The characteristic signal and operational factor of induction element dynamic detection machinery equipment；Hardware components in hardware/software system complete signal transacting；Software section in hardware/software system uses the old attribute reduction algorithms in rough set theory.Uncertain factor is reduced, intrinsic dimensionality is reduced, amount of calculation is reduced, it is ensured that diagnostic accuracy is substantially constant.
Description
Technical field
The present invention relates to artificial intelligence, fault diagnosis, relate more specifically to a kind of mechanical fault diagnosis system.
Background technology
Fault diagnosis technology is a complex art, and it is related to multi-door subject, such as modern control theory, reliability theory,
The subjects such as mathematical statistics, signal transacting, pattern-recognition, artificial intelligence.Failure theory, to senior, can be divided into four mainly by rudimentary
The content of aspect：(1) fault modeling.According to prior information and the relation of input and output, the mathematical modeling of the system failure is set up, is made
For the foundation of fault detection and diagnosis；(2) from can survey or immesurable predictor in detect failure；(3) separation of failure with
Estimation.As system there occurs failure, provide the position of the source of trouble, the reason for difference is out of order, determine the degree of failure, size,
Time and the time-varying characteristics of failure that failure occurs；(4) classification of failure, evaluation and decision.
From the point of view of the position that failure occurs, instrument fault, actuator failures and element fault can be divided into；According to fault
Matter, can be divided into mutation failure and slow failure；It can be divided into multiplying property failure and additivity failure from modeling angle.As for fault diagnosis
Method, generally can be divided into hardware redundancy method and software redundancy method.Hardware redundancy method needs to increase test equipment, makes system
Complexity, cost is high, so using software redundancy more.Software redundancy method can be divided into two major classes：One is based on control system parsing
The diagnostic method of model；Two are not dependent on the diagnostic method of analytic modell analytical model, and it can be divided into the diagnosis side based on signal transacting again
Method and Knowledge based engineering diagnostic method.
Mechanical fault diagnosis is a typical information fusion process, it is necessary to enter to the much information in machine running process
Row integrated treatment and Cooperative Analysis.In actual applications, and machine operational factor is (such as machine characteristic signal (such as vibration, noise)
Working medium pressure, temperature) a lot, the state of machine operation can be reflected.First have to the machine characteristic signal or machine to acquisition
Device operational factor carries out feature extraction, also needs to be compressed diagnostic characteristic or yojan afterwards, rejects unwanted feature, or
Substantial amounts of feature is simplified, so as to greatly reduce the amount of calculation of diagnostic message fusion process, fault diagnosis is improved
Efficiency.
For Diagnosis system of mechanical failure, because the mechanism that failure is produced is unclear, the form of expression of failure is not only,
It is sometimes ambiguous, also there is blindness often when extracting fault signature, so that between result in the machine state of actual description
It is fuzzy.The feature for describing machine state is often a lot, and some are characterized in related, and some are independent.Independent spy
Complementary information can be provided by levying, thus should be retained；Correlative character produces redundancy, while amount of calculation can be increased,
Thus need to be eliminated.
In existing achievement in research and open source literature, not yet find in the case where ensureing that diagnostic accuracy is substantially constant,
Uncertain factor is reduced, intrinsic dimensionality is reduced, the mechanical fault diagnosis system of amount of calculation is reduced.
The content of the invention
Goal of the invention.
The present invention proposes a kind of mechanical fault diagnosis system, it is ensured that diagnostic accuracy is substantially constant, reduces uncertain
Factor, reduces intrinsic dimensionality, reduces amount of calculation.
The technical solution adopted in the present invention.
A kind of mechanical fault diagnosis system proposed by the present invention, by induction element, hardware/software system, man-machine friendship
Mutual interface composition, induction element is connected with hardware/software system, and induction element transmits a signal to hardware/software system, firmly
Part/software systems are connected with Man Machine Interface, and people passes through Man Machine Interface and hardware/software system interactive information.
Further, the characteristic signal of the mechanical equipment of induction element dynamic detection, including vibration, noise.
Further, the operational factor of the mechanical equipment of induction element dynamic detection, including working medium pressure, temperature.
Further, the hardware components in hardware/software system complete signal transacting, including convert analog signals into number
Word signal.
Further, the software section in hardware/software system uses the old attribute reduction algorithms in rough set theory：
(1) tectonic information table;
(2) object set is classified by decision attribute, produces and expect collection K;
(3) all property set C classification quality γ C (K) are calculated;
(4) composite attribute collection Q classification quality γ Q (K), Q is calculated<C;
(5) r=min { Q, Q<C }, r is exactly former property set C yojan.
Wherein, the indiscernibly object collection determined by status attribute collection P is referred to as P unit collection, by decision kind set institute really
Fixed indiscernibly object collection is referred to as expecting.One kind point that unit set representations are done according to status attribute (such as symptom etc.) to object
Class result, and expect the classification results for then representing object to be done according to decision attribute, unit collection and imaginary not necessarily complete phase
Together.
Further, the object set of failure composition is U={ e1, e2, e3, e4, e5 ..., e10 }, imaginary K={ e1, e2 },
{ e3, e4 }, { e5, e6 }, { e7, e8 }, { e9, e10 } }, expect and divided according to fault type.
Technique effect produced by the present invention.
The present invention passes through many experiments, draws the old attribute reduction algorithms in hardware/software system, reduces uncertain factor,
Intrinsic dimensionality is reduced, amount of calculation is reduced, it is ensured that diagnostic accuracy is substantially constant.
Brief description of the drawings
Fig. 1 is mechanical fault diagnosis system schematic of the invention.
Embodiment
Embodiment
A variety of oil path failures are simulated in experiment automobile engine, and measure the injection pressure curve under various failures, so
The relation between oil piping system failure and tubing pressure waveform information is summed up afterwards.
The induction element of fault diagnosis system is liquid-pressure pick-up.
Old attribute reduction algorithms in rough set theory：
(1) tectonic information table;
(2) object set is classified by decision attribute, produces and expect collection K;
(3) all property set C classification quality γ C (K) are calculated;
(4) composite attribute collection Q classification quality γ Q (K), Q is calculated<C;
(5) r=min { Q, Q<C }, r is exactly former property set C yojan
The object set of automobile engine oil supply system failure composition is U={ e1, e2 ..., e10 }, imaginary K={ e1, e2 }, e3,
E4 }, { e5, e6 }, { e7, e8 }, { e9, e10 } }, expect and divided according to fault type.
Calculate correspondence property set { s1, s2, s3, s4, s5 }, classification quality γ P (K)=0.8;Meet r=min { Q, Q<
P } minimal attribute set have { s1, s2, s5 }, { s1, s4, s5 } and { s2, s3, s5 }, dominant attribute be { s5 }.
In the case where ensureing that classification quality is constant, it is main to have 3 features in former feature, and 3 feature sets may have 4
The situation of kind, wherein most crucial is characterized in injection advance angle.Rule of thumb, injection advance angle can determine the combustion of automobile engine
Burning situation, is a leading indicator for reflecting engine fuel system failure, it is correct to demonstrate diagnostic result.
Claims (6)
1. a kind of mechanical fault diagnosis system, it is characterised in that：Connect by induction element, hardware/software system, man-machine interaction
Mouth composition, induction element is connected with hardware/software system, and induction element transmits a signal to hardware/software system, hardware/soft
Part system is connected with Man Machine Interface, and people passes through Man Machine Interface and hardware/software system interactive information.
2. a kind of mechanical fault diagnosis system according to claim 1, it is characterised in that：Induction element dynamic detection
The characteristic signal of plant equipment, including vibration, noise.
3. a kind of mechanical fault diagnosis system according to claim 1, it is characterised in that：Induction element dynamic detection
The operational factor of plant equipment, including working medium pressure, temperature.
4. a kind of mechanical fault diagnosis system according to claim 1, it is characterised in that：In hardware/software system
Hardware components, complete signal transacting, including convert analog signals into data signal.
5. a kind of mechanical fault diagnosis system according to claim 1, it is characterised in that：In hardware/software system
Software section, using the old attribute reduction algorithms in rough set theory：
(1) tectonic information table;
(2) object set is classified by decision attribute, produces and expect collection K;
(3) all property set C classification quality γ C (K) are calculated;
(4) composite attribute collection Q classification quality γ Q (K), Q is calculated<C;
(5) r=min { Q, Q<C }, r is exactly former property set C yojan.
6. a kind of mechanical fault diagnosis system according to claim 1 or 5, it is characterised in that：Pair of failure composition
As integrating as U={ e1, e2, e3, e4, e5 ..., e10 }, imaginary K={ e1, e2 }, { e3, e4 }, { e5, e6 }, { e7, e8 }, e9,
E10 } }, expect and divided according to fault type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710392430.6A CN107194429A (en) | 2017-05-27 | 2017-05-27 | A kind of mechanical fault diagnosis system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710392430.6A CN107194429A (en) | 2017-05-27 | 2017-05-27 | A kind of mechanical fault diagnosis system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107194429A true CN107194429A (en) | 2017-09-22 |
Family
ID=59874986
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710392430.6A Withdrawn CN107194429A (en) | 2017-05-27 | 2017-05-27 | A kind of mechanical fault diagnosis system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107194429A (en) |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676842A (en) * | 2016-03-14 | 2016-06-15 | 中国铁路总公司 | High-speed railway train control vehicle-mounted equipment fault diagnosis method |
-
2017
- 2017-05-27 CN CN201710392430.6A patent/CN107194429A/en not_active Withdrawn
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105676842A (en) * | 2016-03-14 | 2016-06-15 | 中国铁路总公司 | High-speed railway train control vehicle-mounted equipment fault diagnosis method |
Non-Patent Citations (1)
| Title |
|---|
| 袁小宏 等: "粗糙集理论在机械故障诊断中的应用研究", 《西安交通大学学报》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102061810B1 (en) | System and Method for Processing Multi type Sensor Signal Based on Multi modal Deep Learning | |
| CN103147972B (en) | A kind of reciprocal compressor method for diagnosing faults based on multi-sensor information fusion | |
| CN104390657B (en) | A kind of Generator Unit Operating Parameters measurement sensor fault diagnosis method and system | |
| CN102999038B (en) | The diagnostic device of generating set and the diagnostic method of generating set | |
| Shi et al. | Fault diagnosis in a hydraulic directional valve using a two-stage multi-sensor information fusion | |
| CN106644484A (en) | Turboprop Engine rotor system fault diagnosis method through combination of EEMD and neighborhood rough set | |
| CN105466693B (en) | The pre- diagnostic method of Fault of Diesel Fuel System based on gray model | |
| CN112560919A (en) | Man-machine asynchronous recognition method based on one-dimensional interpretable convolutional neural network | |
| CN105090001B (en) | Reciprocating compressor signal complete period phase correction method based on similarity analysis | |
| CN101581295A (en) | Airborne hydraulic pump source fault diagnosis system based on DSP | |
| Liao et al. | Research on a rolling bearing fault detection method with wavelet convolution deep transfer learning | |
| CN110245085A (en) | The embedded real-time operating system verification method and system examined using on-time model | |
| CN111678699A (en) | Early fault monitoring and diagnosing method and system for rolling bearing | |
| Sun et al. | Data-driven fault diagnosis of control valve with missing data based on modeling and deep residual shrinkage network | |
| Li et al. | A soft-target difference scaling network via relational knowledge distillation for fault detection of liquid rocket engine under multi-source trouble-free samples | |
| Wan et al. | Bearing Fault Diagnosis Based on Multi-Sensor Information Coupling and Attentional Feature Fusion | |
| Jakobsson et al. | Time series fault classification for wave propagation systems with sparse fault data | |
| Breikin et al. | Dynamic modelling for condition monitoring of gas turbines: Genetic algorithms approach | |
| CN107194429A (en) | A kind of mechanical fault diagnosis system | |
| CN111753876B (en) | Product quality detection method based on deep neural network | |
| CN111366184B (en) | Shield tunneling machine multi-sensor performance online monitoring method | |
| CN104457828A (en) | Sensor-contained system model for state monitoring and fault diagnosis of hydraulic system | |
| CN104764871B (en) | A kind of water content in oil on-line monitoring method of multivariable detection | |
| CN113298133A (en) | Supercritical unit boiler tube burst fault diagnosis method | |
| Lei et al. | Testability modeling of hydraulic system based on multi-signal flow model |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20170922 |
|
| WW01 | Invention patent application withdrawn after publication |