CN108398271A - A kind of engine state monitor method based on vibration and nerual network technique - Google Patents
A kind of engine state monitor method based on vibration and nerual network technique Download PDFInfo
- Publication number
- CN108398271A CN108398271A CN201710066763.XA CN201710066763A CN108398271A CN 108398271 A CN108398271 A CN 108398271A CN 201710066763 A CN201710066763 A CN 201710066763A CN 108398271 A CN108398271 A CN 108398271A
- Authority
- CN
- China
- Prior art keywords
- engine
- network
- fault
- nerual
- vibration
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M15/00—Testing of engines
- G01M15/04—Testing internal-combustion engines
- G01M15/12—Testing internal-combustion engines by monitoring vibrations
Landscapes
- Chemical & Material Sciences (AREA)
- Engineering & Computer Science (AREA)
- Combustion & Propulsion (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Engines (AREA)
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The engine state monitor method based on vibration and nerual network technique that the invention discloses a kind of, belongs to engine failure monitoring method field, including extracts the Faults by Vibrating of engine and nerual network technique is utilized to carry out engine condition analysis.The vibration monitoring experimental test point of engine is selected at the measuring point near cylinder head cover, cylinder body and crankcase side wall, reduces the arrangement difficulty of sensor.Include using the step of nerual network technique progress engine condition analysis：1）The signal under specific operation under fault-free and malfunction is obtained, failure symptom data are extracted and is normalized, the input as BP neural network；2）BP neural network system is established, using the characteristic parameter of known fault conditions as training sample, network is trained, reaches required diagnostic accuracy；3）The Fault characteristic parameters of unknown state are inputted trained neural network to test, the network under the state is obtained and exports and post-processed, result is compared with the fault mode of training network, obtains diagnostic result, i.e. fault type.
Description
Technical field
The present invention relates to a kind of engine failure monitoring methods more particularly to a kind of based on vibration and nerual network technique
Engine state monitor method.
Background technology
For mechanical equipment, engine is the core drive group of a kind of important dynamic power machine and mechanical equipment
At part.The method of engine diagnosis disclosed in the prior art is mainly with failure tree analysis (FTA) and point of Multi-sensor Fusion
Judgment method is analysed, these fault analysis and handling methods can not accurately judge the operating status of engine.
Invention content
The technical assignment of the present invention is to solve the deficiencies in the prior art, is provided a kind of based on vibration and nerual network technique
Engine state monitor method, it is intended to solve existing fault analysis and handling method and be unable to asking for accurate judgement engine operating state
Topic.
The technical solution adopted by the present invention to solve the technical problems is：
A kind of engine state monitor method based on vibration and nerual network technique, includes the following steps：
1）Extract the Faults by Vibrating of engine；
2）Engine condition analysis is carried out using nerual network technique.
Further, the extraction of the engine luggine characteristic parameter is to be selected in engine luggine monitoring test test point
At measuring point near cylinder head cover, cylinder body and crankcase side wall.
Further, nonlinear fitting is carried out using nerual network technique, complicated nonlinear dependence between mapping and failure
System, according to fuzzy inference synthesis rule, obtains Model for Comprehensive.
Further, include using the step of nerual network technique progress engine condition analysis：
1）The signal under specific operation under fault-free and malfunction is obtained, failure symptom data are extracted and is normalized, as
The input of BP neural network；
2）BP neural network system is established, using the characteristic parameter of known fault conditions as training sample, network is trained,
Reach required diagnostic accuracy；
3）The Fault characteristic parameters of unknown state are inputted trained neural network to test, obtain the network under the state
It exports and is post-processed, result is compared with the fault mode of training network, obtains diagnostic result, i.e. fault type.
The engine state monitor method based on vibration and nerual network technique of the present invention is produced compared with prior art
Raw advantageous effect is：
（1）Engine luggine monitoring test test point is selected in the survey near cylinder head cover, cylinder body and crankcase side wall by the present invention
At point, the arrangement difficulty of sensor is reduced.
（2）The present invention carries out engine condition analysis using nerual network technique, and this method is more suitable for the event of engine
It is the Nonlinear Mapping relationship of complexity between barrier parameter and fault mode, is a kind of effective means of fault diagnosis.
Specific implementation mode
The engine state monitor method based on vibration and nerual network technique of the present invention, including the vibration of extraction engine is special
The step of levying parameter and step two parts that engine condition analysis is carried out using nerual network technique, wherein：
Extraction to engine luggine characteristic parameter be by engine luggine monitoring test test point be selected in cylinder head cover, cylinder body and
At measuring point near crankcase side wall.
Engine condition analysis is carried out using nerual network technique, is to carry out nonlinear fitting using nerual network technique,
Complicated non-linear relation obtains Model for Comprehensive according to fuzzy inference synthesis rule between mapping and failure.
Its specific steps includes：
1）The signal under specific operation under fault-free and malfunction is obtained, failure symptom data are extracted and is normalized, as
The input of BP neural network；
2）BP neural network system is established, using the characteristic parameter of known fault conditions as training sample, network is trained,
Reach required diagnostic accuracy；
3）The Fault characteristic parameters of unknown state are inputted trained neural network to test, obtain the network under the state
It exports and is post-processed, result is compared with the fault mode of training network, obtains diagnostic result, i.e. fault type.
Claims (4)
1. a kind of engine state monitor method based on vibration and nerual network technique, which is characterized in that include the following steps：
1）Extract the Faults by Vibrating of engine；
2）Engine condition analysis is carried out using nerual network technique.
2. special according to a kind of engine state monitor method based on vibration and nerual network technique described in claim 1
Sign is,
The extraction of the engine luggine characteristic parameter be by engine luggine monitoring test test point be selected in cylinder head cover, cylinder body with
And at the measuring point near crankcase side wall.
3. special according to a kind of engine state monitor method based on vibration and nerual network technique described in claim 1
Sign is：
Nonlinear fitting is carried out using nerual network technique, complicated non-linear relation between mapping and failure is pushed away according to fuzzy
Composition rule is managed, Model for Comprehensive is obtained.
4. special according to a kind of engine state monitor method based on vibration and nerual network technique described in claim 1
Sign is：
Include using the step of nerual network technique progress engine condition analysis：
1）The signal under specific operation under fault-free and malfunction is obtained, failure symptom data are extracted and is normalized, as
The input of BP neural network；
2）BP neural network system is established, using the characteristic parameter of known fault conditions as training sample, network is trained,
Reach required diagnostic accuracy；
3）The Fault characteristic parameters of unknown state are inputted trained neural network to test, obtain the network under the state
It exports and is post-processed, result is compared with the fault mode of training network, obtains diagnostic result, i.e. fault type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710066763.XA CN108398271A (en) | 2017-02-07 | 2017-02-07 | A kind of engine state monitor method based on vibration and nerual network technique |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710066763.XA CN108398271A (en) | 2017-02-07 | 2017-02-07 | A kind of engine state monitor method based on vibration and nerual network technique |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108398271A true CN108398271A (en) | 2018-08-14 |
Family
ID=63094586
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710066763.XA Pending CN108398271A (en) | 2017-02-07 | 2017-02-07 | A kind of engine state monitor method based on vibration and nerual network technique |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108398271A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109580230A (en) * | 2018-12-11 | 2019-04-05 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of Fault Diagnosis of Engine and device based on BP neural network |
| CN110441065A (en) * | 2019-07-04 | 2019-11-12 | 杭州华电江东热电有限公司 | Gas turbine online test method and device based on LSTM |
| US20200118358A1 (en) * | 2018-10-11 | 2020-04-16 | Hyundai Motor Company | Failure diagnosis method for power train components |
| CN111551368A (en) * | 2019-02-08 | 2020-08-18 | 丰田自动车株式会社 | Knock detection device and knock detection method for internal combustion engine |
| CN113554085A (en) * | 2021-07-20 | 2021-10-26 | 云南电力试验研究院(集团)有限公司 | System and method for sensing vibration safety situation of induced draft fan |
-
2017
- 2017-02-07 CN CN201710066763.XA patent/CN108398271A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20200118358A1 (en) * | 2018-10-11 | 2020-04-16 | Hyundai Motor Company | Failure diagnosis method for power train components |
| CN109580230A (en) * | 2018-12-11 | 2019-04-05 | 中国航空工业集团公司西安航空计算技术研究所 | A kind of Fault Diagnosis of Engine and device based on BP neural network |
| CN111551368A (en) * | 2019-02-08 | 2020-08-18 | 丰田自动车株式会社 | Knock detection device and knock detection method for internal combustion engine |
| CN110441065A (en) * | 2019-07-04 | 2019-11-12 | 杭州华电江东热电有限公司 | Gas turbine online test method and device based on LSTM |
| CN110441065B (en) * | 2019-07-04 | 2022-02-08 | 杭州华电江东热电有限公司 | Gas turbine on-line detection method and device based on LSTM |
| CN113554085A (en) * | 2021-07-20 | 2021-10-26 | 云南电力试验研究院(集团)有限公司 | System and method for sensing vibration safety situation of induced draft fan |
| CN113554085B (en) * | 2021-07-20 | 2023-04-18 | 云南电力试验研究院(集团)有限公司 | System and method for sensing vibration safety situation of induced draft fan |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108398271A (en) | A kind of engine state monitor method based on vibration and nerual network technique | |
| US10288043B2 (en) | Wind turbine condition monitoring method and system | |
| CN110867196B (en) | A machine equipment status monitoring system based on deep learning and sound recognition | |
| CN102053016B (en) | System for monitoring vibration of rotating machinery rolling bearing in wireless mode | |
| CN204324627U (en) | A kind of elevator internal contracting brake performance detecting system | |
| CN103901882B (en) | A kind of system and method for train dynamics system on-line monitoring fault diagnosis | |
| CN103544389B (en) | Autocrane method for diagnosing faults based on fault tree and fuzzy neural network | |
| CN103900824B (en) | Diagnosis Method of Diesel Fault based on transient speed cluster analysis | |
| CN102494899A (en) | Composite fault diagnosis method for diesel engine and diagnosis system | |
| WO2008040019A3 (en) | Abnormal situation prevention in a coker heater | |
| CN108331718A (en) | Wind turbines yaw system monitors mechanism and fault diagnosis system and method on-line | |
| CN109724791A (en) | A kind of intelligence vibration analysis and trouble-shooter and its working method | |
| CN104266841A (en) | Fault diagnosis device and diagnosis method of diesel engine | |
| CN105571638A (en) | Machinery device fault combination prediction system and method | |
| CN106446339A (en) | Rotating machine operation state anomaly detection method based on Dirichlet mixture model | |
| CN108008718A (en) | Study on intelligent based on model | |
| CN117740242A (en) | Dynamic balance test system of power turbine | |
| CN108709744A (en) | Motor bearing fault diagnosis method under variable load working condition | |
| CN115215215A (en) | An intelligent early warning and fault diagnosis method for a large gantry shipbuilding crane | |
| CN103267652B (en) | Intelligent online diagnosis method for early failures of equipment | |
| CN105784364A (en) | Bearing fault diagnosis method based on total experience mode decomposition and fractal box dimensions | |
| CN113033625A (en) | Industrial air conditioner fault diagnosis method based on neural network and integrated learning fusion | |
| CN208431106U (en) | Wind turbines yaw system monitors mechanism on-line | |
| CN104569814A (en) | Approximate entropy-based direct-current traction motor health condition real-time analysis method | |
| CN111456915A (en) | Fault diagnosis device and method for internal components of fan engine room |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180814 |