CN113109043A - Method for establishing fault model database of active automobile transmission system - Google Patents
Method for establishing fault model database of active automobile transmission system Download PDFInfo
- Publication number
- CN113109043A CN113109043A CN202110379158.4A CN202110379158A CN113109043A CN 113109043 A CN113109043 A CN 113109043A CN 202110379158 A CN202110379158 A CN 202110379158A CN 113109043 A CN113109043 A CN 113109043A
- Authority
- CN
- China
- Prior art keywords
- fault
- monitored
- rotating speed
- type
- transmission system
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/021—Gearings
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M13/00—Testing of machine parts
- G01M13/02—Gearings; Transmission mechanisms
- G01M13/025—Test-benches with rotational drive means and loading means; Load or drive simulation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01M—TESTING STATIC OR DYNAMIC BALANCE OF MACHINES OR STRUCTURES; TESTING OF STRUCTURES OR APPARATUS, NOT OTHERWISE PROVIDED FOR
- G01M17/00—Testing of vehicles
- G01M17/007—Wheeled or endless-tracked vehicles
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Testing Of Devices, Machine Parts, Or Other Structures Thereof (AREA)
Abstract
The invention discloses a method for establishing a fault model database of an active automobile transmission system, which comprises the steps of collecting all fault characteristics of the automobile transmission system to be monitored from historical maintenance data, screening out fault characteristics related to rotating speed, and classifying the fault characteristics to obtain the type of the fault to be monitored; according to the classification of the fault types to be monitored, selecting a prototype with the single fault type to be monitored for each fault type to be monitored, testing on a test bench according to a test working condition, acquiring a rotating speed signal under the fault type to be monitored through a rotating speed sensor arranged on a power transmission system, and calculating according to the rotating speed signal to obtain an instantaneous rotating speed change characteristic under the fault type to be monitored; and (4) forming a fault model database by each fault type to be monitored and the corresponding instantaneous rotating speed change characteristics. The method establishes the relation between the rotating speed signal and the fault type, fault degree and residual life, and is convenient for accurately forecasting the fault.
Description
Technical Field
The invention relates to the technical field of automobile detection, in particular to a method for establishing a fault model database of an active automobile transmission system.
Background
Early vehicle failure diagnosis mainly aims at the problem that the normal use of the vehicle is influenced (such as the problem that the engine cannot be started or the power is insufficient) and determines the source of the problem by disassembling and checking the vehicle engine. With the development of science and technology, the fault diagnosis of automobiles has been developed to monitor the real-time running state of automobiles through a series of precision sensors, such as monitoring the temperature of an engine through a temperature sensor, monitoring the tire pressure through a tire pressure sensor, monitoring the oil pressure through a pressure sensor and the like, when the problems of overhigh oil temperature, insufficient oil pressure of an air inlet pump and the like occur in the driving process of the automobiles, a monitoring system can light on an automobile instrument panel for prompting.
However, such a monitoring system is basic in function, and can only display whether a fault state occurs at present, roughly judge the running state of the automobile, and cannot further identify the fault state. Moreover, the existing monitoring system can only passively prompt the driver when the problem of the automobile failure is serious. The automobile transmission system is the core of a vehicle form, and once a fault state prompt related to the transmission system occurs in an automobile, a serious fault is usually accompanied, and the maintenance cost is high.
Therefore, the inventor designs a vehicle-mounted running state monitoring and fault forecasting system capable of actively monitoring the running state of an automobile on the real automobile and pre-judging faults according to the running state, in the system, collected signals of a rotating speed sensor are processed and matched with a built-in fault model database, so that the judgment and the forecasting of the faults are realized, and therefore, how to establish a complete fault model database becomes the problem to be solved urgently.
Disclosure of Invention
Aiming at the defects of the prior art, the technical problems to be solved by the invention are as follows: how to establish an active automobile transmission system fault model database for vehicle-mounted running state monitoring and fault prediction.
In order to solve the technical problems, the invention adopts the following technical scheme:
a method for establishing a fault model database of an active automobile transmission system is characterized by comprising the following steps:
s1, collecting all fault characteristics of the automobile transmission system to be monitored from historical maintenance data, screening out fault characteristics related to the rotating speed as fault characteristics to be monitored, and classifying the fault characteristics to be monitored to obtain fault types to be monitored;
s2, according to the classification of the fault types to be monitored, selecting a prototype with the single fault type to be monitored for each fault type to be monitored, testing on a test bench according to the test working condition, acquiring a rotating speed signal under the fault type to be monitored through a rotating speed sensor arranged on a power transmission system, and calculating to obtain the instantaneous rotating speed change characteristic under the fault type to be monitored according to the rotating speed signal;
and S3, forming a fault model database by each fault type to be monitored and the corresponding instantaneous rotating speed change characteristics.
Further, for each fault type to be monitored, selecting a plurality of prototype machines which only have the fault type to be monitored and have different fault degrees, and respectively testing each prototype machine on a test bench according to the test working condition to obtain the instantaneous rotating speed change characteristic value of the prototype machine with different fault degrees under the fault mode to be monitored;
and combining the corresponding instantaneous rotating speed change characteristic values of each type of fault to be monitored under different fault degrees into the fault model database.
Further, the corresponding instantaneous rotating speed change characteristic values of each fault type to be monitored under different fault degrees are led into an artificial intelligence deep learning algorithm for model training, and a parameter model of the instantaneous rotating speed change characteristic values and the fault degrees under each fault type to be monitored is obtained.
Further, for each fault type to be monitored, a plurality of prototype machines which only have the fault type to be monitored and have different fault degrees are selected, fatigue life tests are respectively carried out on each prototype machine on a test bench, and a relation curve between the different fault degrees and the residual life in the fault mode to be monitored is obtained.
Further, a relation curve of different fault degrees and residual lives of each fault type to be monitored is led into an artificial intelligence deep learning algorithm for model training, and a parameter model of the fault degree and the residual life of each fault type to be monitored is obtained.
Further, matching the instantaneous rotating speed change characteristic value and the parameter model of the fault degree and the parameter model of the residual service life under the same fault mode to be monitored to obtain an instantaneous rotating speed change characteristic value, a fault degree and a corresponding comprehensive parameter model of the residual service life; and constructing the fault model database by using the comprehensive parameter models under different fault modes to be monitored.
The invention has the following benefits:
1. the invention establishes the association between the fault type and the instantaneous rotating speed change characteristic by extracting the instantaneous rotating speed change characteristic through the rotating speed signal, and is convenient to directly pre-judge the possible fault type through the rotating speed signal during the vehicle-following detection.
2. The invention establishes the corresponding instantaneous rotating speed change characteristic values of different fault degrees under different rotating speeds under the same fault type, thereby being capable of pre-judging the fault degree by combining the rotating speed of the rotating speed signal and the instantaneous rotating speed change characteristic values according to the pre-judged fault type.
3. The invention establishes the residual life under different fault degrees under the same fault type, thereby further pre-judging the residual life according to the pre-judged fault type and fault degree.
Drawings
Fig. 1 is a flowchart of a method for building a fault model database.
FIG. 2 is a control flow diagram of an active powertrain condition monitoring system.
FIG. 3 is a logic flow diagram for implementing failure mode prediction for an active driveline state monitoring system.
Detailed Description
The invention is described in further detail below with reference to an example of a method in which the invention is used.
In the specific implementation: as shown in fig. 1 to 3, in the implementation process, a fault model database is firstly constructed, then a vehicle-mounted running state monitoring and fault forecasting system is constructed, and corresponding fault types and residual lives are matched in the fault model database according to rotating speed signals of vehicle-mounted rotating speed sensors for forecasting faults and residual lives.
For convenience of explanation, the following describes in detail a method for constructing a fault model database by taking a new energy reducer in a power transmission system as an example:
1. the method comprises the steps of firstly collecting all fault characteristics of the new energy speed reducer from historical maintenance data, then screening out fault characteristics related to the rotating speed as fault characteristics to be monitored, and classifying the fault characteristics to be monitored to obtain fault types to be monitored.
Such as: the common failure types of the gears are classified into fault types such as tooth breakage, tooth surface pitting, tooth surface abrasion, tooth surface gluing and the like, and the fault types can reflect different signal waveforms from signals detected by the rotating speed sensor.
2. According to the classification of the fault types to be monitored, for each fault type to be monitored, a prototype (power transmission system) with a single fault type to be monitored is collected, or a normal prototype is processed according to the fault type to be monitored, so that a corresponding prototype of the fault type to be monitored is obtained.
3. And respectively installing the prototype with the single fault type to be monitored on a new energy speed reducer test bench for testing, and setting the test working condition according to the actual operation working condition of the prototype on a real vehicle.
If the new energy reducer is applied to a passenger vehicle, a sample machine can be subjected to a cycle test according to the WLTP working condition.
4. In the test process, a rotating speed signal, specifically a rotating speed pulse signal, of a rotating speed sensor on a prototype is collected, and the rotating speed signal (the rotating speed pulse signal) is subjected to rotating speed conversion to obtain an instantaneous rotating speed change curve.
5. And analyzing and processing the instantaneous rotating speed change curve of each fault type to be monitored respectively, and extracting the characteristic instantaneous rotating speed change characteristic of the fault type.
If the corresponding fault tooth is meshed under the fault type of broken tooth, the rapid rotating speed change can occur, and signals such as instantaneous impact and the like are shown on an instantaneous rotating speed change curve, so that the instantaneous impact signal in the rotating speed can be used as the instantaneous rotating speed change characteristic of the fault type of broken tooth and used as the fault index of the fault type to be monitored.
6. After establishing fault indexes for different prototype machines of the fault types to be monitored, sequencing the prototype machines of the same fault type to be monitored according to different fault degrees, such as sequencing from slight fault to serious fault or sequencing from serious fault to slight fault.
7. And respectively carrying out fault index detection bench tests on prototype machines with different fault degrees under the same fault type to be monitored, detecting fault index values of each rotating speed stage under different fault degrees, and obtaining a preliminary corresponding relation model of the fault index values of different fault degrees under different rotating speeds.
Specifically, when a prototype with a certain fault degree is tested, the prototype is tested according to a common test working condition, such as a WLTP working condition, so as to obtain a fault index value change curve which changes along with the rotating speed, such as fault index values of the rotating speed of 500r/min, 1000r/min and 1500 r/min.
8. Introducing the preliminary corresponding relation model of the fault degree, the rotating speed and the fault index value obtained in the previous step into an artificial intelligence algorithm for training, wherein an Adaboost algorithm (a self-adaptive enhancement algorithm) is adopted in the embodiment, and based on the classification result of each iterative training on the data in the training sample set, the weight of the corresponding data is updated according to a preset first classification rule based on correct classification, or the weight of the corresponding data is updated according to a preset second classification rule based on wrong classification; and responding to the iterative training that the classification accuracy of the sample set is greater than a preset threshold value, finishing the iterative training, and obtaining a parameter model of the fault degree, the rotating speed and the fault index value.
9. And respectively carrying out fatigue life tests on prototype machines with different fault degrees under the same fault type to be monitored to obtain a fault degree-residual life relation curve.
10. And importing the relation curves of the fault degrees and the residual lives of all fault types to be monitored into an artificial intelligence algorithm Adaboost for training to obtain a parameter matching model of the fault degrees and the residual lives of the same fault type.
11. And matching the parameter models of the fault degree, the rotating speed and the fault index value under the same fault type to be monitored and the parameter matching model of the fault degree-residual life, taking the fault index value as an independent variable and the fault degree and the residual life as dependent variables according to the corresponding relation of the function values, and establishing a comprehensive judgment model of each fault type.
During real vehicle monitoring and fault pre-reporting, the current rotating speed and instantaneous rotating speed change characteristics (fault index values) are obtained through analysis of rotating speed signals detected by a rotating speed sensor, corresponding fault types and fault degrees are obtained through matching of the rotating speed and the fault index values, and corresponding residual lives are obtained through the fault degrees.
12. And (4) carrying out statistical arrangement on all the comprehensive judgment models of the fault types to be monitored, and establishing a comprehensive judgment index model database, namely a fault model database.
In this embodiment, the vehicle-mounted operation state monitoring and fault forecasting system is shown in fig. 2, and the system includes a digital quantity acquisition module, an integrated industrial personal computer, a CAN communication module, an I/O control module, a cable, and the like. The digital quantity acquisition module, the CAN communication module and the I/O control module are integrated with the integrated industrial personal computer, and an interface with the outside is reserved.
The integrated industrial control computer connects the vehicle-mounted monitoring system with the photoelectric type rotating speed sensor on the power transmission system through a reserved BNC interface through a connecting cable. The integrated industrial control computer is connected with an alarm indicator lamp and a fault indicator lamp on an automobile instrument panel through an I/O control module. And the CAN communication module is connected into an automobile CAN communication network.
In specific implementation, in the construction process of the fault model database, the following test steps can be adopted:
2. for each fault type to be monitored, a prototype (power transmission system) with a single fault type to be monitored is collected, or a normal prototype is processed according to the fault type to be monitored to obtain a corresponding prototype of the fault type to be monitored, and the prototype is in the initial stage of the fault type to be monitored.
3. And respectively installing the prototype with the single fault type to be monitored and at the initial stage of the fault on a new energy speed reducer test bed for life test, and setting the test working condition according to the actual operation working condition of the prototype on a real vehicle.
4. In the test process, the fault degree development of the fault type to be monitored is monitored, the rotating speed signals, specifically rotating speed pulse signals, of the rotating speed sensors on the sample machines are respectively collected under different fault degrees, and rotating speed conversion is carried out on the rotating speed signals (rotating speed pulse signals) to obtain instantaneous rotating speed change curves of the sample machines under different fault degrees. And analyzing and processing the instantaneous rotating speed change curve of each fault type to be monitored respectively, and extracting the characteristic instantaneous rotating speed change characteristic of the fault type. And obtaining fault index values of all rotation speed stages under different fault degrees until the fault prototype is scrapped, and finally obtaining a preliminary corresponding relation model of the fault index values of different fault degrees under different rotation speeds.
By adopting the test mode, for each fault type to be monitored, only one or two sample machines are needed to carry out the life test, the fault degree of the sample machines is monitored in the life test process, the working condition test is carried out under different fault degrees, the fault index values under different rotating speeds under the fault degree are obtained, the fault index values of the sample machines of the fault type to be monitored in all stages under the full life cycle can be obtained until the test sample machines are scrapped, and all the fault index values of the sample machines of the fault type to be monitored under the full life cycle can be obtained through the training of the model by machine learning. The time cost and the economic cost for constructing the fault model database are greatly saved.
As shown in fig. 3, when real vehicle monitoring and failure prediction are specifically performed, the following steps are adopted:
and (3) importing the fault model database into an integrated industrial control computer, controlling an encoder acquisition module to be connected to a photoelectric rotation speed sensor on the real-vehicle new energy speed reducer in real time or at intervals in a timing manner during the running process of the real vehicle, and acquiring a rotation speed sensor signal (rotation speed pulse signal) installed on the new energy speed reducer.
After acquiring the signal of the rotation speed sensor, the integrated industrial control computer performs rotation speed conversion on the rotation speed signal (rotation speed pulse signal) to obtain an instantaneous rotation speed change curve, and according to the type of instantaneous rotation speed change characteristics in the fault model database, as several faults possibly coexist in the running process of the real vehicle, the possible instantaneous rotation speed change characteristics, namely fault indexes, are extracted one by one.
If 5 types of instantaneous rotating speed change characteristics (fault indexes) are totally covered in a fault model database, namely a fault index A, a fault index B, a fault index C, a fault index D and a fault index E, after rotating speed conversion is carried out on collected rotating speed pulse signals, an instantaneous rotating speed change curve is obtained, extraction of the 5 types of instantaneous rotating speed change characteristics is carried out on the instantaneous rotating speed change curve, if no fault hidden danger exists, the final extraction result is empty, and if the fault hidden danger exists, one type of fault index (such as the fault index A) can be finally extracted or several types of fault indexes (such as the fault index B and the fault index D) can be simultaneously extracted.
For the preliminary fault forecast, when a fault hidden trouble exists, a corresponding fault warning lamp on the instrument CAN be activated through the I/O control module, and meanwhile, fault mode information (extracted fault type) is sent to a vehicle-mounted computer in a CAN communication mode, so that a driver or a maintenance worker is reminded to process the fault mode in a striking mode.
In this embodiment, in order to further obtain more detailed fault information, the instantaneous speed change characteristic values of the extracted instantaneous speed change characteristics are respectively calculated, and matching is performed in the fault model database in combination with the extraction of the average speed of the speed signal, so as to obtain the fault degree and the predicted value of the remaining life under the fault type.
If a rotating speed signal is extracted at 3500r/min, the extracted fault index is a fault index B, and the instantaneous rotating speed change characteristic value (fault index value) of the fault index B is obtained as N, because the fault model database is subjected to model training by an artificial intelligence deep learning algorithm, the fault model database has instantaneous rotating speed change characteristic values (fault index values) of different fault indexes at different rotating speeds, in the fault model database, when the instantaneous rotating speed change characteristic value (fault index value) of the fault index B is N at 3500r/min, the fault degree of the fault index B is primary, and the corresponding residual life is K hours, the corresponding fault warning lamp on the instrument CAN be activated by the I/O control module, and simultaneously, the fault mode information (fault type), the residual life, the current fault monitoring value (instantaneous rotating speed change characteristic value) and the current fault monitoring value (instantaneous rotating speed change characteristic value) are set in a CAN communication mode, And sending detailed information such as fault degree and the like to a vehicle-mounted computer, and reminding a driver or a maintenance person to process in a striking mode.
After the driver or the maintenance personnel carry out corresponding operation processing, if the alarm information is manually cleared, the alarm state is cancelled or the position with possible fault is maintained and replaced, the alarm state can be automatically eliminated, the alarm information is cleared, and the alarm indicator lamp is cancelled when the monitoring index value is smaller than the fault index limit value.
The above description is only exemplary of the present invention and should not be taken as limiting, and any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (6)
1. A method for establishing a fault model database of an active automobile transmission system is characterized by comprising the following steps:
s1, collecting all fault characteristics of the automobile transmission system to be monitored from historical maintenance data, screening out fault characteristics related to the rotating speed as fault characteristics to be monitored, and classifying the fault characteristics to be monitored to obtain fault types to be monitored;
s2, according to the classification of the fault types to be monitored, selecting a prototype with the single fault type to be monitored for each fault type to be monitored, testing on a test bench according to the test working condition, acquiring a rotating speed signal under the fault type to be monitored through a rotating speed sensor arranged on a power transmission system, and calculating to obtain the instantaneous rotating speed change characteristic under the fault type to be monitored according to the rotating speed signal;
and S3, forming a fault model database by each fault type to be monitored and the corresponding instantaneous rotating speed change characteristics.
2. The method for establishing the active automobile transmission system fault model database according to claim 1, wherein for each fault type to be monitored, a plurality of prototypes which only have the fault type to be monitored and have different fault degrees are selected, and each prototype is tested on a test bench according to test conditions to obtain instantaneous rotating speed change characteristic values of the prototypes with different fault degrees in the fault mode to be monitored;
and combining the corresponding instantaneous rotating speed change characteristic values of each type of fault to be monitored under different fault degrees into the fault model database.
3. The method for establishing the active automobile transmission system fault model database according to claim 2, wherein the instantaneous rotation speed change characteristic values corresponding to each type of fault to be monitored under different fault degrees are introduced into an artificial intelligence deep learning algorithm for model training to obtain the parameter models of the instantaneous rotation speed change characteristic values and the fault degrees under each type of fault to be monitored.
4. The method for establishing the active automobile transmission system fault model database according to claim 3, wherein for each fault type to be monitored, a plurality of prototypes which only have the fault type to be monitored and have different fault degrees are selected, fatigue life tests are respectively carried out on each prototype on a test bench, and a relation curve between the different fault degrees and the residual life in the fault mode to be monitored is obtained.
5. The method for establishing the active automobile transmission system fault model database according to claim 4, wherein the relationship curve of different fault degrees and residual lives of each type of fault to be monitored is introduced into an artificial intelligence deep learning algorithm for model training to obtain a parameter model of the fault degrees and the residual lives of each type of fault to be monitored.
6. The method for establishing the active automobile transmission system fault model database according to claim 5, characterized in that the instantaneous speed change characteristic value under the same fault mode to be monitored is matched with the parameter model of the fault degree and the residual life to obtain a comprehensive parameter model of the instantaneous speed change characteristic value, the fault degree and the corresponding residual life; and constructing the fault model database by using the comprehensive parameter models under different fault modes to be monitored.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379158.4A CN113109043A (en) | 2021-04-08 | 2021-04-08 | Method for establishing fault model database of active automobile transmission system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110379158.4A CN113109043A (en) | 2021-04-08 | 2021-04-08 | Method for establishing fault model database of active automobile transmission system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113109043A true CN113109043A (en) | 2021-07-13 |
Family
ID=76714702
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110379158.4A Pending CN113109043A (en) | 2021-04-08 | 2021-04-08 | Method for establishing fault model database of active automobile transmission system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113109043A (en) |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127976A1 (en) * | 2011-03-24 | 2012-09-27 | 本田技研工業株式会社 | Method and apparatus for diagnosing engine fault |
| CN203069611U (en) * | 2012-12-17 | 2013-07-17 | 武汉理工大学 | FPGA (Field Programmable Gate Array) based instantaneous rotating speed online monitoring device for ship diesel engine |
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN105258940A (en) * | 2015-11-30 | 2016-01-20 | 上海无线电设备研究所 | Standardized multiwavelet and multiwavelet packet transformation method for mechanical failure quantitative extraction |
| WO2018120054A1 (en) * | 2016-12-30 | 2018-07-05 | Abb Schweiz Ag | Method and control system for faulted phase detection |
| CN108692939A (en) * | 2018-03-27 | 2018-10-23 | 西北工业大学 | Method for Bearing Fault Diagnosis under the conditions of a kind of variable speed based on thermal infrared imager |
| CN109708872A (en) * | 2017-10-20 | 2019-05-03 | 株洲中车时代电气股份有限公司 | A kind of train gear-box shaft coupling method for diagnosing faults, apparatus and system |
| CN110297178A (en) * | 2018-05-11 | 2019-10-01 | 宫文峰 | Diesel generating set fault diagnosis and detection device and method based on deep learning |
| CN111071291A (en) * | 2018-10-19 | 2020-04-28 | 株洲中车时代电气股份有限公司 | Train wheel set monitoring system and train wheel set monitoring method |
-
2021
- 2021-04-08 CN CN202110379158.4A patent/CN113109043A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012127976A1 (en) * | 2011-03-24 | 2012-09-27 | 本田技研工業株式会社 | Method and apparatus for diagnosing engine fault |
| CN203069611U (en) * | 2012-12-17 | 2013-07-17 | 武汉理工大学 | FPGA (Field Programmable Gate Array) based instantaneous rotating speed online monitoring device for ship diesel engine |
| WO2015158198A1 (en) * | 2014-04-17 | 2015-10-22 | 北京泰乐德信息技术有限公司 | Fault recognition method and system based on neural network self-learning |
| CN105258940A (en) * | 2015-11-30 | 2016-01-20 | 上海无线电设备研究所 | Standardized multiwavelet and multiwavelet packet transformation method for mechanical failure quantitative extraction |
| WO2018120054A1 (en) * | 2016-12-30 | 2018-07-05 | Abb Schweiz Ag | Method and control system for faulted phase detection |
| CN109708872A (en) * | 2017-10-20 | 2019-05-03 | 株洲中车时代电气股份有限公司 | A kind of train gear-box shaft coupling method for diagnosing faults, apparatus and system |
| CN108692939A (en) * | 2018-03-27 | 2018-10-23 | 西北工业大学 | Method for Bearing Fault Diagnosis under the conditions of a kind of variable speed based on thermal infrared imager |
| CN110297178A (en) * | 2018-05-11 | 2019-10-01 | 宫文峰 | Diesel generating set fault diagnosis and detection device and method based on deep learning |
| CN111071291A (en) * | 2018-10-19 | 2020-04-28 | 株洲中车时代电气股份有限公司 | Train wheel set monitoring system and train wheel set monitoring method |
Non-Patent Citations (2)
| Title |
|---|
| 宋宏智等: "高速机车轴承故障诊断与剩余寿命预测的发展及展望", 《轴承》 * |
| 蒋爱华: "基于虚拟仪器的发动机功率检测与故障诊断的研究", 《中国优秀硕士学位论文全文数据库 工程科技II辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106406273B (en) | Determination of the cause of a fault in a vehicle | |
| US6941204B2 (en) | System and method for diagnosing aircraft components for maintenance purposes | |
| CN108444708A (en) | The method for building up of rolling bearing intelligent diagnostics model based on convolutional neural networks | |
| CN108569607B (en) | Elevator fault early warning method based on bidirectional gating cyclic neural network | |
| US5809437A (en) | On board vehicle diagnostic module using pattern recognition | |
| US8996235B2 (en) | Repair assist system for vehicle servicing | |
| CN108027611B (en) | Decision assistance system and method for machine maintenance using expert opinion supervised decision mode learning | |
| CN107797537A (en) | A kind of prognostic and health management method applied to automatic production line | |
| EP2442288A1 (en) | Device abnormality monitoring method and system | |
| CN113063611B (en) | Equipment monitoring management method and system | |
| CN110515781B (en) | Complex system state monitoring and fault diagnosis method | |
| CN107490479A (en) | Bearing residual life Forecasting Methodology and device | |
| CN104266841A (en) | Fault diagnosis device and diagnosis method of diesel engine | |
| CN114738132A (en) | Supercharger speed sensor fault diagnosis method and system based on real ship data | |
| CN112558592B (en) | Vehicle fault prediction method and system and vehicle | |
| CN113109043A (en) | Method for establishing fault model database of active automobile transmission system | |
| CN113093709B (en) | Active on-vehicle running state monitoring and fault forecasting method | |
| CN113093712A (en) | Active vehicle-mounted running state monitoring and fault forecasting system for automobile transmission system | |
| CN115774955A (en) | Intelligent health degree assessment method for wind power gear box | |
| Kushiro et al. | Initial practice of telematics-based prognostics for commercial vehicles: Analysis tool for building faults progress model for trucks on telematics data | |
| CN114633709A (en) | Vehicle fault processing system and method | |
| CN115186007A (en) | Airborne data identification real-time display method and system for monitoring and reminding | |
| CN113865879A (en) | Guide system for automobile detection | |
| CN106528940A (en) | A method for evaluation and early warning for train axle properties based on mathematical models | |
| CN113487189A (en) | Petrochemical equipment fault probability risk assessment system and assessment method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |