CN104568446A - Method for diagnosing engine failure - Google Patents
Method for diagnosing engine failure Download PDFInfo
- Publication number
- CN104568446A CN104568446A CN201410503718.2A CN201410503718A CN104568446A CN 104568446 A CN104568446 A CN 104568446A CN 201410503718 A CN201410503718 A CN 201410503718A CN 104568446 A CN104568446 A CN 104568446A
- Authority
- CN
- China
- Prior art keywords
- data
- engine
- sensor
- genetic
- neural network
- 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
- 238000000034 method Methods 0.000 title claims abstract description 31
- 230000002068 genetic effect Effects 0.000 claims abstract description 32
- 238000013528 artificial neural network Methods 0.000 claims abstract description 28
- 238000003745 diagnosis Methods 0.000 claims abstract description 14
- 230000008569 process Effects 0.000 claims description 17
- 238000005457 optimization Methods 0.000 claims description 14
- 239000000523 sample Substances 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 230000007935 neutral effect Effects 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 4
- 230000001537 neural effect Effects 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 abstract 1
- 238000007873 sieving Methods 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 5
- 238000012544 monitoring process Methods 0.000 description 5
- 210000000349 chromosome Anatomy 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 230000001133 acceleration Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000000919 ceramic Substances 0.000 description 1
- 238000012512 characterization method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000008303 genetic mechanism Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000000977 initiatory effect Effects 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000011159 matrix material Substances 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000003014 reinforcing effect Effects 0.000 description 1
- 230000035807 sensation Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 238000010186 staining Methods 0.000 description 1
- 208000024891 symptom Diseases 0.000 description 1
Landscapes
- Combined Controls Of Internal Combustion Engines (AREA)
Abstract
The invention relates to a method for diagnosing engine failure, and belongs to the technical field of diagnosis of the engine failure. The method comprises the following steps: step 1, acquiring engine parameter data detected by a sensor; step 2, pre-processing the data in step 1; step 3, sieving the data in step 2 by a genetic BP neural network algorithm; step 4, comparing the sieved data with a set feature frequency range; step 5, outputting the failure. According to the method, the data detected by the sensor is processed and sieved by the genetic BP neural network algorithm, so that the objectivity and accuracy of the diagnosis are improved, whether an engine has a certain failure or not can be diagnosed accurately, false alarm can be avoided, and the problem of false alarm caused by the problem data detected by the sensor in the prior art is solved.
Description
Technical field
The present invention relates to Engine Failure Diagnostic Technology field, be specifically related to a kind of Fault Diagnosis of Engine.
Background technology
Engine is as the heart of engineering machinery, and the quality of its performance is directly connected to dynamic property, economy, reliability, the feature of environmental protection and the security of the operation of engineering machinery whole system.Along with the raising of engine reinforcing degree, the structure of engine also becomes very complicated, and condition of work is also very severe, and the possibility broken down increases greatly.
The former prisoners such as the Long-Time Service friction of engine, wearing and tearing and installation, adjustment maintenance are improper, cause the tolerance clearance of engine each portion parts excessive, cause the various abnormal voice of engine.Modal Engine Wear Fault Based on Integrated has: piston knock rings, piston pin rings, the connecting-rod bearing rings, crankshaft bearing rings, valve rings.The method generally applied is by the observation of diagnostic personnel and sensation and simple tool, adopts indivedual symptom to be amplified or the method for temporarily blanking is diagnosed, and this just requires to have suitable knowwhy, operative skill and abundant practical experience.Along with the development of modern science technology, people carry out Real-Time Monitoring by utilizing each parts of various sensor to engine, but the data of Real-Time Monitoring are not representative and can not autonomous garbled data, there will be the event of false alarm, affect the judgement of driver or maintenance personal.
Summary of the invention
In order to overcome Sensor monitoring in prior art to problem data cause the problem of false alarm, the invention provides a kind of Fault Diagnosis of Engine.
Technical scheme of the present invention is: a kind of Fault Diagnosis of Engine, and the method comprising the steps of:
The engine parameter data that step one, acquisition sensor detect;
Step 2, pre-service process is carried out to the data in step one;
Step 3, the data of Genetic BP Neutral Network algorithm to step 2 are utilized to screen;
After step 4, screening, data compare with setting characteristic frequency region;
Step 5, output fault.
The sensor of described step one comprises at least one speed probe and at least one vibration transducer.
Genetic BP Neutral Network algorithm in described step 3 is divided into three parts: determine BP neural network structure; Genetic algorithm optimization weights and threshold; BP neural metwork training and prediction.
What export after genetic algorithm optimization BP neural network is the network trained, and screens for the data detected sensor.
The present invention has following good effect: the present invention can detect the faults such as piston knock rings, piston pin rings, connecting-rod bearing sound, crankshaft bearing sound and valve ring, by the frequency detecting to different parts, the different faults problem of engine can be detected, reach the effect of accurately detection of engine faults in real time.In addition make use of genetic optimization BP neural network algorithm in the present invention to process the data that sensor records and screen, improve objectivity and the accuracy of diagnosis, whether can there is certain fault by Diagnosis on Engine exactly, the situation of false alarm can not occur.
Accompanying drawing explanation
Fig. 1 is the workflow diagram of the Fault Diagnosis of Engine in the present invention;
Fig. 2 is the process flow diagram of the BP neural network of genetic algorithm optimization in the present invention;
Fig. 3 is the process flow diagram of the neural network algorithm in the present invention.
Embodiment
Contrast accompanying drawing below, by the description to embodiment, the specific embodiment of the present invention is as the effect of the mutual alignment between the shape of involved each component, structure, each several part and annexation, each several part and principle of work, manufacturing process and operation using method etc., be described in further detail, have more complete, accurate and deep understanding to help those skilled in the art to inventive concept of the present invention, technical scheme.
A kind of Fault Diagnosis of Engine, this process employs Genetic BP Neutral Network algorithm to screen the data that sensor detects and preferentially go out best measurement value sensor, then compare to obtain with the characteristic frequency region of default the conclusion that is out of order, the ordinary sensors data of ratio send recording controller always and carry out real time of day to compare the accuracy that process data come high, and the problem of false alarm can not occur.
As shown in Figure 1, method step of the present invention comprises:
The data that S01 step one, acquisition sensor detect.Sensor comprises at least one speed probe and at least one vibration transducer,
Wherein, vibration transducer is positioned on petrol engine monitoring point, and speed probe is positioned near the main shaft of engine.Vibration transducer can be piezoelectric ceramic vibrator dynamic sensor or ICP acceleration transducer; Speed probe mainly refers to Hall element, photoelectric sensor or magnetoelectric sensor, at least will have a vibration transducer and a speed probe in whole engine failure method for diagnosing faults.If what vibration transducer adopted is ICP acceleration transducer, then adopt constant current source to be ICP sensor power, ensure that ICP sensor is in standard operation range of current.Use system of the present invention can be the accessory that hand-held also can be mounted in automotive interior, multiple use-pattern, can choose at random, if hand-held, during use, sensor is placed on assigned address, is arranged on vehicle body, and the data detected in real time all can be sent to pretreatment module and carry out data prediction by sensor.
S02 step 2, pre-service process is carried out to the data in step one.Pre-service is normalized the data that sensor records, and normalization can accelerate the convergence of training network, and normalized concrete effect is the statistical distribution concluding unified samples.No matter be in order to modeling or in order to calculate, first basic measuring unit is same, the use of convenient Genetic BP Neutral Network algorithm below.
Because genetic algorithm directly can not process the parameter of problem space, therefore must by coding requiring that the feasible solution of problem is expressed as chromosome or the individuality in hereditary space.Conventional coding method has bit-string encodings, Gray coding, real coding (floating point coding), multistage parameter coding, in order string encoding, structured coding etc.Real coding need not carry out numerical value conversion, directly can carry out operatings of genetic algorithm in the phenotype of separating.Therefore the present invention first carries out pre-service to data, and each chromosome is a real number vector.
S03 step 3, utilize genetic algorithm optimization after the data of BP neural network algorithm to step 2 screen, obtain best sensor measurement data, so that step by step rapid under carrying out accurately, avoid sensor and send the data difference and false alarm situation that data cause due to accidental error in real time, and the situation of false alarm can not be there is in the sensing data in the present invention after algorithm process.
The learning algorithm of BP neural network is based on Gradient Descent, and therefore easy local minimum, exists the slow and network parameter of speed of convergence simultaneously and training parameter is difficult to shortcomings such as determining.Genetic algorithm is a kind of searching algorithm using for reference organic sphere natural selection and natural genetic mechanism, and it can find optimum or quasi-optimal solution in complicated and huge search volume, and has the advantages such as algorithm is simple, applicable, strong robustness, and its application is very ripe at present.Based on the relative merits of BP artificial neural network and genetic algorithms, the two is combined the relative merits making them complementary, have greatly improved.
Genetic BP Neutral Network algorithm is mainly divided into three parts: determine BP neural network structure; Genetic algorithm optimization weights and threshold; BP neural metwork training and prediction.Its flow process as shown in Figure 2 and Figure 3, first the topological structure of neural network is determined, then coding is carried out to the weights and threshold of neural network and obtain initial population, genetic algorithm processing section is entered after the process of neural network algorithm part, the new colony produced in genetic algorithm continues when can not meet end condition to run from neural network algorithm part, if meet end condition, carries out decoding process and obtains best neural network weight and threshold value.
Neural network algorithm partial process view as shown in Figure 3, after initial population is obtained to neural network weight and threshold coding, decoding obtains weights and threshold, weights and threshold is assigned to newly-built BP network, use training sample training network, then use test sample book test network, finally carry out test error, continue to enter in genetic algorithm flow process.Network training is a process constantly revising weights and door screen value, by training, makes the output error of network more and more less.
BP neural network structure is topological structure, is to determine according to the input/output parameters number of sample, so just can determine the number of genetic algorithm optimization parameter, thus determine the code length of population at individual.Because genetic algorithm optimization parameter is initial weight and the door screen value of BP neural network, as long as network structure is known, the number of weights and news value just there is known.The weights and threshold of neural network is generally be [-0.5 by random initializtion, 0.5] interval random number, this initiation parameter is very large on the impact of network training, but cannot accurately obtain again, for identical initial weight value and threshold value, the training result of network is the same, and introducing genetic algorithm is exactly initial weight in order to optimization the best and threshold value.
Genetic algorithm optimization BP neural network is initial weight value and the threshold value of carrying out Optimized BP Neural Network by genetic algorithm, enables the BP neural network after optimization carry out sample predictions better.The key element of genetic algorithm optimization BP neural network comprises initialization of population, fitness function, selection opertor, crossover operator and mutation operator etc., as shown in Figure 2.
In genetic algorithm, neural network is encoded: replace the binary digit string in genetic algorithm to carry out direct characterization parameter for weights and threshold with decimal number word string.
Calculate and be suitable for angle value: ideal adaptation degree adopts the function error of network, and its fitness of individuality that namely error is large is little, is specifically expressed as the inverse that fitness is network error function.The present invention is in order to make BP network when predicting, the residual error of predicted value and expectation value is little as far as possible, so select the output of norm as objective function of the predicted value of forecast sample and the error matrix of expectation value.
Selective staining body copies: after the calculating of ideal adaptation degree completes, and selects individual inheritance that fitness is large to of future generation, makes weights more and more close to optimum solution sky.
Intersection, mutation process: adopt the random two-way search technique based on probability; With certain probability, from male parent population, choose two chromosomes randomly carry out interlace operation, when new chromosome makes current solution Quality advance, just receive this solution be modified as new current solution.
After S04 step 4, screening, data compare with setting characteristic frequency region, thus can judge whether engine has fault.
Sensing data is after screening, the best expression data of engine condition and the characteristic frequency region of setting compare, and the energy value in characteristic frequency extraction calculating frequency range is carried out to vibration signal, if energy value is less than threshold value, illustrate that engine does not have certain fault; Otherwise illustrate to there is certain fault, the trend of the position of further failure judgement, fault degree and fault.Wherein piston knock rings characteristic frequency is 1360-2400Hz; It is 1500-2500Hz that piston pin rings characteristic frequency; It is 660-860Hz that the connecting-rod bearing rings characteristic frequency; It is 330-605Hz that crankshaft bearing rings characteristic frequency; It is 4600-6800Hz that valve rings characteristic frequency; By detecting the energy variation in characteristic spectra, can identify whether engine has certain fault.
S05 step 5, output fault, by the relatively rear output engine fault type of data, facilitate driver or maintenance personal to check.The engine failure of the present invention's monitoring has: piston knock rings, piston pin rings, the connecting-rod bearing rings, crankshaft bearing rings and valve rings, the characteristic frequency of each parts is in the existing introduction of step 4, by the frequency detecting to different parts, the different faults problem of engine can be detected, reach the effect of accurately detection of engine faults in real time.
Above by reference to the accompanying drawings to invention has been exemplary description; obvious specific implementation of the present invention is not subject to the restrictions described above; as long as have employed the improvement of the various unsubstantialities that method of the present invention is conceived and technical scheme is carried out; or design of the present invention and technical scheme directly applied to other occasion, all within protection scope of the present invention without to improve.
Claims (4)
1. a Fault Diagnosis of Engine, is characterized in that, the method comprising the steps of:
The engine parameter data that step one, acquisition sensor detect;
Step 2, pre-service process is carried out to the data in step one;
Step 3, the data of Genetic BP Neutral Network algorithm to step 2 are utilized to screen;
After step 4, screening, data compare with setting characteristic frequency region;
Step 5, output fault.
2. Fault Diagnosis of Engine according to claim 1, is characterized in that, the sensor of described step one comprises at least one speed probe and at least one vibration transducer.
3. Fault Diagnosis of Engine according to claim 1, is characterized in that, the Genetic BP Neutral Network algorithm in described step 3 is divided into three parts:
Determine BP neural network structure;
Genetic algorithm optimization weights and threshold;
BP neural metwork training and prediction.
4. Fault Diagnosis of Engine according to claim 3, is characterized in that, what export after genetic algorithm optimization BP neural network is the network trained, and screens for the data detected sensor.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410503718.2A CN104568446A (en) | 2014-09-27 | 2014-09-27 | Method for diagnosing engine failure |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410503718.2A CN104568446A (en) | 2014-09-27 | 2014-09-27 | Method for diagnosing engine failure |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104568446A true CN104568446A (en) | 2015-04-29 |
Family
ID=53085027
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410503718.2A Pending CN104568446A (en) | 2014-09-27 | 2014-09-27 | Method for diagnosing engine failure |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104568446A (en) |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105572492A (en) * | 2015-10-22 | 2016-05-11 | 北京建筑大学 | City rail train auxiliary inverter fault diagnosis device |
| CN105572493A (en) * | 2015-10-22 | 2016-05-11 | 北京建筑大学 | Vehicle-mounted-ground auxiliary inverter remote fault diagnosis system |
| CN106102140A (en) * | 2016-05-27 | 2016-11-09 | 北京灵龄科技有限责任公司 | The power consumption optimization method of wireless senser and device |
| CN106339720A (en) * | 2016-08-23 | 2017-01-18 | 万毅 | Automobile engine failure detection method |
| CN106408687A (en) * | 2016-11-24 | 2017-02-15 | 沈阳航空航天大学 | Automobile engine fault early warning method based on machine learning method |
| CN108303262A (en) * | 2018-01-19 | 2018-07-20 | 南京世界村汽车动力有限公司 | A kind of automobile engine on-line monitoring and fault diagnosis system |
| CN108871781A (en) * | 2018-04-25 | 2018-11-23 | 佛山科学技术学院 | A kind of Fault Diagnosis of Engine and its system |
| CN105928710B (en) * | 2016-04-15 | 2019-02-12 | 中国船舶工业系统工程研究院 | A kind of diesel engine fault monitoring method |
| CN109357876A (en) * | 2018-12-29 | 2019-02-19 | 潍柴动力股份有限公司 | Method and device for determining engine failure |
| 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 |
| CN109933572A (en) * | 2019-01-28 | 2019-06-25 | 安徽斯瑞菱智能科技有限公司 | A kind of data managing method and system for large enterprise |
| CN110470481A (en) * | 2019-08-13 | 2019-11-19 | 南京信息工程大学 | Fault Diagnosis of Engine based on BP neural network |
| US20200118358A1 (en) * | 2018-10-11 | 2020-04-16 | Hyundai Motor Company | Failure diagnosis method for power train components |
| CN111259993A (en) * | 2020-03-05 | 2020-06-09 | 沈阳工程学院 | Fault diagnosis method and device based on neural network |
| CN111435557A (en) * | 2019-01-15 | 2020-07-21 | 卡特彼勒公司 | Fault detection device for detecting problems with machine components |
| CN112327734A (en) * | 2020-10-29 | 2021-02-05 | 工业互联网创新中心（上海）有限公司 | Engineering machine tool remote monitering system based on internet |
| CN115130522A (en) * | 2022-07-15 | 2022-09-30 | 南方电网数字电网研究院有限公司 | Secondary circuit fault detection method and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5361628A (en) * | 1993-08-02 | 1994-11-08 | Ford Motor Company | System and method for processing test measurements collected from an internal combustion engine for diagnostic purposes |
| CN101354315A (en) * | 2008-09-05 | 2009-01-28 | 爱立迈科（宁波）计测仪器有限公司 | Device and method for tracking and detecting engine state based on vibration signal |
| CN101839805A (en) * | 2010-03-19 | 2010-09-22 | 同济大学 | Method for quality inspection of active fault and diagnosis of intelligent fault of engine |
| CN102620939A (en) * | 2012-04-10 | 2012-08-01 | 潍柴动力股份有限公司 | Engine torque predicting method and engine torque predicting device |
| CN102661866A (en) * | 2012-05-11 | 2012-09-12 | 天津工业大学 | Engine fault identification method based on time-domain energy and support vector machine |
| CN103278329A (en) * | 2013-05-21 | 2013-09-04 | 哈尔滨理工大学 | Portable handheld automobile engine failure prediction instrument |
-
2014
- 2014-09-27 CN CN201410503718.2A patent/CN104568446A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5361628A (en) * | 1993-08-02 | 1994-11-08 | Ford Motor Company | System and method for processing test measurements collected from an internal combustion engine for diagnostic purposes |
| CN101354315A (en) * | 2008-09-05 | 2009-01-28 | 爱立迈科（宁波）计测仪器有限公司 | Device and method for tracking and detecting engine state based on vibration signal |
| CN101839805A (en) * | 2010-03-19 | 2010-09-22 | 同济大学 | Method for quality inspection of active fault and diagnosis of intelligent fault of engine |
| CN102620939A (en) * | 2012-04-10 | 2012-08-01 | 潍柴动力股份有限公司 | Engine torque predicting method and engine torque predicting device |
| CN102661866A (en) * | 2012-05-11 | 2012-09-12 | 天津工业大学 | Engine fault identification method based on time-domain energy and support vector machine |
| CN103278329A (en) * | 2013-05-21 | 2013-09-04 | 哈尔滨理工大学 | Portable handheld automobile engine failure prediction instrument |
Non-Patent Citations (1)
| Title |
|---|
| 董恩国等: "基于遗传神经网络算法的发动机性能预测", 《起重运输机械》 * |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105572493A (en) * | 2015-10-22 | 2016-05-11 | 北京建筑大学 | Vehicle-mounted-ground auxiliary inverter remote fault diagnosis system |
| CN105572492B (en) * | 2015-10-22 | 2018-05-04 | 北京建筑大学 | A kind of municipal rail train subordinate inverter trouble-shooter |
| CN105572493B (en) * | 2015-10-22 | 2018-05-04 | 北京建筑大学 | A kind of vehicle-mounted-ground subordinate inverter remote failure diagnosis system |
| CN105572492A (en) * | 2015-10-22 | 2016-05-11 | 北京建筑大学 | City rail train auxiliary inverter fault diagnosis device |
| CN105928710B (en) * | 2016-04-15 | 2019-02-12 | 中国船舶工业系统工程研究院 | A kind of diesel engine fault monitoring method |
| CN106102140A (en) * | 2016-05-27 | 2016-11-09 | 北京灵龄科技有限责任公司 | The power consumption optimization method of wireless senser and device |
| CN106102140B (en) * | 2016-05-27 | 2022-03-22 | 集道成科技(北京)有限公司 | Power consumption optimization method and device of wireless sensor |
| CN106339720A (en) * | 2016-08-23 | 2017-01-18 | 万毅 | Automobile engine failure detection method |
| CN106339720B (en) * | 2016-08-23 | 2019-09-10 | 温州大学 | A kind of abatement detecting method of automobile engine |
| CN106408687A (en) * | 2016-11-24 | 2017-02-15 | 沈阳航空航天大学 | Automobile engine fault early warning method based on machine learning method |
| CN108303262A (en) * | 2018-01-19 | 2018-07-20 | 南京世界村汽车动力有限公司 | A kind of automobile engine on-line monitoring and fault diagnosis system |
| CN108871781A (en) * | 2018-04-25 | 2018-11-23 | 佛山科学技术学院 | A kind of Fault Diagnosis of Engine and its system |
| 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 |
| CN109357876A (en) * | 2018-12-29 | 2019-02-19 | 潍柴动力股份有限公司 | Method and device for determining engine failure |
| CN111435557B (en) * | 2019-01-15 | 2023-07-14 | 卡特彼勒公司 | Fault detection device for detecting machine part problems |
| CN111435557A (en) * | 2019-01-15 | 2020-07-21 | 卡特彼勒公司 | Fault detection device for detecting problems with machine components |
| CN109933572A (en) * | 2019-01-28 | 2019-06-25 | 安徽斯瑞菱智能科技有限公司 | A kind of data managing method and system for large enterprise |
| CN110470481B (en) * | 2019-08-13 | 2020-11-24 | 南京信息工程大学 | Engine Fault Diagnosis Method Based on BP Neural Network |
| CN110470481A (en) * | 2019-08-13 | 2019-11-19 | 南京信息工程大学 | Fault Diagnosis of Engine based on BP neural network |
| CN111259993A (en) * | 2020-03-05 | 2020-06-09 | 沈阳工程学院 | Fault diagnosis method and device based on neural network |
| CN112327734A (en) * | 2020-10-29 | 2021-02-05 | 工业互联网创新中心（上海）有限公司 | Engineering machine tool remote monitering system based on internet |
| CN112327734B (en) * | 2020-10-29 | 2021-06-29 | 工业互联网创新中心（上海）有限公司 | Engineering machine tool remote monitering system based on internet |
| CN115130522A (en) * | 2022-07-15 | 2022-09-30 | 南方电网数字电网研究院有限公司 | Secondary circuit fault detection method and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104568446A (en) | Method for diagnosing engine failure | |
| CN116578940B (en) | Bearing fault new type identification and diagnosis method based on mixed depth self-coding | |
| CN108444708A (en) | The method for building up of rolling bearing intelligent diagnostics model based on convolutional neural networks | |
| CN118212938B (en) | Iron tower bolt health detection method and system based on artificial intelligence and voiceprint | |
| CN119848787B (en) | Coal mine equipment failure prediction system and method based on big data | |
| CN110375983B (en) | Valve fault real-time diagnosis system and method based on time series analysis | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index | |
| CN112820321A (en) | Remote intelligent audio diagnosis system, method, equipment and medium for oil pumping unit | |
| CN112179691A (en) | Anomaly detection system and method for mechanical equipment running state based on adversarial learning strategy | |
| CN119515085A (en) | A method and system for managing safety of suspended basket transportation | |
| CN111710329A (en) | Deep learning-based ship engine voiceprint fault discrimination method and system | |
| CN118013275A (en) | Fault diagnosis method, device and computer equipment for screw transmission system | |
| CN118051822A (en) | Equipment running state abnormality detection method based on voiceprint recognition technology | |
| CN119377616B (en) | A method and device for constructing a hydraulic pump life prediction model | |
| CN119475231B (en) | Substation equipment fault early warning system and method integrating defect detection | |
| CN120217195A (en) | Motor fault diagnosis method, system, electronic equipment and motor fault diagnosis model training method | |
| CN119807753A (en) | Machine residual life prediction method, system and equipment based on hybrid data driving model | |
| CN115358055B (en) | Aero-engine operation risk monitoring and early warning system based on degradation level soft representation | |
| CN119124676A (en) | A bogie frame fault early warning method and system based on dynamic strain signal | |
| CN117664558A (en) | Generator gearbox abnormality detection method, device, equipment and storage medium | |
| CN111259494B (en) | Health monitoring and analyzing method for heavy machine equipment | |
| Medina et al. | A LSTM neural network approach using vibration signals for classifying faults in a gearbox | |
| CN115270875A (en) | Diaphragm pump running state monitoring method based on deep learning | |
| CN121090088A (en) | Large sliding bearing state monitoring method, device and system | |
| CN121026310A (en) | A structural vibration anomaly detection system based on a multi-task autoencoder |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150429 |