CN107905990A - A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method - Google Patents
A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method Download PDFInfo
- Publication number
- CN107905990A CN107905990A CN201710472427.5A CN201710472427A CN107905990A CN 107905990 A CN107905990 A CN 107905990A CN 201710472427 A CN201710472427 A CN 201710472427A CN 107905990 A CN107905990 A CN 107905990A
- Authority
- CN
- China
- Prior art keywords
- hydraulic pump
- fuzzy
- nets
- fault diagnosis
- sensor
- 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
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F04—POSITIVE - DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS FOR LIQUIDS OR ELASTIC FLUIDS
- F04B—POSITIVE-DISPLACEMENT MACHINES FOR LIQUIDS; PUMPS
- F04B51/00—Testing machines, pumps, or pumping installations
Landscapes
- Engineering & Computer Science (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Testing And Monitoring For Control Systems (AREA)
- Fluid-Pressure Circuits (AREA)
Abstract
The present invention relates to a kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method, it is characterised in that including：STM32F103 microcontrollers (101), hydraulic pump (102), speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106), light-emitting diode display (107), light emission alarm device (108), A/D converter (109), keyboard (110), power circuit (111)；The present invention carries out fault diagnosis with bayes method based on FUZZY H NETS to hydraulic pump, FUZZY H pessimistic concurrency control is constructed using its failure sequence, bayes method and FUZZY H NETS are combined, the prior probability of bayes method is sought using FUZZY H NETS, differentiate the relation between conditional attribute, so that diagnostic method is guaranteed from terms of logic and accuracy two, make diagnostic system more intelligent, reliable.
Description
Technical field
The present invention relates to a kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method, belong to hydraulic pressure system
The fault diagnosis field of system.
Background technology
With the rapid development of science and technology, failure is carried out to hydraulic system with subjects such as electronics, computer, artificial intelligence and is examined
Disconnected and status monitoring, still belongs to newer research topic.Since most hydraulic system relative size is smaller, and modern hydraulic pressure
System develops to high pressure, high accuracy, powerful direction.Because the hydraulic unit of these large-scale hydraulic systems is accurate
Component simultaneously uses under high pressure, so need good maintaining, to prevent from getting rusty, burn into dirt, deterioration of oil etc.
Deng.Once hydraulic system failure cannot be rapid, will cause to stop production, or even huge economic loss can be caused.Therefore, hydraulic pressure
The system fault diagnosis subject very strong as a practicality, shows its importance.Reliability of the people to hydraulic system
Propose requirements at the higher level, Hydraulic Elements and system state monitoring and fault diagnosis technology is paid more and more attention.
Hydraulic pump is whole hydraulic system " heart ", it is the power source in whole hydraulic system, and whole system is produced
Raw conclusive influence.Its complicated, longevity of service, so being easiest to break down.For hydraulic pump, the cleaning of fluid
Whether, the height of cooling effect or user's level all directly influence his service life, while the holding of the performance of hydraulic pump
Also the service life of whole system other elements and the normal operation of system are directly influenced.So the level pumped in raising system, must
It is set to hydraulic pump early detection and prevention, the normal operation of hydraulic system system brings great benefit.
FUZZY H NETS is the modified network of Petri network, also similar with Petri network in terms of processing information.But with
Petri network processing information but also can store information compared to H nets only a kind of H nodes (also referred to as node).Its ability to express ratio
Petri network is stronger, is more suitable in current diagnostic techniques.On the one hand H nets compensate for Bayes when Bayes is combined
The defects of can not realizing extensive model, on the one hand allow H nets to have stronger learning ability.
The content of the invention
The present invention relates to a kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method, to improve at present
Some shortcomings in diagnostic techniques, allow staff to complete more accurately and efficiently on-line fault diagnosis.
To achieve the above object, the present invention provides following technical solution：
It is combined using FUZZY H NETS and bayes method and Hydraulic pump fault is analyzed in real time, makes system detectio more
Accurately.STM32F103 microcontrollers are a common enhanced Series of MCU, integrated chip timer, CAN, ADC,
SPI, I2C, USB, UART, can be with the intelligence of strengthening system and accuracy etc. multiple functions.It is suitable for the failure of hydraulic pump
Diagnostic system.
The all types of failure causes of hydraulic pump are concluded and analyzed, as hydraulic pump does not turn, normal rotation but not oil suction, work
Make the factors such as room noise is excessive and carry out detailed conclusion and analysis, find out the reason for causing failure, and so on look for it is out of order
Bottom reason, then carry out the modeling of FUZZY H NETS.In the algorithm write-in program that FUZZY H NETS is combined with bayesian theory again.
When hydraulic pump system breaks down, detected signal is converted to telecommunications by each corresponding detection in sensor
Number, then there is A/D converter to be converted into digital signal transmission as in microcontroller, the rational analysis of system is carried out to it by microcontroller.
The keyboard then processing as various functions key and number key, inputs microcontroller.Microcontroller again shows analysis result afterwards
Show in LED pipe, and carry out the luminous alarm signal of synchronism output, warning device is carried out luminous alarm.
System includes：STM32F103 microcontrollers (101), hydraulic pump (102), speed probe (103), temperature sensor
(104), flow sensor (105), pressure sensor (106), light-emitting diode display (107), light emission alarm device (108), A/D turn
Parallel operation (109), keyboard (110), power circuit (111)；Wherein hydraulic pump (102) is to diagnose object, hydraulic pump (102) test section
Mutually repeatedly kicked into speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106) respectively position
The detection of row parameters, speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor
(106) it is connected respectively with A/D converter (109), the analog signal of gained is then converted into digital signal by A/D converter
(109) input in STM32F103 microcontrollers (101), STM32F103 microcontrollers (101) again with keyboard (110), power circuit
(111), light-emitting diode display (107), light emission alarm device (108) are connected；
STM32F103 microcontrollers (101), for the reception and storage of each information of system, recycle program to carry out event
Barrier diagnosis；
Speed probe (103), is detected and becomes to the rotating speed of hydraulic pump and turn to electric signal；
Temperature sensor (104), is detected and becomes to the temperature of hydraulic pump and turn to electric signal；
Flow sensor (105), is detected the flow of hydraulic pump and is converted into electric signal；
Pressure sensor (106), is detected the operating pressure of hydraulic pump system and is converted into electric signal；
Light-emitting diode display (107), shows various digital signals；
Light warning device (108), luminous alarm is carried out to fault condition；
A/D converter (109), digital number amount is converted into by analog quantity；
Keyboard (110), inputs as function key and to various digital signals；
Power circuit (111), is powered whole system；
Technical solution：When hydraulic pump breaks down, the signal detected by sensor is converted into electric signal, turns by A/D
Change device and be translated into digital signal and input to STM32F103 microcontrollers and data are stored and analyzed, carry out FUZZY H NETS
With the reasoning that the fuzzy Bayes H that bayes method is combined is netted, in the process with keyboard come input and the function control of advancing
Operation, feeds back on light-emitting diode display by the reasoning results, and luminous alarm is carried out to failure by light emission alarm device.
The reasoning of Bayes's FUZZY H NETS and algorithm are as follows：
Bayes's FUZZY H pessimistic concurrency control of hydraulic pump system is established, to describe the process of the fault propagation of hydraulic pump system.Will
Event of the event of failure out as top is given, then finds out the occurrence cause of event.Similarly, analogize always until being
The reason for bottom for failure of uniting, establish the fault model of the system of hydraulic pump；
Each proposition collection is respectively：p1：Electrical circuit fault；p2：Relief valve spool is stuck；p3：Power supply is obstructed；p4：Pumping oil
Chamber enters foreign matter；p5：Electric wiring reversal connection；p6：Pump drive key comes off；p7：Rotating speed too bargain-hunting power deficiency；p8：Oil viscosity is excessive
It is or too low；p9：Intake line formula filtration apparatus blocks；p10：Intake line gas leakage；p11：Pasta is too low；p12：Revolution speed is too
It hurry up；p13：Parts depreciation formula is damaged；p14：Pump cover links screw loosening；p15：Revolution speed is too low；p16：There is leakage in system；p17：
Intake line latus rectum is small；p18：Pump does not turn；p19：Hydraulic pump turns to mistake；p20：Hydraulic pump oil suction obstacle；p21：Noise is excessive；
p22：Pump discharge deficiency；p23：Pump operating is bad；p24：Hydraulic pump produces failure；
By the available node reachable set (RS) of the model established, node reachable set (IRS) and adjacent bonds point set immediately
(AP), reverse reachable set (RIRS) immediately of node；
According to the FUZZY H pessimistic concurrency control and generation rule of foundation, the approach that its failure is occurred is obtained, and its failure is occurred
Confidence level u and threshold values λ, two adjacent nodes can be regarded as a fuzzy rule in FUZZY H NETS, in the mould of hydraulic pump
Rule in paste H nets can be expressed as
IF d1 THEN d2(CF=u1),
d1It is conditional proposition, d2It is conclusion proposition.The input intensity Q (p) of initial node p is calculated first.The input of node p
Intensity is exactly its corresponding ident value Q (p)=α (p), and as α (p) ＞ λ, node is lighted a fire, can be with for arbitrary next node
It is expressed as a (pm)=ua (pi), p ∈ pi,
Determine initial node collection SP, the probability of malfunction a (p to each initial node for having expertise and historical datai),
Each failure path l is determined further according to the excitating sequence of FUZZY H NETSi, and calculate whether each path has ignition ability, trigger
The highest node p of failurenIgniting, has the ability all to reach system highest node igniting path and is defined as N set.
The initial node probability a (p respectively obtained in N set by expertise and historical datai) general for the priori of failure
Rate, then by the order using FUZZY H NETS excitation, the probable value of the intensity of each node in set of computations N, and find out highest node
pnEach reversely reachable set (RIRS) p immediatelymi, obtain its probability a (pmi|pi)。
Given real time fail information is recycled to obtain its pmiProbability of malfunction a (pmi), recycle Bayesian inference formula
Calculate the posterior probability of its initial node failure
The posterior probability of its each initial node is arranged in order in the size by probability, obtained preceding 2 conducts
Diagnostic result, output are shown in fault diagnosis system.
The present invention can show diagnostic result situation by fault diagnosis platform.
Present invention incorporates Bayesian inference and FUZZY H NETS, diagnostic result is extrapolated using Bayesian probability law, by general
The size of rate provides several abort situation, then by fault diagnosis system, shows diagnostic result situation.Its algorithm is simple, diagnosis
Speed is fast, and fault-tolerance is strong, and the deficiency that FUZZY H NETS relies on priori in fault diagnosis is compensate for using bayes method,
There is certain meaning in the fault diagnosis of hydraulic pump in technology.
Brief description of the drawings
Fig. 1 is a kind of Fault Diagnosis of Hydraulic Pump system structure based on FUZZY H NETS and bayes method of patent of the present invention
Schematic diagram；
Fig. 2 is a kind of shellfish of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method of patent of the present invention
The algorithm pattern of this FUZZY H NETS of leaf；
Fig. 3 is a kind of event of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method of patent of the present invention
Hinder diagnostic model figure；
Embodiment
The embodiment of the present invention is described in detail below in conjunction with attached drawing.
Fig. 1 is a kind of Fault Diagnosis of Hydraulic Pump system structure based on FUZZY H NETS and bayes method of patent of the present invention
Schematic diagram.
Including：STM32F103 microcontrollers (101), hydraulic pump (102), speed probe (103), temperature sensor
(104), flow sensor (105), pressure sensor (106), light-emitting diode display (107), light emission alarm device (108), A/D turn
Parallel operation (109), keyboard (110), power circuit (111)；Wherein hydraulic pump (102) is to diagnose object, hydraulic pump (102) test section
Mutually repeatedly kicked into speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106) respectively position
The detection of row parameters, speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor
(106) it is connected respectively with A/D converter (109), the analog signal of gained is then converted into digital signal by A/D converter
(109) input in STM32F103 microcontrollers (101), STM32F103 microcontrollers (101) again with keyboard (110), power circuit
(111), light-emitting diode display (107), light emission alarm device (108) are connected；
STM32F103 microcontrollers (101), for the reception and storage of each information of system, recycle program to carry out event
Barrier diagnosis；
Speed probe (103), is detected and becomes to the rotating speed of hydraulic pump and turn to electric signal；
Temperature sensor (104), is detected and becomes to the temperature of hydraulic pump and turn to electric signal；
Flow sensor (105), is detected the flow of hydraulic pump and is converted into electric signal；
Pressure sensor (106), is detected the operating pressure of hydraulic pump system and is converted into electric signal；
Light-emitting diode display (107), shows various digital signals；
Light warning device (108), luminous alarm is carried out to fault condition；
A/D converter (109), digital number amount is converted into by analog quantity；
Keyboard (110), inputs as function key and to various digital signals；
Power circuit (111), is powered whole system；
Technical solution：When hydraulic pump breaks down, the signal detected by sensor is converted into electric signal, turns by A/D
Change device (109) and be translated into digital signal and input to STM32F103 microcontrollers (101) and data are stored and analyzed,
The reasoning for the fuzzy Bayes H nets that FUZZY H NETS is combined with bayes method is carried out, in the process with keyboard come input of advancing
With function control operate, on the reasoning results to be fed back to light-emitting diode display (107), by light emission alarm device (108) to failure into
Row luminous alarm.
Fig. 2 is a kind of shellfish of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method of patent of the present invention
The algorithm pattern of this FUZZY H NETS of leaf.
The reasoning of Bayes's FUZZY H NETS and algorithm are as follows：
In step 201, Bayes's FUZZY H pessimistic concurrency control of hydraulic pump system is established, is passed to describe the failure of hydraulic pump system
The process broadcast.Using the event to event of failure out as top, then find out the occurrence cause of event.Similarly, class always
Push away until the reason for obtain the bottom of the system failure, establish the fault model of the system of hydraulic pump；
A kind of failure of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method of Fig. 3 patents of invention is examined
Disconnected illustraton of model, each proposition collection are respectively：p1：Electrical circuit fault；p2：Relief valve spool is stuck；p3：Power supply is obstructed；p4：Pumping
Oil pocket enters foreign matter；p5：Electric wiring reversal connection；p6：Pump drive key comes off；p7：Rotating speed too bargain-hunting power deficiency；p8：Oil viscosity mistake
It is high or too low；p9：Intake line formula filtration apparatus blocks；p10：Intake line gas leakage；p11：Pasta is too low；p12：Revolution speed is too
It hurry up；p13：Parts depreciation formula is damaged；p14：Pump cover links screw loosening；p15：Revolution speed is too low；p16：There is leakage in system；p17：
Intake line latus rectum is small；p18：Pump does not turn；p19：Hydraulic pump turns to mistake；p20：Hydraulic pump oil suction obstacle；p21：Noise is excessive；
p22：Pump discharge deficiency；p23：Pump operating is bad；p24：Hydraulic pump produces failure；
In step 201, by the available node reachable set (RS) of the model established, node immediately reachable set (IRS) and
Adjacent bonds point set (AP), reverse reachable set (RIRS) immediately of node；
In step 202, according to the FUZZY H pessimistic concurrency control and generation rule of foundation, the approach that its failure is occurred, and its are obtained
The confidence level u and threshold values λ that failure is occurred, can regard two adjacent nodes as a fuzzy rule in FUZZY H NETS,
Rule in the FUZZY H NETS of hydraulic pump can be expressed as
IF d1 THEN d2(CF=u1),
d1It is conditional proposition, d2It is conclusion proposition.The input intensity Q (p) of initial node p is calculated first.The input of node p
Intensity is exactly its corresponding ident value Q (p)=α (p), and as α (p) ＞ λ, node is lighted a fire, can be with for arbitrary next node
It is expressed as a (pm)=ua (pi), p ∈ pi,
In step 203, initial node collection SP is determined, the failure to each initial node for having expertise and historical data
Probability a (pi), determine each failure path l further according to the excitating sequence of FUZZY H NETSi, and calculate whether each path has igniting
Ability, triggers the highest node p of failurenIgniting, has the ability all to reach system highest node igniting path and is defined as N collection
Close.
In step 204, the initial node probability a (p respectively obtained in N set by expertise and historical datai) it is event
The prior probability of barrier, then by the order using FUZZY H NETS excitation, the probable value of the intensity of each node in set of computations N, and look for
Go out highest node pnEach reversely reachable set (RIRS) p immediatelymi, obtain its probability a (pmi|pi)。
In step 205, given real time fail information is recycled to obtain its pmiProbability of malfunction a (pmi), recycle pattra leaves
This rational formula calculates the posterior probability of its initial node failure
In step 206, the posterior probability of its each initial node is arranged in order in the size by probability, it is obtained
First 2 are used as diagnostic result, and output is shown in fault diagnosis system.
The invention of this reality can show diagnostic result situation by fault diagnosis platform.
The invention of this reality combines Bayesian inference and FUZZY H NETS, extrapolates diagnostic result using Bayesian probability law, presses
The size of probability provides several abort situation, then by fault diagnosis system, shows diagnostic result situation.Its algorithm is simple, examines
Disconnected speed is fast, and fault-tolerance is strong, and the deficiency that FUZZY H NETS relies on priori in fault diagnosis is compensate for using bayes method,
There is certain meaning in the fault diagnosis of hydraulic pump in technology.
Claims (2)
- A kind of 1. Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method, it is characterised in that including： STM32F103 microcontrollers (101), hydraulic pump (102), speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106), light-emitting diode display (107), light emission alarm device (108), A/D converter (109), keyboard (110), power circuit (111)；Wherein hydraulic pump (102) for diagnosis object, hydraulic pump (102) respectively with speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106), which are connected, carries out the detection of parameters； And speed probe (103), temperature sensor (104), flow sensor (105), pressure sensor (106) and A/D respectively Converter (109) is connected, and the analog signal obtained by sensor is converted to digital signal by A/D converter (109), input In STM32F103 microcontrollers (101), STM32F103 microcontrollers (101) respectively with keyboard (110), power circuit (111), LED Display (107), light emission alarm device (108) are connected, and carry out detection and luminous alarm in real time, allow operating personnel to carry out failure Judge, and then the fault condition of detection device.
- 2. a kind of new hydraulic pump fault diagnosis system according to claim 1, it is characterised in that system uses FUZZY H Net carries out fault diagnosis with the method that Bayes is combined.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710472427.5A CN107905990A (en) | 2017-06-13 | 2017-06-13 | A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710472427.5A CN107905990A (en) | 2017-06-13 | 2017-06-13 | A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107905990A true CN107905990A (en) | 2018-04-13 |
Family
ID=61840973
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710472427.5A Pending CN107905990A (en) | 2017-06-13 | 2017-06-13 | A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107905990A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872004A (en) * | 2019-03-08 | 2019-06-11 | 北京工商大学 | A kind of equipment fault prediction based on fuzzy Bayesian network and health evaluating method |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101915234A (en) * | 2010-07-16 | 2010-12-15 | 西安交通大学 | Method for diagnosing compressor-associated failure based on Bayesian network |
| KR20110116565A (en) * | 2010-04-19 | 2011-10-26 | 목포대학교산학협력단 | Method determining indoor location using bayesian algorithm |
| CN105547717A (en) * | 2015-12-04 | 2016-05-04 | 哈尔滨工程大学 | Diesel engine lubricating system fault diagnosis method based on Bayes network |
| CN205563262U (en) * | 2016-01-12 | 2016-09-07 | 武汉科技大学 | Novel city rail train door fault diagnostic |
| CN106015028A (en) * | 2016-05-04 | 2016-10-12 | 江苏大学 | Intelligent water pump set monitoring and fault early warning method based on internet of things |
-
2017
- 2017-06-13 CN CN201710472427.5A patent/CN107905990A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20110116565A (en) * | 2010-04-19 | 2011-10-26 | 목포대학교산학협력단 | Method determining indoor location using bayesian algorithm |
| CN101915234A (en) * | 2010-07-16 | 2010-12-15 | 西安交通大学 | Method for diagnosing compressor-associated failure based on Bayesian network |
| CN105547717A (en) * | 2015-12-04 | 2016-05-04 | 哈尔滨工程大学 | Diesel engine lubricating system fault diagnosis method based on Bayes network |
| CN205563262U (en) * | 2016-01-12 | 2016-09-07 | 武汉科技大学 | Novel city rail train door fault diagnostic |
| CN106015028A (en) * | 2016-05-04 | 2016-10-12 | 江苏大学 | Intelligent water pump set monitoring and fault early warning method based on internet of things |
Non-Patent Citations (1)
| Title |
|---|
| 何友奇，等: "基于模糊贝叶斯网络的叉装车制动系统故障诊断研究", 《微型机与应用》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109872004A (en) * | 2019-03-08 | 2019-06-11 | 北京工商大学 | A kind of equipment fault prediction based on fuzzy Bayesian network and health evaluating method |
| CN109872004B (en) * | 2019-03-08 | 2021-06-04 | 北京工商大学 | Equipment fault prediction and health assessment method based on fuzzy Bayesian network |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108520080B (en) | Ship diesel generator fault prediction and health state online evaluation system and method | |
| CN108647716A (en) | A kind of diagnosing failure of photovoltaic array method based on composite information | |
| CN109766334A (en) | Processing method and system for electrical equipment online supervision abnormal data | |
| CN110297179A (en) | Diesel-driven generator failure predication and monitoring system device based on integrated deep learning | |
| CN111311059A (en) | Knowledge graph-based water mill room fault diagnosis method | |
| Liu et al. | Sparse dictionary learning based adversarial variational auto-encoders for fault identification of wind turbines | |
| CN110363090A (en) | Intelligent heart disease detection method, device and computer readable storage medium | |
| CN110084158A (en) | A kind of electrical equipment recognition methods based on intelligent algorithm | |
| CN112234707B (en) | High-energy synchrotron radiation light source magnet power failure recognition system | |
| CN111273125A (en) | RST-CNN-based power cable channel fault diagnosis method | |
| CN107905990A (en) | A kind of Fault Diagnosis of Hydraulic Pump system based on FUZZY H NETS and bayes method | |
| CN117131110A (en) | Method and system for monitoring dielectric loss of capacitive equipment based on correlation analysis | |
| CN116520806A (en) | Intelligent fault diagnosis system and method for industrial system | |
| CN111483125A (en) | Hydraulic fault early warning system for injection molding machine | |
| CN108051637A (en) | A kind of Intelligent electric energy meter clock battery failures diagnostic method | |
| CN110110426A (en) | A kind of Switching Power Supply filter capacitor abatement detecting method | |
| CN116611523B (en) | Method and system for predicting interpretable faults of turbofan engine | |
| CN117275202A (en) | Omnibearing real-time intelligent early warning method and system for dangerous sources in important areas of cultural relics | |
| CN108228800B (en) | Photovoltaic power generation system anomaly detection system and method based on data mining | |
| CN108096665B (en) | Equipment is nursed in the infusion for sentencing survey based on adaptive more redundancies | |
| Aihong et al. | Notice of Retraction: Fault diagnosis based on adaptive genetic algorithm and BP neural network | |
| CN103676835A (en) | Cloud computing based safety monitoring and auxiliary operation method for petrochemical device | |
| Zhu et al. | Research on SDG fault diagnosis of ocean shipping boiler system based on fuzzy granular computing under data fusion | |
| Reznik et al. | Signal change detection in sensor networks with artificial neural network structure | |
| CN112560252A (en) | Prediction method for residual life of aircraft engine |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180413 |
|
| WD01 | Invention patent application deemed withdrawn after publication |