CN108931387A - The method for diagnosing faults based on multiple sensor signals analysis of Accurate Diagnosis decision is provided - Google Patents
The method for diagnosing faults based on multiple sensor signals analysis of Accurate Diagnosis decision is provided Download PDFInfo
- Publication number
- CN108931387A CN108931387A CN201810498072.1A CN201810498072A CN108931387A CN 108931387 A CN108931387 A CN 108931387A CN 201810498072 A CN201810498072 A CN 201810498072A CN 108931387 A CN108931387 A CN 108931387A
- Authority
- CN
- China
- Prior art keywords
- neural network
- data
- decision
- temperature
- failure
- 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.)
- Granted
Links
Abstract
The method for diagnosing faults based on multiple sensor signals analysis of Accurate Diagnosis decision is provided the invention discloses a kind of, using multiple sensors acquisition heat pump unit in parameters such as the pressure, temperature, flow of operational process, and using the vibration signal of vibrating sensor acquisition unit, to grasp the equipment state of net for air-source heat pump units comprehensively with this.On this basis, combine Multi Intelligent Techniques method, the advantage of integrated use intellectual technology respectively, it maximizes favourable factors and minimizes unfavourable ones, status monitoring, fault diagnosis and intelligence are carried out to net for air-source heat pump units to indicate, can be effectively improved the sensibility and accuracy of monitoring diagnosis system, be reduced misdiagnosis rate and rate of missed diagnosis.Meanwhile signal processing platform convenient to use is had devised using GUI design method based on MATLAB language.In the case where not having to understand system mechanism and analysis data, accurately diagnosis decision is provided for general operator.
Description
The application is application number：201510846925.2, the applying date：2015-11-30, title " are believed based on multisensor
Number analysis method for diagnosing faults " divisional application.
Technical field
The present invention relates to a kind of diagnosis for obtaining mechanical equipment information using multisensor, being analyzed using polyhybird algorithm
Method, and constituted with this method for diagnosing faults of a kind of high precision, low misdiagnosis rate.
Background technique
Heat pump techniques experienced tortuous development process after 1854 propose, has entered high speed comprehensively at present and has sent out
In the exhibition stage, especially under energy crisis and the environmental pressure of global warming, heat pump techniques become various countries' focus of attention, right
Research, application and the popularization of all kinds of heat pump techniques have also risen to the height given more sustained attention.Skill as energy-saving and emission-reduction
Art, heat pump techniques have a extensive future, have more and more countries and governments, Enterprise Consciousness to heat pump can it is energy saving with bring and
Environmental benefit, marketing data also indicate that future developing trend is good.The application of heat pump techniques in practical projects is studied, heat is made
The energy conservation and environmental protection effect of pump is preferably played in practice, is the important foundation for promoting heat pump techniques, therefore Practical Project
Using and optimizing research work it is particularly significant.
In recent years, in order to meet user's domestic hot-water's needs, heat pump hot-water system use at home it is more and more extensive, but
It is the aging of equipment or other reasons in heat pump hot-water system as time goes by, leads to system operation inevitably
There are various enemy's barriers.Currently, removal of faults on system and maintenance of equipment rely primarily on Field Force experience and pertinent instruments it is complete
At the diagnosis of failure, can failure exclude the constraint by Field Force's level and experience in time.And it is only limited to failure portion
The local diagnosis divided, is short of systematic diagnosis maintenance and failure prediction method, and failure cause search and investigation empirically account for
It is total to eliminate 50% or more of fault time.Therefore, establish a perfect fault diagnosis system over the ground source heat pump hot-water system into
Quickly and effectively intelligent diagnostics are of great significance row.
Fault diagnosis is substantially a pattern recognition problem, it includes signal acquisition, feature extraction and selection and state
Identify three links, wherein signal acquisition is the premise of fault diagnosis, and feature extraction and selection are the key that fault diagnosises, and
State recognition is then the core of diagnosis.It only ensure that the correctness of acquisition signal, extract and select the sensibility of feature, with
And the validity of state identification method, the precision of fault diagnosis could be improved.
Some parameters of mechanical equipment can reflect mechanical failure that may be present, such as temperature, pressure, flow parameter,
The measurement that sensor can be used in these parameters obtains.The vibration and noise and its spy that mechanical equipment generates in the process of running
Reference breath is the main signal for reflecting mechanical equipment and its operating status variation.Can be obtained by using sensor it is a kind of or
Multi-signal, for grasping the state of machine operation.Obtaining multiple sensors signal can contribute to grasp machinery in all directions
Operating status grasps the equipment state of net for air-source heat pump units comprehensively with this.
Currently, the method for diagnosing faults for heat pump unit is less, or only take single method for diagnosing faults, root
System failure differentiation is carried out according to the data that certain single sensors obtain, result not only lacks accuracy, but also there is
Wrong diagnosis.Therefore, the multiple sensors signal for obtaining the same system a certain moment takes long benefit using a variety of Intelligent Diagnosis Technologies
It is short, can efficiently solve single Intelligent Diagnosis Technology there are the problem of, improve accuracy, the sensitivity of diagnosis detection system
Property, reduce misdiagnosis rate.
State identification method based on single Intelligence Classifier, it is difficult to the accurately early stage event of diagnosis of complex mechanical equipment
Barrier and combined failure.In order to overcome the shortcomings of single Intelligence Classifier, the diagnosis rate of raising complex device fault diagnosis need
The mixed intelligent diagnosing method combined using multiple Intelligence Classifiers.Combination of Multiple Classifiers diagnosis is to realize that hybrid intelligent is examined
One of disconnected mode.Different input feature vectors can be obtained by using different preconditioning technique or feature extracting method
Collection, and input and typically exhibit complementary sort feature between several classifiers of different characteristic collection.Therefore, if by different
Several classifiers output result of input feature vector collection is synthesized using integrated technology, and final result can be better than best list
One classifier.
By the knowledge-softwared of heat-pump hot-water domain expert, failure is identified using intelligent algorithm, Ke Yigeng
The normal operation of Guarantee control system well.Knowledge based engineering fault diagnosis method is due to having in artificial intelligence diagnosis' technology
Intelligence and be widely used independent of the characteristics of mathematical model.
Jiang Yiqiang of Harbin Institute of Technology et al. to the fault diagnosis of net for air-source heat pump units neural network based into
It has gone research, has been simulated using performance of the BP neural network model to heat pump unit, and is real with the sign from simulated experiment
Knowledge in example and specialist field trains neural network.
Zhang Zhonghe, Wang Kang of Xi'an University of Architecture and Technology et al. application Artificial Neural Network are to groundwater heat pump
The failure of system is diagnosed.Compared with research before, the difference is that research center of gravity has been placed on to efficiency by they
Have an impact and on not noticeable " soft fault ".There is positive meaning to the operation and maintenance of groundwater heat pumps.
Summarizing domestic and international research achievement can see, and application of China's fault diagnosis technology in heat pump unit field is existing
Certain development and application, but still have the following problems：
Existing hybrid intelligent diagnostic research still constitutes diagnostic message using the discrete physical signal such as temperature, pressure mostly,
It is fresh to use the continuous signals such as vibration information or acoustic information less, cause the incomplete of diagnostic message.Mechanical System Trouble is normal
It often shows the multiple physical fields such as dynamics, acoustics, tribology, thermodynamics, therefore causes diagnosis to believe just with a certain physical field
What is ceased is incomplete, inevitably causes the missing inspection and erroneous judgement of failure, especially to ten early stages, faint and combined failure, fault signature
It is often all unobvious in any one physical field, only comprehensive utilization multiple physical field information be just expected to improve fault diagnosis and in advance
The precision shown.
From the point of view of the method for diagnosis, with going deep into for research and application, single failure diagnostic method has inevitable
Defect.Such as diagnostic message faced is imperfect, fuzzy membership function artificial determination, the knowledge acquisition of expert system are tired
Difficult, neural network lacks the problems such as fault sample training, limits the application of these single intellectual technologies.Therefore, a variety of diagnosis
Method, which is combined, can make knowledge representation in diagnostic system more improve and clearly, be not limited to a certain specific diagnosis side
Method, then can greatly improve diagnosis accuracy and can be existing.
Summary of the invention
The purpose of the present invention is to provide one kind can effectively diagnose and indicate complicated machinery fault mode based on
The method for diagnosing faults of multiple sensor signals analysis.
The technical solution of the invention is as follows：
A kind of method for diagnosing faults based on multiple sensor signals analysis, it is characterized in that：Include the following steps：
(1) the multiple sensor collection unit data of MCU driving are utilized, unit operating parameter includes supply water temperature, returns
Coolant-temperature gage, water tank water temperature and cistern water level, and serial communication is carried out with PC machine, PC machine is sent by data collected；
(2) vibration data is passed to computer by wireless module using wireless sensor by the acquisition of unit vibration signal
On；
(3) pressure, the temperature, stream of the heat pump unit of each sensor measurement in the process of running under different transitions are obtained
Parameter is measured, and carries out mixing operation, constitutes the feature vector under different conditions；
(4) feature vector and state that the sensing data at the multiple moment or multiple operating statuses that will acquire is constituted
Mode map is carried out, the relationship that must be out of order between sign designs and trains neural network with this to carry out failure modes,
When carrying out fault diagnosis so as to system, mode map process can be completed according to different failure symptoms；
(5) according to the feature vector dimension of data fusion, the structure of the BP neural network of genetic algorithm optimization is determined, it is complete
Relevant optimization is carried out according to the training result of neural network at the training process of neural network；
(6) initial weight and the threshold value distribution of BP neural network are optimized using genetic algorithm, by selecting, handing over
Fork and mutation operation find the best initial weights and threshold value of BP neural network；Herein using test data to the BP nerve after optimization
Network is trained, and obtains the good BP neural network fault grader of final optimization pass；
(7) for the vibration signal obtained under corresponding machine performance, after carrying out denoising relevant operation, using wavelet packet point
Analysis method carries out wavelet decomposition to vibrational waveform, obtains the reconstruct wavelet coefficient of each node and reconstruct after three layers of wavelet decomposition
Wavelet Energy Spectrum；
(8) extracted from the reconstruct wavelet coefficient of acquisition and reconstruct Wavelet Energy Spectrum the energy of each node, variance and
Wavelet coefficient data, similarly by the feature vector after these data fusions, as the vibration signal；
(9) feature reduction is carried out using feature vector of the rough set theory to vibration signal, by carrying out item to decision table
Part attribute reduction, Decision Rule Reduction obtain minimal decision-making regulation, as final classification rule；
(10) it according to the rule after Rough Set Reduction, design and training counterpropagation network, after training successfully, obtains
Take the fault mode classification device of vibration signal；
(11) enter the failure Decision fusion stage, by the feature vector of the S3 signal obtained as input, utilize step
(6) trained neural network failure classifier obtains fail result, while the feature of the vibration signal obtained by step (8)
The fault mode classification device for the vibration signal that vector is obtained using step (10) is diagnosed, and diagnostic result is obtained；Finally, will
The diagnostic result of both unlike signals carries out D-S Decision fusion, and final fusion results are diagnostic result；
(12) finally, MATLAB language is based on, using GUI design method, design error failure diagnostic signal processing platform；Skill
Art personnel can obtain current unit operating parameter by simple operations, make breakdown judge in time, and can save current
Data check historical data.
The beneficial effects of the invention are as follows：
1, it using multiple sensors acquisition heat pump unit in parameters such as the pressure, temperature, flow of operational process, and utilizes
Vibrating sensor acquires the vibration signal of unit, to grasp the equipment state of net for air-source heat pump units comprehensively with this.
2, combine Multi Intelligent Techniques method, the advantage of integrated use intellectual technology respectively is maximized favourable factors and minimized unfavourable ones, to air-source
Heat pump unit carry out status monitoring, fault diagnosis and intelligence indicate, can effectively improve monitoring diagnosis system sensibility and
Accuracy reduces misdiagnosis rate and rate of missed diagnosis.
3, signal processing platform convenient to use is had devised using GUI design method based on MATLAB language.Not
In the case where understanding system mechanism and analysis data, accurately diagnosis decision is provided for general operator.
Detailed description of the invention
Present invention will be further explained below with reference to the attached drawings and examples.
Fig. 1 is that the present invention is based on the schematic diagrames of the fault diagnosis system of the multiple sensor signals of heat pump unit analysis.
Fig. 2 is multiple sensor faults diagnosis model.
Fig. 3 is the BP neural network structure chart designed in the present invention.
Fig. 4 is Algorithm for Attribute Reduction flow diagram.
Fig. 5 is the main interface of heat pump unit fault diagnosis system.
Each label in the above figure：P1- high pressure, P2- low pressure, P3- condensation temperature, P4- evaporating temperature, P5- suction superheat
Temperature, P6- liquid supercooling temperature, P7- delivery temperature and P8- pass through the water flow temperature difference of condenser.T1- fault-free, T2- refrigeration
Agent leakage, the leakage of T3- compressor exhaust valve, T4- liquid line are obstructed, T5- condenser fouling, T6- fouling of evaporator.
Specific embodiment
It include first feature of the data fusions such as temperature, pressure at this moment by the parameter of a certain moment operation of unit
Vector, obtains multiple sensing datas of multiple moment or multiple machine performances, the relationship that must be out of order between sign,
Mode map process is completed according to different failure symptoms.In this, as the training set of BP neural network, BP nerve net is determined
Input layer number, the output layer number of nodes of network, and rule of thumb formulaDetermine node in hidden layer.It is empty
The common soft fault of air supply heat pump unit has：Leakage of refrigerant, compressor exhaust valve are revealed, liquid line is obstructed, condenser knot
Dirt and fouling of evaporator.The input sample data and target output of network are determined first.There are 8 spies for heat pump unit
Sign amount：High pressure P1, low pressure P2, condensation temperature P3, evaporating temperature P4, suction superheat temperature P5, liquid supercooling temperature P6, exhaust
Temperature P7 and water flow temperature difference P8 by condenser.The data obtained by l-G simulation test are exported as input as fault-free
T1, leakage of refrigerant T2, compressor exhaust valve reveal T3, and liquid line is obstructed T4, condenser fouling T5 and fouling of evaporator
T6.Then network structure is determined.Fault diagnosis is carried out using BP neural network.The input layer number for designing BP network is 8,
Output layer number of nodes is 6, determines that node in hidden layer is 13.The structure for determining BP neural network is 8-13-6.Its structure chart is such as
Fig. 3.
But because BP network is easily trapped into local minimum, so that desired training result be not achieved in the training process.Mind
Through network itself there are some defects and deficiency, need to optimize it.Due to genetic algorithm have ability of searching optimum and
Stronger robustness with Strengthens network training and can improve network performance, it is easier to find globally optimal solution.Therefore, something lost is utilized
Propagation algorithm carrys out the initial value and threshold value of Optimized BP Neural Network.The initial connection weight and threshold of each layer before BP neural network training
The random value being worth between [0,1], this random value being not optimised can make the convergence rate of BP neural network slack-off, and be easy
Make final result non-optimal solution.The basic thought of genetic algorithm optimization BP neural network is：Using genetic algorithm to BP nerve
Initial weight and the threshold value distribution of network optimize, and find BP neural network most by selection, intersection and mutation operation
Excellent weight and threshold value.It is trained BP neural network using new weight and threshold value, preferable training result can be obtained.
Meanwhile the vibration signal under above-mentioned multiple machine performances being handled.In heat pump unit fault-free T1, failure
Under T2~T6 mode using vibrating sensor carry out vibration signal acquisition, using wavelet packet analysis algorithm to vibration signal into
Row decomposes, and extracts the feature vector of each waveform.WAVELET PACKET DECOMPOSITION follows principle of conservation of energy, and the signal of each frequency band is with regard to generation
Table information of the original signal in the frequency band.Small echo is surrounded by higher resolution ratio, after realizing that deep layer is decomposed to signal, asks
The energy value for taking special frequency band constitutes diagnostic characteristic vector using the characteristic value acquired.The WAVELET PACKET DECOMPOSITION of signal can be used more
Kind wavelet packet basis is realized, can seek an Optimum Wavelet Packet by cost cost function.The feature of signal can use small echo
Packet coefficient embodies, and the size of coefficient can characterize the information in the wavelet packet basis to the contribution of signal.Here it uses
The closely related standard of Shannon seeks Optimum Wavelet Packet as cost cost function.
There may be the redundancy features of a part in the primitive character that WAVELET PACKET DECOMPOSITION is extracted, and redundancy feature can make
Later period failure modes are increasingly complex, and on nicety of grading, there is also influences.Therefore, it is necessary to the feature of extraction carry out reduction and
Selection chooses input of the sensitive features as classifier in the case where not losing fault message.Reduction is to utilize rough set
Theory obtains minimal decision-making regulation, as final point by carrying out reduction of condition attributes, Decision Rule Reduction to decision table
Rule-like.Algorithm for Attribute Reduction flow diagram such as Fig. 4.By feature vector and the corresponding failure mould after these reduction
Training set of the formula as classifier, determines classifier structure.
Into the failure Decision fusion stage, using Dempster-Shafer (abbreviation D-S) evidence theory fusion algorithm into
Row fusion.The core concept of decision level fusion is that each sensor makes local decisions according to respective observed result, then will
Court verdict is transmitted to fusion center via communication channel, then carries out integrated treatment to each local decisions by fusion center, makes
Conclusive judgement.Assuming that two groups of evidence E under framework of identification Ω1And E2, corresponding basic trust partition function is respectively m1And m2,
Burnt member is respectively AiAnd Bj, D-S composition rule is：
Several independent evidences can be combined using D-S composition rule.Compared with singleton independent process, information
The confidence level of the result of decision can be improved in fusion, while reducing reasoning fog-level, improves detection accuracy, improves spatial discrimination
Rate, and system survivability and adaptivity can be enhanced, to improve system-wide performance.Finally fusion results are
Diagnostic result.
Finally, MATLAB language is based on, using GUI design method, design error failure diagnostic signal processing platform.Technology people
Member can obtain current unit operating parameter by simple operations, make breakdown judge in time, and can save current data,
Check historical data.Its main interface such as Fig. 5.
The present invention is being run using certain net for air-source heat pump units as research object using multiple sensors acquisition heat pump unit
The parameters such as pressure, temperature, the flow of process, and using the vibration signal of vibrating sensor acquisition unit, it is grasped comprehensively with this
The equipment state of net for air-source heat pump units.On this basis, combine Multi Intelligent Techniques method, to net for air-source heat pump units into
Row status monitoring, fault diagnosis and intelligence indicate.Meanwhile it being had devised based on MATLAB language using GUI design method
Signal processing platform convenient to use.
Based on the method for diagnosing faults of multiple sensor signals analysis, include the following steps：
(1) the multiple sensor collection unit data of MCU driving are utilized, unit operating parameter includes supply water temperature, returns
Coolant-temperature gage, water tank water temperature and cistern water level etc., and serial communication is carried out with PC machine, PC machine is sent by data collected.
(2) acquisition of unit vibration signal, can use wireless sensor, and power consumption is small.By wireless module by vibration number
According to passing on computer.
(S)：Obtain pressure, the temperature, stream of the heat pump unit of each sensor measurement in the process of running under different transitions
The parameters such as amount, and mixing operation is carried out, constitute the feature vector under different conditions.
(4) feature vector and state that the sensing data at the multiple moment or multiple operating statuses that will acquire is constituted
Mode map is carried out, the relationship that must be out of order between sign designs and trains neural network with this to carry out failure modes,
When carrying out fault diagnosis so as to system, mode map process can be completed according to different failure symptoms.
(5) according to the feature vector dimension of data fusion, the structure of the BP neural network of genetic algorithm optimization is determined, it is complete
At the training process of neural network.But because BP network is easily trapped into local minimum, to be not achieved in the training process desired
Training result.Therefore, according to the training result of neural network, relevant optimization is carried out.
(6) initial weight and the threshold value distribution of BP neural network are optimized using genetic algorithm, by selecting, handing over
Fork and mutation operation find the best initial weights and threshold value of BP neural network.Herein using test data to the BP nerve after optimization
Network is trained.Obtain the good BP neural network fault grader of final optimization pass.
(7) it for the vibration signal obtained under corresponding machine performance, carries out after the relevant operation such as denoising, using wavelet packet
Analysis method carries out wavelet decomposition to vibrational waveform, obtain after three layers of wavelet decomposition the reconstruct wavelet coefficient of each node with again
Structure Wavelet Energy Spectrum.
(8) extracted from the reconstruct wavelet coefficient of acquisition and reconstruct Wavelet Energy Spectrum the energy of each node, variance and
The data such as wavelet coefficient, similarly by the feature vector after these data fusions, as the vibration signal.
(9) there may be the redundancy features of a part in the primitive character that WAVELET PACKET DECOMPOSITION is extracted, and redundancy feature can make
Later period failure modes are increasingly complex, therefore, it is necessary to carry out reduction and selection to the feature of extraction.Rough set can be used
Theory carries out feature reduction to the feature vector of vibration signal, by carrying out reduction of condition attributes, decision rule about to decision table
Letter obtains minimal decision-making regulation, as final classification rule.
(10) according to the rule after Rough Set Reduction, design and training counterpropagation network, after training successfully.It obtains
Take the fault mode classification device of vibration signal.
(11) enter the failure Decision fusion stage, by the feature vector of the S3 signal obtained as input, utilize S6 training
Good neural network failure classifier obtains fail result, while utilizing step by the feature vector of the S8 vibration signal obtained
(10) the fault mode classification device of the vibration signal obtained is diagnosed, and obtains diagnostic result.Finally, both differences are believed
Number diagnostic result carry out D-S Decision fusion, final fusion results are diagnostic result.
(12) finally, MATLAB language is based on, using GUI design method, design error failure diagnostic signal processing platform.Skill
Art personnel can obtain current unit operating parameter by simple operations, make breakdown judge in time, and can save current
Data check historical data, and the fault diagnosis for after provides more reliable failure symptom information, can be more quick, accurate
Anticipation unit machine performance.
Those of ordinary skill in the art it should be appreciated that more than embodiment be intended merely to illustrate the present invention
Technical solution, and be not used as limitation of the invention, it is any that the above is implemented based on connotation of the invention
Variation, modification, will all fall in scope of protection of the claims of the invention made by example.
Claims (1)
1. a kind of provide the method for diagnosing faults based on multiple sensor signals analysis of Accurate Diagnosis decision, it is characterized in that：
Include the following steps：
(1) the multiple sensor collection unit data of MCU driving are utilized, unit operating parameter includes supply water temperature, return water temperature
Degree, water tank water temperature and cistern water level, and serial communication is carried out with PC machine, PC machine is sent by data collected；
(2) acquisition of unit vibration signal is passed to vibration data on computer by wireless module using wireless sensor；
(3) pressure, the temperature, flow ginseng of the heat pump unit of each sensor measurement in the process of running under different transitions are obtained
Number, and mixing operation is carried out, constitute the feature vector under different conditions；
(4) feature vector and state that the sensing data at the multiple moment or multiple operating statuses that will acquire is constituted carry out mould
Formula mapping, the relationship that must be out of order between sign design with this and train neural network to carry out failure modes, so as to system
When carrying out fault diagnosis, mode map process can be completed according to different failure symptoms；
(5) it according to the feature vector dimension of data fusion, determines the structure of the BP neural network of genetic algorithm optimization, completes nerve
The training process of network carries out relevant optimization according to the training result of neural network；
(6) initial weight and the threshold value distribution of BP neural network are optimized using genetic algorithm, passes through selection, intersection and change
ETTHER-OR operation finds the best initial weights and threshold value of BP neural network；The BP neural network after optimization is carried out using test data herein
Training obtains the good BP neural network fault grader of final optimization pass；
(7) for the vibration signal obtained under corresponding machine performance, after carrying out denoising relevant operation, using analysis method of wavelet packet
Wavelet decomposition is carried out to vibrational waveform, obtains the reconstruct wavelet coefficient and reconstruct wavelet energy of each node after three layers of wavelet decomposition
Spectrum；
(8) energy, variance and the small echo of each node are extracted from the reconstruct wavelet coefficient of acquisition and reconstruct Wavelet Energy Spectrum
Coefficient data, similarly by the feature vector after these data fusions, as the vibration signal；
(9) feature reduction is carried out using feature vector of the rough set theory to vibration signal, by carrying out condition category to decision table
Property reduction, Decision Rule Reduction, obtain minimal decision-making regulation, as final classification rule；
(10) according to the rule after Rough Set Reduction, design and training counterpropagation network, after training successfully, vibration is obtained
The fault mode classification device of signal；
(11) enter the failure Decision fusion stage, by the feature vector of the S3 signal obtained as input, utilize step (6) training
Good neural network failure classifier obtains fail result, while the feature vector of the vibration signal obtained by step (8) utilizes
The fault mode classification device for the vibration signal that step (10) obtains is diagnosed, and diagnostic result is obtained；Finally, by both differences
The diagnostic result of signal carries out D-S Decision fusion, and final fusion results are diagnostic result；
(12) finally, MATLAB language is based on, using GUI design method, design error failure diagnostic signal processing platform；Technical staff
Current unit operating parameter can be obtained by simple operations, make breakdown judge in time, and current data can be saved, look into
See historical data；
Wherein step (1)-(5) the specific steps are：
It include first feature vector of the data fusions such as temperature, pressure at this moment by the parameter of a certain moment operation of unit,
Obtain multiple sensing datas of multiple moment or multiple machine performances, the relationship that must be out of order between sign, according to not
With failure symptom complete mode map process；In this, as the training set of BP neural network, the defeated of BP neural network is determined
Enter node layer number, output layer number of nodes, and rule of thumb formulaDetermine node in hidden layer；Air source heat pump
The common soft fault of unit has：Leakage of refrigerant, compressor exhaust valve leakage, liquid line be obstructed, condenser fouling and evaporation
Device fouling；The input sample data and target output of network are determined first；There are 8 characteristic quantities for heat pump unit：High pressure
P1, low pressure P2, condensation temperature P3, evaporating temperature P4, suction superheat temperature P5, liquid supercooling temperature P6, delivery temperature P7 and logical
Cross the water flow temperature difference P8 of condenser；The data obtained by l-G simulation test are exported as input as fault-free T1, leakage of refrigerant
T2, compressor exhaust valve reveal T3, and liquid line is obstructed T4, condenser fouling T5 and fouling of evaporator T6；Then network is determined
Structure carries out fault diagnosis using BP neural network, and the input layer number of design BP network is 8, and output layer number of nodes is 6,
It determines that node in hidden layer is 13, determines that the structure of BP neural network is 8-13-6；
Step (11) the specific steps are：
Into the failure Decision fusion stage, merged using Dempster-Shafer evidence theory fusion algorithm；Decision level is melted
The core concept of conjunction is：Each sensor makes local decisions according to respective observed result, then by court verdict via communication
Channel is transmitted to fusion center, then carries out integrated treatment to each local decisions by fusion center, makes conclusive judgement；Assuming that identification
Two groups of evidence E under frame Ω1And E2, corresponding basic trust partition function is respectively m1And m2, burnt member is respectively AiAnd Bj, D-S
Composition rule is：
Several independent evidences can be combined using D-S composition rule；Final fusion results are diagnostic result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810498072.1A CN108931387B (en) | 2015-11-30 | 2015-11-30 | Fault diagnosis method based on multi-sensor signal analysis and capable of providing accurate diagnosis decision |
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810498072.1A CN108931387B (en) | 2015-11-30 | 2015-11-30 | Fault diagnosis method based on multi-sensor signal analysis and capable of providing accurate diagnosis decision |
| CN201510846925.2A CN105372087B (en) | 2015-11-30 | 2015-11-30 | Method for diagnosing faults based on multiple sensor signals analysis |
Related Parent Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510846925.2A Division CN105372087B (en) | 2015-11-30 | 2015-11-30 | Method for diagnosing faults based on multiple sensor signals analysis |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108931387A true CN108931387A (en) | 2018-12-04 |
| CN108931387B CN108931387B (en) | 2020-05-12 |
Family
ID=55374485
Family Applications (2)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510846925.2A Active CN105372087B (en) | 2015-11-30 | 2015-11-30 | Method for diagnosing faults based on multiple sensor signals analysis |
| CN201810498072.1A Active CN108931387B (en) | 2015-11-30 | 2015-11-30 | Fault diagnosis method based on multi-sensor signal analysis and capable of providing accurate diagnosis decision |
Family Applications Before (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510846925.2A Active CN105372087B (en) | 2015-11-30 | 2015-11-30 | Method for diagnosing faults based on multiple sensor signals analysis |
Country Status (1)
| Country | Link |
|---|---|
| CN (2) | CN105372087B (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110108509A (en) * | 2019-04-28 | 2019-08-09 | 西安建筑科技大学 | A kind of sewage source heat pump unit intelligent failure diagnosis method |
| CN110110424A (en) * | 2019-04-29 | 2019-08-09 | 西南石油大学 | A kind of compressor adaptive performance curve generation method |
| CN110135081A (en) * | 2019-05-20 | 2019-08-16 | 哈尔滨工程大学 | A kind of internal combustion engine tribology Expert System Design method based on artificial intelligence |
| CN111297178A (en) * | 2020-04-17 | 2020-06-19 | 青岛海尔智慧厨房电器有限公司 | Steam box and control method thereof |
| CN112894882A (en) * | 2020-12-30 | 2021-06-04 | 哈尔滨工业大学芜湖机器人产业技术研究院 | Robot fault detection system based on industrial internet |
| CN115374881A (en) * | 2022-10-17 | 2022-11-22 | 图林科技(深圳)有限公司 | Fault diagnosis method for running state of refrigeration equipment |
| CN115421073A (en) * | 2022-08-29 | 2022-12-02 | 吉林大学 | Method for identifying pseudo evidence of normalized curve |
| CN117780679A (en) * | 2024-02-26 | 2024-03-29 | 无锡精恩风机有限公司 | Centrifugal fan fault diagnosis method and online monitoring system |
| CN117780679B (en) * | 2024-02-26 | 2024-05-03 | 无锡精恩风机有限公司 | Centrifugal fan fault diagnosis method and online monitoring system |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105915891B9 (en) * | 2016-05-06 | 2018-08-24 | 哈尔滨工程大学 | A kind of imaging sensor key parameter test method based on details in a play not acted out on stage, but told through dialogues variance signal |
| CN106369834A (en) * | 2016-09-02 | 2017-02-01 | 南通大学 | Directly-heated type heat pump system constant-temperature flow control method based on neural network |
| CN106482938B (en) * | 2016-10-14 | 2018-08-03 | 温州大学 | Brake fluid system multi-source fusion failure predicting method based on GA-BP networks |
| CN107606739B (en) * | 2017-08-15 | 2019-07-26 | 清华大学 | The fault detection method of heating ventilation air-conditioning system |
| CN107730000A (en) * | 2017-09-15 | 2018-02-23 | 珠海格力电器股份有限公司 | Coolant leakage detection method and device for air-conditioning |
| CN107830997A (en) * | 2017-10-25 | 2018-03-23 | 华北电力大学（保定） | Equipment fault diagnosis method based on industrial wireless sensor network and wavelet transformation |
| WO2019166397A1 (en) | 2018-02-28 | 2019-09-06 | Robert Bosch Gmbh | Intelligent audio analytic apparatus (iaaa) and method for space system |
| CN108958221A (en) * | 2018-07-12 | 2018-12-07 | 华北电力大学（保定） | Equipment fault diagnosis method based on industrial Internet of Things Yu support vector machines multi-classification algorithm |
| CN109297077B (en) * | 2018-09-03 | 2020-04-21 | 西安石油大学 | Method for monitoring step utilization system of middle-deep layer non-interference ground rock heat supply system |
| CN109764476B (en) * | 2018-12-18 | 2020-09-04 | 珠海格力电器股份有限公司 | Refrigerant leakage monitoring method and system and air conditioning unit |
| CN109858352B (en) * | 2018-12-26 | 2020-09-18 | 华中科技大学 | Fault diagnosis method based on compressed sensing and improved multi-scale network |
| CN110008914A (en) * | 2019-04-11 | 2019-07-12 | 杨勇 | A kind of pattern recognition system neural network based and recognition methods |
| CN110210459A (en) * | 2019-06-24 | 2019-09-06 | 北京航空航天大学 | A kind of prediction technique and prediction meanss of engine valve clearance |
| CN111307453B (en) * | 2020-03-20 | 2021-11-12 | 朗斯顿科技(北京)有限公司 | Transmission system fault diagnosis method based on multi-information fusion |
| CN111967486A (en) * | 2020-06-02 | 2020-11-20 | 安徽三禾一信息科技有限公司 | Complex equipment fault diagnosis method based on multi-sensor fusion |
| CN112598019B (en) * | 2020-10-28 | 2024-04-02 | 南京航空航天大学 | Heterogeneous vibration signal space-time multi-cross-correlation analysis and self-adaptive weighted fusion method |
| CN112733692B (en) * | 2021-01-04 | 2021-11-30 | 润联智慧科技(西安)有限公司 | Fault prediction method and device based on integrated hybrid model and related equipment |
| CN112748317B (en) * | 2021-03-23 | 2022-03-25 | 国网河南省电力公司电力科学研究院 | Switch cabinet partial discharge fault detection method and system based on multiple monitoring data |
| CN113359623B (en) * | 2021-05-08 | 2022-08-23 | 深圳有象智联科技有限公司 | Method and device for monitoring working state and computer readable storage medium |
| CN113188235A (en) * | 2021-05-28 | 2021-07-30 | 西安建筑科技大学 | Multi-source fault diagnosis method, system and equipment for sensor in air conditioning system |
| CN113640027A (en) * | 2021-08-12 | 2021-11-12 | 常州英集动力科技有限公司 | Heat exchange unit fault diagnosis method and system based on edge calculation and neural network |
| CN114882680A (en) * | 2022-04-19 | 2022-08-09 | 深圳闪回科技有限公司 | Remote terminal management system and method |
| CN116538092B (en) * | 2023-07-06 | 2023-11-14 | 中国科学院理化技术研究所 | Compressor on-line monitoring and diagnosing method, device, equipment and storage medium |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101867486A (en) * | 2010-06-08 | 2010-10-20 | 江苏大学 | Wireless sensor network fault diagnosis method |
| CN102736562A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Knowledge base construction method oriented to fault diagnosis and fault prediction of numerical control machine tool |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN104330255A (en) * | 2014-11-04 | 2015-02-04 | 徐州隆安光电科技有限公司 | Gear fault diagnosing method based on multi-sensor information fusion |
| EP2869153A1 (en) * | 2013-11-01 | 2015-05-06 | Hitachi Power Solutions Co., Ltd. | Health management system, fault diagnosis system, health management method, and fault diagnosis method |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1166922C (en) * | 2002-07-18 | 2004-09-15 | 上海交通大学 | Multiple-sensor and multiple-object information fusing method |
| CN102944416B (en) * | 2012-12-06 | 2015-04-01 | 南京匹瑞电气科技有限公司 | Multi-sensor signal fusion technology-based fault diagnosis method for wind turbine blades |
| CN104503235B (en) * | 2014-12-09 | 2017-05-10 | 中国石油大学(华东) | Condition monitoring method based on improved BP neural network for power plant equipment |
| CN104636493A (en) * | 2015-03-04 | 2015-05-20 | 浪潮电子信息产业股份有限公司 | Method for classifying dynamic data on basis of multi-classifier fusion |
| CN104833534A (en) * | 2015-04-21 | 2015-08-12 | 广州市地下铁道总公司 | Train running fault diagnosis device based on multi-source information fusion, and method |
| CN104834828A (en) * | 2015-05-26 | 2015-08-12 | 重庆大学 | Method for diagnosing physiological abnormality of old people based on DS evidence theory-neural network algorithm |
| CN104866904B (en) * | 2015-06-16 | 2019-01-01 | 中电科软件信息服务有限公司 | A kind of BP neural network parallel method of the genetic algorithm optimization based on spark |
-
2015
- 2015-11-30 CN CN201510846925.2A patent/CN105372087B/en active Active
- 2015-11-30 CN CN201810498072.1A patent/CN108931387B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101867486A (en) * | 2010-06-08 | 2010-10-20 | 江苏大学 | Wireless sensor network fault diagnosis method |
| CN102736562A (en) * | 2012-07-10 | 2012-10-17 | 北京信息科技大学 | Knowledge base construction method oriented to fault diagnosis and fault prediction of numerical control machine tool |
| EP2869153A1 (en) * | 2013-11-01 | 2015-05-06 | Hitachi Power Solutions Co., Ltd. | Health management system, fault diagnosis system, health management method, and fault diagnosis method |
| CN103971162A (en) * | 2014-04-04 | 2014-08-06 | 华南理工大学 | Method for improving BP (back propagation) neutral network and based on genetic algorithm |
| CN103900816A (en) * | 2014-04-14 | 2014-07-02 | 上海电机学院 | Method for diagnosing bearing breakdown of wind generating set |
| CN104330255A (en) * | 2014-11-04 | 2015-02-04 | 徐州隆安光电科技有限公司 | Gear fault diagnosing method based on multi-sensor information fusion |
Non-Patent Citations (1)
| Title |
|---|
| 姜益强、姚杨、马最良: "基于神经网络的空气源热泵机组的故障诊断", 《哈尔滨工业大学学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110108509A (en) * | 2019-04-28 | 2019-08-09 | 西安建筑科技大学 | A kind of sewage source heat pump unit intelligent failure diagnosis method |
| CN110110424A (en) * | 2019-04-29 | 2019-08-09 | 西南石油大学 | A kind of compressor adaptive performance curve generation method |
| CN110135081A (en) * | 2019-05-20 | 2019-08-16 | 哈尔滨工程大学 | A kind of internal combustion engine tribology Expert System Design method based on artificial intelligence |
| CN111297178A (en) * | 2020-04-17 | 2020-06-19 | 青岛海尔智慧厨房电器有限公司 | Steam box and control method thereof |
| CN111297178B (en) * | 2020-04-17 | 2022-03-29 | 青岛海尔智慧厨房电器有限公司 | Steam box and control method thereof |
| CN112894882A (en) * | 2020-12-30 | 2021-06-04 | 哈尔滨工业大学芜湖机器人产业技术研究院 | Robot fault detection system based on industrial internet |
| CN115421073A (en) * | 2022-08-29 | 2022-12-02 | 吉林大学 | Method for identifying pseudo evidence of normalized curve |
| CN115374881A (en) * | 2022-10-17 | 2022-11-22 | 图林科技(深圳)有限公司 | Fault diagnosis method for running state of refrigeration equipment |
| CN117780679A (en) * | 2024-02-26 | 2024-03-29 | 无锡精恩风机有限公司 | Centrifugal fan fault diagnosis method and online monitoring system |
| CN117780679B (en) * | 2024-02-26 | 2024-05-03 | 无锡精恩风机有限公司 | Centrifugal fan fault diagnosis method and online monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105372087A (en) | 2016-03-02 |
| CN105372087B (en) | 2018-06-22 |
| CN108931387B (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108931387A (en) | The method for diagnosing faults based on multiple sensor signals analysis of Accurate Diagnosis decision is provided | |
| CN104712542B (en) | A kind of reciprocating compressor sensitive features based on Internet of Things are extracted and method for diagnosing faults | |
| CN109655259A (en) | Combined failure diagnostic method and device based on depth decoupling convolutional neural networks | |
| Cao et al. | The fault diagnosis of a switch machine based on deep random forest fusion | |
| CN102520697B (en) | Onsite information preprocessing method of remote cooperative diagnosis | |
| CN106338406A (en) | On-line monitoring and fault early-warning system and method for traction electric transmission system of train | |
| CN101819411B (en) | GPU-based equipment fault early-warning and diagnosis method for improving weighted association rules | |
| CN107884475A (en) | A kind of city gas pipeline method for diagnosing faults based on deep learning neutral net | |
| CN109299705A (en) | Rotary machinery fault diagnosis method based on one-dimensional depth residual error convolutional neural networks | |
| CN110414383A (en) | Convolutional neural networks based on Wasserstein distance fight transfer learning method and its application | |
| CN110242865B (en) | Gas leakage detection and judgment method and system easy for continuous optimization | |
| CN105930629B (en) | A kind of on-line fault diagnosis method based on magnanimity service data | |
| CN103091112A (en) | Method and device of car emission fault detection and diagnosis based on fuzzy reasoning and self-learning | |
| CN203083829U (en) | Automobile fault diagnosis system based on tail gas discharge detection adopting simple driving mode | |
| CN115187832A (en) | Energy system fault diagnosis method based on deep learning and gram angular field image | |
| Chen et al. | Deep attention relation network: A zero-shot learning method for bearing fault diagnosis under unknown domains | |
| CN107101829A (en) | A kind of intelligent diagnosing method of aero-engine structure class failure | |
| Zhang et al. | Imbalanced data based fault diagnosis of the chiller via integrating a new resampling technique with an improved ensemble extreme learning machine | |
| CN106706314A (en) | Automobile automatic transmission fault diagnosis tester based on virtual instrument and automobile automatic transmission fault diagnosis method based on virtual instrument | |
| CN109389325A (en) | Transformer substation electronic transducer state evaluating method based on wavelet neural network | |
| CN116894187A (en) | Gear box fault diagnosis method based on deep migration learning | |
| CN101539137B (en) | Residual life gray prediction method of aerospace hydraulic pump based on delta filter | |
| CN107169658A (en) | The method for diagnosing faults of hydrometallurgy concentrator based on confidence level | |
| CN109870306A (en) | A kind of tractor engine Fault diagnosis and forecast method | |
| CN109409541A (en) | The method for realizing abandoned car battery reverse logistic feasibility assessment |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210616 Address after: 226019 No.205, building 6, Nantong University, No.9, Siyuan Road, Nantong City, Jiangsu Province Patentee after: Center for technology transfer, Nantong University Address before: 226019 Jiangsu city of Nantong province sik Road No. 9 Patentee before: NANTONG University |
|
| TR01 | Transfer of patent right | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20181204 Assignee: Nantong Zhijia Intelligent Equipment Co.,Ltd. Assignor: Center for technology transfer, Nantong University Contract record no.: X2022320000355 Denomination of invention: Fault diagnosis method based on multi-sensor signal analysis to provide accurate diagnosis decision Granted publication date: 20200512 License type: Common License Record date: 20221210 |
|
| EE01 | Entry into force of recordation of patent licensing contract |