CN104503434B - Fault diagnosis method based on active fault symptom pushing - Google Patents
Fault diagnosis method based on active fault symptom pushing Download PDFInfo
- Publication number
- CN104503434B CN104503434B CN201410720508.9A CN201410720508A CN104503434B CN 104503434 B CN104503434 B CN 104503434B CN 201410720508 A CN201410720508 A CN 201410720508A CN 104503434 B CN104503434 B CN 104503434B
- Authority
- CN
- China
- Prior art keywords
- parameter
- fault
- symbol
- symptom
- failure symptom
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
- G05B23/00—Testing or monitoring of control systems or parts thereof
- G05B23/02—Electric testing or monitoring
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Test And Diagnosis Of Digital Computers (AREA)
Abstract
The invention provides a fault diagnosis method based on active fault symptom pushing, comprising the following steps: symbols of all fault mode parameter representation forms are generated; a system fault symptom set is obtained; a system parameter is acquired, and the symbol of the representation form of the acquired parameter is generated; whether the generated symbol is matched with the symbol corresponding to at least one fault symptom in the fault symptom set is judged, the corresponding fault symptom is output and the method ends if the generated symbol is matched with the symbol corresponding to at least one fault symptom in the fault symptom set, or a fault symptom is determined based on the generated symbol; and the method goes to a step of active fault symptom pushing, a fault symptom already existing shows that an original knowledge base has a fault symptom fully consistent with the newly-emerging fault symptom, and the original knowledge base is not treated under the situation, and if a fault symptom is completely new, the corresponding relationship between the determined fault symptom and the generated symbol is added to the fault symptom set. The fault diagnosis method is based on active pushing instead of passive identification, so that complicated information search is reduced, and quick and correct fault diagnosis is realized.
Description
Technical field
The present invention relates to a kind of method for diagnosing faults based on failure symptom active push, it is adaptable to which complication system failure is certainly
Diagnosis and state belong to fault diagnosis technology field from confirming.
Background technology
Due in large scale, complex structure, part category is more, influence factor is more the characteristics of so that the failure of complication system
Probability of happening is larger, and without fault self-diagnosis function, it is impossible to whether the working condition for understanding system is normal, once system is sent out
Raw failure, it is impossible to which real-time detection is to mistake.Existing diagnosis method for system fault, mostly using the method based on Mathematical Modeling,
This Method Modeling is complicated, computationally intensive, and for complicated nonlinear system, it is impossible to set up for the accurate of fault diagnosis
Dynamic mathematical models.
For the fault diagnosis system of complication system, the initial stage is all according to expertise and historical data analysis result
Set up knowledge base.Due to some non-intellectuals and the uncertainty of emergency case of system factor, set up knowledge base is made unavoidably
There are some incompleteness, this is accomplished by after new barrier pattern occurs, and existing knowledge storehouse is updated, the new failure of supplement
Pattern knowledge.Because fault diagnosis relatively depends on the knowledge base of fault mode, so the pattern knowledge for newly increasing can be to existing
Knowledge base causes to compare large effect.
In the face of new in conventional fault diagnosis method (such as pivot analysis, artificial neural network or SVMs method)
Fault mode when, new fault mode knowledge and original training set are generally constituted new training set by people, are trained and are included
The new diagnostic rule of new fault mode.As new fault mode increases, training data is more and more, occurs new model every time all
Recalculated, diagnostic system adaptability is very poor, needed the limitation for overcoming traditional fault diagnosis.
The content of the invention
In view of this, ask the invention aims to solve complication system and can not carry out self diagnosis to oneself state
Topic, and when breaking down, it is impossible to the problem of failure judgement type, and introduce failure symptom active push link and update failure mould
Formula knowledge, proposes a kind of method for diagnosing faults based on failure symptom active push, accelerates diagnostic reasoning speed and correctness.
Realization the technical scheme is that：
A kind of method for diagnosing faults based on failure symptom active push, detailed process is：
Step one, for the system of required diagnosis, all fault mode parameter representations are carried out into symbol generation；
Step 2, the corresponding relation for setting up each failure symptom and fault mode parameter, obtain system failure symptom set；
Step 3, acquisition system parameter, and the parameter representation for being gathered is carried out into symbol generation；
Step 4, judge in step 3 generate symbol whether match failure symptom concentrate at least one failure symptom correspondence
Symbol, if so, then will terminate the method after corresponding failure symptom output, otherwise, based on the symbol generated in step 3
Determine failure symptom, step 5 is entered after output；
Step 5, into failure symptom active push link, for already present failure symptom, show original knowledge stock
With the on all four situation of emerging failure symptom, this situation do not do any process to original knowledge storehouse；For completely new
Failure symptom, by the failure symptom and step 3 of determination generate symbol corresponding relation be added to failure symptom concentrate,
Terminate the method.
Further, symbol of the present invention is generated as：Parameter attribute is defined as into four classes：
Firstth, whether threshold range is exceeded,
| Parameter value | Normally | Higher than threshold value | Less than threshold value | Unusual fluctuations |
| Symbolic representation | A1 | A2 | A3 | A4 |
Secondth, Parameter Variation,
3rd, parameter zero-bit characteristic variable,
| Parameter zero-bit | It is not classified as zero-bit | It is classified as zero-bit |
| Symbolic representation | C1 | C2 |
4th, whether there is sensor fault,
| Sensor fault | There is no sensor fault feature | With sensor fault feature |
| Symbolic representation | D1 | D2 |
For each parameter, symbol generation is carried out according to above-mentioned four attribute.
Further, the present invention represents parameter attribute symbol using binary value：
Firstth, whether threshold range is exceeded,
| Parameter value | Normally | Higher than threshold value | Less than threshold value | Unusual fluctuations |
| Binary system is characterized | 00 | 01 | 10 | 11 |
Secondth, Parameter Variation,
3rd, parameter zero-bit characteristic variable,
| Parameter zero-bit | It is not classified as zero-bit | It is classified as zero-bit |
| Binary system is characterized | 0 | 1 |
4th, whether there is sensor fault,
| Sensor fault | There is no sensor fault feature | With sensor fault feature |
| Binary system is characterized | 0 | 1 |
Beneficial effect：
First, method for diagnosing faults of the present invention based on failure symptom active push, by the detection parameter to symbolism
Matched, active push is changed to by passive discerning, reduced numerous and diverse information search work, realized the quick, correct of failure
Diagnosis.
Second, the present invention characterizes the measuring point parametic fault pattern of complication system by many bits, and information is clear, only
The sign of a large amount of fault characteristic informations is capable of achieving with less memory space, and is easy to retrieval, improve failure symptom feature
Information Store and the efficiency of identification.
Description of the drawings
Fig. 1 is the flow chart of method for diagnosing faults of the present invention；
Inference machine schematic diagrames of the Fig. 2 based on failure symptom active push；
The corresponding relation of Fig. 3 parameters and its attribute and sign.
Specific embodiment
With reference to the accompanying drawings and detailed description the present invention is described in detail.
As shown in figure 1, a kind of method for diagnosing faults based on failure symptom active push of the present invention, detailed process is：
Step one, for the system of required diagnosis, all fault mode parameter representations are carried out into symbol generation；
Step 2, the corresponding relation for setting up each failure symptom and fault mode parameter, obtain system failure symptom set；
Step 3, acquisition system parameter, and the parameter representation for being gathered is carried out into symbol generation；
Step 4, judge in step 3 generate symbol whether match failure symptom concentrate at least one failure symptom correspondence
Symbol, if so, then will terminate the method after corresponding failure symptom output, otherwise, based on the symbol generated in step 3
Determine that failure symptom (can adopt pivot analysis, artificial neural network or supporting vector as determined using the method for classical reasoning
The concrete grammars such as machine), step 5 is entered after output；
Step 5, into failure symptom active push link, for already present failure symptom, show original knowledge stock
With the on all four situation of emerging failure symptom, this situation do not do any process to original knowledge storehouse；For completely new
Failure symptom, the corresponding relation of symbol generated in the failure symptom and step 3 of determination is added in fault knowledge storehouse more
Newly.
The present invention, can not be actively for existing method based on the method for diagnosing faults based on failure symptom active push
Failure symptom characteristic information is passed to into the shortcoming of policymaker, it is proposed that with the failure symptom active push side of data flow driven
Formula.By the structure and operation principle of analysis complication system comprehensively, failure mode analysis (FMA) is carried out to system, by every kind of fault mode
Standard symbol is carried out, the failure symptom collection of system is set up.According to the analysis and description of the systematic parameter feature to gathering, general
The failure symptom matched somebody with somebody timely and accurately is delivered in policymaker's hand, reduces various numerous and diverse search works, realize failure it is quick,
Correct diagnosis.Simultaneously the present invention is preserved the fault diagnosis result not appeared on symptom set, then using it to failure
Symptom set is updated, if occurring identical failure symptom after this, immediately diagnostic result is pushed to into user, and its process is such as
Shown in Fig. 2.
Symbol of the present invention is generated as：Parameter attribute is defined as into four classes：
Firstth, whether threshold range is exceeded,
| Parameter value | Normally | Higher than threshold value | Less than threshold value | Abnormal (fluctuation) |
| Symbolic representation | A1 | A2 | A3 | A4 |
Secondth, Parameter Variation,
3rd, parameter zero-bit characteristic variable,
| Parameter zero-bit | It is not classified as zero-bit | It is classified as zero-bit |
| Symbolic representation | C1 | C2 |
4th, whether there is sensor fault,
| Sensor fault | There is no sensor fault feature | With sensor fault feature |
| Symbolic representation | D1 | D2 |
For each parameter, symbol generation is carried out according to above-mentioned four attribute.
For example, when collecting the parameter of sensor higher than threshold value, and for the form of Spline smoothing, while not to be classified as zero-bit
State, then the representation after its symbolism be A2B3C1D2.
The present invention carries out symbolism, each failure by the fault mode parameter that may be present to required diagnostic system
Mode parameter one symbol of unique correspondence；The corresponding relation of each failure symptom and fault mode parameter is then set up, is
System failure symptom collection.
For example, when there is filter clog fault sign, the fault mode corresponding to it is pressure and flow parameter
Decline suddenly, thus the fault mode that pressure and flow parameter are declined suddenly respectively symbol turns to corresponding symbol and represents shape
Formula；Concentrate in failure symptom, the symbol that the corresponding pressure of filter clog fault and flow parameter decline suddenly is represented.Due to every
One failure symptom is prior art with the corresponding relation of fault mode parameter, therefore here is not enumerated.
Complication system in the present invention, in the course of the work, by sensor or Network Capture system measuring point parameter, utilizes
Above-mentioned four attributes for being given are analyzed, and realize the symbolism of measuring point parameter.If the measuring point parameter after symbolism is and failure
The corresponding fault mode match parameters of at least one failure million in symptom set, then it represents that system has this failure, if not existing
Situation about matching, then it represents that the failure that system occurs does not represent in symptom set, now needs to be analyzed parameter, again
Determine failure symptom, then update failure symptom collection using the failure symptom for determining；Therefore the present invention is judging out of order
Simultaneously, moreover it is possible to the constantly improve to symptom set is realized, so as to the quick and precisely judgement of follow-up system failure.
Symptom set be designed as the present invention important component part, failure symptom characteristic information it is correct, effective and abundant
Be based on failure symptom active push fault diagnosis system effectively solving problem premise and guarantee, to a certain extent, therefore
The level of barrier sign characteristic information determines the validity of this method.Originally be in embodiment symptom set by the knot of failure mode analysis (FMA)
Fruit is encoded using binary form, each fault mode one parameter sets of correspondence, each ginseng in parameter sets
Number one group of parameter attribute of correspondence.These binary codes are stored in database so that the memory capacity of symptom set is little, retrieval speed
Degree is fast, calls conveniently.
Concrete actual conditions according to complication system of the invention, the fault mode parameter form of expression is included but is not limited to：
Parameter value exceeds threshold range：It is high and low.
Parameter Variation：Gradual, step, impulse.
The specific performance characteristic of parameter, such as：The fault parameter feature and special value feature of measuring point or sensor.
It is as follows for each parameter performance formal definition parameter attribute variate-value：
L1 parameter values variables, span and its implication it is as shown in table 1.
The parameter value binary system of table 1 is characterized
| Parameter value | Normally | Higher than threshold value | Less than threshold value | Abnormal (fluctuation) |
| Binary system is characterized | 00 | 01 | 10 | 11 |
L2 parameter regularity variables, span and its implication it is as shown in table 2.
The binary system of the Parameter Variation of table 2 is characterized
L3 parameter zero-bit characteristic variables, span and its implication it is as shown in table 3.
The binary system of the parameter zero-bit feature of table 3 is characterized
| Parameter zero-bit | It is not classified as zero-bit | It is classified as zero-bit |
| Binary system is characterized | 0 | 1 |
L4 sensor characteristics variables, span and its implication it is as shown in table 4.
The binary system of the sensor fault of table 4 is characterized
| Sensor fault | There is no sensor fault feature | With sensor fault feature |
| Binary system is characterized | 0 | 1 |
For each parameter correspond to one group of logical variable value L4L3L2L1, the logical variable set each
One group of value, one matching condition of correspondence, that is, as the sign of matching condition, as shown in Figure 3.
The present invention is transformed fault diagnosis system, after sign symbolism is carried out, into failure symptom active push
Link, the sign of symbolism is matched with symptom set, and corresponding failure symptom knot is directly exported if the match is successful
Really, classical reasoning process is entered if it fails to match, such as using pivot analysis, artificial neural network or SVMs tool
Body method, and the result of determination is fed back in symptom set.The result of each fault diagnosis of system is preserved, after which
If there is identical failure symptom, immediately diagnostic result is pushed to into user, accelerates the inference speed of inference machine.
Example 1：
By taking a specific process system as an example, P represents pressure elements, and T represents temperature element (TE, and Q represents flow element, then
Typical fault feature coding is as follows：
(1) filter clog fault is characterized as that pressure and flow parameter decline suddenly.According to coding rule, its pressure with
The corresponding binary coding of flow is L4=0, L3=0, L2=010, L1=10.Then its pressure fault is encoded to binary system
0001010；Flow Fault is encoded to Binary Zero 001010.
(2) pressure-measuring-point fracture defect is characterized as the unexpected decreasing value atmospheric pressure of pressure parameter.According to coding rule, its pressure
Corresponding binary coding be L4=0, L3=1, L2=010, L1=10, flow correspondence binary coding be L4=0, L3=0,
L2=000, L1=00.Then its pressure fault is encoded to Binary Zero 101010；Flow Fault is encoded to Binary Zero 000000.
For the value that each parameter corresponds to one group of logical variable, each group of value pair of the logical variable set
An Inference Conditions are answered, that is, as the sign of Inference Conditions.The failure symptom collection coding of the present embodiment is as follows：
| Fault type | P | Q |
| Plugged filter | 0001010 | 0001010 |
| Pressure-measuring-point ruptures | 0101010 | 0000000 |
This binary coding is stored in failure symptom concentration, when there are P=0001010 and Q=0001010 signs, that is, pushes away
Send " plugged filter " sign；When there are P=0101010 and Q=0000000 signs, that is, push " pressure-measuring-point fracture " and levy
Million.
In sum, presently preferred embodiments of the present invention is these are only, is not intended to limit protection scope of the present invention.
All any modification, equivalent substitution and improvements within the spirit and principles in the present invention, made etc., should be included in the present invention's
Within protection domain.
Claims (1)
1. a kind of method for diagnosing faults based on failure symptom active push, it is characterised in that detailed process is：
Step one, for the system of required diagnosis, all fault mode parameter representations are carried out into symbol generation；
Step 2, the corresponding relation for setting up each failure symptom and fault mode parameter, obtain system failure symptom set；
Step 3, acquisition system parameter, and the parameter representation for being gathered is carried out into symbol generation；
Step 4, judge whether the symbol generated in step 3 matches failure symptom and concentrate the corresponding symbol of at least one failure symptom
Number, if so, then will terminate the method after corresponding failure symptom output, otherwise, determined based on the symbol generated in step 3
Failure symptom, enters step 5 after output；
Step 5, by the failure symptom and step 3 of determination generate symbol corresponding relation be added to failure symptom concentrate,
Terminate the method；
The symbol is generated as：Parameter attribute is defined as into four classes：
Firstth, whether threshold range is exceeded,
Secondth, Parameter Variation,
3rd, parameter zero-bit characteristic variable,
4th, whether there is sensor fault,
For each parameter, symbol generation is carried out according to above-mentioned four attribute；
Parameter attribute symbol is represented using binary value：
Firstth, whether threshold range is exceeded,
Secondth, Parameter Variation,
3rd, parameter zero-bit characteristic variable,
4th, whether there is sensor fault,
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410720508.9A CN104503434B (en) | 2014-12-01 | 2014-12-01 | Fault diagnosis method based on active fault symptom pushing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410720508.9A CN104503434B (en) | 2014-12-01 | 2014-12-01 | Fault diagnosis method based on active fault symptom pushing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104503434A CN104503434A (en) | 2015-04-08 |
| CN104503434B true CN104503434B (en) | 2017-05-03 |
Family
ID=52944838
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410720508.9A Active CN104503434B (en) | 2014-12-01 | 2014-12-01 | Fault diagnosis method based on active fault symptom pushing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104503434B (en) |
Families Citing this family (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105096053B (en) * | 2015-08-14 | 2018-11-09 | 哈尔滨工业大学 | A kind of health control decision-making technique suitable for complicated technology system |
| CN105160081B (en) * | 2015-08-14 | 2018-11-09 | 北京航天试验技术研究所 | A kind of method for diagnosing faults based on three-dimensional cognitive environment |
| CN107316158A (en) * | 2017-07-05 | 2017-11-03 | 云能服(北京)科技有限公司 | A kind of multidimensional work data treating method and apparatus |
| CN109961199A (en) * | 2017-12-25 | 2019-07-02 | 北京京东尚科信息技术有限公司 | A kind of method and apparatus for analyzing data fluctuations |
| CN109408542B (en) * | 2018-09-26 | 2021-02-09 | 北京航天自动控制研究所 | Fault reasoning method of expert system based on symptoms |
| CN109632315A (en) * | 2019-01-11 | 2019-04-16 | 浙江浙能技术研究院有限公司 | A kind of Steam Turbine Vibration fault reasoning diagnostic method based on two-parameter rule match |
| CN110993135A (en) * | 2019-10-09 | 2020-04-10 | 中国核电工程有限公司 | Sign-based design method for secondary side heat trap control strategy of pressurized water reactor nuclear power plant |
| CN111896865B (en) * | 2020-07-30 | 2021-06-25 | 电子科技大学 | Fault position detection method for signal acquisition system |
| CN116208464B (en) * | 2022-12-30 | 2024-04-30 | 王家耿 | Broadcast transmitter fault big data information analysis method and system based on cloud computing |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634851A (en) * | 2009-08-25 | 2010-01-27 | 西安交通大学 | Method based on cause-and-effect relation of variables for diagnosing failures in process industry |
| CN102004486A (en) * | 2010-09-26 | 2011-04-06 | 中国石油化工股份有限公司 | Hybrid fault diagnosis method based on qualitative signed directed graph in petrochemical process |
| CN102521613A (en) * | 2011-12-17 | 2012-06-27 | 山东省科学院自动化研究所 | Method for fault diagnosis of automobile electronic system |
| CN103593336A (en) * | 2013-10-30 | 2014-02-19 | 中国运载火箭技术研究院 | Knowledge pushing system and method based on semantic analysis |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101491196B1 (en) * | 2007-08-03 | 2015-02-06 | 스마트시그널 코포레이션 | Fuzzy classification approach to fault pattern matching |
-
2014
- 2014-12-01 CN CN201410720508.9A patent/CN104503434B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101634851A (en) * | 2009-08-25 | 2010-01-27 | 西安交通大学 | Method based on cause-and-effect relation of variables for diagnosing failures in process industry |
| CN102004486A (en) * | 2010-09-26 | 2011-04-06 | 中国石油化工股份有限公司 | Hybrid fault diagnosis method based on qualitative signed directed graph in petrochemical process |
| CN102521613A (en) * | 2011-12-17 | 2012-06-27 | 山东省科学院自动化研究所 | Method for fault diagnosis of automobile electronic system |
| CN103593336A (en) * | 2013-10-30 | 2014-02-19 | 中国运载火箭技术研究院 | Knowledge pushing system and method based on semantic analysis |
Non-Patent Citations (1)
| Title |
|---|
| 一种基于知识推送的故障诊断系统;杨思锋 等;《航空动力学报》;20100115;第25卷(第1期);第203-207页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104503434A (en) | 2015-04-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104503434B (en) | Fault diagnosis method based on active fault symptom pushing | |
| CN111798312B (en) | Financial transaction system anomaly identification method based on isolated forest algorithm | |
| Jack et al. | Genetic algorithms for feature selection in machine condition monitoring with vibration signals | |
| KR102444442B1 (en) | System and method for diagnosing facility fault | |
| CN109977146B (en) | Fault diagnosis method and device and electronic equipment | |
| CN111027615B (en) | Middleware fault early warning method and system based on machine learning | |
| CN106021545A (en) | Method for remote diagnoses of cars and retrieval of spare parts | |
| CN113570138B (en) | Method and device for predicting residual service life of equipment of time convolution network | |
| US11860608B2 (en) | Industrial equipment operation, maintenance and optimization method and system based on complex network model | |
| CN105577440A (en) | Network fault time location method and analyzing device | |
| CN111209934B (en) | Fan fault pre-alarm method and system | |
| CN104202765A (en) | Method and device for detecting sensor faults based on distributed network | |
| CN112598172A (en) | Wind turbine bearing temperature early warning method | |
| CN117241306B (en) | Real-time monitoring method for abnormal flow data of 4G network | |
| CN115062272A (en) | Water quality monitoring data abnormity identification and early warning method | |
| CN105302123A (en) | Online data monitoring method | |
| CN115577701A (en) | Risk behavior identification method, device, equipment and medium for big data security | |
| CN113505531B (en) | Diagnostic model construction method based on combination of traditional diagnosis and machine learning method and aiming at abnormal valve clearance faults of reciprocating machinery | |
| CN110852860A (en) | Vehicle maintenance reimbursement behavior abnormity detection method, equipment and storage medium | |
| CN112787984A (en) | Vehicle-mounted network anomaly detection method and system based on correlation analysis | |
| CN111275136B (en) | Fault prediction system based on small sample and early warning method thereof | |
| CN117312879A (en) | Injection molding machine production data supervision and early warning method, system and medium | |
| CN115422263B (en) | Multifunctional universal fault analysis method and system for electric power field | |
| CN103514458A (en) | Sensor fault distinguishing method based on combination of error correction codes and support vector machine | |
| CN113537360B (en) | Point-to-point classification fault detection method based on deep learning |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |