CN111832730B - Reliability characterization and state identification method for uncertain oil state - Google Patents
Reliability characterization and state identification method for uncertain oil state Download PDFInfo
- Publication number
- CN111832730B CN111832730B CN202010655583.7A CN202010655583A CN111832730B CN 111832730 B CN111832730 B CN 111832730B CN 202010655583 A CN202010655583 A CN 202010655583A CN 111832730 B CN111832730 B CN 111832730B
- Authority
- CN
- China
- Prior art keywords
- oil
- state
- attribute
- index
- evidence
- 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
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012512 characterization method Methods 0.000 title claims abstract description 13
- 238000012544 monitoring process Methods 0.000 claims abstract description 61
- 238000011156 evaluation Methods 0.000 claims abstract description 39
- 239000007788 liquid Substances 0.000 claims abstract description 14
- 238000010606 normalization Methods 0.000 claims abstract description 11
- 238000012545 processing Methods 0.000 claims abstract description 10
- 230000008901 benefit Effects 0.000 claims abstract description 7
- 238000004364 calculation method Methods 0.000 claims description 8
- 230000008859 change Effects 0.000 claims description 7
- 238000005315 distribution function Methods 0.000 claims description 7
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000013139 quantization Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 239000003921 oil Substances 0.000 description 104
- 230000015572 biosynthetic process Effects 0.000 description 6
- 239000010687 lubricating oil Substances 0.000 description 6
- 238000003786 synthesis reaction Methods 0.000 description 5
- 239000000654 additive Substances 0.000 description 4
- 230000000996 additive effect Effects 0.000 description 4
- 239000002253 acid Substances 0.000 description 3
- 239000003344 environmental pollutant Substances 0.000 description 3
- 231100000719 pollutant Toxicity 0.000 description 3
- 238000005299 abrasion Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000356 contaminant Substances 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007123 defense Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 230000002542 deteriorative effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003745 diagnosis Methods 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000011155 quantitative monitoring Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000010561 standard procedure Methods 0.000 description 1
- 230000002194 synthesizing effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/04—Inference or reasoning models
- G06N5/048—Fuzzy inferencing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06393—Score-carding, benchmarking or key performance indicator [KPI] analysis
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Entrepreneurship & Innovation (AREA)
- Economics (AREA)
- Artificial Intelligence (AREA)
- Educational Administration (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Development Economics (AREA)
- Strategic Management (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Tourism & Hospitality (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Marketing (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Evolutionary Biology (AREA)
- General Business, Economics & Management (AREA)
- Automation & Control Theory (AREA)
- Fuzzy Systems (AREA)
- Probability & Statistics with Applications (AREA)
- Computational Linguistics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Testing Or Calibration Of Command Recording Devices (AREA)
Abstract
A reliability characterization and state recognition method for an oil uncertain state is used for carrying out normalization processing on oil monitoring data to obtain oil index monitoring data; dividing the oil into N state grades from good to bad according to the attribute state of the oil; carrying out fuzzy evaluation on the oil index monitoring data; probability assignment is carried out on the evaluation result to obtain the joint probability of a certain attribute belonging to each state grade, and finally a comprehensive attribute state, namely the fuzzy membership degree, is formed; the fuzzy membership degree is used as an evidence of evidence reasoning ER, the uncertainty of each evidence is calculated according to the weights of different attribute states, and the evidence reasoning ER algorithm is applied to realize the reliability representation of the uncertain state of the oil liquid; the method and the device have the advantages that the judgment standard of the oil state evidence reasoning result is made, the identification of the oil state is realized, and the problems that the oil state is difficult to represent and the evaluation result is large in uncertainty due to inconsistent multi-index information in the multi-index oil monitoring process are solved.
Description
Technical Field
The invention belongs to the technical field of oil state monitoring, and particularly relates to a reliability characterization and state identification method for an uncertain oil state.
Background
The oil state is the basis of equipment health assessment, the state of the machine is reflected by monitoring oil information, predictive judgment and prospective decision can be provided for the early failure state of the machine, and the method is a first defense line for preventing the equipment state from deteriorating. However, a single index only reflects partial information of the oil, and the comprehensive oil information cannot be represented by one or a small number of indexes, so that the research on the multi-index oil monitoring technology has great significance.
Oil monitoring is to provide equipment state information by monitoring the comprehensive information of the continuously running lubricating oil of the friction system, and is not to provide monitoring information by a sensor which is locally installed. The oil state is a comprehensive representation of multi-index information, and the change of the oil state is accompanied with the change of various index information. However, lubricating oils have dozens of characteristic indexes including physical and chemical properties, contaminant content, metal element content, additive content, and the like. The evidence reasoning method (ER) is firstly proposed in 1994, is used for solving the multi-index decision problem, can qualitatively and quantitatively represent the problem of unknown and uncertain probability, and is widely applied to oil fault diagnosis and state evaluation. The FER algorithm is established by the combined fuzzy evaluation method, namely, the evaluation state grade is not a clear state set any more but is defined as a dependent fuzzy set, quantitative monitoring data information can be converted into a fuzzy belief structure, and oil state evaluation is realized by a probability and fuzzy mathematics-based method.
In the oil monitoring process, inconsistent multi-index information conflicts can generate oil comprehensive state representation with high uncertainty, in addition, the multi-index interaction causes that accurate and effective results cannot be obtained in the oil state identification process, and the problems strictly limit the development of the oil state monitoring technology. With the requirement of machine reliability maintenance, the representation and state identification of uncertain states in oil state monitoring become one of the problems which need to be solved urgently.
Disclosure of Invention
In order to overcome the defects of the prior art, the invention aims to provide a method for representing the reliability of an uncertain oil state and identifying the state, the method comprises the steps of obtaining a confidence value of an oil state through evidence synthesis and reasoning, solving the problems that the oil state is difficult to characterize and identify in the oil monitoring process through setting a confidence threshold value and judging uncertainty, specifically classifying oil monitoring index data according to different attribute classes, realizing fuzzy evaluation of the states of different classes based on fuzzy mathematics and probabilistic statistics, the credibility representation of the uncertain state of the oil is realized by applying an Evidence Reasoning (ER) method, the state identification of the oil is realized by constructing corresponding judgment standards, the problems that in the multi-index oil monitoring process, the oil state characterization is difficult and the uncertainty of the evaluation result is large due to the inconsistency of the multi-index information.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a reliability characterization and state identification method for an oil uncertain state comprises the following steps:
(1) normalization processing is carried out, oil monitoring data are normalized by a linear interpolation method, and oil index monitoring data { x }are obtained 11 ,x 12 ,…x ij ,…}；
(2) Setting the state grade, and classifying the oil into (H) according to the attribute state of the oil from good to bad 1 ,H 2 ,…,H c …,H N N status levels;
(3) fuzzy state evaluation, fuzzy evaluation is carried out on the oil index monitoring data, and the fuzzy state evaluation method is applied to the oil index monitoring data { x } 11 ,x 12 ,…x ij … } are evaluated separately;
(4) forming attribute states, namely performing probability assignment on the evaluation result obtained in the step (3) to obtain the joint probability of a certain attribute belonging to each state grade, and finally forming a comprehensive attribute state, namely fuzzy membership;
(5) taking the fuzzy membership degree obtained in the step (4) as evidence of evidence reasoning ER, calculating uncertainty of each evidence according to weights of different attribute states, and applying an evidence reasoning ER algorithm to realize reliability representation of the uncertain state of the oil liquid;
(6) and (4) formulating an oil state evidence reasoning result judgment standard to realize the identification of the oil state.
The step (1) specifically comprises the following steps:
dividing oil monitoring data into benefit type data and loss type data, defining the data with the higher index value as the benefit type data, and applying a formula (1) to carry out data normalization processing; defining data with smaller index value as loss data, and applying an equation (2) to perform data normalization processing:
in the formula, x min Representing an oil initial index value, and selecting new oil frequently or monitoring the oil index value at the initial time; x is the number of max The index value of the oil failure can be set by referring to the index value of the specified oil change in the corresponding standard;
to take on a value of [0,1]And normalizing the index value of the oil monitoring data in the interval, wherein i is 1,2, … r, r represents the number of attributes, and j is 1,2, … g, and g represents the number of indexes in the ith attribute.
The step (2) specifically comprises the following steps:
the state grade is used for measuring the decay degree of the oil liquid, and is divided into { H } from good to bad according to the attribute state of the oil liquid 1 ,H 2 ,…,H c …,H N N state levels are obtained, each state level corresponds to an interval of a quantization value, oil index values in known states are trained, and corresponding interval boundary points c are obtained by dividing an ROC curve i 。
The step (3) specifically comprises the following steps:
calculating the index value normalized in the step (1) by using the Gaussian membership function shown in the formula (3)
Corresponding state class of H c Degree of (i.e. degree of membership)
Wherein c and sigma respectively represent the mean and standard deviation of the Gaussian membership function;
then all monitoring data of j index sequence
Fuzzy conversion and arrangement are carried out, as shown in formula (4), after the conversion of the formula (4), the monitoring data of each index is converted into fuzzy membership P corresponding to each state grade j (H)：
Wherein p is j (H) And (3) representing the fuzzy membership degree of all data monitored by the jth index corresponding to each state grade, wherein N represents the number of the state grades.
The step (4) specifically comprises the following steps:
monitoring oil index data with time series { (x) 11 ,t 1 ),(x 12 ,t 2 )…(x 1j ,t j ) Calculating index weight by using an entropy weight method, wherein the calculation method is shown as the formula (5):
wherein,
characterizing the information fluctuation degree of the monitoring data in the step (1);
calculating the attribute containing a plurality of indexes by applying a formula (6) to obtain the joint probability of the attribute and obtain the weighted fuzzy evaluation result of the oil attribute:
in the formula (6), M i (H) Is the ith attribute membershipMembership degree of each state grade is also a basic probability distribution function of the ith attribute evidence in the ER algorithm, g represents the number of indexes in the ith attribute, and w ij Representing the importance, P, of the jth index in the ith attribute j (H) And the membership degree of the j index in the i attribute in the monitoring sequence data corresponding to each state grade is represented.
The step (5) specifically comprises the following steps:
the weight coefficient w of each attribute state is calculated by applying the formula (7) i Wherein i is 1,2 … r:
wherein,
characterizing the information fluctuation degree of the monitoring data in the step (1);
the basic probability function BPA of evidence reasoning is calculated by applying the formulas (6) and (8):
m i (H)＝α i ×M i (H) (8)
an uncertain confidence distribution function of evidence reasoning is calculated by applying a formula (9):
m i (Θ)＝1-α i (9)
α i ＝α K ×(w i /w max ) (10)
wherein alpha is K ＝0.9，w i ＝{w 1 ,w 2 ,…w r }，w max The weight which is the largest weight in the attribute weights;
the ER algorithm is applied to carry out oil state reliability calculation, and the synthetic rule is shown as a formula (11):
K＝(1-m I (H c+1 )m i (H c )-m I (H c )m i (H c+1 )) -1
wherein m is I (H c ) Assigning probability, m, to the synthesized evidence i (H c ) Assign probability, m, to new evidence Ii (H c ) Assigning probabilities to the synthetic evidence; likewise, m i (Θ)，m I (Θ)，m Ii (Θ) representing the unassigned probabilities of new evidence, synthesized evidence, and synthesized evidence, respectively; h c And H c+1 Are adjacent state levels in the attribute level.
The step (6) specifically comprises the following steps:
and (4) performing evidence reasoning based on a reasoning rule in the formula (11), wherein the evaluation state meeting the constraint condition of the formula (12) is the determined oil state.
Wherein m is I (H N1 ) The probability is the maximum distribution probability; m is I (H N2 ) To remove m I (H N1 ) An outer maximum distribution probability; m is I (Θ) is the unassigned probability; epsilon 0 Is set to 0.01,. epsilon 1 Set to 0.04, smaller ε 1 The more accurate and reliable the evaluation result obtained by the value is, the more epsilon 1 The result of the evaluation of the value is considered to be an unreliable result; the oil state grade satisfying the constraint condition of the formula (12) is H N1 。
The invention has the beneficial effects that: the method comprises the steps of obtaining a reliability value of the oil liquid state through evidence synthesis and reasoning, and solving the problems that the oil liquid state is difficult to characterize and identify in the oil liquid monitoring process through reliability threshold setting and uncertainty judgment. In the oil state monitoring process, monitoring indexes are various, index information has ambiguity and uncertainty, in order to obtain an oil state evaluation result with high accuracy and high reliability value, the invention classifies multiple lubricating oil information indexes, performs fuzzy state evaluation on different index data respectively, takes the attribute of lubricating oil as an evidence for representing the oil state, obtains the reliability value of the oil state through evidence reasoning and synthesis, and realizes reliability representation and state evaluation of the uncertain oil state through reliability threshold setting and uncertainty judgment.
Drawings
FIG. 1 is a diagram of oil monitoring index and attribute status classification according to the present invention.
FIG. 2 is a flow chart of a state estimation method according to the present invention.
Fig. 3 is a diagram illustrating an evaluation result of an oil state in an actual monitoring process according to the present invention.
Detailed Description
The invention is further described below with reference to the accompanying drawings.
The indexes of the oil state monitoring can be classified into the oil physical and chemical state of the lubricating oil, the additive state, the pollutant state and the wear state reflected by the flowing of the abrasive dust generated by the abrasion of parts into the oil according to different action objects, and respectively correspond to the indexes { x } 11 ,x 12 ,…x ij … and attribute H 1 ,H 2 ,…,H c …,H N }. As shown in figure 1, the oil monitoring data is classified and comprises an index layer, an attribute layer and a state layer, wherein the index layer is the obtained oil index monitoring data, the attribute layer comprises physicochemical attributes, additive attributes, pollutant attributes and abrasive particle attributes reflected by abrasive dust generated by component abrasion flowing into oil, and the state layer is composed of [0,1 ]]The numerical value of (1) represents the fault condition of the equipment, 0 represents that the equipment is in the best state, and 1 represents that the equipment is in the most serious state; the method comprises the steps of taking different attribute grades of oil as evidences reflecting the oil state, obtaining a confidence value of the oil state through evidence synthesis and reasoning, and realizing confidence representation and state evaluation of the oil state through setting of a confidence threshold and judgment of uncertainty.
Based on the analysis, the invention provides a reliability characterization and state identification method for an oil uncertain state, and the method specifically comprises the following steps with reference to fig. 2:
(1) data normalization: the oil monitoring data is normalized by a linear interpolation method to obtainObtaining oil index monitoring data { x } 11 ,x 12 ,…x ij ,…}；
Due to the fact that dimensions and sizes of time series data of different oil indicators are different, the oil indicators need to be normalized by a linear interpolation method. In order to enable the monitoring data to be unified and trended and dimensionless, the oil monitoring data is divided into benefit type data and loss type data. The larger the index value is, the better the data is, such as the additive content, the Total Base Number (TBN) and the volume of the lubricating oil are defined as benefit type data, and data normalization processing is carried out by applying the formula (1); data with a smaller index value, such as viscosity change rate, acid value (TAN) change, and pollutant content, is better, and is defined as loss-type data, and data normalization processing is performed by applying formula (2).
In the formula, x min Representing an oil initial index value, and frequently selecting new oil or monitoring the oil index value at the initial time; x is the number of max The index value of the oil failure can be set by referring to the index value of the specified oil change in the corresponding standard;
to take on a value of [0,1]And normalizing index values of the oil monitoring data in the interval, wherein i is 1,2, … r, r represents the number of attributes, and j is 1,2, … g, g represents the number of indexes in the ith attribute.
(2) Setting of state level: the state grade is used for measuring the decay degree of the oil liquid, and is divided into { H } according to the state of the oil liquid attribute from good to bad 1 ,H 2 ,…,H c …,H N N oil state grades are obtained, each state grade corresponds to an interval of a quantization value, and corresponding interval demarcation points c are obtained by training various index values of oil in known states and dividing an ROC curve i 。
(3) Fuzzy state evaluation, fuzzy evaluation is carried out on the oil index monitoring data, and the oil index monitoring data { x is evaluated by applying a fuzzy state evaluation method 11 ,x 12 ,…x ij … } are evaluated separately;
it is impractical for any one of the indicators to describe only that it belongs to a particular state class, for example, the viscosity-characterized oil state class is H 1 The oil state grade characterized by the acid number is H 2 However, it is not possible to effectively obtain the oil state grade represented by the physicochemical properties represented by the multiple indexes including viscosity and acid value, and it is more difficult to obtain the oil state grade including the multiple attributes. Therefore, the probability P corresponding to the oil state grade is obtained by synthesizing information of a plurality of indexes and attributes on the premise of reasonably distributing different indexes and attribute weights by applying the possibility of calculating the state grade represented by the index data in the step (1) by using the Gaussian membership function j (H)。
Calculating the index value normalized in the step (1) by using the Gaussian membership function shown in the formula (3)
Corresponding state class of H c Degree of (2), i.e. degree of membership
Where c and σ represent the mean and standard deviation of the gaussian membership function, respectively.
Then, all the monitoring data of each j index sequence are processed
Fuzzy transformation and arrangement are carried out as shown in formula (4). After transformation by the formula (4), the monitoring data of each index is converted into fuzzy membership corresponding to each state gradeDegree P j (H)。
Wherein p is j (H) And (3) representing the fuzzy membership degree of all data monitored by the jth index corresponding to each state grade, wherein N represents the number of the state grades.
(4) Formation of attribute states
Probability assignment is carried out on the evaluation result obtained in the step (3), the joint probability that a certain attribute belongs to each state grade is obtained, and finally a comprehensive attribute state, namely the fuzzy membership degree P is formed j (H)。
First, index data { (x) having a time series 11 ,t 1 ),(x 12 ,t 2 )…(x ji ,t j ) Calculating index weight by using an entropy weight method, wherein the calculation method is shown as the formula (5):
wherein,
and (2) reflecting the information fluctuation degree of the monitoring data in the step (1).
Then, in order to quantitatively represent the attribute information, the joint probability of the attributes is calculated by applying formula (6) to the attributes including a plurality of indexes, and the weighted fuzzy evaluation result of the oil attribute is obtained.
In the formula (6), M i (H) The attribute distribution function is the membership degree of the ith attribute to each state grade and is also the basic probability distribution function of the ith attribute evidence in the ER algorithm; g represents the number of indexes in the ith attribute, w ij Representing j-th index in i-th attributeImportance, P j (H) And the membership degree of the j index in the i attribute in the monitoring sequence data corresponding to each state grade is represented.
(5) And (4) taking the oil attribute state obtained by calculation in the step (4) as an evidence of Evidence Reasoning (ER), obtaining a confidence value of the oil state through evidence reasoning and synthesis, and realizing the confidence representation and state evaluation of the uncertain oil state through setting a confidence threshold and judging uncertainty.
The weight coefficient w of each attribute state is calculated by applying equation (7) i Wherein i is 1,2 … r.
Wherein,
and (2) characterizing the information fluctuation degree of the monitoring data in the step (1).
The basic probability function (BPA) of evidence reasoning is calculated by applying the formulas (6) and (8):
m i (H)＝α i ×M i (H) (8)
an uncertain confidence distribution function of evidence reasoning is calculated by applying a formula (9):
m i (Θ)＝1-α i (9)
α i ＝α K ×(w i /w max ) (10)
wherein alpha is K ＝0.9，w i ＝{w 1 ,w 2 ,…w r }，w max Is the largest weight among the attribute weights.
And (3) carrying out oil state reliability calculation by applying an Evidence Reasoning (ER) algorithm, wherein the synthetic rule is shown as a formula (11):
wherein m is I (H c ) To be synthesizedIs assigned probability, m i (H c ) Assign probability, m, for new evidence Ii (H c ) Probability is assigned to the synthetic evidence. Likewise, m i (Θ)，m I (Θ)，m Ii (Θ) represents the unassigned probabilities of new evidence, synthesized evidence, and synthesized evidence, respectively. H c And H c+1 Are adjacent state levels in the attribute level.
(6) And (4) making a judgment standard of an oil liquid state evaluation result, and realizing the judgment of the oil liquid state, as shown in figure 3.
Performing evidence reasoning based on a reasoning rule in an equation (11), wherein the state meeting the constraint condition of the equation (12) is the determined state of the oil liquid:
wherein m is I (H N1 ) The maximum distribution probability is obtained; m is a unit of I (H N2 ) To remove m I (H N1 ) An outer maximum distribution probability; m is a unit of I (Θ) is the unassigned probability; epsilon 0 Set to 0.01, referenced to expert or standard techniques; epsilon 1 Set to 0.04, smaller ε 1 The more accurate and reliable the evaluation result obtained by the value is, the more epsilon 1 The result of the evaluation of the value is considered to be an unreliable result; the oil state grade satisfying the constraint condition of the formula (12) is H N1 。
Claims (5)
1. A reliability characterization and state identification method for an oil uncertain state is characterized by comprising the following steps:
(1) normalization processing, namely performing normalization processing on the oil monitoring data by using a linear interpolation method to obtain oil index monitoring data;
(2) setting the state grade, and dividing the oil into { H) from good to bad according to the attribute state of the oil 1 ，H 2 ，…，H c …，H N N status levels;
(3) fuzzy state evaluation, fuzzy evaluation is carried out on oil index monitoring data, and the fuzzy state is appliedOil index monitoring data { x) by evaluation method 11 ，x 12 ，…x ij … } are evaluated separately;
(4) forming attribute states, namely performing probability assignment on the evaluation result obtained in the step (3) to obtain the joint probability of a certain attribute belonging to each state grade, and finally forming a comprehensive attribute state, namely fuzzy membership;
(5) taking the fuzzy membership degree obtained by calculation in the step (4) as an evidence of evidence reasoning ER, calculating the uncertainty of each evidence according to the weights of different attribute states, and realizing the reliability characterization of the uncertain state of the oil by applying an evidence reasoning ER algorithm;
(6) formulating an oil state evidence reasoning result judgment standard to realize the identification of the oil state;
the step (1) specifically comprises the following steps:
dividing oil monitoring data into benefit type data and loss type data, defining the data with the higher index value as the benefit type data, and applying a formula (1) to carry out data normalization processing; defining the data with smaller index value as loss type data, and applying formula (2) to perform data normalization processing:
in the formula, x min Representing an oil initial index value, and frequently selecting new oil or monitoring the oil index value at the initial time; x is the number of max The index value of the oil failure can be set by referring to the index value of the specified oil change in the corresponding standard;
to take on a value of [0,1]Normalizing index values of oil monitoring data in the interval, wherein i is 1,2, … r, r represents the attribute number, and j isi ═ 1,2,. g, g denote the number of indicators in the ith attribute;
the step (4) specifically comprises the following steps:
monitoring oil index data with time series { (x) 11 ，t 1 )，(x 12 ，t 2 )…(x 1j ，t j ) Calculating index weight by using an entropy weight method, wherein the calculation method is shown as the formula (5):
wherein,
wherein i is 1,2, … r, r represents the number of attributes, and j is 1, 2.. g, g represents the number of indexes in the ith attribute;
calculating the attribute containing a plurality of indexes by applying a formula (6) to obtain the joint probability of the attribute and obtain the weighted fuzzy evaluation result of the oil attribute:
in the formula (6), M i (H) Is the membership degree of the ith attribute to each state grade and is also the basic probability distribution function of the ith attribute evidence in the ER algorithm, wherein i is 1,2 ij Representing the importance, P, of the jth index in the ith attribute j (H) And the membership degree of the j index in the i attribute in the monitoring sequence data corresponding to each state grade is represented.
2. The method for reliability characterization and state identification of an oil uncertain state according to claim 1,
the step (2) specifically comprises the following steps:
the state grade is used for measuring the decay degree of the oil liquid, and is divided into { H } from good to bad according to the attribute state of the oil liquid 1 ，H 2 ，…，H c …，H N N state levels are obtained, each state level corresponds to an interval of a quantization value, oil index values in known states are trained, and corresponding interval boundary points c are obtained by dividing an ROC curve i 。
3. A method for reliability characterization and status identification of an uncertain condition of oil according to claim 2,
the step (3) specifically comprises the following steps:
calculating the normalized index Bo in the step (1) by using the Gaussian membership function shown in the formula (3)
Corresponding state class of H c Degree of (2), i.e. degree of membership
Wherein c and sigma respectively represent the mean and standard deviation of the Gaussian membership function;
then all monitoring data of j index sequence
Carrying out fuzzy conversion and arrangement, as shown in formula (4), converting the monitoring data of each index into fuzzy membership P corresponding to each state grade after transformation of formula (4) j (H)；
Wherein p is j (H) And (3) representing the fuzzy membership degree of all data monitored by the jth index corresponding to each state grade, wherein N represents the number of the state grades.
4. A method for reliability characterization and status identification of an uncertain state of oil according to claim 1,
the step (5) specifically comprises the following steps:
the weight coefficient w of each attribute state is calculated by applying the formula (7) i Wherein i is 1,2 … r; r represents the number of attributes;
wherein,
r represents the number of attributes, j is 1, 2.. g, g represents the number of indexes in the ith attribute;
the basic probability function BPA of evidence reasoning is calculated by applying the formulas (6) and (8):
m i (H)＝α i ×M i (H) (8)
an uncertain confidence distribution function for evidence reasoning is calculated using equation (9):
m i (Θ)＝1-α i (9)
α i ＝α K ×(w i /w max ) (10)
wherein alpha is K ＝0.9，w i ＝{w 1 ，w 2 ，…w r }，w max Is the largest weight among the attribute weightsWeighing;
the ER algorithm is applied to carry out oil state reliability calculation, and the synthetic rule is shown as the formula (11):
wherein m is I (H c ) Assigning probability, m, to the synthesized evidence i (H c ) Assign probability, m, for new evidence Ii (H c ) Assigning probabilities to the synthetic evidence; likewise, m i (Θ)，m I (Θ)，m Ii (Θ) representing the unassigned probabilities of new evidence, synthesized evidence, and synthesized evidence, respectively; h c And H c+1 Are adjacent state levels in the attribute level.
5. A method for reliability characterization and status identification of an uncertain state of oil according to claim 4,
the step (6) specifically comprises the following steps:
performing evidence reasoning based on a reasoning rule in the formula (11), wherein the evaluation state meeting the constraint condition of the formula (12) is the determined oil state;
wherein m is I (H N1 ) The probability is the maximum distribution probability; m is a unit of I (H N2 ) To remove m I (H N1 ) An outer maximum distribution probability; m is a unit of I (Θ) is the unassigned probability; epsilon 0 Is set to 0.01,. epsilon 1 Set to 0.04, the smaller epsilon 1 The more accurate and reliable the evaluation result obtained by the value is, the more epsilon 1 The result of the evaluation of the value is considered to be an unreliable result; the oil state grade satisfying the constraint condition of the formula (12) is H N1 。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655583.7A CN111832730B (en) | 2020-07-09 | 2020-07-09 | Reliability characterization and state identification method for uncertain oil state |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010655583.7A CN111832730B (en) | 2020-07-09 | 2020-07-09 | Reliability characterization and state identification method for uncertain oil state |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111832730A CN111832730A (en) | 2020-10-27 |
| CN111832730B true CN111832730B (en) | 2022-07-26 |
Family
ID=72900485
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010655583.7A Active CN111832730B (en) | 2020-07-09 | 2020-07-09 | Reliability characterization and state identification method for uncertain oil state |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111832730B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112784480B (en) * | 2021-01-13 | 2023-08-08 | 西安交通大学 | Oil liquid state self-learning quantitative characterization method, storage medium and equipment |
| CN112949022B (en) * | 2021-01-13 | 2024-04-02 | 西安交通大学 | Fuzzy evidence reasoning method, storage medium and device for integrated expert system |
| CN114187464A (en) * | 2021-11-22 | 2022-03-15 | 南京理工大学 | Multi-cycle target identification method based on laser radar and vision fusion in complex environment |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5305425A (en) * | 1989-04-14 | 1994-04-19 | Omron Corporation | Method of and apparatus for evaluating membership functions or rules in fuzzy reasoning system |
| US5805773A (en) * | 1990-11-28 | 1998-09-08 | Hitachi Ltd. | Fuzzy reasoning method and system |
| CN105512962A (en) * | 2016-01-13 | 2016-04-20 | 武汉大学 | Method for comprehensively evaluating insulation status of gas insulated switchgear (GIS) |
| CN106651169A (en) * | 2016-12-19 | 2017-05-10 | 国家电网公司 | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
| CN106940281A (en) * | 2016-12-09 | 2017-07-11 | 中国航空工业集团公司上海航空测控技术研究所 | A kind of aviation oil analysis method based on information fusion technology model of mind |
| CN106997489A (en) * | 2017-03-09 | 2017-08-01 | 国家电网公司 | New variable impedance transformer state evaluating method based on evidence theory |
| CN110119713A (en) * | 2019-05-14 | 2019-08-13 | 云南电网有限责任公司电力科学研究院 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
| CN110333414A (en) * | 2019-08-02 | 2019-10-15 | 华北电力大学（保定） | The multi-level state evaluating method of power transformer |
| CN110428151A (en) * | 2019-07-18 | 2019-11-08 | 国网山东省电力公司电力科学研究院 | A kind of method for evaluating state of synchronous capacitor oil system |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB2520987B (en) * | 2013-12-06 | 2016-06-01 | Cyberlytic Ltd | Using fuzzy logic to assign a risk level profile to a potential cyber threat |
-
2020
- 2020-07-09 CN CN202010655583.7A patent/CN111832730B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5305425A (en) * | 1989-04-14 | 1994-04-19 | Omron Corporation | Method of and apparatus for evaluating membership functions or rules in fuzzy reasoning system |
| US5805773A (en) * | 1990-11-28 | 1998-09-08 | Hitachi Ltd. | Fuzzy reasoning method and system |
| CN105512962A (en) * | 2016-01-13 | 2016-04-20 | 武汉大学 | Method for comprehensively evaluating insulation status of gas insulated switchgear (GIS) |
| CN106940281A (en) * | 2016-12-09 | 2017-07-11 | 中国航空工业集团公司上海航空测控技术研究所 | A kind of aviation oil analysis method based on information fusion technology model of mind |
| CN106651169A (en) * | 2016-12-19 | 2017-05-10 | 国家电网公司 | Fuzzy comprehensive evaluation-based distribution automation terminal state evaluation method and system |
| CN106997489A (en) * | 2017-03-09 | 2017-08-01 | 国家电网公司 | New variable impedance transformer state evaluating method based on evidence theory |
| CN106919982A (en) * | 2017-03-20 | 2017-07-04 | 中国科学院沈阳自动化研究所 | A kind of method for diagnosing faults towards semiconductor manufacturing equipment |
| CN110119713A (en) * | 2019-05-14 | 2019-08-13 | 云南电网有限责任公司电力科学研究院 | Mechanical Failure of HV Circuit Breaker diagnostic method based on D-S evidence theory |
| CN110428151A (en) * | 2019-07-18 | 2019-11-08 | 国网山东省电力公司电力科学研究院 | A kind of method for evaluating state of synchronous capacitor oil system |
| CN110333414A (en) * | 2019-08-02 | 2019-10-15 | 华北电力大学（保定） | The multi-level state evaluating method of power transformer |
Non-Patent Citations (2)
| Title |
|---|
| Detection and Diagnosis of Incipient Faults in Heavy-Duty Diesel Engines;Ian Morgan 等;《IEEE Transactions on Industrial Electronics 》;20091231;第57卷(第10期);第3522-3532页 * |
| 基于支持概率距离的变压器状态评估方法;李菲等;《电气应用》;20171205;第36卷(第23期);第76-82页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111832730A (en) | 2020-10-27 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111832730B (en) | Reliability characterization and state identification method for uncertain oil state | |
| CN110263846B (en) | Fault diagnosis method based on fault data deep mining and learning | |
| Pal et al. | Development of a hybrid methodology for dimensionality reduction in Mahalanobis–Taguchi system using Mahalanobis distance and binary particle swarm optimization | |
| CN113762329A (en) | Method and system for constructing state prediction model of large rolling mill | |
| CN112085947A (en) | Traffic jam prediction method based on deep learning and fuzzy clustering | |
| CN111382542A (en) | Road electromechanical equipment life prediction system oriented to full life cycle | |
| CN104809877A (en) | Expressway site traffic state estimation method based on feature parameter weighted GEFCM algorithm | |
| CN115508073A (en) | Prototype adaptation mechanical equipment fault diagnosis method based on multi-scale attention | |
| CN111833175A (en) | Internet financial platform application fraud behavior detection method based on KNN algorithm | |
| CN116976857A (en) | Predictive maintenance method and system for railway power equipment based on deep learning | |
| CN118132849A (en) | Steel structure welding process quality management recommendation method based on big data processing | |
| CN118097567A (en) | Work material machine elemental analysis acquisition system and method based on construction site video | |
| CN112069621B (en) | Method for predicting residual service life of rolling bearing based on linear reliability index | |
| CN107169532B (en) | Internet of vehicles fuel consumption data quality evaluation method based on wavelet analysis and semi-supervised learning | |
| CN112732787A (en) | Equipment portrait and personalized operation and maintenance service method for important parts of motor train unit | |
| CN111832731B (en) | Multi-index monitoring method for representing uncertain state of oil and diagnosing faults | |
| CN114167837B (en) | Intelligent fault diagnosis method and system for railway signal system | |
| CN114580472B (en) | Large-scale equipment fault prediction method with repeated cause and effect and attention in industrial internet | |
| CN114547796B (en) | Ball mill feature fusion fault diagnosis method based on optimized BN network | |
| CN116956089A (en) | Training method and detection method for temperature anomaly detection model of electrical equipment | |
| Zhao et al. | Performance prediction methodology based on pattern recognition | |
| Chen | Data Quality Assessment Methodology for Improved Prognostics Modeling | |
| Saeed et al. | A novel fuzzy-based similarity measure for collaborative filtering to alleviate the sparsity problem | |
| CN116665342B (en) | New energy automobile driving behavior analysis method, system and equipment | |
| CN116862308A (en) | Rail health state evaluation method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |