CN114357644A - Health degree evaluation method based on air separation equipment - Google Patents
Health degree evaluation method based on air separation equipment Download PDFInfo
- Publication number
- CN114357644A CN114357644A CN202111645050.1A CN202111645050A CN114357644A CN 114357644 A CN114357644 A CN 114357644A CN 202111645050 A CN202111645050 A CN 202111645050A CN 114357644 A CN114357644 A CN 114357644A
- Authority
- CN
- China
- Prior art keywords
- air separation
- health degree
- health
- evaluation index
- score
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Landscapes
- Separation By Low-Temperature Treatments (AREA)
Abstract
The invention relates to the technical field of fault diagnosis, and discloses a health degree evaluation method based on air separation equipment. The method establishes a hierarchical health degree quantitative evaluation mechanism, gives out the health degree score according to the percentage system and dynamically displays the score in real time, brings visual health degree display to equipment monitoring personnel, and is more scientific and accurate.
Description
Technical Field
The invention belongs to the technical field of fault diagnosis, and particularly relates to a health degree evaluation method based on an air separation plant.
Background
At present, most of evaluation methods of the health degree of the equipment are completed by establishing a statistical model, the establishment of the statistical model requires obtaining historical fault data of the equipment, however, the historical fault data is often difficult to obtain, and quantitative analysis of the health degree is also difficult to realize by using the statistical model. Particularly for an air separation device, the number of subsystems is large, each subsystem has a plurality of parameters, the value of each parameter can affect the health degree of the whole system, the weight of each parameter on the health degree of the subsystem is different when the parameter is different, and when the parameter approaches an alarm value, the weight occupied by the parameter needs to be enough to affect the health degree of the subsystem so as to affect the health degree of the whole system, so that a traditional statistical model is difficult to give a sufficiently accurate health degree judgment result.
Disclosure of Invention
In view of the above, the health degree evaluation method based on the air separation plant provided by the invention can at least partially solve the problems existing in the prior art, and in order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
the health degree evaluation method of the air separation plant is characterized by comprising the following steps of:
s1, m primary evaluation indexes are established for the air separation equipment to form a primary evaluation index set U-U1,u2,…,umAnd for each primary evaluation index ui(1. ltoreq. i. ltoreq.m) establishing niEach corresponding secondary evaluation index uij(1≤j≤ni) To form a secondary evaluation index set
S2, evaluating index set U ═ U { for the first order1,u2,…,umGiving the corresponding weight vector w ═ w1,w2,…,wm};
S3, obtaining each secondary evaluation index uijAnd calculating the health degree score y of the real-time value through an empirical formulaijAnd weight wij;
S5, calculating the total score of the health degree of the air separation equipmentAnd displaying the total score in real time and giving a final health degree conclusion according to corresponding criteria.
Further, the weight vector w in step S2 is calculated as follows:
s21, giving out an interval number judgment matrix A (a) for pairwise judgment of the primary evaluation indexes according to engineering experienceij)m×mWherein any interval number aij(i is less than or equal to m, j is less than or equal to m) represents a first-level evaluation index uiRelative ujTo an important degree, and
S23, calculating matrix A respectively-And A+Normalized eigenvector lambda corresponding to the largest eigenvalue of-And λ+And calculating the corresponding weight vector w-And w+:w-=αλ-,w+=βλ+Wherein
S24, calculating weight vector w ═ w (w)-+w+)/2。
Further, in step S21, the interval number determination matrix a is (a)ij)m×mThe specific expression form of (A) is as follows: andfollows the reciprocal 1-9 scale rule, andat the same time
Further, in step S3, a trip down value t is defined1Lower alarm value t2Lower limit value t3Optimal lower limit value t4Optimum upper limit value t5Upper limit value t6Reporting the alarm value t7Trip value t8Eight different thresholds and satisfy t1<t2<t3<t4<t5<t6<t7<t8For each secondary evaluation index uijDefining corresponding threshold values and evaluating the index u in two stagesijThe threshold of (c) is divided into two cases:
(1)uijcontains all t1~t8Total 8 values, when the score y is givenijAnd a weight wijThe calculation formulas of (A) and (B) are respectively as follows:
(2)uijincludes t3~t8Total 6 values, when the score y is givenijAnd a weight wijThe calculation formulas of (A) and (B) are respectively as follows:
preferably, the optimum lower limit value t4And an optimum upper limit value t5The calculation formulas of (A) and (B) are respectively as follows:
preferably, the specific rules of the criteria in step S5 are: when the total score is more than 80 and less than or equal to 100, the health degree is concluded as 'healthy'; when the total score is more than 60 and less than or equal to 80, the health degree is concluded as 'attention'; when the total score is more than 40 and less than or equal to 60, the health degree conclusion is 'alarm'; when the total score is 0-40, the health degree is concluded as 'failure'.
Compared with the prior art, the invention has the following obvious advantages:
1. the system complexity of the air separation equipment is fully considered, a hierarchical quantitative evaluation mechanism of the health degree is established, the health degree score is given according to the percentage system and is dynamically displayed in real time, visual health degree display is brought to equipment monitoring personnel, and the evaluation method is more scientific;
2. the interval number judgment matrix of the first-level evaluation index is combined with engineering experience, the second-level index gives scores and corresponding weights in intervals according to threshold values, and the evaluation result is more accurate.
Drawings
FIG. 1 is a flow chart of a computing method of the present invention;
FIG. 2 is a model of a hierarchy of actual air separation plants at a site;
FIG. 3 is t1~t8Score curves of the secondary evaluation indexes when both exist;
FIG. 4 is a view showing onlyt3~t8Score curve chart of the second-level evaluation index.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, embodiments of the present invention will be described in detail below with reference to the accompanying drawings.
The health degree evaluation method of the air separation plant comprises the following steps:
and S1, dividing the operation state of the air separation unit into four levels of 'health', 'caution', 'alarm' and 'fault' according to the management requirements of the operation state of the equipment and by combining actual engineering experience, wherein the four levels are specifically shown in Table 1.
TABLE 1 Total score description of air separation plant
M primary evaluation indexes are established for the air separation plant shown in fig. 2, wherein m is 4, and a primary evaluation index set U is formed as { U ═ U }1,u2,u3,u4And (c) evaluating each first-level evaluation index u, namely { an air compressor system, a supercharger system, an expander system and an oxygen compressor system }, andi(1. ltoreq. i. ltoreq.m) establishing niEach corresponding secondary evaluation index uij(1≤j≤ni) To form a secondary evaluation index setDifferent first-grade evaluation indexes uiNumber n of second-order evaluation indexesiMay be different.
Where n is1=n2=n3=n4Secondary evaluation index u 51={u11,u12,u13,u14,u15J { (vibration of air compressor, bearing temperature of air compressor, winding temperature of motor of air compressor, axial displacement of air compressor, lubricating oil pressure of air compressor }, u ═ vibration of air compressor, bearing temperature of air compressor, motor winding temperature of air compressor, axial displacement of air compressor, lubricating oil pressure of air compressor }, and2={u21,u22,u23,u24,u25vibration of supercharger, bearing temperature of supercharger, superchargerHeat exchanger temperature, booster heat exchanger pressure, booster power }, and so on.
S2, giving out corresponding weight vector w as { w for the first-level evaluation index set U as { air compressor system, supercharger system, expander system, oxygen compressor system }1,w2,w3,w4The specific calculation method is as follows:
s21, providing a range number judgment matrix for pairwise judgment of primary evaluation indexes according to engineering experienceWherein any interval number aij(i is less than or equal to 4, j is less than or equal to 4) represents a first-level evaluation index uiRelative ujTo an important degree, and andthe values of (a) follow the reciprocal 1-9 scale rule, as shown in table 2.
TABLE 2 mutually inverse 1-9 Scale rules
Degree of language description | Grade |
Of equal importance | 1 |
Of slight importance | 3 |
ComparisonOf importance | 5 |
Of strong importance | 7 |
Of extreme importance | 9 |
Intermediate values of two adjacent judgments | 2,4,6,8 |
For example, if the importance of an air compressor system compared to an expander system is considered a13Between "more important" and "strongly important", the linguistic descriptions of the above empirical judgment comparisons can be quantified by looking up table 2, with the result being the number of intervals [5,7]And satisfyAt the same timeI.e. importance of the expander system compared to the air compressor system a31Has interval number of [1/7, 1/5 ]]And finally, a first-level evaluation index interval number judgment matrix is obtained and is shown in table 3.
TABLE 3 determination matrix of number of first-level evaluation index intervals
A | Air compressor system | Supercharger system | Expander system | Oxygen compressor system |
Air compressor system | [1,1] | [2,4] | [5,7] | [7,9] |
Supercharger system | [1/4,1/2] | [1,1] | [4,6] | [5,7] |
Expander system | [1/7,1/5] | [1/6,1/4] | [1,1] | [1,3] |
Oxygen compressor system | [1/9,1/7] | [1/7,1/5] | [1/3,1] | [1,1] |
S22, splitting the interval number judgment matrix A into two judgment matrixes:
s23, calculating matrix A respectively-And A+Normalized eigenvector lambda corresponding to the largest eigenvalue of-And λ+,λ-=[0.568,0.300,0.077,0.055]T,λ+=[0.563,0.294,0.087,0.056]TAnd is and
and calculates the corresponding weight vector w-And w+:w-=αλ-=[0.521,0.275,0.071,0.050]T,w+=βλ+=[0.609,0.318,0.094,0.061]T。
S24, calculating weight vector w ═ w (w)-+w+)/2=[0.565,0.297,0.083,0.056]T。
S3, evaluating each secondary evaluation index uijCalculating the health degree score y thereof by an empirical formulaijAnd weight wijThe parameter of the second level index defines the trip value t1Lower alarm value t2Lower limit value t3Optimal lower limit value t4Optimum upper limit value t5Upper limit value t6Reporting the alarm value t7Trip value t8Eight different thresholds and satisfy t1<t2<t3<t4<t5<t6<t7<t8For each secondary evaluation index uijDefining corresponding threshold values, the homogeneous threshold values of different secondary indexes being independent of each other, the secondary evaluation index uijThe threshold value of (1) is divided into two cases, one case is that all t are contained1~t8A total of 8 values, e.g. shaft displacement, another value comprising t3~t8A total of 6 values, such as vibration. Moreover, the weights corresponding to different index values are different, for example, when the displacement value of the motor shaft of the air compressor exceeds the alarm value, the weight of the index should have a large proportion, so that the weight of the index can be enabled to be differentThe index can affect the health state of the air separation equipment, if the index reaches the trip value, the whole air separation equipment is shut down, the air separation equipment is in a fault state, and the score y is obtainedijAnd a weight wijThe calculation formula (2) is discussed in the following cases:
(1) for threshold t1~t8All exist in the situation
The relationship between the index score and the index value is shown in fig. 3, and is specifically expressed by the formula:
(2) for threshold values only t3~t8In the case of
The relationship between the index score and the index value is shown in fig. 4, and is specifically expressed by the formula:
on-line monitoring data of the air separation plant operating at a certain time of a day are obtained, and the weight and the score of each index parameter are obtained according to a secondary index weight and index score calculation formula, as shown in table 4.
TABLE 4 weight and score of each Secondary index parameter of a device at a time
S4, calculating each primary evaluation index uiIs scored byObtaining the score of the air compressor system: s195.80, turbocharger system score s295.82, expander system score s390.27, oxygen compressor system score s4=92.44。
S5, calculating the total score of the health degree of the air separation equipmentAnd the health degree conclusion is 'healthy' when the total score is more than 80 and less than or equal to 100; when the total score is more than 60 and less than or equal to 80, the health degree is concluded as 'attention'; when the total score is more than 40 and less than or equal to 60, the health degree conclusion is 'alarm'; and when the total score is 0-40, the health degree conclusion is 'fault', so that the total score is displayed in real time and the equipment is judged to be in a 'healthy' state according to the criterion.
Although the embodiments of the present invention have been described above, the contents of the embodiments are only for the convenience of understanding the present invention, and are not intended to limit the present invention. It will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (6)
1. The health degree evaluation method of the air separation plant is characterized by comprising the following steps of:
s1, m primary evaluation indexes are established for the air separation equipment to form a primary evaluation index set U-U1,u2,…,umAnd for each primary evaluation index ui(1. ltoreq. i. ltoreq.m) establishing niEach corresponding secondary evaluation index uij(1≤j≤ni) To form a secondary evaluation index set
S2, evaluating index set U ═ U { for the first order1,u2,…,umGiving the corresponding weight vector w ═ w1,w2,…,wm};
S3, obtaining each secondary evaluation index uijAnd calculating the health degree score y of the real-time value through an empirical formulaijAnd weight wij;
2. The method for evaluating the degree of health of an air separation plant according to claim 1, characterized in that the weight vector w in step S2 is calculated as follows:
s21, giving out an interval number judgment matrix A (a) for pairwise judgment of the primary evaluation indexes according to engineering experienceij)m×mWherein any interval number aij(i is less than or equal to m, j is less than or equal to m) represents a first-level evaluation index uiRelative ujTo an important degree, and
S23, calculating matrix A respectively-And A+Normalized eigenvector lambda corresponding to the largest eigenvalue of-And λ+And calculating the corresponding weight vector w-And w+:w-=αλ-,w+=βλ+Wherein
S24, calculating weight vector w ═ w (w)-+w+)/2。
4. The method for evaluating the health of an air separation plant according to claim 1, wherein in step S3, a trip-down value t is defined1Lower alarm value t2Lower limit value t3Optimal lower limit value t4Optimum upper limit value t5Upper limit value t6Reporting the alarm value t7Trip value t8Eight different thresholds and satisfy t1<t2<t3<t4<t5<t6<t7<t8For each secondary evaluation index uijDefining corresponding threshold value, secondary evaluation index uijThe threshold of (c) is divided into two cases:
(1)uijcontains all t1~t8Total 8 values, when the score y is givenijAnd a weight wijThe calculation formulas of (A) and (B) are respectively as follows:
(2)uijincludes t3~t8Total 6 values, when the score y is givenijAnd a weight wijThe calculation formulas of (A) and (B) are respectively as follows:
6. the method for evaluating the health of an air separation plant according to claim 1, wherein the specific rules of the criterion in the step S5 are: when the total score is more than 80 and less than or equal to 100, the health degree is concluded as 'healthy'; when the total score is more than 60 and less than or equal to 80, the health degree is concluded as 'attention'; when the total score is more than 40 and less than or equal to 60, the health degree conclusion is 'alarm'; when the total score is 0-40, the health degree is concluded as 'failure'.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111645050.1A CN114357644A (en) | 2021-12-30 | 2021-12-30 | Health degree evaluation method based on air separation equipment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111645050.1A CN114357644A (en) | 2021-12-30 | 2021-12-30 | Health degree evaluation method based on air separation equipment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN114357644A true CN114357644A (en) | 2022-04-15 |
Family
ID=81104218
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111645050.1A Pending CN114357644A (en) | 2021-12-30 | 2021-12-30 | Health degree evaluation method based on air separation equipment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114357644A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115511399A (en) * | 2022-11-23 | 2022-12-23 | 昆山斯沃普智能装备有限公司 | Dynamic weight-based power station replacement health state assessment method |
CN116205538A (en) * | 2023-03-15 | 2023-06-02 | 成都地铁运营有限公司 | Rail transit turnout equipment health degree evaluation method |
-
2021
- 2021-12-30 CN CN202111645050.1A patent/CN114357644A/en active Pending
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115511399A (en) * | 2022-11-23 | 2022-12-23 | 昆山斯沃普智能装备有限公司 | Dynamic weight-based power station replacement health state assessment method |
CN116205538A (en) * | 2023-03-15 | 2023-06-02 | 成都地铁运营有限公司 | Rail transit turnout equipment health degree evaluation method |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114357644A (en) | Health degree evaluation method based on air separation equipment | |
CN103150473A (en) | Method and device for monitoring and diagnosing generating efficiency of wind turbine generator in real-time manner | |
CN113779496A (en) | Power equipment state evaluation method and system based on equipment panoramic data | |
CN108009937B (en) | Method for evaluating health state of power distribution main equipment | |
CN113592359B (en) | Method and device for evaluating health degree of power transformer | |
CN106780127A (en) | Evaluation method containing distributed photovoltaic power distribution network | |
Zhu et al. | Failure mode and effect analysis: A three-way decision approach | |
CN107220498A (en) | A kind of mechanical material evaluation method and its system | |
CN108305014A (en) | A kind of failure model and effect analysis method based on reliability room and Rough Ideals point method | |
CN114936758A (en) | Health state evaluation method and device for wind turbine generator and electronic equipment | |
CN109144986A (en) | A kind of importance appraisal procedure of industrial equipment data | |
CN115187013A (en) | Lithium battery performance scoring calculation method and system | |
CN113240263A (en) | Comprehensive energy system planning combination evaluation method based on entropy weight fuzzy | |
CN114169718A (en) | Method for improving reliability of wind turbine generator based on state evaluation of wind turbine generator | |
CN106126949A (en) | A kind of steam turbine generator running status appraisal procedure | |
CN111536639B (en) | Water chilling unit operation optimization control method based on Lagrange multiplier method | |
CN112182730A (en) | Industrial building legacy value comprehensive evaluation method based on analytic hierarchy process | |
CN111563685A (en) | Power generation equipment state early warning method based on auto-associative kernel regression algorithm | |
CN113537738B (en) | Aviation emergency rescue efficiency evaluation method integrating multiple cycles and multiple constraints | |
CN110289112A (en) | Nuclear power unit health status diagnostic method based on step analysis and fuzzy evaluation | |
CN111667568B (en) | Variable information board information release effect evaluation method based on driving simulation technology | |
CN111159641B (en) | Power grid comprehensive difficulty risk assessment method | |
CN114332515A (en) | Online evaluation method for operation safety of coal mill based on intuition fuzzy clustering | |
CN114418412B (en) | Operation and maintenance health evaluation method for power plant equipment of cigarette factory | |
CN113627705A (en) | Safety city evaluation system and 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 |